codemap-java 0.1.0a1__tar.gz

codemap_java-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_java-0.1.0a1/PKG-INFO

@@ -0,0 +1,70 @@
+Metadata-Version: 2.4
+Name: codemap-java
+Version: 0.1.0a1
+Summary: Java indexer plugin for CodeMap
+Project-URL: Homepage, https://github.com/qxbyte/codemap
+Author: CodeMap Contributors
+License: MIT
+Keywords: codemap,indexer,java,tree-sitter
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Java
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Software Development
+Requires-Python: >=3.11
+Requires-Dist: codemap-core<0.2,>=0.1.0a1
+Requires-Dist: tree-sitter-java>=0.23
+Requires-Dist: tree-sitter>=0.25
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# codemap-java
+
+> A Java indexer for [CodeMap](https://github.com/qxbyte/codemap),
+> distributed as an independent PyPI package.
+
+## What it captures
+
+Backed by `tree-sitter-java`. Single-file, no cross-file type inference (MVP):
+
+| AST node | Symbol kind |
+|---|---|
+| `class_declaration` | `class` |
+| `interface_declaration` | `interface` (stored as `class` with `extra.java_kind=interface`) |
+| `enum_declaration` | stored as `class` with `extra.java_kind=enum` |
+| `record_declaration` | stored as `class` with `extra.java_kind=record` |
+| `method_declaration` (inside type) | `method` |
+| `constructor_declaration` | `method` (signature prefixed with `<init>`) |
+| `field_declaration` (inside type) | `field` |
+
+Package declarations are captured and used as a prefix for the in-file
+`package` namespace.
+
+## SymbolID encoding
+
+```
+scip-java . . . src/com/example/Greeter.java/Greeter#hello().
+└────────┘ └────────────────────────────────┘ └──────┘ └─────┘
+  scheme              file path                  type   method
+```
+
+## Install
+
+```bash
+pip install "git+https://github.com/qxbyte/codemap.git#subdirectory=plugins/codemap-java"
+```
+
+After installation, `codemap doctor` lists `java` next to the other
+indexers on identical terms — same Indexer Protocol, same entry-point
+group, no main-repo change required (ADR-004 + ADR-L001).
+
+## Limits
+
+* No `extends` / `implements` edges yet. Easy to add in v0.2.0.
+* No generic-parameter descriptors.
+* No annotation extraction (planned).
+* Anonymous classes are skipped.
+
+## License
+
+MIT.

codemap_java-0.1.0a1/README.md

@@ -0,0 +1,50 @@
+# codemap-java
+
+> A Java indexer for [CodeMap](https://github.com/qxbyte/codemap),
+> distributed as an independent PyPI package.
+
+## What it captures
+
+Backed by `tree-sitter-java`. Single-file, no cross-file type inference (MVP):
+
+| AST node | Symbol kind |
+|---|---|
+| `class_declaration` | `class` |
+| `interface_declaration` | `interface` (stored as `class` with `extra.java_kind=interface`) |
+| `enum_declaration` | stored as `class` with `extra.java_kind=enum` |
+| `record_declaration` | stored as `class` with `extra.java_kind=record` |
+| `method_declaration` (inside type) | `method` |
+| `constructor_declaration` | `method` (signature prefixed with `<init>`) |
+| `field_declaration` (inside type) | `field` |
+
+Package declarations are captured and used as a prefix for the in-file
+`package` namespace.
+
+## SymbolID encoding
+
+```
+scip-java . . . src/com/example/Greeter.java/Greeter#hello().
+└────────┘ └────────────────────────────────┘ └──────┘ └─────┘
+  scheme              file path                  type   method
+```
+
+## Install
+
+```bash
+pip install "git+https://github.com/qxbyte/codemap.git#subdirectory=plugins/codemap-java"
+```
+
+After installation, `codemap doctor` lists `java` next to the other
+indexers on identical terms — same Indexer Protocol, same entry-point
+group, no main-repo change required (ADR-004 + ADR-L001).
+
+## Limits
+
+* No `extends` / `implements` edges yet. Easy to add in v0.2.0.
+* No generic-parameter descriptors.
+* No annotation extraction (planned).
+* Anonymous classes are skipped.
+
+## License
+
+MIT.

