Compare commits
No commits in common. "main" and "asch/simplify" have entirely different histories.
main
...
asch/simpl
146 changed files with 1887 additions and 20879 deletions
14
.editorconfig
Normal file
14
.editorconfig
Normal file
|
|
@ -0,0 +1,14 @@
|
||||||
|
# https://editorconfig.org
|
||||||
|
|
||||||
|
root = true
|
||||||
|
|
||||||
|
[*]
|
||||||
|
end_of_line = lf
|
||||||
|
insert_final_newline = true
|
||||||
|
trim_trailing_whitespace = true
|
||||||
|
charset = utf-8
|
||||||
|
indent_style = space
|
||||||
|
indent_size = 4
|
||||||
|
|
||||||
|
[*.{yml,yaml}]
|
||||||
|
indent_size = 2
|
||||||
|
|
@ -1,74 +0,0 @@
|
||||||
name: Check
|
|
||||||
|
|
||||||
on:
|
|
||||||
push:
|
|
||||||
branches: ['main']
|
|
||||||
pull_request:
|
|
||||||
branches: ['main']
|
|
||||||
|
|
||||||
env:
|
|
||||||
CARGO_TERM_COLOR: always
|
|
||||||
RUSTFLAGS: '-Dwarnings'
|
|
||||||
|
|
||||||
jobs:
|
|
||||||
build:
|
|
||||||
runs-on: docker
|
|
||||||
|
|
||||||
steps:
|
|
||||||
- uses: actions/checkout@v4
|
|
||||||
|
|
||||||
- name: Setup Node
|
|
||||||
uses: actions/setup-node@v4
|
|
||||||
with:
|
|
||||||
node-version: '22.x'
|
|
||||||
check-latest: true
|
|
||||||
|
|
||||||
- name: Cache Rust dependencies
|
|
||||||
uses: actions/cache@v4
|
|
||||||
with:
|
|
||||||
path: |
|
|
||||||
~/.cargo/bin/
|
|
||||||
~/.cargo/registry/index/
|
|
||||||
~/.cargo/registry/cache/
|
|
||||||
~/.cargo/git/db/
|
|
||||||
target/
|
|
||||||
key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
|
|
||||||
restore-keys: |
|
|
||||||
${{ runner.os }}-cargo-
|
|
||||||
|
|
||||||
- name: Cache npm dependencies
|
|
||||||
uses: actions/cache@v4
|
|
||||||
with:
|
|
||||||
path: |
|
|
||||||
reconcile-js/node_modules
|
|
||||||
examples/website/node_modules
|
|
||||||
~/.npm
|
|
||||||
key: >-
|
|
||||||
${{ runner.os }}-npm-${{
|
|
||||||
hashFiles(
|
|
||||||
'reconcile-js/package-lock.json',
|
|
||||||
'examples/website/package-lock.json'
|
|
||||||
)
|
|
||||||
}}
|
|
||||||
restore-keys: |
|
|
||||||
${{ runner.os }}-npm-
|
|
||||||
|
|
||||||
- name: Install Rust toolchain
|
|
||||||
run: |
|
|
||||||
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \
|
|
||||||
| sh -s -- -y --default-toolchain none --profile minimal
|
|
||||||
echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
|
|
||||||
|
|
||||||
- name: Install uv
|
|
||||||
run: |
|
|
||||||
curl --proto '=https' --tlsv1.2 -LsSf https://astral.sh/uv/install.sh | sh
|
|
||||||
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
|
|
||||||
|
|
||||||
- name: Lint
|
|
||||||
run: scripts/lint.sh
|
|
||||||
|
|
||||||
- name: Test
|
|
||||||
run: scripts/test.sh
|
|
||||||
|
|
||||||
- name: Build website
|
|
||||||
run: scripts/build-website.sh
|
|
||||||
|
|
@ -1,265 +0,0 @@
|
||||||
name: Publish
|
|
||||||
|
|
||||||
on:
|
|
||||||
push:
|
|
||||||
branches: ['main']
|
|
||||||
tags: ['*']
|
|
||||||
workflow_dispatch:
|
|
||||||
|
|
||||||
env:
|
|
||||||
CARGO_TERM_COLOR: always
|
|
||||||
RUSTFLAGS: '-Dwarnings'
|
|
||||||
|
|
||||||
concurrency:
|
|
||||||
group: 'pages'
|
|
||||||
cancel-in-progress: false
|
|
||||||
|
|
||||||
jobs:
|
|
||||||
build:
|
|
||||||
runs-on: docker
|
|
||||||
|
|
||||||
steps:
|
|
||||||
- uses: actions/checkout@v4
|
|
||||||
|
|
||||||
- name: Setup Node
|
|
||||||
uses: actions/setup-node@v4
|
|
||||||
with:
|
|
||||||
node-version: '22.x'
|
|
||||||
check-latest: true
|
|
||||||
|
|
||||||
- name: Cache Rust dependencies
|
|
||||||
uses: actions/cache@v4
|
|
||||||
with:
|
|
||||||
path: |
|
|
||||||
~/.cargo/bin/
|
|
||||||
~/.cargo/registry/index/
|
|
||||||
~/.cargo/registry/cache/
|
|
||||||
~/.cargo/git/db/
|
|
||||||
target/
|
|
||||||
key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
|
|
||||||
restore-keys: |
|
|
||||||
${{ runner.os }}-cargo-
|
|
||||||
|
|
||||||
- name: Cache npm dependencies
|
|
||||||
uses: actions/cache@v4
|
|
||||||
with:
|
|
||||||
path: |
|
|
||||||
reconcile-js/node_modules
|
|
||||||
examples/website/node_modules
|
|
||||||
~/.npm
|
|
||||||
key: >-
|
|
||||||
${{ runner.os }}-npm-${{
|
|
||||||
hashFiles(
|
|
||||||
'reconcile-js/package-lock.json',
|
|
||||||
'examples/website/package-lock.json'
|
|
||||||
)
|
|
||||||
}}
|
|
||||||
restore-keys: |
|
|
||||||
${{ runner.os }}-npm-
|
|
||||||
|
|
||||||
- name: Install Rust toolchain
|
|
||||||
run: |
|
|
||||||
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \
|
|
||||||
| sh -s -- -y --default-toolchain none --profile minimal
|
|
||||||
echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
|
|
||||||
|
|
||||||
- name: Install uv
|
|
||||||
run: |
|
|
||||||
curl --proto '=https' --tlsv1.2 -LsSf https://astral.sh/uv/install.sh | sh
|
|
||||||
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
|
|
||||||
|
|
||||||
- name: Lint
|
|
||||||
run: scripts/lint.sh
|
|
||||||
|
|
||||||
- name: Test
|
|
||||||
run: scripts/test.sh
|
|
||||||
|
|
||||||
- name: Build website
|
|
||||||
run: scripts/build-website.sh
|
|
||||||
|
|
||||||
- name: Deploy to pages mount
|
|
||||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
|
||||||
run: |
|
|
||||||
apt-get update && apt-get install -y rsync
|
|
||||||
rsync -a --delete examples/website/dist/ /pages/reconcile
|
|
||||||
|
|
||||||
publish-crate:
|
|
||||||
needs: build
|
|
||||||
runs-on: docker
|
|
||||||
if: startsWith(github.ref, 'refs/tags/')
|
|
||||||
|
|
||||||
steps:
|
|
||||||
- uses: actions/checkout@v4
|
|
||||||
|
|
||||||
- name: Cache Rust dependencies
|
|
||||||
uses: actions/cache@v4
|
|
||||||
with:
|
|
||||||
path: |
|
|
||||||
~/.cargo/bin/
|
|
||||||
~/.cargo/registry/index/
|
|
||||||
~/.cargo/registry/cache/
|
|
||||||
~/.cargo/git/db/
|
|
||||||
target/
|
|
||||||
key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
|
|
||||||
restore-keys: |
|
|
||||||
${{ runner.os }}-cargo-
|
|
||||||
|
|
||||||
- name: Install Rust toolchain
|
|
||||||
run: |
|
|
||||||
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \
|
|
||||||
| sh -s -- -y --default-toolchain none --profile minimal
|
|
||||||
echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
|
|
||||||
|
|
||||||
- name: Publish to crates.io
|
|
||||||
run: cargo publish --token ${{ secrets.CRATES_IO_TOKEN }}
|
|
||||||
|
|
||||||
publish-npm:
|
|
||||||
needs: build
|
|
||||||
runs-on: docker
|
|
||||||
if: startsWith(github.ref, 'refs/tags/')
|
|
||||||
|
|
||||||
steps:
|
|
||||||
- uses: actions/checkout@v4
|
|
||||||
|
|
||||||
- name: Setup Node
|
|
||||||
uses: actions/setup-node@v4
|
|
||||||
with:
|
|
||||||
node-version: '22.x'
|
|
||||||
check-latest: true
|
|
||||||
registry-url: 'https://registry.npmjs.org'
|
|
||||||
|
|
||||||
- name: Cache Rust dependencies
|
|
||||||
uses: actions/cache@v4
|
|
||||||
with:
|
|
||||||
path: |
|
|
||||||
~/.cargo/bin/
|
|
||||||
~/.cargo/registry/index/
|
|
||||||
~/.cargo/registry/cache/
|
|
||||||
~/.cargo/git/db/
|
|
||||||
target/
|
|
||||||
key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
|
|
||||||
restore-keys: |
|
|
||||||
${{ runner.os }}-cargo-
|
|
||||||
|
|
||||||
- name: Cache npm dependencies
|
|
||||||
uses: actions/cache@v4
|
|
||||||
with:
|
|
||||||
path: |
|
|
||||||
reconcile-js/node_modules
|
|
||||||
~/.npm
|
|
||||||
key: >-
|
|
||||||
${{ runner.os }}-npm-${{
|
|
||||||
hashFiles('reconcile-js/package-lock.json')
|
|
||||||
}}
|
|
||||||
restore-keys: |
|
|
||||||
${{ runner.os }}-npm-
|
|
||||||
|
|
||||||
- name: Install Rust toolchain
|
|
||||||
run: |
|
|
||||||
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \
|
|
||||||
| sh -s -- -y --default-toolchain none --profile minimal
|
|
||||||
echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
|
|
||||||
|
|
||||||
- name: Build website
|
|
||||||
run: scripts/build-website.sh
|
|
||||||
|
|
||||||
- name: Publish reconcile-js to NPM
|
|
||||||
run: |
|
|
||||||
cd reconcile-js
|
|
||||||
cp ../README.md .
|
|
||||||
npm publish
|
|
||||||
env:
|
|
||||||
NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
|
|
||||||
|
|
||||||
publish-pypi:
|
|
||||||
needs: build
|
|
||||||
runs-on: docker
|
|
||||||
if: startsWith(github.ref, 'refs/tags/')
|
|
||||||
|
|
||||||
steps:
|
|
||||||
- uses: actions/checkout@v4
|
|
||||||
|
|
||||||
- name: Cache Rust dependencies
|
|
||||||
uses: actions/cache@v4
|
|
||||||
with:
|
|
||||||
path: |
|
|
||||||
~/.cargo/bin/
|
|
||||||
~/.cargo/registry/index/
|
|
||||||
~/.cargo/registry/cache/
|
|
||||||
~/.cargo/git/db/
|
|
||||||
target/
|
|
||||||
key: ${{ runner.os }}-cargo-pypi-${{ hashFiles('**/Cargo.lock') }}
|
|
||||||
restore-keys: |
|
|
||||||
${{ runner.os }}-cargo-pypi-
|
|
||||||
${{ runner.os }}-cargo-
|
|
||||||
|
|
||||||
# clang/lld/llvm provide clang-cl, lld-link and llvm-lib, which cargo-xwin
|
|
||||||
# uses to cross-compile the Windows wheel from this Linux runner.
|
|
||||||
- name: Install cross-compilation system dependencies
|
|
||||||
run: |
|
|
||||||
apt-get update
|
|
||||||
apt-get install -y clang lld llvm
|
|
||||||
|
|
||||||
- name: Install Rust toolchain
|
|
||||||
run: |
|
|
||||||
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \
|
|
||||||
| sh -s -- -y --default-toolchain none --profile minimal
|
|
||||||
echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
|
|
||||||
|
|
||||||
# The Linux targets ship in rust-toolchain.toml; add the cross targets.
|
|
||||||
- name: Add cross-compilation Rust targets
|
|
||||||
run: |
|
|
||||||
rustup target add aarch64-unknown-linux-gnu x86_64-pc-windows-msvc
|
|
||||||
|
|
||||||
# zig is the C toolchain maturin's `--zig` uses to produce manylinux2014
|
|
||||||
# wheels with a pinned (old) glibc, independent of the runner's glibc.
|
|
||||||
- name: Install zig
|
|
||||||
run: |
|
|
||||||
ZIG_VERSION=0.13.0
|
|
||||||
curl --proto '=https' --tlsv1.2 -fLsS \
|
|
||||||
"https://ziglang.org/download/${ZIG_VERSION}/zig-linux-x86_64-${ZIG_VERSION}.tar.xz" \
|
|
||||||
| tar -xJ
|
|
||||||
echo "$PWD/zig-linux-x86_64-${ZIG_VERSION}" >> "$GITHUB_PATH"
|
|
||||||
|
|
||||||
- name: Install cargo-xwin
|
|
||||||
run: command -v cargo-xwin || cargo install --locked cargo-xwin
|
|
||||||
|
|
||||||
- name: Install uv
|
|
||||||
run: |
|
|
||||||
curl --proto '=https' --tlsv1.2 -LsSf https://astral.sh/uv/install.sh | sh
|
|
||||||
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
|
|
||||||
|
|
||||||
- name: Copy README
|
|
||||||
run: cp README.md reconcile-python/
|
|
||||||
|
|
||||||
- name: Build sdist
|
|
||||||
working-directory: reconcile-python
|
|
||||||
run: uv run maturin sdist --out dist
|
|
||||||
|
|
||||||
- name: Build Linux x86_64 wheel
|
|
||||||
working-directory: reconcile-python
|
|
||||||
run: >-
|
|
||||||
uv run maturin build --release --out dist
|
|
||||||
--compatibility manylinux2014
|
|
||||||
--target x86_64-unknown-linux-gnu --zig
|
|
||||||
|
|
||||||
- name: Build Linux aarch64 wheel
|
|
||||||
working-directory: reconcile-python
|
|
||||||
run: >-
|
|
||||||
uv run maturin build --release --out dist
|
|
||||||
--compatibility manylinux2014
|
|
||||||
--target aarch64-unknown-linux-gnu --zig
|
|
||||||
|
|
||||||
- name: Build Windows x86_64 wheel
|
|
||||||
working-directory: reconcile-python
|
|
||||||
run: >-
|
|
||||||
uv run maturin build --release --out dist
|
|
||||||
--target x86_64-pc-windows-msvc
|
|
||||||
|
|
||||||
# Forgejo cannot use PyPI trusted publishing (OIDC), so authenticate with
|
|
||||||
# an API token. --skip-existing makes re-runs of a tag idempotent.
|
|
||||||
- name: Publish to PyPI
|
|
||||||
working-directory: reconcile-python
|
|
||||||
env:
|
|
||||||
MATURIN_PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
|
||||||
run: uv run maturin upload --skip-existing dist/*
|
|
||||||
16
.github/dependabot.yml
vendored
Normal file
16
.github/dependabot.yml
vendored
Normal file
|
|
@ -0,0 +1,16 @@
|
||||||
|
# To get started with Dependabot version updates, you'll need to specify which
|
||||||
|
# package ecosystems to update and where the package manifests are located.
|
||||||
|
# Please see the documentation for all configuration options:
|
||||||
|
# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
|
||||||
|
|
||||||
|
version: 2
|
||||||
|
updates:
|
||||||
|
- package-ecosystem: "cargo"
|
||||||
|
directories: ["**"]
|
||||||
|
schedule:
|
||||||
|
interval: "daily"
|
||||||
|
|
||||||
|
- package-ecosystem: "github-actions"
|
||||||
|
directories: ["**"]
|
||||||
|
schedule:
|
||||||
|
interval: "daily"
|
||||||
43
.github/workflows/check.yml
vendored
Normal file
43
.github/workflows/check.yml
vendored
Normal file
|
|
@ -0,0 +1,43 @@
|
||||||
|
name: Check
|
||||||
|
|
||||||
|
on:
|
||||||
|
push:
|
||||||
|
branches: ["main"]
|
||||||
|
pull_request:
|
||||||
|
branches: ["main"]
|
||||||
|
|
||||||
|
env:
|
||||||
|
CARGO_TERM_COLOR: always
|
||||||
|
RUSTFLAGS: "-Dwarnings"
|
||||||
|
|
||||||
|
jobs:
|
||||||
|
build:
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
|
||||||
|
- name: Setup Node.js environment
|
||||||
|
uses: actions/setup-node@v4.2.0
|
||||||
|
with:
|
||||||
|
node-version: "22.x"
|
||||||
|
check-latest: true
|
||||||
|
|
||||||
|
- name: Setup rust
|
||||||
|
run: |
|
||||||
|
cargo install wasm-pack cargo-machete
|
||||||
|
|
||||||
|
- name: Build wasm
|
||||||
|
run: |
|
||||||
|
wasm-pack build --target web --features wasm
|
||||||
|
|
||||||
|
- name: Lint
|
||||||
|
run: |
|
||||||
|
cargo clippy --all-targets --all-features
|
||||||
|
cargo fmt --all -- --check
|
||||||
|
cargo machete
|
||||||
|
|
||||||
|
- name: Test
|
||||||
|
run: |
|
||||||
|
cargo test --verbose -- --include-ignored
|
||||||
|
wasm-pack test --node --features wasm
|
||||||
51
.github/workflows/gh-pages.yml
vendored
Normal file
51
.github/workflows/gh-pages.yml
vendored
Normal file
|
|
@ -0,0 +1,51 @@
|
||||||
|
name: Deploy Website to GitHub Pages
|
||||||
|
|
||||||
|
on:
|
||||||
|
push:
|
||||||
|
branches:
|
||||||
|
- main
|
||||||
|
workflow_dispatch:
|
||||||
|
|
||||||
|
# Sets permissions of the GITHUB_TOKEN to allow deployment to GitHub Pages
|
||||||
|
permissions:
|
||||||
|
contents: read
|
||||||
|
pages: write
|
||||||
|
id-token: write
|
||||||
|
|
||||||
|
# Allow only one concurrent deployment, skipping runs queued between the run in-progress and latest queued.
|
||||||
|
# However, do NOT cancel in-progress runs as we want to allow these production deployments to complete.
|
||||||
|
concurrency:
|
||||||
|
group: "pages"
|
||||||
|
cancel-in-progress: false
|
||||||
|
|
||||||
|
jobs:
|
||||||
|
build:
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
permissions:
|
||||||
|
contents: write
|
||||||
|
steps:
|
||||||
|
- name: Checkout repository
|
||||||
|
uses: actions/checkout@v4
|
||||||
|
|
||||||
|
- name: Build wasm
|
||||||
|
run: |
|
||||||
|
cargo install wasm-pack
|
||||||
|
wasm-pack build --target web --features wasm
|
||||||
|
cp -R pkg/reconcile.js examples/website/
|
||||||
|
cp -R pkg/reconcile_bg.wasm examples/website/
|
||||||
|
|
||||||
|
- name: Upload artifact
|
||||||
|
uses: actions/upload-pages-artifact@v3
|
||||||
|
with:
|
||||||
|
path: examples/website
|
||||||
|
|
||||||
|
deploy:
|
||||||
|
environment:
|
||||||
|
name: github-pages
|
||||||
|
url: ${{ steps.deployment.outputs.page_url }}
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
needs: build
|
||||||
|
steps:
|
||||||
|
- name: Deploy to GitHub Pages
|
||||||
|
id: deployment
|
||||||
|
uses: actions/deploy-pages@v4
|
||||||
12
.gitignore
vendored
12
.gitignore
vendored
|
|
@ -3,15 +3,3 @@
|
||||||
|
|
||||||
# Rust build folder
|
# Rust build folder
|
||||||
target
|
target
|
||||||
|
|
||||||
# Node dependencies
|
|
||||||
node_modules
|
|
||||||
|
|
||||||
# WebPack build output
|
|
||||||
dist
|
|
||||||
|
|
||||||
# Generated wasm-bindgen bundler + wasm2js output for the React Native build
|
|
||||||
pkg-rn
|
|
||||||
|
|
||||||
# Python virtual environment
|
|
||||||
.venv
|
|
||||||
|
|
|
||||||
|
|
@ -1,7 +0,0 @@
|
||||||
{
|
|
||||||
"trailingComma": "es5",
|
|
||||||
"printWidth": 90,
|
|
||||||
"tabWidth": 2,
|
|
||||||
"singleQuote": true,
|
|
||||||
"endOfLine": "lf"
|
|
||||||
}
|
|
||||||
21
.vscode/settings.json
vendored
21
.vscode/settings.json
vendored
|
|
@ -1,15 +1,10 @@
|
||||||
{
|
{
|
||||||
|
"jest.jestCommandLine": "NODE_OPTIONS=\"$NODE_OPTIONS --experimental-vm-modules\" npx jest",
|
||||||
|
"jest.rootPath": "plugin",
|
||||||
"files.exclude": {
|
"files.exclude": {
|
||||||
"**/snapshots": true, // cargo-insta outputs
|
"**/dist": true,
|
||||||
"**/node_modules": true, // node.js dependencies
|
"**/node_modules": true,
|
||||||
"**/dist": true, // webpack build directory
|
"**/.sqlx": true,
|
||||||
"pkg": true, // wasm-pack build directory
|
"**/snapshots": true,
|
||||||
"target": true, // rust build directory
|
}
|
||||||
},
|
}
|
||||||
"rust-analyzer.cargo.features": [
|
|
||||||
"all"
|
|
||||||
],
|
|
||||||
"python.analysis.extraPaths": [
|
|
||||||
"./reconcile-python/python"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
|
|
|
||||||
758
Cargo.lock
generated
758
Cargo.lock
generated
File diff suppressed because it is too large
Load diff
51
Cargo.toml
51
Cargo.toml
|
|
@ -1,34 +1,19 @@
|
||||||
[package]
|
[package]
|
||||||
name = "reconcile-text"
|
name = "reconcile"
|
||||||
description = "Intelligent 3-way text merging with automated conflict resolution"
|
rust-version = "1.85"
|
||||||
version = "0.12.1"
|
|
||||||
rust-version = "1.94"
|
|
||||||
authors = ["Andras Schmelczer <andras@schmelczer.dev>"]
|
authors = ["Andras Schmelczer <andras@schmelczer.dev>"]
|
||||||
edition = "2024"
|
edition = "2024"
|
||||||
license = "MIT"
|
license = "MIT"
|
||||||
readme = "README.md"
|
|
||||||
repository = "https://github.com/schmelczer/reconcile"
|
repository = "https://github.com/schmelczer/reconcile"
|
||||||
homepage = "https://schmelczer.dev/reconcile"
|
version = "0.4.0"
|
||||||
keywords = ["merge", "OT", "CRDT", "3-way", "diff"]
|
|
||||||
categories = ["wasm", "text-processing", "text-editors", "algorithms", "data-structures"]
|
|
||||||
exclude = ["reconcile-js", "reconcile-python", ".*", "examples/website"]
|
|
||||||
|
|
||||||
[lib]
|
[lib]
|
||||||
crate-type = ["cdylib", "rlib"]
|
crate-type = ["cdylib", "rlib"]
|
||||||
|
|
||||||
[[example]]
|
|
||||||
name = "merge-file"
|
|
||||||
path = "examples/merge-file.rs"
|
|
||||||
|
|
||||||
[[example]]
|
|
||||||
name = "compare-with-diff-match-patch"
|
|
||||||
path = "examples/compare-with-diff-match-patch.rs"
|
|
||||||
|
|
||||||
[dependencies]
|
[dependencies]
|
||||||
serde = { version = "1.0.228", optional = true, features = ["derive"] }
|
serde = { version = "1.0.219", optional = true, features = ["derive"] }
|
||||||
thiserror = "2.0.18"
|
|
||||||
|
|
||||||
wasm-bindgen = { version = "0.2.114", optional = true }
|
wasm-bindgen = { version = "0.2.99", optional = true }
|
||||||
|
|
||||||
# The `console_error_panic_hook` crate provides better debugging of panics by
|
# The `console_error_panic_hook` crate provides better debugging of panics by
|
||||||
# logging them with `console.error`. This is great for development, but requires
|
# logging them with `console.error`. This is great for development, but requires
|
||||||
|
|
@ -39,27 +24,22 @@ console_error_panic_hook = { version = "0.1.7", optional = true }
|
||||||
[features]
|
[features]
|
||||||
default = []
|
default = []
|
||||||
serde = [ "dep:serde" ]
|
serde = [ "dep:serde" ]
|
||||||
wasm = [ "dep:wasm-bindgen", "console_error_panic_hook" ]
|
wasm = [ "dep:wasm-bindgen"]
|
||||||
console_error_panic_hook = [ "dep:console_error_panic_hook" ]
|
console_error_panic_hook = [ "dep:console_error_panic_hook" ]
|
||||||
all = [ "wasm", "serde" ]
|
|
||||||
|
|
||||||
[dev-dependencies]
|
[dev-dependencies]
|
||||||
insta = "1.46.3"
|
insta = "1.42.2"
|
||||||
pretty_assertions = "1.4.1"
|
pretty_assertions = "1.4.1"
|
||||||
serde = { version = "1.0.228", features = ["derive"] }
|
serde = { version = "1.0.219", features = ["derive"] }
|
||||||
serde_yaml = "0.9.34"
|
serde_yaml ="0.9.34"
|
||||||
test-case = "3.3.1"
|
test-case = "3.3.1"
|
||||||
wasm-bindgen-test = "0.3.64"
|
wasm-bindgen-test = "0.3.49"
|
||||||
diff-match-patch-rs = "0.5.1"
|
|
||||||
|
|
||||||
[profile.release]
|
[profile.release]
|
||||||
codegen-units = 1
|
codegen-units = 1
|
||||||
lto = true
|
lto = true
|
||||||
opt-level = 3
|
opt-level = 3
|
||||||
strip = "symbols"
|
strip="debuginfo" # Keep some info for better panics
|
||||||
|
|
||||||
[package.metadata.wasm-pack.profile.release]
|
|
||||||
wasm-opt = ['-O4', '--enable-bulk-memory', '--enable-nontrapping-float-to-int']
|
|
||||||
|
|
||||||
[lints.rust]
|
[lints.rust]
|
||||||
unsafe_code = "forbid"
|
unsafe_code = "forbid"
|
||||||
|
|
@ -69,7 +49,7 @@ missing_debug_implementations = "warn"
|
||||||
[lints.clippy]
|
[lints.clippy]
|
||||||
await_holding_lock = "warn"
|
await_holding_lock = "warn"
|
||||||
dbg_macro = "warn"
|
dbg_macro = "warn"
|
||||||
empty_enums = "warn"
|
empty_enum = "warn"
|
||||||
enum_glob_use = "warn"
|
enum_glob_use = "warn"
|
||||||
exit = "warn"
|
exit = "warn"
|
||||||
filter_map_next = "warn"
|
filter_map_next = "warn"
|
||||||
|
|
@ -96,9 +76,14 @@ verbose_file_reads = "warn"
|
||||||
|
|
||||||
large_stack_arrays = { level = "allow", priority = 1 } # https://github.com/rust-lang/rust-clippy/issues/13774
|
large_stack_arrays = { level = "allow", priority = 1 } # https://github.com/rust-lang/rust-clippy/issues/13774
|
||||||
|
|
||||||
|
# TODO: fix these
|
||||||
|
cast_possible_truncation = { level = "allow", priority = 1 }
|
||||||
|
cast_sign_loss = { level = "allow", priority = 1 }
|
||||||
|
cast_possible_wrap = { level = "allow", priority = 1 }
|
||||||
|
|
||||||
# Silly lints
|
# Silly lints
|
||||||
implicit_return = { level = "allow", priority = 1 }
|
implicit_return = { level = "allow", priority = 1 }
|
||||||
question_mark_used = { level = "allow", priority = 1 }
|
question_mark_used = { level = "allow", priority = 1 }
|
||||||
struct_field_names = { level = "allow", priority = 1 }
|
struct_field_names = { level = "allow", priority = 1 }
|
||||||
single_char_lifetime_names = { level = "allow", priority = 1 }
|
single_char_lifetime_names = { level = "allow", priority = 1 }
|
||||||
single_call_fn = { level = "allow", priority = 1 }
|
single_call_fn = { level = "allow", priority = 1 }
|
||||||
|
|
|
||||||
21
LICENSE
21
LICENSE
|
|
@ -1,21 +0,0 @@
|
||||||
MIT License
|
|
||||||
|
|
||||||
Copyright (c) 2025 András Schmelczer
|
|
||||||
|
|
||||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
||||||
of this software and associated documentation files (the "Software"), to deal
|
|
||||||
in the Software without restriction, including without limitation the rights
|
|
||||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
||||||
copies of the Software, and to permit persons to whom the Software is
|
|
||||||
furnished to do so, subject to the following conditions:
|
|
||||||
|
|
||||||
The above copyright notice and this permission notice shall be included in all
|
|
||||||
copies or substantial portions of the Software.
|
|
||||||
|
|
||||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
||||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
||||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
||||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
||||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
||||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
||||||
SOFTWARE.
|
|
||||||
278
README.md
278
README.md
|
|
@ -1,256 +1,54 @@
|
||||||
# `reconcile-text`: conflict-free 3-way text merging
|
# VaultLink self-hosted Obsidian plugin for file syncing
|
||||||
|
|
||||||
A Rust, TypeScript, and Python library for merging conflicting text edits without manual intervention. Unlike traditional 3-way merge tools that produce conflict markers, `reconcile-text` automatically resolves conflicts by applying both sets of changes (while updating cursor positions) using an algorithm inspired by Operational Transformation.
|
[](https://github.com/schmelczer/reconcile/actions/workflows/check.yml)
|
||||||
|
[](https://github.com/schmelczer/reconcile/actions/workflows/gh-pages.yml)
|
||||||
|
|
||||||
## Try it
|
## Develop
|
||||||
|
|
||||||
✨ **[Try the interactive demo][8]** to see it in action!
|
### Install [nvm](https://github.com/nvm-sh/nvm)
|
||||||
|
|
||||||
### Install it in your project
|
- `curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash`
|
||||||
|
- `nvm install 22`
|
||||||
|
- `nvm use 22`
|
||||||
|
- Optionally set the system-wide default: `nvm alias default 22`
|
||||||
|
|
||||||
- `cargo add reconcile-text` ([reconcile-text on crates.io][9])
|
### Set up Rust
|
||||||
- `npm install reconcile-text` ([reconcile-text on NPM][10])
|
|
||||||
- `uv add reconcile-text` or `pip install reconcile-text` ([reconcile-text on PyPI][27])
|
|
||||||
|
|
||||||
## Key features
|
- Install [`rustup`](https://rustup.rs): `curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh`
|
||||||
|
- Install [`wasm-pack`](https://rustwasm.github.io/wasm-pack/installer): `curl https://rustwasm.github.io/wasm-pack/installer/init.sh -sSf | sh`
|
||||||
|
- `cargo install cargo-insta sqlx-cli cargo-edit`
|
||||||
|
|
||||||
- **No conflict markers** - Clean, merged output without Git's `<<<<<<<` markers
|
### Install Obsidian on Linux
|
||||||
- **Cursor tracking** - Automatically repositions cursors and selections throughout the merging process
|
|
||||||
- **Flexible tokenisation** - Word-level (default), character-level, line-level, or custom tokenisation strategies
|
|
||||||
- **Unicode support** - Full UTF-8 support with proper handling of complex scripts and grapheme clusters
|
|
||||||
- **Cross-platform** - Native Rust performance with WebAssembly bindings for JavaScript and native bindings for Python
|
|
||||||
|
|
||||||
## Quick start
|
|
||||||
|
|
||||||
### Rust
|
|
||||||
|
|
||||||
Install via crates.io:
|
|
||||||
|
|
||||||
```sh
|
```sh
|
||||||
cargo add reconcile-text
|
apt install flatpak
|
||||||
|
flatpak remote-add --if-not-exists flathub https://dl.flathub.org/repo/flathub.flatpakrepo
|
||||||
|
flatpak install flathub md.obsidian.Obsidian
|
||||||
|
flatpak run md.obsidian.Obsidian
|
||||||
```
|
```
|
||||||
|
|
||||||
Alternatively, add `reconcile-text` to your `Cargo.toml`:
|
|
||||||
|
|
||||||
```toml
|
|
||||||
[dependencies]
|
|
||||||
reconcile-text = "0.8"
|
|
||||||
```
|
|
||||||
|
|
||||||
Then start merging:
|
|
||||||
|
|
||||||
```rust
|
|
||||||
use reconcile_text::{reconcile, BuiltinTokenizer};
|
|
||||||
|
|
||||||
// Start with the original text
|
|
||||||
let parent = "Hello world";
|
|
||||||
// Two users edit simultaneously
|
|
||||||
let left = "Hello beautiful world"; // Added "beautiful"
|
|
||||||
let right = "Hi world"; // Changed "Hello" to "Hi"
|
|
||||||
|
|
||||||
// Reconcile combines both changes
|
|
||||||
let result = reconcile(parent, &left.into(), &right.into(), &*BuiltinTokenizer::Word);
|
|
||||||
assert_eq!(result.apply().text(), "Hi beautiful world");
|
|
||||||
```
|
|
||||||
|
|
||||||
See the [merge-file example](examples/merge-file.rs) for another example, or the [library's documentation][11].
|
|
||||||
|
|
||||||
### JavaScript/TypeScript
|
|
||||||
|
|
||||||
Install via NPM:
|
|
||||||
|
|
||||||
```sh
|
|
||||||
npm install reconcile-text
|
|
||||||
```
|
|
||||||
|
|
||||||
Then use it in your application:
|
|
||||||
|
|
||||||
```javascript
|
|
||||||
import { reconcile } from 'reconcile-text';
|
|
||||||
|
|
||||||
// Start with the original text
|
|
||||||
const parent = 'Hello world';
|
|
||||||
// Two users edit simultaneously
|
|
||||||
const left = 'Hello beautiful world';
|
|
||||||
const right = 'Hi world';
|
|
||||||
|
|
||||||
const result = reconcile(parent, left, right);
|
|
||||||
console.log(result.text); // "Hi beautiful world"
|
|
||||||
```
|
|
||||||
|
|
||||||
See the [example website source](examples/website/src/index.ts) for a more complex example, or the [advanced examples document](docs/advanced-ts.md).
|
|
||||||
|
|
||||||
#### React Native (Hermes)
|
|
||||||
|
|
||||||
React Native's default engine, Hermes, does not expose a runtime `WebAssembly`
|
|
||||||
global, so the WebAssembly build cannot run there. For React Native, the package
|
|
||||||
ships a pure-JavaScript build produced by [Binaryen's `wasm2js`](https://github.com/WebAssembly/binaryen)
|
|
||||||
via its `react-native` entry point.
|
|
||||||
|
|
||||||
### Python
|
|
||||||
|
|
||||||
Install via uv or pip:
|
|
||||||
|
|
||||||
```sh
|
|
||||||
uv add reconcile-text
|
|
||||||
# or: pip install reconcile-text
|
|
||||||
```
|
|
||||||
|
|
||||||
Then use it in your application:
|
|
||||||
|
|
||||||
```python
|
|
||||||
from reconcile_text import reconcile
|
|
||||||
|
|
||||||
# Start with the original text
|
|
||||||
parent = "Hello world"
|
|
||||||
# Two users edit simultaneously
|
|
||||||
left = "Hello beautiful world"
|
|
||||||
right = "Hi world"
|
|
||||||
|
|
||||||
result = reconcile(parent, left, right)
|
|
||||||
print(result["text"]) # "Hi beautiful world"
|
|
||||||
```
|
|
||||||
|
|
||||||
See the [merge-file example](examples/merge_file.py) for a file-merging CLI, or the [advanced examples document](docs/advanced-python.md) for cursor tracking, change provenance, and compact diffs.
|
|
||||||
|
|
||||||
## Motivation
|
|
||||||
|
|
||||||
Collaborative editing presents the challenge of merging conflicting changes when multiple users edit documents simultaneously or asynchronously whilst offline. Traditional solutions like Conflict-free Replicated Data Types (CRDTs) or Operational Transformation (OT) work well when you control the complete editing infrastructure and can capture every individual operation ([1]). However, many workflows involve users editing with various tools, for example, Obsidian users editing Markdown files with various editors ranging from Vim to VS Code.
|
|
||||||
|
|
||||||
This creates **Differential Synchronisation** scenarios ([2], [3]): we only know the final state of each document, not the sequence of operations that produced it. This is the same challenge Git addresses, but Git requires manual conflict resolution. The key insight is that while incorrect merges in source code can introduce bugs, human text is more forgiving: a slightly imperfect sentence is often preferable to conflict markers interrupting the flow.
|
|
||||||
|
|
||||||
> **Note**: Some text domains require more careful handling. Legal contracts, for instance, could have unintended meaning changes from conflicting edits that create double negations. At the same time, semantic conflicts can still arise when merging code, even in the absence of syntactic conflicts.
|
|
||||||
|
|
||||||
Differential sync is implemented by [universal-sync][12], and it requires a merging tool that creates conflict-free results for the best user experience.
|
|
||||||
|
|
||||||
## How it works
|
|
||||||
|
|
||||||
`reconcile-text` starts off similarly to `diff3` ([4], [5]) but adds automated conflict resolution. Given a **parent** document and two modified versions (`left` and `right`), the following happens:
|
|
||||||
|
|
||||||
1. **Tokenisation** - Input texts are split into meaningful units (words, characters, etc.) for granular merging
|
|
||||||
2. **Diff computation** - Myers' algorithm calculates differences between (parent ↔ left) and (parent ↔ right)
|
|
||||||
3. **Diff optimisation** - Operations are reordered and consolidated to maximise chained changes
|
|
||||||
4. **Operational Transformation** - Edits are woven together using OT principles, preserving all modifications and updating cursors
|
|
||||||
|
|
||||||
Whilst the primary goal of `reconcile-text` isn't to implement OT, it provides an elegant way to merge Myers' diff outputs. (For a dedicated Rust OT implementation, see [operational-transform-rs][13].) The same could be achieved with CRDTs, which many libraries implement well for text (see [Loro][14], [cola][15], and [automerge][16]).
|
|
||||||
|
|
||||||
However, when only the end result of concurrent changes is observable, merge quality depends entirely on the quality of the underlying 2-way diffs. For instance, `move` operations cannot be supported because Myers' algorithm decomposes them into separate `insert` and `delete` operations, regardless of the merging algorithm used.
|
|
||||||
|
|
||||||
## Comparison with other approaches
|
|
||||||
|
|
||||||
### Traditional 3-way merge (diff3, Git)
|
|
||||||
|
|
||||||
Tools like `diff3` ([4]) and Git produce **conflict markers** (`<<<<<<<` / `=======` / `>>>>>>>`) when both sides modify the same region. This works for source code where a human must verify correctness, but breaks the reading flow for prose. `reconcile-text` uses the same diff3-like foundation but adds an OT-inspired resolution step that eliminates conflict markers entirely. Libraries like [diffy][17], [merge3][18] (Rust), and [node-diff3][19] (JavaScript) all fall into this category.
|
|
||||||
|
|
||||||
### diff-match-patch
|
|
||||||
|
|
||||||
[diff-match-patch][6] is a widely-used library created by Neil Fraser at Google in 2006, providing character-level diffing (Myers' algorithm), fuzzy string matching (Bitap algorithm), and patch application. It powers Fraser's **Differential Synchronisation** protocol ([2]): compute a diff between two texts, apply the patch to a third text that may have drifted, and repeat until convergence. If a patch fails, the failure self-corrects in the next sync cycle.
|
|
||||||
|
|
||||||
The key differences from `reconcile-text`:
|
|
||||||
|
|
||||||
- **2-way vs 3-way** - diff-match-patch diffs two texts and applies the result as a patch. It has no concept of a common ancestor and cannot reason about "left changes" vs "right changes". `reconcile-text` performs true 3-way merging, understanding the intent behind each side's edits.
|
|
||||||
|
|
||||||
- **Character-level only** - Word-level and line-level diffs require encoding tokens as single Unicode characters before diffing ([7]). `reconcile-text` supports word, character, line, and custom tokenisation natively.
|
|
||||||
|
|
||||||
- **Patches can fail** - `patch_apply` returns a boolean array indicating success per patch; failed patches are silently dropped. In Differential Synchronisation, failures self-correct in the next cycle, but for one-shot merges edits can be lost. `reconcile-text` always produces a complete merged result.
|
|
||||||
|
|
||||||
- **No cursor tracking or change provenance** - diff-match-patch does not reposition cursors or track which side made which edit. `reconcile-text` does both automatically.
|
|
||||||
|
|
||||||
See the [comparison example](examples/compare-with-diff-match-patch.rs) for concrete cases where diff-match-patch garbles adjacent edits and silently drops an entire sentence, while `reconcile-text` merges both users' changes correctly.
|
|
||||||
|
|
||||||
> **When to use diff-match-patch instead**: when you don't have a common ancestor, for example synchronising texts that have diverged through an unknown sequence of edits. If you have a common ancestor (as in most version control and collaborative editing scenarios), `reconcile-text` produces more reliable results.
|
|
||||||
|
|
||||||
### CRDTs (Yjs, Automerge, Loro, diamond-types)
|
|
||||||
|
|
||||||
Conflict-free Replicated Data Types guarantee convergence by mathematical construction: every operation commutes, so the order of application doesn't matter. Libraries like [Yjs][20] (and its Rust port [Yrs][21]), [Automerge][16], [Loro][14], [cola][15], and [diamond-types][22] implement this approach.
|
|
||||||
|
|
||||||
CRDTs capture every individual keystroke or operation, assigning each a unique identity. This makes them ideal when you control the complete editing infrastructure: the editor, the transport layer, and the storage format. They work peer-to-peer, handle arbitrary numbers of concurrent editors, and never lose an edit.
|
|
||||||
|
|
||||||
The trade-off is that CRDTs require **maintaining document state over time** - an operation log or internal data structure that grows with the document's edit history. You cannot simply hand a CRDT library three plain strings and get a merged result. This makes them unsuitable for Differential Synchronisation scenarios where you only observe the final state of each document, which is exactly the niche `reconcile-text` fills.
|
|
||||||
|
|
||||||
> **When to use CRDTs instead**: if you control the complete editing stack and can capture every operation as it happens, CRDTs provide stronger convergence guarantees. They also support more than two concurrent editors naturally, whereas `reconcile-text` merges exactly two forks at a time (though merges can be chained).
|
|
||||||
|
|
||||||
### Operational Transformation (OT)
|
|
||||||
|
|
||||||
OT libraries like [ot.js][23] and [ShareJS][24] transform concurrent operations against each other so that applying them in any order produces the same result. Like CRDTs, they capture individual operations and require infrastructure to coordinate them, typically a central server that determines the canonical operation order.
|
|
||||||
|
|
||||||
`reconcile-text` borrows the *concept* of OT (transforming one side's edits against the other) but applies it to a different problem. Instead of transforming individual keystrokes in real time, it transforms the consolidated diff output of two complete edits. This means it doesn't need a server, doesn't need to capture operations as they happen, and works entirely offline.
|
|
||||||
|
|
||||||
> **When to use OT instead**: if you need real-time collaboration with sub-second latency and can run a coordination server, dedicated OT libraries handle this well. `reconcile-text` is designed for merge points, not live keystroke-by-keystroke synchronisation.
|
|
||||||
|
|
||||||
## Development
|
|
||||||
|
|
||||||
Contributions are welcome!
|
|
||||||
|
|
||||||
### Environment
|
|
||||||
|
|
||||||
#### Python setup
|
|
||||||
|
|
||||||
Install [uv](https://docs.astral.sh/uv/getting-started/installation/) and build the extension for development:
|
|
||||||
|
|
||||||
```sh
|
|
||||||
cd reconcile-python
|
|
||||||
uv run maturin develop
|
|
||||||
```
|
|
||||||
|
|
||||||
#### Node.js setup
|
|
||||||
|
|
||||||
1. Install [nvm][25]:
|
|
||||||
```sh
|
|
||||||
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash
|
|
||||||
```
|
|
||||||
2. Install and use Node 22:
|
|
||||||
```sh
|
|
||||||
nvm install 22 && nvm use 22
|
|
||||||
```
|
|
||||||
3. Optionally, set as default:
|
|
||||||
```sh
|
|
||||||
nvm alias default 22
|
|
||||||
```
|
|
||||||
|
|
||||||
#### Rust toolchain
|
|
||||||
|
|
||||||
Install [rustup][26]:
|
|
||||||
```bash
|
|
||||||
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
|
|
||||||
```
|
|
||||||
|
|
||||||
### Scripts
|
### Scripts
|
||||||
|
|
||||||
- **Run tests**: `scripts/test.sh`
|
#### Update HTTP API TS bindings
|
||||||
- **Lint and format**: `scripts/lint.sh`
|
|
||||||
- **Develop demo website**: `scripts/dev-website.sh`
|
|
||||||
- **Build demo website**: `scripts/build-website.sh`
|
|
||||||
- **Publish new version**: `scripts/bump-version.sh patch`
|
|
||||||
|
|
||||||
## License
|
```sh
|
||||||
|
scripts/update-api-types.sh
|
||||||
|
```
|
||||||
|
|
||||||
[MIT](./LICENSE)
|
#### Publish new version
|
||||||
|
|
||||||
[1]: https://marijnhaverbeke.nl/blog/collaborative-editing-cm.html
|
```sh
|
||||||
[2]: https://neil.fraser.name/writing/sync/
|
scripts/bump-version.sh patch
|
||||||
[3]: https://www.cis.upenn.edu/~bcpierce/papers/diff3-short.pdf
|
```
|
||||||
[4]: https://blog.jcoglan.com/2017/05/08/merging-with-diff3/
|
|
||||||
[5]: https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/35605.pdf
|
#### Run E2E tests
|
||||||
[6]: https://github.com/google/diff-match-patch
|
|
||||||
[7]: https://github.com/google/diff-match-patch/wiki/Line-or-Word-Diffs
|
```sh
|
||||||
[8]: https://schmelczer.dev/reconcile
|
scripts/e2e.sh
|
||||||
[9]: https://crates.io/crates/reconcile-text
|
```
|
||||||
[10]: https://www.npmjs.com/package/reconcile-text
|
|
||||||
[11]: https://docs.rs/reconcile-text/latest/reconcile_text
|
And to clean up the logs & database files, run `scripts/clean-up.sh`
|
||||||
[12]: https://github.com/invisible-college/universal-sync
|
|
||||||
[13]: https://github.com/spebern/operational-transform-rs
|
## Projects
|
||||||
[14]: https://github.com/loro-dev/loro/
|
|
||||||
[15]: https://github.com/nomad/cola
|
- [Sync server](./backend/sync_server/README.md)
|
||||||
[16]: https://github.com/automerge/automerge
|
|
||||||
[17]: https://crates.io/crates/diffy
|
|
||||||
[18]: https://github.com/breezy-team/merge3-rs
|
|
||||||
[19]: https://github.com/bhousel/node-diff3
|
|
||||||
[20]: https://github.com/yjs/yjs
|
|
||||||
[21]: https://github.com/y-crdt/y-crdt
|
|
||||||
[22]: https://github.com/josephg/diamond-types
|
|
||||||
[23]: https://ot.js.org/
|
|
||||||
[24]: https://github.com/josephg/ShareJS
|
|
||||||
[25]: https://github.com/nvm-sh/nvm
|
|
||||||
[26]: https://rustup.rs
|
|
||||||
[27]: https://pypi.org/project/reconcile-text/
|
|
||||||
|
|
|
||||||
|
|
@ -1,92 +0,0 @@
|
||||||
# Advanced Usage (Python)
|
|
||||||
|
|
||||||
## Edit Provenance
|
|
||||||
|
|
||||||
Track which changes came from where using `reconcile_with_history`:
|
|
||||||
|
|
||||||
```python
|
|
||||||
from reconcile_text import reconcile_with_history
|
|
||||||
|
|
||||||
result = reconcile_with_history(
|
|
||||||
"Hello world",
|
|
||||||
"Hello beautiful world",
|
|
||||||
"Hi world",
|
|
||||||
)
|
|
||||||
|
|
||||||
print(result["text"]) # "Hi beautiful world"
|
|
||||||
print(result["history"]) #
|
|
||||||
# [
|
|
||||||
# {"text": "Hello", "history": "RemovedFromRight"},
|
|
||||||
# {"text": "Hi", "history": "AddedFromRight"},
|
|
||||||
# {"text": " beautiful", "history": "AddedFromLeft"},
|
|
||||||
# {"text": " ", "history": "Unchanged"},
|
|
||||||
# {"text": "world", "history": "Unchanged"},
|
|
||||||
# ]
|
|
||||||
```
|
|
||||||
|
|
||||||
## Tokenization Strategies
|
|
||||||
|
|
||||||
`reconcile-text` offers different approaches to split text for merging:
|
|
||||||
|
|
||||||
- **Word tokenizer** (`"Word"`) - Splits on word boundaries (recommended for prose)
|
|
||||||
- **Character tokenizer** (`"Character"`) - Individual characters (fine-grained control)
|
|
||||||
- **Line tokenizer** (`"Line"`) - Line-by-line (similar to `git merge` or more precisely [`git merge-file`](https://git-scm.com/docs/git-merge-file))
|
|
||||||
- **Markdown tokenizer** (`"Markdown"`) - Splits on Markdown structural boundaries (headings, list items, paragraphs)
|
|
||||||
|
|
||||||
```python
|
|
||||||
from reconcile_text import reconcile
|
|
||||||
|
|
||||||
result = reconcile("abc", "axc", "abyc", "Character")
|
|
||||||
print(result["text"]) # "axyc"
|
|
||||||
```
|
|
||||||
|
|
||||||
## Cursor Tracking
|
|
||||||
|
|
||||||
`reconcile-text` automatically tracks cursor positions through merges, which is useful for collaborative editors. Selections can be tracked by providing them as a pair of cursors.
|
|
||||||
|
|
||||||
```python
|
|
||||||
from reconcile_text import reconcile
|
|
||||||
|
|
||||||
result = reconcile(
|
|
||||||
"Hello world",
|
|
||||||
{
|
|
||||||
"text": "Hello beautiful world",
|
|
||||||
"cursors": [{"id": 1, "position": 6}], # After "Hello "
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"text": "Hi world",
|
|
||||||
"cursors": [{"id": 2, "position": 0}], # At the beginning
|
|
||||||
},
|
|
||||||
)
|
|
||||||
|
|
||||||
# Result: "Hi beautiful world" with repositioned cursors
|
|
||||||
print(result["text"]) # "Hi beautiful world"
|
|
||||||
print(result["cursors"]) # [{"id": 2, "position": 0}, {"id": 1, "position": 3}]
|
|
||||||
```
|
|
||||||
|
|
||||||
> The `cursors` list is sorted by character position (not IDs).
|
|
||||||
|
|
||||||
## Compact Diffs
|
|
||||||
|
|
||||||
Generate and apply compact diff representations:
|
|
||||||
|
|
||||||
```python
|
|
||||||
from reconcile_text import diff, undiff
|
|
||||||
|
|
||||||
original = "Hello world"
|
|
||||||
changed = "Hello beautiful world"
|
|
||||||
|
|
||||||
# Generate a compact diff
|
|
||||||
d = diff(original, changed)
|
|
||||||
print(d) # [5, ' beautiful world']
|
|
||||||
|
|
||||||
# Reconstruct the changed text from the diff
|
|
||||||
reconstructed = undiff(original, d)
|
|
||||||
assert reconstructed == changed
|
|
||||||
```
|
|
||||||
|
|
||||||
Diff entries are positive integers (retain N characters), negative integers (delete N characters), and strings (insert text).
|
|
||||||
|
|
||||||
## File Merging Example
|
|
||||||
|
|
||||||
For a complete file-merging CLI (a trivial `git merge-file`), see [`examples/merge_file.py`](../examples/merge_file.py).
|
|
||||||
|
|
@ -1,231 +0,0 @@
|
||||||
# Advanced Usage (TypeScript)
|
|
||||||
|
|
||||||
## Edit Provenance
|
|
||||||
|
|
||||||
Track which changes came from where using `reconcileWithHistory`. The result's
|
|
||||||
`history` field is typed as `SpanWithHistory[]`, and each span's `history` is a
|
|
||||||
`History` string-literal union.
