refactor composer to use sqlalchemy, avoid string concatenations and follow conventions

tests/test_composer_dates.py

@@ -1,10 +1,25 @@
-"""Date-range resolver tests — bounds parsing + dispatch on column type."""
+"""Date-range resolver tests — bounds parsing + dispatch on column type/encoding.
+
+`resolve_date_range` now returns an `exp` node and takes the effective encoding
+map (built-in defaults overlaid with any dataset overrides). Tests render the
+node to SQL to assert on the predicate.
+"""
 
 import pytest
+from sqlglot import exp
 
 from api.composer.dates import _bounds, resolve_date_range
+from api.composer.encodings import DEFAULT_ENCODINGS, effective_encodings
 from api.composer.types import PickValidationError
-from api.recon.types import Column
+from api.recon.types import Column, Recon
+
+
+def _col(name: str = "date", table: str = "l") -> exp.Column:
+    return exp.column(name, table=table, quoted=True)
+
+
+def _sql(node: exp.Expression) -> str:
+    return node.sql(dialect="postgres", identify=True)
 
 
 def test_bounds_year():
@@ -26,25 +41,56 @@ def test_bounds_unsupported_raises():
 
 def test_resolve_real_date_column():
     col = Column(name="date", sql_type="DATE", nullable=False)
-    out = resolve_date_range("1996", col, '"l"."date"')
+    out = _sql(resolve_date_range("1996", col, _col(), {}))
     assert out == "\"l\".\"date\" BETWEEN '1996-01-01' AND '1996-12-31'"
 
 
 def test_resolve_timestamp_column():
     col = Column(name="created_at", sql_type="TIMESTAMP WITHOUT TIME ZONE", nullable=True)
-    out = resolve_date_range("1996-Q2", col, '"x"."created_at"')
+    out = _sql(resolve_date_range("1996-Q2", col, _col("created_at", "x"), {}))
     assert out == "\"x\".\"created_at\" BETWEEN '1996-04-01' AND '1996-06-30'"
 
 
-def test_resolve_yymmdd_semantic_type():
+def test_resolve_yymmdd_via_default_encoding():
     col = Column(name="date", sql_type="INTEGER", nullable=False,
                  semantic_type="date_yymmdd")
-    out = resolve_date_range("1996", col, '"l"."date"')
+    out = _sql(resolve_date_range("1996", col, _col(), DEFAULT_ENCODINGS))
     assert "TO_DATE(LPAD(" in out
     assert "BETWEEN '1996-01-01' AND '1996-12-31'" in out
 
 
+def test_dataset_encoding_overrides_default():
+    # A dataset can override a built-in encoding with its own coercion SQL.
+    col = Column(name="d", sql_type="INTEGER", nullable=False,
+                 semantic_type="date_yymmdd")
+    override = {"date_yymmdd": {"as_date": "MAKE_DATE(1900 + {col} / 10000, 1, 1)"}}
+    out = _sql(resolve_date_range("1996", col, _col("d"), override))
+    assert "MAKE_DATE(" in out
+    assert "TO_DATE" not in out
+
+
+def test_resolve_semantic_type_without_encoding_raises():
+    # Declared semantic_type but no matching encoding and not a native date type.
+    col = Column(name="d", sql_type="INTEGER", nullable=False,
+                 semantic_type="date_yymmdd")
+    with pytest.raises(PickValidationError, match="not supported"):
+        resolve_date_range("1996", col, _col("d"), {})
+
+
 def test_resolve_unsupported_column_type_raises():
     col = Column(name="x", sql_type="TEXT", nullable=True)
     with pytest.raises(PickValidationError, match="not supported"):
-        resolve_date_range("1996", col, '"x"."x"')
+        resolve_date_range("1996", col, _col("x", "x"), {})
+
+
+def test_effective_encodings_merges_defaults_with_dataset():
+    recon = Recon(schema="t", tables={}, metrics={},
+                  encodings={"my_epoch": {"as_date": "TO_TIMESTAMP({col})::date"}})
+    eff = effective_encodings(recon)
+    assert "date_yymmdd" in eff          # default survives
+    assert eff["my_epoch"]["as_date"].startswith("TO_TIMESTAMP")  # dataset added
+
+    # Dataset entry wins on key collision.
+    recon2 = Recon(schema="t", tables={}, metrics={},
+                   encodings={"date_yymmdd": {"as_date": "CUSTOM({col})"}})
+    assert effective_encodings(recon2)["date_yymmdd"]["as_date"] == "CUSTOM({col})"