codemap-sql 0.1.0a1__tar.gz

codemap_sql-0.1.0a1/.gitignore

@@ -0,0 +1,43 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Build artifacts
+build/
+dist/
+*.egg-info/
+*.egg
+.eggs/
+
+# Test / coverage
+.pytest_cache/
+.coverage
+.coverage.*
+htmlcov/
+coverage.xml
+.tox/
+.mypy_cache/
+.ruff_cache/
+.benchmarks/
+
+# Virtualenv
+.venv/
+venv/
+env/
+
+# uv / pdm lockfiles (commit uv.lock once we settle)
+# uv.lock
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# OS
+.DS_Store
+Thumbs.db
+
+# CodeMap own index when dogfooding
+.codemap/

codemap_sql-0.1.0a1/PKG-INFO

@@ -0,0 +1,73 @@
+Metadata-Version: 2.4
+Name: codemap-sql
+Version: 0.1.0a1
+Summary: SQL indexer plugin for CodeMap
+Project-URL: Homepage, https://github.com/qxbyte/codemap
+Author: CodeMap Contributors
+License: MIT
+Keywords: codemap,indexer,sql,tree-sitter
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: SQL
+Classifier: Topic :: Database
+Classifier: Topic :: Software Development
+Requires-Python: >=3.11
+Requires-Dist: codemap-core<0.2,>=0.1.0a1
+Requires-Dist: tree-sitter-sql>=0.3
+Requires-Dist: tree-sitter>=0.25
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# codemap-sql
+
+> A SQL indexer for [CodeMap](https://github.com/qxbyte/codemap), shipped
+> as an independent PyPI package.
+
+Indexes DDL (schema) statements so AI agents can answer "which table has
+column X" and similar structural questions without scanning every
+migration file. Query (`SELECT`/`INSERT`/...) statements are ignored —
+they are not durable schema artefacts.
+
+## What it captures
+
+Backed by `tree-sitter-sql`:
+
+| AST node | Symbol kind |
+|---|---|
+| `create_table` | `class` (with `extra.sql_kind=table`) |
+| `create_view` | `class` (with `extra.sql_kind=view`) |
+| `create_index` | `variable` (with `extra.sql_kind=index`) |
+| `column_definition` inside `create_table` | `field` (attached to the table) |
+
+Asset-style scheme: this plugin uses ``scip-sql`` so a downstream
+``http_route`` / ``orm_mapping`` bridge can cross-reference these
+symbols against application code that talks to them.
+
+## SymbolID encoding
+
+```
+scip-sql . . . db/migrations/0001_init.sql/users#
+scip-sql . . . db/migrations/0001_init.sql/users#email.
+scip-sql . . . db/migrations/0001_init.sql/idx_users_email.
+```
+
+## Install
+
+```bash
+pip install "git+https://github.com/qxbyte/codemap.git#subdirectory=plugins/codemap-sql"
+```
+
+## Limits
+
+* Only DDL is indexed; `SELECT` / `INSERT` / `UPDATE` / `DELETE` are
+  walked past silently.
+* `CREATE PROCEDURE` / `CREATE FUNCTION` / `CREATE TRIGGER` are not
+  yet captured — the grammar reports them under generic statement nodes.
+* Dialect-specific features (e.g. PostgreSQL extensions) may not be
+  parsed.
+* `ALTER TABLE` statements that add columns are not tracked.
+
+## License
+
+MIT.

