Rust things

server-rs/src/data/places.rs

@@ -97,7 +97,7 @@ fn build_search_text(name: &str, place_type: &str) -> String {
     }
 
     if place_type == "station" {
-        let suffix_aliases: [(&str, &[&str]); 5] = [
+        let suffix_aliases: [(&str, &[&str]); 6] = [
             (
                 " tube station",
                 &[" underground station", " station", " tube", " underground"],
@@ -118,6 +118,7 @@ fn build_search_text(name: &str, place_type: &str) -> String {
                 " elizabeth line station",
                 &[" station", " elizabeth line", " crossrail station"],
             ),
+            (" dlr station", &[" station", " dlr"]),
         ];
 
         for (suffix, replacements) in suffix_aliases {
@@ -139,10 +140,15 @@ fn extract_str_col(df: &DataFrame, name: &str) -> anyhow::Result<Vec<String>> {
     let string_column = column
         .str()
         .with_context(|| format!("Column '{name}' is not a string column"))?;
-    Ok(string_column
+    string_column
         .into_iter()
-        .map(|value| value.unwrap_or("").to_string())
-        .collect())
+        .enumerate()
+        .map(|(row, value)| {
+            value
+                .map(ToString::to_string)
+                .with_context(|| format!("Column '{name}' has null at row {row}"))
+        })
+        .collect()
 }
 
 fn extract_f32_col(df: &DataFrame, name: &str) -> anyhow::Result<Vec<f32>> {
@@ -155,33 +161,37 @@ fn extract_f32_col(df: &DataFrame, name: &str) -> anyhow::Result<Vec<f32>> {
     let float_column = cast
         .f32()
         .with_context(|| format!("Column '{name}' is not a float32 column"))?;
-    Ok(float_column
+    float_column
         .into_iter()
-        .map(|value| value.unwrap_or(0.0))
-        .collect())
+        .enumerate()
+        .map(|(row, value)| value.with_context(|| format!("Column '{name}' has null at row {row}")))
+        .collect()
 }
 
-fn extract_bool_col_or_default(
-    df: &DataFrame,
-    name: &str,
-    default_value: bool,
-) -> anyhow::Result<Vec<bool>> {
-    let Ok(column) = df.column(name) else {
-        return Ok(vec![default_value; df.height()]);
-    };
+fn extract_bool_col(df: &DataFrame, name: &str) -> anyhow::Result<Vec<bool>> {
+    let column = df
+        .column(name)
+        .with_context(|| format!("Missing column '{name}' in places data"))?;
     let bool_column = column
         .bool()
         .with_context(|| format!("Column '{name}' is not a boolean column"))?;
-    Ok(bool_column
+    bool_column
         .into_iter()
-        .map(|value| value.unwrap_or(default_value))
-        .collect())
+        .enumerate()
+        .map(|(row, value)| value.with_context(|| format!("Column '{name}' has null at row {row}")))
+        .collect()
 }
 
 impl PlaceData {
     pub fn load(parquet_path: &Path) -> anyhow::Result<Self> {
+        super::run_polars_io(|| Self::load_inner(parquet_path))
+    }
+
+    fn load_inner(parquet_path: &Path) -> anyhow::Result<Self> {
         info!("Loading place data from {:?}...", parquet_path);
 
+        let parquet_path = PlRefPath::try_from_path(parquet_path)
+            .context("Failed to normalize places parquet path")?;
         let df = LazyFrame::scan_parquet(parquet_path, Default::default())
             .context("Failed to scan places parquet")?
             .collect()
@@ -210,7 +220,7 @@ impl PlaceData {
         let type_rank_vec: Vec<u8> = place_type_raw.iter().map(|pt| type_rank(pt)).collect();
         let place_type = InternedColumn::build(&place_type_raw);
         let travel_destination = if df.column("travel_destination").is_ok() {
-            extract_bool_col_or_default(&df, "travel_destination", true)?
+            extract_bool_col(&df, "travel_destination")?
         } else {
             place_type_raw
                 .iter()
@@ -296,6 +306,7 @@ mod tests {
         assert!(build_search_text("King's Cross tube station", "station")
             .contains("kings cross underground"));
         assert!(build_search_text("St Albans", "city").contains("saint albans"));
+        assert!(build_search_text("Shadwell DLR station", "station").contains("shadwell station"));
     }
 
     #[test]