coderay 1.0.0__py3-none-any.whl

coderay/vcs/git.py

@@ -0,0 +1,193 @@
+from __future__ import annotations
+
+import logging
+import subprocess
+from pathlib import Path
+
+import pathspec
+
+logger = logging.getLogger(__name__)
+
+
+def load_gitignore(repo_root: Path) -> pathspec.PathSpec:
+    """Parse .gitignore into a PathSpec matcher."""
+    gitignore = repo_root / ".gitignore"
+    if not gitignore.is_file():
+        return pathspec.PathSpec.from_lines("gitignore", [])
+    try:
+        lines = gitignore.read_text(encoding="utf-8", errors="replace").splitlines()
+        return pathspec.PathSpec.from_lines("gitignore", lines)
+    except Exception:
+        logger.warning("Failed to parse .gitignore; no patterns loaded")
+        return pathspec.PathSpec.from_lines("gitignore", [])
+
+
+def _parse_status_line(line: str) -> tuple[str, str] | None:
+    """Parse one line of git status --short --porcelain."""
+    if len(line) < 4:
+        return None
+    status_xy = line[:2]
+    path_part = line[3:].strip()
+    if " -> " in path_part:
+        path_part = path_part.split(" -> ", 1)[1].strip()
+    return (status_xy, path_part)
+
+
+class Git:
+    """Git operations for file discovery and change detection."""
+
+    def __init__(self, repo_root: str | Path = ".") -> None:
+        """Initialize with the repository root."""
+        self.repo_root = Path(repo_root)
+
+    def run(self, *args: str) -> str:
+        """Run a git command and return stripped stdout."""
+        result = subprocess.run(
+            ["git", *args],
+            cwd=self.repo_root,
+            capture_output=True,
+            text=True,
+            timeout=30,
+        )
+        if result.returncode != 0:
+            raise RuntimeError(
+                f"git {' '.join(args)}: {result.stderr or result.stdout}"
+            )
+        return (result.stdout or "").strip()
+
+    def get_head_commit(self) -> str | None:
+        """Return current HEAD commit hash, or None if unavailable."""
+        try:
+            return self.run("rev-parse", "HEAD")
+        except (RuntimeError, FileNotFoundError):
+            return None
+
+    def get_current_branch(self) -> str | None:
+        """Return current branch name, or None if detached HEAD."""
+        try:
+            name = self.run("rev-parse", "--abbrev-ref", "HEAD")
+            if name and name != "HEAD":
+                return name
+        except (RuntimeError, FileNotFoundError):
+            pass
+        return None
+
+    def is_branch_switched(self, last_branch: str | None = None) -> bool:
+        """Return True if the current branch differs from *last_branch*."""
+        current_branch = self.get_current_branch()
+        return (
+            current_branch is not None
+            and last_branch is not None
+            and current_branch != last_branch
+        )
+
+    def get_files_to_index(
+        self, last_commit: str | None
+    ) -> tuple[list[Path], list[str]]:
+        """Return (paths_to_add, paths_to_remove) since last indexed commit."""
+        from coderay.chunking.registry import get_supported_extensions
+
+        supported = get_supported_extensions()
+
+        def _is_supported(path: str) -> bool:
+            from pathlib import PurePosixPath
+
+            return PurePosixPath(path).suffix in supported
+
+        to_add: set[str] = set()
+        to_remove: set[str] = set()
+
+        try:
+            head = self.get_head_commit()
+            if not head or last_commit is None:
+                return [], []
+
+            # 1. Committed changes since last indexed commit.
+            try:
+                diff_out = self.run("diff", "--name-status", f"{last_commit}...HEAD")
+                for line in diff_out.splitlines():
+                    parts = line.split("\t")
+                    if len(parts) < 2:
+                        continue
+                    status = parts[0].strip()
+                    path = (
+                        parts[-1].strip() if status in ("R", "C") else parts[1].strip()
+                    )
+                    if not _is_supported(path):
+                        continue
+                    if status == "D":
+                        to_remove.add(path)
+                    else:
+                        to_add.add(path)
+            except RuntimeError:
+                pass
+
+            # 2. Uncommitted changes (working tree + staging area).
+            #    Instead of matching against a status-code set, check
+            #    the filesystem: if the file exists → re-index,
+            #    otherwise → remove.
+            try:
+                status_out = self.run("status", "--short", "--porcelain")
+                for line in status_out.splitlines():
+                    parsed = _parse_status_line(line)
+                    if not parsed:
+                        continue
+                    status_xy, path = parsed
+                    if status_xy == "!!":
+                        continue
+                    if not _is_supported(path):
+                        continue
+                    if (self.repo_root / path).is_file():
+                        to_add.add(path)
+                    else:
+                        to_remove.add(path)
+            except RuntimeError:
+                pass
+
+        except Exception as e:
+            logger.warning("Git sync failed: %s", e)
+            return [], []
+
+        add_paths = [self.repo_root / p for p in sorted(to_add)]
+        remove_paths = sorted(to_remove)
+        return add_paths, remove_paths
+
+    def discover_python_files(self) -> list[Path]:
+        """List all Python files. Alias for ``discover_files(extensions={'.py'})``."""
+        return self.discover_files(extensions={".py"})
+
+    def discover_files(
+        self,
+        extensions: set[str] | None = None,
+    ) -> list[Path]:
+        """List all source files matching the given extensions."""
+        if extensions is None:
+            from coderay.chunking.registry import get_supported_extensions
+
+            extensions = get_supported_extensions()
+
+        if (self.repo_root / ".git").exists():
+            try:
+                globs = [f"*{ext}" for ext in extensions]
+                out = self.run("ls-files", *globs)
+                if out:
+                    lines = [p.strip() for p in out.splitlines() if p.strip()]
+                    return sorted(self.repo_root / p for p in lines)
+            except (RuntimeError, FileNotFoundError):
+                pass
+
+        # Fallback: rglob filtered through .gitignore.
+        ignore = load_gitignore(self.repo_root)
+        result: list[Path] = []
+        for f in self.repo_root.rglob("*"):
+            if not f.is_file():
+                continue
+            if f.suffix not in extensions:
+                continue
+            rel = str(f.relative_to(self.repo_root))
+            if ignore.match_file(rel):
+                continue
+            if ".git" in Path(rel).parts:
+                continue
+            result.append(f)
+        return sorted(result)