codemap_java-0.1.0a1/pyproject.toml

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

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

@@ -0,0 +1,8 @@
+"""Java indexer plugin for CodeMap."""
+
+from __future__ import annotations
+
+from codemap_java.indexer import JavaIndexer
+
+__all__ = ["JavaIndexer"]
+__version__ = "0.1.0"

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

@@ -0,0 +1,254 @@
+"""Java indexer built on tree-sitter-java.
+
+Covers class / interface / enum / record / method / constructor / field
+declarations. Package declarations are honoured as a namespace prefix
+under the file path. Nested types track a class stack to produce the
+correct ``Cls#Inner#m()`` chain.
+
+The indexer is single-file by design; cross-file `extends` / `implements`
+resolution lives in a future bridge so the indexer surface stays narrow.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path, PurePosixPath
+from typing import ClassVar
+
+import tree_sitter
+import tree_sitter_java
+
+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-java"
+LANG = "java"
+
+_JAVA_LANG = tree_sitter.Language(tree_sitter_java.language())
+
+_TYPE_DECLS = frozenset(
+    {
+        "class_declaration",
+        "interface_declaration",
+        "enum_declaration",
+        "record_declaration",
+    }
+)
+
+
+class JavaIndexer:
+    name: ClassVar[str] = "java"
+    version: ClassVar[str] = "0.1.0"
+    file_patterns: ClassVar[list[str]] = ["*.java"]
+    languages: ClassVar[list[str]] = [LANG]
+
+    def supports(self, path: Path) -> bool:
+        return path.suffix == ".java"
+
+    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="JAVA002",
+                        message=f"not valid UTF-8: {exc}",
+                        producer=self.name,
+                    )
+                ]
+            )
+        parser = tree_sitter.Parser(_JAVA_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="JAVA001",
+                    message="tree-sitter reported parse errors; symbols may be incomplete",
+                    producer=self.name,
+                )
+            )
+        return IndexResult(
+            symbols=visitor.symbols,
+            edges=visitor.edges,
+            diagnostics=diagnostics,
+        )
+
+
+# ---------------------------------------------------------------------------
+# AST visitor
+# ---------------------------------------------------------------------------
+
+
+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._class_stack: list[str] = []
+        self._package: str = ""
+
+    def visit(self, node: tree_sitter.Node) -> None:
+        if node.type == "package_declaration":
+            self._package = _node_text(node.children[1]) if node.child_count > 1 else ""
+            return
+        if node.type in _TYPE_DECLS:
+            self._visit_type(node)
+            return
+        if node.type == "method_declaration" and self._class_stack:
+            self._visit_method(node, is_constructor=False)
+            return
+        if node.type == "constructor_declaration" and self._class_stack:
+            self._visit_method(node, is_constructor=True)
+            return
+        if node.type == "field_declaration" and self._class_stack:
+            self._visit_field(node)
+            return
+        for child in node.children:
+            self.visit(child)
+
+    # ------------------------------------------------------------- types
+
+    def _visit_type(self, node: tree_sitter.Node) -> None:
+        name = _name_child(node)
+        if name is None:
+            return