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
import { reconcileWithHistory, type History, type SpanWithHistory } from 'reconcile-text';
|
|
||||||
|
|
||||||
const result = reconcileWithHistory('Hello world', 'Hello beautiful world', 'Hi world');
|
|
||||||
|
|
||||||
console.log(result.text); // "Hi beautiful world"
|
|
||||||
|
|
||||||
const history: SpanWithHistory[] = result.history;
|
|
||||||
console.log(history);
|
|
||||||
// [
|
|
||||||
// { text: "Hello", history: "RemovedFromRight" },
|
|
||||||
// { text: "Hi", history: "AddedFromRight" },
|
|
||||||
// { text: " beautiful", history: "AddedFromLeft" },
|
|
||||||
// { text: " ", history: "Unchanged" },
|
|
||||||
// { text: "world", history: "Unchanged" },
|
|
||||||
// ]
|
|
||||||
|
|
||||||
const classByHistory = {
|
|
||||||
Unchanged: 'merge-unchanged',
|
|
||||||
AddedFromLeft: 'merge-added-left',
|
|
||||||
AddedFromRight: 'merge-added-right',
|
|
||||||
RemovedFromLeft: 'merge-removed-left',
|
|
||||||
RemovedFromRight: 'merge-removed-right',
|
|
||||||
} satisfies Record<History, string>;
|
|
||||||
```
|
|
||||||
|
|
||||||
Using `satisfies Record<History, string>` keeps the object literal's values
|
|
||||||
narrow while forcing every history case to be handled. If a future version adds
|
|
||||||
another `History` value, TypeScript will point at this mapping.
|
|
||||||
|
|
||||||
For control flow, use the same union as an exhaustiveness check:
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
import type { History } from 'reconcile-text';
|
|
||||||
|
|
||||||
function historyLabel(history: History): string {
|
|
||||||
switch (history) {
|
|
||||||
case 'Unchanged':
|
|
||||||
return 'unchanged';
|
|
||||||
case 'AddedFromLeft':
|
|
||||||
return 'added by left';
|
|
||||||
case 'AddedFromRight':
|
|
||||||
return 'added by right';
|
|
||||||
case 'RemovedFromLeft':
|
|
||||||
return 'removed from left';
|
|
||||||
case 'RemovedFromRight':
|
|
||||||
return 'removed from right';
|
|
||||||
default:
|
|
||||||
return assertNever(history);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
function assertNever(value: never): never {
|
|
||||||
throw new Error(`Unhandled history value: ${value}`);
|
|
||||||
}
|
|
||||||
```
|
|
||||||
|
|
||||||
## Tokenisation Strategies
|
|
||||||
|
|
||||||
`reconcile-text` offers different approaches to split text for merging:
|
|
||||||
|
|
||||||
- **Word tokeniser** (`"Word"`) - Splits on word boundaries (recommended for prose)
|
|
||||||
- **Character tokeniser** (`"Character"`) - Individual characters (fine-grained control)
|
|
||||||
- **Line tokeniser** (`"Line"`) - Line-by-line (similar to `git merge` or more precisely [`git merge-file`](https://git-scm.com/docs/git-merge-file))
|
|
||||||
- **Markdown tokeniser** (`"Markdown"`) - Splits on Markdown structural boundaries (headings, list items, paragraphs)
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
import { reconcile, type BuiltinTokenizer } from 'reconcile-text';
|
|
||||||
|
|
||||||
const tokenizers = [
|
|
||||||
'Word',
|
|
||||||
'Character',
|
|
||||||
'Line',
|
|
||||||
'Markdown',
|
|
||||||
] as const satisfies readonly BuiltinTokenizer[];
|
|
||||||
|
|
||||||
const result = reconcile('abc', 'axc', 'abyc', 'Character');
|
|
||||||
console.log(result.text); // "axyc"
|
|
||||||
|
|
||||||
for (const tokenizer of tokenizers) {
|
|
||||||
const merged = reconcile(
|
|
||||||
'# Title\n\n- old item\n',
|
|
||||||
'# Title\n\n- old item\n- left item\n',
|
|
||||||
'# New title\n\n- old item\n',
|
|
||||||
tokenizer
|
|
||||||
);
|
|
||||||
|
|
||||||
console.log(tokenizer, merged.text);
|
|
||||||
}
|
|
||||||
```
|
|
||||||
|
|
||||||
## Cursor Tracking
|
|
||||||
|
|
||||||
`reconcile-text` automatically tracks cursor positions through merges, which is
|
|
||||||
useful for collaborative editors. Selections can be tracked by providing them as
|
|
||||||
a pair of cursors.
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
import { reconcile, type TextWithOptionalCursors } from 'reconcile-text';
|
|
||||||
|
|
||||||
const left = {
|
|
||||||
text: 'Hello beautiful world',
|
|
||||||
cursors: [{ id: 1, position: 6 }], // After "Hello "
|
|
||||||
} satisfies TextWithOptionalCursors;
|
|
||||||
|
|
||||||
const right = {
|
|
||||||
text: 'Hi world',
|
|
||||||
cursors: [{ id: 2, position: 0 }], // At the beginning
|
|
||||||
} satisfies TextWithOptionalCursors;
|
|
||||||
|
|
||||||
const result = reconcile('Hello world', left, right);
|
|
||||||
|
|
||||||
// Result: "Hi beautiful world" with repositioned cursors
|
|
||||||
console.log(result.text); // "Hi beautiful world"
|
|
||||||
console.log(result.cursors); // [{ id: 2, position: 0 }, { id: 1, position: 3 }]
|
|
||||||
```
|
|
||||||
|
|
||||||
> The `cursors` list is sorted by character position (not IDs).
|
|
||||||
|
|
||||||
## Generic Helpers and Inference
|
|
||||||
|
|
||||||
The exported merge functions are intentionally small: they merge strings, or
|
|
||||||
strings plus cursor metadata. In TypeScript applications, keep domain-specific
|
|
||||||
metadata in your own typed wrappers and let inference preserve the surrounding
|
|
||||||
shape.
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
import { reconcile, type BuiltinTokenizer } from 'reconcile-text';
|
|
||||||
|
|
||||||
type ReconciledText<T extends { text: string }> = Omit<T, 'text'> & {
|
|
||||||
text: string;
|
|
||||||
};
|
|
||||||
|
|
||||||
function reconcileDraft<TDraft extends { text: string }>(
|
|
||||||
parent: TDraft,
|
|
||||||
left: TDraft,
|
|
||||||
right: TDraft,
|
|
||||||
tokenizer?: BuiltinTokenizer
|
|
||||||
): ReconciledText<TDraft> {
|
|
||||||
return {
|
|
||||||
...right,
|
|
||||||
text: reconcile(parent.text, left.text, right.text, tokenizer).text,
|
|
||||||
};
|
|
||||||
}
|
|
||||||
|
|
||||||
interface MarkdownDraft {
|
|
||||||
id: string;
|
|
||||||
text: string;
|
|
||||||
updatedAt: Date;
|
|
||||||
}
|
|
||||||
|
|
||||||
const parent: MarkdownDraft = {
|
|
||||||
id: 'intro',
|
|
||||||
text: '# Title\n\nOld text\n',
|
|
||||||
updatedAt: new Date('2026-01-01T00:00:00Z'),
|
|
||||||
};
|
|
||||||
|
|
||||||
const left: MarkdownDraft = {
|
|
||||||
...parent,
|
|
||||||
text: '# Title\n\nOld text\n\n- left note\n',
|
|
||||||
};
|
|
||||||
|
|
||||||
const right: MarkdownDraft = {
|
|
||||||
...parent,
|
|
||||||
text: '# New title\n\nOld text\n',
|
|
||||||
};
|
|
||||||
|
|
||||||
const merged = reconcileDraft(parent, left, right, 'Markdown');
|
|
||||||
// merged is inferred as { id: string; updatedAt: Date; text: string }
|
|
||||||
```
|
|
||||||
|
|
||||||
Use `satisfies` for configuration objects and cursor payloads when you want
|
|
||||||
compile-time checking without widening everything to the library interface.
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
import type { BuiltinTokenizer, TextWithOptionalCursors } from 'reconcile-text';
|
|
||||||
|
|
||||||
const mergeOptions = {
|
|
||||||
tokenizer: 'Markdown',
|
|
||||||
renderDeletedSpans: true,
|
|
||||||
} satisfies {
|
|
||||||
tokenizer: BuiltinTokenizer;
|
|
||||||
renderDeletedSpans: boolean;
|
|
||||||
};
|
|
||||||
|
|
||||||
const documentWithSelection = {
|
|
||||||
text: 'Hello beautiful world',
|
|
||||||
cursors: [
|
|
||||||
{ id: 1, position: 6 },
|
|
||||||
{ id: 2, position: 15 },
|
|
||||||
],
|
|
||||||
} satisfies TextWithOptionalCursors;
|
|
||||||
```
|
|
||||||
|
|
||||||
## Compact Diffs
|
|
||||||
|
|
||||||
Generate and apply compact diff representations. The TypeScript type is
|
|
||||||
`Array<number | string>` for `diff()` and `Array<number | bigint | string>` for
|
|
||||||
`undiff()`, because the underlying WebAssembly layer may represent integer
|
|
||||||
entries as `bigint`.
|
|
||||||
|
|
||||||
```typescript
|
|
||||||
import { diff, undiff } from 'reconcile-text';
|
|
||||||
|
|
||||||
const original = 'Hello world';
|
|
||||||
const changed = 'Hello beautiful world';
|
|
||||||
|
|
||||||
// Generate a compact diff
|
|
||||||
const changes = diff(original, changed);
|
|
||||||
console.log(changes); // [5, " beautiful world"]
|
|
||||||
|
|
||||||
// Reconstruct the changed text from the diff
|
|
||||||
const reconstructed = undiff(original, changes);
|
|
||||||
console.assert(reconstructed === changed);
|
|
||||||
```
|
|
||||||
|
|
||||||
Diff entries are positive integers (retain N characters), negative integers
|
|
||||||
(delete N characters), and strings (insert text).
|
|
||||||
|
|
||||||
## Complete Example
|
|
||||||
|
|
||||||
For a complete browser example that renders `SpanWithHistory` values and cursor
|
|
||||||
selections, see the [example website source](../examples/website/src/index.ts).
|
|
||||||
|
|
@ -1,95 +0,0 @@
|
||||||
use std::panic;
|
|
||||||
|
|
||||||
use diff_match_patch_rs::{Compat, DiffMatchPatch, PatchInput};
|
|
||||||
use reconcile_text::{BuiltinTokenizer, reconcile};
|
|
||||||
|
|
||||||
fn dmp_merge(parent: &str, left: &str, right: &str) -> Option<String> {
|
|
||||||
let parent = parent.to_owned();
|
|
||||||
let left = left.to_owned();
|
|
||||||
let right = right.to_owned();
|
|
||||||
|
|
||||||
// diff-match-patch-rs can panic on some inputs, so we catch that.
|
|
||||||
panic::catch_unwind(|| {
|
|
||||||
let dmp = DiffMatchPatch::new();
|
|
||||||
let diffs = dmp.diff_main::<Compat>(&parent, &left).ok()?;
|
|
||||||
let patches = dmp
|
|
||||||
.patch_make(PatchInput::new_text_diffs(&parent, &diffs))
|
|
||||||
.ok()?;
|
|
||||||
let (result, _) = dmp.patch_apply(&patches, &right).ok()?;
|
|
||||||
Some(result)
|
|
||||||
})
|
|
||||||
.ok()
|
|
||||||
.flatten()
|
|
||||||
}
|
|
||||||
|
|
||||||
fn try_merge(parent: &str, left: &str, right: &str) {
|
|
||||||
let dmp_result = dmp_merge(parent, left, right);
|
|
||||||
|
|
||||||
let reconcile_result = reconcile(
|
|
||||||
parent,
|
|
||||||
&left.into(),
|
|
||||||
&right.into(),
|
|
||||||
&*BuiltinTokenizer::Word,
|
|
||||||
)
|
|
||||||
.apply()
|
|
||||||
.text();
|
|
||||||
|
|
||||||
println!("Parent: {parent:?}");
|
|
||||||
println!("Left: {left:?}");
|
|
||||||
println!("Right: {right:?}");
|
|
||||||
println!();
|
|
||||||
match dmp_result {
|
|
||||||
Some(r) => println!("diff-match-patch: {r:?}"),
|
|
||||||
None => println!("diff-match-patch: <panic or error>"),
|
|
||||||
}
|
|
||||||
println!("reconcile-text: {reconcile_result:?}");
|
|
||||||
println!();
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Demonstrates cases where diff-match-patch silently produces incorrect
|
|
||||||
/// output, while reconcile-text preserves both users' edits correctly
|
|
||||||
///
|
|
||||||
/// Run it with:
|
|
||||||
/// `cargo run --example compare-with-diff-match-patch`
|
|
||||||
fn main() {
|
|
||||||
// Example 1
|
|
||||||
// Two users edit the same short phrase. Alice replaces "old(!)" with
|
|
||||||
// "new improved", Bob replaces "broken" with "working". These are
|
|
||||||
// independent changes to adjacent words.
|
|
||||||
//
|
|
||||||
// diff-match-patch has no common ancestor, so it diffs parent → left
|
|
||||||
// and applies the patch to right. The character-level patches overlap
|
|
||||||
// and produce garbled text ("impovind"). It reports success.
|
|
||||||
//
|
|
||||||
// reconcile-text sees both changes relative to the parent and merges
|
|
||||||
// them cleanly.
|
|
||||||
|
|
||||||
println!("── Example 1: adjacent edits ──");
|
|
||||||
try_merge(
|
|
||||||
"old(!) broken code",
|
|
||||||
"new improved code",
|
|
||||||
"old(!) working code",
|
|
||||||
);
|
|
||||||
|
|
||||||
// Example 2
|
|
||||||
// Alice adds a sentence. Bob rewrites the surrounding text. Because
|
|
||||||
// diff-match-patch works without a common ancestor, Alice's entire
|
|
||||||
// sentence is silently lost.
|
|
||||||
|
|
||||||
println!("── Example 2: sentence lost ──");
|
|
||||||
// Alice adds a sentence in the middle of a paragraph. Bob rephrases
|
|
||||||
// the same paragraph. Because the patch context from Alice's edit no
|
|
||||||
// longer appears in Bob's version, diff-match-patch silently drops
|
|
||||||
// Alice's entire sentence.
|
|
||||||
//
|
|
||||||
// reconcile-text understands both edits relative to the common ancestor
|
|
||||||
// and keeps both.
|
|
||||||
try_merge(
|
|
||||||
"We used the existing parsing approach for processing. The output was saved to the \
|
|
||||||
database.",
|
|
||||||
"We used the existing parsing approach for processing. Always validate the schema! The \
|
|
||||||
output was saved to the database.",
|
|
||||||
"We adopted a brand new analysis pipeline for execution. The results were written to \
|
|
||||||
cloud storage.",
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
@ -1,58 +0,0 @@
|
||||||
use std::{env, fs, process};
|
|
||||||
|
|
||||||
use reconcile_text::{BuiltinTokenizer, reconcile};
|
|
||||||
|
|
||||||
/// Merges three versions of a file: mine, base, and theirs.
|
|
||||||
/// Implement a trivial version git merge-file (<https://git-scm.com/docs/git-merge-file>)
|
|
||||||
///
|
|
||||||
/// Run it with:
|
|
||||||
/// `cargo run --example merge-file my.txt base.txt their.txt [output_file.txt]`
|
|
||||||
fn main() {
|
|
||||||
let args: Vec<String> = env::args().collect();
|
|
||||||
|
|
||||||
if args.len() < 4 || args.len() > 5 {
|
|
||||||
eprintln!("Usage: merge-file <mine> <base> <theirs> [output]");
|
|
||||||
process::exit(1);
|
|
||||||
}
|
|
||||||
|
|
||||||
let mine_file = &args[1];
|
|
||||||
let base_file = &args[2];
|
|
||||||
let theirs_file = &args[3];
|
|
||||||
let output_file = args.get(4);
|
|
||||||
|
|
||||||
// Read files
|
|
||||||
let mine_content = fs::read_to_string(mine_file).unwrap_or_else(|e| {
|
|
||||||
eprintln!("Error reading {mine_file}: {e}");
|
|
||||||
process::exit(1);
|
|
||||||
});
|
|
||||||
|
|
||||||
let base_content = fs::read_to_string(base_file).unwrap_or_else(|e| {
|
|
||||||
eprintln!("Error reading {base_file}: {e}");
|
|
||||||
process::exit(1);
|
|
||||||
});
|
|
||||||
|
|
||||||
let theirs_content = fs::read_to_string(theirs_file).unwrap_or_else(|e| {
|
|
||||||
eprintln!("Error reading {theirs_file}: {e}");
|
|
||||||
process::exit(1);
|
|
||||||
});
|
|
||||||
|
|
||||||
// Perform the merge using reconcile
|
|
||||||
let result = reconcile(
|
|
||||||
&base_content,
|
|
||||||
&mine_content.into(),
|
|
||||||
&theirs_content.into(),
|
|
||||||
&*BuiltinTokenizer::Word,
|
|
||||||
);
|
|
||||||
|
|
||||||
let merged_content = result.apply().text();
|
|
||||||
|
|
||||||
// Write the result
|
|
||||||
if let Some(output_path) = output_file {
|
|
||||||
if let Err(e) = fs::write(output_path, merged_content) {
|
|
||||||
eprintln!("Error writing to {output_path}: {e}");
|
|
||||||
process::exit(1);
|
|
||||||
}
|
|
||||||
} else {
|
|
||||||
print!("{merged_content}");
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
@ -1,38 +0,0 @@
|
||||||
"""Merge three versions of a file: mine, base, and theirs.
|
|
||||||
|
|
||||||
A trivial version of git merge-file (https://git-scm.com/docs/git-merge-file).
|
|
||||||
|
|
||||||
Run it with:
|
|
||||||
uv run --directory reconcile-python \
|
|
||||||
python ../examples/merge_file.py my.txt base.txt their.txt [output.txt]
|
|
||||||
"""
|
|
||||||
|
|
||||||
from __future__ import annotations
|
|
||||||
|
|
||||||
import sys
|
|
||||||
from pathlib import Path
|
|
||||||
|
|
||||||
from reconcile_text import reconcile
|
|
||||||
|
|
||||||
|
|
||||||
def main() -> None:
|
|
||||||
args = sys.argv[1:]
|
|
||||||
|
|
||||||
if len(args) < 3 or len(args) > 4:
|
|
||||||
print("Usage: merge_file.py <mine> <base> <theirs> [output]", file=sys.stderr)
|
|
||||||
sys.exit(1)
|
|
||||||
|
|
||||||
mine = Path(args[0]).read_text()
|
|
||||||
base = Path(args[1]).read_text()
|
|
||||||
theirs = Path(args[2]).read_text()
|
|
||||||
|
|
||||||
result = reconcile(base, mine, theirs)
|
|
||||||
|
|
||||||
if len(args) == 4:
|
|
||||||
Path(args[3]).write_text(result["text"])
|
|
||||||
else:
|
|
||||||
print(result["text"], end="")
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
main()
|
|
||||||
3
examples/website/.gitignore
vendored
Normal file
3
examples/website/.gitignore
vendored
Normal file
|
|
@ -0,0 +1,3 @@
|
||||||
|
reconcile.js
|
||||||
|
reconcile_bg.wasm
|
||||||
|
|
||||||
77
examples/website/index.html
Normal file
77
examples/website/index.html
Normal file
|
|
@ -0,0 +1,77 @@
|
||||||
|
<!DOCTYPE html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="UTF-8" />
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||||
|
<meta
|
||||||
|
name="description"
|
||||||
|
content="Easily merge three versions of a text document with this 3-way text merge tool."
|
||||||
|
/>
|
||||||
|
<meta property="og:title" content="3-Way Text Merge" />
|
||||||
|
<meta
|
||||||
|
property="og:description"
|
||||||
|
content="Easily merge three versions of a text document with this 3-way text merge tool."
|
||||||
|
/>
|
||||||
|
<meta property="og:type" content="website" />
|
||||||
|
<meta
|
||||||
|
property="og:url"
|
||||||
|
content="https://github.com/schmelczer/reconcile"
|
||||||
|
/>
|
||||||
|
<meta property="og:image" content="/favicon.ico" />
|
||||||
|
<link rel="icon" type="image/x-icon" href="favicon.ico" />
|
||||||
|
<title>3-Way Text Merge</title>
|
||||||
|
<link rel="stylesheet" href="style.css" />
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<header>
|
||||||
|
<h1>3-Way Text Merge</h1>
|
||||||
|
<p>Use this tool to merge three versions of a text.</p>
|
||||||
|
</header>
|
||||||
|
|
||||||
|
<main>
|
||||||
|
<div class="text-area diamond-parent">
|
||||||
|
<label for="original">Original</label>
|
||||||
|
<textarea id="original" name="original"></textarea>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<div class="text-area diamond-left">
|
||||||
|
<label for="left">First concurrent edit</label>
|
||||||
|
<textarea id="left" name="left"></textarea>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<div class="text-area diamond-right">
|
||||||
|
<label for="right">Second concurrent edit</label>
|
||||||
|
<textarea id="right" name="right"></textarea>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<button id="merge-button" type="button">Merge</button>
|
||||||
|
|
||||||
|
<div class="text-area diamond-result">
|
||||||
|
<label for="merged">Deconflicted result (readonly)</label>
|
||||||
|
<textarea id="merged" name="merged" readonly></textarea>
|
||||||
|
</div>
|
||||||
|
</main>
|
||||||
|
|
||||||
|
<footer>
|
||||||
|
<p>2025 Andras Schmelczer</p>
|
||||||
|
<a
|
||||||
|
href="https://github.com/schmelczer/reconcile"
|
||||||
|
class="github-link"
|
||||||
|
aria-label="GitHub repository"
|
||||||
|
>
|
||||||
|
<svg
|
||||||
|
xmlns="http://www.w3.org/2000/svg"
|
||||||
|
width="24"
|
||||||
|
height="24"
|
||||||
|
viewBox="0 0 24 24"
|
||||||
|
>
|
||||||
|
<path
|
||||||
|
d="M12 0c-6.626 0-12 5.373-12 12 0 5.302 3.438 9.8 8.207 11.387.599.111.793-.261.793-.577v-2.234c-3.338.726-4.033-1.416-4.033-1.416-.546-1.387-1.333-1.756-1.333-1.756-1.089-.745.083-.729.083-.729 1.205.084 1.839 1.237 1.839 1.237 1.07 1.834 2.807 1.304 3.492.997.107-.775.418-1.305.762-1.604-2.665-.305-5.467-1.334-5.467-5.931 0-1.311.469-2.381 1.236-3.221-.124-.303-.535-1.524.117-3.176 0 0 1.008-.322 3.301 1.23.957-.266 1.983-.399 3.003-.404 1.02.005 2.047.138 3.006.404 2.291-1.552 3.297-1.23 3.297-1.23.653 1.653.242 2.874.118 3.176.77.84 1.235 1.911 1.235 3.221 0 4.609-2.807 5.624-5.479 5.921.43.372.823 1.102.823 2.222v3.293c0 .319.192.694.801.576 4.765-1.589 8.199-6.086 8.199-11.386 0-6.627-5.373-12-12-12z"
|
||||||
|
/>
|
||||||
|
</svg>
|
||||||
|
</a>
|
||||||
|
</footer>
|
||||||
|
|
||||||
|
<script type="module" src="script.js"></script>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
5913
examples/website/package-lock.json
generated
5913
examples/website/package-lock.json
generated
File diff suppressed because it is too large
Load diff
|
|
@ -1,43 +0,0 @@
|
||||||
{
|
|
||||||
"name": "reconcile-example-website",
|
|
||||||
"description": "",
|
|
||||||
"private": true,
|
|
||||||
"scripts": {
|
|
||||||
"start": "webpack serve --open --mode development",
|
|
||||||
"format": "prettier --write \"./**/*.(ts|scss|json|html)\"",
|
|
||||||
"build": "webpack --mode production"
|
|
||||||
},
|
|
||||||
"repository": {
|
|
||||||
"type": "git",
|
|
||||||
"url": "git+https://github.com/schmelczer/reconcile.git"
|
|
||||||
},
|
|
||||||
"keywords": [],
|
|
||||||
"author": "Andras Schmelczer",
|
|
||||||
"license": "GPL-3.0-or-later",
|
|
||||||
"bugs": {
|
|
||||||
"url": "https://github.com/schmelczer/reconcile/issues"
|
|
||||||
},
|
|
||||||
"browserslist": [
|
|
||||||
"defaults"
|
|
||||||
],
|
|
||||||
"homepage": "https://github.com/schmelczer/reconcile#readme",
|
|
||||||
"devDependencies": {
|
|
||||||
"copy-webpack-plugin": "^14.0.0",
|
|
||||||
"css-loader": "^7.1.4",
|
|
||||||
"html-webpack-plugin": "^5.6.6",
|
|
||||||
"inline-source-webpack-plugin": "^3.0.1",
|
|
||||||
"mini-css-extract-plugin": "^2.10.1",
|
|
||||||
"prettier": "^3.8.1",
|
|
||||||
"reconcile-text": "file:../../reconcile-js",
|
|
||||||
"resolve-url-loader": "^5.0.0",
|
|
||||||
"sass": "^1.98.0",
|
|
||||||
"sass-loader": "^16.0.7",
|
|
||||||
"svg-inline-loader": "^0.8.2",
|
|
||||||
"terser-webpack-plugin": "^5.4.0",
|
|
||||||
"ts-loader": "^9.5.4",
|
|
||||||
"typescript": "^5.9.3",
|
|
||||||
"webpack": "^5.105.4",
|
|
||||||
"webpack-cli": "^6.0.1",
|
|
||||||
"webpack-dev-server": "^5.2.3"
|
|
||||||
}
|
|
||||||
}
|
|
||||||
41
examples/website/script.js
Normal file
41
examples/website/script.js
Normal file
|
|
@ -0,0 +1,41 @@
|
||||||
|
import init, { mergeText } from "./reconcile.js";
|
||||||
|
|
||||||
|
const originalTextArea = document.getElementById("original");
|
||||||
|
const leftTextArea = document.getElementById("left");
|
||||||
|
const rightTextArea = document.getElementById("right");
|
||||||
|
const mergedTextArea = document.getElementById("merged");
|
||||||
|
const mergeButton = document.getElementById("merge-button");
|
||||||
|
|
||||||
|
const sampleTexts = [
|
||||||
|
"The quick brown fox jumps over the lazy dog.",
|
||||||
|
"Lorem ipsum dolor sit amet, consectetur adipiscing elit.",
|
||||||
|
"Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium.",
|
||||||
|
"A journey of a thousand miles begins with a single step.",
|
||||||
|
"To be, or not to be, that is the question.",
|
||||||
|
];
|
||||||
|
|
||||||
|
async function run() {
|
||||||
|
await init();
|
||||||
|
|
||||||
|
mergeButton.addEventListener("click", () => {
|
||||||
|
const original = originalTextArea.value;
|
||||||
|
const left = leftTextArea.value;
|
||||||
|
const right = rightTextArea.value;
|
||||||
|
|
||||||
|
const result = mergeText(original, left, right);
|
||||||
|
mergedTextArea.value = result;
|
||||||
|
});
|
||||||
|
|
||||||
|
loadSample();
|
||||||
|
}
|
||||||
|
|
||||||
|
function loadSample() {
|
||||||
|
const randomIndex = Math.floor(Math.random() * sampleTexts.length);
|
||||||
|
const text = sampleTexts[randomIndex];
|
||||||
|
originalTextArea.value = text;
|
||||||
|
leftTextArea.value = text;
|
||||||
|
rightTextArea.value = text;
|
||||||
|
mergedTextArea.value = "";
|
||||||
|
}
|
||||||
|
|
||||||
|
run();
|
||||||
Binary file not shown.
|
Before Width: | Height: | Size: 4.2 KiB |
|
|
@ -1,279 +0,0 @@
|
||||||
<!doctype html>
|
|
||||||
<html lang="en">
|
|
||||||
<head>
|
|
||||||
<meta charset="UTF-8" />
|
|
||||||
<meta
|
|
||||||
name="viewport"
|
|
||||||
content="width=device-width, initial-scale=1.0, viewport-fit=cover"
|
|
||||||
/>
|
|
||||||
<meta
|
|
||||||
name="description"
|
|
||||||
content="3-way text merging that automatically resolves conflicts. No more Git conflict markers - just clean, merged results."
|
|
||||||
/>
|
|
||||||
<meta property="og:title" content="3-Way Text Merge" />
|
|
||||||
<meta
|
|
||||||
property="og:description"
|
|
||||||
content="3-way text merging that automatically resolves conflicts. No more Git conflict markers - just clean, merged results."
|
|
||||||
/>
|
|
||||||
<meta property="og:type" content="website" />
|
|
||||||
<meta property="og:url" content="https://schmelczer.dev/reconcile" />
|
|
||||||
<meta property="og:image" content="https://schmelczer.dev/reconcile/og-image.png" />
|
|
||||||
<meta property="og:image:width" content="1200" />
|
|
||||||
<meta property="og:image:height" content="630" />
|
|
||||||
<meta name="twitter:card" content="summary_large_image" />
|
|
||||||
<link rel="icon" type="image/x-icon" href="favicon.ico" />
|
|
||||||
<title>reconcile-text: conflict-free 3-way text merging</title>
|
|
||||||
<link inline inline-asset="index.css" inline-asset-delete />
|
|
||||||
<script
|
|
||||||
defer
|
|
||||||
data-domain="reconcile"
|
|
||||||
data-api="https://stats.schmelczer.dev/status"
|
|
||||||
src="https://stats.schmelczer.dev/js/script.outbound-links.js"
|
|
||||||
></script>
|
|
||||||
</head>
|
|
||||||
<body>
|
|
||||||
<div class="background"></div>
|
|
||||||
|
|
||||||
<div class="scroll-container">
|
|
||||||
<div class="page-wrapper">
|
|
||||||
<header>
|
|
||||||
<h1><code>reconcile-text</code>: conflict-free 3-way text merging</h1>
|
|
||||||
<p>
|
|
||||||
Think
|
|
||||||
<a
|
|
||||||
href="https://www.gnu.org/software/diffutils/manual/html_node/Invoking-diff3.html"
|
|
||||||
target="_blank"
|
|
||||||
rel="noopener noreferrer"
|
|
||||||
>diff3</a
|
|
||||||
>
|
|
||||||
(or more specifically, <code>git merge</code>), but with intelligent conflict
|
|
||||||
resolution that requires no user intervention. The
|
|
||||||
<a
|
|
||||||
href="https://github.com/schmelczer/reconcile"
|
|
||||||
target="_blank"
|
|
||||||
rel="noopener noreferrer"
|
|
||||||
>reconcile-text</a
|
|
||||||
>
|
|
||||||
library tackles a fundamental challenge in collaborative editing: what happens
|
|
||||||
when multiple users edit the same text simultaneously, but the conflict
|
|
||||||
resolver only has access to the final results, not the intermediate steps?
|
|
||||||
</p>
|
|
||||||
|
|
||||||
<p>
|
|
||||||
Where traditional merge tools leave you with conflict markers to resolve
|
|
||||||
manually, <code>reconcile-text</code> automatically weaves changes together.
|
|
||||||
The <code>reconcile(parent, left, right)</code> function takes conflicting
|
|
||||||
edits and produces clean, unified results using an algorithm inspired by
|
|
||||||
Operational Transformation. No more
|
|
||||||
<code><<<<<<<</code> markers cluttering your text.
|
|
||||||
</p>
|
|
||||||
|
|
||||||
<p>
|
|
||||||
The process starts with your chosen tokenisation strategy, then applies Myers'
|
|
||||||
2-way diff algorithm to compare the original with both modified versions.
|
|
||||||
These diffs are optimised and transformed to preserve the longest meaningful
|
|
||||||
changes, before a final merge strategy combines all insertions and deletions
|
|
||||||
without losing any edits. Cursor positions can be tracked and updated during
|
|
||||||
merging as well.
|
|
||||||
</p>
|
|
||||||
|
|
||||||
<p>
|
|
||||||
Ready to dive deeper? Check out the
|
|
||||||
<a
|
|
||||||
href="https://github.com/schmelczer/reconcile"
|
|
||||||
target="_blank"
|
|
||||||
rel="noopener noreferrer"
|
|
||||||
>documentation</a
|
|
||||||
>
|
|
||||||
or try editing the text boxes below to see <code>reconcile-text</code> in
|
|
||||||
action. Use the tokenisation options to experiment with different approaches -
|
|
||||||
the Rust library also supports custom tokenisers.
|
|
||||||
</p>
|
|
||||||
</header>
|
|
||||||
|
|
||||||
<main>
|
|
||||||
<section class="tokenizer-selector">
|
|
||||||
<div class="radio-group" role="radiogroup" aria-label="Tokenization strategy">
|
|
||||||
<label class="radio-option">
|
|
||||||
<input
|
|
||||||
type="radio"
|
|
||||||
name="tokenizer"
|
|
||||||
value="Character"
|
|
||||||
id="tokenizer-character"
|
|
||||||
/>
|
|
||||||
<span class="radio-custom" aria-hidden="true"></span>
|
|
||||||
<div class="radio-content">
|
|
||||||
<span class="radio-label">Character</span>
|
|
||||||
<span class="radio-description">Fine-grained merging</span>
|
|
||||||
</div>
|
|
||||||
</label>
|
|
||||||
<label class="radio-option">
|
|
||||||
<input type="radio" name="tokenizer" value="Word" id="tokenizer-word" />
|
|
||||||
<span class="radio-custom" aria-hidden="true"></span>
|
|
||||||
<div class="radio-content">
|
|
||||||
<span class="radio-label">Word</span>
|
|
||||||
<span class="radio-description">Retain full words (default)</span>
|
|
||||||
</div>
|
|
||||||
</label>
|
|
||||||
<label class="radio-option">
|
|
||||||
<input
|
|
||||||
type="radio"
|
|
||||||
name="tokenizer"
|
|
||||||
value="Markdown"
|
|
||||||
id="tokenizer-markdown"
|
|
||||||
checked
|
|
||||||
/>
|
|
||||||
<span class="radio-custom" aria-hidden="true"></span>
|
|
||||||
<div class="radio-content">
|
|
||||||
<span class="radio-label">Markdown</span>
|
|
||||||
<span class="radio-description">Preserve formatting</span>
|
|
||||||
</div>
|
|
||||||
</label>
|
|
||||||
</div>
|
|
||||||
</section>
|
|
||||||
|
|
||||||
<div class="text-area-card diamond-parent">
|
|
||||||
<label
|
|
||||||
for="original"
|
|
||||||
title="The original text before any concurrent edits were made."
|
|
||||||
>Original</label
|
|
||||||
>
|
|
||||||
<textarea id="original" name="original"></textarea>
|
|
||||||
</div>
|
|
||||||
|
|
||||||
<div class="text-area-card diamond-left">
|
|
||||||
<label
|
|
||||||
for="left"
|
|
||||||
title="First user's edits - changes from this box appear in green in the result."
|
|
||||||
>
|
|
||||||
First user's edits
|
|
||||||
<div class="box Left"></div>
|
|
||||||
</label>
|
|
||||||
<textarea id="left" name="left"></textarea>
|
|
||||||
</div>
|
|
||||||
|
|
||||||
<div class="text-area-card diamond-right">
|
|
||||||
<label
|
|
||||||
for="right"
|
|
||||||
title="Second user's edits - changes from this box appear in blue in the result."
|
|
||||||
>
|
|
||||||
Second user's edits
|
|
||||||
<div class="box Right"></div>
|
|
||||||
</label>
|
|
||||||
<textarea id="right" name="right"></textarea>
|
|
||||||
</div>
|
|
||||||
|
|
||||||
<div class="text-area-card diamond-result">
|
|
||||||
<label
|
|
||||||
for="merged"
|
|
||||||
title="The automatically merged result - edit the boxes above to see changes in real-time."
|
|
||||||
>
|
|
||||||
Merged result
|
|
||||||
<svg
|
|
||||||
xmlns="http://www.w3.org/2000/svg"
|
|
||||||
width="24"
|
|
||||||
height="24"
|
|
||||||
viewBox="0 0 24 24"
|
|
||||||
fill="none"
|
|
||||||
stroke="currentColor"
|
|
||||||
stroke-width="2"
|
|
||||||
stroke-linecap="round"
|
|
||||||
stroke-linejoin="round"
|
|
||||||
aria-hidden="true"
|
|
||||||
>
|
|
||||||
<path stroke="none" d="M0 0h24v24H0z" fill="none"></path>
|
|
||||||
<path
|
|
||||||
d="M10 10l-6 6v4h4l6 -6m1.99 -1.99l2.504 -2.504a2.828 2.828 0 1 0 -4 -4l-2.5 2.5"
|
|
||||||
></path>
|
|
||||||
<path d="M13.5 6.5l4 4"></path>
|
|
||||||
<path d="M3 3l18 18"></path>
|
|
||||||
</svg>
|
|
||||||
</label>
|
|
||||||
<div id="merged" role="textbox" aria-readonly="true" aria-live="off"></div>
|
|
||||||
</div>
|
|
||||||
</main>
|
|
||||||
|
|
||||||
<footer>
|
|
||||||
<p>© 2025-2026 András Schmelczer</p>
|
|
||||||
<div class="footer-links">
|
|
||||||
<a
|
|
||||||
href="https://www.npmjs.com/package/reconcile-text"
|
|
||||||
target="_blank"
|
|
||||||
rel="noopener noreferrer"
|
|
||||||
aria-label="npm package"
|
|
||||||
>
|
|
||||||
<svg
|
|
||||||
xmlns="http://www.w3.org/2000/svg"
|
|
||||||
viewBox="0 0 24 24"
|
|
||||||
fill="currentColor"
|
|
||||||
>
|
|
||||||
<path
|
|
||||||
d="M1.763 0C.786 0 0 .786 0 1.763v20.474C0 23.214.786 24 1.763 24h20.474c.977 0 1.763-.786 1.763-1.763V1.763C24 .786 23.214 0 22.237 0zM5.13 5.323l13.837.019-.009 13.836h-3.464l.01-10.382h-3.456L12.04 19.17H5.113z"
|
|
||||||
/>
|
|
||||||
</svg>
|
|
||||||
</a>
|
|
||||||
<a
|
|
||||||
href="https://pypi.org/project/reconcile-text/"
|
|
||||||
target="_blank"
|
|
||||||
rel="noopener noreferrer"
|
|
||||||
aria-label="PyPI package"
|
|
||||||
>
|
|
||||||
<svg
|
|
||||||
xmlns="http://www.w3.org/2000/svg"
|
|
||||||
viewBox="0 0 24 24"
|
|
||||||
fill="currentColor"
|
|
||||||
>
|
|
||||||
<path
|
|
||||||
d="M23.922 13.58v3.912L20.55 18.72l-.078.055.052.037 3.45-1.256.026-.036v-3.997l-.053-.036-.025.092zM23.621 5.618l-3.04 1.107v3.912l3.339-1.215V5.509zM23.92 13.457V9.544l-3.336 1.215v3.913zM20.47 14.71V10.8L17.17 12v3.913zM17.034 19.996v-3.912l-3.313 1.206v3.912zM17.17 16.057v3.868l3.314-1.206V14.85l-3.314 1.206zm2.093 1.882c-.367.134-.663-.074-.663-.463s.296-.814.663-.947c.365-.133.662.075.662.464s-.297.814-.662.946zM13.225 9.315l.365-.132-3.285-1.197-3.323 1.21.102.037 3.184 1.16zM20.507 10.664V6.751L17.17 7.965v3.913zM17.058 11.918V8.005l-3.302 1.202v3.912zM13.643 9.246l-3.336 1.215v3.913l3.336-1.215zM6.907 13.165l3.322 1.209v-3.913L6.907 9.252zM10.34 7.873l3.281 1.193V5.198l-3.28-1.193zM20.507 2.715L17.19 3.922v3.913l3.317-1.207zM16.95 3.903L13.724 2.73l-3.269 1.19 3.225 1.174zM15.365 4.606l-1.624.592v3.868l3.317-1.207V3.991l-1.693.615zm-.391 2.778c-.367.134-.662-.074-.662-.464s.295-.813.662-.946c.366-.133.663.074.663.464s-.297.813-.663.946zM10.229 18.41v-3.914l-3.322-1.209V17.2zM13.678 17.182v-3.913l-3.371 1.227v3.913zM13.756 17.154l3.3-1.2V12.04l-3.3 1.2zM13.678 21.217l-3.371 1.227v-3.912h-.078v3.912l-3.322-1.209v-3.913l-.053-.058-.025-.06-3.336-1.21v-3.948l.034.013 3.287 1.196.015-.078-3.261-1.187 3.26-1.187v-.109L3.876 9.62l-.307-.112 3.26-1.188v.877l.079-.055V6.769l3.257 1.185.058-.061L7.084 6.75l-.102-.037 3.24-1.179v-.083L6.854 6.677v.018l-.025.018v1.523L3.44 9.47v.02l-.025.017v4.007l-3.39 1.233v.019L0 14.784v3.995l.025.037 3.4 1.237.008-.006.007.01 3.4 1.238.008-.006.006.01 3.4 1.237.014-.009.012.01 3.45-1.256.026-.037-.078-.027zM3.493 9.563l3.257 1.185-3.257 1.187V9.562zM3.4 19.96L.078 18.752v-3.913l2.361.86.96.349v3.913zm.015-3.99L.335 14.85l-.182-.066 3.262-1.187v2.374zm3.399 5.231l-3.321-1.209v-3.912l3.321 1.209v3.912zM23.791 5.434l-3.21-1.17v2.338zM20.387 2.643l-3.24-1.18-3.27 1.19 3.247 1.182z"
|
|
||||||
/>
|
|
||||||
</svg>
|
|
||||||
</a>
|
|
||||||
<a
|
|
||||||
href="https://crates.io/crates/reconcile-text"
|
|
||||||
target="_blank"
|
|
||||||
rel="noopener noreferrer"
|
|
||||||
aria-label="crates.io crate"
|
|
||||||
>
|
|
||||||
<svg
|
|
||||||
xmlns="http://www.w3.org/2000/svg"
|
|
||||||
viewBox="0 0 24 24"
|
|
||||||
fill="currentColor"
|
|
||||||
>
|
|
||||||
<path
|
|
||||||
d="M23.8346 11.7033l-1.0073-.6236a13.7268 13.7268 0 00-.0283-.2936l.8656-.8069a.3483.3483 0 00-.1154-.578l-1.1066-.414a8.4958 8.4958 0 00-.087-.2856l.6904-.9587a.3462.3462 0 00-.2257-.5446l-1.1663-.1894a9.3574 9.3574 0 00-.1407-.2622l.49-1.0761a.3437.3437 0 00-.0274-.3361.3486.3486 0 00-.3006-.154l-1.1845.0416a6.7444 6.7444 0 00-.1873-.2268l.2723-1.153a.3472.3472 0 00-.417-.4172l-1.1532.2724a14.0183 14.0183 0 00-.2278-.1873l.0415-1.1845a.3442.3442 0 00-.49-.328l-1.076.491c-.0872-.0476-.1742-.0952-.2623-.1407l-.1903-1.1673A.3483.3483 0 0016.256.955l-.9597.6905a8.4867 8.4867 0 00-.2855-.086l-.414-1.1066a.3483.3483 0 00-.5781-.1154l-.8069.8666a9.2936 9.2936 0 00-.2936-.0284L12.2946.1683a.3462.3462 0 00-.5892 0l-.6236 1.0073a13.7383 13.7383 0 00-.2936.0284L9.9803.3374a.3462.3462 0 00-.578.1154l-.4141 1.1065c-.0962.0274-.1903.0567-.2855.086L7.744.955a.3483.3483 0 00-.5447.2258L7.009 2.348a9.3574 9.3574 0 00-.2622.1407l-1.0762-.491a.3462.3462 0 00-.49.328l.0416 1.1845a7.9826 7.9826 0 00-.2278.1873L3.8413 3.425a.3472.3472 0 00-.4171.4171l.2713 1.1531c-.0628.075-.1255.1509-.1863.2268l-1.1845-.0415a.3462.3462 0 00-.328.49l.491 1.0761a9.167 9.167 0 00-.1407.2622l-1.1662.1894a.3483.3483 0 00-.2258.5446l.6904.9587a13.303 13.303 0 00-.087.2855l-1.1065.414a.3483.3483 0 00-.1155.5781l.8656.807a9.2936 9.2936 0 00-.0283.2935l-1.0073.6236a.3442.3442 0 000 .5892l1.0073.6236c.008.0982.0182.1964.0283.2936l-.8656.8079a.3462.3462 0 00.1155.578l1.1065.4141c.0273.0962.0567.1914.087.2855l-.6904.9587a.3452.3452 0 00.2268.5447l1.1662.1893c.0456.088.0922.1751.1408.2622l-.491 1.0762a.3462.3462 0 00.328.49l1.1834-.0415c.0618.0769.1235.1528.1873.2277l-.2713 1.1541a.3462.3462 0 00.4171.4161l1.153-.2713c.075.0638.151.1255.2279.1863l-.0415 1.1845a.3442.3442 0 00.49.327l1.0761-.49c.087.0486.1741.0951.2622.1407l.1903 1.1662a.3483.3483 0 00.5447.2268l.9587-.6904a9.299 9.299 0 00.2855.087l.414 1.1066a.3452.3452 0 00.5781.1154l.8079-.8656c.0972.0111.1954.0203.2936.0294l.6236 1.0073a.3472.3472 0 00.5892 0l.6236-1.0073c.0982-.0091.1964-.0183.2936-.0294l.8069.8656a.3483.3483 0 00.578-.1154l.4141-1.1066a8.4626 8.4626 0 00.2855-.087l.9587.6904a.3452.3452 0 00.5447-.2268l.1903-1.1662c.088-.0456.1751-.0931.2622-.1407l1.0762.49a.3472.3472 0 00.49-.327l-.0415-1.1845a6.7267 6.7267 0 00.2267-.1863l1.1531.2713a.3472.3472 0 00.4171-.416l-.2713-1.1542c.0628-.0749.1255-.1508.1863-.2278l1.1845.0415a.3442.3442 0 00.328-.49l-.49-1.076c.0475-.0872.0951-.1742.1407-.2623l1.1662-.1893a.3483.3483 0 00.2258-.5447l-.6904-.9587.087-.2855 1.1066-.414a.3462.3462 0 00.1154-.5781l-.8656-.8079c.0101-.0972.0202-.1954.0283-.2936l1.0073-.6236a.3442.3442 0 000-.5892zm-6.7413 8.3551a.7138.7138 0 01.2986-1.396.714.714 0 11-.2997 1.396zm-.3422-2.3142a.649.649 0 00-.7715.5l-.3573 1.6685c-1.1035.501-2.3285.7795-3.6193.7795a8.7368 8.7368 0 01-3.6951-.814l-.3574-1.6684a.648.648 0 00-.7714-.499l-1.473.3158a8.7216 8.7216 0 01-.7613-.898h7.1676c.081 0 .1356-.0141.1356-.088v-2.536c0-.074-.0536-.0881-.1356-.0881h-2.0966v-1.6077h2.2677c.2065 0 1.1065.0587 1.394 1.2088.0901.3533.2875 1.5044.4232 1.8729.1346.413.6833 1.2381 1.2685 1.2381h3.5716a.7492.7492 0 00.1296-.0131 8.7874 8.7874 0 01-.8119.9526zM6.8369 20.024a.714.714 0 11-.2997-1.396.714.714 0 01.2997 1.396zM4.1177 8.9972a.7137.7137 0 11-1.304.5791.7137.7137 0 011.304-.579zm-.8352 1.9813l1.5347-.6824a.65.65 0 00.33-.8585l-.3158-.7147h1.2432v5.6025H3.5669a8.7753 8.7753 0 01-.2834-3.348zm6.7343-.5437V8.7836h2.9601c.153 0 1.0792.1772 1.0792.8697 0 .575-.7107.7815-1.2948.7815zm10.7574 1.4862c0 .2187-.008.4363-.0243.651h-.9c-.09 0-.1265.0586-.1265.1477v.413c0 .973-.5487 1.1846-1.0296 1.2382-.4576.0517-.9648-.1913-1.0275-.4717-.2704-1.5186-.7198-1.8436-1.4305-2.4034.8817-.5599 1.799-1.386 1.799-2.4915 0-1.1936-.819-1.9458-1.3769-2.3153-.7825-.5163-1.6491-.6195-1.883-.6195H5.4682a8.7651 8.7651 0 014.907-2.7699l1.0974 1.151a.648.648 0 00.9182.0213l1.227-1.1743a8.7753 8.7753 0 016.0044 4.2762l-.8403 1.8982a.652.652 0 00.33.8585l1.6178.7188c.0283.2875.0425.577.0425.8717zm-9.3006-9.5993a.7128.7128 0 11.984 1.0316.7137.7137 0 01-.984-1.0316zm8.3389 6.71a.7107.7107 0 01.9395-.3625.7137.7137 0 11-.9405.3635z"
|
|
||||||
/>
|
|
||||||
</svg>
|
|
||||||
</a>
|
|
||||||
<a
|
|
||||||
href="https://github.com/schmelczer/reconcile"
|
|
||||||
target="_blank"
|
|
||||||
rel="noopener noreferrer"
|
|
||||||
aria-label="GitHub repository"
|
|
||||||
>
|
|
||||||
<svg
|
|
||||||
xmlns="http://www.w3.org/2000/svg"
|
|
||||||
width="24"
|
|
||||||
height="24"
|
|
||||||
viewBox="0 0 24 24"
|
|
||||||
fill="none"
|
|
||||||
stroke="currentColor"
|
|
||||||
stroke-width="2"
|
|
||||||
stroke-linecap="round"
|
|
||||||
stroke-linejoin="round"
|
|
||||||
>
|
|
||||||
<path stroke="none" d="M0 0h24v24H0z" fill="none" />
|
|
||||||
<path
|
|
||||||
d="M9 19c-4.3 1.4 -4.3 -2.5 -6 -3m12 5v-3.5c0 -1 .1 -1.4 -.5 -2c2.8 -.3 5.5 -1.4 5.5 -6a4.6 4.6 0 0 0 -1.3 -3.2a4.2 4.2 0 0 0 -.1 -3.2s-1.1 -.3 -3.5 1.3a12.3 12.3 0 0 0 -6.2 0c-2.4 -1.6 -3.5 -1.3 -3.5 -1.3a4.2 4.2 0 0 0 -.1 3.2a4.6 4.6 0 0 0 -1.3 3.2c0 4.6 2.7 5.7 5.5 6c-.6 .6 -.6 1.2 -.5 2v3.5"
|
|
||||||
/>
|
|
||||||
</svg>
|
|
||||||
</a>
|
|
||||||
</div>
|
|
||||||
</footer>
|
|
||||||
</div>
|
|
||||||
</div>
|
|
||||||
|
|
||||||
<noscript>JavaScript is required for this website to function properly.</noscript>
|
|
||||||
|
|
||||||
<script inline inline-asset="index.js" inline-asset-delete></script>
|
|
||||||
</body>
|
|
||||||
</html>
|
|
||||||
|
|
@ -1,218 +0,0 @@
|
||||||
import { reconcileWithHistory } from 'reconcile-text';
|
|
||||||
import type { BuiltinTokenizer } from 'reconcile-text';
|
|
||||||
import './style.scss';
|
|
||||||
|
|
||||||
const originalTextArea = document.getElementById('original') as HTMLTextAreaElement;
|
|
||||||
const leftTextArea = document.getElementById('left') as HTMLTextAreaElement;
|
|
||||||
const rightTextArea = document.getElementById('right') as HTMLTextAreaElement;
|
|
||||||
const mergedTextArea = document.getElementById('merged') as HTMLDivElement;
|
|
||||||
const tokenizerRadios = document.querySelectorAll(
|
|
||||||
'input[name="tokenizer"]'
|
|
||||||
) as NodeListOf<HTMLInputElement>;
|
|
||||||
|
|
||||||
const sampleText = `The reconcile-text library is embedded on this page as a WASM module and powers these text boxes. Experiment with changing the "Original", "First user's edit", and "Second user's edit" text boxes to see competing changes get merged in real-time within the "Merged result" box.
