feat: ajouter traducteurs filter_query→SQL et sort_by→SQL

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-21 23:33:49 +02:00
parent abc6390174
commit 95c90e319e
2 changed files with 253 additions and 0 deletions
@@ -0,0 +1,103 @@
+import polars as pl
+
+from src.utils import logger
+from src.utils.table import split_filter_part
+
+
+def filter_query_to_sql(filter_query: str, schema: pl.Schema) -> tuple[str, list]:
+    """Traduit le DSL de filtres de dash_table.DataTable en fragment SQL DuckDB.
+
+    Retourne (where_clause, params) où where_clause est un fragment à injecter
+    après WHERE et params est la liste des valeurs à passer à
+    cursor.execute(sql, params). Les identifiants de colonnes sont validés
+    contre le schéma fourni ; jamais concaténés avec des valeurs utilisateur.
+    """
+    if not filter_query:
+        return "TRUE", []
+
+    clauses: list[str] = []
+    params: list = []
+
+    for part in filter_query.split(" && "):
+        col_name, operator, raw_value = split_filter_part(part)
+        if not isinstance(col_name, str) or not isinstance(raw_value, str):
+            continue
+
+        if col_name not in schema.names():
+            logger.warning(f"Colonne inconnue ignorée : {col_name!r}")
+            continue
+
+        col_type = str(schema[col_name])
+        is_numeric = col_type.startswith("Int") or col_type.startswith("Float")
+        quoted_col = f'"{col_name}"'
+
+        if is_numeric:
+            try:
+                value = (
+                    int(raw_value) if col_type.startswith("Int") else float(raw_value)
+                )
+            except ValueError:
+                logger.warning(f"Valeur numérique invalide ignorée : {raw_value!r}")
+                continue
+
+            if operator == "contains":
+                clauses.append(f"{quoted_col} IS NOT NULL AND {quoted_col} = ?")
+            elif operator == ">":
+                clauses.append(f"{quoted_col} IS NOT NULL AND {quoted_col} > ?")
+            elif operator == "<":
+                clauses.append(f"{quoted_col} IS NOT NULL AND {quoted_col} < ?")
+            else:
+                logger.warning(f"Opérateur invalide pour numérique : {operator!r}")
+                continue
+            params.append(value)
+            continue
+
+        # String / Date : toujours traité comme texte (parité avec Polars)
+        value = raw_value.strip('"')
+        col_is_date = col_type == "Date"
+
+        if operator == "contains":
+            if value.endswith("*") and not value.startswith("*"):
+                like = value[:-1] + "%"
+            elif value.startswith("*") and not value.endswith("*"):
+                like = "%" + value[1:]
+            else:
+                like = "%" + value + "%"
+            target = f"CAST({quoted_col} AS VARCHAR)" if col_is_date else quoted_col
+            clauses.append(
+                f"{quoted_col} IS NOT NULL AND {target} <> '' AND {target} ILIKE ?"
+            )
+            params.append(like)
+        elif operator in (">", "<"):
+            target = f"CAST({quoted_col} AS VARCHAR)" if col_is_date else quoted_col
+            clauses.append(f"{quoted_col} IS NOT NULL AND {target} {operator} ?")
+            params.append(value)
+        else:
+            logger.warning(f"Opérateur invalide pour chaîne : {operator!r}")
+            continue
+
+    if not clauses:
+        return "TRUE", []
+    return " AND ".join(clauses), params
+
+
+def sort_by_to_sql(sort_by: list[dict] | None, schema: pl.Schema) -> str:
+    """Traduit sort_by (format Dash) en clause ORDER BY DuckDB.
+
+    Retourne '' si pas de tri (aucun ORDER BY à ajouter).
+    """
+    if not sort_by:
+        return ""
+
+    fragments: list[str] = []
+    for entry in sort_by:
+        col = entry.get("column_id")
+        direction = entry.get("direction")
+        if col not in schema.names():
+            logger.warning(f"Tri sur colonne inconnue ignoré : {col!r}")
+            continue
+        if direction not in ("asc", "desc"):
+            continue
+        fragments.append(f'"{col}" {direction.upper()} NULLS LAST')
+
+    return ", ".join(fragments)
@@ -0,0 +1,150 @@
+import polars as pl
+
+SCHEMA = pl.Schema(
+    {
+        "uid": pl.String,
+        "objet": pl.String,
+        "acheteur_id": pl.String,
+        "montant": pl.Float64,
+        "dureeMois": pl.Int64,
+        "dateNotification": pl.Date,
+    }
+)
+
+
+def test_empty_filter_returns_true():
+    from src.utils.table_sql import filter_query_to_sql
+
+    where, params = filter_query_to_sql("", SCHEMA)
+    assert where == "TRUE"
+    assert params == []
+
+
+def test_icontains_string_is_case_insensitive_like():
+    from src.utils.table_sql import filter_query_to_sql
+
+    where, params = filter_query_to_sql("{objet} icontains travaux", SCHEMA)
+    assert where == '"objet" IS NOT NULL AND "objet" <> \'\' AND "objet" ILIKE ?'