+        java_kind = node.type.removesuffix("_declaration")
+        sid = self._make_id(name, kind=DescriptorKind.TYPE)
+        self.symbols.append(
+            Symbol(
+                id=sid,
+                kind="class",  # Symbol schema has no separate interface/enum kind
+                language=LANG,
+                file=self.relative_path,
+                range=_node_range(node),
+                extra={"java_kind": java_kind, "package": self._package}
+                if self._package or java_kind != "class"
+                else {},
+            )
+        )
+        body = node.child_by_field_name("body")
+        if body is None:
+            return
+        self._class_stack.append(name)
+        try:
+            for child in body.children:
+                self.visit(child)
+        finally:
+            self._class_stack.pop()
+
+    # ----------------------------------------------------------- members
+
+    def _visit_method(self, node: tree_sitter.Node, *, is_constructor: bool) -> None:
+        name = _name_child(node)
+        if name is None:
+            return
+        if is_constructor:
+            display = "<init>"
+            sid = self._make_id(display, kind=DescriptorKind.METHOD)
+        else:
+            display = name
+            sid = self._make_id(name, kind=DescriptorKind.METHOD)
+        signature = _method_signature(node, name, is_constructor=is_constructor)
+        self.symbols.append(
+            Symbol(
+                id=sid,
+                kind="method",
+                language=LANG,
+                file=self.relative_path,
+                range=_node_range(node),
+                signature=signature,
+            )
+        )
+
+    def _visit_field(self, node: tree_sitter.Node) -> None:
+        for child in node.children:
+            if child.type != "variable_declarator":
+                continue
+            name_node = child.child_by_field_name("name")
+            if name_node is None:
+                continue
+            name = _node_text(name_node)
+            if not name:
+                continue
+            sid = self._make_id(name, kind=DescriptorKind.TERM)
+            self.symbols.append(
+                Symbol(
+                    id=sid,
+                    kind="field",
+                    language=LANG,
+                    file=self.relative_path,
+                    range=_node_range(child),
+                )
+            )
+
+    # ----------------------------------------------------------- helpers
+
+    def _make_id(self, name: str, *, kind: DescriptorKind) -> SymbolID:
+        descriptors = list(_path_namespaces(self.relative_path))
+        descriptors.extend(
+            Descriptor(name=cls, kind=DescriptorKind.TYPE) for cls in self._class_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 _name_child(node: tree_sitter.Node) -> str | None:
+    name_node = node.child_by_field_name("name")
+    if name_node is None or name_node.text is None:
+        return None
+    text = _node_text(name_node).strip()
+    return text or None
+
+
+def _method_signature(
+    node: tree_sitter.Node,
+    name: str,
+    *,
+    is_constructor: bool,
+) -> str:
+    params = node.child_by_field_name("parameters")
+    params_text = _node_text(params) if params is not None else "()"
+    if is_constructor:
+        return f"{name}{params_text}"
+    return_type = node.child_by_field_name("type")
+    rt_text = _node_text(return_type) + " " if return_type is not None else ""
+    return f"{rt_text}{name}{params_text}"