|
|
||||||
|
|
||||||
Here, you will see color-coded tokens marking the origin of each token, including ones that got deleted. The result highly depends on the tokenisation strategy which may be:
|
|
||||||
- Character-based
|
|
||||||
- Word-based`;
|
|
||||||
|
|
||||||
let pendingUpdate: number | null = null;
|
|
||||||
function scheduleUpdate(): void {
|
|
||||||
if (pendingUpdate === null) {
|
|
||||||
pendingUpdate = requestAnimationFrame(() => {
|
|
||||||
pendingUpdate = null;
|
|
||||||
updateMergedText();
|
|
||||||
});
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
async function main(): Promise<void> {
|
|
||||||
originalTextArea.addEventListener('input', scheduleUpdate);
|
|
||||||
leftTextArea.addEventListener('input', scheduleUpdate);
|
|
||||||
rightTextArea.addEventListener('input', scheduleUpdate);
|
|
||||||
|
|
||||||
document.addEventListener('selectionchange', () => {
|
|
||||||
if (
|
|
||||||
document.activeElement === leftTextArea ||
|
|
||||||
document.activeElement === rightTextArea
|
|
||||||
) {
|
|
||||||
scheduleUpdate();
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
window.addEventListener('resize', resizeTextAreas);
|
|
||||||
|
|
||||||
tokenizerRadios.forEach((radio) => {
|
|
||||||
radio.addEventListener('change', scheduleUpdate);
|
|
||||||
});
|
|
||||||
|
|
||||||
loadSample();
|
|
||||||
updateMergedText();
|
|
||||||
}
|
|
||||||
|
|
||||||
// Edit the instructions to generate example edits
|
|
||||||
function loadSample(): void {
|
|
||||||
originalTextArea.value = sampleText;
|
|
||||||
leftTextArea.value =
|
|
||||||
sampleText.replace('color', 'colour') +
|
|
||||||
"\n- Line-based\n\nCheck out what's the most complex conflict you can come up with!";
|
|
||||||
rightTextArea.value =
|
|
||||||
sampleText.replace(', for example,', ' such as').replace('WASM', 'WebAssembly') +
|
|
||||||
'\n- Or your custom tokeniser';
|
|
||||||
}
|
|
||||||
|
|
||||||
function updateMergedText(): void {
|
|
||||||
resizeTextAreas();
|
|
||||||
|
|
||||||
const original = originalTextArea.value;
|
|
||||||
const left = leftTextArea.value;
|
|
||||||
const right = rightTextArea.value;
|
|
||||||
|
|
||||||
const selectedTokenizer = getSelectedTokenizer();
|
|
||||||
|
|
||||||
const { leftCursors, rightCursors } = getCursorsFromActiveTextArea();
|
|
||||||
|
|
||||||
const results = reconcileWithHistory(
|
|
||||||
original,
|
|
||||||
{
|
|
||||||
text: left,
|
|
||||||
cursors: leftCursors,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
text: right,
|
|
||||||
cursors: rightCursors,
|
|
||||||
},
|
|
||||||
selectedTokenizer
|
|
||||||
);
|
|
||||||
|
|
||||||
let selectionStart: number = Number.NEGATIVE_INFINITY;
|
|
||||||
let selectionEnd: number = Number.NEGATIVE_INFINITY;
|
|
||||||
if ((results.cursors?.length ?? 0) > 0) {
|
|
||||||
selectionStart = results.cursors![0].position;
|
|
||||||
selectionEnd = results.cursors![1].position;
|
|
||||||
}
|
|
||||||
const isSelection = selectionStart !== selectionEnd;
|
|
||||||
|
|
||||||
const selectionSide = leftCursors ? 'left' : 'right';
|
|
||||||
const fragment = document.createDocumentFragment();
|
|
||||||
|
|
||||||
let currentPosition = 0;
|
|
||||||
if (selectionEnd === 0) {
|
|
||||||
fragment.appendChild(createSelectionOverlay(selectionSide === 'left', isSelection));
|
|
||||||
}
|
|
||||||
|
|
||||||
for (const { text, history } of results.history) {
|
|
||||||
const isDelete = history === 'RemovedFromLeft' || history === 'RemovedFromRight';
|
|
||||||
let spanChars: string[] = [];
|
|
||||||
let currentClass = '';
|
|
||||||
|
|
||||||
const flushSpan = () => {
|
|
||||||
if (spanChars.length > 0) {
|
|
||||||
const span = document.createElement('span');
|
|
||||||
span.className = currentClass;
|
|
||||||
span.textContent = spanChars.join('');
|
|
||||||
fragment.appendChild(span);
|
|
||||||
spanChars = [];
|
|
||||||
}
|
|
||||||
};
|
|
||||||
|
|
||||||
for (const character of text) {
|
|
||||||
let className = history;
|
|
||||||
if (
|
|
||||||
!isDelete &&
|
|
||||||
selectionStart <= currentPosition &&
|
|
||||||
currentPosition < selectionEnd
|
|
||||||
) {
|
|
||||||
className += ` selection-${selectionSide}`;
|
|
||||||
}
|
|
||||||
|
|
||||||
if (className !== currentClass) {
|
|
||||||
flushSpan();
|
|
||||||
currentClass = className;
|
|
||||||
}
|
|
||||||
spanChars.push(character);
|
|
||||||
|
|
||||||
if (!isDelete) {
|
|
||||||
if (currentPosition === selectionEnd - 1) {
|
|
||||||
flushSpan();
|
|
||||||
fragment.appendChild(
|
|
||||||
createSelectionOverlay(selectionSide === 'left', isSelection)
|
|
||||||
);
|
|
||||||
}
|
|
||||||
currentPosition++;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
flushSpan();
|
|
||||||
}
|
|
||||||
|
|
||||||
mergedTextArea.innerHTML = '';
|
|
||||||
mergedTextArea.appendChild(fragment);
|
|
||||||
}
|
|
||||||
|
|
||||||
function getCursorsFromActiveTextArea() {
|
|
||||||
const activeElement = document.activeElement;
|
|
||||||
let leftCursors = undefined;
|
|
||||||
let rightCursors = undefined;
|
|
||||||
|
|
||||||
if (activeElement === leftTextArea) {
|
|
||||||
leftCursors = [
|
|
||||||
{ id: 1, position: leftTextArea.selectionStart },
|
|
||||||
{ id: 2, position: leftTextArea.selectionEnd },
|
|
||||||
];
|
|
||||||
} else if (activeElement === rightTextArea) {
|
|
||||||
rightCursors = [
|
|
||||||
{ id: 1, position: rightTextArea.selectionStart },
|
|
||||||
{ id: 2, position: rightTextArea.selectionEnd },
|
|
||||||
];
|
|
||||||
}
|
|
||||||
return { leftCursors, rightCursors };
|
|
||||||
}
|
|
||||||
|
|
||||||
function createSelectionOverlay(isLeft: boolean, isSelection: boolean): HTMLSpanElement {
|
|
||||||
const caretSpan = document.createElement('span');
|
|
||||||
caretSpan.className = `selection-caret selection-caret-${isLeft ? 'left' : 'right'}`;
|
|
||||||
|
|
||||||
const stickDiv = document.createElement('div');
|
|
||||||
stickDiv.className = 'stick';
|
|
||||||
caretSpan.appendChild(stickDiv);
|
|
||||||
|
|
||||||
const dotDiv = document.createElement('div');
|
|
||||||
dotDiv.className = 'dot';
|
|
||||||
caretSpan.appendChild(dotDiv);
|
|
||||||
|
|
||||||
const infoDiv = document.createElement('div');
|
|
||||||
infoDiv.className = 'info';
|
|
||||||
const selectionType = isSelection ? 'selection' : 'cursor';
|
|
||||||
infoDiv.textContent = isLeft
|
|
||||||
? `Left user's ${selectionType}`
|
|
||||||
: `Right user's ${selectionType}`;
|
|
||||||
caretSpan.appendChild(infoDiv);
|
|
||||||
|
|
||||||
return caretSpan;
|
|
||||||
}
|
|
||||||
|
|
||||||
function getSelectedTokenizer(): BuiltinTokenizer {
|
|
||||||
const selectedRadio = Array.from(tokenizerRadios).find((radio) => radio.checked);
|
|
||||||
return (selectedRadio?.value ?? 'Markdown') as BuiltinTokenizer;
|
|
||||||
}
|
|
||||||
|
|
||||||
function resizeTextAreas(): void {
|
|
||||||
// Only auto-resize if field-sizing CSS property is not supported, like in Safari as of now
|
|
||||||
if (!CSS.supports('field-sizing', 'content')) {
|
|
||||||
autoResize(originalTextArea);
|
|
||||||
autoResize(leftTextArea);
|
|
||||||
autoResize(rightTextArea);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
function autoResize(textarea: HTMLTextAreaElement): void {
|
|
||||||
textarea.style.height = 'auto';
|
|
||||||
textarea.style.height = textarea.scrollHeight + 'px';
|
|
||||||
}
|
|
||||||
|
|
||||||
main().catch((error) => {
|
|
||||||
document.body.textContent =
|
|
||||||
'Failed to load the application. Please ensure your browser supports WebAssembly.';
|
|
||||||
console.error(error);
|
|
||||||
});
|
|
||||||
Binary file not shown.
|
Before Width: | Height: | Size: 47 KiB |
|
|
@ -1,507 +0,0 @@
|
||||||
@use 'sass:color';
|
|
||||||
|
|
||||||
// Colour palette
|
|
||||||
$primary-blue: #2451a6;
|
|
||||||
$light-blue: #85bff7;
|
|
||||||
$green: #12d197;
|
|
||||||
$text-primary: #23272f;
|
|
||||||
$text-secondary: #5a6272;
|
|
||||||
$border-grey: #d1d5db;
|
|
||||||
$code-bg: #61769a;
|
|
||||||
$code-text: #e2e8f0;
|
|
||||||
$white: #fff;
|
|
||||||
$light-bg: #f8fafc;
|
|
||||||
$gradient-end: #e0e7ef;
|
|
||||||
|
|
||||||
// Function to create selection colour with opacity
|
|
||||||
@function selection-colour($colour, $opacity: 0.3) {
|
|
||||||
@return rgba($colour, $opacity);
|
|
||||||
}
|
|
||||||
|
|
||||||
@function caret-colour($colour, $amount: 20%) {
|
|
||||||
@return color.adjust($colour, $lightness: -$amount);
|
|
||||||
}
|
|
||||||
|
|
||||||
* {
|
|
||||||
box-sizing: border-box;
|
|
||||||
margin: 0;
|
|
||||||
user-select: none;
|
|
||||||
}
|
|
||||||
|
|
||||||
html,
|
|
||||||
body {
|
|
||||||
height: 100%;
|
|
||||||
}
|
|
||||||
|
|
||||||
body {
|
|
||||||
font-family: 'Segoe UI', Arial, sans-serif;
|
|
||||||
color: $text-primary;
|
|
||||||
}
|
|
||||||
|
|
||||||
.scroll-container {
|
|
||||||
height: 100vh;
|
|
||||||
height: 100dvh;
|
|
||||||
overflow-y: auto;
|
|
||||||
overflow-x: hidden;
|
|
||||||
}
|
|
||||||
|
|
||||||
.background {
|
|
||||||
background: linear-gradient(135deg, $light-bg 0%, $gradient-end 100%);
|
|
||||||
position: fixed;
|
|
||||||
top: 0;
|
|
||||||
left: 0;
|
|
||||||
width: 100vw;
|
|
||||||
height: 100vh;
|
|
||||||
z-index: -1;
|
|
||||||
}
|
|
||||||
|
|
||||||
.page-wrapper {
|
|
||||||
display: flex;
|
|
||||||
flex-direction: column;
|
|
||||||
justify-content: space-between;
|
|
||||||
min-height: 100%;
|
|
||||||
max-width: 1000px;
|
|
||||||
margin: 0 auto;
|
|
||||||
}
|
|
||||||
|
|
||||||
header {
|
|
||||||
padding: 32px 32px 0 32px;
|
|
||||||
}
|
|
||||||
|
|
||||||
header > h1 {
|
|
||||||
font-size: 2.5rem;
|
|
||||||
font-weight: 700;
|
|
||||||
color: $primary-blue;
|
|
||||||
margin-bottom: 24px;
|
|
||||||
text-align: center;
|
|
||||||
}
|
|
||||||
|
|
||||||
h1,
|
|
||||||
code,
|
|
||||||
p,
|
|
||||||
p * {
|
|
||||||
user-select: text;
|
|
||||||
}
|
|
||||||
|
|
||||||
code {
|
|
||||||
background: $code-bg;
|
|
||||||
color: $code-text;
|
|
||||||
padding: 2px 6px;
|
|
||||||
border-radius: 4px;
|
|
||||||
font-family: 'SF Mono', 'Monaco', 'Inconsolata', 'Roboto Mono', 'Consolas', monospace;
|
|
||||||
font-size: 0.875em;
|
|
||||||
font-weight: 500;
|
|
||||||
}
|
|
||||||
|
|
||||||
header > p {
|
|
||||||
color: $text-secondary;
|
|
||||||
font-size: 1.1rem;
|
|
||||||
margin-bottom: 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
header > p:not(:first-of-type) {
|
|
||||||
margin-top: 16px;
|
|
||||||
}
|
|
||||||
|
|
||||||
main {
|
|
||||||
display: grid;
|
|
||||||
grid-template-rows: min-content min-content min-content;
|
|
||||||
grid-template-columns: 1fr 1fr;
|
|
||||||
gap: 20px;
|
|
||||||
justify-items: center;
|
|
||||||
align-items: center;
|
|
||||||
padding: 32px;
|
|
||||||
}
|
|
||||||
|
|
||||||
.tokenizer-selector {
|
|
||||||
grid-column: 1 / -1;
|
|
||||||
grid-row: 1;
|
|
||||||
width: 100%;
|
|
||||||
margin-bottom: 8px;
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-group {
|
|
||||||
display: flex;
|
|
||||||
gap: 16px;
|
|
||||||
justify-content: center;
|
|
||||||
flex-wrap: wrap;
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-option {
|
|
||||||
display: flex;
|
|
||||||
align-items: center;
|
|
||||||
gap: 12px;
|
|
||||||
padding: 16px 20px;
|
|
||||||
background: $white;
|
|
||||||
border-radius: 12px;
|
|
||||||
box-shadow: 0 2px 8px selection-colour($primary-blue, 0.08);
|
|
||||||
cursor: pointer;
|
|
||||||
transition: all 0.2s ease;
|
|
||||||
border: 2px solid transparent;
|
|
||||||
min-width: 180px;
|
|
||||||
position: relative;
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-option:hover {
|
|
||||||
box-shadow: 0 4px 16px selection-colour($primary-blue, 0.12);
|
|
||||||
transform: translateY(-2px);
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-option:has(input:checked) {
|
|
||||||
background: $gradient-end;
|
|
||||||
border-color: $primary-blue;
|
|
||||||
box-shadow: 0 4px 16px selection-colour($primary-blue, 0.16);
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-option input[type='radio'] {
|
|
||||||
position: absolute;
|
|
||||||
opacity: 0;
|
|
||||||
pointer-events: none;
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-custom {
|
|
||||||
width: 20px;
|
|
||||||
height: 20px;
|
|
||||||
border: 2px solid $border-grey;
|
|
||||||
border-radius: 50%;
|
|
||||||
position: relative;
|
|
||||||
transition: all 0.2s ease;
|
|
||||||
flex-shrink: 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-option:has(input:checked) .radio-custom {
|
|
||||||
border-color: $primary-blue;
|
|
||||||
background: $primary-blue;
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-custom::after {
|
|
||||||
content: '';
|
|
||||||
position: absolute;
|
|
||||||
top: 50%;
|
|
||||||
left: 50%;
|
|
||||||
transform: translate(-50%, -50%) scale(0);
|
|
||||||
width: 8px;
|
|
||||||
height: 8px;
|
|
||||||
border-radius: 50%;
|
|
||||||
background: white;
|
|
||||||
transition: transform 0.2s ease;
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-option:has(input:checked) .radio-custom::after {
|
|
||||||
transform: translate(-50%, -50%) scale(1);
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-content {
|
|
||||||
display: flex;
|
|
||||||
flex-direction: column;
|
|
||||||
gap: 2px;
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-label {
|
|
||||||
font-weight: 600;
|
|
||||||
color: $primary-blue;
|
|
||||||
font-size: 0.95rem;
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-description {
|
|
||||||
font-size: 0.8rem;
|
|
||||||
color: $text-primary;
|
|
||||||
line-height: 1.2;
|
|
||||||
}
|
|
||||||
|
|
||||||
.diamond-parent {
|
|
||||||
grid-column: 1 / -1;
|
|
||||||
grid-row: 2;
|
|
||||||
}
|
|
||||||
|
|
||||||
.diamond-left {
|
|
||||||
grid-column: 1;
|
|
||||||
grid-row: 3;
|
|
||||||
}
|
|
||||||
|
|
||||||
.diamond-right {
|
|
||||||
grid-column: 2;
|
|
||||||
grid-row: 3;
|
|
||||||
}
|
|
||||||
|
|
||||||
.diamond-result {
|
|
||||||
grid-column: 1 / -1;
|
|
||||||
grid-row: 4;
|
|
||||||
}
|
|
||||||
|
|
||||||
.diamond-result label {
|
|
||||||
display: flex;
|
|
||||||
align-items: center;
|
|
||||||
}
|
|
||||||
|
|
||||||
.diamond-result svg {
|
|
||||||
width: 20px;
|
|
||||||
height: 20px;
|
|
||||||
margin-left: 8px;
|
|
||||||
}
|
|
||||||
|
|
||||||
.text-area-card {
|
|
||||||
width: 100%;
|
|
||||||
height: 100%;
|
|
||||||
background: $white;
|
|
||||||
border-radius: 10px;
|
|
||||||
box-shadow: 0 2px 12px 0 selection-colour($primary-blue, 0.06);
|
|
||||||
padding: 18px 20px 16px 20px;
|
|
||||||
margin-bottom: 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
label {
|
|
||||||
display: inline-block;
|
|
||||||
margin-bottom: 8px;
|
|
||||||
font-weight: 600;
|
|
||||||
color: $primary-blue;
|
|
||||||
cursor: help;
|
|
||||||
}
|
|
||||||
|
|
||||||
.box {
|
|
||||||
width: 1ch;
|
|
||||||
height: 1ch;
|
|
||||||
border-radius: 50%;
|
|
||||||
margin-left: 6px;
|
|
||||||
display: inline-block;
|
|
||||||
transform: scale(1.5);
|
|
||||||
}
|
|
||||||
|
|
||||||
textarea {
|
|
||||||
width: 100%;
|
|
||||||
border: none;
|
|
||||||
font-size: 1rem;
|
|
||||||
font-family: inherit;
|
|
||||||
color: $text-primary;
|
|
||||||
box-sizing: border-box;
|
|
||||||
resize: none;
|
|
||||||
outline: none;
|
|
||||||
margin-bottom: 0;
|
|
||||||
field-sizing: content; /* Doesn't work in Safari yet */
|
|
||||||
}
|
|
||||||
|
|
||||||
#merged {
|
|
||||||
width: 100%;
|
|
||||||
user-select: text;
|
|
||||||
|
|
||||||
> * {
|
|
||||||
position: relative;
|
|
||||||
white-space: pre-wrap;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
.Unchanged {
|
|
||||||
user-select: text;
|
|
||||||
}
|
|
||||||
|
|
||||||
.Left,
|
|
||||||
.AddedFromLeft,
|
|
||||||
.RemovedFromLeft {
|
|
||||||
user-select: text;
|
|
||||||
background: $green;
|
|
||||||
}
|
|
||||||
|
|
||||||
.selection-left::after,
|
|
||||||
.selection-right::after {
|
|
||||||
content: '';
|
|
||||||
position: absolute;
|
|
||||||
top: 0;
|
|
||||||
left: 0;
|
|
||||||
width: 100%;
|
|
||||||
height: 100%;
|
|
||||||
}
|
|
||||||
|
|
||||||
.selection-left::after {
|
|
||||||
background: selection-colour($green);
|
|
||||||
}
|
|
||||||
|
|
||||||
.selection-right::after {
|
|
||||||
background: selection-colour($light-blue);
|
|
||||||
}
|
|
||||||
|
|
||||||
.Right,
|
|
||||||
.AddedFromRight,
|
|
||||||
.RemovedFromRight {
|
|
||||||
user-select: text;
|
|
||||||
background: $light-blue;
|
|
||||||
}
|
|
||||||
|
|
||||||
.RemovedFromLeft,
|
|
||||||
.RemovedFromRight {
|
|
||||||
user-select: none;
|
|
||||||
text-decoration: line-through;
|
|
||||||
}
|
|
||||||
|
|
||||||
// Selection caret styles
|
|
||||||
$CARET_WIDTH: 2;
|
|
||||||
$DOT_RADIUS: 4;
|
|
||||||
|
|
||||||
.selection-caret {
|
|
||||||
position: relative;
|
|
||||||
z-index: 1000;
|
|
||||||
|
|
||||||
&.selection-caret-left {
|
|
||||||
background: caret-colour($green);
|
|
||||||
}
|
|
||||||
|
|
||||||
&.selection-caret-right {
|
|
||||||
background: caret-colour($light-blue);
|
|
||||||
}
|
|
||||||
|
|
||||||
> * {
|
|
||||||
position: absolute;
|
|
||||||
background-color: inherit;
|
|
||||||
}
|
|
||||||
|
|
||||||
> .stick {
|
|
||||||
left: 0;
|
|
||||||
top: 0;
|
|
||||||
transform: translateX(-50%);
|
|
||||||
width: #{$CARET_WIDTH}px;
|
|
||||||
height: 100%;
|
|
||||||
display: block;
|
|
||||||
border-radius: calc(#{$CARET_WIDTH} / 2 * 1px);
|
|
||||||
animation: blink-stick 1s steps(1) infinite;
|
|
||||||
}
|
|
||||||
|
|
||||||
> .dot {
|
|
||||||
border-radius: 50%;
|
|
||||||
width: #{$DOT_RADIUS * 2}px;
|
|
||||||
height: #{$DOT_RADIUS * 2}px;
|
|
||||||
top: -#{$DOT_RADIUS}px;
|
|
||||||
left: -#{$DOT_RADIUS}px;
|
|
||||||
transition: opacity 0.3s ease-in-out;
|
|
||||||
transform-origin: bottom center;
|
|
||||||
box-sizing: border-box;
|
|
||||||
|
|
||||||
&::before {
|
|
||||||
content: '';
|
|
||||||
position: absolute;
|
|
||||||
top: 50%;
|
|
||||||
left: 50%;
|
|
||||||
transform: translate(-50%, -50%);
|
|
||||||
width: 30px;
|
|
||||||
height: 30px;
|
|
||||||
border-radius: 50%;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
&:hover > .dot {
|
|
||||||
opacity: 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
> .info {
|
|
||||||
top: -1.3em;
|
|
||||||
left: calc(-#{$CARET_WIDTH} / 2 * 1px);
|
|
||||||
font-size: 0.9em;
|
|
||||||
user-select: none;
|
|
||||||
color: white;
|
|
||||||
padding: 0 2px;
|
|
||||||
transition: opacity 0.3s ease-in-out;
|
|
||||||
opacity: 0;
|
|
||||||
white-space: nowrap;
|
|
||||||
border-radius: 3px 3px 3px 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
&:hover > .info {
|
|
||||||
opacity: 1;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
@keyframes blink-stick {
|
|
||||||
0%,
|
|
||||||
100% {
|
|
||||||
opacity: 1;
|
|
||||||
}
|
|
||||||
50% {
|
|
||||||
opacity: 0;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
@media (max-width: 900px) {
|
|
||||||
header {
|
|
||||||
padding: 32px 18px 0 18px;
|
|
||||||
}
|
|
||||||
|
|
||||||
header > h1 {
|
|
||||||
margin-bottom: 18px;
|
|
||||||
}
|
|
||||||
|
|
||||||
header > p {
|
|
||||||
font-size: 1rem;
|
|
||||||
}
|
|
||||||
|
|
||||||
main {
|
|
||||||
padding: 18px;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
@media (max-width: 768px) {
|
|
||||||
main {
|
|
||||||
grid-template-columns: 1fr;
|
|
||||||
grid-template-rows: auto auto auto auto auto;
|
|
||||||
}
|
|
||||||
|
|
||||||
.tokenizer-selector {
|
|
||||||
grid-column: 1;
|
|
||||||
grid-row: 1;
|
|
||||||
}
|
|
||||||
|
|
||||||
.diamond-parent {
|
|
||||||
grid-column: 1;
|
|
||||||
grid-row: 2;
|
|
||||||
}
|
|
||||||
|
|
||||||
.diamond-left {
|
|
||||||
grid-column: 1;
|
|
||||||
grid-row: 3;
|
|
||||||
}
|
|
||||||
|
|
||||||
.diamond-right {
|
|
||||||
grid-column: 1;
|
|
||||||
grid-row: 4;
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-group {
|
|
||||||
flex-direction: column;
|
|
||||||
gap: 12px;
|
|
||||||
}
|
|
||||||
|
|
||||||
.radio-option {
|
|
||||||
min-width: unset;
|
|
||||||
width: 100%;
|
|
||||||
}
|
|
||||||
|
|
||||||
.diamond-result {
|
|
||||||
grid-column: 1;
|
|
||||||
grid-row: 5;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
footer {
|
|
||||||
padding: 32px 16px;
|
|
||||||
width: 100%;
|
|
||||||
display: flex;
|
|
||||||
justify-content: center;
|
|
||||||
align-items: center;
|
|
||||||
gap: 24px;
|
|
||||||
color: $text-secondary;
|
|
||||||
}
|
|
||||||
|
|
||||||
.footer-links {
|
|
||||||
display: flex;
|
|
||||||
align-items: center;
|
|
||||||
gap: 16px;
|
|
||||||
}
|
|
||||||
|
|
||||||
.footer-links > a > svg {
|
|
||||||
color: $text-secondary;
|
|
||||||
width: 28px;
|
|
||||||
height: 28px;
|
|
||||||
transition: transform 0.2s;
|
|
||||||
}
|
|
||||||
|
|
||||||
.footer-links > a > svg:hover {
|
|
||||||
cursor: pointer;
|
|
||||||
transform: scale(1.15);
|
|
||||||
}
|
|
||||||
192
examples/website/style.css
Normal file
192
examples/website/style.css
Normal file
|
|
@ -0,0 +1,192 @@
|
||||||
|
* {
|
||||||
|
box-sizing: border-box;
|
||||||
|
margin: 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
html,
|
||||||
|
body {
|
||||||
|
height: 100%;
|
||||||
|
}
|
||||||
|
|
||||||
|
body {
|
||||||
|
font-family: "Segoe UI", Arial, sans-serif;
|
||||||
|
background: linear-gradient(135deg, #f8fafc 0%, #e0e7ef 100%);
|
||||||
|
color: #23272f;
|
||||||
|
display: flex;
|
||||||
|
flex-direction: column;
|
||||||
|
justify-content: space-between;
|
||||||
|
}
|
||||||
|
|
||||||
|
header {
|
||||||
|
padding: 32px 20px 0 20px;
|
||||||
|
|
||||||
|
text-align: center;
|
||||||
|
}
|
||||||
|
|
||||||
|
header > h1 {
|
||||||
|
font-size: 2.5rem;
|
||||||
|
font-weight: 700;
|
||||||
|
color: #2451a6;
|
||||||
|
margin-bottom: 8px;
|
||||||
|
}
|
||||||
|
|
||||||
|
header > p {
|
||||||
|
color: #5a6272;
|
||||||
|
font-size: 1.1rem;
|
||||||
|
margin-bottom: 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
main {
|
||||||
|
flex: 1;
|
||||||
|
display: grid;
|
||||||
|
grid-template-rows: auto auto auto;
|
||||||
|
grid-template-columns: 1fr auto 1fr;
|
||||||
|
gap: 20px;
|
||||||
|
justify-items: center;
|
||||||
|
align-items: center;
|
||||||
|
padding: 32px 12vw 32px 12vw;
|
||||||
|
min-height: 540px;
|
||||||
|
}
|
||||||
|
|
||||||
|
.diamond-parent {
|
||||||
|
grid-column: 1 / -1;
|
||||||
|
}
|
||||||
|
|
||||||
|
.diamond-left {
|
||||||
|
grid-column: 1;
|
||||||
|
grid-row: 2;
|
||||||
|
}
|
||||||
|
|
||||||
|
.diamond-right {
|
||||||
|
grid-column: 3;
|
||||||
|
grid-row: 2;
|
||||||
|
}
|
||||||
|
|
||||||
|
#merge-button {
|
||||||
|
grid-column: 2;
|
||||||
|
grid-row: 2;
|
||||||
|
padding: 12px 36px;
|
||||||
|
border: none;
|
||||||
|
border-radius: 8px;
|
||||||
|
background: linear-gradient(90deg, #2451a6 0%, #3486eb 100%);
|
||||||
|
color: #fff;
|
||||||
|
font-size: 1.15rem;
|
||||||
|
font-weight: 600;
|
||||||
|
box-shadow: 0 2px 12px 0 rgba(36, 81, 166, 0.08);
|
||||||
|
cursor: pointer;
|
||||||
|
align-self: center;
|
||||||
|
transition: transform 0.2s;
|
||||||
|
margin: 0 32px;
|
||||||
|
}
|
||||||
|
|
||||||
|
#merge-button:hover {
|
||||||
|
transform: scale(1.1);
|
||||||
|
}
|
||||||
|
|
||||||
|
.diamond-right {
|
||||||
|
grid-column: 3;
|
||||||
|
grid-row: 2;
|
||||||
|
}
|
||||||
|
|
||||||
|
.diamond-result {
|
||||||
|
grid-column: 1 / -1;
|
||||||
|
grid-row: 3;
|
||||||
|
display: flex;
|
||||||
|
align-items: center;
|
||||||
|
pointer-events: none;
|
||||||
|
}
|
||||||
|
|
||||||
|
.text-area {
|
||||||
|
display: flex;
|
||||||
|
flex-direction: column;
|
||||||
|
align-items: center;
|
||||||
|
width: 100%;
|
||||||
|
height: 100%;
|
||||||
|
background: #fff;
|
||||||
|
border-radius: 10px;
|
||||||
|
box-shadow: 0 2px 12px 0 rgba(36, 81, 166, 0.06);
|
||||||
|
padding: 18px 20px 16px 20px;
|
||||||
|
margin-bottom: 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
label {
|
||||||
|
margin-bottom: 8px;
|
||||||
|
font-weight: 600;
|
||||||
|
color: #2451a6;
|
||||||
|
}
|
||||||
|
|
||||||
|
textarea {
|
||||||
|
width: 100%;
|
||||||
|
border: none;
|
||||||
|
font-size: 1rem;
|
||||||
|
font-family: inherit;
|
||||||
|
color: #23272f;
|
||||||
|
box-sizing: border-box;
|
||||||
|
resize: none;
|
||||||
|
outline: none;
|
||||||
|
margin-bottom: 0;
|
||||||
|
height: 100%;
|
||||||
|
}
|
||||||
|
|
||||||
|
@media (max-width: 900px) {
|
||||||
|
main {
|
||||||
|
padding: 24px 2vw;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
@media (max-width: 768px) {
|
||||||
|
main {
|
||||||
|
grid-template-columns: 1fr;
|
||||||
|
grid-template-rows: auto auto auto auto auto;
|
||||||
|
}
|
||||||
|
.diamond-parent {
|
||||||
|
grid-row: 1;
|
||||||
|
grid-column: 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
.diamond-left {
|
||||||
|
grid-row: 2;
|
||||||
|
grid-column: 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
.diamond-right {
|
||||||
|
grid-row: 3;
|
||||||
|
grid-column: 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
#merge-button {
|
||||||
|
grid-row: 4;
|
||||||
|
grid-column: 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
.diamond-result {
|
||||||
|
grid-row: 5;
|
||||||
|
grid-column: 1;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
footer {
|
||||||
|
position: relative;
|
||||||
|
margin-top: 32px;
|
||||||
|
padding: 28px 0 18px 0;
|
||||||
|
text-align: center;
|
||||||
|
color: #5a6272;
|
||||||
|
font-size: 1rem;
|
||||||
|
box-shadow: 0 -4px 12px 0 rgba(28, 28, 87, 0.1),
|
||||||
|
0 -1px 2px 0 rgba(1, 1, 3, 0.1);
|
||||||
|
}
|
||||||
|
|
||||||
|
.github-link > svg {
|
||||||
|
position: absolute;
|
||||||
|
top: 50%;
|
||||||
|
right: 36px;
|
||||||
|
transform: translateY(-50%);
|
||||||
|
width: 32px;
|
||||||
|
height: 32px;
|
||||||
|
transition: transform 0.2s;
|
||||||
|
}
|
||||||
|
|
||||||
|
.github-link > svg:hover {
|
||||||
|
cursor: pointer;
|
||||||
|
transform: translateY(-50%) scale(1.15);
|
||||||
|
}
|
||||||
|
|
@ -1,15 +0,0 @@
|
||||||
{
|
|
||||||
"compilerOptions": {
|
|
||||||
"module": "ESNext",
|
|
||||||
"target": "ES2017",
|
|
||||||
"strict": true,
|
|
||||||
"allowSyntheticDefaultImports": true,
|
|
||||||
"esModuleInterop": true,
|
|
||||||
"moduleResolution": "bundler",
|
|
||||||
"outDir": "./dist",
|
|
||||||
"rootDir": "./src",
|
|
||||||
"skipLibCheck": true,
|
|
||||||
"inlineSourceMap": true
|
|
||||||
},
|
|
||||||
"exclude": ["./dist"]
|
|
||||||
}
|
|
||||||
|
|
@ -1,94 +0,0 @@
|
||||||
const path = require('path');
|
|
||||||
const HtmlWebpackPlugin = require('html-webpack-plugin');
|
|
||||||
const TerserPlugin = require('terser-webpack-plugin');
|
|
||||||
const InlineSourceWebpackPlugin = require('inline-source-webpack-plugin');
|
|
||||||
const MiniCssExtractPlugin = require('mini-css-extract-plugin');
|
|
||||||
const CopyWebpackPlugin = require('copy-webpack-plugin');
|
|
||||||
|
|
||||||
module.exports = (_env, argv) => ({
|
|
||||||
devtool: argv.mode === 'development' ? 'inline-source-map' : false,
|
|
||||||
entry: {
|
|
||||||
index: './src/index.ts',
|
|
||||||
},
|
|
||||||
devServer: {
|
|
||||||
allowedHosts: 'all',
|
|
||||||
},
|
|
||||||
watchOptions: {
|
|
||||||
ignored: '**/node_modules',
|
|
||||||
},
|
|
||||||
optimization: {
|
|
||||||
minimizer: [
|
|
||||||
new TerserPlugin({
|
|
||||||
terserOptions: {
|
|
||||||
module: true,
|
|
||||||
},
|
|
||||||
}),
|
|
||||||
],
|
|
||||||
},
|
|
||||||
performance: {
|
|
||||||
assetFilter: (f) => !/\.(webm|mp4|pdf)$/.test(f),
|
|
||||||
maxEntrypointSize: 100000,
|
|
||||||
maxAssetSize: 512000,
|
|
||||||
},
|
|
||||||
plugins: [
|
|
||||||
new HtmlWebpackPlugin({
|
|
||||||
template: './src/index.html',
|
|
||||||
}),
|
|
||||||
new MiniCssExtractPlugin(),
|
|
||||||
new CopyWebpackPlugin({
|
|
||||||
patterns: [
|
|
||||||
{
|
|
||||||
from: 'src/*.ico',
|
|
||||||
to: '[name][ext]',
|
|
||||||
},
|
|
||||||
{
|
|
||||||
from: 'src/*.png',
|
|
||||||
to: '[name][ext]',
|
|
||||||
},
|
|
||||||
],
|
|
||||||
}),
|
|
||||||
argv.mode === 'production'
|
|
||||||
? new InlineSourceWebpackPlugin({
|
|
||||||
compress: true,
|
|
||||||
})
|
|
||||||
: null,
|
|
||||||
].filter(Boolean),
|
|
||||||
module: {
|
|
||||||
rules: [
|
|
||||||
{
|
|
||||||
test: /\.svg$/i,
|
|
||||||
use: 'svg-inline-loader',
|
|
||||||
},
|
|
||||||
{
|
|
||||||
test: /\.scss$/i,
|
|
||||||
use: [
|
|
||||||
MiniCssExtractPlugin.loader,
|
|
||||||
'css-loader',
|
|
||||||
'resolve-url-loader',
|
|
||||||
{
|
|
||||||
loader: 'sass-loader',
|
|
||||||
options: {
|
|
||||||
sourceMap: true, // required by resolve-url-loader
|
|
||||||
},
|
|
||||||
},
|
|
||||||
],
|
|
||||||
},
|
|
||||||
{
|
|
||||||
test: /\.ts$/,
|
|
||||||
use: 'ts-loader',
|
|
||||||
},
|
|
||||||
],
|
|
||||||
},
|
|
||||||
resolve: {
|
|
||||||
extensions: [
|
|
||||||
'.ts',
|
|
||||||
'.js', // required for development
|
|
||||||
],
|
|
||||||
},
|
|
||||||
output: {
|
|
||||||
clean: true,
|
|
||||||
filename: '[name].js',
|
|
||||||
path: path.resolve(__dirname, 'dist'),
|
|
||||||
publicPath: '',
|
|
||||||
},
|
|
||||||
});
|
|
||||||
|
|
@ -1,9 +0,0 @@
|
||||||
const fs = require('fs');
|
|
||||||
const path = require('path');
|
|
||||||
|
|
||||||
// Read the actual WASM file and convert to base64 for testing
|
|
||||||
const wasmPath = path.join(__dirname, '../../pkg/reconcile_text_bg.wasm');
|
|
||||||
const wasmBuffer = fs.readFileSync(wasmPath);
|
|
||||||
const wasmBase64 = wasmBuffer.toString('base64');
|
|
||||||
|
|
||||||
module.exports = wasmBase64;
|
|
||||||
|
|
@ -1,6 +0,0 @@
|
||||||
module.exports = {
|
|
||||||
preset: 'ts-jest/presets/js-with-babel-esm',
|
|
||||||
moduleNameMapper: {
|
|
||||||
'^reconcile-text/reconcile_text_bg\\.wasm$': `<rootDir>/__mocks__/wasm.js`,
|
|
||||||
},
|
|
||||||
};
|
|
||||||
5458
reconcile-js/package-lock.json
generated
5458
reconcile-js/package-lock.json
generated
File diff suppressed because it is too large
Load diff
|
|
@ -1,53 +0,0 @@
|
||||||
{
|
|
||||||
"name": "reconcile-text",
|
|
||||||
"version": "0.12.1",
|
|
||||||
"description": "Intelligent 3-way text merging with automated conflict resolution",
|
|
||||||
"main": "dist/reconcile.node.js",
|
|
||||||
"browser": "dist/reconcile.web.js",
|
|
||||||
"react-native": "dist/reconcile.rn.js",
|
|
||||||
"keywords": [
|
|
||||||
"text editing",
|
|
||||||
"sync",
|
|
||||||
"collaborative editing",
|
|
||||||
"3-way",
|
|
||||||
"merge",
|
|
||||||
"conflict resolution",
|
|
||||||
"OT",
|
|
||||||
"operational transformation",
|
|
||||||
"CRDT"
|
|
||||||
],
|
|
||||||
"homepage": "https://schmelczer.dev/reconcile/",
|
|
||||||
"repository": {
|
|
||||||
"type": "git",
|
|
||||||
"url": "git+https://github.com/schmelczer/reconcile.git"
|
|
||||||
},
|
|
||||||
"bugs": {
|
|
||||||
"url": "https://github.com/schmelczer/reconcile/issues",
|
|
||||||
"email": "andras@schmelczer.dev"
|
|
||||||
},
|
|
||||||
"author": "András Schmelczer <andras@schmelczer.dev>",
|
|
||||||
"license": "MIT",
|
|
||||||
"types": "dist/types/index.d.ts",
|
|
||||||
"files": [
|
|
||||||
"dist/**/*"
|
|
||||||
],
|
|
||||||
"scripts": {
|
|
||||||
"build": "node scripts/build-rn.mjs && webpack --mode production",
|
|
||||||
"format": "prettier --write \"./**/*.(ts|mjs|scss|json|html)\"",
|
|
||||||
"test": "NODE_OPTIONS=\"$NODE_OPTIONS --experimental-vm-modules\" jest"
|
|
||||||
},
|
|
||||||
"devDependencies": {
|
|
||||||
"@types/jest": "^30.0.0",
|
|
||||||
"binaryen": "^123.0.0",
|
|
||||||
"jest": "^30.3.0",
|
|
||||||
"prettier": "^3.8.1",
|
|
||||||
"reconcile-text": "file:../pkg",
|
|
||||||
"ts-jest": "^29.4.6",
|
|
||||||
"ts-loader": "^9.5.4",
|
|
||||||
"tslib": "2.8.1",
|
|
||||||
"typescript": "5.9.3",
|
|
||||||
"webpack": "^5.105.4",
|
|
||||||
"webpack-cli": "^6.0.1",
|
|
||||||
"webpack-merge": "^6.0.1"
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
@ -1,307 +0,0 @@
|
||||||
// Generates `pkg-rn/`: a React Native / Hermes-compatible build of the
|
|
||||||
// wasm-bindgen bindings in which the WebAssembly module is replaced by its
|
|
||||||
// wasm2js (pure-JS) translation.
|
|
||||||
|
|
||||||
import { execFileSync } from 'node:child_process';
|
|
||||||
import { existsSync, readdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs';
|
|
||||||
import { dirname, resolve } from 'node:path';
|
|
||||||
import { fileURLToPath, pathToFileURL } from 'node:url';
|
|
||||||
import { homedir } from 'node:os';
|
|
||||||
|
|
||||||
const here = dirname(fileURLToPath(import.meta.url));
|
|
||||||
const reconcileJsDir = resolve(here, '..');
|
|
||||||
const repoRoot = resolve(reconcileJsDir, '..');
|
|
||||||
|
|
||||||
const releaseWasm = resolve(
|
|
||||||
repoRoot,
|
|
||||||
'target/wasm32-unknown-unknown/release/reconcile_text.wasm'
|
|
||||||
);
|
|
||||||
const outDir = resolve(reconcileJsDir, 'pkg-rn');
|
|
||||||
const bgWasm = resolve(outDir, 'reconcile_text_bg.wasm');
|
|
||||||
const bgWasmJs = resolve(outDir, 'reconcile_text_bg.wasm.js');
|
|
||||||
const loweredWasm = resolve(outDir, '_lowered.wasm');
|
|
||||||
const entryJs = resolve(outDir, 'reconcile_text.js');
|
|
||||||
|
|
||||||
const wasmOpt = resolve(reconcileJsDir, 'node_modules/.bin/wasm-opt');
|
|
||||||
const wasm2js = resolve(reconcileJsDir, 'node_modules/.bin/wasm2js');
|
|
||||||
|
|
||||||
function run(cmd, args) {
|
|
||||||
execFileSync(cmd, args, { stdio: 'inherit' });
|
|
||||||
}
|
|
||||||
|
|
||||||
// Locate the wasm-bindgen CLI. It MUST match the `wasm-bindgen` crate version pinned
|
|
||||||
// in Cargo.toml: a mismatched CLI emits bindings the runtime can't use. So we resolve
|
|
||||||
// the required version first and verify every candidate against it, failing loudly
|
|
||||||
// rather than silently falling back to whatever other version happens to be around.
|
|
||||||
function findWasmBindgen() {
|
|
||||||
const cargoToml = readFileSync(resolve(repoRoot, 'Cargo.toml'), 'utf8');
|
|
||||||
const wanted = cargoToml.match(
|
|
||||||
/wasm-bindgen\s*=\s*\{[^}]*version\s*=\s*"([^"]+)"/
|
|
||||||
)?.[1];
|
|
||||||
if (!wanted) {
|
|
||||||
throw new Error(
|
|
||||||
'[build-rn] Could not parse the pinned wasm-bindgen version from Cargo.toml, so ' +
|
|
||||||
'the required CLI version is unknown. Has the dependency declaration changed?'
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
// 1. On PATH: accept it only if its version matches the pin.
|
|
||||||
let onPath = null;
|
|
||||||
try {
|
|
||||||
onPath = execFileSync('which', ['wasm-bindgen'], { encoding: 'utf8' }).trim();
|
|
||||||
} catch {
|
|
||||||
/* not on PATH; try the wasm-pack cache next */
|
|
||||||
}
|
|
||||||
if (onPath) {
|
|
||||||
const version = execFileSync(onPath, ['--version'], { encoding: 'utf8' }).match(
|
|
||||||
/\d+\.\d+\.\d+/
|
|
||||||
)?.[0];
|
|
||||||
if (version !== wanted) {
|
|
||||||
throw new Error(
|
|
||||||
`[build-rn] wasm-bindgen on PATH (${onPath}) is ${version ?? 'an unknown version'}, ` +
|
|
||||||
`but Cargo.toml pins ${wanted}. Install the matching CLI ` +
|
|
||||||
`(\`cargo install wasm-bindgen-cli --version ${wanted}\`) or remove the mismatched one.`
|
|
||||||
);
|
|
||||||
}
|
|
||||||
return onPath;
|
|
||||||
}
|
|
||||||
|
|
||||||
const cacheRoots = [
|
|
||||||
resolve(homedir(), 'Library/Caches/.wasm-pack'),
|
|
||||||
resolve(homedir(), '.cache/.wasm-pack'),
|
|
||||||
];
|
|
||||||
for (const root of cacheRoots) {
|
|
||||||
if (!existsSync(root)) {
|
|
||||||
continue;
|
|
||||||
}
|
|
||||||
for (const entry of readdirSync(root)) {
|
|
||||||
const candidate = resolve(root, entry, 'wasm-bindgen');
|
|
||||||
if (!existsSync(candidate)) {
|
|
||||||
continue;
|
|
||||||
}
|
|
||||||
let version;
|
|
||||||
try {
|
|
||||||
version = execFileSync(candidate, ['--version'], { encoding: 'utf8' }).match(
|
|
||||||
/\d+\.\d+\.\d+/
|
|
||||||
)?.[0];
|
|
||||||
} catch {
|
|
||||||
continue; // not an invokable wasm-bindgen; ignore
|
|
||||||
}
|
|
||||||
if (version === wanted) {
|
|
||||||
return candidate;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
throw new Error(
|
|
||||||
`[build-rn] No wasm-bindgen ${wanted} found on PATH or in the wasm-pack cache. ` +
|
|
||||||
'Run `wasm-pack build --target web --features wasm` first (it caches the matching ' +
|
|
||||||
`wasm-bindgen), or \`cargo install wasm-bindgen-cli --version ${wanted}\`.`
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
if (!existsSync(releaseWasm)) {
|
|
||||||
throw new Error(
|
|
||||||
`Missing ${releaseWasm}.\nRun \`wasm-pack build --target web --features wasm\` from the repo root first.`
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
console.log('[build-rn] generating bundler-target bindings with wasm-bindgen');
|
|
||||||
rmSync(outDir, { recursive: true, force: true });
|
|
||||||
const wasmBindgen = findWasmBindgen();
|
|
||||||
run(wasmBindgen, ['--target', 'bundler', '--out-dir', outDir, releaseWasm]);
|
|
||||||
|
|
||||||
// --- Patch wasm-bindgen's cached-memory getters for wasm2js -----------------
|
|
||||||
//
|
|
||||||
// wasm-bindgen caches typed-array / DataView views over `wasm.memory.buffer` and
|
|
||||||
// only re-creates them when it detects the heap grew. It detects a grow by looking
|
|
||||||
// for ArrayBuffer *detachment*: a real `WebAssembly.Memory.grow()` detaches the old
|
|
||||||
// buffer (its `byteLength` becomes 0 and `.detached` becomes true), and those are the
|
|
||||||
// only signals the generated getters check:
|
|
||||||
// - getUint8ArrayMemory0(): refreshes when `byteLength === 0` (detach only)
|
|
||||||
// - getDataViewMemory0(): refreshes when `.detached === true`, OR when the buffer
|
|
||||||
// identity changed but only `if (.detached === undefined)` — i.e. that identity
|
|
||||||
// fallback runs solely on engines lacking `ArrayBuffer.prototype.detached`.
|
|
||||||
//
|
|
||||||
// wasm2js grows differently: `__wasm_memory_grow` (in reconcile_text_bg.wasm.js)
|
|
||||||
// allocates a NEW ArrayBuffer, copies the old heap into it, and reassigns
|
|
||||||
// `memory.buffer` WITHOUT ever detaching the old buffer. So the old buffer keeps
|
|
||||||
// `byteLength > 0` and `.detached === false`, and on modern engines that DO expose
|
|
||||||
// `ArrayBuffer.prototype.detached` (Node 25+, current Hermes) the identity fallback is
|
|
||||||
// gated off. Net effect: after a grow the getters keep returning views over the stale
|
|
||||||
// pre-grow buffer, silently corrupting any operation large enough to grow the heap.
|
|
||||||
// Small inputs never grow, so this escapes naive testing.
|
|
||||||
//
|
|
||||||
// WHY WE PATCH INSTEAD OF CONFIGURING.
|
|
||||||
// This is not fixed or configurable upstream: wasm-bindgen has no wasm2js / asm.js /
|
|
||||||
// React Native / "no-WebAssembly" target (every target assumes real WebAssembly
|
|
||||||
// detach-on-grow semantics), there is no flag to force buffer-identity comparison, and
|
|
||||||
// the getter-generation logic (crates/cli-support/src/js/mod.rs `memview`) is
|
|
||||||
// byte-for-byte identical from the pinned 0.2.114 through the latest release and
|
|
||||||
// `main`. The non-detaching-grow case is not even a tracked upstream issue. Rewriting
|
|
||||||
// the generated glue is therefore the only available fix: the two replacements below
|
|
||||||
// make BOTH getters also refresh on a buffer-identity change
|
|
||||||
// (`buffer !== wasm.memory.buffer`), which is the one signal wasm2js does give.
|
|
||||||
//
|
|
||||||
// Each replacement is asserted independently. If a future wasm-bindgen reshapes one
|
|
||||||
// getter but not the other, we MUST fail the build rather than ship a half-patched
|
|
||||||
// module whose un-patched getter corrupts large inputs. The post-build self-test at
|
|
||||||
// the bottom of this file is the backstop that proves the result survives a real grow.
|
|
||||||
const bgJsPath = resolve(outDir, 'reconcile_text_bg.js');
|
|
||||||
let bgJs = readFileSync(bgJsPath, 'utf8');
|
|
||||||
|
|
||||||
// (1) Uint8Array getter: append an unconditional buffer-identity check to the
|
|
||||||
// `byteLength === 0` detach guard (upstream has no identity check here at all).
|
|
||||||
const byteLengthGuard = /(cached\w*Memory0)\.byteLength === 0/g;
|
|
||||||
const byteLengthHits = bgJs.match(byteLengthGuard)?.length ?? 0;
|
|
||||||
if (byteLengthHits === 0) {
|
|
||||||
throw new Error(
|
|
||||||
`[build-rn] Could not find the Uint8Array \`byteLength === 0\` growth guard in ` +
|
|
||||||
`${bgJsPath} to patch for wasm2js. The wasm-bindgen output shape changed; update ` +
|
|
||||||
'this patch (see crates/cli-support/src/js/mod.rs `memview`) — do NOT ship an ' +
|
|
||||||
'unpatched getter, it will corrupt large inputs under wasm2js.'
|
|
||||||
);
|
|
||||||
}
|
|
||||||
bgJs = bgJs.replace(
|
|
||||||
byteLengthGuard,
|
|
||||||
'$1.byteLength === 0 || $1.buffer !== wasm.memory.buffer'
|
|
||||||
);
|
|
||||||
|
|
||||||
// (2) DataView getter: drop the `detached === undefined &&` prefix so the existing
|
|
||||||
// buffer-identity check runs on every runtime, not only legacy ones.
|
|
||||||
const gatedGuard =
|
|
||||||
/(cached\w*Memory0)\.buffer\.detached === undefined && \1\.buffer !== wasm\.memory\.buffer/g;
|
|
||||||
const gatedHits = bgJs.match(gatedGuard)?.length ?? 0;
|
|
||||||
if (gatedHits === 0) {
|
|
||||||
throw new Error(
|
|
||||||
`[build-rn] Could not find the DataView \`detached === undefined\`-gated buffer-identity ` +
|
|
||||||
`check in ${bgJsPath} to un-gate for wasm2js. The wasm-bindgen output shape changed; ` +
|
|
||||||
'update this patch (see crates/cli-support/src/js/mod.rs `memview`) — do NOT ship an ' +
|
|
||||||
'unpatched getter, it will corrupt large inputs under wasm2js.'
|
|
||||||
);
|
|
||||||
}
|
|
||||||
bgJs = bgJs.replace(gatedGuard, '$1.buffer !== wasm.memory.buffer');
|
|
||||||
|
|
||||||
writeFileSync(bgJsPath, bgJs);
|
|
||||||
|
|
||||||
// Post-MVP features that wasm2js cannot translate must be lowered to MVP first.
|
|
||||||
// reference-types stays enabled: it only covers the funcref table here, which
|
|
||||||
// wasm2js handles via call_indirect.
|
|
||||||
const featureFlags = [
|
|
||||||
'--enable-bulk-memory',
|
|
||||||
'--enable-sign-ext',
|
|
||||||
'--enable-nontrapping-float-to-int',
|
|
||||||
'--enable-mutable-globals',
|
|
||||||
'--enable-reference-types',
|
|
||||||
];
|
|
||||||
|
|
||||||
console.log('[build-rn] optimising and lowering to MVP with wasm-opt');
|
|
||||||
run(wasmOpt, [
|
|
||||||
...featureFlags,
|
|
||||||
'-O3',
|
|
||||||
'--signext-lowering',
|
|
||||||
'--llvm-memory-copy-fill-lowering',
|
|
||||||
'--llvm-nontrapping-fptoint-lowering',
|
|
||||||
bgWasm,
|
|
||||||
'-o',
|
|
||||||
loweredWasm,
|
|
||||||
]);
|
|
||||||
|
|
||||||
console.log('[build-rn] translating wasm -> JS with wasm2js');
|
|
||||||
run(wasm2js, ['--enable-reference-types', loweredWasm, '-o', bgWasmJs]);
|
|
||||||
|
|
||||||
console.log('[build-rn] wiring the JS translation into reconcile_text.js');
|
|
||||||
const entry = readFileSync(entryJs, 'utf8');
|
|
||||||
const rewired = entry.replace(
|
|
||||||
/from\s+(['"])\.\/reconcile_text_bg\.wasm\1/,
|
|
||||||
'from $1./reconcile_text_bg.wasm.js$1'
|
|
||||||
);
|
|
||||||
if (rewired === entry) {
|
|
||||||
throw new Error(
|
|
||||||
`Could not find the \`./reconcile_text_bg.wasm\` import in ${entryJs}; ` +
|
|
||||||
'the wasm-bindgen bundler output layout may have changed.'
|
|
||||||
);
|
|
||||||
}
|
|
||||||
writeFileSync(entryJs, rewired);
|
|
||||||
|
|
||||||
// The binary and the intermediate are no longer referenced; remove them so no
|
|
||||||
// bundler attempts to instantiate WebAssembly from this directory.
|
|
||||||
rmSync(bgWasm, { force: true });
|
|
||||||
rmSync(loweredWasm, { force: true });
|
|
||||||
|
|
||||||
// Mark the directory as ESM (matching the web `pkg/`) so Node and Jest treat
|
|
||||||
// these `.js` files as modules. `sideEffects` stays true because importing the
|
|
||||||
// entry runs `__wbg_set_wasm(...)`, which must not be tree-shaken away.
|
|
||||||
writeFileSync(
|
|
||||||
resolve(outDir, 'package.json'),
|
|
||||||
JSON.stringify({ type: 'module', sideEffects: true }, null, 2) + '\n'
|
|
||||||
);
|
|
||||||
|
|
||||||
// Backstop: import the freshly generated module and prove it survives a heap grow.
