pgdevkit 0.4.0__tar.gz → 0.5.0__tar.gz

{pgdevkit-0.4.0 → pgdevkit-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: pgdevkit
-Version: 0.4.0
+Version: 0.5.0
 Summary: A helper for developing with Postgres
 Requires-Python: >=3.14
 Requires-Dist: docker>=7.1.0
@@ -79,7 +79,13 @@ which parses/introspects/diffs like any other column type; see
 handled on the CRUD side (write-side serialization only, no auto-parsing on
 read — `mssql-python` doesn't distinguish `json` columns from `nvarchar`).
 
-### Area tagging and filtering
+### Area and schema filtering
+
+Two independent, composable ways to narrow which files a command touches:
+**area** is an explicit opt-in tag; **schema** is derived automatically from
+each file's own SQL.
+
+#### Area tagging
 
 Any migration file or `database/` code file can declare one or more areas by
 starting with a `-- area:` comment:
@@ -97,43 +103,69 @@ first real statement); a `-- area:` comment later in the file doesn't count.
 A file with no directive is untagged, and untagged files are treated as
 shared/common.
 
-`pgdb compare`, `pgdb migrate check`, and `pgdb migrate apply` all accept:
+#### Schema filtering
+
+No tag needed — schema membership is parsed straight out of the SQL itself:
+every schema-qualified (or default-schema, when unqualified) table/view/
+function/index reference across every statement in the file, DDL or DML
+alike, plus any `CREATE SCHEMA name`. A file whose schema(s) can't be
+determined (unparseable content, or no table/schema reference in it at all)
+is treated the same as an untagged file — always kept.
+
+#### Options
+
+`pgdb compare`, `pgdb migrate check`, `pgdb migrate apply`, `pgdb testdb up`,
+and `pgdb testdb reset` all accept:
 
 - `--area NAME` (repeatable) — restrict to files declaring one of the given
   areas, **plus every untagged file** (untagged files always stay in scope).
 - `--exclude-area NAME` (repeatable) — drop files declaring one of the given
   areas; untagged files are never dropped by this.
+- `--schema NAME` (repeatable) — restrict to files referencing one of the
+  given schemas, **plus every file with no detectable schema reference**.
+- `--exclude-schema NAME` (repeatable) — drop files referencing one of the
+  given schemas; files with no detectable reference are never dropped.
 
-Both can be combined; a file matching both an included and an excluded area
-is excluded. Passing neither option applies no filtering (the default,
-unchanged behavior).
+All four can be combined — a file must pass every filter it's subject to (an
+area match doesn't excuse a schema mismatch, and vice versa), and a file
+matching both an included and an excluded value on the same axis is
+excluded. Passing none of them applies no filtering (the default, unchanged
+behavior).
 
 ```bash
 pgdb migrate apply path/to/database/_migration_scripts --url ... --area billing
 pgdb compare path/to/database/ --url ... --exclude-area reporting
+pgdb migrate check path/to/database/_migration_scripts --url ... --schema billing --exclude-schema reporting
+pgdb testdb up --schema billing
 ```
 