codemap_sql-0.1.0a1/README.md

@@ -0,0 +1,52 @@
+# codemap-sql
+
+> A SQL indexer for [CodeMap](https://github.com/qxbyte/codemap), shipped
+> as an independent PyPI package.
+
+Indexes DDL (schema) statements so AI agents can answer "which table has
+column X" and similar structural questions without scanning every
+migration file. Query (`SELECT`/`INSERT`/...) statements are ignored —
+they are not durable schema artefacts.
+
+## What it captures
+
+Backed by `tree-sitter-sql`:
+
+| AST node | Symbol kind |
+|---|---|
+| `create_table` | `class` (with `extra.sql_kind=table`) |
+| `create_view` | `class` (with `extra.sql_kind=view`) |
+| `create_index` | `variable` (with `extra.sql_kind=index`) |
+| `column_definition` inside `create_table` | `field` (attached to the table) |
+
+Asset-style scheme: this plugin uses ``scip-sql`` so a downstream
+``http_route`` / ``orm_mapping`` bridge can cross-reference these
+symbols against application code that talks to them.
+
+## SymbolID encoding
+
+```
+scip-sql . . . db/migrations/0001_init.sql/users#
+scip-sql . . . db/migrations/0001_init.sql/users#email.
+scip-sql . . . db/migrations/0001_init.sql/idx_users_email.
+```
+
+## Install
+
+```bash
+pip install "git+https://github.com/qxbyte/codemap.git#subdirectory=plugins/codemap-sql"
+```
+
+## Limits
+
+* Only DDL is indexed; `SELECT` / `INSERT` / `UPDATE` / `DELETE` are
+  walked past silently.
+* `CREATE PROCEDURE` / `CREATE FUNCTION` / `CREATE TRIGGER` are not
+  yet captured — the grammar reports them under generic statement nodes.
+* Dialect-specific features (e.g. PostgreSQL extensions) may not be
+  parsed.
+* `ALTER TABLE` statements that add columns are not tracked.
+
+## License
+
+MIT.

codemap_sql-0.1.0a1/pyproject.toml

@@ -0,0 +1,37 @@
+[build-system]
+requires = ["hatchling>=1.21"]
+build-backend = "hatchling.build"
+
+[project]
+name = "codemap-sql"
+version = "0.1.0a1"
+description = "SQL indexer plugin for CodeMap"
+readme = "README.md"
+requires-python = ">=3.11"
+license = { text = "MIT" }
+authors = [{ name = "CodeMap Contributors" }]
+keywords = ["codemap", "sql", "indexer", "tree-sitter"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: SQL",
+    "Topic :: Software Development",
+    "Topic :: Database",
+]
+dependencies = [
+    "codemap-core>=0.1.0a1,<0.2",
+    "tree-sitter>=0.25",
+    "tree-sitter-sql>=0.3",
+]
+
+[project.optional-dependencies]
+dev = ["pytest>=8.0"]
+
+[project.entry-points."codemap.indexers"]
+sql = "codemap_sql:SqlIndexer"
+
+[project.urls]
+Homepage = "https://github.com/qxbyte/codemap"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/codemap_sql"]

codemap_sql-0.1.0a1/src/codemap_sql/__init__.py

@@ -0,0 +1,8 @@
+"""SQL indexer plugin for CodeMap."""
+
+from __future__ import annotations
+
+from codemap_sql.indexer import SqlIndexer
+
+__all__ = ["SqlIndexer"]
+__version__ = "0.1.0"

codemap_sql-0.1.0a1/src/codemap_sql/indexer.py

@@ -0,0 +1,236 @@
+"""SQL indexer built on tree-sitter-sql.
+
+Only DDL statements (CREATE TABLE / VIEW / INDEX) produce symbols. The
+table column list is walked to emit field symbols attached to the
+parent table, so callers can answer "which table has column X" and the
+http_route / asset bridges can cross-reference application code against
+schema state.
+
+Query statements (SELECT / INSERT / UPDATE / DELETE) are intentionally
+ignored — they are not durable schema artefacts.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path, PurePosixPath
+from typing import ClassVar
+
+import tree_sitter
+import tree_sitter_sql
+
+from codemap.core.models import Diagnostic, Edge, IndexResult, Range, Symbol
+from codemap.core.symbol import Descriptor, DescriptorKind, SymbolID
+from codemap.indexers.base import IndexContext
+
+SCHEME = "scip-sql"
+LANG = "sql"
+
+_SQL_LANG = tree_sitter.Language(tree_sitter_sql.language())
+
+
+class SqlIndexer:
+    name: ClassVar[str] = "sql"
+    version: ClassVar[str] = "0.1.0"
+    file_patterns: ClassVar[list[str]] = ["*.sql", "*.ddl"]
+    languages: ClassVar[list[str]] = [LANG]
+
+    def supports(self, path: Path) -> bool:
+        return path.suffix in {".sql", ".ddl"}
+
+    def index_file(
+        self,
+        path: Path,
+        source: bytes,
+        ctx: IndexContext,
+    ) -> IndexResult:
+        try:
+            source.decode("utf-8")
+        except UnicodeDecodeError as exc:
+            return IndexResult(
+                diagnostics=[
+                    Diagnostic(
+                        severity="error",
+                        file=ctx.relative_path,
+                        code="SQL002",
+                        message=f"not valid UTF-8: {exc}",
+                        producer=self.name,
+                    )
+                ]
+            )
+        parser = tree_sitter.Parser(_SQL_LANG)
+        tree = parser.parse(source)
+        visitor = _Visitor(ctx.relative_path)
+        visitor.visit(tree.root_node)
+        diagnostics = list(visitor.diagnostics)
+        if tree.root_node.has_error:
+            diagnostics.append(
+                Diagnostic(
+                    severity="warning",
+                    file=ctx.relative_path,
+                    range=Range(start_line=1, end_line=1),
+                    code="SQL001",
+                    message="tree-sitter reported parse errors; symbols may be incomplete",
+                    producer=self.name,
+                )
+            )
+        return IndexResult(
+            symbols=visitor.symbols,
+            edges=visitor.edges,
+            diagnostics=diagnostics,
+        )
+
+
+class _Visitor:
+    def __init__(self, relative_path: PurePosixPath) -> None:
+        self.relative_path = relative_path
+        self.symbols: list[Symbol] = []
+        self.edges: list[Edge] = []
+        self.diagnostics: list[Diagnostic] = []
+
+    def visit(self, node: tree_sitter.Node) -> None:
+        kind = node.type
+        if kind == "create_table":
+            self._visit_create_table(node)
+            return
+        if kind == "create_view":
+            self._visit_create_view(node)
+            return
+        if kind == "create_index":
+            self._visit_create_index(node)
+            return
+        for child in node.children:
+            self.visit(child)
+
+    # -------------------------------------------------------- types
+
+    def _visit_create_table(self, node: tree_sitter.Node) -> None:
+        name = _object_name(node)
+        if name is None:
+            return
+        sid = self._make_id([], name, kind=DescriptorKind.TYPE)
+        self.symbols.append(
+            Symbol(
+                id=sid,
+                kind="class",
+                language=LANG,
+                file=self.relative_path,
+                range=_node_range(node),
+                extra={"sql_kind": "table"},
+            )
+        )
+        # Walk column_definitions for column names.
+        for child in node.children:
+            if child.type != "column_definitions":
+                continue
+            for sub in child.children:
+                if sub.type == "column_definition":
+                    self._emit_column(name, sub)
+
+    def _emit_column(self, table_name: str, node: tree_sitter.Node) -> None:
+        col_name = None
+        for child in node.children:
+            if child.type == "identifier":
+                col_name = _node_text(child)
+                break
+        if not col_name:
+            return
+        sid = self._make_id([table_name], col_name, kind=DescriptorKind.TERM)
+        self.symbols.append(
+            Symbol(
+                id=sid,
+                kind="field",
+                language=LANG,
+                file=self.relative_path,
+                range=_node_range(node),
+            )
+        )
+
+    def _visit_create_view(self, node: tree_sitter.Node) -> None:
+        name = _object_name(node)
+        if name is None:
+            return
+        sid = self._make_id([], name, kind=DescriptorKind.TYPE)
+        self.symbols.append(
+            Symbol(
+                id=sid,
+                kind="class",
+                language=LANG,
+                file=self.relative_path,
+                range=_node_range(node),
+                extra={"sql_kind": "view"},
+            )
+        )
+
+    def _visit_create_index(self, node: tree_sitter.Node) -> None:
+        # create_index > identifier (index name) is the first identifier.
+        name = None
+        for child in node.children:
+            if child.type == "identifier":
+                name = _node_text(child)
+                break
+        if name is None:
+            return
+        sid = self._make_id([], name, kind=DescriptorKind.TERM)
+        self.symbols.append(
+            Symbol(
+                id=sid,
+                kind="variable",
+                language=LANG,
+                file=self.relative_path,
+                range=_node_range(node),
+                extra={"sql_kind": "index"},
+            )
+        )
+
+    # ---------------------------------------------------- helpers
+
+    def _make_id(
+        self,
+        type_chain: list[str],
+        name: str,
+        *,
+        kind: DescriptorKind,
+    ) -> SymbolID:
+        descriptors = list(_path_namespaces(self.relative_path))
+        descriptors.extend(Descriptor(name=t, kind=DescriptorKind.TYPE) for t in type_chain)
+        descriptors.append(Descriptor(name=name, kind=kind))
+        return SymbolID(scheme=SCHEME, descriptors=tuple(descriptors))
+
+
+# ---------------------------------------------------------------------------
+# Pure helpers
+# ---------------------------------------------------------------------------
+
+
+def _path_namespaces(path: PurePosixPath) -> list[Descriptor]:
+    return [Descriptor(name=part, kind=DescriptorKind.NAMESPACE) for part in path.parts]
+
+
+def _node_range(node: tree_sitter.Node) -> Range:
+    sr, sc = node.start_point
+    er, ec = node.end_point
+    return Range(
+        start_line=sr + 1,
+        start_col=sc,
+        end_line=max(er + 1, sr + 1),
+        end_col=ec,
+    )
+
+
+def _node_text(node: tree_sitter.Node) -> str:
+    return node.text.decode("utf-8") if node.text is not None else ""
+
+
+def _object_name(node: tree_sitter.Node) -> str | None:
+    """Pull a CREATE TABLE / VIEW target name from `object_reference`."""
+    for child in node.children:
+        if child.type != "object_reference":
+            continue
+        # Take the last identifier so schema-qualified `db.users` → "users".
+        last = None
+        for grand in child.children:
+            if grand.type == "identifier":
+                last = grand
+        if last is not None:
+            return _node_text(last)
+    return None

codemap_sql-0.1.0a1/tests/test_indexer.py

@@ -0,0 +1,155 @@
+"""Unit tests for the SQL indexer plugin."""
+
+from __future__ import annotations
+
+import textwrap
+from pathlib import Path, PurePosixPath
+
+from codemap_sql import SqlIndexer
+from codemap_sql.indexer import SCHEME
+
+from codemap.core.models import IndexResult
+from codemap.indexers.base import IndexContext
+
+
+def _index(source: str, *, path: str = "schema.sql") -> IndexResult:
+    code = textwrap.dedent(source).lstrip("\n")
+    return SqlIndexer().index_file(
+        Path(path),
+        code.encode("utf-8"),
+        IndexContext(
+            project_root=Path("/tmp/proj"),
+            relative_path=PurePosixPath(path),
+            language="sql",
+        ),
+    )
+
+
+def test_indexer_metadata() -> None:
+    ix = SqlIndexer()
+    assert ix.name == "sql"
+    assert ix.languages == ["sql"]
+    assert ix.supports(Path("a.sql"))
+    assert ix.supports(Path("a.ddl"))
+    assert not ix.supports(Path("a.py"))
+
+
+def test_scheme_is_consistent() -> None:
+    r = _index("CREATE TABLE u (id INT);")
+    for s in r.symbols:
+        assert str(s.id).startswith(f"{SCHEME} ")
+
+
+def test_create_table_with_columns() -> None:
+    r = _index(
+        """
+        CREATE TABLE users (
+            id INTEGER PRIMARY KEY,
+            name TEXT NOT NULL,
+            email TEXT UNIQUE
+        );
+        """
+    )
+    tables = [s for s in r.symbols if s.kind == "class"]
+    assert len(tables) == 1
+    assert tables[0].extra.get("sql_kind") == "table"
+    assert "users#" in str(tables[0].id)
+
+    fields = [s for s in r.symbols if s.kind == "field"]
+    field_names = {s.id.descriptors[-1].name for s in fields}
+    assert field_names == {"id", "name", "email"}
+
+
+def test_create_view() -> None:
+    r = _index(
+        """
+        CREATE VIEW active_users AS
+            SELECT * FROM users WHERE active = 1;
+        """
+    )
+    view = next(s for s in r.symbols if s.kind == "class")
+    assert view.extra.get("sql_kind") == "view"
+    assert "active_users#" in str(view.id)
+
+
+def test_create_index() -> None:
+    r = _index("CREATE INDEX idx_users_email ON users(email);")
+    indexes = [s for s in r.symbols if s.kind == "variable"]
+    assert len(indexes) == 1
+    assert indexes[0].extra.get("sql_kind") == "index"
+    assert "idx_users_email." in str(indexes[0].id)
+
+
+def test_columns_attached_to_table() -> None:
+    r = _index(
+        """
+        CREATE TABLE products (
+            sku TEXT PRIMARY KEY,
+            price DECIMAL
+        );
+        """
+    )
+    fields = [s for s in r.symbols if s.kind == "field"]
+    for f in fields:
+        assert "products#" in str(f.id)
+
+
+def test_multiple_tables_in_one_file() -> None:
+    r = _index(
+        """
+        CREATE TABLE a (x INT);
+        CREATE TABLE b (y INT);
+        """
+    )
+    tables = [s for s in r.symbols if s.kind == "class"]
+    assert {t.id.descriptors[-1].name for t in tables} == {"a", "b"}
+
+
+def test_select_statements_ignored() -> None:
+    r = _index(
+        """
+        CREATE TABLE u (id INT);
+        SELECT * FROM u WHERE id = 1;
+        INSERT INTO u VALUES (1);
+        """
+    )
+    tables = [s for s in r.symbols if s.kind == "class"]
+    # Only `u` from the CREATE TABLE; SELECT/INSERT don't add symbols.
+    assert len(tables) == 1
+
+
+def test_symbol_id_uses_path_namespaces() -> None:
+    r = _index("CREATE TABLE u (id INT);", path="db/migrations/0001.sql")
+    table = next(s for s in r.symbols if s.kind == "class")
+    assert str(table.id) == "scip-sql . . . db/migrations/0001.sql/u#"
+
+
+def test_lowercase_keywords_supported() -> None:
+    r = _index("create table u (id int);")
+    tables = [s for s in r.symbols if s.kind == "class"]
+    assert len(tables) == 1
+
+
+def test_empty_file_yields_no_symbols() -> None:
+    r = _index("")
+    assert r.symbols == []
+
+
+def test_invalid_utf8_yields_diagnostic() -> None:
+    ix = SqlIndexer()
+    r = ix.index_file(
+        Path("bad.sql"),
+        b"\xff\xfe CREATE",
+        IndexContext(
+            project_root=Path("/tmp/proj"),
+            relative_path=PurePosixPath("bad.sql"),
+            language="sql",
+        ),
+    )
+    assert r.symbols == []
+    assert r.diagnostics[0].code == "SQL002"
+
+
+def test_ddl_extension_supported() -> None:
+    r = _index("CREATE TABLE t (id INT);", path="schema.ddl")
+    assert any(s.kind == "class" for s in r.symbols)