pgdevkit 0.2.4__tar.gz → 0.3.0__tar.gz

pgdevkit-0.3.0/.github/workflows/python-test.yml

@@ -0,0 +1,56 @@
+name: Python Test
+
+on:
+  push:
+    branches: ["main"]
+    paths-ignore: ["README.md", "docs", ".github"]
+  pull_request:
+    branches: ["main"]
+    paths-ignore: ["README.md", "docs", ".github"]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.14"]
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install uv
+        run: curl -LsSf https://astral.sh/uv/install.sh | sh
+      - name: Install project dependencies
+        run: uv sync --all-extras --all-groups
+      - name: ty check
+        run: uv run ty check pgdevkit
+      - name: Test with pytest
+        run: uv run -m pytest --capture=tee-sys --maxfail=3 -m "not mssql" tests
+
+  mssql-test:
+    # Separate job (not folded into `build`) so a live SQL Server -- a much
+    # larger image and slower cold start than the Postgres container --
+    # never slows down or blocks the fast, always-run Postgres suite above.
+    # mssql-python bundles its own ODBC driver, so unlike pyodbc this needs
+    # no system driver package install here.
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+      - name: Set up Python 3.14
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.14"
+      - name: Install uv
+        run: curl -LsSf https://astral.sh/uv/install.sh | sh
+      - name: Install project dependencies
+        run: uv sync --all-extras --all-groups
+      - name: Run MSSQL-only tests
+        run: uv run -m pytest --capture=tee-sys --maxfail=3 -m mssql tests

{pgdevkit-0.2.4 → pgdevkit-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pgdevkit
-Version: 0.2.4
+Version: 0.3.0
 Summary: A helper for developing with Postgres
 Requires-Python: >=3.14
 Requires-Dist: docker>=7.1.0
@@ -14,6 +14,8 @@ Requires-Dist: typer>=0.26.7; extra == 'cli'
 Provides-Extra: db
 Requires-Dist: psycopg-pool>=3.3.0; extra == 'db'
 Requires-Dist: pydantic>=2.0; extra == 'db'
+Provides-Extra: mssql
+Requires-Dist: mssql-python>=1.0.0; extra == 'mssql'
 Description-Content-Type: text/markdown
 
 # pgdevkit
@@ -56,6 +58,26 @@ pgdb compare --url postgresql://instance-abc.database.azuredatabricks.net:5432/d
 (`--url`'s own user/password, if any, are discarded and replaced — `--entra-user`
 plus the fetched token become the connection's actual credentials.)
 
+### MSSQL
+
+`pgdb compare`/`pgdb fetch-missing` default to Postgres. Pass `--dialect mssql`
+to compare against a SQL Server database instead:
+
+```bash
+pgdb compare --dialect mssql --url "Server=host,1433;Database=db;UID=user;PWD=pass" path/to/database/
+```
+
+Requires the `mssql` extra: `pip install pgdevkit[mssql]` (pulls in
+[mssql-python](https://github.com/microsoft/mssql-python), which bundles its
+own driver — no system ODBC driver install needed). MSSQL has no composite
+type or native enum equivalent, so those areas of a `database/` tree don't
+have a direct equivalent on this backend — see `docs/database-layout.md`.
+Current Azure SQL/SQL Server (2025+) does have a native `json` column type,
+which parses/introspects/diffs like any other column type; see
+"`pgdevkit.db` — helpers for application code" below for how JSON values are
+handled on the CRUD side (write-side serialization only, no auto-parsing on
+read — `mssql-python` doesn't distinguish `json` columns from `nvarchar`).
+
 ## `pgdb testdb`
 
 Manages a single shared, Podman-backed Postgres container for local tests
@@ -107,12 +129,29 @@ The role named by `PGDEVKIT_TESTDB_USER` must exist and match your OS user
 (`CREATE ROLE <user> SUPERUSER LOGIN;`) and `pg_hba.conf` must allow `peer`
 auth for local connections (Debian/Ubuntu Postgres ships this by default).
 