|
|
||||||
// The patches above are matched by regex against wasm-bindgen output; a silently
|
|
||||||
// mis-applied patch (or a wasm-bindgen change we matched too loosely) would leave a
|
|
||||||
// getter reading the stale pre-grow buffer and corrupt large inputs only. Rather than
|
|
||||||
// trust the regexes, we force a grow here and assert a byte-exact round-trip, so a
|
|
||||||
// broken bundle fails the build instead of reaching a React Native consumer.
|
|
||||||
async function selfTest() {
|
|
||||||
// Importing the entry runs `__wbg_set_wasm(...)`, initialising the wasm2js module.
|
|
||||||
const api = await import(pathToFileURL(entryJs).href);
|
|
||||||
// Same module instance (Node caches by resolved path), so this `memory` is the heap
|
|
||||||
// the API operates on; its `.buffer` getter reflects the current (post-grow) buffer.
|
|
||||||
const { memory } = await import(pathToFileURL(bgWasmJs).href);
|
|
||||||
|
|
||||||
// ~100 KB of distinct tokens. The diff working set amplifies the input many-fold
|
|
||||||
// (a ~50 KB input already forces dozens of grows), so this reliably grows the heap
|
|
||||||
// well past wasm2js's ~1 MB initial allocation while staying fast. A tiny parent
|
|
||||||
// keeps the edit distance — and therefore the runtime — small.
|
|
||||||
const tokens = [];
|
|
||||||
for (let i = 0; i < 10000; i++) {
|
|
||||||
tokens.push(`token-${i}`);
|
|
||||||
}
|
|
||||||
const target = tokens.join(' ');
|
|
||||||
const parent = 'reconcile self-test';
|
|
||||||
|
|
||||||
const heapBefore = memory.buffer.byteLength;
|
|
||||||
|
|
||||||
// Stale post-grow reads surface either as an out-of-bounds throw or as silently
|
|
||||||
// wrong bytes, so handle both: a throw here is itself the failure signal.
|
|
||||||
let roundTripped;
|
|
||||||
try {
|
|
||||||
const changed = new api.TextWithCursors(target, []);
|
|
||||||
const compact = api
|
|
||||||
.diff(parent, changed, 'Word')
|
|
||||||
// This build's `undiff` rejects BigInt; normalise exactly as src/core.ts does.
|
|
||||||
.map((item) => (typeof item === 'bigint' ? Number(item) : item));
|
|
||||||
changed.free();
|
|
||||||
roundTripped = api.undiff(parent, compact, 'Word');
|
|
||||||
} catch (cause) {
|
|
||||||
throw new Error(
|
|
||||||
'[build-rn] self-test crashed during a large diff/undiff round-trip (after the heap ' +
|
|
||||||
'grew). This is the signature of unpatched wasm2js cached-memory getters reading the ' +
|
|
||||||
'stale pre-grow buffer. The growth patch is not taking effect. Refusing to ship this ' +
|
|
||||||
'React Native bundle.',
|
|
||||||
{ cause }
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
const heapAfter = memory.buffer.byteLength;
|
|
||||||
|
|
||||||
if (heapAfter <= heapBefore) {
|
|
||||||
throw new Error(
|
|
||||||
`[build-rn] self-test did not grow the wasm heap (stayed at ${heapBefore} bytes), ` +
|
|
||||||
'so it cannot validate the memory-growth patch. Enlarge the self-test input.'
|
|
||||||
);
|
|
||||||
}
|
|
||||||
if (roundTripped !== target) {
|
|
||||||
throw new Error(
|
|
||||||
'[build-rn] self-test FAILED: diff/undiff round-trip did not match after a heap grow. ' +
|
|
||||||
'The patched wasm2js cached-memory getters are returning stale/corrupt data — the ' +
|
|
||||||
'growth patch is not taking effect. Refusing to ship this React Native bundle.'
|
|
||||||
);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
console.log('[build-rn] self-testing the patched module (forces a heap grow)');
|
|
||||||
await selfTest();
|
|
||||||
|
|
||||||
console.log('[build-rn] done -> pkg-rn/');
|
|
||||||
|
|
@ -1,400 +0,0 @@
|
||||||
// Shared, platform-agnostic wrapper around the generated wasm-bindgen surface.
|
|
||||||
//
|
|
||||||
// The actual wasm bindings are injected by a platform-specific entrypoint:
|
|
||||||
// - `index.ts` (web/node) instantiates the real WebAssembly module lazily
|
|
||||||
// on first use via `initSync`.
|
|
||||||
// - `index.rn.ts` (React Native / Hermes) links a wasm2js (pure-JS)
|
|
||||||
// implementation, since Hermes does not expose a runtime
|
|
||||||
// `WebAssembly` global. See `scripts/build-rn.mjs`.
|
|
||||||
|
|
||||||
type WasmModule = typeof import('reconcile-text');
|
|
||||||
|
|
||||||
/**
|
|
||||||
* The generated wasm-bindgen surface this library wraps, plus a hook to make
|
|
||||||
* sure the underlying module is ready. Supplied by a platform entrypoint.
|
|
||||||
*/
|
|
||||||
export interface WasmBackend {
|
|
||||||
CursorPosition: WasmModule['CursorPosition'];
|
|
||||||
TextWithCursors: WasmModule['TextWithCursors'];
|
|
||||||
reconcile: WasmModule['reconcile'];
|
|
||||||
reconcileWithHistory: WasmModule['reconcileWithHistory'];
|
|
||||||
diff: WasmModule['diff'];
|
|
||||||
undiff: WasmModule['undiff'];
|
|
||||||
/**
|
|
||||||
* Make the wasm module ready for use. Invoked before every operation, so it
|
|
||||||
* must be cheap and idempotent (a no-op once initialised).
|
|
||||||
*/
|
|
||||||
ensureReady(): void;
|
|
||||||
}
|
|
||||||
|
|
||||||
// Define the enum values as a const array to avoid duplication
|
|
||||||
const BUILTIN_TOKENIZERS = ['Character', 'Line', 'Markdown', 'Word'] as const;
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Tokenisation strategies for text merging.
|
|
||||||
*
|
|
||||||
* These correspond to the built-in tokenizers available in the underlying WASM module.
|
|
||||||
*/
|
|
||||||
export type BuiltinTokenizer = (typeof BUILTIN_TOKENIZERS)[number];
|
|
||||||
|
|
||||||
/**
|
|
||||||
* History classification for text spans in merge results.
|
|
||||||
*
|
|
||||||
* Indicates the origin of each text span in the merged document.
|
|
||||||
*/
|
|
||||||
export type History =
|
|
||||||
| 'Unchanged'
|
|
||||||
| 'AddedFromLeft'
|
|
||||||
| 'AddedFromRight'
|
|
||||||
| 'RemovedFromLeft'
|
|
||||||
| 'RemovedFromRight';
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Represents a text document with associated cursor positions.
|
|
||||||
*
|
|
||||||
* This interface is used both as input to reconcile functions (to specify where
|
|
||||||
* cursors are positioned in the original documents) and as output (with cursors
|
|
||||||
* automatically repositioned after merging).
|
|
||||||
*/
|
|
||||||
export interface TextWithCursors {
|
|
||||||
/** The document's entire content as a string */
|
|
||||||
text: string;
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Array of cursor positions within the text. Can be empty if there are no cursors to track.
|
|
||||||
* Each cursor has a unique ID and position.
|
|
||||||
*/
|
|
||||||
cursors: CursorPosition[];
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Like `TextWithCursors`, but cursors may be null or undefined (treated as empty).
|
|
||||||
* Used as input where cursor tracking is optional.
|
|
||||||
*/
|
|
||||||
export interface TextWithOptionalCursors {
|
|
||||||
/** The document's entire content as a string */
|
|
||||||
text: string;
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Array of cursor positions within the text. Can be null, undefined, or empty
|
|
||||||
* if there are no cursors to track. Each cursor has a unique ID and position.
|
|
||||||
*/
|
|
||||||
cursors: null | undefined | CursorPosition[];
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Represents a cursor position within a text document.
|
|
||||||
*
|
|
||||||
* Cursors are automatically repositioned during text merging to maintain their
|
|
||||||
* relative positions as text is inserted, deleted, or modified around them.
|
|
||||||
*/
|
|
||||||
export interface CursorPosition {
|
|
||||||
/** Unique identifier for the cursor (can be any number, must be unique within the document) */
|
|
||||||
id: number;
|
|
||||||
|
|
||||||
/** Character position in the text, 0-based index from the beginning of the document */
|
|
||||||
position: number;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Represents a merged text document with cursor positions and detailed change history.
|
|
||||||
*
|
|
||||||
* This is the return type of `reconcileWithHistory()` and provides complete information
|
|
||||||
* about how the merge was performed, including which parts of the final text came from
|
|
||||||
* which source documents.
|
|
||||||
*/
|
|
||||||
export interface TextWithCursorsAndHistory {
|
|
||||||
/** The merged document's entire content */
|
|
||||||
text: string;
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Array of cursor positions within the merged text. Can be empty if there are no cursors to track.
|
|
||||||
* All cursors are automatically repositioned from the left and right documents.
|
|
||||||
*/
|
|
||||||
cursors: CursorPosition[];
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Detailed provenance information showing the origin of each text span in the result.
|
|
||||||
* Each span indicates whether it was unchanged, added from left, added from right, etc.
|
|
||||||
*/
|
|
||||||
history: SpanWithHistory[];
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Represents a span of text in the merged result with its change history.
|
|
||||||
*
|
|
||||||
* This shows exactly which source document contributed each piece of text to the
|
|
||||||
* final merged result. Useful for understanding merge decisions and creating
|
|
||||||
* visualisations of how documents were combined.
|
|
||||||
*/
|
|
||||||
export interface SpanWithHistory {
|
|
||||||
/** The text content of this span */
|
|
||||||
text: string;
|
|
||||||
|
|
||||||
/** The origin of this text span in the merge result */
|
|
||||||
history: History;
|
|
||||||
}
|
|
||||||
|
|
||||||
/** The public, synchronous API surface, identical across platforms. */
|
|
||||||
export interface ReconcileApi {
|
|
||||||
/**
|
|
||||||
* Merges three versions of text using intelligent conflict resolution.
|
|
||||||
*
|
|
||||||
* This is the primary function for 3-way text merging. Unlike traditional merge tools
|
|
||||||
* that produce conflict markers, this function automatically resolves conflicts by
|
|
||||||
* applying both sets of changes where possible.
|
|
||||||
*
|
|
||||||
* @param original - The original/base version of the text that both sides diverged from
|
|
||||||
* @param left - The left version of the text (either string or TextWithCursors with cursor positions)
|
|
||||||
* @param right - The right version of the text (either string or TextWithCursors with cursor positions)
|
|
||||||
* @param tokenizer - The tokenisation strategy: "Word" (default, recommended for prose),
|
|
||||||
* "Character" (fine-grained), "Line" (similar to git merge), or
|
|
||||||
* "Markdown" (splits on Markdown structure)
|
|
||||||
* @returns The reconciled text with automatically repositioned cursor positions
|
|
||||||
*
|
|
||||||
* @example
|
|
||||||
* ```typescript
|
|
||||||
* const original = "Hello world";
|
|
||||||
* const left = "Hello beautiful world"; // Added "beautiful"
|
|
||||||
* const right = "Hi world"; // Changed "Hello" to "Hi"
|
|
||||||
*
|
|
||||||
* const result = reconcile(original, left, right);
|
|
||||||
* console.log(result.text); // "Hi beautiful world"
|
|
||||||
* ```
|
|
||||||
*/
|
|
||||||
reconcile(
|
|
||||||
original: string,
|
|
||||||
left: string | TextWithOptionalCursors,
|
|
||||||
right: string | TextWithOptionalCursors,
|
|
||||||
tokenizer?: BuiltinTokenizer
|
|
||||||
): TextWithCursors;
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Generates a compact diff representation between an original and changed text.
|
|
||||||
*
|
|
||||||
* These can be parsed and unpacked using the `undiff` function or the Rust crate's EditedText::from_diff.
|
|
||||||
* Cursor positions are omitted from the diff result.
|
|
||||||
*
|
|
||||||
* This function computes the differences between two versions of text and returns
|
|
||||||
* a compact representation of those changes.
|
|
||||||
*
|
|
||||||
* @param original - The original/base version of the text
|
|
||||||
* @param changed - The modified version of the text (either string or TextWithCursors with cursor positions)
|
|
||||||
* @param tokenizer - The tokenisation strategy, which is the same as used in `reconcile`.
|
|
||||||
* @returns An array of inserts (strings), deletes (negative integers), and retained spans (positive integers).
|
|
||||||
*/
|
|
||||||
diff(
|
|
||||||
original: string,
|
|
||||||
changed: string | TextWithOptionalCursors,
|
|
||||||
tokenizer?: BuiltinTokenizer
|
|
||||||
): Array<number | string>;
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Applies a compact diff to an original text to reconstruct the changed version.
|
|
||||||
*
|
|
||||||
* This function takes an original text and a compact diff representation (as produced
|
|
||||||
* by the `diff` function) and reconstructs the modified text.
|
|
||||||
*
|
|
||||||
* @param original - The original/base version of the text
|
|
||||||
* @param diff - The compact diff array (inserts as strings, deletes as negative integers, retained spans as positive integers)
|
|
||||||
* @param tokenizer - The tokenisation strategy, which is the same as used in `reconcile`.
|
|
||||||
* @returns The reconstructed changed text as a string.
|
|
||||||
*/
|
|
||||||
undiff(
|
|
||||||
original: string,
|
|
||||||
diff: Array<number | bigint | string>,
|
|
||||||
tokenizer?: BuiltinTokenizer
|
|
||||||
): string;
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Merges three versions of text and returns detailed provenance information.
|
|
||||||
*
|
|
||||||
* This function behaves like `reconcile()` but also provides
|
|
||||||
* detailed historical information about the origin of each text span in the result.
|
|
||||||
* This is valuable for understanding how the merge was performed and which changes
|
|
||||||
* came from which source.
|
|
||||||
*
|
|
||||||
* Note: Computing the history is computationally more expensive than the basic merge.
|
|
||||||
*
|
|
||||||
* @param original - The original/base version of the text that both sides diverged from
|
|
||||||
* @param left - The left version of the text (either string or TextWithCursors with cursor positions)
|
|
||||||
* @param right - The right version of the text (either string or TextWithCursors with cursor positions)
|
|
||||||
* @param tokenizer - The tokenisation strategy: "Word" (default, recommended for prose),
|
|
||||||
* "Character" (fine-grained), "Line" (similar to git merge), or
|
|
||||||
* "Markdown" (splits on Markdown structure)
|
|
||||||
* @returns The reconciled text with cursor positions and detailed change history
|
|
||||||
*
|
|
||||||
* @example
|
|
||||||
* ```typescript
|
|
||||||
* const original = "Hello world";
|
|
||||||
* const left = "Hello beautiful world";
|
|
||||||
* const right = "Hi world";
|
|
||||||
*
|
|
||||||
* const result = reconcileWithHistory(original, left, right);
|
|
||||||
* console.log(result.text); // "Hi beautiful world"
|
|
||||||
* console.log(result.history); // Array of SpanWithHistory objects showing change origins
|
|
||||||
* ```
|
|
||||||
*/
|
|
||||||
reconcileWithHistory(
|
|
||||||
original: string,
|
|
||||||
left: string | TextWithOptionalCursors,
|
|
||||||
right: string | TextWithOptionalCursors,
|
|
||||||
tokenizer?: BuiltinTokenizer
|
|
||||||
): TextWithCursorsAndHistory;
|
|
||||||
}
|
|
||||||
|
|
||||||
const UNSUPPORTED_TOKENIZER_ERROR = `Unsupported tokenizer, only ${BUILTIN_TOKENIZERS.join(
|
|
||||||
', '
|
|
||||||
)} are supported`;
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Build the public {@link ReconcileApi} on top of a {@link WasmBackend}.
|
|
||||||
*
|
|
||||||
* Each operation calls `backend.ensureReady()` first, then marshals JS values
|
|
||||||
* into the wasm representation, invokes the binding, and frees the wasm-side
|
|
||||||
* objects. The behaviour is identical regardless of whether the backend is a
|
|
||||||
* real WebAssembly module or its wasm2js translation.
|
|
||||||
*/
|
|
||||||
export function makeReconcileApi(backend: WasmBackend): ReconcileApi {
|
|
||||||
function assertTokenizer(tokenizer: BuiltinTokenizer): void {
|
|
||||||
if (!BUILTIN_TOKENIZERS.includes(tokenizer)) {
|
|
||||||
throw new Error(UNSUPPORTED_TOKENIZER_ERROR);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
function toWasmTextWithCursors(text: string | TextWithOptionalCursors) {
|
|
||||||
const isInputString = typeof text === 'string';
|
|
||||||
const innerText = isInputString ? text : text.text;
|
|
||||||
const innerCursors = isInputString ? [] : (text.cursors ?? []);
|
|
||||||
|
|
||||||
return new backend.TextWithCursors(
|
|
||||||
innerText,
|
|
||||||
innerCursors.map(({ id, position }) => new backend.CursorPosition(id, position))
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
function toTextWithCursors(textWithCursor: {
|
|
||||||
text(): string;
|
|
||||||
cursors(): Array<{ id(): number; characterIndex(): number; free(): void }>;
|
|
||||||
}): TextWithCursors {
|
|
||||||
const wasmCursors = textWithCursor.cursors();
|
|
||||||
const cursors = wasmCursors.map((cursor) => ({
|
|
||||||
id: cursor.id(),
|
|
||||||
position: cursor.characterIndex(),
|
|
||||||
}));
|
|
||||||
for (const cursor of wasmCursors) {
|
|
||||||
cursor.free();
|
|
||||||
}
|
|
||||||
|
|
||||||
return {
|
|
||||||
text: textWithCursor.text(),
|
|
||||||
cursors,
|
|
||||||
};
|
|
||||||
}
|
|
||||||
|
|
||||||
function toSpanWithHistory(span: {
|
|
||||||
text(): string;
|
|
||||||
history(): History;
|
|
||||||
free(): void;
|
|
||||||
}): SpanWithHistory {
|
|
||||||
const result = {
|
|
||||||
text: span.text(),
|
|
||||||
history: span.history(),
|
|
||||||
};
|
|
||||||
span.free();
|
|
||||||
return result;
|
|
||||||
}
|
|
||||||
|
|
||||||
function reconcile(
|
|
||||||
original: string,
|
|
||||||
left: string | TextWithOptionalCursors,
|
|
||||||
right: string | TextWithOptionalCursors,
|
|
||||||
tokenizer: BuiltinTokenizer = 'Word'
|
|
||||||
): TextWithCursors {
|
|
||||||
backend.ensureReady();
|
|
||||||
assertTokenizer(tokenizer);
|
|
||||||
|
|
||||||
const leftCursor = toWasmTextWithCursors(left);
|
|
||||||
const rightCursor = toWasmTextWithCursors(right);
|
|
||||||
|
|
||||||
const result = backend.reconcile(original, leftCursor, rightCursor, tokenizer);
|
|
||||||
|
|
||||||
leftCursor.free();
|
|
||||||
rightCursor.free();
|
|
||||||
|
|
||||||
const jsResult = toTextWithCursors(result);
|
|
||||||
result.free();
|
|
||||||
|
|
||||||
return jsResult;
|
|
||||||
}
|
|
||||||
|
|
||||||
function diff(
|
|
||||||
original: string,
|
|
||||||
changed: string | TextWithOptionalCursors,
|
|
||||||
tokenizer: BuiltinTokenizer = 'Word'
|
|
||||||
): Array<number | string> {
|
|
||||||
backend.ensureReady();
|
|
||||||
assertTokenizer(tokenizer);
|
|
||||||
|
|
||||||
const changedWasm = toWasmTextWithCursors(changed);
|
|
||||||
|
|
||||||
const result = backend.diff(original, changedWasm, tokenizer);
|
|
||||||
|
|
||||||
changedWasm.free();
|
|
||||||
|
|
||||||
return result.map((item) => (typeof item === 'bigint' ? Number(item) : item));
|
|
||||||
}
|
|
||||||
|
|
||||||
function undiff(
|
|
||||||
original: string,
|
|
||||||
diffValue: Array<number | bigint | string>,
|
|
||||||
tokenizer: BuiltinTokenizer = 'Word'
|
|
||||||
): string {
|
|
||||||
backend.ensureReady();
|
|
||||||
assertTokenizer(tokenizer);
|
|
||||||
|
|
||||||
// The real-WebAssembly backend's `diff` emits BigInt spans, whereas the
|
|
||||||
// wasm2js (React Native) backend rejects BigInt outright. Normalise to
|
|
||||||
// plain numbers - exactly as `diff` does on the way out - so a `diff`
|
|
||||||
// result round-trips through `undiff` identically on every platform.
|
|
||||||
return backend.undiff(
|
|
||||||
original,
|
|
||||||
diffValue.map((item) => (typeof item === 'bigint' ? Number(item) : item)),
|
|
||||||
tokenizer
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
function reconcileWithHistory(
|
|
||||||
original: string,
|
|
||||||
left: string | TextWithOptionalCursors,
|
|
||||||
right: string | TextWithOptionalCursors,
|
|
||||||
tokenizer: BuiltinTokenizer = 'Word'
|
|
||||||
): TextWithCursorsAndHistory {
|
|
||||||
backend.ensureReady();
|
|
||||||
assertTokenizer(tokenizer);
|
|
||||||
|
|
||||||
const leftCursor = toWasmTextWithCursors(left);
|
|
||||||
const rightCursor = toWasmTextWithCursors(right);
|
|
||||||
|
|
||||||
const result = backend.reconcileWithHistory(
|
|
||||||
original,
|
|
||||||
leftCursor,
|
|
||||||
rightCursor,
|
|
||||||
tokenizer
|
|
||||||
);
|
|
||||||
|
|
||||||
leftCursor.free();
|
|
||||||
rightCursor.free();
|
|
||||||
|
|
||||||
const jsResult = toTextWithCursors(result);
|
|
||||||
const history = result.history().map(toSpanWithHistory);
|
|
||||||
result.free();
|
|
||||||
|
|
||||||
return {
|
|
||||||
...jsResult,
|
|
||||||
history,
|
|
||||||
};
|
|
||||||
}
|
|
||||||
|
|
||||||
return { reconcile, diff, undiff, reconcileWithHistory };
|
|
||||||
}
|
|
||||||
|
|
@ -1,47 +0,0 @@
|
||||||
// React Native entrypoint (resolved via the `react-native` package field).
|
|
||||||
//
|
|
||||||
// Hermes — the default React Native engine since RN 0.84 / Expo SDK 56 — does
|
|
||||||
// not expose a runtime `WebAssembly` global, so the normal `new
|
|
||||||
// WebAssembly.Module(...)` path used by `index.ts` throws
|
|
||||||
// `ReferenceError: Property 'WebAssembly' doesn't exist`.
|
|
||||||
//
|
|
||||||
// Instead we link a wasm2js translation of the module: pure JavaScript that
|
|
||||||
// needs no `WebAssembly` global and is instantiated synchronously at import
|
|
||||||
// time. The public API and its synchronous signatures are unchanged, so
|
|
||||||
// callers need no modification. The `pkg-rn` directory is generated by
|
|
||||||
// `scripts/build-rn.mjs`.
|
|
||||||
|
|
||||||
import {
|
|
||||||
CursorPosition as wasmCursorPosition,
|
|
||||||
TextWithCursors as wasmTextWithCursors,
|
|
||||||
reconcile as wasmReconcile,
|
|
||||||
reconcileWithHistory as wasmReconcileWithHistory,
|
|
||||||
diff as wasmDiff,
|
|
||||||
undiff as wasmUndiff,
|
|
||||||
} from '../pkg-rn/reconcile_text.js';
|
|
||||||
|
|
||||||
import { makeReconcileApi, type WasmBackend } from './core';
|
|
||||||
|
|
||||||
const backend: WasmBackend = {
|
|
||||||
CursorPosition: wasmCursorPosition,
|
|
||||||
TextWithCursors: wasmTextWithCursors,
|
|
||||||
reconcile: wasmReconcile,
|
|
||||||
reconcileWithHistory: wasmReconcileWithHistory,
|
|
||||||
diff: wasmDiff,
|
|
||||||
undiff: wasmUndiff,
|
|
||||||
// The wasm2js module initialises itself at import time, so this is a no-op.
|
|
||||||
ensureReady() {},
|
|
||||||
};
|
|
||||||
|
|
||||||
export const { reconcile, diff, undiff, reconcileWithHistory } =
|
|
||||||
makeReconcileApi(backend);
|
|
||||||
|
|
||||||
export type {
|
|
||||||
BuiltinTokenizer,
|
|
||||||
History,
|
|
||||||
CursorPosition,
|
|
||||||
TextWithCursors,
|
|
||||||
TextWithOptionalCursors,
|
|
||||||
TextWithCursorsAndHistory,
|
|
||||||
SpanWithHistory,
|
|
||||||
} from './core';
|
|
||||||
|
|
@ -1,152 +0,0 @@
|
||||||
import * as webApi from './index';
|
|
||||||
import * as rnApi from './index.rn';
|
|
||||||
import { installWasmLeakDetector, checkForWasmLeaks } from './wasm-leak-detector';
|
|
||||||
import * as fs from 'fs';
|
|
||||||
import * as path from 'path';
|
|
||||||
import { fileURLToPath } from 'url';
|
|
||||||
|
|
||||||
const __dirname = path.dirname(fileURLToPath(import.meta.url));
|
|
||||||
|
|
||||||
installWasmLeakDetector();
|
|
||||||
|
|
||||||
afterEach(() => {
|
|
||||||
const leaks = checkForWasmLeaks();
|
|
||||||
if (leaks.length > 0) {
|
|
||||||
throw new Error(
|
|
||||||
`WASM memory leak: ${leaks.length} object(s) not freed:\n ${leaks.join('\n ')}`
|
|
||||||
);
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
// `./index` is the web/node build (real WebAssembly); `./index.rn` is the React
|
|
||||||
// Native build (the wasm2js pure-JS translation). Both are thin backends over the
|
|
||||||
// same `src/core.ts` wrapper and expose an identical public API, so the behavioural
|
|
||||||
// suite below runs against both to guarantee they stay in lock-step.
|
|
||||||
const backends = [
|
|
||||||
{ name: 'web/node (WebAssembly)', api: webApi },
|
|
||||||
{ name: 'React Native (wasm2js)', api: rnApi },
|
|
||||||
];
|
|
||||||
|
|
||||||
describe.each(backends)('reconcile [$name]', ({ api }) => {
|
|
||||||
const { reconcile, reconcileWithHistory, diff, undiff } = api;
|
|
||||||
|
|
||||||
it('call reconcile without cursors', () => {
|
|
||||||
expect(reconcile('Hello', 'Hello world', 'Hi world').text).toEqual('Hi world');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('call reconcile with cursors', () => {
|
|
||||||
const result = reconcile(
|
|
||||||
'Hello',
|
|
||||||
{
|
|
||||||
text: 'Hello world',
|
|
||||||
cursors: [
|
|
||||||
{
|
|
||||||
id: 3,
|
|
||||||
position: 2,
|
|
||||||
},
|
|
||||||
],
|
|
||||||
},
|
|
||||||
{
|
|
||||||
text: 'Hi world',
|
|
||||||
cursors: [
|
|
||||||
{
|
|
||||||
id: 4,
|
|
||||||
position: 0,
|
|
||||||
},
|
|
||||||
{ id: 5, position: 3 },
|
|
||||||
],
|
|
||||||
}
|
|
||||||
);
|
|
||||||
|
|
||||||
expect(result.text).toEqual('Hi world');
|
|
||||||
expect(result.cursors).toEqual([
|
|
||||||
{ id: 3, position: 0 },
|
|
||||||
{ id: 4, position: 0 },
|
|
||||||
{ id: 5, position: 3 },
|
|
||||||
]);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('call reconcileWithHistory', () => {
|
|
||||||
const result = reconcileWithHistory('Hello', 'Hello world', 'Hi world');
|
|
||||||
|
|
||||||
expect(result.text).toEqual('Hi world');
|
|
||||||
expect(result.history.length).toBeGreaterThan(0);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('undiff accepts bigint entries (per the Array<number | bigint | string> type)', () => {
|
|
||||||
const original = 'Hello world';
|
|
||||||
const changed = 'Hello cruel world';
|
|
||||||
|
|
||||||
// `diff` returns plain numbers; emulate a caller that supplies BigInt, which the
|
|
||||||
// public signature permits. The wasm2js build rejects raw BigInt, so the shared
|
|
||||||
// wrapper must normalise it — running this on both backends asserts the contract.
|
|
||||||
const withBigints = diff(original, changed).map((item) =>
|
|
||||||
typeof item === 'number' ? BigInt(item) : item
|
|
||||||
);
|
|
||||||
|
|
||||||
expect(withBigints.some((item) => typeof item === 'bigint')).toBe(true);
|
|
||||||
expect(undiff(original, withBigints)).toEqual(changed);
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe.each(backends)('diff and undiff are inverse [$name]', ({ api }) => {
|
|
||||||
const { diff, undiff } = api;
|
|
||||||
|
|
||||||
const resourcesPath = path.join(__dirname, '../../tests/resources');
|
|
||||||
|
|
||||||
const readFileSlice = (fileName: string, start: number, end: number): string => {
|
|
||||||
const filePath = path.join(resourcesPath, fileName);
|
|
||||||
const content = fs.readFileSync(filePath, 'utf-8');
|
|
||||||
const chars = Array.from(content); // Handle unicode properly
|
|
||||||
return chars.slice(start, Math.min(end, chars.length)).join('');
|
|
||||||
};
|
|
||||||
|
|
||||||
const files = ['pride_and_prejudice.txt', 'room_with_a_view.txt', 'blns.txt'];
|
|
||||||
|
|
||||||
const ranges = [{ start: 0, end: 50000 }];
|
|
||||||
|
|
||||||
files.forEach((file1) => {
|
|
||||||
files.forEach((file2) => {
|
|
||||||
ranges.forEach((range1) => {
|
|
||||||
ranges.forEach((range2) => {
|
|
||||||
it(`should diff & undiff ${file1}[${range1.start}..${range1.end}], ${file2}[${range2.start}..${range2.end}] without panic`, () => {
|
|
||||||
const content1 = readFileSlice(file1, range1.start, range1.end);
|
|
||||||
const content2 = readFileSlice(file2, range2.start, range2.end);
|
|
||||||
|
|
||||||
const changes = diff(content1, content2);
|
|
||||||
const actual = undiff(content1, changes);
|
|
||||||
expect(actual).toEqual(content2);
|
|
||||||
});
|
|
||||||
});
|
|
||||||
});
|
|
||||||
});
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
// React-Native-only: Hermes exposes no `WebAssembly` global, which is the whole reason
|
|
||||||
// the RN entry point links a wasm2js build. Only the wasm2js backend can satisfy this.
|
|
||||||
describe('React Native (wasm2js) Hermes parity', () => {
|
|
||||||
const { reconcile, reconcileWithHistory, diff, undiff } = rnApi;
|
|
||||||
|
|
||||||
it('runs every operation with no WebAssembly global', () => {
|
|
||||||
const descriptor = Object.getOwnPropertyDescriptor(globalThis, 'WebAssembly');
|
|
||||||
delete (globalThis as { WebAssembly?: unknown }).WebAssembly;
|
|
||||||
try {
|
|
||||||
expect((globalThis as { WebAssembly?: unknown }).WebAssembly).toBeUndefined();
|
|
||||||
|
|
||||||
expect(reconcile('Hello', 'Hello world', 'Hi world').text).toEqual('Hi world');
|
|
||||||
|
|
||||||
const changes = diff('Hello world', 'Hello cruel world');
|
|
||||||
expect(undiff('Hello world', changes)).toEqual('Hello cruel world');
|
|
||||||
|
|
||||||
expect(
|
|
||||||
reconcileWithHistory('Hello', 'Hello world', 'Hi world').history.length
|
|
||||||
).toBeGreaterThan(0);
|
|
||||||
} finally {
|
|
||||||
// Restore the global so the leak check and later suites are unaffected.
|
|
||||||
if (descriptor) {
|
|
||||||
Object.defineProperty(globalThis, 'WebAssembly', descriptor);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
@ -1,49 +0,0 @@
|
||||||
import {
|
|
||||||
CursorPosition as wasmCursorPosition,
|
|
||||||
TextWithCursors as wasmTextWithCursors,
|
|
||||||
reconcile as wasmReconcile,
|
|
||||||
reconcileWithHistory as wasmReconcileWithHistory,
|
|
||||||
diff as wasmDiff,
|
|
||||||
undiff as wasmUndiff,
|
|
||||||
initSync,
|
|
||||||
} from 'reconcile-text';
|
|
||||||
|
|
||||||
import wasmBytes from 'reconcile-text/reconcile_text_bg.wasm';
|
|
||||||
|
|
||||||
import { makeReconcileApi, type WasmBackend } from './core';
|
|
||||||
|
|
||||||
let isInitialised = false;
|
|
||||||
|
|
||||||
const backend: WasmBackend = {
|
|
||||||
CursorPosition: wasmCursorPosition,
|
|
||||||
TextWithCursors: wasmTextWithCursors,
|
|
||||||
reconcile: wasmReconcile,
|
|
||||||
reconcileWithHistory: wasmReconcileWithHistory,
|
|
||||||
diff: wasmDiff,
|
|
||||||
undiff: wasmUndiff,
|
|
||||||
ensureReady() {
|
|
||||||
if (isInitialised) {
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
|
|
||||||
const wasmBinary = Uint8Array.from(atob(wasmBytes as unknown as string), (c) =>
|
|
||||||
c.charCodeAt(0)
|
|
||||||
);
|
|
||||||
initSync({ module: wasmBinary });
|
|
||||||
|
|
||||||
isInitialised = true;
|
|
||||||
},
|
|
||||||
};
|
|
||||||
|
|
||||||
export const { reconcile, diff, undiff, reconcileWithHistory } =
|
|
||||||
makeReconcileApi(backend);
|
|
||||||
|
|
||||||
export type {
|
|
||||||
BuiltinTokenizer,
|
|
||||||
History,
|
|
||||||
CursorPosition,
|
|
||||||
TextWithCursors,
|
|
||||||
TextWithOptionalCursors,
|
|
||||||
TextWithCursorsAndHistory,
|
|
||||||
SpanWithHistory,
|
|
||||||
} from './core';
|
|
||||||
|
|
@ -1,63 +0,0 @@
|
||||||
/**
|
|
||||||
* Test utility for detecting WASM memory leaks.
|
|
||||||
*
|
|
||||||
* wasm-bindgen registers every JS-side object with a `FinalizationRegistry`.
|
|
||||||
* This detector patches `FinalizationRegistry.prototype.register` to collect
|
|
||||||
* references to all WASM objects. After each test, {@link checkForWasmLeaks}
|
|
||||||
* inspects `__wbg_ptr` on every tracked object - a non-zero pointer means
|
|
||||||
* `.free()` was never called, i.e. a leak.
|
|
||||||
*
|
|
||||||
* Install once (before any WASM calls) and call {@link checkForWasmLeaks}
|
|
||||||
* in an `afterEach` hook.
|
|
||||||
*/
|
|
||||||
|
|
||||||
let trackedObjects: object[] = [];
|
|
||||||
let originalRegister: Function | null = null;
|
|
||||||
|
|
||||||
interface WasmBindgenObject {
|
|
||||||
__wbg_ptr: number;
|
|
||||||
constructor: { name?: string };
|
|
||||||
}
|
|
||||||
|
|
||||||
function isWasmBindgenObject(target: unknown): target is WasmBindgenObject {
|
|
||||||
return (
|
|
||||||
target !== null &&
|
|
||||||
typeof target === 'object' &&
|
|
||||||
'__wbg_ptr' in (target as Record<string, unknown>)
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Patches `FinalizationRegistry.prototype.register` to track all wasm-bindgen
|
|
||||||
* objects. Safe to call multiple times (idempotent).
|
|
||||||
*/
|
|
||||||
export function installWasmLeakDetector(): void {
|
|
||||||
if (originalRegister) return;
|
|
||||||
|
|
||||||
originalRegister = FinalizationRegistry.prototype.register;
|
|
||||||
|
|
||||||
FinalizationRegistry.prototype.register = function (
|
|
||||||
target: object,
|
|
||||||
heldValue: unknown,
|
|
||||||
unregisterToken?: object
|
|
||||||
) {
|
|
||||||
if (isWasmBindgenObject(target)) {
|
|
||||||
trackedObjects.push(target);
|
|
||||||
}
|
|
||||||
return originalRegister!.call(this, target, heldValue, unregisterToken);
|
|
||||||
};
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Returns any tracked WASM objects whose `__wbg_ptr` is still non-zero
|
|
||||||
* (i.e. `.free()` was never called). Clears the tracked set afterwards.
|
|
||||||
*/
|
|
||||||
export function checkForWasmLeaks(): string[] {
|
|
||||||
const leaks = trackedObjects
|
|
||||||
.filter(isWasmBindgenObject)
|
|
||||||
.filter((obj) => obj.__wbg_ptr !== 0)
|
|
||||||
.map((obj) => `${obj.constructor?.name ?? 'Unknown'} (ptr=${obj.__wbg_ptr})`);
|
|
||||||
|
|
||||||
trackedObjects = [];
|
|
||||||
return leaks;
|
|
||||||
}
|
|
||||||
|
|
@ -1,13 +0,0 @@
|
||||||
{
|
|
||||||
"compilerOptions": {
|
|
||||||
"module": "ESNext",
|
|
||||||
"target": "ESNext",
|
|
||||||
"strict": true,
|
|
||||||
"allowSyntheticDefaultImports": true,
|
|
||||||
"moduleResolution": "bundler",
|
|
||||||
"declaration": true,
|
|
||||||
"declarationDir": "./dist/types",
|
|
||||||
"skipLibCheck": true,
|
|
||||||
"inlineSourceMap": true
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
@ -1,81 +0,0 @@
|
||||||
const path = require('path');
|
|
||||||
const { merge } = require('webpack-merge');
|
|
||||||
|
|
||||||
const common = {
|
|
||||||
optimization: {
|
|
||||||
// the consuming project should take care of minification
|
|
||||||
minimize: false,
|
|
||||||
},
|
|
||||||
resolve: {
|
|
||||||
extensions: ['.ts', '.js'],
|
|
||||||
alias: {
|
|
||||||
root: __dirname,
|
|
||||||
src: path.resolve(__dirname, 'src'),
|
|
||||||
},
|
|
||||||
},
|
|
||||||
performance: {
|
|
||||||
hints: false,
|
|
||||||
},
|
|
||||||
experiments: {
|
|
||||||
asyncWebAssembly: true,
|
|
||||||
},
|
|
||||||
module: {
|
|
||||||
rules: [
|
|
||||||
{
|
|
||||||
test: /\.ts$/,
|
|
||||||
use: ['ts-loader'],
|
|
||||||
},
|
|
||||||
{
|
|
||||||
test: /\.wasm$/,
|
|
||||||
type: 'asset/inline',
|
|
||||||
generator: {
|
|
||||||
dataUrl: (content) => content.toString('base64'),
|
|
||||||
},
|
|
||||||
},
|
|
||||||
],
|
|
||||||
},
|
|
||||||
};
|
|
||||||
|
|
||||||
module.exports = [
|
|
||||||
// Web build: real WebAssembly, instantiated synchronously from inlined base64.
|
|
||||||
merge(common, {
|
|
||||||
target: 'web',
|
|
||||||
entry: './src/index.ts',
|
|
||||||
output: {
|
|
||||||
path: path.resolve(__dirname, 'dist'),
|
|
||||||
filename: 'reconcile.web.js',
|
|
||||||
library: {
|
|
||||||
name: 'reconcile',
|
|
||||||
type: 'umd',
|
|
||||||
},
|
|
||||||
globalObject: 'this',
|
|
||||||
},
|
|
||||||
}),
|
|
||||||
|
|
||||||
// Node build: real WebAssembly.
|
|
||||||
merge(common, {
|
|
||||||
target: 'node',
|
|
||||||
entry: './src/index.ts',
|
|
||||||
output: {
|
|
||||||
path: path.resolve(__dirname, 'dist'),
|
|
||||||
filename: 'reconcile.node.js',
|
|
||||||
libraryTarget: 'commonjs2',
|
|
||||||
},
|
|
||||||
}),
|
|
||||||
|
|
||||||
// React Native build: wasm2js (pure JS), for Hermes which has no
|
|
||||||
// `WebAssembly` global. Sources come from `pkg-rn/`
|
|
||||||
merge(common, {
|
|
||||||
target: 'web',
|
|
||||||
entry: './src/index.rn.ts',
|
|
||||||
output: {
|
|
||||||
path: path.resolve(__dirname, 'dist'),
|
|
||||||
filename: 'reconcile.rn.js',
|
|
||||||
library: {
|
|
||||||
name: 'reconcile',
|
|
||||||
type: 'umd',
|
|
||||||
},
|
|
||||||
globalObject: 'this',
|
|
||||||
},
|
|
||||||
}),
|
|
||||||
];
|
|
||||||
10
reconcile-python/.gitignore
vendored
10
reconcile-python/.gitignore
vendored
|
|
@ -1,10 +0,0 @@
|
||||||
.venv/
|
|
||||||
.pytest_cache/
|
|
||||||
.ruff_cache/
|
|
||||||
__pycache__/
|
|
||||||
*.egg-info/
|
|
||||||
*.so
|
|
||||||
*.dylib
|
|
||||||
*.dSYM/
|
|
||||||
dist/
|
|
||||||
README.md
|
|
||||||
193
reconcile-python/Cargo.lock
generated
193
reconcile-python/Cargo.lock
generated
|
|
@ -1,193 +0,0 @@
|
||||||
# This file is automatically @generated by Cargo.
|
|
||||||
# It is not intended for manual editing.
|
|
||||||
version = 4
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "cc"
|
|
||||||
version = "1.2.63"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "556e016178bb5662a08681bbe0f00f8e17631781a4dfc8c45e466e4b185ec27f"
|
|
||||||
dependencies = [
|
|
||||||
"find-msvc-tools",
|
|
||||||
"shlex",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "find-msvc-tools"
|
|
||||||
version = "0.1.9"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "heck"
|
|
||||||
version = "0.5.0"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "libc"
|
|
||||||
version = "0.2.183"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "b5b646652bf6661599e1da8901b3b9522896f01e736bad5f723fe7a3a27f899d"
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "once_cell"
|
|
||||||
version = "1.21.3"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "portable-atomic"
|
|
||||||
version = "1.13.1"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "c33a9471896f1c69cecef8d20cbe2f7accd12527ce60845ff44c153bb2a21b49"
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "proc-macro2"
|
|
||||||
version = "1.0.106"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
|
|
||||||
dependencies = [
|
|
||||||
"unicode-ident",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "pyo3"
|
|
||||||
version = "0.28.2"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "cf85e27e86080aafd5a22eae58a162e133a589551542b3e5cee4beb27e54f8e1"
|
|
||||||
dependencies = [
|
|
||||||
"libc",
|
|
||||||
"once_cell",
|
|
||||||
"portable-atomic",
|
|
||||||
"pyo3-build-config",
|
|
||||||
"pyo3-ffi",
|
|
||||||
"pyo3-macros",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "pyo3-build-config"
|
|
||||||
version = "0.28.2"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "8bf94ee265674bf76c09fa430b0e99c26e319c945d96ca0d5a8215f31bf81cf7"
|
|
||||||
dependencies = [
|
|
||||||
"python3-dll-a",
|
|
||||||
"target-lexicon",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "pyo3-ffi"
|
|
||||||
version = "0.28.2"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "491aa5fc66d8059dd44a75f4580a2962c1862a1c2945359db36f6c2818b748dc"
|
|
||||||
dependencies = [
|
|
||||||
"libc",
|
|
||||||
"pyo3-build-config",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "pyo3-macros"
|
|
||||||
version = "0.28.2"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "f5d671734e9d7a43449f8480f8b38115df67bef8d21f76837fa75ee7aaa5e52e"
|
|
||||||
dependencies = [
|
|
||||||
"proc-macro2",
|
|
||||||
"pyo3-macros-backend",
|
|
||||||
"quote",
|
|
||||||
"syn",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "pyo3-macros-backend"
|
|
||||||
version = "0.28.2"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "22faaa1ce6c430a1f71658760497291065e6450d7b5dc2bcf254d49f66ee700a"
|
|
||||||
dependencies = [
|
|
||||||
"heck",
|
|
||||||
"proc-macro2",
|
|
||||||
"pyo3-build-config",
|
|
||||||
"quote",
|
|
||||||
"syn",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "python3-dll-a"
|
|
||||||
version = "0.2.15"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "d80ba7540edb18890d444c5aa8e1f1f99b1bdf26fb26ae383135325f4a36042b"
|
|
||||||
dependencies = [
|
|
||||||
"cc",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "quote"
|
|
||||||
version = "1.0.45"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
|
|
||||||
dependencies = [
|
|
||||||
"proc-macro2",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "reconcile-text"
|
|
||||||
version = "0.12.1"
|
|
||||||
dependencies = [
|
|
||||||
"thiserror",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "reconcile-text-python"
|
|
||||||
version = "0.12.1"
|
|
||||||
dependencies = [
|
|
||||||
"pyo3",
|
|
||||||
"reconcile-text",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "shlex"
|
|
||||||
version = "2.0.1"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "f8fadd59c855ef2080decdef8ff161eb6661b86933c9d82e5ba29dc602a55aba"
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "syn"
|
|
||||||
version = "2.0.117"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
|
|
||||||
dependencies = [
|
|
||||||
"proc-macro2",
|
|
||||||
"quote",
|
|
||||||
"unicode-ident",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "target-lexicon"
|
|
||||||
version = "0.13.5"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "adb6935a6f5c20170eeceb1a3835a49e12e19d792f6dd344ccc76a985ca5a6ca"
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "thiserror"
|
|
||||||
version = "2.0.18"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
|
|
||||||
dependencies = [
|
|
||||||
"thiserror-impl",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "thiserror-impl"
|
|
||||||
version = "2.0.18"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "ebc4ee7f67670e9b64d05fa4253e753e016c6c95ff35b89b7941d6b856dec1d5"
|
|
||||||
dependencies = [
|
|
||||||
"proc-macro2",
|
|
||||||
"quote",
|
|
||||||
"syn",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "unicode-ident"
|
|
||||||
version = "1.0.24"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
|
|
||||||
|
|
@ -1,16 +0,0 @@
|
||||||
[package]
|
|
||||||
name = "reconcile-text-python"
|
|
||||||
version = "0.12.1"
|
|
||||||
edition = "2024"
|
|
||||||
rust-version = "1.94"
|
|
||||||
authors = ["Andras Schmelczer <andras@schmelczer.dev>"]
|
|
||||||
license = "MIT"
|
|
||||||
publish = false
|
|
||||||
|
|
||||||
[lib]
|
|
||||||
name = "_native"
|
|
||||||
crate-type = ["cdylib"]
|
|
||||||
|
|
||||||
[dependencies]
|
|
||||||
reconcile-text = { path = ".." }
|
|
||||||
pyo3 = { version = "0.28.2", features = ["extension-module", "abi3-py39", "generate-import-lib"] }
|
|
||||||
|
|
@ -1,52 +0,0 @@
|
||||||
[build-system]
|
|
||||||
requires = ["maturin>=1.0,<2.0"]
|
|
||||||
build-backend = "maturin"
|
|
||||||
|
|
||||||
[project]
|
|
||||||
name = "reconcile-text"
|
|
||||||
version = "0.12.1"
|
|
||||||
description = "Intelligent 3-way text merging with automated conflict resolution"
|
|
||||||
readme = "README.md"
|
|
||||||
license = { text = "MIT" }
|
|
||||||
authors = [{ name = "Andras Schmelczer", email = "andras@schmelczer.dev" }]
|
|
||||||
requires-python = ">=3.9"
|
|
||||||
classifiers = [
|
|
||||||
"Programming Language :: Rust",
|
|
||||||
"Programming Language :: Python :: Implementation :: CPython",
|
|
||||||
"Programming Language :: Python :: Implementation :: PyPy",
|
|
||||||
"License :: OSI Approved :: MIT License",
|
|
||||||
"Operating System :: OS Independent",
|
|
||||||
"Typing :: Typed",
|
|
||||||
]
|
|
||||||
keywords = ["merge", "OT", "CRDT", "3-way", "diff", "text"]
|
|
||||||
|
|
||||||
[dependency-groups]
|
|
||||||
dev = ["maturin>=1.0,<2.0", "pytest>=8", "ruff>=0.15", "pyright>=1"]
|
|
||||||
|
|
||||||
[project.urls]
|
|
||||||
Homepage = "https://schmelczer.dev/reconcile"
|
|
||||||
Repository = "https://github.com/schmelczer/reconcile"
|
|
||||||
Issues = "https://github.com/schmelczer/reconcile/issues"
|
|
||||||
|
|
||||||
[tool.maturin]
|
|
||||||
manifest-path = "Cargo.toml"
|
|
||||||
module-name = "reconcile_text._native"
|
|
||||||
python-source = "python"
|
|
||||||
|
|
||||||
[tool.pytest.ini_options]
|
|
||||||
testpaths = ["tests"]
|
|
||||||
|
|
||||||
[tool.ruff]
|
|
||||||
target-version = "py39"
|
|
||||||
line-length = 100
|
|
||||||
|
|
||||||
[tool.ruff.lint]
|
|
||||||
select = ["E", "F", "W", "I", "UP", "B", "SIM", "RUF"]
|
|
||||||
|
|
||||||
[tool.ruff.lint.isort]
|
|
||||||
known-first-party = ["reconcile_text"]
|
|
||||||
|
|
||||||
[tool.pyright]
|
|
||||||
pythonVersion = "3.9"
|
|
||||||
typeCheckingMode = "strict"
|
|
||||||
include = ["python", "tests"]
|
|
||||||
|
|
@ -1,165 +0,0 @@
|
||||||
"""Intelligent 3-way text merging with automated conflict resolution."""
|
|
||||||
|
|
||||||
from __future__ import annotations
|
|
||||||
|
|
||||||
from typing import Literal, TypedDict, Union
|
|
||||||
|
|
||||||
from reconcile_text._native import diff as _diff
|
|
||||||
from reconcile_text._native import reconcile as _reconcile
|
|
||||||
from reconcile_text._native import reconcile_with_history as _reconcile_with_history
|
|
||||||
from reconcile_text._native import undiff as _undiff
|
|
||||||
|
|
||||||
BuiltinTokenizer = Literal["Character", "Line", "Markdown", "Word"]
|
|
||||||
"""Tokenization strategy for text merging."""
|
|
||||||
|
|
||||||
History = Literal[
|
|
||||||
"Unchanged", "AddedFromLeft", "AddedFromRight", "RemovedFromLeft", "RemovedFromRight"
|
|
||||||
]
|
|
||||||
"""Provenance label for each span in a merge result."""
|
|
||||||
|
|
||||||
|
|
||||||
class CursorPosition(TypedDict):
|
|
||||||
"""A cursor position within a text document."""
|
|
||||||
|
|
||||||
id: int
|
|
||||||
"""Unique identifier for the cursor."""
|
|
||||||
position: int
|
|
||||||
"""Character position in the text (0-based)."""
|
|
||||||
|
|
||||||
|
|
||||||
class TextWithCursors(TypedDict):
|
|
||||||
"""A text document with associated cursor positions."""
|
|
||||||
|
|
||||||
text: str
|
|
||||||
"""The document content."""
|
|
||||||
cursors: list[CursorPosition]
|
|
||||||
"""Cursor positions within the text."""
|
|
||||||
|
|
||||||
|
|
||||||
class SpanWithHistory(TypedDict):
|
|
||||||
"""A text span annotated with its origin in a merge result."""
|
|
||||||
|
|
||||||
text: str
|
|
||||||
"""The text content of this span."""
|
|
||||||
history: History
|
|
||||||
"""Which source this span came from."""
|
|
||||||
|
|
||||||
|
|
||||||
class TextWithCursorsAndHistory(TypedDict):
|
|
||||||
"""A merged text document with cursor positions and change provenance."""
|
|
||||||
|
|
||||||
text: str
|
|
||||||
"""The merged document content."""
|
|
||||||
cursors: list[CursorPosition]
|
|
||||||
"""Repositioned cursor positions."""
|
|
||||||
history: list[SpanWithHistory]
|
|
||||||
"""Provenance information for each text span."""
|
|
||||||
|
|
||||||
|
|
||||||
TextInput = Union[str, TextWithCursors]
|
|
||||||
"""Input type for text arguments: either a plain string or a dict with text and cursors."""
|
|
||||||
|
|
||||||
|
|
||||||
def reconcile(
|
|
||||||
parent: str,
|
|
||||||
left: TextInput,
|
|
||||||
right: TextInput,
|
|
||||||
tokenizer: BuiltinTokenizer = "Word",
|
|
||||||
) -> TextWithCursors:
|
|
||||||
"""Merge three versions of text using conflict-free resolution.
|
|
||||||
|
|
||||||
Takes a parent text and two concurrent edits (left and right), returning
|
|
||||||
the merged result with automatically repositioned cursors.
|
|
||||||
|
|
||||||
Args:
|
|
||||||
parent: The original text that both sides diverged from.
|
|
||||||
left: The left edit (string or dict with "text" and "cursors").
|
|
||||||
right: The right edit (string or dict with "text" and "cursors").
|
|
||||||
tokenizer: Tokenization strategy. Defaults to "Word".
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
A dict with "text" (merged string) and "cursors" (repositioned cursor list).
|
|
||||||
"""
|
|
||||||
return _reconcile(parent, left, right, tokenizer) # type: ignore[return-value]
|
|
||||||
|
|
||||||
|
|
||||||
def reconcile_with_history(
|
|
||||||
parent: str,
|
|
||||||
left: TextInput,
|
|
||||||
right: TextInput,
|
|
||||||
tokenizer: BuiltinTokenizer = "Word",
|
|
||||||
) -> TextWithCursorsAndHistory:
|
|
||||||
"""Merge three versions of text and return provenance history.
|
|
||||||
|
|
||||||
Like `reconcile`, but also returns which source each text span came from.
|
|
||||||
|
|
||||||
Args:
|
|
||||||
parent: The original text that both sides diverged from.
|
|
||||||
left: The left edit (string or dict with "text" and "cursors").
|
|
||||||
right: The right edit (string or dict with "text" and "cursors").
|
|
||||||
tokenizer: Tokenization strategy. Defaults to "Word".
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
A dict with "text", "cursors", and "history".
|
|
||||||
"""
|
|
||||||
return _reconcile_with_history(parent, left, right, tokenizer) # type: ignore[return-value]
|
|
||||||
|
|
||||||
|
|
||||||
def diff(
|
|
||||||
parent: str,
|
|
||||||
changed: TextInput,
|
|
||||||
tokenizer: BuiltinTokenizer = "Word",
|
|
||||||
) -> list[int | str]:
|
|
||||||
"""Generate a compact diff between two texts.
|
|
||||||
|
|
||||||
Returns retain counts (positive ints), delete counts (negative ints),
|
|
||||||
and inserted strings.
|
|
||||||
|
|
||||||
Args:
|
|
||||||
parent: The original text.
|
|
||||||
changed: The modified text (string or dict with "text" and "cursors").
|
|
||||||
tokenizer: Tokenization strategy. Defaults to "Word".
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
A list of ints and strings representing the diff.
|
|
||||||
|
|
||||||
Raises:
|
|
||||||
ValueError: If the diff computation overflows.
|
|
||||||
"""
|
|
||||||
return _diff(parent, changed, tokenizer) # type: ignore[return-value]
|
|
||||||
|
|
||||||
|
|
||||||
def undiff(
|
|
||||||
parent: str,
|
|
||||||
diff: list[int | str],
|
|
||||||
tokenizer: BuiltinTokenizer = "Word",
|
|
||||||
) -> str:
|
|
||||||
"""Apply a compact diff to reconstruct the changed text.
|
|
||||||
|
|
||||||
Args:
|
|
||||||
parent: The original text.
|
|
||||||
diff: A list of ints and strings (as produced by `diff`).
|
|
||||||
tokenizer: Tokenization strategy. Defaults to "Word".
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
The reconstructed text.
|
|
||||||
|
|
||||||
Raises:
|
|
||||||
ValueError: If the diff format is invalid.
|
|
||||||
"""
|
|
||||||
return _undiff(parent, diff, tokenizer)
|
|
||||||
|
|
||||||
|
|
||||||
__all__ = [
|
|
||||||
"BuiltinTokenizer",
|
|
||||||
"CursorPosition",
|
|
||||||
"History",
|
|
||||||
"SpanWithHistory",
|
|
||||||
"TextInput",
|
|
||||||
"TextWithCursors",
|
|
||||||
"TextWithCursorsAndHistory",
|
|
||||||
"diff",
|
|
||||||
"reconcile",
|
|
||||||
"reconcile_with_history",
|
|
||||||
"undiff",
|
|
||||||
]
|
|
||||||
|
|
@ -1,24 +0,0 @@
|
||||||
from typing import Any
|
|
||||||
|
|
||||||
def reconcile(
|
|
||||||
parent: str,
|
|
||||||
left: Any,
|
|
||||||
right: Any,
|
|
||||||
tokenizer: str = "Word",
|
|
||||||
) -> dict[str, Any]: ...
|
|
||||||
def reconcile_with_history(
|
|
||||||
parent: str,
|
|
||||||
left: Any,
|
|
||||||
right: Any,
|
|
||||||
tokenizer: str = "Word",
|
|
||||||
) -> dict[str, Any]: ...
|
|
||||||
def diff(
|
|
||||||
parent: str,
|
|
||||||
changed: Any,
|
|
||||||
tokenizer: str = "Word",
|
|
||||||
) -> list[int | str]: ...
|
|
||||||
def undiff(
|
|
||||||
parent: str,
|
|
||||||
diff: list[int | str],
|
|
||||||
tokenizer: str = "Word",
|
|
||||||
) -> str: ...
|
|
||||||
|
|
@ -1,235 +0,0 @@
|
||||||
use pyo3::prelude::*;
|
|
||||||
use pyo3::types::{PyDict, PyList};
|
|
||||||
use reconcile_text::{
|
|
||||||
BuiltinTokenizer, CursorPosition, EditedText, NumberOrText, TextWithCursors,
|
|
||||||
};
|
|
||||||
|
|
||||||
fn parse_tokenizer(tokenizer: &str) -> PyResult<BuiltinTokenizer> {
|
|
||||||
match tokenizer {
|
|
||||||
"Character" => Ok(BuiltinTokenizer::Character),
|
|
||||||
"Line" => Ok(BuiltinTokenizer::Line),
|
|
||||||
"Markdown" => Ok(BuiltinTokenizer::Markdown),
|
|
||||||
"Word" => Ok(BuiltinTokenizer::Word),
|
|
||||||
_ => Err(pyo3::exceptions::PyValueError::new_err(format!(
|
|
||||||
"Unknown tokenizer '{tokenizer}', expected Character, Line, Markdown, or Word"
|
|
||||||
))),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
fn extract_text_with_cursors(input: &Bound<'_, PyAny>) -> PyResult<TextWithCursors> {
|
|
||||||
if let Ok(text) = input.extract::<String>() {
|
|
||||||
return Ok(TextWithCursors::from(text));
|
|
||||||
}
|
|
||||||
|
|
||||||
let dict = input.cast::<PyDict>()?;
|
|
||||||
|
|
||||||
let text: String = dict
|
|
||||||
.get_item("text")?
|
|
||||||
.ok_or_else(|| pyo3::exceptions::PyKeyError::new_err("text"))?
|
|
||||||
.extract()?;
|
|
||||||
|
|
||||||
let cursors = match dict.get_item("cursors")? {
|
|
||||||
Some(obj) if !obj.is_none() => {
|
|
||||||
let list = obj.cast::<PyList>()?;
|
|
||||||
let mut cursors = Vec::with_capacity(list.len());
|
|
||||||
for item in list {
|
|
||||||
let cursor_dict = item.cast::<PyDict>()?;
|
|
||||||
let id: usize = cursor_dict
|
|
||||||
.get_item("id")?
|
|
||||||
.ok_or_else(|| pyo3::exceptions::PyKeyError::new_err("id"))?
|
|
||||||
.extract()?;
|
|
||||||
let position: usize = cursor_dict
|
|
||||||
.get_item("position")?
|
|
||||||
.ok_or_else(|| pyo3::exceptions::PyKeyError::new_err("position"))?
|
|
||||||
.extract()?;
|
|
||||||
cursors.push(CursorPosition::new(id, position));
|
|
||||||
}
|
|
||||||
cursors
|
|
||||||
}
|
|
||||||
_ => Vec::new(),
|
|
||||||
};
|
|
||||||
|
|
||||||
Ok(TextWithCursors::new(text, cursors))
|
|
||||||
}
|
|
||||||
|
|
||||||
fn text_with_cursors_to_dict<'py>(
|
|
||||||
py: Python<'py>,
|
|
||||||
twc: &TextWithCursors,
|
|
||||||
) -> PyResult<Bound<'py, PyDict>> {
|
|
||||||
let dict = PyDict::new(py);
|
|
||||||
dict.set_item("text", twc.text())?;
|
|
||||||
|
|
||||||
let cursors = PyList::new(
|
|
||||||
py,
|
|
||||||
twc.cursors().iter().map(|c| {
|
|
||||||
let d = PyDict::new(py);
|
|
||||||
d.set_item("id", c.id()).unwrap();
|
|
||||||
d.set_item("position", c.char_index()).unwrap();
|
|
||||||
d
|
|
||||||
}),
|
|
||||||
)?;
|
|
||||||
dict.set_item("cursors", cursors)?;
|
|
||||||
|
|
||||||
Ok(dict)
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Merge three versions of text using conflict-free resolution.
|
|
||||||
///
|
|
||||||
/// Takes a parent text and two concurrent edits (left and right), returning
|
|
||||||
/// the merged result with automatically repositioned cursors.
|
|
||||||
///
|
|
||||||
/// Args:
|
|
||||||
/// parent: The original text that both sides diverged from.
|
|
||||||
/// left: The left edit, either a string or a dict with "text" and "cursors" keys.
|
|
||||||
/// right: The right edit, either a string or a dict with "text" and "cursors" keys.
|
|
||||||
/// tokenizer: Tokenization strategy - "Word" (default), "Character", "Line", or "Markdown".
|
|
||||||
///
|
|
||||||
/// Returns:
|
|
||||||
/// A dict with "text" (merged string) and "cursors" (list of repositioned cursors).
|
|
||||||
#[pyfunction]
|
|
||||||
#[pyo3(signature = (parent, left, right, tokenizer = "Word"))]
|
|
||||||
fn reconcile<'py>(
|
|
||||||
py: Python<'py>,
|
|
||||||
parent: &str,
|
|
||||||
left: &Bound<'py, PyAny>,
|
|
||||||
right: &Bound<'py, PyAny>,
|
|
||||||
tokenizer: &str,
|
|
||||||
) -> PyResult<Bound<'py, PyDict>> {
|
|
||||||
let tokenizer = parse_tokenizer(tokenizer)?;
|
|
||||||
let left = extract_text_with_cursors(left)?;
|
|
||||||
let right = extract_text_with_cursors(right)?;
|
|
||||||
|
|
||||||
let result = reconcile_text::reconcile(parent, &left, &right, &*tokenizer).apply();
|
|
||||||
text_with_cursors_to_dict(py, &result)
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Merge three versions of text and return provenance history.
|
|
||||||
///
|
|
||||||
/// Like `reconcile`, but also returns which source each text span came from.
|
|
||||||
///
|
|
||||||
/// Args:
|
|
||||||
/// parent: The original text that both sides diverged from.
|
|
||||||
/// left: The left edit, either a string or a dict with "text" and "cursors" keys.
|
|
||||||
/// right: The right edit, either a string or a dict with "text" and "cursors" keys.
|
|
||||||
/// tokenizer: Tokenization strategy - "Word" (default), "Character", "Line", or "Markdown".
|
|
||||||
///
|
|
||||||
/// Returns:
|
|
||||||
/// A dict with "text", "cursors", and "history" (list of dicts with "text" and "history" keys).
|
|
||||||
#[pyfunction]
|
|
||||||
#[pyo3(signature = (parent, left, right, tokenizer = "Word"))]
|
|
||||||
fn reconcile_with_history<'py>(
|
|
||||||
py: Python<'py>,
|
|
||||||
parent: &str,
|
|
||||||
left: &Bound<'py, PyAny>,
|
|
||||||
right: &Bound<'py, PyAny>,
|
|
||||||
tokenizer: &str,
|
|
||||||
) -> PyResult<Bound<'py, PyDict>> {
|
|
||||||
let tokenizer = parse_tokenizer(tokenizer)?;
|
|
||||||
let left = extract_text_with_cursors(left)?;
|
|
||||||
let right = extract_text_with_cursors(right)?;
|
|
||||||
|
|
||||||
let reconciled = reconcile_text::reconcile(parent, &left, &right, &*tokenizer);
|
|
||||||
let (text_with_cursors, history_spans) = reconciled.apply_with_all();
|
|
||||||
|
|
||||||
let dict = text_with_cursors_to_dict(py, &text_with_cursors)?;
|
|
||||||
|
|
||||||
let history = PyList::new(
|
|
||||||
py,
|
|
||||||
history_spans.iter().map(|span| {
|
|
||||||
let d = PyDict::new(py);
|
|
||||||
d.set_item("text", span.text()).unwrap();
|
|
||||||
d.set_item("history", format!("{:?}", span.history()))
|
|
||||||
.unwrap();
|
|
||||||
d
|
|
||||||
}),
|
|
||||||
)?;
|
|
||||||
dict.set_item("history", history)?;
|
|
||||||
|
|
||||||
Ok(dict)
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Generate a compact diff between two texts.
|
|
||||||
///
|
|
||||||
/// Returns a list of retain counts (positive ints), delete counts (negative ints),
|
|
||||||
/// and inserted strings.
|
|
||||||
///
|
|
||||||
/// Args:
|
|
||||||
/// parent: The original text.
|
|
||||||
/// changed: The modified text, either a string or a dict with "text" and "cursors" keys.
|
|
||||||
/// tokenizer: Tokenization strategy - "Word" (default), "Character", "Line", or "Markdown".
|
|
||||||
///
|
|
||||||
/// Returns:
|
|
||||||
/// A list of ints and strings representing the diff.
|
|
||||||
///
|
|
||||||
/// Raises:
|
|
||||||
/// ValueError: If the diff computation overflows.
|
|
||||||
#[pyfunction]
|
|
||||||
#[pyo3(signature = (parent, changed, tokenizer = "Word"))]
|
|
||||||
fn diff<'py>(
|
|
||||||
py: Python<'py>,
|
|
||||||
parent: &str,
|
|
||||||
changed: &Bound<'py, PyAny>,
|
|
||||||
tokenizer: &str,
|
|
||||||
) -> PyResult<Bound<'py, PyList>> {
|
|
||||||
let tokenizer = parse_tokenizer(tokenizer)?;
|
|
||||||
let changed = extract_text_with_cursors(changed)?;
|
|
||||||
|
|
||||||
let edited = EditedText::from_strings_with_tokenizer(parent, &changed, &*tokenizer);
|
|
||||||
let diff_result = edited
|
|
||||||
.to_diff()
|
|
||||||
.map_err(|e| pyo3::exceptions::PyValueError::new_err(e.to_string()))?;
|
|
||||||
|
|
||||||
let list = PyList::empty(py);
|
|
||||||
for item in diff_result {
|
|
||||||
match item {
|
|
||||||
NumberOrText::Number(n) => list.append(n)?,
|
|
||||||
NumberOrText::Text(s) => list.append(s)?,
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
Ok(list)
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Apply a compact diff to a parent text to reconstruct the changed version.
|
|
||||||
///
|
|
||||||
/// Args:
|
|
||||||
/// parent: The original text.
|
|
||||||
/// diff: A list of ints and strings (as produced by `diff`).
|
|
||||||
/// tokenizer: Tokenization strategy - "Word" (default), "Character", "Line", or "Markdown".
|
|
||||||
///
|
|
||||||
/// Returns:
|
|
||||||
/// The reconstructed text.
|
|
||||||
///
|
|
||||||
/// Raises:
|
|
||||||
/// ValueError: If the diff format is invalid.
|
|
||||||
#[pyfunction]
|
|
||||||
#[pyo3(signature = (parent, diff, tokenizer = "Word"))]
|
|
||||||
fn undiff(parent: &str, diff: &Bound<'_, PyList>, tokenizer: &str) -> PyResult<String> {
|
|
||||||
let tokenizer = parse_tokenizer(tokenizer)?;
|
|
||||||
|
|
||||||
let mut parsed: Vec<NumberOrText> = Vec::with_capacity(diff.len());
|
|
||||||
for item in diff {
|
|
||||||
if let Ok(n) = item.extract::<i64>() {
|
|
||||||
parsed.push(NumberOrText::Number(n));
|
|
||||||
} else if let Ok(s) = item.extract::<String>() {
|
|
||||||
parsed.push(NumberOrText::Text(s));
|
|
||||||
} else {
|
|
||||||
return Err(pyo3::exceptions::PyTypeError::new_err(
|
|
||||||
"Diff items must be int or str",
|
|
||||||
));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
EditedText::from_diff(parent, parsed, &*tokenizer)
|
|
||||||
.map(|edited| edited.apply().text())
|
|
||||||
.map_err(|e| pyo3::exceptions::PyValueError::new_err(e.to_string()))
|
|
||||||
}
|
|
||||||
|
|
||||||
#[pymodule]
|
|
||||||
fn _native(m: &Bound<'_, PyModule>) -> PyResult<()> {
|
|
||||||
m.add_function(wrap_pyfunction!(reconcile, m)?)?;
|
|
||||||
m.add_function(wrap_pyfunction!(reconcile_with_history, m)?)?;
|
|
||||||
m.add_function(wrap_pyfunction!(diff, m)?)?;
|
|
||||||
m.add_function(wrap_pyfunction!(undiff, m)?)?;
|
|
||||||
Ok(())
|
|
||||||
}
|
|
||||||
|
|
@ -1,179 +0,0 @@
|
||||||
from __future__ import annotations
|
|
||||||
|
|
||||||
import subprocess
|
|
||||||
import sys
|
|
||||||
from pathlib import Path
|
|
||||||
|
|
||||||
import pytest
|
|
||||||
|
|
||||||
from reconcile_text import diff, reconcile, reconcile_with_history, undiff
|
|
||||||
|
|
||||||
EXAMPLES_DIR = Path(__file__).resolve().parent.parent.parent / "examples"
|
|
||||||
RESOURCES_DIR = Path(__file__).resolve().parent.parent.parent / "tests" / "resources"
|
|
||||||
|
|
||||||
FILES = ["pride_and_prejudice.txt", "room_with_a_view.txt", "blns.txt"]
|
|
||||||
|
|
||||||
|
|
||||||
class TestReconcile:
|
|
||||||
def test_basic_merge(self) -> None:
|
|
||||||
result = reconcile("Hello", "Hello world", "Hi world")
|
|
||||||
assert result["text"] == "Hi world"
|
|
||||||
|
|
||||||
def test_three_way_merge(self) -> None:
|
|
||||||
parent = "Merging text is hard!"
|
|
||||||
left = "Merging text is easy!"
|
|
||||||
right = "With reconcile, merging documents is hard!"
|
|
||||||
|
|
||||||
result = reconcile(parent, left, right)
|
|
||||||
assert result["text"] == "With reconcile, merging documents is easy!"
|
|
||||||
|
|
||||||
def test_with_cursors(self) -> None:
|
|
||||||
result = reconcile(
|
|
||||||
"Hello",
|
|
||||||
{"text": "Hello world", "cursors": [{"id": 3, "position": 2}]},
|
|
||||||
{
|
|
||||||
"text": "Hi world",
|
|
||||||
"cursors": [{"id": 4, "position": 0}, {"id": 5, "position": 3}],
|
|
||||||
},
|
|
||||||
)
|
|
||||||
|
|
||||||
assert result["text"] == "Hi world"
|
|
||||||
assert result["cursors"] == [
|
|
||||||
{"id": 3, "position": 0},
|
|
||||||
{"id": 4, "position": 0},
|
|
||||||
{"id": 5, "position": 3},
|
|
||||||
]
|
|
||||||
|
|
||||||
def test_character_tokenizer(self) -> None:
|
|
||||||
result = reconcile("abc", "axc", "abyc", "Character")
|
|
||||||
assert result["text"] == "axyc"
|
|
||||||
|
|
||||||
def test_line_tokenizer(self) -> None:
|
|
||||||
parent = "line1\nline2\nline3\n"
|
|
||||||
left = "line1\nmodified\nline3\n"
|
|
||||||
right = "line1\nline2\nnew line\n"
|
|
||||||
|
|
||||||
result = reconcile(parent, left, right, "Line")
|
|
||||||
assert result["text"] == "line1\nmodified\nnew line\n"
|
|
||||||
|
|
||||||
def test_empty_texts(self) -> None:
|
|
||||||
result = reconcile("", "", "")
|
|
||||||
assert result["text"] == ""
|
|
||||||
assert result["cursors"] == []
|
|
||||||
|
|
||||||
def test_invalid_tokenizer(self) -> None:
|
|
||||||
with pytest.raises(ValueError, match="Unknown tokenizer"):
|
|
||||||
reconcile("a", "b", "c", "Invalid") # type: ignore[arg-type]
|
|
||||||
|
|
||||||
|
|
||||||
class TestReconcileWithHistory:
|
|
||||||
def test_returns_history(self) -> None:
|
|
||||||
result = reconcile_with_history(
|
|
||||||
"Merging text is hard!",
|
|
||||||
"Merging text is easy!",
|
|
||||||
"With reconcile, merging documents is hard!",
|
|
||||||
)
|
|
||||||
|
|
||||||
assert result["text"] == "With reconcile, merging documents is easy!"
|
|
||||||
assert len(result["history"]) > 0
|
|
||||||
assert all("text" in span and "history" in span for span in result["history"])
|
|
||||||
|
|
||||||
def test_history_values(self) -> None:
|
|
||||||
valid_histories = {
|
|
||||||
"Unchanged",
|
|
||||||
"AddedFromLeft",
|
|
||||||
"AddedFromRight",
|
|
||||||
"RemovedFromLeft",
|
|
||||||
"RemovedFromRight",
|
|
||||||
}
|
|
||||||
result = reconcile_with_history("Hello", "Hello world", "Hi")
|
|
||||||
for span in result["history"]:
|
|
||||||
assert span["history"] in valid_histories
|
|
||||||
|
|
||||||
|
|
||||||
class TestDiff:
|
|
||||||
def test_basic_diff(self) -> None:
|
|
||||||
result = diff("Hello world", "Hello beautiful world")
|
|
||||||
assert isinstance(result, list)
|
|
||||||
assert all(isinstance(item, (int, str)) for item in result)
|
|
||||||
|
|
||||||
def test_no_change(self) -> None:
|
|
||||||
result = diff("same text", "same text")
|
|
||||||
# A retain-only diff
|
|
||||||
assert all(isinstance(item, int) and item > 0 for item in result)
|
|
||||||
|
|
||||||
|
|
||||||
class TestUndiff:
|
|
||||||
def test_roundtrip(self) -> None:
|
|
||||||
original = "Hello world"
|
|
||||||
changed = "Hello beautiful world"
|
|
||||||
|
|
||||||
d = diff(original, changed)
|
|
||||||
reconstructed = undiff(original, d)
|
|
||||||
assert reconstructed == changed
|
|
||||||
|
|
||||||
def test_empty_roundtrip(self) -> None:
|
|
||||||
d = diff("", "")
|
|
||||||
assert undiff("", d) == ""
|
|
||||||
|
|
||||||
def test_invalid_diff(self) -> None:
|
|
||||||
with pytest.raises(ValueError):
|
|
||||||
undiff("short", [100])
|
|
||||||
|
|
||||||
|
|
||||||
class TestExamples:
|
|
||||||
def test_merge_file_stdout(self, tmp_path: Path) -> None:
|
|
||||||
(tmp_path / "base.txt").write_text("Hello world")
|
|
||||||
(tmp_path / "mine.txt").write_text("Hello beautiful world")
|
|
||||||
(tmp_path / "theirs.txt").write_text("Hi world")
|
|
||||||
|
|
||||||
result = subprocess.run(
|
|
||||||
[
|
|
||||||
sys.executable,
|
|
||||||
str(EXAMPLES_DIR / "merge_file.py"),
|
|
||||||
str(tmp_path / "mine.txt"),
|
|
||||||
str(tmp_path / "base.txt"),
|
|
||||||
str(tmp_path / "theirs.txt"),
|
|
||||||
],
|
|
||||||
capture_output=True,
|
|
||||||
text=True,
|
|
||||||
check=True,
|
|
||||||
)
|
|
||||||
|
|
||||||
assert result.stdout == "Hi beautiful world"
|
|
||||||
|
|
||||||
def test_merge_file_output_file(self, tmp_path: Path) -> None:
|
|
||||||
(tmp_path / "base.txt").write_text("Hello world")
|
|
||||||
(tmp_path / "mine.txt").write_text("Hello beautiful world")
|
|
||||||
(tmp_path / "theirs.txt").write_text("Hi world")
|
|
||||||
output = tmp_path / "output.txt"
|
|
||||||
|
|
||||||
subprocess.run(
|
|
||||||
[
|
|
||||||
sys.executable,
|
|
||||||
str(EXAMPLES_DIR / "merge_file.py"),
|
|
||||||
str(tmp_path / "mine.txt"),
|
|
||||||
str(tmp_path / "base.txt"),
|
|
||||||
str(tmp_path / "theirs.txt"),
|
|
||||||
str(output),
|
|
||||||
],
|
|
||||||
capture_output=True,
|
|
||||||
text=True,
|
|
||||||
check=True,
|
|
||||||
)
|
|
||||||
|
|
||||||
assert output.read_text() == "Hi beautiful world"
|
|
||||||
|
|
||||||
|
|
||||||
class TestDiffUndiffInverse:
|
|
||||||
"""Verify diff/undiff roundtrip across large real-world texts."""
|
|
||||||
|
|
||||||
@pytest.mark.parametrize("file1", FILES)
|
|
||||||
@pytest.mark.parametrize("file2", FILES)
|
|
||||||
def test_roundtrip_files(self, file1: str, file2: str) -> None:
|
|
||||||
content1 = (RESOURCES_DIR / file1).read_text()[:50000]
|
|
||||||
content2 = (RESOURCES_DIR / file2).read_text()[:50000]
|
|
||||||
|
|
||||||
changes = diff(content1, content2)
|
|
||||||
actual = undiff(content1, changes)
|
|
||||||
assert actual == content2
|
|
||||||
279
reconcile-python/uv.lock
generated
279
reconcile-python/uv.lock
generated
|
|
@ -1,279 +0,0 @@
|
||||||
version = 1
|
|
||||||
revision = 3
|
|
||||||
requires-python = ">=3.9"
|
|
||||||
resolution-markers = [
|
|
||||||
"python_full_version >= '3.10'",
|
|
||||||
"python_full_version < '3.10'",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "colorama"
|
|
||||||
version = "0.4.6"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/d8/53/6f443c9a4a8358a93a6792e2acffb9d9d5cb0a5cfd8802644b7b1c9a02e4/colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44", size = 27697, upload-time = "2022-10-25T02:36:22.414Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "exceptiongroup"
|
|
||||||
version = "1.3.1"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
dependencies = [
|
|
||||||
{ name = "typing-extensions", marker = "python_full_version < '3.13'" },
|
|
||||||
]
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/50/79/66800aadf48771f6b62f7eb014e352e5d06856655206165d775e675a02c9/exceptiongroup-1.3.1.tar.gz", hash = "sha256:8b412432c6055b0b7d14c310000ae93352ed6754f70fa8f7c34141f91c4e3219", size = 30371, upload-time = "2025-11-21T23:01:54.787Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/8a/0e/97c33bf5009bdbac74fd2beace167cab3f978feb69cc36f1ef79360d6c4e/exceptiongroup-1.3.1-py3-none-any.whl", hash = "sha256:a7a39a3bd276781e98394987d3a5701d0c4edffb633bb7a5144577f82c773598", size = 16740, upload-time = "2025-11-21T23:01:53.443Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "iniconfig"
|
|
||||||
version = "2.1.0"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
resolution-markers = [
|
|
||||||
"python_full_version < '3.10'",
|
|
||||||
]
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/f2/97/ebf4da567aa6827c909642694d71c9fcf53e5b504f2d96afea02718862f3/iniconfig-2.1.0.tar.gz", hash = "sha256:3abbd2e30b36733fee78f9c7f7308f2d0050e88f0087fd25c2645f63c773e1c7", size = 4793, upload-time = "2025-03-19T20:09:59.721Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/2c/e1/e6716421ea10d38022b952c159d5161ca1193197fb744506875fbb87ea7b/iniconfig-2.1.0-py3-none-any.whl", hash = "sha256:9deba5723312380e77435581c6bf4935c94cbfab9b1ed33ef8d238ea168eb760", size = 6050, upload-time = "2025-03-19T20:10:01.071Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "iniconfig"
|
|
||||||
version = "2.3.0"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
resolution-markers = [
|
|
||||||
"python_full_version >= '3.10'",
|
|
||||||
]
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/72/34/14ca021ce8e5dfedc35312d08ba8bf51fdd999c576889fc2c24cb97f4f10/iniconfig-2.3.0.tar.gz", hash = "sha256:c76315c77db068650d49c5b56314774a7804df16fee4402c1f19d6d15d8c4730", size = 20503, upload-time = "2025-10-18T21:55:43.219Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/cb/b1/3846dd7f199d53cb17f49cba7e651e9ce294d8497c8c150530ed11865bb8/iniconfig-2.3.0-py3-none-any.whl", hash = "sha256:f631c04d2c48c52b84d0d0549c99ff3859c98df65b3101406327ecc7d53fbf12", size = 7484, upload-time = "2025-10-18T21:55:41.639Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "maturin"
|
|
||||||
version = "1.12.6"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
dependencies = [
|
|
||||||
{ name = "tomli", marker = "python_full_version < '3.11'" },
|
|
||||||
]
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/0c/18/8b2eebd3ea086a5ec73d7081f95ec64918ceda1900075902fc296ea3ad55/maturin-1.12.6.tar.gz", hash = "sha256:d37be3a811a7f2ee28a0fa0964187efa50e90f21da0c6135c27787fa0b6a89db", size = 269165, upload-time = "2026-03-01T14:54:04.21Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/71/8b/9ddfde8a485489e3ebdc50ee3042ef1c854f00dfea776b951068f6ffe451/maturin-1.12.6-py3-none-linux_armv6l.whl", hash = "sha256:6892b4176992fcc143f9d1c1c874a816e9a041248eef46433db87b0f0aff4278", size = 9789847, upload-time = "2026-03-01T14:54:09.172Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/ef/e8/5f7fd3763f214a77ac0388dbcc71cc30aec5490016bd0c8e6bd729fc7b0a/maturin-1.12.6-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:c0c742beeeef7fb93b6a81bd53e75507887e396fd1003c45117658d063812dad", size = 19023833, upload-time = "2026-03-01T14:53:46.743Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/e0/7f/706ff3839c8b2046436d4c2bc97596c558728264d18abc298a1ad862a4be/maturin-1.12.6-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:2cb41139295eed6411d3cdafc7430738094c2721f34b7eeb44f33cac516115dc", size = 9821620, upload-time = "2026-03-01T14:54:12.04Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/0e/9c/70917fb123c8dd6b595e913616c9c72d730cbf4a2b6cac8077dc02a12586/maturin-1.12.6-py3-none-manylinux_2_12_i686.manylinux2010_i686.musllinux_1_1_i686.whl", hash = "sha256:351f3af1488a7cbdcff3b6d8482c17164273ac981378a13a4a9937a49aec7d71", size = 9849107, upload-time = "2026-03-01T14:53:48.971Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/59/ea/f1d6ad95c0a12fbe761a7c28a57540341f188564dbe8ad730a4d1788cd32/maturin-1.12.6-py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.musllinux_1_1_x86_64.whl", hash = "sha256:6dbddfe4dc7ddee60bbac854870bd7cfec660acb54d015d24597d59a1c828f61", size = 10242855, upload-time = "2026-03-01T14:53:44.605Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/93/1b/2419843a4f1d2fb4747f3dc3d9c4a2881cd97a3274dd94738fcdf0835e79/maturin-1.12.6-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.musllinux_1_1_aarch64.whl", hash = "sha256:8fdb0f63e77ee3df0f027a120e9af78dbc31edf0eb0f263d55783c250c33b728", size = 9674972, upload-time = "2026-03-01T14:53:52.763Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/71/46/b60ab2fc996d904b40e55bd475599dcdccd8f7ad3e649bf95e87970df466/maturin-1.12.6-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.musllinux_1_1_armv7l.whl", hash = "sha256:fa84b7493a2e80759cacc2e668fa5b444d55b9994e90707c42904f55d6322c1e", size = 9645755, upload-time = "2026-03-01T14:53:58.497Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/a4/96/03f2b55a8c226805115232fc23c4a4f33f0c9d39e11efab8166dc440f80d/maturin-1.12.6-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.musllinux_1_1_ppc64le.whl", hash = "sha256:e90dc12bc6a38e9495692a36c9e231c4d7e0c9bfde60719468ab7d8673db3c45", size = 12737612, upload-time = "2026-03-01T14:54:05.393Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/2b/c2/648667022c5b53cdccefa67c245e8a984970f3045820f00c2e23bdb2aff4/maturin-1.12.6-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:06fc8d089f98623ce924c669b70911dfed30f9a29956c362945f727f9abc546b", size = 10455028, upload-time = "2026-03-01T14:54:07.349Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/63/d6/5b5efe3ca0c043357ed3f8d2b2d556169fdbf1ff75e50e8e597708a359d2/maturin-1.12.6-py3-none-manylinux_2_31_riscv64.musllinux_1_1_riscv64.whl", hash = "sha256:75133e56274d43b9227fd49dca9a86e32f1fd56a7b55544910c4ce978c2bb5aa", size = 10014531, upload-time = "2026-03-01T14:53:54.548Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/68/d5/39c594c27b1a8b32a0cb95fff9ad60b888c4352d1d1c389ac1bd20dc1e16/maturin-1.12.6-py3-none-win32.whl", hash = "sha256:3f32e0a3720b81423c9d35c14e728cb1f954678124749776dc72d533ea1115e8", size = 8553012, upload-time = "2026-03-01T14:53:50.706Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/94/66/b262832a91747e04051e21f986bd01a8af81fbffafacc7d66a11e79aab5f/maturin-1.12.6-py3-none-win_amd64.whl", hash = "sha256:977290159d252db946054a0555263c59b3d0c7957135c69e690f4b1558ee9983", size = 9890470, upload-time = "2026-03-01T14:53:56.659Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/e3/47/76b8ca470ddc8d7d36aa8c15f5a6aed1841806bb93a0f4ead8ee61e9a088/maturin-1.12.6-py3-none-win_arm64.whl", hash = "sha256:bae91976cdc8148038e13c881e1e844e5c63e58e026e8b9945aa2d19b3b4ae89", size = 8606158, upload-time = "2026-03-01T14:54:02.423Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "nodeenv"
|
|
||||||
version = "1.10.0"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/24/bf/d1bda4f6168e0b2e9e5958945e01910052158313224ada5ce1fb2e1113b8/nodeenv-1.10.0.tar.gz", hash = "sha256:996c191ad80897d076bdfba80a41994c2b47c68e224c542b48feba42ba00f8bb", size = 55611, upload-time = "2025-12-20T14:08:54.006Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/88/b2/d0896bdcdc8d28a7fc5717c305f1a861c26e18c05047949fb371034d98bd/nodeenv-1.10.0-py2.py3-none-any.whl", hash = "sha256:5bb13e3eed2923615535339b3c620e76779af4cb4c6a90deccc9e36b274d3827", size = 23438, upload-time = "2025-12-20T14:08:52.782Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "packaging"
|
|
||||||
version = "26.0"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/65/ee/299d360cdc32edc7d2cf530f3accf79c4fca01e96ffc950d8a52213bd8e4/packaging-26.0.tar.gz", hash = "sha256:00243ae351a257117b6a241061796684b084ed1c516a08c48a3f7e147a9d80b4", size = 143416, upload-time = "2026-01-21T20:50:39.064Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/b7/b9/c538f279a4e237a006a2c98387d081e9eb060d203d8ed34467cc0f0b9b53/packaging-26.0-py3-none-any.whl", hash = "sha256:b36f1fef9334a5588b4166f8bcd26a14e521f2b55e6b9de3aaa80d3ff7a37529", size = 74366, upload-time = "2026-01-21T20:50:37.788Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "pluggy"
|
|
||||||
version = "1.6.0"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/f9/e2/3e91f31a7d2b083fe6ef3fa267035b518369d9511ffab804f839851d2779/pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3", size = 69412, upload-time = "2025-05-15T12:30:07.975Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/54/20/4d324d65cc6d9205fabedc306948156824eb9f0ee1633355a8f7ec5c66bf/pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746", size = 20538, upload-time = "2025-05-15T12:30:06.134Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "pygments"
|
|
||||||
version = "2.19.2"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/b0/77/a5b8c569bf593b0140bde72ea885a803b82086995367bf2037de0159d924/pygments-2.19.2.tar.gz", hash = "sha256:636cb2477cec7f8952536970bc533bc43743542f70392ae026374600add5b887", size = 4968631, upload-time = "2025-06-21T13:39:12.283Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/c7/21/705964c7812476f378728bdf590ca4b771ec72385c533964653c68e86bdc/pygments-2.19.2-py3-none-any.whl", hash = "sha256:86540386c03d588bb81d44bc3928634ff26449851e99741617ecb9037ee5ec0b", size = 1225217, upload-time = "2025-06-21T13:39:07.939Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "pyright"
|
|
||||||
version = "1.1.408"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
dependencies = [
|
|
||||||
{ name = "nodeenv" },
|
|
||||||
{ name = "typing-extensions" },
|
|
||||||
]
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/74/b2/5db700e52554b8f025faa9c3c624c59f1f6c8841ba81ab97641b54322f16/pyright-1.1.408.tar.gz", hash = "sha256:f28f2321f96852fa50b5829ea492f6adb0e6954568d1caa3f3af3a5f555eb684", size = 4400578, upload-time = "2026-01-08T08:07:38.795Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/0c/82/a2c93e32800940d9573fb28c346772a14778b84ba7524e691b324620ab89/pyright-1.1.408-py3-none-any.whl", hash = "sha256:090b32865f4fdb1e0e6cd82bf5618480d48eecd2eb2e70f960982a3d9a4c17c1", size = 6399144, upload-time = "2026-01-08T08:07:37.082Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "pytest"
|
|
||||||
version = "8.4.2"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
resolution-markers = [
|
|
||||||
"python_full_version < '3.10'",
|
|
||||||
]
|
|
||||||
dependencies = [
|
|
||||||
{ name = "colorama", marker = "python_full_version < '3.10' and sys_platform == 'win32'" },
|
|
||||||
{ name = "exceptiongroup", marker = "python_full_version < '3.10'" },
|
|
||||||
{ name = "iniconfig", version = "2.1.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
|
|
||||||
{ name = "packaging", marker = "python_full_version < '3.10'" },
|
|
||||||
{ name = "pluggy", marker = "python_full_version < '3.10'" },
|
|
||||||
{ name = "pygments", marker = "python_full_version < '3.10'" },
|
|
||||||
{ name = "tomli", marker = "python_full_version < '3.10'" },
|
|
||||||
]
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/a3/5c/00a0e072241553e1a7496d638deababa67c5058571567b92a7eaa258397c/pytest-8.4.2.tar.gz", hash = "sha256:86c0d0b93306b961d58d62a4db4879f27fe25513d4b969df351abdddb3c30e01", size = 1519618, upload-time = "2025-09-04T14:34:22.711Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/a8/a4/20da314d277121d6534b3a980b29035dcd51e6744bd79075a6ce8fa4eb8d/pytest-8.4.2-py3-none-any.whl", hash = "sha256:872f880de3fc3a5bdc88a11b39c9710c3497a547cfa9320bc3c5e62fbf272e79", size = 365750, upload-time = "2025-09-04T14:34:20.226Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "pytest"
|
|
||||||
version = "9.0.2"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
resolution-markers = [
|
|
||||||
"python_full_version >= '3.10'",
|
|
||||||
]
|
|
||||||
dependencies = [
|
|
||||||
{ name = "colorama", marker = "python_full_version >= '3.10' and sys_platform == 'win32'" },
|
|
||||||
{ name = "exceptiongroup", marker = "python_full_version == '3.10.*'" },
|
|
||||||
{ name = "iniconfig", version = "2.3.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.10'" },
|
|
||||||
{ name = "packaging", marker = "python_full_version >= '3.10'" },
|
|
||||||
{ name = "pluggy", marker = "python_full_version >= '3.10'" },
|
|
||||||
{ name = "pygments", marker = "python_full_version >= '3.10'" },
|
|
||||||
{ name = "tomli", marker = "python_full_version == '3.10.*'" },
|
|
||||||
]
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/d1/db/7ef3487e0fb0049ddb5ce41d3a49c235bf9ad299b6a25d5780a89f19230f/pytest-9.0.2.tar.gz", hash = "sha256:75186651a92bd89611d1d9fc20f0b4345fd827c41ccd5c299a868a05d70edf11", size = 1568901, upload-time = "2025-12-06T21:30:51.014Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/3b/ab/b3226f0bd7cdcf710fbede2b3548584366da3b19b5021e74f5bde2a8fa3f/pytest-9.0.2-py3-none-any.whl", hash = "sha256:711ffd45bf766d5264d487b917733b453d917afd2b0ad65223959f59089f875b", size = 374801, upload-time = "2025-12-06T21:30:49.154Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "reconcile-text"
|
|
||||||
version = "0.12.1"
|
|
||||||
source = { editable = "." }
|
|
||||||
|
|
||||||
[package.dev-dependencies]
|
|
||||||
dev = [
|
|
||||||
{ name = "maturin" },
|
|
||||||
{ name = "pyright" },
|
|
||||||
{ name = "pytest", version = "8.4.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
|
|
||||||
{ name = "pytest", version = "9.0.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.10'" },
|
|
||||||
{ name = "ruff" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[package.metadata]
|
|
||||||
|
|
||||||
[package.metadata.requires-dev]
|
|
||||||
dev = [
|
|
||||||
{ name = "maturin", specifier = ">=1.0,<2.0" },
|
|
||||||
{ name = "pyright", specifier = ">=1" },
|
|
||||||
{ name = "pytest", specifier = ">=8" },
|
|
||||||
{ name = "ruff", specifier = ">=0.15" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "ruff"
|
|
||||||
version = "0.15.5"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/77/9b/840e0039e65fcf12758adf684d2289024d6140cde9268cc59887dc55189c/ruff-0.15.5.tar.gz", hash = "sha256:7c3601d3b6d76dce18c5c824fc8d06f4eef33d6df0c21ec7799510cde0f159a2", size = 4574214, upload-time = "2026-03-05T20:06:34.946Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/47/20/5369c3ce21588c708bcbe517a8fbe1a8dfdb5dfd5137e14790b1da71612c/ruff-0.15.5-py3-none-linux_armv6l.whl", hash = "sha256:4ae44c42281f42e3b06b988e442d344a5b9b72450ff3c892e30d11b29a96a57c", size = 10478185, upload-time = "2026-03-05T20:06:29.093Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/44/ed/e81dd668547da281e5dce710cf0bc60193f8d3d43833e8241d006720e42b/ruff-0.15.5-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:6edd3792d408ebcf61adabc01822da687579a1a023f297618ac27a5b51ef0080", size = 10859201, upload-time = "2026-03-05T20:06:32.632Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/c4/8f/533075f00aaf19b07c5cd6aa6e5d89424b06b3b3f4583bfa9c640a079059/ruff-0.15.5-py3-none-macosx_11_0_arm64.whl", hash = "sha256:89f463f7c8205a9f8dea9d658d59eff49db05f88f89cc3047fb1a02d9f344010", size = 10184752, upload-time = "2026-03-05T20:06:40.312Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/66/0e/ba49e2c3fa0395b3152bad634c7432f7edfc509c133b8f4529053ff024fb/ruff-0.15.5-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ba786a8295c6574c1116704cf0b9e6563de3432ac888d8f83685654fe528fd65", size = 10534857, upload-time = "2026-03-05T20:06:19.581Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/59/71/39234440f27a226475a0659561adb0d784b4d247dfe7f43ffc12dd02e288/ruff-0.15.5-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:fd4b801e57955fe9f02b31d20375ab3a5c4415f2e5105b79fb94cf2642c91440", size = 10309120, upload-time = "2026-03-05T20:06:00.435Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/f5/87/4140aa86a93df032156982b726f4952aaec4a883bb98cb6ef73c347da253/ruff-0.15.5-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:391f7c73388f3d8c11b794dbbc2959a5b5afe66642c142a6effa90b45f6f5204", size = 11047428, upload-time = "2026-03-05T20:05:51.867Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/5a/f7/4953e7e3287676f78fbe85e3a0ca414c5ca81237b7575bdadc00229ac240/ruff-0.15.5-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8dc18f30302e379fe1e998548b0f5e9f4dff907f52f73ad6da419ea9c19d66c8", size = 11914251, upload-time = "2026-03-05T20:06:22.887Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/77/46/0f7c865c10cf896ccf5a939c3e84e1cfaeed608ff5249584799a74d33835/ruff-0.15.5-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1cc6e7f90087e2d27f98dc34ed1b3ab7c8f0d273cc5431415454e22c0bd2a681", size = 11333801, upload-time = "2026-03-05T20:05:57.168Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/d3/01/a10fe54b653061585e655f5286c2662ebddb68831ed3eaebfb0eb08c0a16/ruff-0.15.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c1cb7169f53c1ddb06e71a9aebd7e98fc0fea936b39afb36d8e86d36ecc2636a", size = 11206821, upload-time = "2026-03-05T20:06:03.441Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/7a/0d/2132ceaf20c5e8699aa83da2706ecb5c5dcdf78b453f77edca7fb70f8a93/ruff-0.15.5-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:9b037924500a31ee17389b5c8c4d88874cc6ea8e42f12e9c61a3d754ff72f1ca", size = 11133326, upload-time = "2026-03-05T20:06:25.655Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/72/cb/2e5259a7eb2a0f87c08c0fe5bf5825a1e4b90883a52685524596bfc93072/ruff-0.15.5-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:65bb414e5b4eadd95a8c1e4804f6772bbe8995889f203a01f77ddf2d790929dd", size = 10510820, upload-time = "2026-03-05T20:06:37.79Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/ff/20/b67ce78f9e6c59ffbdb5b4503d0090e749b5f2d31b599b554698a80d861c/ruff-0.15.5-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:d20aa469ae3b57033519c559e9bc9cd9e782842e39be05b50e852c7c981fa01d", size = 10302395, upload-time = "2026-03-05T20:05:54.504Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/5f/e5/719f1acccd31b720d477751558ed74e9c88134adcc377e5e886af89d3072/ruff-0.15.5-py3-none-musllinux_1_2_i686.whl", hash = "sha256:15388dd28c9161cdb8eda68993533acc870aa4e646a0a277aa166de9ad5a8752", size = 10754069, upload-time = "2026-03-05T20:06:06.422Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/c3/9c/d1db14469e32d98f3ca27079dbd30b7b44dbb5317d06ab36718dee3baf03/ruff-0.15.5-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:b30da330cbd03bed0c21420b6b953158f60c74c54c5f4c1dabbdf3a57bf355d2", size = 11304315, upload-time = "2026-03-05T20:06:10.867Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/28/3a/950367aee7c69027f4f422059227b290ed780366b6aecee5de5039d50fa8/ruff-0.15.5-py3-none-win32.whl", hash = "sha256:732e5ee1f98ba5b3679029989a06ca39a950cced52143a0ea82a2102cb592b74", size = 10551676, upload-time = "2026-03-05T20:06:13.705Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/b8/00/bf077a505b4e649bdd3c47ff8ec967735ce2544c8e4a43aba42ee9bf935d/ruff-0.15.5-py3-none-win_amd64.whl", hash = "sha256:821d41c5fa9e19117616c35eaa3f4b75046ec76c65e7ae20a333e9a8696bc7fe", size = 11678972, upload-time = "2026-03-05T20:06:45.379Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/fe/4e/cd76eca6db6115604b7626668e891c9dd03330384082e33662fb0f113614/ruff-0.15.5-py3-none-win_arm64.whl", hash = "sha256:b498d1c60d2fe5c10c45ec3f698901065772730b411f164ae270bb6bfcc4740b", size = 10965572, upload-time = "2026-03-05T20:06:16.984Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "tomli"
|
|
||||||
version = "2.4.0"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/82/30/31573e9457673ab10aa432461bee537ce6cef177667deca369efb79df071/tomli-2.4.0.tar.gz", hash = "sha256:aa89c3f6c277dd275d8e243ad24f3b5e701491a860d5121f2cdd399fbb31fc9c", size = 17477, upload-time = "2026-01-11T11:22:38.165Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/3c/d9/3dc2289e1f3b32eb19b9785b6a006b28ee99acb37d1d47f78d4c10e28bf8/tomli-2.4.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b5ef256a3fd497d4973c11bf142e9ed78b150d36f5773f1ca6088c230ffc5867", size = 153663, upload-time = "2026-01-11T11:21:45.27Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/51/32/ef9f6845e6b9ca392cd3f64f9ec185cc6f09f0a2df3db08cbe8809d1d435/tomli-2.4.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:5572e41282d5268eb09a697c89a7bee84fae66511f87533a6f88bd2f7b652da9", size = 148469, upload-time = "2026-01-11T11:21:46.873Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/d6/c2/506e44cce89a8b1b1e047d64bd495c22c9f71f21e05f380f1a950dd9c217/tomli-2.4.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:551e321c6ba03b55676970b47cb1b73f14a0a4dce6a3e1a9458fd6d921d72e95", size = 236039, upload-time = "2026-01-11T11:21:48.503Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/b3/40/e1b65986dbc861b7e986e8ec394598187fa8aee85b1650b01dd925ca0be8/tomli-2.4.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5e3f639a7a8f10069d0e15408c0b96a2a828cfdec6fca05296ebcdcc28ca7c76", size = 243007, upload-time = "2026-01-11T11:21:49.456Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/9c/6f/6e39ce66b58a5b7ae572a0f4352ff40c71e8573633deda43f6a379d56b3e/tomli-2.4.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:1b168f2731796b045128c45982d3a4874057626da0e2ef1fdd722848b741361d", size = 240875, upload-time = "2026-01-11T11:21:50.755Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/aa/ad/cb089cb190487caa80204d503c7fd0f4d443f90b95cf4ef5cf5aa0f439b0/tomli-2.4.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:133e93646ec4300d651839d382d63edff11d8978be23da4cc106f5a18b7d0576", size = 246271, upload-time = "2026-01-11T11:21:51.81Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/0b/63/69125220e47fd7a3a27fd0de0c6398c89432fec41bc739823bcc66506af6/tomli-2.4.0-cp311-cp311-win32.whl", hash = "sha256:b6c78bdf37764092d369722d9946cb65b8767bfa4110f902a1b2542d8d173c8a", size = 96770, upload-time = "2026-01-11T11:21:52.647Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/1e/0d/a22bb6c83f83386b0008425a6cd1fa1c14b5f3dd4bad05e98cf3dbbf4a64/tomli-2.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:d3d1654e11d724760cdb37a3d7691f0be9db5fbdaef59c9f532aabf87006dbaa", size = 107626, upload-time = "2026-01-11T11:21:53.459Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/2f/6d/77be674a3485e75cacbf2ddba2b146911477bd887dda9d8c9dfb2f15e871/tomli-2.4.0-cp311-cp311-win_arm64.whl", hash = "sha256:cae9c19ed12d4e8f3ebf46d1a75090e4c0dc16271c5bce1c833ac168f08fb614", size = 94842, upload-time = "2026-01-11T11:21:54.831Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/3c/43/7389a1869f2f26dba52404e1ef13b4784b6b37dac93bac53457e3ff24ca3/tomli-2.4.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:920b1de295e72887bafa3ad9f7a792f811847d57ea6b1215154030cf131f16b1", size = 154894, upload-time = "2026-01-11T11:21:56.07Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/e9/05/2f9bf110b5294132b2edf13fe6ca6ae456204f3d749f623307cbb7a946f2/tomli-2.4.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:7d6d9a4aee98fac3eab4952ad1d73aee87359452d1c086b5ceb43ed02ddb16b8", size = 149053, upload-time = "2026-01-11T11:21:57.467Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/e8/41/1eda3ca1abc6f6154a8db4d714a4d35c4ad90adc0bcf700657291593fbf3/tomli-2.4.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:36b9d05b51e65b254ea6c2585b59d2c4cb91c8a3d91d0ed0f17591a29aaea54a", size = 243481, upload-time = "2026-01-11T11:21:58.661Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/d2/6d/02ff5ab6c8868b41e7d4b987ce2b5f6a51d3335a70aa144edd999e055a01/tomli-2.4.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1c8a885b370751837c029ef9bc014f27d80840e48bac415f3412e6593bbc18c1", size = 251720, upload-time = "2026-01-11T11:22:00.178Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/7b/57/0405c59a909c45d5b6f146107c6d997825aa87568b042042f7a9c0afed34/tomli-2.4.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:8768715ffc41f0008abe25d808c20c3d990f42b6e2e58305d5da280ae7d1fa3b", size = 247014, upload-time = "2026-01-11T11:22:01.238Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/2c/0e/2e37568edd944b4165735687cbaf2fe3648129e440c26d02223672ee0630/tomli-2.4.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:7b438885858efd5be02a9a133caf5812b8776ee0c969fea02c45e8e3f296ba51", size = 251820, upload-time = "2026-01-11T11:22:02.727Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/5a/1c/ee3b707fdac82aeeb92d1a113f803cf6d0f37bdca0849cb489553e1f417a/tomli-2.4.0-cp312-cp312-win32.whl", hash = "sha256:0408e3de5ec77cc7f81960c362543cbbd91ef883e3138e81b729fc3eea5b9729", size = 97712, upload-time = "2026-01-11T11:22:03.777Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/69/13/c07a9177d0b3bab7913299b9278845fc6eaaca14a02667c6be0b0a2270c8/tomli-2.4.0-cp312-cp312-win_amd64.whl", hash = "sha256:685306e2cc7da35be4ee914fd34ab801a6acacb061b6a7abca922aaf9ad368da", size = 108296, upload-time = "2026-01-11T11:22:04.86Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/18/27/e267a60bbeeee343bcc279bb9e8fbed0cbe224bc7b2a3dc2975f22809a09/tomli-2.4.0-cp312-cp312-win_arm64.whl", hash = "sha256:5aa48d7c2356055feef06a43611fc401a07337d5b006be13a30f6c58f869e3c3", size = 94553, upload-time = "2026-01-11T11:22:05.854Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/34/91/7f65f9809f2936e1f4ce6268ae1903074563603b2a2bd969ebbda802744f/tomli-2.4.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:84d081fbc252d1b6a982e1870660e7330fb8f90f676f6e78b052ad4e64714bf0", size = 154915, upload-time = "2026-01-11T11:22:06.703Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/20/aa/64dd73a5a849c2e8f216b755599c511badde80e91e9bc2271baa7b2cdbb1/tomli-2.4.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:9a08144fa4cba33db5255f9b74f0b89888622109bd2776148f2597447f92a94e", size = 149038, upload-time = "2026-01-11T11:22:07.56Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/9e/8a/6d38870bd3d52c8d1505ce054469a73f73a0fe62c0eaf5dddf61447e32fa/tomli-2.4.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c73add4bb52a206fd0c0723432db123c0c75c280cbd67174dd9d2db228ebb1b4", size = 242245, upload-time = "2026-01-11T11:22:08.344Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/59/bb/8002fadefb64ab2669e5b977df3f5e444febea60e717e755b38bb7c41029/tomli-2.4.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1fb2945cbe303b1419e2706e711b7113da57b7db31ee378d08712d678a34e51e", size = 250335, upload-time = "2026-01-11T11:22:09.951Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/a5/3d/4cdb6f791682b2ea916af2de96121b3cb1284d7c203d97d92d6003e91c8d/tomli-2.4.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:bbb1b10aa643d973366dc2cb1ad94f99c1726a02343d43cbc011edbfac579e7c", size = 245962, upload-time = "2026-01-11T11:22:11.27Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/f2/4a/5f25789f9a460bd858ba9756ff52d0830d825b458e13f754952dd15fb7bb/tomli-2.4.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4cbcb367d44a1f0c2be408758b43e1ffb5308abe0ea222897d6bfc8e8281ef2f", size = 250396, upload-time = "2026-01-11T11:22:12.325Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/aa/2f/b73a36fea58dfa08e8b3a268750e6853a6aac2a349241a905ebd86f3047a/tomli-2.4.0-cp313-cp313-win32.whl", hash = "sha256:7d49c66a7d5e56ac959cb6fc583aff0651094ec071ba9ad43df785abc2320d86", size = 97530, upload-time = "2026-01-11T11:22:13.865Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/3b/af/ca18c134b5d75de7e8dc551c5234eaba2e8e951f6b30139599b53de9c187/tomli-2.4.0-cp313-cp313-win_amd64.whl", hash = "sha256:3cf226acb51d8f1c394c1b310e0e0e61fecdd7adcb78d01e294ac297dd2e7f87", size = 108227, upload-time = "2026-01-11T11:22:15.224Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/22/c3/b386b832f209fee8073c8138ec50f27b4460db2fdae9ffe022df89a57f9b/tomli-2.4.0-cp313-cp313-win_arm64.whl", hash = "sha256:d20b797a5c1ad80c516e41bc1fb0443ddb5006e9aaa7bda2d71978346aeb9132", size = 94748, upload-time = "2026-01-11T11:22:16.009Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/f3/c4/84047a97eb1004418bc10bdbcfebda209fca6338002eba2dc27cc6d13563/tomli-2.4.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:26ab906a1eb794cd4e103691daa23d95c6919cc2fa9160000ac02370cc9dd3f6", size = 154725, upload-time = "2026-01-11T11:22:17.269Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/a8/5d/d39038e646060b9d76274078cddf146ced86dc2b9e8bbf737ad5983609a0/tomli-2.4.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:20cedb4ee43278bc4f2fee6cb50daec836959aadaf948db5172e776dd3d993fc", size = 148901, upload-time = "2026-01-11T11:22:18.287Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/73/e5/383be1724cb30f4ce44983d249645684a48c435e1cd4f8b5cded8a816d3c/tomli-2.4.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:39b0b5d1b6dd03684b3fb276407ebed7090bbec989fa55838c98560c01113b66", size = 243375, upload-time = "2026-01-11T11:22:19.154Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/31/f0/bea80c17971c8d16d3cc109dc3585b0f2ce1036b5f4a8a183789023574f2/tomli-2.4.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a26d7ff68dfdb9f87a016ecfd1e1c2bacbe3108f4e0f8bcd2228ef9a766c787d", size = 250639, upload-time = "2026-01-11T11:22:20.168Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/2c/8f/2853c36abbb7608e3f945d8a74e32ed3a74ee3a1f468f1ffc7d1cb3abba6/tomli-2.4.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:20ffd184fb1df76a66e34bd1b36b4a4641bd2b82954befa32fe8163e79f1a702", size = 246897, upload-time = "2026-01-11T11:22:21.544Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/49/f0/6c05e3196ed5337b9fe7ea003e95fd3819a840b7a0f2bf5a408ef1dad8ed/tomli-2.4.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:75c2f8bbddf170e8effc98f5e9084a8751f8174ea6ccf4fca5398436e0320bc8", size = 254697, upload-time = "2026-01-11T11:22:23.058Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/f3/f5/2922ef29c9f2951883525def7429967fc4d8208494e5ab524234f06b688b/tomli-2.4.0-cp314-cp314-win32.whl", hash = "sha256:31d556d079d72db7c584c0627ff3a24c5d3fb4f730221d3444f3efb1b2514776", size = 98567, upload-time = "2026-01-11T11:22:24.033Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/7b/31/22b52e2e06dd2a5fdbc3ee73226d763b184ff21fc24e20316a44ccc4d96b/tomli-2.4.0-cp314-cp314-win_amd64.whl", hash = "sha256:43e685b9b2341681907759cf3a04e14d7104b3580f808cfde1dfdb60ada85475", size = 108556, upload-time = "2026-01-11T11:22:25.378Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/48/3d/5058dff3255a3d01b705413f64f4306a141a8fd7a251e5a495e3f192a998/tomli-2.4.0-cp314-cp314-win_arm64.whl", hash = "sha256:3d895d56bd3f82ddd6faaff993c275efc2ff38e52322ea264122d72729dca2b2", size = 96014, upload-time = "2026-01-11T11:22:26.138Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/b8/4e/75dab8586e268424202d3a1997ef6014919c941b50642a1682df43204c22/tomli-2.4.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:5b5807f3999fb66776dbce568cc9a828544244a8eb84b84b9bafc080c99597b9", size = 163339, upload-time = "2026-01-11T11:22:27.143Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/06/e3/b904d9ab1016829a776d97f163f183a48be6a4deb87304d1e0116a349519/tomli-2.4.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:c084ad935abe686bd9c898e62a02a19abfc9760b5a79bc29644463eaf2840cb0", size = 159490, upload-time = "2026-01-11T11:22:28.399Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/e3/5a/fc3622c8b1ad823e8ea98a35e3c632ee316d48f66f80f9708ceb4f2a0322/tomli-2.4.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0f2e3955efea4d1cfbcb87bc321e00dc08d2bcb737fd1d5e398af111d86db5df", size = 269398, upload-time = "2026-01-11T11:22:29.345Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/fd/33/62bd6152c8bdd4c305ad9faca48f51d3acb2df1f8791b1477d46ff86e7f8/tomli-2.4.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0e0fe8a0b8312acf3a88077a0802565cb09ee34107813bba1c7cd591fa6cfc8d", size = 276515, upload-time = "2026-01-11T11:22:30.327Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/4b/ff/ae53619499f5235ee4211e62a8d7982ba9e439a0fb4f2f351a93d67c1dd2/tomli-2.4.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:413540dce94673591859c4c6f794dfeaa845e98bf35d72ed59636f869ef9f86f", size = 273806, upload-time = "2026-01-11T11:22:32.56Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/47/71/cbca7787fa68d4d0a9f7072821980b39fbb1b6faeb5f5cf02f4a5559fa28/tomli-2.4.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:0dc56fef0e2c1c470aeac5b6ca8cc7b640bb93e92d9803ddaf9ea03e198f5b0b", size = 281340, upload-time = "2026-01-11T11:22:33.505Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/f5/00/d595c120963ad42474cf6ee7771ad0d0e8a49d0f01e29576ee9195d9ecdf/tomli-2.4.0-cp314-cp314t-win32.whl", hash = "sha256:d878f2a6707cc9d53a1be1414bbb419e629c3d6e67f69230217bb663e76b5087", size = 108106, upload-time = "2026-01-11T11:22:34.451Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/de/69/9aa0c6a505c2f80e519b43764f8b4ba93b5a0bbd2d9a9de6e2b24271b9a5/tomli-2.4.0-cp314-cp314t-win_amd64.whl", hash = "sha256:2add28aacc7425117ff6364fe9e06a183bb0251b03f986df0e78e974047571fd", size = 120504, upload-time = "2026-01-11T11:22:35.764Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/b3/9f/f1668c281c58cfae01482f7114a4b88d345e4c140386241a1a24dcc9e7bc/tomli-2.4.0-cp314-cp314t-win_arm64.whl", hash = "sha256:2b1e3b80e1d5e52e40e9b924ec43d81570f0e7d09d11081b797bc4692765a3d4", size = 99561, upload-time = "2026-01-11T11:22:36.624Z" },
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/23/d1/136eb2cb77520a31e1f64cbae9d33ec6df0d78bdf4160398e86eec8a8754/tomli-2.4.0-py3-none-any.whl", hash = "sha256:1f776e7d669ebceb01dee46484485f43a4048746235e683bcdffacdf1fb4785a", size = 14477, upload-time = "2026-01-11T11:22:37.446Z" },
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "typing-extensions"
|
|
||||||
version = "4.15.0"
|
|
||||||
source = { registry = "https://pypi.org/simple" }
|
|
||||||
sdist = { url = "https://files.pythonhosted.org/packages/72/94/1a15dd82efb362ac84269196e94cf00f187f7ed21c242792a923cdb1c61f/typing_extensions-4.15.0.tar.gz", hash = "sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466", size = 109391, upload-time = "2025-08-25T13:49:26.313Z" }
|
|
||||||
wheels = [
|
|
||||||
{ url = "https://files.pythonhosted.org/packages/18/67/36e9267722cc04a6b9f15c7f3441c2363321a3ea07da7ae0c0707beb2a9c/typing_extensions-4.15.0-py3-none-any.whl", hash = "sha256:f0fa19c6845758ab08074a0cfa8b7aecb71c999ca73d62883bc25cc018c4e548", size = 44614, upload-time = "2025-08-25T13:49:24.86Z" },
|
|
||||||
]
|
|
||||||
|
|
@ -1,4 +1,4 @@
|
||||||
[toolchain]
|
[toolchain]
|
||||||
channel = "1.94.0"
|
channel = "nightly-2025-06-06"
|
||||||
targets = [ "x86_64-unknown-linux-gnu", "x86_64-unknown-linux-musl" ]
|
targets = [ "x86_64-unknown-linux-gnu", "x86_64-unknown-linux-musl" ]
|
||||||
profile = "default"
|
profile = "default"
|
||||||
|
|
|
||||||
|
|
@ -1 +1,8 @@
|
||||||
|
imports_granularity = "crate"
|
||||||
|
condense_wildcard_suffixes = true
|
||||||
|
fn_single_line = true
|
||||||
|
format_strings = true
|
||||||
|
reorder_impl_items = true
|
||||||
|
group_imports = "StdExternalCrate"
|
||||||
use_field_init_shorthand = true
|
use_field_init_shorthand = true
|
||||||
|
wrap_comments=true
|
||||||
|
|
|
||||||
|
|
@ -1,14 +0,0 @@
|
||||||
#!/bin/bash
|
|
||||||
|
|
||||||
set -e
|
|
||||||
|
|
||||||
which wasm-pack || cargo install wasm-pack
|
|
||||||
wasm-pack build --target web --features wasm
|
|
||||||
|
|
||||||
cd reconcile-js
|
|
||||||
npm ci
|
|
||||||
npm run build
|
|
||||||
cd ../examples/website
|
|
||||||
npm ci
|
|
||||||
npm run build
|
|
||||||
cd -
|
|
||||||
|
|
@ -2,8 +2,6 @@
|
||||||
|
|
||||||
set -e
|
set -e
|
||||||
|
|
||||||
git pull --rebase
|
|
||||||
|
|
||||||
if [[ -z $1 ]]; then
|
if [[ -z $1 ]]; then
|
||||||
echo "Usage: $0 {patch|minor|major}"
|
echo "Usage: $0 {patch|minor|major}"
|
||||||
exit 1
|
exit 1
|
||||||
|
|
@ -25,33 +23,15 @@ else
|
||||||
fi
|
fi
|
||||||
|
|
||||||
echo "Bumping versions"
|
echo "Bumping versions"
|
||||||
|
cd backend
|
||||||
which cargo-set-version || cargo install cargo-edit
|
|
||||||
cargo set-version --bump $1
|
cargo set-version --bump $1
|
||||||
|
|
||||||
which wasm-pack || cargo install wasm-pack
|
|
||||||
|
|
||||||
wasm-pack build --target web --features wasm
|
wasm-pack build --target web --features wasm
|
||||||
|
|
||||||
cd reconcile-js
|
|
||||||
npm version $1
|
|
||||||
npm install
|
|
||||||
|
|
||||||
NEWVER=$(grep '^version = ' ../Cargo.toml | head -1 | sed 's/version = "\(.*\)"/\1/')
|
|
||||||
cd ../reconcile-python
|
|
||||||
sed -i '' "s/^version = \".*\"/version = \"$NEWVER\"/" Cargo.toml
|
|
||||||
sed -i '' "s/^version = \".*\"/version = \"$NEWVER\"/" pyproject.toml
|
|
||||||
cargo update --workspace
|
|
||||||
uv lock
|
|
||||||
|
|
||||||
cd ../examples/website
|
|
||||||
npm install
|
|
||||||
|
|
||||||
cd ../..