 `compare`'s default report (no `--report-extra-db`) only checks that the
 filtered scripts exist correctly in the DB, so it composes safely with area
-filtering. Passing `--report-extra-db` together with an area filter also
-reports every DB object outside the filtered area(s) as "missing in
-scripts" — since the live database has no concept of areas, only the
-scripts side is filtered — so treat that combination's "missing in scripts"
-results with that in mind (the CLI prints a warning when you combine them).
-
-`pgdb fetch-missing` deliberately has **no** `--area`/`--exclude-area`: it
-diffs the full database against scripts to find genuinely untracked
-objects, so narrowing the scripts side by area would make every object
-tracked only under a different area look "missing" too — and `--write`
-would then reconstruct a duplicate file for something that already exists.
-
-`pgdevkit.areas` exposes the same logic for scripting:
+and schema filtering. Passing `--report-extra-db` together with either kind
+of filter also reports every DB object outside the filtered area(s)/
+schema(s) as "missing in scripts" — since the live database has no concept
+of areas, and isn't itself filtered by `--schema` either — only the scripts
+side is filtered — so treat that combination's "missing in scripts" results
+with that in mind (the CLI prints a warning when you combine them).
+
+`pgdb fetch-missing` deliberately has **no** `--area`/`--exclude-area` (or
+`--schema`/`--exclude-schema`): it diffs the full database against scripts
+to find genuinely untracked objects, so narrowing the scripts side would
+make every object tracked under a different area/schema look "missing" too
+— and `--write` would then reconstruct a duplicate file for something that
+already exists.
+
+`pgdevkit.areas` exposes the tag-filtering logic for scripting:
 `parse_areas`/`file_areas` read a file's declared areas, and
 `area_allowed`/`filter_by_area` apply the `only`/`exclude` semantics above.
-`pgdevkit.migrate.list_migration_files`/`pending_migrations` and
-`pgdevkit.parser.parse_directory` take the same `areas`/`exclude_areas`
-keyword arguments (`pgdevkit.fetch_missing.find_missing_objects` doesn't,
-for the reason above).
+`pgdevkit.schemas` exposes the equivalent for schema filtering:
+`sql_schemas`/`file_schemas` detect a file's referenced schemas, and
+`schema_allowed`/`filter_by_schema` apply the same `only`/`exclude`
+semantics. `pgdevkit.migrate.list_migration_files`/`pending_migrations` and
+`pgdevkit.parser.parse_directory` take both pairs of keyword arguments
+(`areas`/`exclude_areas` and `schemas`/`exclude_schemas`);
+`pgdevkit.fetch_missing.find_missing_objects` takes neither, for the reason
+above.
 
 ## `pgdb testdb`
 
@@ -165,6 +197,13 @@ def ensure_test_postgres():
 
 CLI: `pgdb testdb up|reset|run-sql|status|shell|clean`.
 
+`up`/`reset` accept `--area`/`--exclude-area` and `--schema`/`--exclude-schema`
+(see "Area and schema filtering" above) to scope which `database/` files get
+applied — e.g. `pgdb testdb up --schema billing` for a test DB with only the
+`billing` schema's tables/views/functions, without waiting on the rest of the
+project's schema to apply. `ensure_testdb`/`reset_testdb` take the same
+keyword arguments when called from Python (e.g. from a pytest fixture).
+
 Container connection defaults (`localhost:54322`, `postgres`/`testpwd`) can
 be overridden with `PGDEVKIT_TESTDB_HOST`, `PGDEVKIT_TESTDB_PORT`,
 `PGDEVKIT_TESTDB_USER`, `PGDEVKIT_TESTDB_PASSWORD`. Before touching the

{pgdevkit-0.4.0 → pgdevkit-0.5.0}/README.md

@@ -58,7 +58,13 @@ which parses/introspects/diffs like any other column type; see
 handled on the CRUD side (write-side serialization only, no auto-parsing on
 read — `mssql-python` doesn't distinguish `json` columns from `nvarchar`).
 
-### Area tagging and filtering
+### Area and schema filtering
+
+Two independent, composable ways to narrow which files a command touches:
+**area** is an explicit opt-in tag; **schema** is derived automatically from
+each file's own SQL.
+
+#### Area tagging
 
 Any migration file or `database/` code file can declare one or more areas by
 starting with a `-- area:` comment:
@@ -76,43 +82,69 @@ first real statement); a `-- area:` comment later in the file doesn't count.
 A file with no directive is untagged, and untagged files are treated as
 shared/common.
 
-`pgdb compare`, `pgdb migrate check`, and `pgdb migrate apply` all accept:
+#### Schema filtering
+
+No tag needed — schema membership is parsed straight out of the SQL itself:
+every schema-qualified (or default-schema, when unqualified) table/view/
+function/index reference across every statement in the file, DDL or DML
+alike, plus any `CREATE SCHEMA name`. A file whose schema(s) can't be
+determined (unparseable content, or no table/schema reference in it at all)
+is treated the same as an untagged file — always kept.
+
+#### Options
+
+`pgdb compare`, `pgdb migrate check`, `pgdb migrate apply`, `pgdb testdb up`,
+and `pgdb testdb reset` all accept:
 
 - `--area NAME` (repeatable) — restrict to files declaring one of the given
   areas, **plus every untagged file** (untagged files always stay in scope).
 - `--exclude-area NAME` (repeatable) — drop files declaring one of the given
   areas; untagged files are never dropped by this.
+- `--schema NAME` (repeatable) — restrict to files referencing one of the
+  given schemas, **plus every file with no detectable schema reference**.
+- `--exclude-schema NAME` (repeatable) — drop files referencing one of the
+  given schemas; files with no detectable reference are never dropped.
 
-Both can be combined; a file matching both an included and an excluded area
-is excluded. Passing neither option applies no filtering (the default,
-unchanged behavior).
+All four can be combined — a file must pass every filter it's subject to (an
+area match doesn't excuse a schema mismatch, and vice versa), and a file
+matching both an included and an excluded value on the same axis is
+excluded. Passing none of them applies no filtering (the default, unchanged
+behavior).
 
 ```bash
 pgdb migrate apply path/to/database/_migration_scripts --url ... --area billing
 pgdb compare path/to/database/ --url ... --exclude-area reporting
+pgdb migrate check path/to/database/_migration_scripts --url ... --schema billing --exclude-schema reporting
+pgdb testdb up --schema billing
 ```
 
 `compare`'s default report (no `--report-extra-db`) only checks that the
 filtered scripts exist correctly in the DB, so it composes safely with area
-filtering. Passing `--report-extra-db` together with an area filter also
-reports every DB object outside the filtered area(s) as "missing in
-scripts" — since the live database has no concept of areas, only the
-scripts side is filtered — so treat that combination's "missing in scripts"
-results with that in mind (the CLI prints a warning when you combine them).
-
-`pgdb fetch-missing` deliberately has **no** `--area`/`--exclude-area`: it
-diffs the full database against scripts to find genuinely untracked
-objects, so narrowing the scripts side by area would make every object
-tracked only under a different area look "missing" too — and `--write`
-would then reconstruct a duplicate file for something that already exists.
-
-`pgdevkit.areas` exposes the same logic for scripting:
+and schema filtering. Passing `--report-extra-db` together with either kind
+of filter also reports every DB object outside the filtered area(s)/
+schema(s) as "missing in scripts" — since the live database has no concept
+of areas, and isn't itself filtered by `--schema` either — only the scripts
+side is filtered — so treat that combination's "missing in scripts" results
+with that in mind (the CLI prints a warning when you combine them).
+
+`pgdb fetch-missing` deliberately has **no** `--area`/`--exclude-area` (or
+`--schema`/`--exclude-schema`): it diffs the full database against scripts
+to find genuinely untracked objects, so narrowing the scripts side would
+make every object tracked under a different area/schema look "missing" too
+— and `--write` would then reconstruct a duplicate file for something that
+already exists.
+
+`pgdevkit.areas` exposes the tag-filtering logic for scripting:
 `parse_areas`/`file_areas` read a file's declared areas, and
 `area_allowed`/`filter_by_area` apply the `only`/`exclude` semantics above.
-`pgdevkit.migrate.list_migration_files`/`pending_migrations` and
-`pgdevkit.parser.parse_directory` take the same `areas`/`exclude_areas`
-keyword arguments (`pgdevkit.fetch_missing.find_missing_objects` doesn't,
-for the reason above).
+`pgdevkit.schemas` exposes the equivalent for schema filtering:
+`sql_schemas`/`file_schemas` detect a file's referenced schemas, and
+`schema_allowed`/`filter_by_schema` apply the same `only`/`exclude`
+semantics. `pgdevkit.migrate.list_migration_files`/`pending_migrations` and
+`pgdevkit.parser.parse_directory` take both pairs of keyword arguments
+(`areas`/`exclude_areas` and `schemas`/`exclude_schemas`);
+`pgdevkit.fetch_missing.find_missing_objects` takes neither, for the reason
+above.
 
 ## `pgdb testdb`
 
@@ -144,6 +176,13 @@ def ensure_test_postgres():
 
 CLI: `pgdb testdb up|reset|run-sql|status|shell|clean`.
 
+`up`/`reset` accept `--area`/`--exclude-area` and `--schema`/`--exclude-schema`
+(see "Area and schema filtering" above) to scope which `database/` files get
+applied — e.g. `pgdb testdb up --schema billing` for a test DB with only the
+`billing` schema's tables/views/functions, without waiting on the rest of the
+project's schema to apply. `ensure_testdb`/`reset_testdb` take the same
+keyword arguments when called from Python (e.g. from a pytest fixture).
+
 Container connection defaults (`localhost:54322`, `postgres`/`testpwd`) can
 be overridden with `PGDEVKIT_TESTDB_HOST`, `PGDEVKIT_TESTDB_PORT`,
 `PGDEVKIT_TESTDB_USER`, `PGDEVKIT_TESTDB_PASSWORD`. Before touching the

{pgdevkit-0.4.0 → pgdevkit-0.5.0}/pgdevkit/cli.py

@@ -29,9 +29,21 @@ _AREA_OPTION = typer.Option(
 _EXCLUDE_AREA_OPTION = typer.Option(
     [], "--exclude-area", help="Skip files declaring this area (repeatable); untagged files are never excluded"
 )
+_SCHEMA_OPTION = typer.Option(
+    [],
+    "--schema",
+    help="Restrict to files referencing this DB schema (repeatable); "
+    "files with no detectable schema reference always stay in scope",
+)
+_EXCLUDE_SCHEMA_OPTION = typer.Option(
+    [],
+    "--exclude-schema",
+    help="Skip files referencing this DB schema (repeatable); "
+    "files with no detectable schema reference are never excluded",
+)
 
 
-def _as_area_set(values: list[str]) -> frozenset[str] | None:
+def _as_set(values: list[str]) -> frozenset[str] | None:
     return frozenset(values) if values else None
 
 testdb_app = typer.Typer(name="testdb", help="Manage the shared local Postgres test container")
@@ -59,17 +71,20 @@ def compare(
     dialect: str = typer.Option("postgres", "--dialect", help="postgres (default) or mssql"),
     area: list[str] = _AREA_OPTION,
     exclude_area: list[str] = _EXCLUDE_AREA_OPTION,
+    schema: list[str] = _SCHEMA_OPTION,
+    exclude_schema: list[str] = _EXCLUDE_SCHEMA_OPTION,
     scripts_dir: Path = typer.Argument(..., help="Directory containing SQL scripts"),
 ) -> None:
     """Compare SQL scripts to a live database and report differences."""
     if not scripts_dir.is_dir():
         err_console.print(f"[red]Error:[/red] {scripts_dir} is not a directory")
         raise typer.Exit(2)
-    if report_extra_db and (area or exclude_area):
+    if report_extra_db and (area or exclude_area or schema or exclude_schema):
         console.print(
-            "[yellow]⚠[/yellow]  --report-extra-db with --area/--exclude-area will report every DB object "
-            "outside the filtered area(s) as \"missing in scripts\", since the live database has no concept "
-            "of areas — only the scripts side is filtered."
+            "[yellow]⚠[/yellow]  --report-extra-db with --area/--exclude-area/--schema/--exclude-schema will "
+            "report every DB object outside the filtered area(s)/schema(s) as \"missing in scripts\", since the "
+            "live database has no concept of areas — and isn't itself filtered by --schema either — only the "
+            "scripts side is filtered."
         )
 
     try:
@@ -91,7 +106,12 @@ def compare(
 
     with console.status("Parsing SQL scripts..."):
         scripts_schema = parse_directory(
-            scripts_dir, dialect=backend.dialect, areas=_as_area_set(area), exclude_areas=_as_area_set(exclude_area)
+            scripts_dir,
+            dialect=backend.dialect,
+            areas=_as_set(area),
+            exclude_areas=_as_set(exclude_area),
+            schemas=_as_set(schema),
+            exclude_schemas=_as_set(exclude_schema),
         )
 
     with console.status("Introspecting database..."):
@@ -188,17 +208,33 @@ def fetch_missing(
 
 
 @testdb_app.command("up")
-def testdb_up() -> None:
+def testdb_up(
+    area: list[str] = _AREA_OPTION,
+    exclude_area: list[str] = _EXCLUDE_AREA_OPTION,
+    schema: list[str] = _SCHEMA_OPTION,
+    exclude_schema: list[str] = _EXCLUDE_SCHEMA_OPTION,
+) -> None:
     """Ensure the container is running, the workspace DB exists, and schema is applied."""
-    testdb.ensure_testdb()
+    testdb.ensure_testdb(
+        areas=_as_set(area), exclude_areas=_as_set(exclude_area), schemas=_as_set(schema),
+        exclude_schemas=_as_set(exclude_schema),
+    )
     info = testdb.status()
     console.print(f"[green]Test DB ready:[/green] {info['database']} ({info['dsn']})")
 
 
 @testdb_app.command("reset")
-def testdb_reset() -> None:
+def testdb_reset(
+    area: list[str] = _AREA_OPTION,
+    exclude_area: list[str] = _EXCLUDE_AREA_OPTION,
+    schema: list[str] = _SCHEMA_OPTION,
+    exclude_schema: list[str] = _EXCLUDE_SCHEMA_OPTION,
+) -> None:
     """Drop and recreate only this workspace's database, then reapply schema + seed data."""
-    testdb.reset_testdb()
+    testdb.reset_testdb(
+        areas=_as_set(area), exclude_areas=_as_set(exclude_area), schemas=_as_set(schema),
+        exclude_schemas=_as_set(exclude_schema),
+    )
     info = testdb.status()
     console.print(f"[green]Test DB reset:[/green] {info['database']}")
 
@@ -272,6 +308,8 @@ def migrate_check(
     ),
     area: list[str] = _AREA_OPTION,
     exclude_area: list[str] = _EXCLUDE_AREA_OPTION,
+    schema: list[str] = _SCHEMA_OPTION,
+    exclude_schema: list[str] = _EXCLUDE_SCHEMA_OPTION,
 ) -> None:
     """List which migration files under migrations_dir are applied vs. pending."""
     if not migrations_dir.is_dir():
@@ -281,7 +319,11 @@ def migrate_check(
     conninfo = build_conninfo(url, entra_user)
     tracking_table = tracking_table or migrate.default_tracking_table(migrations_dir)
     local_files = migrate.list_migration_files(
-        migrations_dir, areas=_as_area_set(area), exclude_areas=_as_area_set(exclude_area)
+        migrations_dir,
+        areas=_as_set(area),
+        exclude_areas=_as_set(exclude_area),
+        schemas=_as_set(schema),
+        exclude_schemas=_as_set(exclude_schema),
     )
     try:
         applied = migrate.applied_migrations(conninfo, tracking_table)
@@ -323,6 +365,8 @@ def migrate_apply(
     yes: bool = typer.Option(False, "--yes", "-y", help="Skip the confirm-target prompt"),
     area: list[str] = _AREA_OPTION,
     exclude_area: list[str] = _EXCLUDE_AREA_OPTION,
+    schema: list[str] = _SCHEMA_OPTION,
+    exclude_schema: list[str] = _EXCLUDE_SCHEMA_OPTION,
 ) -> None:
     """Apply pending migration files, in filename order, tracking each in tracking_table."""
     if not migrations_dir.is_dir():
@@ -331,7 +375,8 @@ def migrate_apply(
 
