codemap-ruby 0.1.0a1__tar.gz

codemap_ruby-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_ruby-0.1.0a1/PKG-INFO

@@ -0,0 +1,65 @@
+Metadata-Version: 2.4
+Name: codemap-ruby
+Version: 0.1.0a1
+Summary: Ruby indexer plugin for CodeMap
+Project-URL: Homepage, https://github.com/qxbyte/codemap
+Author: CodeMap Contributors
+License: MIT
+Keywords: codemap,indexer,ruby,tree-sitter
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Ruby
+Classifier: Topic :: Software Development
+Requires-Python: >=3.11
+Requires-Dist: codemap-core<0.2,>=0.1.0a1
+Requires-Dist: tree-sitter-ruby>=0.23
+Requires-Dist: tree-sitter>=0.25
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# codemap-ruby
+
+> A Ruby indexer for [CodeMap](https://github.com/qxbyte/codemap),
+> shipped as an independent PyPI package.
+
+## What it captures
+
+Backed by `tree-sitter-ruby`:
+
+| AST node | Symbol kind |
+|---|---|
+| `class` | `class` (with `extra.ruby_kind=class`) |
+| `module` | `class` (with `extra.ruby_kind=module`) |
+| `method` (inside class/module) | `method` |
+| `method` (top level) | `function` |
+| `singleton_method` | `method` (with `extra.ruby_kind=singleton`) |
+| top-level constant `assignment` | `variable` |
+| constant assignment inside class/module | `field` |
+
+Nested class / module declarations are tracked with a class stack:
+`module A; class B; def m; end; end; end` produces `A#B#m()`.
+
+## Install
+
+```bash
+pip install "git+https://github.com/qxbyte/codemap.git#subdirectory=plugins/codemap-ruby"
+```
+
+## SymbolID encoding
+
+```
+scip-ruby . . . app/models/user.rb/User#hello().
+```
+
+## Limits
+
+* `attr_accessor` / `attr_reader` / `attr_writer` macros are not
+  expanded into individual field symbols.
+* `define_method`, `class_eval`, and other metaprogramming are not
+  resolved.
+* Mixin (`include`/`extend`) edges are not yet emitted.
+
+## License
+
+MIT.

codemap_ruby-0.1.0a1/README.md

@@ -0,0 +1,45 @@
+# codemap-ruby
+
+> A Ruby indexer for [CodeMap](https://github.com/qxbyte/codemap),
+> shipped as an independent PyPI package.
+
+## What it captures
+
+Backed by `tree-sitter-ruby`:
+
+| AST node | Symbol kind |
+|---|---|
+| `class` | `class` (with `extra.ruby_kind=class`) |
+| `module` | `class` (with `extra.ruby_kind=module`) |
+| `method` (inside class/module) | `method` |
+| `method` (top level) | `function` |
+| `singleton_method` | `method` (with `extra.ruby_kind=singleton`) |
+| top-level constant `assignment` | `variable` |
+| constant assignment inside class/module | `field` |
+
+Nested class / module declarations are tracked with a class stack:
+`module A; class B; def m; end; end; end` produces `A#B#m()`.
+
+## Install
+
+```bash
+pip install "git+https://github.com/qxbyte/codemap.git#subdirectory=plugins/codemap-ruby"
+```
+
+## SymbolID encoding
+
+```
+scip-ruby . . . app/models/user.rb/User#hello().
+```
+
+## Limits
+
+* `attr_accessor` / `attr_reader` / `attr_writer` macros are not
+  expanded into individual field symbols.
+* `define_method`, `class_eval`, and other metaprogramming are not
+  resolved.
+* Mixin (`include`/`extend`) edges are not yet emitted.
+
+## License
+
+MIT.

codemap_ruby-0.1.0a1/pyproject.toml

@@ -0,0 +1,36 @@
+[build-system]
+requires = ["hatchling>=1.21"]
+build-backend = "hatchling.build"
+
+[project]
+name = "codemap-ruby"
+version = "0.1.0a1"
+description = "Ruby indexer plugin for CodeMap"
+readme = "README.md"
+requires-python = ">=3.11"
+license = { text = "MIT" }
+authors = [{ name = "CodeMap Contributors" }]
+keywords = ["codemap", "ruby", "indexer", "tree-sitter"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Ruby",
+    "Topic :: Software Development",
+]
+dependencies = [
+    "codemap-core>=0.1.0a1,<0.2",
+    "tree-sitter>=0.25",
+    "tree-sitter-ruby>=0.23",
+]
+
+[project.optional-dependencies]
+dev = ["pytest>=8.0"]
+
+[project.entry-points."codemap.indexers"]
+ruby = "codemap_ruby:RubyIndexer"
+
+[project.urls]
+Homepage = "https://github.com/qxbyte/codemap"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/codemap_ruby"]

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

@@ -0,0 +1,8 @@
+"""Ruby indexer plugin for CodeMap."""
+
+from __future__ import annotations
+
+from codemap_ruby.indexer import RubyIndexer
+
+__all__ = ["RubyIndexer"]
+__version__ = "0.1.0"

