Skip to content

Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

fix(workspace): skip Postgres catalog and alembic_version consumers (#4187)

Abdullah Azmifa5200347355
diff --git a/packages/core/src/repowise/core/workspace/extractors/data/dialect.py b/packages/core/src/repowise/core/workspace/extractors/data/dialect.py
index 56dc92e1e..b54338241 100644
--- a/packages/core/src/repowise/core/workspace/extractors/data/dialect.py
+++ b/packages/core/src/repowise/core/workspace/extractors/data/dialect.py
@@ -17,7 +17,7 @@ from repowise.core.workspace.origins import ContractOrigin
from ..base import line_at
from ..dialect import build_contract
-from .names import normalize_table_name
+from .names import is_system_table, normalize_table_name
if TYPE_CHECKING:
from repowise.core.workspace.contracts import Contract
@@ -107,7 +107,7 @@ def build_table_consumer(
names the embedded engine the file opens, when it opens one.
"""
table = normalize_table_name(table_raw)
- if table is None:
+ if table is None or is_system_table(table):
return None
engine = embedded_engine(ctx)
return build_contract(
diff --git a/packages/core/src/repowise/core/workspace/extractors/data/names.py b/packages/core/src/repowise/core/workspace/extractors/data/names.py
index dc9a74f61..bf0058c8e 100644
--- a/packages/core/src/repowise/core/workspace/extractors/data/names.py
+++ b/packages/core/src/repowise/core/workspace/extractors/data/names.py
@@ -67,6 +67,23 @@ def normalize_table_name(raw: str) -> str | None:
return f"{schema}.{table}" if schema else table
+# Database catalogs and migration-bookkeeping tables that no service owns as a
+# cross-repo data contract. Skipping them on the consumer side keeps schema
+# probes (``pg_*``, ``pg_catalog.*``, ``information_schema.*``, ``alembic_version``)
+# out of unmatched ``no_provider`` diagnostics.
+_SYSTEM_SCHEMAS = frozenset({"pg_catalog", "information_schema"})
+_SYSTEM_TABLES = frozenset({"alembic_version"})
+_SYSTEM_TABLE_PREFIXES = ("pg_",)
+
+
+def is_system_table(table: str) -> bool:
+ """True when a normalized *table* names a database catalog or bookkeeping table."""
+ schema, _, bare = table.rpartition(".")
+ if schema in _SYSTEM_SCHEMAS:
+ return True
+ return bare in _SYSTEM_TABLES or bare.startswith(_SYSTEM_TABLE_PREFIXES)
+
+
def snake_case(name: str) -> str:
return re.sub(r"(?<=[a-z0-9])(?=[A-Z])", "_", name).lower()
diff --git a/tests/unit/workspace/test_data_contracts.py b/tests/unit/workspace/test_data_contracts.py
index 71425a9d5..e4031cafc 100644
--- a/tests/unit/workspace/test_data_contracts.py
+++ b/tests/unit/workspace/test_data_contracts.py
@@ -12,6 +12,7 @@ from pathlib import Path
from repowise.core.workspace.contracts import normalize_contract_id
from repowise.core.workspace.extractors.data import DataExtractor
from repowise.core.workspace.extractors.data.names import (
+ is_system_table,
normalize_table_name,
split_qualified,
)
@@ -64,6 +65,22 @@ class TestNormalizeTableName:
assert split_qualified("a.b") == ("a", "b")
assert split_qualified("b") == (None, "b")
+ def test_is_system_table(self) -> None:
+ for sys_tbl in (
+ "pg_database",
+ "pg_roles",
+ "pg_class",
+ "pg_catalog.pg_tables",
+ "pg_catalog.custom_view",
+ "information_schema.tables",
+ "information_schema.columns",
+ "alembic_version",
+ "core.alembic_version",
+ ):
+ assert is_system_table(sys_tbl), sys_tbl
+ for user_tbl in ("users", "page_views", "pgadmin", "analytics.events"):
+ assert not is_system_table(user_tbl), user_tbl
+
def _write(repo: Path, rel: str, content: str) -> None:
path = repo / rel
@@ -292,6 +309,22 @@ class TestSqlStringConsumers:
contracts = DataExtractor().extract(tmp_path, "api", make_exclude_predicate())
assert contracts == []
+ def test_system_catalogs_and_alembic_version_skipped(self, tmp_path: Path) -> None:
+ _write(
+ tmp_path,
+ "scripts/promote.py",
+ 'q1 = "SELECT datname FROM pg_database WHERE datistemplate = false"\n'
+ 'q2 = "SELECT rolname FROM pg_roles WHERE rolcanlogin = true"\n'
+ 'q3 = "SELECT relname FROM pg_class WHERE relkind = \'r\'"\n'
+ 'q4 = "SELECT table_name FROM information_schema.tables WHERE table_schema = \'public\'"\n'
+ 'q5 = "SELECT version_num FROM alembic_version"\n'
+ 'q6 = "SELECT nspname FROM pg_catalog.pg_namespace"\n'
+ 'q7 = "SELECT id FROM orders WHERE promoted = true"\n',
+ )
+ contracts = DataExtractor().extract(tmp_path, "api")
+ consumers = [c for c in contracts if c.role == "consumer"]
+ assert [c.contract_id for c in consumers] == ["data::orders"]
+
class TestDataMatching:
def test_normalize_contract_id_lowercases(self) -> None: