Fix data pipelines once and for all

pipeline/transform/join_epc_pp.py

@@ -109,6 +109,27 @@ def _clean_number(column: str, dtype: pl.DataType) -> pl.Expr:
     return _clean_string(column).cast(dtype, strict=False)
 
 
+def _join_address_parts(*columns: str) -> pl.Expr:
+    """Join address components into one display address, single-spaced.
+
+    Price-paid SAON/PAON/STREET are EMPTY STRINGS (not null) when absent —
+    saon is "" on ~88% of rows — and ``concat_str(..., ignore_nulls=True)``
+    skips only nulls, so empty components still contributed their separator
+    (``' 10 PALACE GREEN'``, doubled spaces when a middle part was empty).
+    Convert ``''``→null per component so ignore_nulls works as intended, then
+    defensively collapse residual whitespace runs and strip the result. A
+    fully-empty address becomes null (dropped by the downstream
+    ``pp_address.is_not_null()`` filter) instead of whitespace junk.
+    """
+    joined = pl.concat_str(
+        [_clean_string(column) for column in columns],
+        separator=" ",
+        ignore_nulls=True,
+    )
+    cleaned = joined.str.replace_all(r"\s+", " ").str.strip_chars()
+    return pl.when(cleaned == "").then(None).otherwise(cleaned)
+
+
 def _select_epc_columns(raw: pl.LazyFrame) -> pl.LazyFrame:
     return (
         raw.select(
@@ -436,11 +457,7 @@ def _run(epc_path: Path, price_paid_path: Path, output_path: Path, temp_dir: Pat
         )
         .filter(pl.col("pp_property_type") != "Other")
         .with_columns(
-            pl.concat_str(
-                [pl.col("saon"), pl.col("paon"), pl.col("street")],
-                separator=" ",
-                ignore_nulls=True,
-            ).alias("pp_address"),
+            _join_address_parts("saon", "paon", "street").alias("pp_address"),
         )
         .with_columns(
             normalize_address_key(pl.col("pp_address")).alias("_pp_match_address"),