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

@@ -0,0 +1,232 @@
+"""Ruby indexer built on tree-sitter-ruby.
+
+Tracks a class stack so nested modules / classes produce qualified
+symbol IDs (``Outer#Inner#m()``). Top-level ``def`` is a function; ``def``
+inside a class or module body is a method. ``singleton_method`` (``def
+self.x``) is recorded as a method tagged ``extra.ruby_kind="singleton"``.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path, PurePosixPath
+from typing import ClassVar
+
+import tree_sitter
+import tree_sitter_ruby
+
+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-ruby"
+LANG = "ruby"
+
+_RB_LANG = tree_sitter.Language(tree_sitter_ruby.language())
+
+
+class RubyIndexer:
+    name: ClassVar[str] = "ruby"
+    version: ClassVar[str] = "0.1.0"
+    file_patterns: ClassVar[list[str]] = ["*.rb"]
+    languages: ClassVar[list[str]] = [LANG]
+
+    def supports(self, path: Path) -> bool:
+        return path.suffix == ".rb"
+
+    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="RB002",
+                        message=f"not valid UTF-8: {exc}",
+                        producer=self.name,
+                    )
+                ]
+            )
+        parser = tree_sitter.Parser(_RB_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="RB001",
+                    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] = []
+        self._type_stack: list[str] = []
+
+    def visit(self, node: tree_sitter.Node) -> None:
+        kind = node.type
+        if kind == "class":
+            self._visit_type(node, ruby_kind="class")
+            return
+        if kind == "module":
+            self._visit_type(node, ruby_kind="module")
+            return
+        if kind == "method":
+            self._visit_method(node, singleton=False)
+            return
+        if kind == "singleton_method":
+            self._visit_method(node, singleton=True)
+            return
+        if kind == "assignment":
+            self._visit_assignment(node)
+        for child in node.children:
+            self.visit(child)
+
+    # ----------------------------------------------------- type-level
+
+    def _visit_type(self, node: tree_sitter.Node, *, ruby_kind: str) -> None:
+        name = _first_constant(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={"ruby_kind": ruby_kind},
+            )
+        )
+        self._type_stack.append(name)
+        try:
+            for child in node.children:
+                if child.type == "body_statement":
+                    for grand in child.children:
+                        self.visit(grand)
+        finally:
+            self._type_stack.pop()
+
+    # ----------------------------------------------------- methods
+
+    def _visit_method(self, node: tree_sitter.Node, *, singleton: bool) -> None:
+        name = _method_name(node)
+        if name is None:
+            return
+        sym_kind: str = "method" if self._type_stack else "function"
+        sid = self._make_id(name, kind=DescriptorKind.METHOD)
+        extra: dict[str, str] = {}
+        if singleton:
+            extra["ruby_kind"] = "singleton"
+        self.symbols.append(
+            Symbol(
+                id=sid,
+                kind=sym_kind,  # type: ignore[arg-type]
+                language=LANG,
+                file=self.relative_path,
+                range=_node_range(node),
+                signature=f"def {name}",
+                extra=extra,
+            )
+        )
+
+    # ------------------------------------------------- constants / vars
+
+    def _visit_assignment(self, node: tree_sitter.Node) -> None:
+        # Capture top-level / inside-class assignments where the lhs is a
+        # constant (uppercase Ruby identifier). Ignore everything else
+        # (local variable assignments inside methods are not symbols).
+        lhs = node.children[0] if node.children else None
+        if lhs is None or lhs.type != "constant":
+            return
+        name = _node_text(lhs)
+        if not name:
+            return
+        sym_kind: str = "field" if self._type_stack else "variable"
+        sid = self._make_id(name, kind=DescriptorKind.TERM)
+        self.symbols.append(
+            Symbol(
+                id=sid,
+                kind=sym_kind,  # type: ignore[arg-type]
+                language=LANG,
+                file=self.relative_path,
+                range=_node_range(node),
+            )
+        )
+
+    # -------------------------------------------------------- helpers
+
+    def _make_id(self, name: str, *, kind: DescriptorKind) -> SymbolID:
+        descriptors = list(_path_namespaces(self.relative_path))
+        descriptors.extend(Descriptor(name=t, kind=DescriptorKind.TYPE) for t in self._type_stack)
+        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 _first_constant(node: tree_sitter.Node) -> str | None:
+    for child in node.children:
+        if child.type == "constant":
+            return _node_text(child)
+        if child.type == "scope_resolution":
+            # nested: `class A::B` — take the trailing constant.
+            last = None
+            for grand in child.children:
+                if grand.type == "constant":
+                    last = grand
+            if last is not None:
+                return _node_text(last)
+    return None
+
+
+def _method_name(node: tree_sitter.Node) -> str | None:
+    """For ``def x`` returns ``x``; for ``def self.x`` returns ``x``."""
+    for child in node.children:
+        if child.type == "identifier":
+            return _node_text(child)
+    return None