+### MSSQL
+
+Add `engine = "mssql"` to `[tool.pgdevkit]` (or set
+`PGDEVKIT_TESTDB_ENGINE=mssql` for a one-off run) to manage a shared SQL
+Server container instead of Postgres — same one-container-per-machine,
+one-database-per-workspace model. Requires the `mssql` extra (see above).
+
+Container defaults (`localhost:14330`, `sa`/a generated complexity-valid
+password) can be overridden with `PGDEVKIT_TESTDB_MSSQL_HOST`, `_PORT`,
+`_USER`, `_PASSWORD`, `_IMAGE`, `_MEMORY_LIMIT_MB`. The container only
+bootstraps the `sa` login — additional logins are a known limitation.
+`pgdb testdb shell` execs into
+[`sqlcmd`](https://github.com/microsoft/go-sqlcmd) (an external prerequisite,
+the same category as `psql` for the Postgres path) rather than a Python
+REPL.
+
 ## `pgdevkit.db` — helpers for application code
 
 Install with the `db` extra: `pip install pgdevkit[db]`.
 
-- **`PostgresTableModel`** — a `pydantic.BaseModel` base class for models
-  that map 1:1 to a table row. Implement `get_table_name()` (returns
+- **`TableModel`** (formerly `PostgresTableModel`, still importable under
+  that name) — a `pydantic.BaseModel` base class for models that map 1:1 to
+  a table row, for either engine. Implement `get_table_name()` (returns
   `(schema, table)`) and `get_primary_key()` on each model.
 - **`PgPool`** — an async connection pool keyed off
   `{env_prefix}HOST/PORT/DB/USER/PASSWORD` env vars. Call `await pool.open()`
@@ -125,8 +164,21 @@ Install with the `db` extra: `pip install pgdevkit[db]`.
 - **CRUD functions** — `pg_retrieve`, `pg_retrieve_many`, `pg_insert`,
   `pg_insert_many`, `pg_update`, `pg_update_dict`, `pg_upsert`,
   `pg_upsert_dict`, `pg_upsert_many`, `pg_upsert_many_dict`, `pg_delete`,
-  `pg_delete_dict` — typed (`PostgresTableModel`-based) or dict-based CRUD
-  against a table, built on `psycopg` for safe identifier/value handling.
+  `pg_delete_dict` — typed (`TableModel`-based) or dict-based CRUD against a
+  table, built on `psycopg` for safe identifier/value handling. The `mssql`
+  extra provides an `mssql_*`-prefixed mirror of the same functions in
+  `pgdevkit.db.mssql_crud`, built on `mssql-python` (`MERGE`-based upsert,
+  `OUTPUT` instead of `RETURNING`) — MSSQL has no composite/enum equivalent,
+  so `complex_helper` is always `None` on that path. It does have a native
+  `json` column type on current versions (and the older
+  `NVARCHAR(MAX)`-plus-`OPENJSON()` convention works on any version), but
+  `mssql-python` has no auto-serialization for dict/list parameter values
+  (binding one raises `TypeError`) and no way to distinguish a `json`
+  column from `nvarchar` on fetch — so every `mssql_*` write function
+  serializes dict/list values to JSON text automatically
+  (`db.mssql_sql.json_encode_value`), while reads always come back as plain
+  `str`; deserialize with `json.loads()` yourself if you need the parsed
+  value back.
 - **`SqlLoader`** — loads and caches `.sql` files from
   `{root}/<topic>/<name>.sql`, for keeping hand-written queries out of
   Python source.

{pgdevkit-0.2.4 → pgdevkit-0.3.0}/README.md

@@ -38,6 +38,26 @@ pgdb compare --url postgresql://instance-abc.database.azuredatabricks.net:5432/d
 (`--url`'s own user/password, if any, are discarded and replaced — `--entra-user`
 plus the fetched token become the connection's actual credentials.)
 
+### MSSQL
+
+`pgdb compare`/`pgdb fetch-missing` default to Postgres. Pass `--dialect mssql`
+to compare against a SQL Server database instead:
+
+```bash
+pgdb compare --dialect mssql --url "Server=host,1433;Database=db;UID=user;PWD=pass" path/to/database/
+```
+
+Requires the `mssql` extra: `pip install pgdevkit[mssql]` (pulls in
+[mssql-python](https://github.com/microsoft/mssql-python), which bundles its
+own driver — no system ODBC driver install needed). MSSQL has no composite
+type or native enum equivalent, so those areas of a `database/` tree don't
+have a direct equivalent on this backend — see `docs/database-layout.md`.
+Current Azure SQL/SQL Server (2025+) does have a native `json` column type,
+which parses/introspects/diffs like any other column type; see
+"`pgdevkit.db` — helpers for application code" below for how JSON values are
+handled on the CRUD side (write-side serialization only, no auto-parsing on
+read — `mssql-python` doesn't distinguish `json` columns from `nvarchar`).
+
 ## `pgdb testdb`
 
 Manages a single shared, Podman-backed Postgres container for local tests
@@ -89,12 +109,29 @@ The role named by `PGDEVKIT_TESTDB_USER` must exist and match your OS user
 (`CREATE ROLE <user> SUPERUSER LOGIN;`) and `pg_hba.conf` must allow `peer`
 auth for local connections (Debian/Ubuntu Postgres ships this by default).
 
+### MSSQL
+
+Add `engine = "mssql"` to `[tool.pgdevkit]` (or set
+`PGDEVKIT_TESTDB_ENGINE=mssql` for a one-off run) to manage a shared SQL
+Server container instead of Postgres — same one-container-per-machine,
+one-database-per-workspace model. Requires the `mssql` extra (see above).
+
+Container defaults (`localhost:14330`, `sa`/a generated complexity-valid
+password) can be overridden with `PGDEVKIT_TESTDB_MSSQL_HOST`, `_PORT`,
+`_USER`, `_PASSWORD`, `_IMAGE`, `_MEMORY_LIMIT_MB`. The container only
+bootstraps the `sa` login — additional logins are a known limitation.
+`pgdb testdb shell` execs into
+[`sqlcmd`](https://github.com/microsoft/go-sqlcmd) (an external prerequisite,
+the same category as `psql` for the Postgres path) rather than a Python
+REPL.
+
 ## `pgdevkit.db` — helpers for application code
 
 Install with the `db` extra: `pip install pgdevkit[db]`.
 
-- **`PostgresTableModel`** — a `pydantic.BaseModel` base class for models
-  that map 1:1 to a table row. Implement `get_table_name()` (returns
+- **`TableModel`** (formerly `PostgresTableModel`, still importable under
+  that name) — a `pydantic.BaseModel` base class for models that map 1:1 to
+  a table row, for either engine. Implement `get_table_name()` (returns
   `(schema, table)`) and `get_primary_key()` on each model.
 - **`PgPool`** — an async connection pool keyed off
   `{env_prefix}HOST/PORT/DB/USER/PASSWORD` env vars. Call `await pool.open()`
@@ -107,8 +144,21 @@ Install with the `db` extra: `pip install pgdevkit[db]`.
 - **CRUD functions** — `pg_retrieve`, `pg_retrieve_many`, `pg_insert`,
   `pg_insert_many`, `pg_update`, `pg_update_dict`, `pg_upsert`,
   `pg_upsert_dict`, `pg_upsert_many`, `pg_upsert_many_dict`, `pg_delete`,
-  `pg_delete_dict` — typed (`PostgresTableModel`-based) or dict-based CRUD
-  against a table, built on `psycopg` for safe identifier/value handling.
+  `pg_delete_dict` — typed (`TableModel`-based) or dict-based CRUD against a
+  table, built on `psycopg` for safe identifier/value handling. The `mssql`
+  extra provides an `mssql_*`-prefixed mirror of the same functions in
+  `pgdevkit.db.mssql_crud`, built on `mssql-python` (`MERGE`-based upsert,
+  `OUTPUT` instead of `RETURNING`) — MSSQL has no composite/enum equivalent,
+  so `complex_helper` is always `None` on that path. It does have a native
+  `json` column type on current versions (and the older
+  `NVARCHAR(MAX)`-plus-`OPENJSON()` convention works on any version), but
+  `mssql-python` has no auto-serialization for dict/list parameter values
+  (binding one raises `TypeError`) and no way to distinguish a `json`
+  column from `nvarchar` on fetch — so every `mssql_*` write function
+  serializes dict/list values to JSON text automatically
+  (`db.mssql_sql.json_encode_value`), while reads always come back as plain
+  `str`; deserialize with `json.loads()` yourself if you need the parsed
+  value back.
 - **`SqlLoader`** — loads and caches `.sql` files from
   `{root}/<topic>/<name>.sql`, for keeping hand-written queries out of
   Python source.

{pgdevkit-0.2.4 → pgdevkit-0.3.0}/docs/database-layout.md

@@ -121,6 +121,21 @@ comment on column dim.user.is_active is 'False once a user is soft-deleted; keep
 
 ---
 
+## MSSQL projects (`engine = "mssql"`)
+
+Everything above is engine-agnostic *as a folder/apply-order convention*,
+with two exceptions:
+
+- `types/` (custom types / enums) has no direct T-SQL equivalent -- MSSQL
+  has neither a native enum type nor composite types, so a `CREATE TYPE ...
+  AS ENUM`/composite `.sql` file is a Postgres-only construct. `pgdb compare`
+  reports every such object as missing on an MSSQL database (correctly --
+  it genuinely doesn't exist there), rather than erroring.
+- T-SQL scripts conventionally separate batches with a standalone `GO` line
+  (an `sqlcmd`/SSMS scripting convention, not valid inside a single
+  driver `execute()` call). `pgdb testdb` splits on these automatically when
+  applying a file; hand-written `.sql` files may use `GO` freely.
+
 ## Backfilling untracked objects
 
 If a table, scalar function, or table function was created directly on the

pgdevkit-0.3.0/pgdevkit/backends/__init__.py

@@ -0,0 +1,21 @@
+from __future__ import annotations
+
+from ..dialect import Dialect, resolve_dialect
+from .base import Backend
+from .mssql import MssqlBackend
+from .postgres import PostgresBackend
+
+_REGISTRY: dict[str, Backend] = {
+    "postgres": PostgresBackend(),
+    "mssql": MssqlBackend(),
+}
+
+
+def get_backend(dialect: str | Dialect = "postgres") -> Backend:
+    """Look up the `Backend` for a dialect name (or an already-resolved
+    `Dialect`). Defaults to postgres."""
+    resolved = resolve_dialect(dialect)
+    return _REGISTRY[resolved.name]
+
+
+__all__ = ["Backend", "MssqlBackend", "PostgresBackend", "get_backend"]

pgdevkit-0.3.0/pgdevkit/backends/base.py

@@ -0,0 +1,27 @@
+from __future__ import annotations
+
+from typing import Any, Callable, Protocol
+
+from ..dialect import Dialect
+from ..models import DatabaseSchema
+
+
+class Backend(Protocol):
+    """Introspection + a couple of engine facts, behind one interface.
+
+    CRUD is deliberately NOT part of this protocol -- psycopg's
+    `AsyncConnection` and an MSSQL driver's connection type are unrelated,
+    so a unified `backend.retrieve()`/`backend.insert()` surface would force
+    existing Postgres callers to go through a new indirection just to keep
+    working. Callers that want CRUD import `pgdevkit.db.crud`'s `pg_*`
+    functions or `pgdevkit.db.mssql_crud`'s `mssql_*` functions directly,
+    exactly as `db/crud.py`'s functions are imported today."""
+
+    dialect: Dialect
+
+    def introspect(self, conninfo: str) -> DatabaseSchema: ...
+
+    def complex_helper_factory(self) -> Callable[..., Any] | None:
+        """A `ComplexHelper`-like factory for composite/enum/JSONB columns,
+        or None when the engine has no equivalent (MSSQL)."""
+        ...

pgdevkit-0.3.0/pgdevkit/backends/mssql.py

@@ -0,0 +1,27 @@
+from __future__ import annotations
+
+from typing import Any, Callable
+
+from ..dialect import MSSQL, Dialect
+from ..models import DatabaseSchema
+
+
+class MssqlBackend:
+    dialect: Dialect = MSSQL
+
+    def introspect(self, conninfo: str) -> DatabaseSchema:
+        # Imported lazily so `import pgdevkit.backends` (and thus
+        # `pgdevkit.cli`) doesn't require mssql-python/the mssql extra to
+        # be installed unless a caller actually asks for the mssql backend.
+        from ..mssql_introspect import introspect_mssql_db
+
+        return introspect_mssql_db(conninfo)
+
+    def complex_helper_factory(self) -> Callable[..., Any] | None:
+        # MSSQL has no composite type, native enum, or first-class JSONB
+        # column type -- there is nothing for a ComplexHelper to adapt.
+        # Every `complex_helper` parameter in db/crud.py (and its
+        # db/mssql_crud.py counterpart) is already Optional, so callers on
+        # this backend simply pass/receive None and every complex-type
+        # branch takes its existing no-op path.
+        return None

pgdevkit-0.3.0/pgdevkit/backends/postgres.py

@@ -0,0 +1,19 @@
+from __future__ import annotations
+
+from typing import Any, Callable
+
+from ..dialect import POSTGRES, Dialect
+from ..introspect import introspect_db
+from ..models import DatabaseSchema
+
+
+class PostgresBackend:
+    dialect: Dialect = POSTGRES
+
+    def introspect(self, conninfo: str) -> DatabaseSchema:
+        return introspect_db(conninfo)
+
+    def complex_helper_factory(self) -> Callable[..., Any] | None:
+        from ..db.complex_types import ComplexHelper
+
+        return ComplexHelper