     conninfo = build_conninfo(url, entra_user)
     tracking_table = tracking_table or migrate.default_tracking_table(migrations_dir)
-    areas, exclude_areas = _as_area_set(area), _as_area_set(exclude_area)
+    areas, exclude_areas = _as_set(area), _as_set(exclude_area)
+    schemas, exclude_schemas = _as_set(schema), _as_set(exclude_schema)
     target_desc = url.rsplit("@", 1)[-1] if "@" in url else url
     if not yes:
         typer.confirm(f"About to run migrations against {target_desc}. Continue?", abort=True)
@@ -341,13 +386,22 @@ def migrate_apply(
     else:
         try:
             targets = migrate.pending_migrations(
-                migrations_dir, conninfo, tracking_table, areas=areas, exclude_areas=exclude_areas
+                migrations_dir,
+                conninfo,
+                tracking_table,
+                areas=areas,
+                exclude_areas=exclude_areas,
+                schemas=schemas,
+                exclude_schemas=exclude_schemas,
             )
         except migrate.TrackingTableMissing:
             err_console.print(
                 f"[yellow]⚠[/yellow]  {tracking_table} not found — treating every migration as pending"
             )
-            targets = migrate.list_migration_files(migrations_dir, areas=areas, exclude_areas=exclude_areas)
+            targets = migrate.list_migration_files(
+                migrations_dir, areas=areas, exclude_areas=exclude_areas, schemas=schemas,
+                exclude_schemas=exclude_schemas,
+            )
 
     if not targets:
         console.print("No pending migrations.")

{pgdevkit-0.4.0 → pgdevkit-0.5.0}/pgdevkit/dialect.py

@@ -43,6 +43,16 @@ _MSSQL_TYPE_SYNONYMS = {
 }
 
 
+# Schemas that hold system catalog views/tables, never a file any project
+# using pgdevkit manages -- a reference to one (e.g. an idempotency guard
+# querying it, or a `SELECT ... FROM information_schema/pg_catalog/sys ...`)
+# is never a real schema-membership or cross-file-dependency signal. Shared
+# by `schemas.py` (schema-reference filtering) and `testdb/schema.py`
+# (dependency-safe apply ordering), which both walk the same sqlglot Table
+# nodes for a related-but-different purpose.
+SYSTEM_SCHEMAS = {"pg_catalog", "information_schema", "sys"}
+
+
 @dataclass(frozen=True)
 class Dialect:
     """A thin wrapper around a sqlglot dialect name plus the handful of

{pgdevkit-0.4.0 → pgdevkit-0.5.0}/pgdevkit/migrate.py

@@ -19,6 +19,8 @@ from psycopg import errors as pg_errors
 from psycopg import sql as pg_sql
 
 from .areas import filter_by_area
+from .schemas import filter_by_schema
+from .sql_text import strip_line_comments
 
 _IDENTIFIER = r"[A-Za-z_][A-Za-z0-9_]*"
 _DEFAULT_TRACKING_TABLE = "public.schema_migrations"
@@ -124,61 +126,12 @@ def _split_sql(sql: str) -> list[str]:
     return stmts
 
 
-def _strip_line_comments(sql: str) -> str:
-    """Drop '--' line comments, respecting string literals and $$...$$ blocks."""
-    buf: list[str] = []
-    i = 0
-    in_string = False
-    in_line_comment = False
-    dollar_tag: str | None = None
-
-    while i < len(sql):
-        c = sql[i]
-        if in_line_comment:
-            if c == "\n":
-                in_line_comment = False
-                buf.append(c)
-        elif dollar_tag is not None:
-            buf.append(c)
-            if c == "$" and sql[i:i + len(dollar_tag)] == dollar_tag:
-                buf.extend(list(dollar_tag[1:]))
-                i += len(dollar_tag)
-                dollar_tag = None
-                continue
-        elif in_string:
-            if c == "'" and i + 1 < len(sql) and sql[i + 1] == "'":
-                buf.append(c)
-                buf.append(sql[i + 1])
-                i += 2
-                continue
-            elif c == "'":
-                in_string = False
-            buf.append(c)
-        elif c == "-" and i + 1 < len(sql) and sql[i + 1] == "-":
-            in_line_comment = True
-        elif c == "$":
-            m = re.match(r"\$([A-Za-z0-9_]*)\$", sql[i:])
-            if m:
-                dollar_tag = m.group(0)
-                buf.extend(list(dollar_tag))
-                i += len(dollar_tag)
-                continue
-            buf.append(c)
-        elif c == "'":
-            in_string = True
-            buf.append(c)
-        else:
-            buf.append(c)
-        i += 1
-    return "".join(buf)
-
-
 def _created_table_names(stmts: list[str]) -> list[str]:
     """Names of tables any CREATE TABLE statement targets, parsed via sqlglot (falls back to
     regex on comment-stripped text for statements sqlglot's postgres dialect can't parse)."""
     names: list[str] = []
     for stmt in stmts:
-        stripped = _strip_line_comments(stmt)
+        stripped = strip_line_comments(stmt)
         if not re.search(r"CREATE\s+TABLE", stripped, re.IGNORECASE):
             continue  # skip sqlglot entirely for statements that can't be a CREATE TABLE
         try:
@@ -220,7 +173,7 @@ def _idempotent_target(stmt: str) -> tuple[str, ...] | None:
     COLUMN. None if the statement isn't one of these shapes — including any CREATE OR
     REPLACE, which is never safe to treat as a no-op just because the object exists, since
     the migration could be replacing it with different content."""
-    stripped = _strip_line_comments(stmt).strip()
+    stripped = strip_line_comments(stmt).strip()
     if re.search(r"\bOR\s+REPLACE\b", stripped, re.IGNORECASE):
         return None
 