codemap_ruby-0.1.0a1/tests/test_indexer.py

@@ -0,0 +1,171 @@
+"""Unit tests for the Ruby indexer plugin."""
+
+from __future__ import annotations
+
+import textwrap
+from pathlib import Path, PurePosixPath
+
+from codemap_ruby import RubyIndexer
+from codemap_ruby.indexer import SCHEME
+
+from codemap.core.models import IndexResult
+from codemap.indexers.base import IndexContext
+
+
+def _index(source: str, *, path: str = "app/user.rb") -> IndexResult:
+    code = textwrap.dedent(source).lstrip("\n")
+    return RubyIndexer().index_file(
+        Path(path),
+        code.encode("utf-8"),
+        IndexContext(
+            project_root=Path("/tmp/proj"),
+            relative_path=PurePosixPath(path),
+            language="ruby",
+        ),
+    )
+
+
+def test_indexer_metadata() -> None:
+    ix = RubyIndexer()
+    assert ix.name == "ruby"
+    assert ix.languages == ["ruby"]
+    assert ix.supports(Path("a.rb"))
+    assert not ix.supports(Path("a.py"))
+
+
+def test_scheme_is_consistent() -> None:
+    r = _index(
+        """
+        class A; end
+        def f; end
+        X = 1
+        """
+    )
+    for s in r.symbols:
+        assert str(s.id).startswith(f"{SCHEME} ")
+
+
+def test_class_declaration() -> None:
+    r = _index(
+        """
+        class User
+          def hello
+            @name
+          end
+        end
+        """
+    )
+    cls = next(s for s in r.symbols if s.kind == "class")
+    assert cls.extra.get("ruby_kind") == "class"
+    methods = [s for s in r.symbols if s.kind == "method"]
+    assert any("User#hello()." in str(m.id) for m in methods)
+
+
+def test_module_declaration() -> None:
+    r = _index(
+        """
+        module Greeter
+          def hello
+          end
+        end
+        """
+    )
+    mod = next(s for s in r.symbols if s.kind == "class")
+    assert mod.extra.get("ruby_kind") == "module"
+
+
+def test_nested_module_class_namespacing() -> None:
+    r = _index(
+        """
+        module Outer
+          class Inner
+            def m
+            end
+          end
+        end
+        """
+    )
+    ids = [str(s.id) for s in r.symbols]
+    assert any("Outer#Inner#" in i for i in ids)
+    assert any("Outer#Inner#m()." in i for i in ids)
+
+
+def test_singleton_method() -> None:
+    r = _index(
+        """
+        class User
+          def self.create(name)
+            new(name)
+          end
+        end
+        """
+    )
+    singletons = [s for s in r.symbols if s.extra.get("ruby_kind") == "singleton"]
+    assert len(singletons) == 1
+    assert "User#create()." in str(singletons[0].id)
+
+
+def test_top_level_method_is_function() -> None:
+    r = _index(
+        """
+        def helper(x)
+          x + 1
+        end
+        """
+    )
+    funcs = [s for s in r.symbols if s.kind == "function"]
+    assert len(funcs) == 1
+    assert "helper" in str(funcs[0].id)
+
+
+def test_top_level_constant_is_variable() -> None:
+    r = _index("MAX = 10")
+    vars_ = [s for s in r.symbols if s.kind == "variable"]
+    assert len(vars_) == 1
+    assert str(vars_[0].id).endswith("MAX.")
+
+
+def test_constant_inside_class_is_field() -> None:
+    r = _index(
+        """
+        class A
+          DEFAULT = 1
+        end
+        """
+    )
+    fields = [s for s in r.symbols if s.kind == "field"]
+    assert len(fields) == 1
+
+
+def test_symbol_id_uses_path_namespaces() -> None:
+    r = _index("class A; end", path="app/models/user.rb")
+    cls = next(s for s in r.symbols if s.kind == "class")
+    assert str(cls.id) == "scip-ruby . . . app/models/user.rb/A#"
+
+
+def test_empty_file_yields_no_symbols() -> None:
+    r = _index("")
+    assert r.symbols == []
+
+
+def test_invalid_utf8_yields_diagnostic() -> None:
+    ix = RubyIndexer()
+    r = ix.index_file(
+        Path("bad.rb"),
+        b"\xff\xfe class",
+        IndexContext(
+            project_root=Path("/tmp/proj"),
+            relative_path=PurePosixPath("bad.rb"),
+            language="ruby",
+        ),
+    )
+    assert r.symbols == []
+    assert r.diagnostics[0].code == "RB002"
+
+
+def test_method_outside_type_is_function_not_method() -> None:
+    r = _index("def f; end")
+    funcs = [s for s in r.symbols if s.kind == "function"]
+    methods = [s for s in r.symbols if s.kind == "method"]
+    assert len(funcs) == 1
+    assert len(methods) == 0