|
|
||||||
|
|
||||||
|
# Commit and tag
|
||||||
git add .
|
git add .
|
||||||
TAG=$(node -p "require('./reconcile-js/package.json').version")
|
|
||||||
|
|
||||||
git commit -m "Bump versions to $TAG"
|
git commit -m "Bump versions to $TAG"
|
||||||
|
|
||||||
git push
|
git push
|
||||||
|
|
|
||||||
|
|
@ -1,13 +1,12 @@
|
||||||
#!/bin/bash
|
#!/bin/bash
|
||||||
|
|
||||||
set -e
|
rm -rf pkg
|
||||||
|
|
||||||
wasm-pack build --target web --features wasm
|
wasm-pack build --target web --features wasm
|
||||||
|
|
||||||
cd reconcile-js
|
cp -R pkg/reconcile.js examples/website/
|
||||||
npm install
|
cp -R pkg/reconcile_bg.wasm examples/website/
|
||||||
npm run build
|
|
||||||
|
|
||||||
cd ../examples/website
|
cd examples/website/
|
||||||
npm install
|
|
||||||
npm run start
|
python3 -m http.server $1
|
||||||
|
|
|
||||||
|
|
@ -1,27 +0,0 @@
|
||||||
#!/bin/bash
|
|
||||||
|
|
||||||
set -e
|
|
||||||
|
|
||||||
which cargo-machete || cargo install cargo-machete
|
|
||||||
cargo machete
|
|
||||||
|
|
||||||
cargo clippy --all-targets --all-features --fix --allow-dirty --allow-staged
|
|
||||||
cargo fmt --all
|
|
||||||
|
|
||||||
cd reconcile-js
|
|
||||||
npm ci
|
|
||||||
npm run format
|
|
||||||
|
|
||||||
cd ../examples/website
|
|
||||||
npm ci
|
|
||||||
npm run format
|
|
||||||
|
|
||||||
cd ../../reconcile-python
|
|
||||||
cp ../README.md .
|
|
||||||
uv run maturin develop -q
|
|
||||||
uv run ruff check python/ tests/
|
|
||||||
uv run ruff format python/ tests/
|
|
||||||
uv run pyright python/ tests/
|
|
||||||
cd -
|
|
||||||
|
|
||||||
echo "Success!"
|
|
||||||
|
|
@ -1,36 +0,0 @@
|
||||||
#!/bin/bash
|
|
||||||
|
|
||||||
set -e
|
|
||||||
|
|
||||||
which cargo-insta || cargo install cargo-insta
|
|
||||||
which wasm-pack || cargo install wasm-pack
|
|
||||||
|
|
||||||
node_version=$(node --version | cut -d'.' -f1 | tr -d 'v')
|
|
||||||
if [ "$node_version" != "22" ]; then
|
|
||||||
echo "Error: Node.js version 22 is required, but found version $node_version"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
wasm-pack build --target web --features wasm,console_error_panic_hook
|
|
||||||
cargo test --verbose --features serde -- --include-ignored
|
|
||||||
|
|
||||||
cargo test
|
|
||||||
cargo test --features serde
|
|
||||||
cargo test --features wasm
|
|
||||||
cargo test --features all
|
|
||||||
|
|
||||||
wasm-pack test --node --features wasm,console_error_panic_hook
|
|
||||||
|
|
||||||
cd reconcile-js
|
|
||||||
npm ci
|
|
||||||
npm run build
|
|
||||||
npm run test
|
|
||||||
cd -
|
|
||||||
|
|
||||||
cd reconcile-python
|
|
||||||
cp ../README.md .
|
|
||||||
uv run maturin develop
|
|
||||||
uv run pytest -v
|
|
||||||
cd -
|
|
||||||
|
|
||||||
echo "Success!"
|
|
||||||
2
src/diffs.rs
Normal file
2
src/diffs.rs
Normal file
|
|
@ -0,0 +1,2 @@
|
||||||
|
pub mod myers;
|
||||||
|
pub mod raw_operation;
|
||||||
357
src/diffs/myers.rs
Normal file
357
src/diffs/myers.rs
Normal file
|
|
@ -0,0 +1,357 @@
|
||||||
|
//! Taken from <https://github.com/mitsuhiko/similar/blob/7e15c44de11a1cd61e1149189929e189ef977fd8/src/algorithms/myers.rs>
|
||||||
|
//!
|
||||||
|
//! Myers' diff algorithm.
|
||||||
|
//!
|
||||||
|
//! * time: `O((N+M)D)`
|
||||||
|
//! * space `O(N+M)`
|
||||||
|
//!
|
||||||
|
//! See [the original article by Eugene W. Myers](http://www.xmailserver.org/diff2.pdf)
|
||||||
|
//! describing it.
|
||||||
|
//!
|
||||||
|
//! The implementation of this algorithm is based on the implementation by
|
||||||
|
//! Brandon Williams.
|
||||||
|
//!
|
||||||
|
//! # Heuristics
|
||||||
|
//!
|
||||||
|
//! At present this implementation of Myers' does not implement any more
|
||||||
|
//! advanced heuristics that would solve some pathological cases. For instance
|
||||||
|
//! passing two large and completely distinct sequences to the algorithm will
|
||||||
|
//! make it spin without making reasonable progress.
|
||||||
|
//! For potential improvements here see [similar#15](https://github.com/mitsuhiko/similar/issues/15).
|
||||||
|
|
||||||
|
use std::{
|
||||||
|
ops::{Index, IndexMut, Range},
|
||||||
|
vec,
|
||||||
|
};
|
||||||
|
|
||||||
|
use super::raw_operation::RawOperation;
|
||||||
|
use crate::{
|
||||||
|
tokenizer::token::Token,
|
||||||
|
utils::{common_prefix_len::common_prefix_len, common_suffix_len::common_suffix_len},
|
||||||
|
};
|
||||||
|
|
||||||
|
/// Myers' diff algorithm.
|
||||||
|
///
|
||||||
|
/// Diff `old`, between indices `old_range` and `new` between indices
|
||||||
|
/// `new_range`.
|
||||||
|
///
|
||||||
|
/// The returned `RawOperations` all have a token count of 1.
|
||||||
|
pub fn diff<T>(old: &[Token<T>], new: &[Token<T>]) -> Vec<RawOperation<T>>
|
||||||
|
where
|
||||||
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
|
{
|
||||||
|
let max_d = (old.len() + new.len()).div_ceil(2) + 1;
|
||||||
|
let mut vb = V::new(max_d);
|
||||||
|
let mut vf = V::new(max_d);
|
||||||
|
let mut result: Vec<RawOperation<T>> = vec![];
|
||||||
|
|
||||||
|
conquer(
|
||||||
|
old,
|
||||||
|
0..old.len(),
|
||||||
|
new,
|
||||||
|
0..new.len(),
|
||||||
|
&mut vf,
|
||||||
|
&mut vb,
|
||||||
|
&mut result,
|
||||||
|
);
|
||||||
|
|
||||||
|
debug_assert!(
|
||||||
|
result.iter().all(|op| op.tokens().len() == 1),
|
||||||
|
"All operations should be of length 1"
|
||||||
|
);
|
||||||
|
|
||||||
|
result
|
||||||
|
}
|
||||||
|
|
||||||
|
// A D-path is a path which starts at (0,0) that has exactly D non-diagonal
|
||||||
|
// edges. All D-paths consist of a (D - 1)-path followed by a non-diagonal edge
|
||||||
|
// and then a possibly empty sequence of diagonal edges called a snake.
|
||||||
|
|
||||||
|
/// `V` contains the endpoints of the furthest reaching `D-paths`. For each
|
||||||
|
/// recorded endpoint `(x,y)` in diagonal `k`, we only need to retain `x`
|
||||||
|
/// because `y` can be computed from `x - k`. In other words, `V` is an array of
|
||||||
|
/// integers where `V[k]` contains the row index of the endpoint of the furthest
|
||||||
|
/// reaching path in diagonal `k`.
|
||||||
|
///
|
||||||
|
/// We can't use a traditional Vec to represent `V` since we use `k` as an index
|
||||||
|
/// and it can take on negative values. So instead `V` is represented as a
|
||||||
|
/// light-weight wrapper around a Vec plus an `offset` which is the maximum
|
||||||
|
/// value `k` can take on in order to map negative `k`'s back to a value >= 0.
|
||||||
|
#[derive(Debug)]
|
||||||
|
struct V {
|
||||||
|
offset: isize,
|
||||||
|
v: Vec<usize>, // Look into initializing this to -1 and storing isize
|
||||||
|
}
|
||||||
|
|
||||||
|
impl V {
|
||||||
|
fn new(max_d: usize) -> Self {
|
||||||
|
Self {
|
||||||
|
offset: max_d as isize,
|
||||||
|
v: vec![0; 2 * max_d],
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
fn len(&self) -> usize { self.v.len() }
|
||||||
|
}
|
||||||
|
|
||||||
|
impl Index<isize> for V {
|
||||||
|
type Output = usize;
|
||||||
|
|
||||||
|
fn index(&self, index: isize) -> &Self::Output { &self.v[(index + self.offset) as usize] }
|
||||||
|
}
|
||||||
|
|
||||||
|
impl IndexMut<isize> for V {
|
||||||
|
fn index_mut(&mut self, index: isize) -> &mut Self::Output {
|
||||||
|
&mut self.v[(index + self.offset) as usize]
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
fn split_at(range: Range<usize>, at: usize) -> (Range<usize>, Range<usize>) {
|
||||||
|
(range.start..at, at..range.end)
|
||||||
|
}
|
||||||
|
|
||||||
|
/// A `Snake` is a sequence of diagonal edges in the edit graph. Normally
|
||||||
|
/// a snake has a start end end point (and it is possible for a snake to have
|
||||||
|
/// a length of zero, meaning the start and end points are the same) however
|
||||||
|
/// we do not need the end point which is why it's not implemented here.
|
||||||
|
///
|
||||||
|
/// The divide part of a divide-and-conquer strategy. A D-path has D+1 snakes
|
||||||
|
/// some of which may be empty. The divide step requires finding the ceil(D/2) +
|
||||||
|
/// 1 or middle snake of an optimal D-path. The idea for doing so is to
|
||||||
|
/// simultaneously run the basic algorithm in both the forward and reverse
|
||||||
|
/// directions until furthest reaching forward and reverse paths starting at
|
||||||
|
/// opposing corners 'overlap'.
|
||||||
|
fn find_middle_snake<T>(
|
||||||
|
old: &[Token<T>],
|
||||||
|
old_range: Range<usize>,
|
||||||
|
new: &[Token<T>],
|
||||||
|
new_range: Range<usize>,
|
||||||
|
vf: &mut V,
|
||||||
|
vb: &mut V,
|
||||||
|
) -> Option<(usize, usize)>
|
||||||
|
where
|
||||||
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
|
{
|
||||||
|
let n = old_range.len();
|
||||||
|
let m = new_range.len();
|
||||||
|
|
||||||
|
// By Lemma 1 in the paper, the optimal edit script length is odd or even as
|
||||||
|
// `delta` is odd or even.
|
||||||
|
let delta = n as isize - m as isize;
|
||||||
|
let odd = delta & 1 == 1;
|
||||||
|
|
||||||
|
// The initial point at (0, -1)
|
||||||
|
vf[1] = 0;
|
||||||
|
// The initial point at (N, M+1)
|
||||||
|
vb[1] = 0;
|
||||||
|
|
||||||
|
let d_max = (n + m).div_ceil(2) + 1;
|
||||||
|
assert!(vf.len() >= d_max);
|
||||||
|
assert!(vb.len() >= d_max);
|
||||||
|
|
||||||
|
for d in 0..d_max as isize {
|
||||||
|
// Forward path
|
||||||
|
for k in (-d..=d).rev().step_by(2) {
|
||||||
|
let mut x = if k == -d || (k != d && vf[k - 1] < vf[k + 1]) {
|
||||||
|
vf[k + 1]
|
||||||
|
} else {
|
||||||
|
vf[k - 1] + 1
|
||||||
|
};
|
||||||
|
let y = (x as isize - k) as usize;
|
||||||
|
|
||||||
|
// The coordinate of the start of a snake
|
||||||
|
let (x0, y0) = (x, y);
|
||||||
|
// While these sequences are identical, keep moving through the
|
||||||
|
// graph with no cost
|
||||||
|
if x < old_range.len() && y < new_range.len() {
|
||||||
|
let advance = common_prefix_len(
|
||||||
|
old,
|
||||||
|
old_range.start + x..old_range.end,
|
||||||
|
new,
|
||||||
|
new_range.start + y..new_range.end,
|
||||||
|
);
|
||||||
|
x += advance;
|
||||||
|
}
|
||||||
|
|
||||||
|
// This is the new best x value
|
||||||
|
vf[k] = x;
|
||||||
|
|
||||||
|
// Only check for connections from the forward search when N - M is
|
||||||
|
// odd and when there is a reciprocal k line coming from the other
|
||||||
|
// direction.
|
||||||
|
if odd && (k - delta).abs() <= (d - 1) {
|
||||||
|
// TODO optimize this so we don't have to compare against n
|
||||||
|
if vf[k] + vb[-(k - delta)] >= n {
|
||||||
|
// Return the snake
|
||||||
|
return Some((x0 + old_range.start, y0 + new_range.start));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Backward path
|
||||||
|
for k in (-d..=d).rev().step_by(2) {
|
||||||
|
let mut x = if k == -d || (k != d && vb[k - 1] < vb[k + 1]) {
|
||||||
|
vb[k + 1]
|
||||||
|
} else {
|
||||||
|
vb[k - 1] + 1
|
||||||
|
};
|
||||||
|
let mut y = (x as isize - k) as usize;
|
||||||
|
|
||||||
|
// The coordinate of the start of a snake
|
||||||
|
if x < n && y < m {
|
||||||
|
let advance = common_suffix_len(
|
||||||
|
old,
|
||||||
|
old_range.start..old_range.start + n - x,
|
||||||
|
new,
|
||||||
|
new_range.start..new_range.start + m - y,
|
||||||
|
);
|
||||||
|
x += advance;
|
||||||
|
y += advance;
|
||||||
|
}
|
||||||
|
|
||||||
|
// This is the new best x value
|
||||||
|
vb[k] = x;
|
||||||
|
|
||||||
|
if !odd && (k - delta).abs() <= d {
|
||||||
|
// TODO optimize this so we don't have to compare against n
|
||||||
|
if vb[k] + vf[-(k - delta)] >= n {
|
||||||
|
// Return the snake
|
||||||
|
return Some((n - x + old_range.start, m - y + new_range.start));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// TODO: Maybe there's an opportunity to optimize and bail early?
|
||||||
|
}
|
||||||
|
|
||||||
|
None
|
||||||
|
}
|
||||||
|
|
||||||
|
fn conquer<T>(
|
||||||
|
old: &[Token<T>],
|
||||||
|
mut old_range: Range<usize>,
|
||||||
|
new: &[Token<T>],
|
||||||
|
mut new_range: Range<usize>,
|
||||||
|
vf: &mut V,
|
||||||
|
vb: &mut V,
|
||||||
|
result: &mut Vec<RawOperation<T>>,
|
||||||
|
) where
|
||||||
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
|
{
|
||||||
|
// Check for common prefix
|
||||||
|
let common_prefix_len = common_prefix_len(old, old_range.clone(), new, new_range.clone());
|
||||||
|
if common_prefix_len > 0 {
|
||||||
|
result.extend(
|
||||||
|
old[old_range.start..old_range.start + common_prefix_len]
|
||||||
|
.iter()
|
||||||
|
.map(|token| RawOperation::Equal(vec![token.clone()])),
|
||||||
|
);
|
||||||
|
}
|
||||||
|
old_range.start += common_prefix_len;
|
||||||
|
new_range.start += common_prefix_len;
|
||||||
|
|
||||||
|
// Check for common suffix
|
||||||
|
let common_suffix_len = common_suffix_len(old, old_range.clone(), new, new_range.clone());
|
||||||
|
let common_suffix = (
|
||||||
|
old_range.end - common_suffix_len,
|
||||||
|
new_range.end - common_suffix_len,
|
||||||
|
);
|
||||||
|
old_range.end -= common_suffix_len;
|
||||||
|
new_range.end -= common_suffix_len;
|
||||||
|
|
||||||
|
if old_range.is_empty() && new_range.is_empty() {
|
||||||
|
// do nothing
|
||||||
|
} else if new_range.is_empty() {
|
||||||
|
result.extend(
|
||||||
|
old[old_range.start..old_range.start + old_range.len()]
|
||||||
|
.iter()
|
||||||
|
.map(|token| RawOperation::Delete(vec![token.clone()])),
|
||||||
|
);
|
||||||
|
} else if old_range.is_empty() {
|
||||||
|
result.extend(
|
||||||
|
new[new_range.start..new_range.start + new_range.len()]
|
||||||
|
.iter()
|
||||||
|
.map(|token| RawOperation::Insert(vec![token.clone()])),
|
||||||
|
);
|
||||||
|
} else if let Some((x_start, y_start)) =
|
||||||
|
find_middle_snake(old, old_range.clone(), new, new_range.clone(), vf, vb)
|
||||||
|
{
|
||||||
|
let (old_a, old_b) = split_at(old_range, x_start);
|
||||||
|
let (new_a, new_b) = split_at(new_range, y_start);
|
||||||
|
conquer(old, old_a, new, new_a, vf, vb, result);
|
||||||
|
conquer(old, old_b, new, new_b, vf, vb, result);
|
||||||
|
} else {
|
||||||
|
result.extend(
|
||||||
|
old[old_range.start..old_range.end]
|
||||||
|
.iter()
|
||||||
|
.map(|token| RawOperation::Delete(vec![token.clone()])),
|
||||||
|
);
|
||||||
|
result.extend(
|
||||||
|
new[new_range.start..new_range.end]
|
||||||
|
.iter()
|
||||||
|
.map(|token| RawOperation::Insert(vec![token.clone()])),
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
if common_suffix_len > 0 {
|
||||||
|
result.extend(
|
||||||
|
old[common_suffix.0..common_suffix.0 + common_suffix_len]
|
||||||
|
.iter()
|
||||||
|
.map(|token| RawOperation::Equal(vec![token.clone()])),
|
||||||
|
);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
#[cfg(test)]
|
||||||
|
mod tests {
|
||||||
|
use insta::assert_debug_snapshot;
|
||||||
|
|
||||||
|
use super::*;
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_empty_diff() {
|
||||||
|
let old: Vec<Token<String>> = vec![];
|
||||||
|
let new: Vec<Token<String>> = vec![];
|
||||||
|
let result = diff(&old, &new);
|
||||||
|
assert_eq!(result.len(), 0);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_identical_content() {
|
||||||
|
let content = vec!["a".into(), "b".into(), "c".into()];
|
||||||
|
let result = diff(&content, &content);
|
||||||
|
assert_debug_snapshot!(result);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_insert_only() {
|
||||||
|
let old: Vec<Token<String>> = vec![];
|
||||||
|
let new: Vec<Token<String>> = vec!["a".into(), "b".into()];
|
||||||
|
let result = diff(&old, &new);
|
||||||
|
assert_debug_snapshot!(result);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_delete_only() {
|
||||||
|
let old = vec!["a".into(), "b".into()];
|
||||||
|
let new: Vec<Token<String>> = vec![];
|
||||||
|
let result = diff(&old, &new);
|
||||||
|
assert_debug_snapshot!(result);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_prefix_and_suffix() {
|
||||||
|
let old = vec!["a".into(), "b".into(), "c".into(), "d".into()];
|
||||||
|
let new = vec!["a".into(), "x".into(), "d".into()];
|
||||||
|
let result = diff(&old, &new);
|
||||||
|
assert_debug_snapshot!(result);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_complex_diff() {
|
||||||
|
let old = vec!["a".into(), "b".into(), "c".into(), "d".into()];
|
||||||
|
let new = vec!["a".into(), "x".into(), "c".into(), "y".into()];
|
||||||
|
let result = diff(&old, &new);
|
||||||
|
assert_debug_snapshot!(result);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
@ -1,15 +1,9 @@
|
||||||
use std::fmt::Debug;
|
use crate::tokenizer::token::Token;
|
||||||
|
|
||||||
use crate::{tokenizer::token::Token, utils::myers_diff::myers_diff};
|
|
||||||
|
|
||||||
/// Text editing operation containing the affected tokens.
|
|
||||||
///
|
|
||||||
/// `RawOperation`s can be joined together when the underlying tokens
|
|
||||||
/// allow for joining subsequent operations.
|
|
||||||
#[derive(Debug, Clone, PartialEq)]
|
#[derive(Debug, Clone, PartialEq)]
|
||||||
pub enum RawOperation<T>
|
pub enum RawOperation<T>
|
||||||
where
|
where
|
||||||
T: PartialEq + Clone + Debug,
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
{
|
{
|
||||||
Insert(Vec<Token<T>>),
|
Insert(Vec<Token<T>>),
|
||||||
Delete(Vec<Token<T>>),
|
Delete(Vec<Token<T>>),
|
||||||
|
|
@ -18,13 +12,9 @@ where
|
||||||
|
|
||||||
impl<T> RawOperation<T>
|
impl<T> RawOperation<T>
|
||||||
where
|
where
|
||||||
T: PartialEq + Clone + Debug,
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
{
|
{
|
||||||
pub fn vec_from(left: &[Token<T>], right: &[Token<T>]) -> Vec<Self> {
|
pub fn tokens(&self) -> &Vec<Token<T>> {
|
||||||
myers_diff(left, right)
|
|
||||||
}
|
|
||||||
|
|
||||||
pub fn tokens(&self) -> &[Token<T>] {
|
|
||||||
match self {
|
match self {
|
||||||
RawOperation::Insert(tokens)
|
RawOperation::Insert(tokens)
|
||||||
| RawOperation::Delete(tokens)
|
| RawOperation::Delete(tokens)
|
||||||
|
|
@ -36,9 +26,7 @@ where
|
||||||
self.tokens().iter().map(Token::get_original_length).sum()
|
self.tokens().iter().map(Token::get_original_length).sum()
|
||||||
}
|
}
|
||||||
|
|
||||||
pub fn get_original_text(&self) -> String {
|
pub fn get_original_text(self) -> String { self.tokens().iter().map(Token::original).collect() }
|
||||||
self.tokens().iter().map(Token::original).collect()
|
|
||||||
}
|
|
||||||
|
|
||||||
pub fn is_left_joinable(&self) -> bool {
|
pub fn is_left_joinable(&self) -> bool {
|
||||||
let first_token = self.tokens().first();
|
let first_token = self.tokens().first();
|
||||||
|
|
@ -53,7 +41,7 @@ where
|
||||||
/// Extends the operation with another operation. Only operations of the
|
/// Extends the operation with another operation. Only operations of the
|
||||||
/// same type as self can be used to extend self, otherwise the function
|
/// same type as self can be used to extend self, otherwise the function
|
||||||
/// will panic.
|
/// will panic.
|
||||||
pub fn join(self, other: RawOperation<T>) -> RawOperation<T> {
|
pub fn extend(self, other: RawOperation<T>) -> RawOperation<T> {
|
||||||
debug_assert!(
|
debug_assert!(
|
||||||
std::mem::discriminant(&self) == std::mem::discriminant(&other),
|
std::mem::discriminant(&self) == std::mem::discriminant(&other),
|
||||||
"Cannot extend operations of different types. This should have been handled before \
|
"Cannot extend operations of different types. This should have been handled before \
|
||||||
|
|
@ -1,5 +1,5 @@
|
||||||
---
|
---
|
||||||
source: src/utils/myers_diff.rs
|
source: reconcile/src/diffs/myers.rs
|
||||||
expression: result
|
expression: result
|
||||||
snapshot_kind: text
|
snapshot_kind: text
|
||||||
---
|
---
|
||||||
|
|
@ -7,7 +7,7 @@ snapshot_kind: text
|
||||||
Equal(
|
Equal(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "a",
|
normalised: "a",
|
||||||
original: "a",
|
original: "a",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -17,7 +17,7 @@ snapshot_kind: text
|
||||||
Insert(
|
Insert(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "x",
|
normalised: "x",
|
||||||
original: "x",
|
original: "x",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -27,7 +27,7 @@ snapshot_kind: text
|
||||||
Delete(
|
Delete(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "b",
|
normalised: "b",
|
||||||
original: "b",
|
original: "b",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -37,7 +37,7 @@ snapshot_kind: text
|
||||||
Equal(
|
Equal(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "c",
|
normalised: "c",
|
||||||
original: "c",
|
original: "c",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -47,7 +47,7 @@ snapshot_kind: text
|
||||||
Insert(
|
Insert(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "y",
|
normalised: "y",
|
||||||
original: "y",
|
original: "y",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -57,7 +57,7 @@ snapshot_kind: text
|
||||||
Delete(
|
Delete(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "d",
|
normalised: "d",
|
||||||
original: "d",
|
original: "d",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -1,5 +1,5 @@
|
||||||
---
|
---
|
||||||
source: src/utils/myers_diff.rs
|
source: reconcile/src/diffs/myers.rs
|
||||||
expression: result
|
expression: result
|
||||||
snapshot_kind: text
|
snapshot_kind: text
|
||||||
---
|
---
|
||||||
|
|
@ -7,7 +7,7 @@ snapshot_kind: text
|
||||||
Delete(
|
Delete(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "a",
|
normalised: "a",
|
||||||
original: "a",
|
original: "a",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -17,7 +17,7 @@ snapshot_kind: text
|
||||||
Delete(
|
Delete(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "b",
|
normalised: "b",
|
||||||
original: "b",
|
original: "b",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -1,5 +1,5 @@
|
||||||
---
|
---
|
||||||
source: src/utils/myers_diff.rs
|
source: reconcile/src/diffs/myers.rs
|
||||||
expression: result
|
expression: result
|
||||||
snapshot_kind: text
|
snapshot_kind: text
|
||||||
---
|
---
|
||||||
|
|
@ -7,7 +7,7 @@ snapshot_kind: text
|
||||||
Equal(
|
Equal(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "a",
|
normalised: "a",
|
||||||
original: "a",
|
original: "a",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -17,7 +17,7 @@ snapshot_kind: text
|
||||||
Equal(
|
Equal(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "b",
|
normalised: "b",
|
||||||
original: "b",
|
original: "b",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -27,7 +27,7 @@ snapshot_kind: text
|
||||||
Equal(
|
Equal(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "c",
|
normalised: "c",
|
||||||
original: "c",
|
original: "c",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -1,5 +1,5 @@
|
||||||
---
|
---
|
||||||
source: src/utils/myers_diff.rs
|
source: reconcile/src/diffs/myers.rs
|
||||||
expression: result
|
expression: result
|
||||||
snapshot_kind: text
|
snapshot_kind: text
|
||||||
---
|
---
|
||||||
|
|
@ -7,7 +7,7 @@ snapshot_kind: text
|
||||||
Insert(
|
Insert(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "a",
|
normalised: "a",
|
||||||
original: "a",
|
original: "a",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -17,7 +17,7 @@ snapshot_kind: text
|
||||||
Insert(
|
Insert(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "b",
|
normalised: "b",
|
||||||
original: "b",
|
original: "b",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -1,5 +1,5 @@
|
||||||
---
|
---
|
||||||
source: src/utils/myers_diff.rs
|
source: reconcile/src/diffs/myers.rs
|
||||||
expression: result
|
expression: result
|
||||||
snapshot_kind: text
|
snapshot_kind: text
|
||||||
---
|
---
|
||||||
|
|
@ -7,7 +7,7 @@ snapshot_kind: text
|
||||||
Equal(
|
Equal(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "a",
|
normalised: "a",
|
||||||
original: "a",
|
original: "a",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -17,7 +17,7 @@ snapshot_kind: text
|
||||||
Delete(
|
Delete(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "b",
|
normalised: "b",
|
||||||
original: "b",
|
original: "b",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -27,7 +27,7 @@ snapshot_kind: text
|
||||||
Delete(
|
Delete(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "c",
|
normalised: "c",
|
||||||
original: "c",
|
original: "c",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -37,7 +37,7 @@ snapshot_kind: text
|
||||||
Insert(
|
Insert(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "x",
|
normalised: "x",
|
||||||
original: "x",
|
original: "x",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -47,7 +47,7 @@ snapshot_kind: text
|
||||||
Equal(
|
Equal(
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "d",
|
normalised: "d",
|
||||||
original: "d",
|
original: "d",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
224
src/lib.rs
224
src/lib.rs
|
|
@ -1,227 +1,13 @@
|
||||||
//! # Reconcile: conflict-free 3-way text merging
|
mod diffs;
|
||||||
//!
|
|
||||||
//! A library for merging conflicting text edits without manual intervention.
|
|
||||||
//! Unlike traditional 3-way merge tools that produce conflict markers,
|
|
||||||
//! reconcile-text automatically resolves conflicts by applying both sets of
|
|
||||||
//! changes (while updating cursor positions) using an algorithm inspired by
|
|
||||||
//! Operational Transformation.
|
|
||||||
//!
|
|
||||||
//! ✨ **[Try the interactive demo](https://schmelczer.dev/reconcile)** to see it in action.
|
|
||||||
//!
|
|
||||||
//! ## Simple example
|
|
||||||
//!
|
|
||||||
//! ```
|
|
||||||
//! use reconcile_text::{reconcile, BuiltinTokenizer};
|
|
||||||
//!
|
|
||||||
//! // Start with original text
|
|
||||||
//! let parent = "Merging text is hard!";
|
|
||||||
//! // Two people edit simultaneously
|
|
||||||
//! let left = "Merging text is easy!"; // Changed "hard" to "easy"
|
|
||||||
//! let right = "With reconcile, merging documents is hard!"; // Added prefix and changed word
|
|
||||||
//!
|
|
||||||
//! // Reconcile combines both changes intelligently
|
|
||||||
//! let result = reconcile(parent, &left.into(), &right.into(), &*BuiltinTokenizer::Word);
|
|
||||||
//! assert_eq!(result.apply().text(), "With reconcile, merging documents is easy!");
|
|
||||||
//! ```
|
|
||||||
//!
|
|
||||||
//! ## Tokenisation strategies
|
|
||||||
//!
|
|
||||||
//! Merging happens at the token level, and the choice of tokeniser
|
|
||||||
//! significantly affects merge quality and behaviour.
|
|
||||||
//!
|
|
||||||
//! ### Built-in tokenisers
|
|
||||||
//!
|
|
||||||
//! - **`BuiltinTokenizer::Word`** (recommended): Splits on word boundaries,
|
|
||||||
//! preserving word integrity
|
|
||||||
//! - **`BuiltinTokenizer::Character`**: Character-level merging for
|
|
||||||
//! fine-grained control
|
|
||||||
//! - **`BuiltinTokenizer::Line`**: Line-based merging, similar to traditional
|
|
||||||
//! diff tools
|
|
||||||
//!
|
|
||||||
//! ```
|
|
||||||
//! use reconcile_text::{reconcile, BuiltinTokenizer};
|
|
||||||
//!
|
|
||||||
//! let parent = "The quick brown fox\njumps over the lazy dog";
|
|
||||||
//! let left = "The very quick brown fox\njumps over the lazy dog"; // Added "very"
|
|
||||||
//! let right = "The quick red fox\njumps over the lazy dog"; // Changed "brown" to "red"
|
|
||||||
//!
|
|
||||||
//! // Word-level tokenisation (recommended for most text)
|
|
||||||
//! let result = reconcile(parent, &left.into(), &right.into(), &*BuiltinTokenizer::Word);
|
|
||||||
//! assert_eq!(result.apply().text(), "The very quick red fox\njumps over the lazy dog");
|
|
||||||
//!
|
|
||||||
//! // Line-level tokenisation (similar to git merge)
|
|
||||||
//! let result = reconcile(parent, &left.into(), &right.into(), &*BuiltinTokenizer::Line);
|
|
||||||
//! // Line-level produces different results as it treats each line as atomic
|
|
||||||
//! assert_eq!(result.apply().text(), "The quick red foxThe very quick brown fox\njumps over the lazy dog");
|
|
||||||
//! ```
|
|
||||||
//!
|
|
||||||
//! ### Custom tokenisation
|
|
||||||
//!
|
|
||||||
//! For specialised use cases, such as structured languages, custom
|
|
||||||
//! tokenisation logic can be implemented by providing a function with the
|
|
||||||
//! signature `Fn(&str) -> Vec<Token<String>>`:
|
|
||||||
//!
|
|
||||||
//! ```
|
|
||||||
//! use reconcile_text::{reconcile, Token, BuiltinTokenizer};
|
|
||||||
//!
|
|
||||||
//! // Example: sentence-based tokeniser function
|
|
||||||
//! let sentence_tokeniser = |text: &str| {
|
|
||||||
//! text.split_inclusive(". ")
|
|
||||||
//! .map(|sentence| Token::new(
|
|
||||||
//! sentence.to_string(),
|
|
||||||
//! sentence.to_string(),
|
|
||||||
//! false, // don't allow joining with preceding token
|
|
||||||
//! false, // don't allow joining with following token
|
|
||||||
//! ))
|
|
||||||
//! .collect::<Vec<_>>()
|
|
||||||
//! };
|
|
||||||
//!
|
|
||||||
//! let parent = "Hello world. This is a test.";
|
|
||||||
//! let left = "Hello beautiful world. This is a test."; // Added "beautiful"
|
|
||||||
//! let right = "Hello world. This is a great test."; // Changed "a" to "great"
|
|
||||||
//!
|
|
||||||
//! // For most cases, the built-in word tokeniser works well
|
|
||||||
//! let result = reconcile(parent, &left.into(), &right.into(), &sentence_tokeniser);
|
|
||||||
//! assert_eq!(result.apply().text(), "Hello beautiful world. This is a great test.");
|
|
||||||
//! ```
|
|
||||||
//!
|
|
||||||
//! > **Note**: Setting token joinability to `false` causes insertions to
|
|
||||||
//! > interleave (LRLRLR) rather than group together (LLLRRR), which often
|
|
||||||
//! > produces more natural-looking merged text.
|
|
||||||
//!
|
|
||||||
//! ## Cursor tracking
|
|
||||||
//!
|
|
||||||
//! Automatically repositions cursors and selection ranges during merging,
|
|
||||||
//! which is essential for collaborative editors:
|
|
||||||
//!
|
|
||||||
//! ```
|
|
||||||
//! use reconcile_text::{reconcile, BuiltinTokenizer, TextWithCursors, CursorPosition};
|
|
||||||
//!
|
|
||||||
//! let parent = "Hello world";
|
|
||||||
//! let left = TextWithCursors::new(
|
|
||||||
//! "Hello beautiful world".to_string(),
|
|
||||||
//! vec![CursorPosition::new(1, 6)] // After "Hello "
|
|
||||||
//! );
|
|
||||||
//! let right = TextWithCursors::new(
|
|
||||||
//! "Hi world".to_string(),
|
|
||||||
//! vec![CursorPosition::new(2, 0)] // At the beginning
|
|
||||||
//! );
|
|
||||||
//!
|
|
||||||
//! let result = reconcile(parent, &left, &right, &*BuiltinTokenizer::Word);
|
|
||||||
//! let merged = result.apply();
|
|
||||||
//!
|
|
||||||
//! assert_eq!(merged.text(), "Hi beautiful world");
|
|
||||||
//! // Cursors are automatically repositioned in the merged text
|
|
||||||
//! assert_eq!(merged.cursors().len(), 2);
|
|
||||||
//! // Cursor 1 moves from position 6 to position 3 (after "Hi ")
|
|
||||||
//! // Cursor 2 stays at position 0 (at the beginning)
|
|
||||||
//! ```
|
|
||||||
//! > The `cursors` list is sorted by character position (not IDs).
|
|
||||||
//!
|
|
||||||
//! ## Change provenance
|
|
||||||
//!
|
|
||||||
//! Track which changes came from where:
|
|
||||||
//!
|
|
||||||
//! ```rust
|
|
||||||
//! use reconcile_text::{History, SpanWithHistory, BuiltinTokenizer, reconcile};
|
|
||||||
//!
|
|
||||||
//! let parent = "Merging text is hard!";
|
|
||||||
//! let left = "Merging text is easy!"; // Changed "hard" to "easy"
|
|
||||||
//! let right = "With reconcile, merging documents is hard!"; // Added prefix and changed word
|
|
||||||
//!
|
|
||||||
//! let result = reconcile(
|
|
||||||
//! parent,
|
|
||||||
//! &left.into(),
|
|
||||||
//! &right.into(),
|
|
||||||
//! &*BuiltinTokenizer::Word,
|
|
||||||
//! );
|
|
||||||
//!
|
|
||||||
//! assert_eq!(
|
|
||||||
//! result.apply_with_history(),
|
|
||||||
//! vec![
|
|
||||||
//! SpanWithHistory::new("Merging text".to_string(), History::RemovedFromRight),
|
|
||||||
//! SpanWithHistory::new(
|
|
||||||
//! "With reconcile, merging documents".to_string(),
|
|
||||||
//! History::AddedFromRight
|
|
||||||
//! ),
|
|
||||||
//! SpanWithHistory::new(" ".to_string(), History::Unchanged),
|
|
||||||
//! SpanWithHistory::new("is".to_string(), History::Unchanged),
|
|
||||||
//! SpanWithHistory::new(" hard!".to_string(), History::RemovedFromLeft),
|
|
||||||
//! SpanWithHistory::new(" easy!".to_string(), History::AddedFromLeft),
|
|
||||||
//! ]
|
|
||||||
//! );
|
|
||||||
//! ```
|
|
||||||
//!
|
|
||||||
//! ## Compact change serialization
|
|
||||||
//!
|
|
||||||
//! The edits can be serialized into a compact representation without the full
|
|
||||||
//! original text, making the size depend only on the changes made.
|
|
||||||
//!
|
|
||||||
//! ```rust
|
|
||||||
//! # #[cfg(feature = "serde")]
|
|
||||||
//! # {
|
|
||||||
//! use reconcile_text::{EditedText, BuiltinTokenizer};
|
|
||||||
//! use serde_yaml;
|
|
||||||
//! use pretty_assertions::assert_eq;
|
|
||||||
//!
|
|
||||||
//!
|
|
||||||
//! let original = "Merging text is hard!";
|
|
||||||
//! let changes = "Merging text is easy with reconcile!";
|
|
||||||
//!
|
|
||||||
//! let result = EditedText::from_strings(
|
|
||||||
//! original,
|
|
||||||
//! &changes.into()
|
|
||||||
//! );
|
|
||||||
//!
|
|
||||||
//! let serialized = serde_yaml::to_string(&result.to_diff().unwrap()).unwrap();
|
|
||||||
//! assert_eq!(
|
|
||||||
//! serialized,
|
|
||||||
//! concat!(
|
|
||||||
//! "- 15\n",
|
|
||||||
//! "- -6\n",
|
|
||||||
//! "- ' easy with reconcile!'\n"
|
|
||||||
//! )
|
|
||||||
//! );
|
|
||||||
//!
|
|
||||||
//! let deserialized = serde_yaml::from_str(&serialized).unwrap();
|
|
||||||
//! let reconstructed = EditedText::from_diff(
|
|
||||||
//! original,
|
|
||||||
//! deserialized,
|
|
||||||
//! &*BuiltinTokenizer::Word
|
|
||||||
//! ).unwrap();
|
|
||||||
//! assert_eq!(
|
|
||||||
//! reconstructed.apply().text(),
|
|
||||||
//! "Merging text is easy with reconcile!"
|
|
||||||
//! );
|
|
||||||
//! # }
|
|
||||||
//! ```
|
|
||||||
//!
|
|
||||||
//! ## Error handling
|
|
||||||
//!
|
|
||||||
//! The library is designed to be robust and will always produce a result, even
|
|
||||||
//! for edge cases.
|
|
||||||
//!
|
|
||||||
//! ## Performance
|
|
||||||
//!
|
|
||||||
//! Be aware that extremely large diffs may have performance implications.
|
|
||||||
//!
|
|
||||||
//! ## Algorithm overview
|
|
||||||
//!
|
|
||||||
//! For detailed algorithm explanation, see the
|
|
||||||
//! [README](https://github.com/schmelczer/reconcile/blob/main/README.md#how-it-works).
|
|
||||||
|
|
||||||
mod operation_transformation;
|
mod operation_transformation;
|
||||||
mod raw_operation;
|
|
||||||
mod tokenizer;
|
mod tokenizer;
|
||||||
mod types;
|
|
||||||
mod utils;
|
mod utils;
|
||||||
|
|
||||||
pub use operation_transformation::{DiffError, EditedText, reconcile};
|
pub use operation_transformation::{
|
||||||
pub use tokenizer::{BuiltinTokenizer, Tokenizer, token::Token};
|
CursorPosition, EditedText, TextWithCursors, reconcile, reconcile_with_cursors,
|
||||||
pub use types::{
|
reconcile_with_tokenizer,
|
||||||
cursor_position::CursorPosition, history::History, number_or_text::NumberOrText, side::Side,
|
|
||||||
span_with_history::SpanWithHistory, text_with_cursors::TextWithCursors,
|
|
||||||
};
|
};
|
||||||
|
pub use tokenizer::{Tokenizer, token::Token, word_tokenizer::word_tokenizer};
|
||||||
|
|
||||||
#[cfg(feature = "wasm")]
|
#[cfg(feature = "wasm")]
|
||||||
pub mod wasm;
|
pub mod wasm;
|
||||||
|
|
|
||||||
|
|
@ -1,55 +1,51 @@
|
||||||
mod diff_error;
|
mod cursor;
|
||||||
mod edited_text;
|
mod edited_text;
|
||||||
mod operation;
|
mod operation;
|
||||||
mod utils;
|
mod utils;
|
||||||
use std::fmt::Debug;
|
|
||||||
|
|
||||||
pub use diff_error::DiffError;
|
pub use cursor::{CursorPosition, TextWithCursors};
|
||||||
pub use edited_text::EditedText;
|
pub use edited_text::EditedText;
|
||||||
pub use operation::Operation;
|
pub use operation::Operation;
|
||||||
|
|
||||||
use crate::{Tokenizer, types::text_with_cursors::TextWithCursors};
|
use crate::Tokenizer;
|
||||||
|
|
||||||
/// Given an `original` document and two concurrent edits to it,
|
|
||||||
/// return a document containing all changes from both `left`
|
|
||||||
/// and `right`.
|
|
||||||
///
|
|
||||||
/// If a span has been inserted in either the `left` or `right`
|
|
||||||
/// versions, it will be present in the return value. If both sides
|
|
||||||
/// insert the same span with a common prefix, that prefix will only
|
|
||||||
/// be present once in the output.
|
|
||||||
///
|
|
||||||
/// When both sides delete the same span, it will be deleted in the
|
|
||||||
/// return value. If one side deletes a span and the other side inserts
|
|
||||||
/// into that span, the inserted text will be present in the return
|
|
||||||
/// value.
|
|
||||||
///
|
|
||||||
/// Supports UTF-8. Arguments are tokenized using the provided `tokenizer`.
|
|
||||||
///
|
|
||||||
/// ```
|
|
||||||
/// use reconcile_text::{reconcile, BuiltinTokenizer};
|
|
||||||
///
|
|
||||||
/// let parent = "Merging text is hard!";
|
|
||||||
/// let left = "Merging text is easy!";
|
|
||||||
/// let right = "With reconcile, merging documents is hard!";
|
|
||||||
///
|
|
||||||
/// let deconflicted = reconcile(parent, &left.into(), &right.into(), &*BuiltinTokenizer::Word);
|
|
||||||
/// assert_eq!(deconflicted.apply().text(), "With reconcile, merging documents is easy!");
|
|
||||||
/// ```
|
|
||||||
#[must_use]
|
#[must_use]
|
||||||
pub fn reconcile<'a, T>(
|
pub fn reconcile(original: &str, left: &str, right: &str) -> String {
|
||||||
|
reconcile_with_cursors(original, left.into(), right.into())
|
||||||
|
.text
|
||||||
|
.to_string()
|
||||||
|
}
|
||||||
|
|
||||||
|
#[must_use]
|
||||||
|
pub fn reconcile_with_cursors<'a>(
|
||||||
original: &'a str,
|
original: &'a str,
|
||||||
left: &TextWithCursors,
|
left: TextWithCursors<'a>,
|
||||||
right: &TextWithCursors,
|
right: TextWithCursors<'a>,
|
||||||
|
) -> TextWithCursors<'static> {
|
||||||
|
let left_operations = EditedText::from_strings(original, left);
|
||||||
|
let right_operations = EditedText::from_strings(original, right);
|
||||||
|
|
||||||
|
let merged_operations = left_operations.merge(right_operations);
|
||||||
|
|
||||||
|
TextWithCursors::new_owned(merged_operations.apply(), merged_operations.cursors)
|
||||||
|
}
|
||||||
|
|
||||||
|
#[must_use]
|
||||||
|
pub fn reconcile_with_tokenizer<'a, F, T>(
|
||||||
|
original: &str,
|
||||||
|
left: TextWithCursors<'a>,
|
||||||
|
right: TextWithCursors<'a>,
|
||||||
tokenizer: &Tokenizer<T>,
|
tokenizer: &Tokenizer<T>,
|
||||||
) -> EditedText<'a, T>
|
) -> TextWithCursors<'static>
|
||||||
where
|
where
|
||||||
T: PartialEq + Clone + Debug,
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
{
|
{
|
||||||
let left_operations = EditedText::from_strings_with_tokenizer(original, left, tokenizer);
|
let left_operations = EditedText::from_strings_with_tokenizer(original, left, tokenizer);
|
||||||
let right_operations = EditedText::from_strings_with_tokenizer(original, right, tokenizer);
|
let right_operations = EditedText::from_strings_with_tokenizer(original, right, tokenizer);
|
||||||
|
|
||||||
left_operations.merge(right_operations)
|
let merged_operations = left_operations.merge(right_operations);
|
||||||
|
|
||||||
|
TextWithCursors::new_owned(merged_operations.apply(), merged_operations.cursors)
|
||||||
}
|
}
|
||||||
|
|
||||||
#[cfg(test)]
|
#[cfg(test)]
|
||||||
|
|
@ -60,13 +56,13 @@ mod test {
|
||||||
use test_case::test_matrix;
|
use test_case::test_matrix;
|
||||||
|
|
||||||
use super::*;
|
use super::*;
|
||||||
use crate::{BuiltinTokenizer, CursorPosition, types::text_with_cursors::TextWithCursors};
|
use crate::CursorPosition;
|
||||||
|
|
||||||
#[test]
|
#[test]
|
||||||
fn test_cursor_complex() {
|
fn test_cursor_complex() {
|
||||||
let original: &'static str = "this is some complex text to test cursor positions";
|
let original = "this is some complex text to test cursor positions";
|
||||||
let left = TextWithCursors::new(
|
let left = TextWithCursors::new(
|
||||||
"this is really complex text for testing cursor positions".to_owned(),
|
"this is really complex text for testing cursor positions",
|
||||||
vec![
|
vec![
|
||||||
CursorPosition {
|
CursorPosition {
|
||||||
id: 0,
|
id: 0,
|
||||||
|
|
@ -79,7 +75,7 @@ mod test {
|
||||||
],
|
],
|
||||||
);
|
);
|
||||||
let right = TextWithCursors::new(
|
let right = TextWithCursors::new(
|
||||||
"that was some complex sample to test cursor movements".to_owned(),
|
"that was some complex sample to test cursor movements",
|
||||||
vec![
|
vec![
|
||||||
CursorPosition {
|
CursorPosition {
|
||||||
id: 2,
|
id: 2,
|
||||||
|
|
@ -92,31 +88,31 @@ mod test {
|
||||||
],
|
],
|
||||||
);
|
);
|
||||||
|
|
||||||
let merged = reconcile(original, &left, &right, &*BuiltinTokenizer::Word).apply();
|
let merged = reconcile_with_cursors(original, left, right);
|
||||||
|
|
||||||
assert_eq!(
|
assert_eq!(
|
||||||
&merged.text(),
|
merged,
|
||||||
"that was really complex sample for testing cursor movements"
|
TextWithCursors::new(
|
||||||
);
|
"that was really complex sample for testing cursor movements",
|
||||||
assert_eq!(
|
vec![
|
||||||
merged.cursors(),
|
CursorPosition {
|
||||||
vec![
|
id: 2,
|
||||||
CursorPosition {
|
char_index: 5
|
||||||
id: 2,
|
}, // unchanged
|
||||||
char_index: 5
|
CursorPosition {
|
||||||
}, // unchanged
|
id: 0,
|
||||||
CursorPosition {
|
char_index: 9
|
||||||
id: 0,
|
}, // before "really"
|
||||||
char_index: 9
|
CursorPosition {
|
||||||
}, // before "really"
|
id: 1,
|
||||||
CursorPosition {
|
char_index: 23
|
||||||
id: 1,
|
}, // inside of "s|ample" because "text" got replaced by "sample"
|
||||||
char_index: 23
|
CursorPosition {
|
||||||
}, // inside of "s|ample" because "text" got replaced by "sample"
|
id: 3,
|
||||||
CursorPosition {
|
char_index: 30
|
||||||
id: 3,
|
}, // after "complex sample"
|
||||||
char_index: 30
|
]
|
||||||
}, // after "complex sample"
|
)
|
||||||
]
|
|
||||||
);
|
);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -129,11 +125,14 @@ mod test {
|
||||||
], [
|
], [
|
||||||
"pride_and_prejudice.txt",
|
"pride_and_prejudice.txt",
|
||||||
"room_with_a_view.txt",
|
"room_with_a_view.txt",
|
||||||
|
"kun_lu.txt",
|
||||||
|
"blns.txt"
|
||||||
], [
|
], [
|
||||||
|
"pride_and_prejudice.txt",
|
||||||
"room_with_a_view.txt",
|
"room_with_a_view.txt",
|
||||||
"kun_lu.txt",
|
"kun_lu.txt",
|
||||||
"blns.txt"
|
"blns.txt"
|
||||||
], [0..10000], [0..10000, 10000..20000], [0..10000, 10000..20000])]
|
], [0..10000, 10000..20000], [0..10000, 10000..20000], [0..10000, 10000..20000])]
|
||||||
fn test_merge_files_without_panic(
|
fn test_merge_files_without_panic(
|
||||||
file_name_1: &str,
|
file_name_1: &str,
|
||||||
file_name_2: &str,
|
file_name_2: &str,
|
||||||
|
|
@ -156,16 +155,11 @@ mod test {
|
||||||
.unwrap()
|
.unwrap()
|
||||||
.chars()
|
.chars()
|
||||||
.skip(range.start)
|
.skip(range.start)
|
||||||
.take(range.len())
|
.take(range.end)
|
||||||
.collect::<String>()
|
.collect::<String>()
|
||||||
})
|
})
|
||||||
.collect::<Vec<_>>();
|
.collect::<Vec<_>>();
|
||||||
|
|
||||||
let _ = reconcile(
|
let _ = reconcile(&contents[0], &contents[1], &contents[2]);
|
||||||
&contents[0],
|
|
||||||
&(&contents[1]).into(),
|
|
||||||
&(&contents[2]).into(),
|
|
||||||
&*BuiltinTokenizer::Word,
|
|
||||||
);
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
|
||||||
57
src/operation_transformation/cursor.rs
Normal file
57
src/operation_transformation/cursor.rs
Normal file
|
|
@ -0,0 +1,57 @@
|
||||||
|
use std::borrow::Cow;
|
||||||
|
|
||||||
|
#[cfg(feature = "serde")]
|
||||||
|
use serde::{Deserialize, Serialize};
|
||||||
|
|
||||||
|
// CursorPosition represents the position of an identifiable cursor in a text
|
||||||
|
// document based on its (UTF-8) character index.
|
||||||
|
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
|
||||||
|
#[derive(Debug, Clone, PartialEq, Default)]
|
||||||
|
pub struct CursorPosition {
|
||||||
|
pub id: usize,
|
||||||
|
pub char_index: usize,
|
||||||
|
}
|
||||||
|
|
||||||
|
impl CursorPosition {
|
||||||
|
#[must_use]
|
||||||
|
pub fn with_index(&self, index: usize) -> Self {
|
||||||
|
CursorPosition {
|
||||||
|
id: self.id,
|
||||||
|
char_index: index,
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
|
||||||
|
#[derive(Debug, Clone, PartialEq, Default)]
|
||||||
|
pub struct TextWithCursors<'a> {
|
||||||
|
pub text: Cow<'a, str>,
|
||||||
|
pub cursors: Vec<CursorPosition>,
|
||||||
|
}
|
||||||
|
|
||||||
|
impl<'a> TextWithCursors<'a> {
|
||||||
|
#[must_use]
|
||||||
|
pub fn new(text: &'a str, cursors: Vec<CursorPosition>) -> Self {
|
||||||
|
Self {
|
||||||
|
text: text.into(),
|
||||||
|
cursors,
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
#[must_use]
|
||||||
|
pub fn new_owned(text: String, cursors: Vec<CursorPosition>) -> Self {
|
||||||
|
Self {
|
||||||
|
text: text.into(),
|
||||||
|
cursors,
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
impl<'a> From<&'a str> for TextWithCursors<'a> {
|
||||||
|
fn from(text: &'a str) -> Self {
|
||||||
|
Self {
|
||||||
|
text: text.into(),
|
||||||
|
cursors: Vec::new(),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
@ -1,26 +0,0 @@
|
||||||
use thiserror::Error;
|
|
||||||
|
|
||||||
/// Error type for invalid diff operations
|
|
||||||
#[derive(Error, Debug, Clone, PartialEq)]
|
|
||||||
pub enum DiffError {
|
|
||||||
/// The diff references a range that exceeds the original text length
|
|
||||||
#[error(
|
|
||||||
"Invalid diff: attempting to access {requested} characters starting at position \
|
|
||||||
{position}, but original text only has {available} characters remaining"
|
|
||||||
)]
|
|
||||||
LengthExceedsOriginal {
|
|
||||||
/// The position where the operation starts
|
|
||||||
position: usize,
|
|
||||||
/// The number of characters requested
|
|
||||||
requested: usize,
|
|
||||||
/// The number of characters available from the position
|
|
||||||
available: usize,
|
|
||||||
},
|
|
||||||
|
|
||||||
/// A character count was too large to represent as i64
|
|
||||||
#[error("Integer overflow: value {value} cannot be represented as i64")]
|
|
||||||
IntegerOverflow {
|
|
||||||
/// The value that caused the overflow
|
|
||||||
value: usize,
|
|
||||||
},
|
|
||||||
}
|
|
||||||
|
|
@ -1,111 +1,92 @@
|
||||||
use std::fmt::Debug;
|
|
||||||
|
|
||||||
#[cfg(feature = "serde")]
|
#[cfg(feature = "serde")]
|
||||||
use serde::{Deserialize, Serialize};
|
use serde::{Deserialize, Serialize};
|
||||||
|
|
||||||
|
use super::{CursorPosition, Operation, TextWithCursors};
|
||||||
use crate::{
|
use crate::{
|
||||||
BuiltinTokenizer, CursorPosition, TextWithCursors, Token,
|
diffs::{myers::diff, raw_operation::RawOperation},
|
||||||
operation_transformation::{
|
operation_transformation::utils::{
|
||||||
DiffError, Operation,
|
cook_operations::cook_operations, elongate_operations::elongate_operations,
|
||||||
utils::{cook_operations::cook_operations, elongate_operations::elongate_operations},
|
|
||||||
},
|
},
|
||||||
raw_operation::RawOperation,
|
tokenizer::{Tokenizer, word_tokenizer::word_tokenizer},
|
||||||
tokenizer::Tokenizer,
|
utils::{side::Side, string_builder::StringBuilder},
|
||||||
types::{
|
|
||||||
history::History, number_or_text::NumberOrText, side::Side,
|
|
||||||
span_with_history::SpanWithHistory,
|
|
||||||
},
|
|
||||||
utils::string_builder::StringBuilder,
|
|
||||||
};
|
};
|
||||||
|
|
||||||
/// A text document with a sequence of operations derived from diffing it
|
/// A text document and a sequence of operations that can be applied to the text
|
||||||
/// against an updated version. Supports merging two `EditedText` instances
|
/// document. `EditedText` supports merging two sequences of operations using
|
||||||
/// (from the same original) via Operational Transformation.
|
/// the principles of Operational Transformation.
|
||||||
///
|
///
|
||||||
/// Created via `from_strings`, `from_strings_with_tokenizer`, or `from_diff`,
|
/// It's mainly created through the `from_strings` method, then merged with
|
||||||
/// then merged with another `EditedText` and applied to get the reconciled
|
/// another `EditedText` derived from the same original text and then applied to
|
||||||
/// text.
|
/// the original text to get the reconciled text of concurrent edits.
|
||||||
///
|
///
|
||||||
/// Also tracks cursor positions from the updated text, repositioning them
|
/// In addition to text and operations, it also keeps track of cursor positions
|
||||||
/// when operations are applied.
|
/// in the original text. The cursor positions are updated when the operations
|
||||||
|
/// are applied, so that the cursor positions can be used to restore the
|
||||||
|
/// cursor positions in the updated text.
|
||||||
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
|
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
|
||||||
#[derive(Debug, Clone, PartialEq, Default)]
|
#[derive(Debug, Clone, PartialEq, Default)]
|
||||||
pub struct EditedText<'a, T>
|
pub struct EditedText<'a, T>
|
||||||
where
|
where
|
||||||
T: PartialEq + Clone + Debug,
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
{
|
{
|
||||||
text: &'a str,
|
text: &'a str,
|
||||||
operations: Vec<Operation<T>>,
|
operations: Vec<Operation<T>>,
|
||||||
operation_sides: Vec<Side>,
|
pub(crate) cursors: Vec<CursorPosition>,
|
||||||
cursors: Vec<CursorPosition>,
|
|
||||||
}
|
}
|
||||||
|
|
||||||
impl<'a> EditedText<'a, String> {
|
impl<'a> EditedText<'a, String> {
|
||||||
/// Create an `EditedText` from the given original and updated strings.
|
/// Create an `EditedText` from the given original (old) and updated (new)
|
||||||
/// Uses the default word tokenizer (splits on word boundaries).
|
/// strings. The returned `EditedText` represents the changes from the
|
||||||
|
/// original to the updated text. When the return value is applied to
|
||||||
|
/// the original text, it will result in the updated text. The default
|
||||||
|
/// word tokenizer is used to tokenize the text which splits the text on
|
||||||
|
/// whitespaces.
|
||||||
#[must_use]
|
#[must_use]
|
||||||
pub fn from_strings(original: &'a str, updated: &TextWithCursors) -> Self {
|
pub fn from_strings(original: &'a str, updated: TextWithCursors<'a>) -> Self {
|
||||||
Self::from_strings_with_tokenizer(original, updated, &*BuiltinTokenizer::Word)
|
Self::from_strings_with_tokenizer(original, updated, &word_tokenizer)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
impl<'a, T> EditedText<'a, T>
|
impl<'a, T> EditedText<'a, T>
|
||||||
where
|
where
|
||||||
T: PartialEq + Clone + Debug,
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
{
|
{
|
||||||
/// Create an `EditedText` from the given original and updated strings
|
/// Create an `EditedText` from the given original (old) and updated (new)
|
||||||
/// using the provided tokenizer
|
/// strings. The returned `EditedText` represents the changes from the
|
||||||
#[must_use]
|
/// original to the updated text. When the return value is applied to
|
||||||
|
/// the original text, it will result in the updated text. The tokenizer
|
||||||
|
/// function is used to tokenize the text.
|
||||||
pub fn from_strings_with_tokenizer(
|
pub fn from_strings_with_tokenizer(
|
||||||
original: &'a str,
|
original: &'a str,
|
||||||
updated: &TextWithCursors,
|
updated: TextWithCursors<'a>,
|
||||||
tokenizer: &Tokenizer<T>,
|
tokenizer: &Tokenizer<T>,
|
||||||
) -> Self {
|
) -> Self {
|
||||||
let original_tokens = (tokenizer)(original);
|
let original_tokens = (tokenizer)(original);
|
||||||
let updated_tokens = (tokenizer)(&updated.text());
|
let updated_tokens = (tokenizer)(&updated.text);
|
||||||
|
|
||||||
let diff: Vec<RawOperation<T>> = RawOperation::vec_from(&original_tokens, &updated_tokens);
|
let diff: Vec<RawOperation<T>> = diff(&original_tokens, &updated_tokens);
|
||||||
let operations: Vec<Operation<T>> = cook_operations(elongate_operations(diff)).collect();
|
|
||||||
let operation_count = operations.len();
|
|
||||||
|
|
||||||
Self::new(
|
Self::new(
|
||||||
original,
|
original,
|
||||||
operations,
|
cook_operations(elongate_operations(diff)).collect(),
|
||||||
vec![Side::Left; operation_count],
|
updated.cursors,
|
||||||
updated.cursors(),
|
|
||||||
)
|
)
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Create a new `EditedText` with the given operations.
|
/// Create a new `EditedText` with the given operations.
|
||||||
/// The operations must be in the order in which they are meant to be
|
/// The operations must be in the order in which they are meant to be
|
||||||
/// applied. The operations must not overlap.
|
/// applied. The operations must not overlap.
|
||||||
fn new(
|
fn new(text: &'a str, operations: Vec<Operation<T>>, mut cursors: Vec<CursorPosition>) -> Self {
|
||||||
text: &'a str,
|
|
||||||
operations: Vec<Operation<T>>,
|
|
||||||
operation_sides: Vec<Side>,
|
|
||||||
mut cursors: Vec<CursorPosition>,
|
|
||||||
) -> Self {
|
|
||||||
cursors.sort_by_key(|cursor| cursor.char_index);
|
cursors.sort_by_key(|cursor| cursor.char_index);
|
||||||
|
|
||||||
Self {
|
Self {
|
||||||
text,
|
text,
|
||||||
operations,
|
operations,
|
||||||
operation_sides,
|
|
||||||
cursors,
|
cursors,
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Merge two `EditedText` instances. The two instances must be derived
|
|
||||||
/// from the same original text. The operations are merged using the
|
|
||||||
/// principles of Operational Transformation. The cursors are updated
|
|
||||||
/// accordingly to reflect the changes made by the merged operations.
|
|
||||||
///
|
|
||||||
/// # Panics
|
|
||||||
///
|
|
||||||
/// Panics if there's an integer overflow (in isize) when calculating new
|
|
||||||
/// cursor positions.
|
|
||||||
#[must_use]
|
#[must_use]
|
||||||
#[allow(clippy::too_many_lines)]
|
|
||||||
pub fn merge(self, other: Self) -> Self {
|
pub fn merge(self, other: Self) -> Self {
|
||||||
debug_assert_eq!(
|
debug_assert_eq!(
|
||||||
self.text, other.text,
|
self.text, other.text,
|
||||||
|
|
@ -118,8 +99,6 @@ where
|
||||||
|
|
||||||
let mut merged_operations: Vec<Operation<T>> =
|
let mut merged_operations: Vec<Operation<T>> =
|
||||||
Vec::with_capacity(self.operations.len() + other.operations.len());
|
Vec::with_capacity(self.operations.len() + other.operations.len());
|
||||||
let mut merged_operation_sides: Vec<Side> =
|
|
||||||
Vec::with_capacity(self.operations.len() + other.operations.len());
|
|
||||||
|
|
||||||
let mut left_iter = self.operations.into_iter();
|
let mut left_iter = self.operations.into_iter();
|
||||||
let mut right_iter = other.operations.into_iter();
|
let mut right_iter = other.operations.into_iter();
|
||||||
|
|
@ -135,96 +114,83 @@ where
|
||||||
let mut last_right_op = None;
|
let mut last_right_op = None;
|
||||||
|
|
||||||
loop {
|
loop {
|
||||||
let (side, operation) = match (maybe_left_op.as_ref(), maybe_right_op.as_ref()) {
|
let (side, operation, mut last_other_op) =
|
||||||
(Some(left_op), Some(right_op)) => {
|
match (maybe_left_op.clone(), maybe_right_op.clone()) {
|
||||||
if left_op.cmp_priority(seen_left_length, right_op, seen_right_length)
|
(Some(left_op), Some(right_op)) => {
|
||||||
== std::cmp::Ordering::Less
|
if left_op
|
||||||
{
|
.get_sort_key(seen_left_length)
|
||||||
(Side::Left, maybe_left_op.take().unwrap())
|
.partial_cmp(&right_op.get_sort_key(seen_right_length))
|
||||||
} else {
|
== Some(std::cmp::Ordering::Less)
|
||||||
(Side::Right, maybe_right_op.take().unwrap())
|
{
|
||||||
|
(Side::Left, left_op, last_right_op.clone())
|
||||||
|
} else {
|
||||||
|
(Side::Right, right_op, last_left_op.clone())
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
(Some(_), None) => (Side::Left, maybe_left_op.take().unwrap()),
|
(Some(left_op), None) => (Side::Left, left_op, last_right_op.clone()),
|
||||||
(None, Some(_)) => (Side::Right, maybe_right_op.take().unwrap()),
|
(None, Some(right_op)) => (Side::Right, right_op, last_left_op.clone()),
|
||||||
(None, None) => break,
|
(None, None) => break,
|
||||||
};
|
};
|
||||||
|
|
||||||
let is_advancing_operation = matches!(
|
let is_advancing_operation = matches!(
|
||||||
operation,
|
operation,
|
||||||
Operation::Insert { .. } | Operation::Equal { .. }
|
Operation::Insert { .. } | Operation::Equal { .. }
|
||||||
);
|
);
|
||||||
|
|
||||||
let original_length = operation.len();
|
let original_length = operation.len() as i64;
|
||||||
let (side, result) = match side {
|
let result = match side {
|
||||||
Side::Left => {
|
Side::Left => {
|
||||||
let result = operation.merge_operations(last_right_op.as_ref());
|
let result = operation.merge_operations(&mut last_other_op);
|
||||||
|
|
||||||
if let ref op @ (Operation::Insert { .. } | Operation::Equal { .. }) = result {
|
if let ref op @ (Operation::Insert { .. } | Operation::Equal { .. }) = result {
|
||||||
let merged_length_signed = isize::try_from(merged_length)
|
let shift = merged_length as i64 - seen_left_length as i64
|
||||||
.expect("merged_length must fit in isize");
|
+ op.len() as i64
|
||||||
let seen_left_length_signed = isize::try_from(seen_left_length)
|
- original_length;
|
||||||
.expect("seen_left_length must fit in isize");
|
|
||||||
let op_len_signed =
|
|
||||||
isize::try_from(op.len()).expect("op.len() must fit in isize");
|
|
||||||
let original_length_signed = isize::try_from(original_length)
|
|
||||||
.expect("original_length must fit in isize");
|
|
||||||
|
|
||||||
let shift = merged_length_signed - seen_left_length_signed + op_len_signed
|
|
||||||
- original_length_signed;
|
|
||||||
|
|
||||||
while let Some(cursor) = left_cursors.next_if(|cursor| {
|
while let Some(cursor) = left_cursors.next_if(|cursor| {
|
||||||
cursor.char_index <= seen_left_length + original_length
|
cursor.char_index <= seen_left_length + original_length as usize
|
||||||
}) {
|
}) {
|
||||||
merged_cursors.push(
|
merged_cursors.push(
|
||||||
cursor.with_index(cursor.char_index.saturating_add_signed(shift)),
|
cursor.with_index((cursor.char_index as i64 + shift) as usize),
|
||||||
);
|
);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
if is_advancing_operation {
|
if is_advancing_operation {
|
||||||
seen_left_length += original_length;
|
seen_left_length += original_length as usize;
|
||||||
}
|
}
|
||||||
|
|
||||||
maybe_left_op = left_iter.next();
|
maybe_left_op = left_iter.next();
|
||||||
last_left_op = Some(result.clone());
|
last_left_op = Some(result.clone());
|
||||||
|
|
||||||
(Side::Left, result)
|
result
|
||||||
}
|
}
|
||||||
Side::Right => {
|
Side::Right => {
|
||||||
let result = operation.merge_operations(last_left_op.as_ref());
|
let result = operation.merge_operations(&mut last_other_op);
|
||||||
|
|
||||||
if let ref op @ (Operation::Insert { .. } | Operation::Equal { .. }) = result {
|
if let ref op @ (Operation::Insert { .. } | Operation::Equal { .. }) = result {
|
||||||
let merged_length_signed = isize::try_from(merged_length)
|
let shift = merged_length as i64 - seen_right_length as i64
|
||||||
.expect("merged_length must fit in isize");
|
+ op.len() as i64
|
||||||
let seen_right_length_signed = isize::try_from(seen_right_length)
|
- original_length;
|
||||||
.expect("seen_right_length must fit in isize");
|
|
||||||
let op_len_signed =
|
|
||||||
isize::try_from(op.len()).expect("op.len() must fit in isize");
|
|
||||||
let original_length_signed = isize::try_from(original_length)
|
|
||||||
.expect("original_length must fit in isize");
|
|
||||||
|
|
||||||
let shift = merged_length_signed - seen_right_length_signed + op_len_signed
|
|
||||||
- original_length_signed;
|
|
||||||
|
|
||||||
while let Some(cursor) = right_cursors.next_if(|cursor| {
|
while let Some(cursor) = right_cursors.next_if(|cursor| {
|
||||||
cursor.char_index <= seen_right_length + original_length
|
cursor.char_index <= seen_right_length + original_length as usize
|
||||||
}) {
|
}) {
|
||||||
merged_cursors.push(
|
merged_cursors.push(
|
||||||
cursor.with_index(cursor.char_index.saturating_add_signed(shift)),
|
cursor.with_index((cursor.char_index as i64 + shift) as usize),
|
||||||
);
|
);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
if is_advancing_operation {
|
if is_advancing_operation {
|
||||||
seen_right_length += original_length;
|
seen_right_length += original_length as usize;
|
||||||
}
|
}
|
||||||
|
|
||||||
maybe_right_op = right_iter.next();
|
maybe_right_op = right_iter.next();
|
||||||
last_right_op = Some(result.clone());
|
last_right_op = Some(result.clone());
|
||||||
|
|
||||||
(Side::Right, result)
|
result
|
||||||
}
|
}
|
||||||
};
|
};
|
||||||
|
|
||||||
|
|
@ -237,306 +203,25 @@ where
|
||||||
}
|
}
|
||||||
|
|
||||||
merged_operations.push(result);
|
merged_operations.push(result);
|
||||||
merged_operation_sides.push(side);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
for cursor in left_cursors.chain(right_cursors) {
|
for cursor in left_cursors.chain(right_cursors) {
|
||||||
merged_cursors.push(cursor.with_index(merged_length));
|
merged_cursors.push(cursor.with_index(merged_length));
|
||||||
}
|
}
|
||||||
|
|
||||||
debug_assert_eq!(merged_operations.len(), merged_operation_sides.len());
|
Self::new(self.text, merged_operations, merged_cursors)
|
||||||
|
|
||||||
Self::new(
|
|
||||||
self.text,
|
|
||||||
merged_operations,
|
|
||||||
merged_operation_sides,
|
|
||||||
merged_cursors,
|
|
||||||
)
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Apply the operations to the text and return the resulting text
|
/// Apply the operations to the text and return the resulting text.
|
||||||
#[must_use]
|
#[must_use]
|
||||||
pub fn apply(&self) -> TextWithCursors {
|
pub fn apply(&self) -> String {
|
||||||
let mut builder: StringBuilder<'_> = StringBuilder::new(self.text);
|
let mut builder: StringBuilder<'_> = StringBuilder::new(self.text);
|
||||||
|
|
||||||
for operation in &self.operations {
|
for operation in &self.operations {
|
||||||
builder = operation.apply(builder);
|
builder = operation.apply(builder);
|
||||||
}
|
}
|
||||||
|
|
||||||
TextWithCursors::new(builder.take(), self.cursors.clone())
|
builder.build()
|
||||||
}
|
|
||||||
|
|
||||||
/// Apply the operations to the text and return the resulting text in chunks
|
|
||||||
/// together with the provenance describing where each chunk came from.
|
|
||||||
///
|
|
||||||
/// Returns all spans including deletions (not present in the merged text).
|
|
||||||
///
|
|
||||||
/// ```
|
|
||||||
/// use reconcile_text::{History, SpanWithHistory, BuiltinTokenizer, reconcile};
|
|
||||||
///
|
|
||||||
/// let parent = "Merging text is hard!";
|
|
||||||
/// let left = "Merging text is easy!"; // Changed "hard" to "easy"
|
|
||||||
/// let right = "With reconcile, merging documents is hard!"; // Added prefix and changed word
|
|
||||||
///
|
|
||||||
/// let result = reconcile(
|
|
||||||
/// parent,
|
|
||||||
/// &left.into(),
|
|
||||||
/// &right.into(),
|
|
||||||
/// &*BuiltinTokenizer::Word,
|
|
||||||
/// );
|
|
||||||
///
|
|
||||||
/// assert_eq!(
|
|
||||||
/// result.apply_with_history(),
|
|
||||||
/// vec![
|
|
||||||
/// SpanWithHistory::new("Merging text".to_string(), History::RemovedFromRight,),
|
|
||||||
/// SpanWithHistory::new(
|
|
||||||
/// "With reconcile, merging documents".to_string(),
|
|
||||||
/// History::AddedFromRight,
|
|
||||||
/// ),
|
|
||||||
/// SpanWithHistory::new(" ".to_string(), History::Unchanged,),
|
|
||||||
/// SpanWithHistory::new("is".to_string(), History::Unchanged,),
|
|
||||||
/// SpanWithHistory::new(" hard!".to_string(), History::RemovedFromLeft,),
|
|
||||||
/// SpanWithHistory::new(" easy!".to_string(), History::AddedFromLeft,),
|
|
||||||
/// ]
|
|
||||||
/// );
|
|
||||||
/// ```
|
|
||||||
#[must_use]
|
|
||||||
pub fn apply_with_history(&self) -> Vec<SpanWithHistory> {
|
|
||||||
let chars: Vec<char> = self.text.chars().collect();
|
|
||||||
let mut builder: StringBuilder<'_> = StringBuilder::new(self.text);
|
|
||||||
|
|
||||||
let mut history = Vec::with_capacity(self.operations.len());
|
|
||||||
|
|
||||||
for (operation, side) in self.operations.iter().zip(self.operation_sides.iter()) {
|
|
||||||
builder = operation.apply(builder);
|
|
||||||
|
|
||||||
match operation {
|
|
||||||
Operation::Equal { .. } => {
|
|
||||||
history.push(SpanWithHistory::new(builder.take(), History::Unchanged));
|
|
||||||
}
|
|
||||||
Operation::Insert { .. } => {
|
|
||||||
let h = match side {
|
|
||||||
Side::Left => History::AddedFromLeft,
|
|
||||||
Side::Right => History::AddedFromRight,
|
|
||||||
};
|
|
||||||
history.push(SpanWithHistory::new(builder.take(), h));
|
|
||||||
}
|
|
||||||
Operation::Delete {
|
|
||||||
deleted_character_count,
|
|
||||||
order,
|
|
||||||
..
|
|
||||||
} => {
|
|
||||||
let deleted: String = chars[*order..*order + *deleted_character_count]
|
|
||||||
.iter()
|
|
||||||
.collect();
|
|
||||||
let h = match side {
|
|
||||||
Side::Left => History::RemovedFromLeft,
|
|
||||||
Side::Right => History::RemovedFromRight,
|
|
||||||
};
|
|
||||||
history.push(SpanWithHistory::new(deleted, h));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
history
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Apply the operations and return both the merged text with cursors and
|
|
||||||
/// the provenance history in a single pass
|
|
||||||
#[must_use]
|
|
||||||
pub fn apply_with_all(&self) -> (TextWithCursors, Vec<SpanWithHistory>) {
|
|
||||||
let chars: Vec<char> = self.text.chars().collect();
|
|
||||||
let mut builder: StringBuilder<'_> = StringBuilder::new(self.text);
|
|
||||||
let mut history = Vec::with_capacity(self.operations.len());
|
|
||||||
let mut full_text = String::new();
|
|
||||||
|
|
||||||
for (operation, side) in self.operations.iter().zip(self.operation_sides.iter()) {
|
|
||||||
builder = operation.apply(builder);
|
|
||||||
|
|
||||||
match operation {
|
|
||||||
Operation::Equal { .. } => {
|
|
||||||
let span = builder.take();
|
|
||||||
full_text.push_str(&span);
|
|
||||||
history.push(SpanWithHistory::new(span, History::Unchanged));
|
|
||||||
}
|
|
||||||
Operation::Insert { .. } => {
|
|
||||||
let span = builder.take();
|
|
||||||
full_text.push_str(&span);
|
|
||||||
let h = match side {
|
|
||||||
Side::Left => History::AddedFromLeft,
|
|
||||||
Side::Right => History::AddedFromRight,
|
|
||||||
};
|
|
||||||
history.push(SpanWithHistory::new(span, h));
|
|
||||||
}
|
|
||||||
Operation::Delete {
|
|
||||||
deleted_character_count,
|
|
||||||
order,
|
|
||||||
..
|
|
||||||
} => {
|
|
||||||
let deleted: String = chars[*order..*order + *deleted_character_count]
|
|
||||||
.iter()
|
|
||||||
.collect();
|
|
||||||
let h = match side {
|
|
||||||
Side::Left => History::RemovedFromLeft,
|
|
||||||
Side::Right => History::RemovedFromRight,
|
|
||||||
};
|
|
||||||
history.push(SpanWithHistory::new(deleted, h));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
(
|
|
||||||
TextWithCursors::new(full_text, self.cursors.clone()),
|
|
||||||
history,
|
|
||||||
)
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Convert the `EditedText` into a terse representation ready for
|
|
||||||
/// serialization. The result omits cursor positions and the original text.
|
|
||||||
/// This is useful for sending text diffs over the network if there's a
|
|
||||||
/// clear consensus on the original text.
|
|
||||||
///
|
|
||||||
/// Inserts are strings, deletes are negative integers (character count),
|
|
||||||
/// and retained spans are positive integers (character count).
|
|
||||||
///
|
|
||||||
/// # Errors
|
|
||||||
///
|
|
||||||
/// Returns `DiffError::IntegerOverflow` if a character count exceeds
|
|
||||||
/// `i64::MAX`.
|
|
||||||
pub fn to_diff(&self) -> Result<Vec<NumberOrText>, DiffError> {
|
|
||||||
let mut result: Vec<NumberOrText> = Vec::with_capacity(self.operations.len());
|
|
||||||
let mut previous_equal: Option<usize> = None;
|
|
||||||
|
|
||||||
for operation in &self.operations {
|
|
||||||
match operation {
|
|
||||||
Operation::Equal { length, .. } => {
|
|
||||||
if let Some(prev_length) = previous_equal {
|
|
||||||
previous_equal = Some(prev_length + *length);
|
|
||||||
} else {
|
|
||||||
previous_equal = Some(*length);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
Operation::Insert { text, .. } => {
|
|
||||||
if let Some(prev_length) = previous_equal {
|
|
||||||
result
|
|
||||||
.push(NumberOrText::Number(i64::try_from(prev_length).map_err(
|
|
||||||
|_| DiffError::IntegerOverflow { value: prev_length },
|
|
||||||
)?));
|
|
||||||
previous_equal = None;
|
|
||||||
}
|
|
||||||
|
|
||||||
let text: String = text.iter().map(Token::original).collect();
|
|
||||||
result.push(NumberOrText::Text(text));
|
|
||||||
}
|
|
||||||
|
|
||||||
Operation::Delete {
|
|
||||||
deleted_character_count,
|
|
||||||
..
|
|
||||||
} => {
|
|
||||||
if let Some(prev_length) = previous_equal {
|
|
||||||
result
|
|
||||||
.push(NumberOrText::Number(i64::try_from(prev_length).map_err(
|
|
||||||
|_| DiffError::IntegerOverflow { value: prev_length },
|
|
||||||
)?));
|
|
||||||
previous_equal = None;
|
|
||||||
}
|
|
||||||
|
|
||||||
let count = i64::try_from(*deleted_character_count).map_err(|_| {
|
|
||||||
DiffError::IntegerOverflow {
|
|
||||||
value: *deleted_character_count,
|
|
||||||
}
|
|
||||||
})?;
|
|
||||||
result.push(NumberOrText::Number(-count));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if let Some(prev_length) = previous_equal {
|
|
||||||
result
|
|
||||||
.push(NumberOrText::Number(i64::try_from(prev_length).map_err(
|
|
||||||
|_| DiffError::IntegerOverflow { value: prev_length },
|
|
||||||
)?));
|
|
||||||
}
|
|
||||||
|
|
||||||
Ok(result)
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Reconstruct an `EditedText` from a diff and the original text.
|
|
||||||
///
|
|
||||||
/// # Errors
|
|
||||||
///
|
|
||||||
/// Returns `DiffError::LengthExceedsOriginal` if the diff references a
|
|
||||||
/// range that exceeds the original text length.
|
|
||||||
///
|
|
||||||
/// # Panics
|
|
||||||
///
|
|
||||||
/// Panics if there's an integer overflow in i64.
|
|
||||||
pub fn from_diff(
|
|
||||||
original_text: &'a str,
|
|
||||||
diff: Vec<NumberOrText>,
|
|
||||||
tokenizer: &Tokenizer<T>,
|
|
||||||
) -> Result<EditedText<'a, T>, DiffError> {
|
|
||||||
let mut operations: Vec<Operation<T>> = Vec::with_capacity(diff.len());
|
|
||||||
let mut order = 0;
|
|
||||||
let chars: Vec<char> = original_text.chars().collect();
|
|
||||||
let text_length = chars.len();
|
|
||||||
|
|
||||||
for item in diff {
|
|
||||||
match item {
|
|
||||||
NumberOrText::Number(length) => {
|
|
||||||
if length >= 0 {
|
|
||||||
let length = usize::try_from(length).expect("length must fit in usize");
|
|
||||||
|
|
||||||
// Validate that the range doesn't exceed the original text
|
|
||||||
if order + length > text_length {
|
|
||||||
return Err(DiffError::LengthExceedsOriginal {
|
|
||||||
position: order,
|
|
||||||
requested: length,
|
|
||||||
available: text_length.saturating_sub(order),
|
|
||||||
});
|
|
||||||
}
|
|
||||||
|
|
||||||
let original_characters: String =
|
|
||||||
chars[order..order + length].iter().collect();
|
|
||||||
|
|
||||||
let original_tokens = tokenizer(&original_characters);
|
|
||||||
for token in original_tokens {
|
|
||||||
operations
|
|
||||||
.push(Operation::create_equal(order, token.get_original_length()));
|
|
||||||
order += token.get_original_length();
|
|
||||||
}
|
|
||||||
} else {
|
|
||||||
let length =
|
|
||||||
usize::try_from(-length).expect("negative length must fit in usize");
|
|
||||||
|
|
||||||
// Validate that the delete range doesn't exceed the original text
|
|
||||||
if order + length > text_length {
|
|
||||||
return Err(DiffError::LengthExceedsOriginal {
|
|
||||||
position: order,
|
|
||||||
requested: length,
|
|
||||||
available: text_length.saturating_sub(order),
|
|
||||||
});
|
|
||||||
}
|
|
||||||
|
|
||||||
operations.push(Operation::create_delete(order, length));
|
|
||||||
order += length;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
NumberOrText::Text(text) => {
|
|
||||||
let tokens = tokenizer(&text);
|
|
||||||
operations.push(Operation::create_insert(order, tokens));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
let operation_count = operations.len();
|
|
||||||
Ok(EditedText::new(
|
|
||||||
original_text,
|
|
||||||
operations,
|
|
||||||
vec![Side::Left; operation_count],
|
|
||||||
vec![],
|
|
||||||
))
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -552,24 +237,24 @@ mod tests {
|
||||||
let left = "hello world! How are you? Adam";
|
let left = "hello world! How are you? Adam";
|
||||||
let right = "Hello, my friend! How are you doing? Albert";
|
let right = "Hello, my friend! How are you doing? Albert";
|
||||||
|
|
||||||
let operations = EditedText::from_strings(left, &right.into());
|
let operations = EditedText::from_strings(left, right.into());
|
||||||
|
|
||||||
insta::assert_debug_snapshot!(operations);
|
insta::assert_debug_snapshot!(operations);
|
||||||
|
|
||||||
let new_right = operations.apply();
|
let new_right = operations.apply();
|
||||||
assert_eq!(new_right.text(), right);
|
assert_eq!(new_right.to_string(), right);
|
||||||
}
|
}
|
||||||
|
|
||||||
#[test]
|
#[test]
|
||||||
fn test_calculate_operations_with_no_diff() {
|
fn test_calculate_operations_with_no_diff() {
|
||||||
let text = "hello world!";
|
let text = "hello world!";
|
||||||
|
|
||||||
let operations = EditedText::from_strings(text, &text.into());
|
let operations = EditedText::from_strings(text, text.into());
|
||||||
|
|
||||||
assert_debug_snapshot!(operations);
|
assert_debug_snapshot!(operations);
|
||||||
|
|
||||||
let new_right = operations.apply();
|
let new_right = operations.apply();
|
||||||
assert_eq!(new_right.text(), text);
|
assert_eq!(new_right.to_string(), text);
|
||||||
}
|
}
|
||||||
|
|
||||||
#[test]
|
#[test]
|
||||||
|
|
@ -579,98 +264,10 @@ mod tests {
|
||||||
let right = "Hello world! How are you?";
|
let right = "Hello world! How are you?";
|
||||||
let expected = "Hello world! How are you? I'm Andras.";
|
let expected = "Hello world! How are you? I'm Andras.";
|
||||||
|
|
||||||
let operations_1 = EditedText::from_strings(original, &left.into());
|
let operations_1 = EditedText::from_strings(original, left.into());
|
||||||
let operations_2 = EditedText::from_strings(original, &right.into());
|
let operations_2 = EditedText::from_strings(original, right.into());
|
||||||
|
|
||||||
let operations = operations_1.merge(operations_2);
|
let operations = operations_1.merge(operations_2);
|
||||||
assert_eq!(operations.apply().text(), expected);
|
assert_eq!(operations.apply(), expected);
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_from_diff_length_exceeds_original() {
|
|
||||||
let result = EditedText::from_diff(
|
|
||||||
"hello",
|
|
||||||
vec![
|
|
||||||
10.into(), // too large equal span - should error
|
|
||||||
" world".into(),
|
|
||||||
],
|
|
||||||
&*BuiltinTokenizer::Word,
|
|
||||||
);
|
|
||||||
|
|
||||||
assert!(result.is_err());
|
|
||||||
match result {
|
|
||||||
Err(DiffError::LengthExceedsOriginal {
|
|
||||||
position,
|
|
||||||
requested,
|
|
||||||
available,
|
|
||||||
}) => {
|
|
||||||
assert_eq!(position, 0);
|
|
||||||
assert_eq!(requested, 10);
|
|
||||||
assert_eq!(available, 5);
|
|
||||||
}
|
|
||||||
_ => panic!("Expected LengthExceedsOriginal error"),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_from_diff_valid() {
|
|
||||||
let edited_text = EditedText::from_diff(
|
|
||||||
"hello",
|
|
||||||
vec![
|
|
||||||
5.into(), // exact length
|
|
||||||
" world".into(),
|
|
||||||
],
|
|
||||||
&*BuiltinTokenizer::Word,
|
|
||||||
)
|
|
||||||
.unwrap();
|
|
||||||
|
|
||||||
let content = edited_text.apply().text();
|
|
||||||
|
|
||||||
assert_eq!(content, "hello world");
|
|
||||||
}
|
|
||||||
|
|
||||||
#[cfg(feature = "serde")]
|
|
||||||
#[test]
|
|
||||||
fn test_changes_deserialisation() {
|
|
||||||
let original = "Merging text is hard!";
|
|
||||||
let changes = "Merging text is easy with reconcile!";
|
|
||||||
let result = EditedText::from_strings(original, &changes.into());
|
|
||||||
let serialized = serde_yaml::to_string(&result.to_diff().unwrap()).unwrap();
|
|
||||||
|
|
||||||
let expected = concat!("- 15\n", "- -6\n", "- ' easy with reconcile!'\n",);
|
|
||||||
assert_eq!(serialized, expected);
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_apply_with_history_utf8() {
|
|
||||||
let parent = "こんにちは世界"; // "Hello World" in Japanese (7 chars, 21 bytes)
|
|
||||||
let left = "こんにちは宇宙"; // Changed 世界 to 宇宙
|
|
||||||
let right = parent;
|
|
||||||
|
|
||||||
let result = crate::reconcile(
|
|
||||||
parent,
|
|
||||||
&left.into(),
|
|
||||||
&right.into(),
|
|
||||||
&*BuiltinTokenizer::Word,
|
|
||||||
);
|
|
||||||
|
|
||||||
let history = result.apply_with_history();
|
|
||||||
assert!(!history.is_empty());
|
|
||||||
assert_eq!(result.apply().text(), "こんにちは宇宙");
|
|
||||||
}
|
|
||||||
|
|
||||||
#[cfg(feature = "serde")]
|
|
||||||
#[test]
|
|
||||||
fn test_changes_serialization() {
|
|
||||||
let original = "The quick brown fox jumps over the lazy dog.";
|
|
||||||
let updated = "The quick red fox jumped over the very lazy dog!";
|
|
||||||
|
|
||||||
let edited_text = EditedText::from_strings(original, &updated.into());
|
|
||||||
|
|
||||||
let changes = edited_text.to_diff().unwrap();
|
|
||||||
let deserialized_edited_text =
|
|
||||||
EditedText::from_diff(original, changes, &*BuiltinTokenizer::Word).unwrap();
|
|
||||||
|
|
||||||
assert_eq!(deserialized_edited_text.apply().text(), updated);
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
|
||||||
|
|
@ -11,19 +11,18 @@ use crate::{
|
||||||
},
|
},
|
||||||
};
|
};
|
||||||
|
|
||||||
/// Represents a change that can be applied on a `StringBuilder`
|
/// Represents a change that can be applied on a `StringBuilder`.
|
||||||
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
|
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
|
||||||
#[derive(Clone, PartialEq)]
|
#[derive(Clone, PartialEq)]
|
||||||
pub enum Operation<T>
|
pub enum Operation<T>
|
||||||
where
|
where
|
||||||
T: PartialEq + Clone + Debug,
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
{
|
{
|
||||||
Equal {
|
Equal {
|
||||||
order: usize,
|
order: usize,
|
||||||
length: usize,
|
length: usize,
|
||||||
|
|
||||||
#[cfg(debug_assertions)]
|
#[cfg(debug_assertions)]
|
||||||
#[cfg_attr(feature = "serde", serde(skip_serializing))]
|
|
||||||
text: Option<String>,
|
text: Option<String>,
|
||||||
},
|
},
|
||||||
|
|
||||||
|
|
@ -37,17 +36,17 @@ where
|
||||||
deleted_character_count: usize,
|
deleted_character_count: usize,
|
||||||
|
|
||||||
#[cfg(debug_assertions)]
|
#[cfg(debug_assertions)]
|
||||||
#[cfg_attr(feature = "serde", serde(skip_serializing))]
|
|
||||||
deleted_text: Option<String>,
|
deleted_text: Option<String>,
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
impl<T> Operation<T>
|
impl<T> Operation<T>
|
||||||
where
|
where
|
||||||
T: PartialEq + Clone + Debug,
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
{
|
{
|
||||||
/// Creates an equal (retain) operation starting at the given character
|
/// Creates an equal operation with the given index.
|
||||||
/// offset in the original text
|
/// This operation is used to indicate that the text at the given index
|
||||||
|
/// is unchanged.
|
||||||
pub fn create_equal(order: usize, length: usize) -> Self {
|
pub fn create_equal(order: usize, length: usize) -> Self {
|
||||||
Operation::Equal {
|
Operation::Equal {
|
||||||
order,
|
order,
|
||||||
|
|
@ -68,14 +67,13 @@ where
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Creates an insert operation at the given character offset with the
|
/// Creates an insert operation with the given index and text.
|
||||||
/// given tokens
|
|
||||||
pub fn create_insert(order: usize, text: Vec<Token<T>>) -> Self {
|
pub fn create_insert(order: usize, text: Vec<Token<T>>) -> Self {
|
||||||
Operation::Insert { order, text }
|
Operation::Insert { order, text }
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Creates a delete operation at the given character offset for the
|
/// Creates a delete operation with the given index and number of
|
||||||
/// specified number of characters
|
/// to-be-deleted characters.
|
||||||
pub fn create_delete(order: usize, deleted_character_count: usize) -> Self {
|
pub fn create_delete(order: usize, deleted_character_count: usize) -> Self {
|
||||||
Operation::Delete {
|
Operation::Delete {
|
||||||
order,
|
order,
|
||||||
|
|
@ -104,55 +102,28 @@ where
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
fn type_priority(&self) -> u8 {
|
pub fn get_sort_key(&self, insertion_index: usize) -> (usize, usize, usize, String) {
|
||||||
match self {
|
(
|
||||||
Operation::Delete { .. } => 1,
|
self.order(),
|
||||||
Operation::Insert { .. } => 2,
|
match self {
|
||||||
Operation::Equal { .. } => 3,
|
Operation::Delete { .. } => 1,
|
||||||
}
|
Operation::Insert { .. } => 2,
|
||||||
}
|
Operation::Equal { .. } => 3,
|
||||||
|
},
|
||||||
/// Compare two operations for processing order during merging. Uses
|
insertion_index,
|
||||||
/// (order, type, `insertion_index`) with a deterministic content
|
// Make sure that the ordering is deterministic regardless of which text
|
||||||
/// tiebreaker that avoids allocating.
|
// is left or right.