{pgdevkit-0.2.4 → pgdevkit-0.3.0}/pgdevkit/cli.py

@@ -10,10 +10,10 @@ from rich.table import Table
 from rich import box
 
 from . import testdb
+from .backends import get_backend
 from .connection import build_conninfo
 from .diff import DiffKind, compute_diff
 from .fetch_missing import SUBFOLDER, find_missing_objects, layer_folder_for, reconstruct_ddl
-from .introspect import introspect_db
 from .parser import parse_directory
 
 app = typer.Typer(name="pgdb", help="PostgreSQL database schema tools")
@@ -37,9 +37,10 @@ def compare(
         None, "--databricks-instance", help="Lakebase instance name (required for Lakebase hosts)"
     ),
     report_extra_db: bool = typer.Option(False, "--report-extra-db", help="Report objects in DB but not in scripts"),
+    dialect: str = typer.Option("postgres", "--dialect", help="postgres (default) or mssql"),
     scripts_dir: Path = typer.Argument(..., help="Directory containing SQL scripts"),
 ) -> None:
-    """Compare SQL scripts to a live PostgreSQL database and report differences."""
+    """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)
@@ -55,13 +56,19 @@ def compare(
         err_console.print(f"[red]Error:[/red] {e}")
         raise typer.Exit(2)
 
+    try:
+        backend = get_backend(dialect)
+    except ValueError as e:
+        err_console.print(f"[red]Error:[/red] {e}")
+        raise typer.Exit(2)
+
     with console.status("Parsing SQL scripts..."):
-        scripts_schema = parse_directory(scripts_dir)
+        scripts_schema = parse_directory(scripts_dir, dialect=backend.dialect)
 
     with console.status("Introspecting database..."):
-        db_schema = introspect_db(conninfo)
+        db_schema = backend.introspect(conninfo)
 
-    diffs = compute_diff(scripts_schema, db_schema, report_extra_db=report_extra_db)
+    diffs = compute_diff(scripts_schema, db_schema, report_extra_db=report_extra_db, dialect=backend.dialect)
 
     if not diffs:
         console.print("[green]No differences found.[/green]")
@@ -204,8 +211,10 @@ def testdb_status() -> None:
 
 @testdb_app.command("shell")
 def testdb_shell() -> None:
-    """Drop into psql against this workspace's database."""
-    os.execvp("psql", ["psql", testdb.dsn_for()])
+    """Drop into an interactive shell (psql, or sqlcmd for MSSQL) against
+    this workspace's database."""
+    binary, argv = testdb.shell_argv()
+    os.execvp(binary, argv)
 
 
 @testdb_app.command("clean")

{pgdevkit-0.2.4 → pgdevkit-0.3.0}/pgdevkit/db/__init__.py

@@ -17,13 +17,14 @@ from .crud import (
     pg_upsert_many_dict,
 )
 from .loader import SqlLoader
-from .model import PostgresTableModel
+from .model import PostgresTableModel, TableModel
 
 __all__ = [
     "ComplexHelper",
     "PgPool",
     "PostgresTableModel",
     "SqlLoader",
+    "TableModel",
     "pg_delete",
     "pg_delete_dict",
     "pg_insert",

{pgdevkit-0.2.4 → pgdevkit-0.3.0}/pgdevkit/db/model.py

@@ -6,8 +6,10 @@ from typing import Sequence
 from pydantic import BaseModel
 
 
-class PostgresTableModel(BaseModel, ABC):
-    """Base class for models that map 1:1 to a database table/row.
+class TableModel(BaseModel, ABC):
+    """Base class for models that map 1:1 to a database table/row (any
+    engine -- schema/table naming is equally meaningful for Postgres and
+    MSSQL, this base class was never actually Postgres-specific).
 
     Models representing partial results (joins, aggregations, projections)
     should extend `pydantic.BaseModel` directly instead."""
@@ -21,3 +23,8 @@ class PostgresTableModel(BaseModel, ABC):
     @abstractmethod
     def get_primary_key() -> Sequence[str]:
         """Return the primary key column name(s)."""
+
+
+# Backward-compat alias -- this class was named PostgresTableModel before
+# MSSQL support existed; kept so existing imports keep working unchanged.
+PostgresTableModel = TableModel