+    assert params == ["%travaux%"]
+
+
+def test_icontains_with_trailing_wildcard_is_starts_with():
+    from src.utils.table_sql import filter_query_to_sql
+
+    where, params = filter_query_to_sql(
+        "{acheteur_id} icontains 24350013900189*", SCHEMA
+    )
+    assert (
+        where
+        == '"acheteur_id" IS NOT NULL AND "acheteur_id" <> \'\' AND "acheteur_id" ILIKE ?'
+    )
+    assert params == ["24350013900189%"]
+
+
+def test_icontains_with_leading_wildcard_is_ends_with():
+    from src.utils.table_sql import filter_query_to_sql
+
+    where, params = filter_query_to_sql("{uid} icontains *2024", SCHEMA)
+    assert where == '"uid" IS NOT NULL AND "uid" <> \'\' AND "uid" ILIKE ?'
+    assert params == ["%2024"]
+
+
+def test_numeric_greater_than():
+    from src.utils.table_sql import filter_query_to_sql
+
+    where, params = filter_query_to_sql("{montant} i> 40000", SCHEMA)
+    assert where == '"montant" IS NOT NULL AND "montant" > ?'
+    assert params == [40000.0]
+
+
+def test_numeric_less_than():
+    from src.utils.table_sql import filter_query_to_sql
+
+    where, params = filter_query_to_sql("{montant} i< 1000", SCHEMA)
+    assert where == '"montant" IS NOT NULL AND "montant" < ?'
+    assert params == [1000.0]
+
+
+def test_numeric_equality_via_icontains():
+    from src.utils.table_sql import filter_query_to_sql
+
+    where, params = filter_query_to_sql("{dureeMois} icontains 12", SCHEMA)
+    assert where == '"dureeMois" IS NOT NULL AND "dureeMois" = ?'
+    assert params == [12]
+
+
+def test_date_column_treated_as_string_ilike():
+    from src.utils.table_sql import filter_query_to_sql
+
+    where, params = filter_query_to_sql("{dateNotification} icontains 2024*", SCHEMA)
+    assert "ILIKE" in where
+    assert params == ["2024%"]
+
+
+def test_multiple_filters_joined_by_and():
+    from src.utils.table_sql import filter_query_to_sql
+
+    filter_query = "{objet} icontains voirie && {montant} i> 40000"
+    where, params = filter_query_to_sql(filter_query, SCHEMA)
+    assert " AND " in where
+    assert params == ["%voirie%", 40000.0]
+
+
+def test_invalid_numeric_value_is_skipped():
+    from src.utils.table_sql import filter_query_to_sql
+
+    where, params = filter_query_to_sql("{montant} i> notanumber", SCHEMA)
+    assert where == "TRUE"
+    assert params == []
+
+
+def test_unknown_column_is_skipped():
+    from src.utils.table_sql import filter_query_to_sql
+
+    where, params = filter_query_to_sql("{inexistant} icontains foo", SCHEMA)
+    assert where == "TRUE"
+    assert params == []
+
+
+def test_escapes_identifier_with_quotes_not_concatenation():
+    from src.utils.table_sql import filter_query_to_sql
+
+    where, params = filter_query_to_sql(
+        "{objet} icontains '; DROP TABLE decp; --", SCHEMA
+    )
+    assert "DROP TABLE" not in where
+    assert any("DROP TABLE" in str(p) for p in params)
+
+
+def test_sort_by_empty():
+    from src.utils.table_sql import sort_by_to_sql
+
+    assert sort_by_to_sql([], SCHEMA) == ""
+    assert sort_by_to_sql(None, SCHEMA) == ""
+
+
+def test_sort_by_single_column_desc():
+    from src.utils.table_sql import sort_by_to_sql
+
+    result = sort_by_to_sql([{"column_id": "montant", "direction": "desc"}], SCHEMA)
+    assert result == '"montant" DESC NULLS LAST'
+
+
+def test_sort_by_multiple_columns_preserves_order():
+    from src.utils.table_sql import sort_by_to_sql
+
+    result = sort_by_to_sql(
+        [
+            {"column_id": "dateNotification", "direction": "desc"},
+            {"column_id": "montant", "direction": "asc"},
+        ],
+        SCHEMA,
+    )
+    assert result == '"dateNotification" DESC NULLS LAST, "montant" ASC NULLS LAST'
+
+
+def test_sort_by_ignores_unknown_column():
+    from src.utils.table_sql import sort_by_to_sql
+
+    result = sort_by_to_sql([{"column_id": "fake", "direction": "asc"}], SCHEMA)
+    assert result == ""