chore(ingest): bump sqlglot version to latest (#12696)

metadata-ingestion/setup.py

@@ -99,9 +99,9 @@
 
 sqlglot_lib = {
     # We heavily monkeypatch sqlglot.
-    # Prior to the patching, we originally maintained an acryl-sqlglot fork:
-    # https://github.com/tobymao/sqlglot/compare/main...hsheth2:sqlglot:main?expand=1
-    "sqlglot[rs]==25.32.1",
+    # We used to maintain an acryl-sqlglot fork: https://github.com/tobymao/sqlglot/compare/main...hsheth2:sqlglot:main?expand=1
+    # but not longer do.
+    "sqlglot[rs]==26.6.0",
     "patchy==2.8.0",
 }
 

metadata-ingestion/src/datahub/sql_parsing/_sqlglot_patch.py

@@ -172,17 +172,9 @@ class Node(sqlglot.lineage.Node):
          derived_tables = [
              source.expression.parent
              for source in scope.sources.values()
-@@ -254,6 +257,7 @@ def to_node(
-         if dt.comments and dt.comments[0].startswith("source: ")
-     }
-
-+    c: exp.Column
-     for c in source_columns:
-         table = c.table
-         source = scope.sources.get(table)
 @@ -281,8 +285,21 @@ def to_node(
-             # it means this column's lineage is unknown. This can happen if the definition of a source used in a query
-             # is not passed into the `sources` map.
+             # is unknown. This can happen if the definition of a source used in a query is not
+             # passed into the `sources` map.
              source = source or exp.Placeholder()
 +
 +            subfields = []

metadata-ingestion/src/datahub/utilities/unified_diff.py

@@ -2,8 +2,12 @@
 from dataclasses import dataclass
 from typing import List, Tuple
 
+from datahub.cli.env_utils import get_boolean_env_variable
+
+_debug_diff = get_boolean_env_variable("DATAHUB_DEBUG_DIFF_PATCHER")
+
 logger = logging.getLogger(__name__)
-logger.setLevel(logging.INFO)
+logger.setLevel(logging.DEBUG if _debug_diff else logging.INFO)
 
 _LOOKAROUND_LINES = 300