codemap_java-0.1.0a1/tests/test_indexer.py

@@ -0,0 +1,186 @@
+"""Unit tests for the Java indexer plugin."""
+
+from __future__ import annotations
+
+import textwrap
+from pathlib import Path, PurePosixPath
+
+from codemap_java import JavaIndexer
+from codemap_java.indexer import SCHEME
+
+from codemap.core.models import IndexResult
+from codemap.indexers.base import IndexContext
+
+
+def _index(source: str, *, path: str = "src/Foo.java") -> IndexResult:
+    code = textwrap.dedent(source).lstrip("\n")
+    return JavaIndexer().index_file(
+        Path(path),
+        code.encode("utf-8"),
+        IndexContext(
+            project_root=Path("/tmp/proj"),
+            relative_path=PurePosixPath(path),
+            language="java",
+        ),
+    )
+
+
+# ---------------------------------------------------------------------------
+# Metadata
+# ---------------------------------------------------------------------------
+
+
+def test_indexer_metadata() -> None:
+    ix = JavaIndexer()
+    assert ix.name == "java"
+    assert ix.languages == ["java"]
+    assert "*.java" in ix.file_patterns
+    assert ix.supports(Path("a.java"))
+    assert not ix.supports(Path("a.kt"))
+
+
+def test_scheme_is_consistent() -> None:
+    r = _index(
+        """
+        class A {
+            int x;
+            void m() {}
+        }
+        """
+    )
+    for s in r.symbols:
+        assert str(s.id).startswith(f"{SCHEME} ")
+
+
+# ---------------------------------------------------------------------------
+# Declarations
+# ---------------------------------------------------------------------------
+
+
+def test_class_with_method_field_constructor() -> None:
+    r = _index(
+        """
+        class Greeter {
+            String name;
+            Greeter(String n) { name = n; }
+            String hello() { return name; }
+        }
+        """
+    )
+    kinds = sorted(s.kind for s in r.symbols)
+    assert kinds == ["class", "field", "method", "method"]
+    method_sigs = sorted(s.signature or "" for s in r.symbols if s.kind == "method")
+    assert any("hello" in sig for sig in method_sigs)
+    assert any("Greeter" in sig for sig in method_sigs)
+
+
+def test_interface_marked_in_extra() -> None:
+    r = _index(
+        """
+        interface Repo {
+            void save();
+        }
+        """
+    )
+    types = [s for s in r.symbols if s.kind == "class"]
+    assert len(types) == 1
+    assert types[0].extra.get("java_kind") == "interface"
+
+
+def test_enum_marked_in_extra() -> None:
+    r = _index(
+        """
+        enum Color { RED, GREEN, BLUE }
+        """
+    )
+    types = [s for s in r.symbols if s.kind == "class"]
+    assert types[0].extra.get("java_kind") == "enum"
+
+
+def test_record_marked_in_extra() -> None:
+    r = _index("public record Point(int x, int y) {}")
+    types = [s for s in r.symbols if s.kind == "class"]
+    assert types[0].extra.get("java_kind") == "record"
+
+
+def test_nested_class_namespacing() -> None:
+    r = _index(
+        """
+        class Outer {
+            class Inner {
+                void m() {}
+            }
+        }
+        """
+    )
+    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_package_captured_in_extra() -> None:
+    r = _index(
+        """
+        package com.example;
+        class A {}
+        """
+    )
+    cls = next(s for s in r.symbols if s.kind == "class")
+    assert cls.extra.get("package") == "com.example"
+
+
+def test_multiple_fields_in_one_decl() -> None:
+    r = _index(
+        """
+        class A {
+            int x, y, z;
+        }
+        """
+    )
+    fields = [s for s in r.symbols if s.kind == "field"]
+    assert sorted(s.id.descriptors[-1].name for s in fields) == ["x", "y", "z"]
+
+
+# ---------------------------------------------------------------------------
+# SymbolID + edge cases
+# ---------------------------------------------------------------------------
+
+
+def test_symbol_id_uses_path_namespaces() -> None:
+    r = _index("class A {}", path="src/com/foo/A.java")
+    assert str(r.symbols[0].id) == "scip-java . . . src/com/foo/A.java/A#"
+
+
+def test_empty_file_yields_no_symbols() -> None:
+    r = _index("")
+    assert r.symbols == []
+
+
+def test_invalid_utf8_yields_diagnostic() -> None:
+    ix = JavaIndexer()
+    r = ix.index_file(
+        Path("bad.java"),
+        b"\xff\xfe class",
+        IndexContext(
+            project_root=Path("/tmp/proj"),
+            relative_path=PurePosixPath("bad.java"),
+            language="java",
+        ),
+    )
+    assert r.symbols == []
+    assert r.diagnostics[0].code == "JAVA002"
+
+
+def test_syntax_error_yields_warning() -> None:
+    r = _index("class Broken { void m( ")
+    codes = {d.code for d in r.diagnostics}
+    assert "JAVA001" in codes
+
+
+def test_method_outside_class_is_not_recorded() -> None:
+    """Defensive: top-level identifiers that aren't inside a type don't
+    accidentally become methods."""
+    r = _index("class A {} class B { void f() {} }")
+    methods = [s for s in r.symbols if s.kind == "method"]
+    assert len(methods) == 1
+    assert "B#f()." in str(methods[0].id)