@@ -281,9 +234,12 @@ def list_migration_files(
     *,
     areas: frozenset[str] | None = None,
     exclude_areas: frozenset[str] | None = None,
+    schemas: frozenset[str] | None = None,
+    exclude_schemas: frozenset[str] | None = None,
 ) -> list[Path]:
     files = sorted(migrations_dir.glob("*.sql"))
-    return filter_by_area(files, only=areas, exclude=exclude_areas)
+    files = filter_by_area(files, only=areas, exclude=exclude_areas)
+    return filter_by_schema(files, only=schemas, exclude=exclude_schemas)
 
 
 def applied_migrations(conninfo: str, tracking_table: str) -> dict[str, tuple[datetime, str]]:
@@ -306,9 +262,13 @@ def pending_migrations(
     *,
     areas: frozenset[str] | None = None,
     exclude_areas: frozenset[str] | None = None,
+    schemas: frozenset[str] | None = None,
+    exclude_schemas: frozenset[str] | None = None,
 ) -> list[Path]:
     applied = applied_migrations(conninfo, tracking_table)
-    files = list_migration_files(migrations_dir, areas=areas, exclude_areas=exclude_areas)
+    files = list_migration_files(
+        migrations_dir, areas=areas, exclude_areas=exclude_areas, schemas=schemas, exclude_schemas=exclude_schemas
+    )
     return [p for p in files if p.name not in applied]
 
 

{pgdevkit-0.4.0 → pgdevkit-0.5.0}/pgdevkit/parser.py

@@ -10,6 +10,7 @@ import sqlglot.expressions as exp
 
 from .areas import area_allowed, parse_areas
 from .dialect import Dialect, POSTGRES, resolve_dialect
+from .schemas import schema_allowed, sql_schemas
 from .models import (
     ColumnDef, ConstraintDef, CompositeTypeDef, DatabaseSchema,
     EnumDef, FunctionDef, IndexDef, TableDef, ViewDef,
@@ -55,15 +56,21 @@ def parse_directory(
     dialect: str | Dialect = "postgres",
     areas: frozenset[str] | None = None,
     exclude_areas: frozenset[str] | None = None,
+    schemas: frozenset[str] | None = None,
+    exclude_schemas: frozenset[str] | None = None,
 ) -> DatabaseSchema:
     resolved = resolve_dialect(dialect)
     db_schema = DatabaseSchema()
     for sql_file in sorted(_iter_sql_files(scripts_dir)):
-        # Read once and reuse for both the area check and parsing, rather than
-        # filtering the file list up front (which would need its own read).
+        # Read once and reuse for the area/schema checks and parsing, rather
+        # than filtering the file list up front (which would need its own read).
         content = sql_file.read_text(encoding="utf-8")
         if (areas or exclude_areas) and not area_allowed(parse_areas(content), only=areas, exclude=exclude_areas):
             continue
+        if (schemas or exclude_schemas) and not schema_allowed(
+            sql_schemas(content, resolved), only=schemas, exclude=exclude_schemas
+        ):
+            continue
         _parse_file(sql_file, db_schema, resolved, content=content)
     return db_schema