|
||||||
pub fn cmp_priority(
|
match self {
|
||||||
&self,
|
Operation::Equal { length, .. } => length.to_string(),
|
||||||
self_index: usize,
|
Operation::Insert { text, .. } => {
|
||||||
other: &Self,
|
text.iter().map(Token::original).collect::<String>()
|
||||||
other_index: usize,
|
}
|
||||||
) -> std::cmp::Ordering {
|
|
||||||
self.order()
|
|
||||||
.cmp(&other.order())
|
|
||||||
.then_with(|| self.type_priority().cmp(&other.type_priority()))
|
|
||||||
.then_with(|| self_index.cmp(&other_index))
|
|
||||||
.then_with(|| self.deterministic_content_cmp(other))
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Deterministic tiebreaker based on operation content, so that merge
|
|
||||||
/// results are identical regardless of which side is left vs right
|
|
||||||
fn deterministic_content_cmp(&self, other: &Self) -> std::cmp::Ordering {
|
|
||||||
match (self, other) {
|
|
||||||
(Operation::Insert { text: t1, .. }, Operation::Insert { text: t2, .. }) => {
|
|
||||||
let s1 = t1.iter().flat_map(|t| t.original().chars());
|
|
||||||
let s2 = t2.iter().flat_map(|t| t.original().chars());
|
|
||||||
s1.cmp(s2)
|
|
||||||
}
|
|
||||||
(Operation::Equal { length: l1, .. }, Operation::Equal { length: l2, .. }) => {
|
|
||||||
l1.cmp(l2)
|
|
||||||
}
|
|
||||||
(
|
|
||||||
Operation::Delete {
|
Operation::Delete {
|
||||||
deleted_character_count: c1,
|
deleted_character_count,
|
||||||
..
|
..
|
||||||
},
|
} => deleted_character_count.to_string(),
|
||||||
Operation::Delete {
|
},
|
||||||
deleted_character_count: c2,
|
)
|
||||||
..
|
|
||||||
},
|
|
||||||
) => c1.cmp(c2),
|
|
||||||
// Different types are already ordered by type_priority
|
|
||||||
_ => std::cmp::Ordering::Equal,
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Applies the operation to the given `StringBuilder`, returning the
|
/// Applies the operation to the given `StringBuilder`, returning the
|
||||||
|
|
@ -206,8 +177,8 @@ where
|
||||||
builder
|
builder
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Returns the number of affected characters. May be 0 after
|
/// Returns the number of affected characters. It is always greater than 0
|
||||||
/// `merge_operations`.
|
/// because empty operations cannot be created.
|
||||||
pub fn len(&self) -> usize {
|
pub fn len(&self) -> usize {
|
||||||
match self {
|
match self {
|
||||||
Operation::Equal { length, .. } => *length,
|
Operation::Equal { length, .. } => *length,
|
||||||
|
|
@ -219,10 +190,12 @@ where
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Adjusts this operation based on `previous_operation` from the other side
|
/// Merges the operation with the given context, producing a new operation
|
||||||
/// to avoid duplicating or conflicting changes
|
/// and updating the context. This implements a comples FSM that handles
|
||||||
|
/// the merging of operations in a way that is consistent with the text.
|
||||||
|
/// The contexts are updated in-place.
|
||||||
#[allow(clippy::too_many_lines)]
|
#[allow(clippy::too_many_lines)]
|
||||||
pub fn merge_operations(self, previous_operation: Option<&Self>) -> Operation<T> {
|
pub fn merge_operations(self, previous_operation: &mut Option<Self>) -> Operation<T> {
|
||||||
let operation = self;
|
let operation = self;
|
||||||
|
|
||||||
match (operation, previous_operation) {
|
match (operation, previous_operation) {
|
||||||
|
|
@ -261,7 +234,7 @@ where
|
||||||
*last_delete_order + *last_delete_deleted_character_count;
|
*last_delete_order + *last_delete_deleted_character_count;
|
||||||
|
|
||||||
let new_length = deleted_character_count
|
let new_length = deleted_character_count
|
||||||
.min(operation_end_index.saturating_sub(last_delete_end_index));
|
.min(0.max(operation_end_index as i64 - last_delete_end_index as i64) as usize);
|
||||||
|
|
||||||
let overlap = deleted_character_count - new_length;
|
let overlap = deleted_character_count - new_length;
|
||||||
|
|
||||||
|
|
@ -301,57 +274,43 @@ where
|
||||||
let last_delete_end_index =
|
let last_delete_end_index =
|
||||||
*last_delete_order + *last_delete_deleted_character_count;
|
*last_delete_order + *last_delete_deleted_character_count;
|
||||||
|
|
||||||
let overlap = length.min(last_delete_end_index.saturating_sub(order));
|
let overlap =
|
||||||
|
0.max((length as i64).min(last_delete_end_index as i64 - order as i64));
|
||||||
|
|
||||||
#[cfg(debug_assertions)]
|
#[cfg(debug_assertions)]
|
||||||
let updated_equal = text.as_ref().map_or_else(
|
let updated_equal = text.as_ref().map_or_else(
|
||||||
|| Operation::create_equal(order + overlap, length - overlap),
|
|| {
|
||||||
|
Operation::create_equal(
|
||||||
|
order + overlap as usize,
|
||||||
|
(length as i64 - overlap) as usize,
|
||||||
|
)
|
||||||
|
},
|
||||||
|text| {
|
|text| {
|
||||||
Operation::create_equal_with_text(
|
Operation::create_equal_with_text(
|
||||||
order + overlap,
|
order + overlap as usize,
|
||||||
text.chars().skip(overlap).collect::<String>(),
|
text.chars().skip(overlap as usize).collect::<String>(),
|
||||||
)
|
)
|
||||||
},
|
},
|
||||||
);
|
);
|
||||||
|
|
||||||
#[cfg(not(debug_assertions))]
|
#[cfg(not(debug_assertions))]
|
||||||
let updated_equal = Operation::create_equal(order + overlap, length - overlap);
|
let updated_equal = Operation::create_equal(
|
||||||
|
order + overlap as usize,
|
||||||
|
(length as i64 - overlap) as usize,
|
||||||
|
);
|
||||||
|
|
||||||
updated_equal
|
updated_equal
|
||||||
}
|
}
|
||||||
|
|
||||||
(
|
(
|
||||||
ref operation @ Operation::Equal {
|
ref operation @ Operation::Equal { ref order, .. },
|
||||||
ref order,
|
|
||||||
#[cfg(debug_assertions)]
|
|
||||||
ref text,
|
|
||||||
..
|
|
||||||
},
|
|
||||||
Some(Operation::Equal {
|
Some(Operation::Equal {
|
||||||
order: last_equal_order,
|
order: last_equal_order,
|
||||||
length: last_equal_length,
|
length: last_equal_length,
|
||||||
#[cfg(debug_assertions)]
|
|
||||||
text: last_equal_text,
|
|
||||||
..
|
..
|
||||||
}),
|
}),
|
||||||
) => {
|
) => {
|
||||||
if operation.len() == *last_equal_length && *order == *last_equal_order {
|
if operation.len() == *last_equal_length && *order == *last_equal_order {
|
||||||
// Both sides retained the same span from the original text,
|
|
||||||
// so we deduplicate by zeroing one out. This is safe because
|
|
||||||
// both EditedTexts are derived from the same original, and
|
|
||||||
// matching (order, length) means they cover the same substring
|
|
||||||
#[cfg(debug_assertions)]
|
|
||||||
debug_assert_eq!(
|
|
||||||
text,
|
|
||||||
last_equal_text,
|
|
||||||
"Equal operations with same order and length should have the same text, \
|
|
||||||
but got {operation:?} vs {:?}",
|
|
||||||
Operation::<T>::Equal {
|
|
||||||
order: *last_equal_order,
|
|
||||||
length: *last_equal_length,
|
|
||||||
text: last_equal_text.clone(),
|
|
||||||
},
|
|
||||||
);
|
|
||||||
Operation::create_equal(*order, 0)
|
Operation::create_equal(*order, 0)
|
||||||
} else {
|
} else {
|
||||||
operation.clone()
|
operation.clone()
|
||||||
|
|
@ -365,7 +324,7 @@ where
|
||||||
|
|
||||||
impl<T> Display for Operation<T>
|
impl<T> Display for Operation<T>
|
||||||
where
|
where
|
||||||
T: PartialEq + Clone + Debug,
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
{
|
{
|
||||||
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
|
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
|
||||||
match self {
|
match self {
|
||||||
|
|
@ -375,25 +334,22 @@ where
|
||||||
|
|
||||||
#[cfg(debug_assertions)]
|
#[cfg(debug_assertions)]
|
||||||
text,
|
text,
|
||||||
..
|
|
||||||
} => {
|
} => {
|
||||||
#[cfg(debug_assertions)]
|
#[cfg(debug_assertions)]
|
||||||
{
|
write!(
|
||||||
write!(
|
f,
|
||||||
f,
|
"<equal {} from {order}>",
|
||||||
"<equal {} from {order}>",
|
text.as_ref()
|
||||||
text.as_ref()
|
.map(|text| format!("'{}'", text.replace('\n', "\\n")))
|
||||||
.map(|text| format!("'{}'", text.replace('\n', "\\n")))
|
.unwrap_or(format!("{length} characters")),
|
||||||
.unwrap_or(format!("{length} characters")),
|
)?;
|
||||||
)
|
|
||||||
}
|
|
||||||
|
|
||||||
#[cfg(not(debug_assertions))]
|
#[cfg(not(debug_assertions))]
|
||||||
{
|
write!(f, "<equal {length} from {order}>")?;
|
||||||
write!(f, "<equal {length} from {order}>")
|
|
||||||
}
|
Ok(())
|
||||||
}
|
}
|
||||||
Operation::Insert { order, text, .. } => {
|
Operation::Insert { order, text } => {
|
||||||
write!(
|
write!(
|
||||||
f,
|
f,
|
||||||
"<insert '{}' at {order}>",
|
"<insert '{}' at {order}>",
|
||||||
|
|
@ -409,27 +365,24 @@ where
|
||||||
|
|
||||||
#[cfg(debug_assertions)]
|
#[cfg(debug_assertions)]
|
||||||
deleted_text,
|
deleted_text,
|
||||||
..
|
|
||||||
} => {
|
} => {
|
||||||
#[cfg(debug_assertions)]
|
#[cfg(debug_assertions)]
|
||||||
{
|
write!(
|
||||||
write!(
|
f,
|
||||||
f,
|
"<delete {} from {order}>",
|
||||||
"<delete {} from {order}>",
|
deleted_text
|
||||||
deleted_text
|
.as_ref()
|
||||||
.as_ref()
|
.map(|text| format!("'{}'", text.replace('\n', "\\n")))
|
||||||
.map(|text| format!("'{}'", text.replace('\n', "\\n")))
|
.unwrap_or(format!("{deleted_character_count} characters")),
|
||||||
.unwrap_or(format!("{deleted_character_count} characters")),
|
)?;
|
||||||
)
|
|
||||||
}
|
|
||||||
|
|
||||||
#[cfg(not(debug_assertions))]
|
#[cfg(not(debug_assertions))]
|
||||||
{
|
write!(
|
||||||
write!(
|
f,
|
||||||
f,
|
"<delete {deleted_character_count} characters from {order}>",
|
||||||
"<delete {deleted_character_count} characters from {order}>",
|
)?;
|
||||||
)
|
|
||||||
}
|
Ok(())
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
@ -437,11 +390,9 @@ where
|
||||||
|
|
||||||
impl<T> Debug for Operation<T>
|
impl<T> Debug for Operation<T>
|
||||||
where
|
where
|
||||||
T: PartialEq + Clone + Debug,
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
{
|
{
|
||||||
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
|
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result { write!(f, "{self}") }
|
||||||
write!(f, "{self}")
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
#[cfg(test)]
|
#[cfg(test)]
|
||||||
|
|
@ -459,7 +410,7 @@ mod tests {
|
||||||
let mut builder = delete_operation.apply(builder);
|
let mut builder = delete_operation.apply(builder);
|
||||||
builder = retain_operation.apply(builder);
|
builder = retain_operation.apply(builder);
|
||||||
|
|
||||||
assert_eq!(builder.take(), "world");
|
assert_eq!(builder.build(), "world");
|
||||||
}
|
}
|
||||||
|
|
||||||
#[test]
|
#[test]
|
||||||
|
|
@ -472,6 +423,6 @@ mod tests {
|
||||||
let mut builder = retain_operation.apply(builder);
|
let mut builder = retain_operation.apply(builder);
|
||||||
builder = insert_operation.apply(builder);
|
builder = insert_operation.apply(builder);
|
||||||
|
|
||||||
assert_eq!(builder.take(), "hello my friend");
|
assert_eq!(builder.build(), "hello my friend");
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
|
||||||
|
|
@ -1,6 +1,7 @@
|
||||||
---
|
---
|
||||||
source: src/operation_transformation/edited_text.rs
|
source: src/operation_transformation/edited_text.rs
|
||||||
expression: operations
|
expression: operations
|
||||||
|
snapshot_kind: text
|
||||||
---
|
---
|
||||||
EditedText {
|
EditedText {
|
||||||
text: "hello world! How are you? Adam",
|
text: "hello world! How are you? Adam",
|
||||||
|
|
@ -14,15 +15,5 @@ EditedText {
|
||||||
<delete ' you? Adam' from 20>,
|
<delete ' you? Adam' from 20>,
|
||||||
<insert ' you doing? Albert' at 31>,
|
<insert ' you doing? Albert' at 31>,
|
||||||
],
|
],
|
||||||
operation_sides: [
|
|
||||||
Left,
|
|
||||||
Left,
|
|
||||||
Left,
|
|
||||||
Left,
|
|
||||||
Left,
|
|
||||||
Left,
|
|
||||||
Left,
|
|
||||||
Left,
|
|
||||||
],
|
|
||||||
cursors: [],
|
cursors: [],
|
||||||
}
|
}
|
||||||
|
|
@ -1,6 +1,7 @@
|
||||||
---
|
---
|
||||||
source: src/operation_transformation/edited_text.rs
|
source: src/operation_transformation/edited_text.rs
|
||||||
expression: operations
|
expression: operations
|
||||||
|
snapshot_kind: text
|
||||||
---
|
---
|
||||||
EditedText {
|
EditedText {
|
||||||
text: "hello world!",
|
text: "hello world!",
|
||||||
|
|
@ -9,10 +10,5 @@ EditedText {
|
||||||
<equal ' ' from 5>,
|
<equal ' ' from 5>,
|
||||||
<equal 'world!' from 6>,
|
<equal 'world!' from 6>,
|
||||||
],
|
],
|
||||||
operation_sides: [
|
|
||||||
Left,
|
|
||||||
Left,
|
|
||||||
Left,
|
|
||||||
],
|
|
||||||
cursors: [],
|
cursors: [],
|
||||||
}
|
}
|
||||||
|
|
@ -0,0 +1,61 @@
|
||||||
|
---
|
||||||
|
source: reconcile/src/operations/edited_text.rs
|
||||||
|
expression: operations
|
||||||
|
snapshot_kind: text
|
||||||
|
---
|
||||||
|
EditedText {
|
||||||
|
text: "hello world! How are you? Adam",
|
||||||
|
operations: [
|
||||||
|
OrderedOperation {
|
||||||
|
order: 0,
|
||||||
|
operation: Insert {
|
||||||
|
index: 0,
|
||||||
|
text: "Hello, my friend! ",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
OrderedOperation {
|
||||||
|
order: 0,
|
||||||
|
operation: Delete {
|
||||||
|
index: 18,
|
||||||
|
deleted_character_count: 13,
|
||||||
|
deleted_text: Some(
|
||||||
|
"hello world! ",
|
||||||
|
),
|
||||||
|
},
|
||||||
|
},
|
||||||
|
OrderedOperation {
|
||||||
|
order: 21,
|
||||||
|
operation: Delete {
|
||||||
|
index: 26,
|
||||||
|
deleted_character_count: 5,
|
||||||
|
deleted_text: Some(
|
||||||
|
"you? ",
|
||||||
|
),
|
||||||
|
},
|
||||||
|
},
|
||||||
|
OrderedOperation {
|
||||||
|
order: 26,
|
||||||
|
operation: Delete {
|
||||||
|
index: 26,
|
||||||
|
deleted_character_count: 5,
|
||||||
|
deleted_text: Some(
|
||||||
|
" Adam",
|
||||||
|
),
|
||||||
|
},
|
||||||
|
},
|
||||||
|
OrderedOperation {
|
||||||
|
order: 31,
|
||||||
|
operation: Insert {
|
||||||
|
index: 26,
|
||||||
|
text: "you ",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
OrderedOperation {
|
||||||
|
order: 31,
|
||||||
|
operation: Insert {
|
||||||
|
index: 30,
|
||||||
|
text: "doing? Albert",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
],
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,60 @@
|
||||||
|
---
|
||||||
|
source: reconcile/src/operations/operation_sequence.rs
|
||||||
|
expression: operations
|
||||||
|
snapshot_kind: text
|
||||||
|
---
|
||||||
|
EditedText {
|
||||||
|
operations: [
|
||||||
|
OrderedOperation {
|
||||||
|
order: 0,
|
||||||
|
operation: Insert {
|
||||||
|
index: 0,
|
||||||
|
text: "Hello, my friend! ",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
OrderedOperation {
|
||||||
|
order: 0,
|
||||||
|
operation: Delete {
|
||||||
|
index: 18,
|
||||||
|
deleted_character_count: 13,
|
||||||
|
deleted_text: Some(
|
||||||
|
"hello world! ",
|
||||||
|
),
|
||||||
|
},
|
||||||
|
},
|
||||||
|
OrderedOperation {
|
||||||
|
order: 21,
|
||||||
|
operation: Delete {
|
||||||
|
index: 26,
|
||||||
|
deleted_character_count: 5,
|
||||||
|
deleted_text: Some(
|
||||||
|
"you? ",
|
||||||
|
),
|
||||||
|
},
|
||||||
|
},
|
||||||
|
OrderedOperation {
|
||||||
|
order: 26,
|
||||||
|
operation: Delete {
|
||||||
|
index: 26,
|
||||||
|
deleted_character_count: 5,
|
||||||
|
deleted_text: Some(
|
||||||
|
" Adam",
|
||||||
|
),
|
||||||
|
},
|
||||||
|
},
|
||||||
|
OrderedOperation {
|
||||||
|
order: 31,
|
||||||
|
operation: Insert {
|
||||||
|
index: 26,
|
||||||
|
text: "you ",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
OrderedOperation {
|
||||||
|
order: 31,
|
||||||
|
operation: Insert {
|
||||||
|
index: 30,
|
||||||
|
text: "doing? Albert",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
],
|
||||||
|
}
|
||||||
|
|
@ -1,13 +1,11 @@
|
||||||
use std::fmt::Debug;
|
use crate::{diffs::raw_operation::RawOperation, operation_transformation::Operation};
|
||||||
|
|
||||||
use crate::{operation_transformation::Operation, raw_operation::RawOperation};
|
|
||||||
|
|
||||||
/// Turn raw operations into ordered operations while keeping track of the
|
/// Turn raw operations into ordered operations while keeping track of the
|
||||||
/// original token's indexes
|
/// original token's indexes.
|
||||||
pub fn cook_operations<I, T>(raw_operations: I) -> impl Iterator<Item = Operation<T>>
|
pub fn cook_operations<I, T>(raw_operations: I) -> impl Iterator<Item = Operation<T>>
|
||||||
where
|
where
|
||||||
I: IntoIterator<Item = RawOperation<T>>,
|
I: IntoIterator<Item = RawOperation<T>>,
|
||||||
T: PartialEq + Clone + Debug,
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
{
|
{
|
||||||
let mut original_text_index = 0; // this is the start index of the operation on the original text
|
let mut original_text_index = 0; // this is the start index of the operation on the original text
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -1,7 +1,6 @@
|
||||||
use core::iter;
|
use core::iter;
|
||||||
use std::fmt::Debug;
|
|
||||||
|
|
||||||
use crate::raw_operation::RawOperation;
|
use crate::diffs::raw_operation::RawOperation;
|
||||||
|
|
||||||
/// Elongates the operations by merging adjacent insertions and deletions that
|
/// Elongates the operations by merging adjacent insertions and deletions that
|
||||||
/// can be joined. This makes the subsequent merging of operations more
|
/// can be joined. This makes the subsequent merging of operations more
|
||||||
|
|
@ -9,7 +8,7 @@ use crate::raw_operation::RawOperation;
|
||||||
pub fn elongate_operations<I, T>(raw_operations: I) -> Vec<RawOperation<T>>
|
pub fn elongate_operations<I, T>(raw_operations: I) -> Vec<RawOperation<T>>
|
||||||
where
|
where
|
||||||
I: IntoIterator<Item = RawOperation<T>>,
|
I: IntoIterator<Item = RawOperation<T>>,
|
||||||
T: PartialEq + Clone + Debug,
|
T: PartialEq + Clone + std::fmt::Debug,
|
||||||
{
|
{
|
||||||
// This might look bad, but this makes sense. The inserts and deltes can be
|
// This might look bad, but this makes sense. The inserts and deltes can be
|
||||||
// interleaved, such as: IDIDID and we need to turn this into IIIDDD.
|
// interleaved, such as: IDIDID and we need to turn this into IIIDDD.
|
||||||
|
|
@ -25,7 +24,7 @@ where
|
||||||
.flat_map(|next| match next {
|
.flat_map(|next| match next {
|
||||||
RawOperation::Insert(..) => match maybe_previous_insert.take() {
|
RawOperation::Insert(..) => match maybe_previous_insert.take() {
|
||||||
Some(prev) if prev.is_right_joinable() && next.is_left_joinable() => {
|
Some(prev) if prev.is_right_joinable() && next.is_left_joinable() => {
|
||||||
maybe_previous_insert = Some(prev.join(next));
|
maybe_previous_insert = Some(prev.extend(next));
|
||||||
Box::new(iter::empty()) as Box<dyn Iterator<Item = RawOperation<T>>>
|
Box::new(iter::empty()) as Box<dyn Iterator<Item = RawOperation<T>>>
|
||||||
}
|
}
|
||||||
prev => {
|
prev => {
|
||||||
|
|
@ -35,7 +34,7 @@ where
|
||||||
},
|
},
|
||||||
RawOperation::Delete(..) => match maybe_previous_delete.take() {
|
RawOperation::Delete(..) => match maybe_previous_delete.take() {
|
||||||
Some(prev) if prev.is_right_joinable() && next.is_left_joinable() => {
|
Some(prev) if prev.is_right_joinable() && next.is_left_joinable() => {
|
||||||
maybe_previous_delete = Some(prev.join(next));
|
maybe_previous_delete = Some(prev.extend(next));
|
||||||
Box::new(iter::empty()) as Box<dyn Iterator<Item = RawOperation<T>>>
|
Box::new(iter::empty()) as Box<dyn Iterator<Item = RawOperation<T>>>
|
||||||
}
|
}
|
||||||
prev => {
|
prev => {
|
||||||
|
|
@ -79,7 +78,7 @@ mod tests {
|
||||||
}
|
}
|
||||||
|
|
||||||
fn ins_custom(text: &str, lj: bool, rj: bool) -> RawOperation<String> {
|
fn ins_custom(text: &str, lj: bool, rj: bool) -> RawOperation<String> {
|
||||||
RawOperation::Insert(vec![Token::new(text.to_owned(), text.to_owned(), lj, rj)])
|
RawOperation::Insert(vec![Token::new(text.to_string(), text.to_string(), lj, rj)])
|
||||||
}
|
}
|
||||||
|
|
||||||
#[test]
|
#[test]
|
||||||
|
|
@ -89,10 +88,7 @@ mod tests {
|
||||||
assert_eq!(result.len(), 1);
|
assert_eq!(result.len(), 1);
|
||||||
match &result[0] {
|
match &result[0] {
|
||||||
RawOperation::Insert(tokens) => {
|
RawOperation::Insert(tokens) => {
|
||||||
let originals: String = tokens
|
let originals: String = tokens.iter().map(|t| t.original()).collect();
|
||||||
.iter()
|
|
||||||
.map(crate::tokenizer::token::Token::original)
|
|
||||||
.collect();
|
|
||||||
assert_eq!(originals, "abc");
|
assert_eq!(originals, "abc");
|
||||||
}
|
}
|
||||||
_ => panic!("Expected single Insert operation"),
|
_ => panic!("Expected single Insert operation"),
|
||||||
|
|
|
||||||
|
|
@ -1,53 +1,7 @@
|
||||||
mod character_tokenizer;
|
|
||||||
mod line_tokenizer;
|
|
||||||
mod markdown_tokenizer;
|
|
||||||
mod word_tokenizer;
|
|
||||||
|
|
||||||
use std::ops::Deref;
|
|
||||||
|
|
||||||
#[cfg(feature = "serde")]
|
|
||||||
use serde::{Deserialize, Serialize};
|
|
||||||
use token::Token;
|
use token::Token;
|
||||||
#[cfg(feature = "wasm")]
|
|
||||||
use wasm_bindgen::prelude::*;
|
|
||||||
|
|
||||||
pub mod token;
|
pub mod token;
|
||||||
|
pub mod word_tokenizer;
|
||||||
|
|
||||||
/// Type alias for tokenizer functions that split a string into tokens
|
/// A trait for tokenizers that take a string and return a list of tokens.
|
||||||
pub type Tokenizer<T> = dyn Fn(&str) -> Vec<Token<T>>;
|
pub type Tokenizer<T> = dyn Fn(&str) -> Vec<Token<T>>;
|
||||||
|
|
||||||
#[cfg_attr(feature = "wasm", wasm_bindgen)]
|
|
||||||
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
|
|
||||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
|
||||||
#[cfg(feature = "wasm")]
|
|
||||||
pub enum BuiltinTokenizer {
|
|
||||||
Character = "Character",
|
|
||||||
Line = "Line",
|
|
||||||
Markdown = "Markdown",
|
|
||||||
Word = "Word",
|
|
||||||
}
|
|
||||||
|
|
||||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
|
||||||
#[cfg(not(feature = "wasm"))]
|
|
||||||
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
|
|
||||||
pub enum BuiltinTokenizer {
|
|
||||||
Character,
|
|
||||||
Line,
|
|
||||||
Markdown,
|
|
||||||
Word,
|
|
||||||
}
|
|
||||||
|
|
||||||
impl Deref for BuiltinTokenizer {
|
|
||||||
type Target = Tokenizer<String>;
|
|
||||||
|
|
||||||
fn deref(&self) -> &Self::Target {
|
|
||||||
match self {
|
|
||||||
BuiltinTokenizer::Character => &character_tokenizer::character_tokenizer,
|
|
||||||
BuiltinTokenizer::Line => &line_tokenizer::line_tokenizer,
|
|
||||||
BuiltinTokenizer::Markdown => &markdown_tokenizer::markdown_tokenizer,
|
|
||||||
BuiltinTokenizer::Word => &word_tokenizer::word_tokenizer,
|
|
||||||
#[cfg(feature = "wasm")]
|
|
||||||
BuiltinTokenizer::__Invalid => panic!("Unexpected tokenizer type"),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
|
||||||
|
|
@ -1,26 +0,0 @@
|
||||||
use super::token::Token;
|
|
||||||
|
|
||||||
/// Splits text into UTF-8 characters
|
|
||||||
///
|
|
||||||
/// ```not_rust
|
|
||||||
/// "Hey!" -> ["H", "e", "y", "!"]
|
|
||||||
/// ```
|
|
||||||
pub fn character_tokenizer(text: &str) -> Vec<Token<String>> {
|
|
||||||
text.chars()
|
|
||||||
.map(|char| Token::new(char.to_string(), char.to_string(), true, true))
|
|
||||||
.collect()
|
|
||||||
}
|
|
||||||
|
|
||||||
#[cfg(test)]
|
|
||||||
mod tests {
|
|
||||||
use insta::assert_debug_snapshot;
|
|
||||||
|
|
||||||
use super::*;
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_with_snapshots() {
|
|
||||||
assert_debug_snapshot!(character_tokenizer(""));
|
|
||||||
|
|
||||||
assert_debug_snapshot!(character_tokenizer(" hello, \nwhere are you?"));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
@ -1,80 +0,0 @@
|
||||||
use super::token::Token;
|
|
||||||
|
|
||||||
/// Splits text into lines, preserving line endings as separate tokens
|
|
||||||
///
|
|
||||||
/// ## Example
|
|
||||||
///
|
|
||||||
/// ```not_rust
|
|
||||||
/// "Hello\nWorld!" -> ["Hello", "\n", "World!"]
|
|
||||||
/// "Line 1\r\nLine 2" -> ["Line 1", "\r\n", "Line 2"]
|
|
||||||
/// ```
|
|
||||||
pub fn line_tokenizer(text: &str) -> Vec<Token<String>> {
|
|
||||||
let mut result = Vec::new();
|
|
||||||
let mut line_start = 0;
|
|
||||||
|
|
||||||
let mut chars = text.char_indices().peekable();
|
|
||||||
while let Some((i, c)) = chars.next() {
|
|
||||||
if c == '\n' {
|
|
||||||
// Add line content if any
|
|
||||||
if i > line_start {
|
|
||||||
result.push(text[line_start..i].into());
|
|
||||||
}
|
|
||||||
// Add newline
|
|
||||||
result.push("\n".into());
|
|
||||||
line_start = i + 1;
|
|
||||||
} else if c == '\r' {
|
|
||||||
if i > line_start {
|
|
||||||
result.push(text[line_start..i].into());
|
|
||||||
}
|
|
||||||
if chars.peek() == Some(&(i + 1, '\n')) {
|
|
||||||
// Handle \r\n
|
|
||||||
chars.next(); // consume \n
|
|
||||||
result.push("\r\n".into());
|
|
||||||
line_start = i + 2;
|
|
||||||
} else {
|
|
||||||
// Handle bare \r
|
|
||||||
result.push("\r".into());
|
|
||||||
line_start = i + 1;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// Add final line if any
|
|
||||||
if line_start < text.len() {
|
|
||||||
result.push(text[line_start..].into());
|
|
||||||
}
|
|
||||||
|
|
||||||
result
|
|
||||||
}
|
|
||||||
|
|
||||||
#[cfg(test)]
|
|
||||||
mod tests {
|
|
||||||
use insta::assert_debug_snapshot;
|
|
||||||
|
|
||||||
use super::*;
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_with_snapshots() {
|
|
||||||
assert_debug_snapshot!(line_tokenizer(""));
|
|
||||||
|
|
||||||
assert_debug_snapshot!(line_tokenizer("Hello"));
|
|
||||||
|
|
||||||
assert_debug_snapshot!(line_tokenizer("Hello\nWorld"));
|
|
||||||
|
|
||||||
assert_debug_snapshot!(line_tokenizer("Hello\nWorld\n"));
|
|
||||||
|
|
||||||
assert_debug_snapshot!(line_tokenizer("Line 1\r\nLine 2"));
|
|
||||||
|
|
||||||
assert_debug_snapshot!(line_tokenizer("Multi\nLine\nText\nHere"));
|
|
||||||
|
|
||||||
assert_debug_snapshot!(line_tokenizer("\n"));
|
|
||||||
|
|
||||||
assert_debug_snapshot!(line_tokenizer("\n\n"));
|
|
||||||
|
|
||||||
assert_debug_snapshot!(line_tokenizer("Start\n\nEnd"));
|
|
||||||
|
|
||||||
assert_debug_snapshot!(line_tokenizer("Old\rMac\rStyle"));
|
|
||||||
|
|
||||||
assert_debug_snapshot!(line_tokenizer("Mixed\r\nand\rbare"));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
@ -1,290 +0,0 @@
|
||||||
use super::{token::Token, word_tokenizer::split_words};
|
|
||||||
|
|
||||||
/// Splits markdown text into tokens that respect markdown formatting structure
|
|
||||||
///
|
|
||||||
/// Builds on word-level tokenization with markdown-specific handling:
|
|
||||||
/// - Newlines are non-joinable tokens (preserves block structure)
|
|
||||||
/// - Block-level prefixes (headings, list markers, blockquotes) attach to the
|
|
||||||
/// first word of their line so they can't be split apart during merge
|
|
||||||
/// - Intra-line whitespace uses the same normalization as the word tokenizer
|
|
||||||
///
|
|
||||||
/// This prevents merges from breaking lists, headings, or other structural
|
|
||||||
/// markdown elements. Inline formatting like `**bold**` is already preserved
|
|
||||||
/// by word-level splitting since formatting markers contain no whitespace.
|
|
||||||
///
|
|
||||||
/// ## Example
|
|
||||||
///
|
|
||||||
/// ```not_rust
|
|
||||||
/// "# Hello\n- item" -> ["# Hello", "\n", "- item"]
|
|
||||||
/// ```
|
|
||||||
pub fn markdown_tokenizer(text: &str) -> Vec<Token<String>> {
|
|
||||||
let mut result = Vec::new();
|
|
||||||
let segments = split_preserving_newlines(text);
|
|
||||||
|
|
||||||
for segment in &segments {
|
|
||||||
if *segment == "\n" || *segment == "\r\n" {
|
|
||||||
let s = (*segment).to_owned();
|
|
||||||
result.push(Token::new(s.clone(), s, false, false));
|
|
||||||
continue;
|
|
||||||
}
|
|
||||||
|
|
||||||
let prefix_len = block_prefix_len(segment);
|
|
||||||
let mut line_tokens = split_words(&segment[prefix_len..]);
|
|
||||||
|
|
||||||
if prefix_len > 0 {
|
|
||||||
let prefix = &segment[..prefix_len];
|
|
||||||
if line_tokens.is_empty() {
|
|
||||||
let s = prefix.to_owned();
|
|
||||||
result.push(Token::new(s.clone(), s, false, false));
|
|
||||||
} else {
|
|
||||||
let first = &line_tokens[0];
|
|
||||||
let combined_original = format!("{prefix}{}", first.original());
|
|
||||||
let combined_normalized = format!("{prefix}{}", first.normalized());
|
|
||||||
line_tokens[0] = Token::new(
|
|
||||||
combined_normalized,
|
|
||||||
combined_original,
|
|
||||||
false,
|
|
||||||
first.is_right_joinable,
|
|
||||||
);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
result.extend(line_tokens);
|
|
||||||
}
|
|
||||||
|
|
||||||
// Normalize non-newline whitespace tokens by appending the next token's
|
|
||||||
// original text (same trick as the word tokenizer so each space is unique
|
|
||||||
// in the diff based on what follows it)
|
|
||||||
if !result.is_empty() {
|
|
||||||
for i in 0..result.len() - 1 {
|
|
||||||
if result[i]
|
|
||||||
.original()
|
|
||||||
.chars()
|
|
||||||
.all(|c| c.is_whitespace() && c != '\n' && c != '\r')
|
|
||||||
{
|
|
||||||
let normalized = result[i].normalized().to_owned() + result[i + 1].original();
|
|
||||||
result[i].set_normalized(normalized);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
result
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Splits text into alternating segments of line content and newline separators
|
|
||||||
fn split_preserving_newlines(text: &str) -> Vec<&str> {
|
|
||||||
let mut segments = Vec::new();
|
|
||||||
let mut line_start = 0;
|
|
||||||
let bytes = text.as_bytes();
|
|
||||||
let mut i = 0;
|
|
||||||
|
|
||||||
while i < bytes.len() {
|
|
||||||
if bytes[i] == b'\r' && i + 1 < bytes.len() && bytes[i + 1] == b'\n' {
|
|
||||||
if i > line_start {
|
|
||||||
segments.push(&text[line_start..i]);
|
|
||||||
}
|
|
||||||
segments.push(&text[i..i + 2]);
|
|
||||||
i += 2;
|
|
||||||
line_start = i;
|
|
||||||
} else if bytes[i] == b'\n' {
|
|
||||||
if i > line_start {
|
|
||||||
segments.push(&text[line_start..i]);
|
|
||||||
}
|
|
||||||
segments.push(&text[i..=i]);
|
|
||||||
i += 1;
|
|
||||||
line_start = i;
|
|
||||||
} else {
|
|
||||||
i += 1;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if line_start < text.len() {
|
|
||||||
segments.push(&text[line_start..]);
|
|
||||||
}
|
|
||||||
|
|
||||||
segments
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Returns the byte length of a markdown block-level prefix at the start of a
|
|
||||||
/// line, or 0 if none is found
|
|
||||||
///
|
|
||||||
/// All recognized prefix characters are ASCII, so byte offsets are always
|
|
||||||
/// valid UTF-8 boundaries.
|
|
||||||
///
|
|
||||||
/// Recognized prefixes:
|
|
||||||
/// - ATX headings: `# ` through `###### `
|
|
||||||
/// - Blockquotes: `> ` (single level)
|
|
||||||
/// - Unordered lists: `- `, `* `, `+ ` (with optional leading whitespace)
|
|
||||||
/// - Ordered lists: `1. `, `2) ` etc (with optional leading whitespace)
|
|
||||||
/// - Task lists: `- [ ] `, `- [x] `, `- [X] ` etc (checkbox included in prefix)
|
|
||||||
fn block_prefix_len(line: &str) -> usize {
|
|
||||||
let trimmed = line.trim_start_matches([' ', '\t']);
|
|
||||||
let indent_len = line.len() - trimmed.len();
|
|
||||||
|
|
||||||
// ATX heading: #{1,6} followed by a space
|
|
||||||
if trimmed.starts_with('#') {
|
|
||||||
let hash_count = trimmed.bytes().take_while(|&b| b == b'#').count();
|
|
||||||
if hash_count <= 6 && trimmed.as_bytes().get(hash_count) == Some(&b' ') {
|
|
||||||
return indent_len + hash_count + 1;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// Blockquote: > followed by optional space
|
|
||||||
if trimmed.starts_with("> ") {
|
|
||||||
return indent_len + 2;
|
|
||||||
}
|
|
||||||
if trimmed.starts_with('>') && (trimmed.len() == 1 || trimmed.as_bytes()[1] == b'>') {
|
|
||||||
return indent_len + 1;
|
|
||||||
}
|
|
||||||
|
|
||||||
// Unordered list: [-*+] followed by a space, optionally with task checkbox
|
|
||||||
if trimmed.len() >= 2 {
|
|
||||||
let first_byte = trimmed.as_bytes()[0];
|
|
||||||
if matches!(first_byte, b'-' | b'*' | b'+') && trimmed.as_bytes()[1] == b' ' {
|
|
||||||
return indent_len + 2 + task_checkbox_len(&line[indent_len + 2..]);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// Ordered list: digits followed by [.)] and a space, optionally with task
|
|
||||||
// checkbox
|
|
||||||
let digit_count = trimmed.bytes().take_while(u8::is_ascii_digit).count();
|
|
||||||
if digit_count > 0 && indent_len + digit_count + 2 <= line.len() {
|
|
||||||
let after_digits = trimmed.as_bytes()[digit_count];
|
|
||||||
let after_marker = trimmed.as_bytes().get(digit_count + 1);
|
|
||||||
if matches!(after_digits, b'.' | b')') && after_marker == Some(&b' ') {
|
|
||||||
return indent_len
|
|
||||||
+ digit_count
|
|
||||||
+ 2
|
|
||||||
+ task_checkbox_len(&line[indent_len + digit_count + 2..]);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
0
|
|
||||||
}
|
|
||||||
|
|
||||||
/// Returns the byte length of a task list checkbox (`[ ] `, `[x] `, `[X] `)
|
|
||||||
/// at the start of `rest`, or 0 if none is found
|
|
||||||
fn task_checkbox_len(rest: &str) -> usize {
|
|
||||||
if rest.len() >= 4
|
|
||||||
&& rest.as_bytes()[0] == b'['
|
|
||||||
&& matches!(rest.as_bytes()[1], b' ' | b'x' | b'X')
|
|
||||||
&& rest.as_bytes()[2] == b']'
|
|
||||||
&& rest.as_bytes()[3] == b' '
|
|
||||||
{
|
|
||||||
4
|
|
||||||
} else {
|
|
||||||
0
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
#[cfg(test)]
|
|
||||||
mod tests {
|
|
||||||
use insta::assert_debug_snapshot;
|
|
||||||
|
|
||||||
use super::*;
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_plain_text() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("Hello world"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_empty() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer(""));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_headings() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("# Hello world"));
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("## Sub heading"));
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("###### Deep heading"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_unordered_list() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("- item one\n- item two\n- item three"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_ordered_list() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("1. first\n2. second\n3. third"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_blockquote() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("> quoted text\n> more quoted"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_inline_formatting() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("Some **bold** and *italic* text"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_mixed_content() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer(
|
|
||||||
"# Title\n\nSome text with **bold**.\n\n- list item\n- another item"
|
|
||||||
));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_indented_list() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer(" - nested item\n - deeper"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_crlf() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("Line 1\r\nLine 2"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_code_fence() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("```rust\nlet x = 1;\n```"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_heading_only() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("# "));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_link() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("Click [here](https://example.com) now"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_multiline_paragraph() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer(
|
|
||||||
"First line\nSecond line\n\nNew paragraph"
|
|
||||||
));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_list_with_star_marker() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("* item one\n* item two"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_bold_not_confused_with_list() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("**bold text**"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_task_list() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer(
|
|
||||||
"- [ ] todo\n- [x] done\n- [X] also done"
|
|
||||||
));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_ordered_task_list() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer("1. [ ] first task\n2. [x] second task"));
|
|
||||||
}
|
|
||||||
|
|
||||||
#[test]
|
|
||||||
fn test_unicode() {
|
|
||||||
assert_debug_snapshot!(markdown_tokenizer(
|
|
||||||
"# \u{1F600} Héllo\n- \u{00E9}lément\n> \u{4F60}\u{597D} world"
|
|
||||||
));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
@ -1,5 +1,5 @@
|
||||||
---
|
---
|
||||||
source: src/tokenizer/word_tokenizer.rs
|
source: reconcile/src/tokenizer/word_tokenizer.rs
|
||||||
expression: "word_tokenizer(\"\")"
|
expression: "word_tokenizer(\"\")"
|
||||||
snapshot_kind: text
|
snapshot_kind: text
|
||||||
---
|
---
|
||||||
|
|
@ -1,23 +1,23 @@
|
||||||
---
|
---
|
||||||
source: src/tokenizer/word_tokenizer.rs
|
source: reconcile/src/tokenizer/word_tokenizer.rs
|
||||||
expression: "word_tokenizer(\" what? \")"
|
expression: "word_tokenizer(\" what? \")"
|
||||||
snapshot_kind: text
|
snapshot_kind: text
|
||||||
---
|
---
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: " what?",
|
normalised: " what?",
|
||||||
original: " ",
|
original: " ",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
},
|
},
|
||||||
Token {
|
Token {
|
||||||
normalized: "what?",
|
normalised: "what?",
|
||||||
original: "what?",
|
original: "what?",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
},
|
},
|
||||||
Token {
|
Token {
|
||||||
normalized: " ",
|
normalised: " ",
|
||||||
original: " ",
|
original: " ",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -1,53 +1,53 @@
|
||||||
---
|
---
|
||||||
source: src/tokenizer/word_tokenizer.rs
|
source: reconcile/src/tokenizer/word_tokenizer.rs
|
||||||
expression: "word_tokenizer(\" hello, \\nwhere are you?\")"
|
expression: "word_tokenizer(\" hello, \\nwhere are you?\")"
|
||||||
snapshot_kind: text
|
snapshot_kind: text
|
||||||
---
|
---
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: " hello,",
|
normalised: " hello,",
|
||||||
original: " ",
|
original: " ",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
},
|
},
|
||||||
Token {
|
Token {
|
||||||
normalized: "hello,",
|
normalised: "hello,",
|
||||||
original: "hello,",
|
original: "hello,",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
},
|
},
|
||||||
Token {
|
Token {
|
||||||
normalized: " \nwhere",
|
normalised: " \nwhere",
|
||||||
original: " \n",
|
original: " \n",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
},
|
},
|
||||||
Token {
|
Token {
|
||||||
normalized: "where",
|
normalised: "where",
|
||||||
original: "where",
|
original: "where",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
},
|
},
|
||||||
Token {
|
Token {
|
||||||
normalized: " are",
|
normalised: " are",
|
||||||
original: " ",
|
original: " ",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
},
|
},
|
||||||
Token {
|
Token {
|
||||||
normalized: "are",
|
normalised: "are",
|
||||||
original: "are",
|
original: "are",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
},
|
},
|
||||||
Token {
|
Token {
|
||||||
normalized: " you?",
|
normalised: " you?",
|
||||||
original: " ",
|
original: " ",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
},
|
},
|
||||||
Token {
|
Token {
|
||||||
normalized: "you?",
|
normalised: "you?",
|
||||||
original: "you?",
|
original: "you?",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -0,0 +1,39 @@
|
||||||
|
---
|
||||||
|
source: reconcile/src/tokenizer/word_tokenizer.rs
|
||||||
|
expression: "word_tokenizer(\" hello, \\nwhere are you?\")"
|
||||||
|
snapshot_kind: text
|
||||||
|
---
|
||||||
|
[
|
||||||
|
Token {
|
||||||
|
normalised: " ",
|
||||||
|
original: " ",
|
||||||
|
},
|
||||||
|
Token {
|
||||||
|
normalised: "hello,",
|
||||||
|
original: "hello,",
|
||||||
|
},
|
||||||
|
Token {
|
||||||
|
normalised: " \n",
|
||||||
|
original: " \n",
|
||||||
|
},
|
||||||
|
Token {
|
||||||
|
normalised: "where",
|
||||||
|
original: "where",
|
||||||
|
},
|
||||||
|
Token {
|
||||||
|
normalised: " ",
|
||||||
|
original: " ",
|
||||||
|
},
|
||||||
|
Token {
|
||||||
|
normalised: "are",
|
||||||
|
original: "are",
|
||||||
|
},
|
||||||
|
Token {
|
||||||
|
normalised: " ",
|
||||||
|
original: " ",
|
||||||
|
},
|
||||||
|
Token {
|
||||||
|
normalised: "you?",
|
||||||
|
original: "you?",
|
||||||
|
},
|
||||||
|
]
|
||||||
|
|
@ -1,23 +1,23 @@
|
||||||
---
|
---
|
||||||
source: src/tokenizer/word_tokenizer.rs
|
source: reconcile/src/tokenizer/word_tokenizer.rs
|
||||||
expression: "word_tokenizer(\"Hi there!\")"
|
expression: "word_tokenizer(\"Hi there!\")"
|
||||||
snapshot_kind: text
|
snapshot_kind: text
|
||||||
---
|
---
|
||||||
[
|
[
|
||||||
Token {
|
Token {
|
||||||
normalized: "Hi",
|
normalised: "Hi",
|
||||||
original: "Hi",
|
original: "Hi",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
},
|
},
|
||||||
Token {
|
Token {
|
||||||
normalized: " there!",
|
normalised: " there!",
|
||||||
original: " ",
|
original: " ",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
},
|
},
|
||||||
Token {
|
Token {
|
||||||
normalized: "there!",
|
normalised: "there!",
|
||||||
original: "there!",
|
original: "there!",
|
||||||
is_left_joinable: true,
|
is_left_joinable: true,
|
||||||
is_right_joinable: true,
|
is_right_joinable: true,
|
||||||
|
|
@ -1,145 +0,0 @@
|
||||||
---
|
|
||||||
source: src/tokenizer/character_tokenizer.rs
|
|
||||||
expression: "character_tokenizer(\" hello, \\nwhere are you?\")"
|
|
||||||
snapshot_kind: text
|
|
||||||
---
|
|
||||||
[
|
|
||||||
Token {
|
|
||||||
normalized: " ",
|
|
||||||
original: " ",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "h",
|
|
||||||
original: "h",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "e",
|
|
||||||
original: "e",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "l",
|
|
||||||
original: "l",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "l",
|
|
||||||
original: "l",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "o",
|
|
||||||
original: "o",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: ",",
|
|
||||||
original: ",",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: " ",
|
|
||||||
original: " ",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\n",
|
|
||||||
original: "\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "w",
|
|
||||||
original: "w",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "h",
|
|
||||||
original: "h",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "e",
|
|
||||||
original: "e",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "r",
|
|
||||||
original: "r",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "e",
|
|
||||||
original: "e",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: " ",
|
|
||||||
original: " ",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "a",
|
|
||||||
original: "a",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "r",
|
|
||||||
original: "r",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "e",
|
|
||||||
original: "e",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: " ",
|
|
||||||
original: " ",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "y",
|
|
||||||
original: "y",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "o",
|
|
||||||
original: "o",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "u",
|
|
||||||
original: "u",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "?",
|
|
||||||
original: "?",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
]
|
|
||||||
|
|
@ -1,6 +0,0 @@
|
||||||
---
|
|
||||||
source: src/tokenizer/character_tokenizer.rs
|
|
||||||
expression: "character_tokenizer(\"\")"
|
|
||||||
snapshot_kind: text
|
|
||||||
---
|
|
||||||
[]
|
|
||||||
|
|
@ -1,36 +0,0 @@
|
||||||
---
|
|
||||||
source: src/tokenizer/line_tokenizer.rs
|
|
||||||
expression: "line_tokenizer(\"Old\\rMac\\rStyle\")"
|
|
||||||
---
|
|
||||||
[
|
|
||||||
Token {
|
|
||||||
normalized: "Old",
|
|
||||||
original: "Old",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\r",
|
|
||||||
original: "\r",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "Mac",
|
|
||||||
original: "Mac",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\r",
|
|
||||||
original: "\r",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "Style",
|
|
||||||
original: "Style",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
]
|
|
||||||
|
|
@ -1,36 +0,0 @@
|
||||||
---
|
|
||||||
source: src/tokenizer/line_tokenizer.rs
|
|
||||||
expression: "line_tokenizer(\"Mixed\\r\\nand\\rbare\")"
|
|
||||||
---
|
|
||||||
[
|
|
||||||
Token {
|
|
||||||
normalized: "Mixed",
|
|
||||||
original: "Mixed",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\r\n",
|
|
||||||
original: "\r\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "and",
|
|
||||||
original: "and",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\r",
|
|
||||||
original: "\r",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "bare",
|
|
||||||
original: "bare",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
]
|
|
||||||
|
|
@ -1,13 +0,0 @@
|
||||||
---
|
|
||||||
source: src/tokenizer/line_tokenizer.rs
|
|
||||||
expression: "line_tokenizer(\"Hello\")"
|
|
||||||
snapshot_kind: text
|
|
||||||
---
|
|
||||||
[
|
|
||||||
Token {
|
|
||||||
normalized: "Hello",
|
|
||||||
original: "Hello",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
]
|
|
||||||
|
|
@ -1,25 +0,0 @@
|
||||||
---
|
|
||||||
source: src/tokenizer/line_tokenizer.rs
|
|
||||||
expression: "line_tokenizer(\"Hello\\nWorld\")"
|
|
||||||
snapshot_kind: text
|
|
||||||
---
|
|
||||||
[
|
|
||||||
Token {
|
|
||||||
normalized: "Hello",
|
|
||||||
original: "Hello",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\n",
|
|
||||||
original: "\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "World",
|
|
||||||
original: "World",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
]
|
|
||||||
|
|
@ -1,31 +0,0 @@
|
||||||
---
|
|
||||||
source: src/tokenizer/line_tokenizer.rs
|
|
||||||
expression: "line_tokenizer(\"Hello\\nWorld\\n\")"
|
|
||||||
snapshot_kind: text
|
|
||||||
---
|
|
||||||
[
|
|
||||||
Token {
|
|
||||||
normalized: "Hello",
|
|
||||||
original: "Hello",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\n",
|
|
||||||
original: "\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "World",
|
|
||||||
original: "World",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\n",
|
|
||||||
original: "\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
]
|
|
||||||
|
|
@ -1,25 +0,0 @@
|
||||||
---
|
|
||||||
source: src/tokenizer/line_tokenizer.rs
|
|
||||||
expression: "line_tokenizer(\"Line 1\\r\\nLine 2\")"
|
|
||||||
snapshot_kind: text
|
|
||||||
---
|
|
||||||
[
|
|
||||||
Token {
|
|
||||||
normalized: "Line 1",
|
|
||||||
original: "Line 1",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\r\n",
|
|
||||||
original: "\r\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "Line 2",
|
|
||||||
original: "Line 2",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
]
|
|
||||||
|
|
@ -1,49 +0,0 @@
|
||||||
---
|
|
||||||
source: src/tokenizer/line_tokenizer.rs
|
|
||||||
expression: "line_tokenizer(\"Multi\\nLine\\nText\\nHere\")"
|
|
||||||
snapshot_kind: text
|
|
||||||
---
|
|
||||||
[
|
|
||||||
Token {
|
|
||||||
normalized: "Multi",
|
|
||||||
original: "Multi",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\n",
|
|
||||||
original: "\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "Line",
|
|
||||||
original: "Line",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\n",
|
|
||||||
original: "\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "Text",
|
|
||||||
original: "Text",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\n",
|
|
||||||
original: "\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "Here",
|
|
||||||
original: "Here",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
]
|
|
||||||
|
|
@ -1,13 +0,0 @@
|
||||||
---
|
|
||||||
source: src/tokenizer/line_tokenizer.rs
|
|
||||||
expression: "line_tokenizer(\"\\n\")"
|
|
||||||
snapshot_kind: text
|
|
||||||
---
|
|
||||||
[
|
|
||||||
Token {
|
|
||||||
normalized: "\n",
|
|
||||||
original: "\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
]
|
|
||||||
|
|
@ -1,19 +0,0 @@
|
||||||
---
|
|
||||||
source: src/tokenizer/line_tokenizer.rs
|
|
||||||
expression: "line_tokenizer(\"\\n\\n\")"
|
|
||||||
snapshot_kind: text
|
|
||||||
---
|
|
||||||
[
|
|
||||||
Token {
|
|
||||||
normalized: "\n",
|
|
||||||
original: "\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
Token {
|
|
||||||
normalized: "\n",
|
|
||||||
original: "\n",
|
|
||||||
is_left_joinable: true,
|
|
||||||
is_right_joinable: true,
|
|
||||||
},
|
|
||||||
]
|
|
||||||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Add table
Add a link
Reference in a new issue