coderay-1.0.0.dist-info/METADATA

@@ -0,0 +1,145 @@
+Metadata-Version: 2.4
+Name: coderay
+Version: 1.0.0
+Summary: X-ray your codebase — semantic search, code graphs, file skeletons, and MCP server
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: networkx>=3.0
+Requires-Dist: tree-sitter>=0.24.0
+Requires-Dist: tree-sitter-python>=0.25.0
+Requires-Dist: lancedb>=0.5.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: click>=8.0
+Requires-Dist: filelock>=3.0
+Requires-Dist: fastembed>=0.4.0
+Requires-Dist: watchdog>=4.0.0
+Requires-Dist: pathspec>=0.12.0
+Provides-Extra: openai
+Requires-Dist: openai>=1.0.0; extra == "openai"
+Provides-Extra: languages
+Requires-Dist: tree-sitter-javascript>=0.23.0; extra == "languages"
+Requires-Dist: tree-sitter-typescript>=0.23.0; extra == "languages"
+Requires-Dist: tree-sitter-go>=0.23.0; extra == "languages"
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.0.0; extra == "mcp"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Requires-Dist: ruff>=0.8.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Requires-Dist: openai>=1.0.0; extra == "dev"
+Requires-Dist: httpx>=0.27.0; extra == "dev"
+Requires-Dist: mcp>=1.0.0; extra == "dev"
+Provides-Extra: maintain
+Requires-Dist: pylance>=0.15.0; extra == "maintain"
+Provides-Extra: all
+Requires-Dist: coderay[dev,languages,maintain,mcp,openai]; extra == "all"
+
+# CodeRay
+
+A local, offline-first semantic code indexer. Builds a vector index,
+call/import graph, and file skeletons — exposed as an MCP server for
+AI coding assistants and a standalone CLI.
+
+## What you get
+
+| Capability | What it does | Why it matters | AI assistant benefit |
+|---|---|---|---|
+| **Semantic search** | Find code by meaning, not keywords. "where do we handle auth errors" returns results even if the code never uses that phrase. | Grep finds text. This finds *intent*. | Better context retrieval for plan and edit modes |
+| **Blast radius** (`get_impact_radius`) | Given a function or module, show every node reachable within N hops via calls, imports, and inheritance. | Before changing `UserService.save()`, see exactly what breaks. | Safer refactors — agent sees downstream impact before editing |
+| **File skeleton** (`get_file_skeleton`) | Signatures, docstrings, imports — no function bodies. The API surface of a file at a glance. | Understand a 500-line file in 30 lines without reading the implementation. | Drastically fewer tokens than reading the full file |
+| **Index status** | Chunk count, schema version, branch, last commit, store health. | Confirm the index is fresh before relying on results. | Agent self-checks before trusting search results |
+
+## Install
+
+```bash
+pip install "coderay[all] @ git+https://github.com/bogdan-copocean/coderay.git"
+```
+
+For development:
+
+```bash
+git clone https://github.com/bogdan-copocean/coderay.git
+cd coderay
+pip install -e ".[all]"
+```
+
+## Quick start
+
+```bash
+cd /path/to/your/project
+coderay build --repo .
+coderay search "how does authentication work"
+coderay watch --repo .
+coderay graph --kind calls
+coderay skeleton src/app/main.py
+```
+
+## MCP server (Claude Code / Cursor)
+
+Add to `~/.claude/claude_code_config.json` or Cursor MCP settings:
+
+```json
+{
+  "mcpServers": {
+    "coderay": {
+      "command": "/path/to/your/.venv/bin/coderay-mcp",
+      "args": []
+    }
+  }
+}
+```
+
+## CLI reference
+
+| Command | Description |
+|---|---|
+| `coderay build [--full] --repo .` | Build index (incremental or full rebuild) |
+| `coderay update --repo .` | Incremental update (changed files only) |
+| `coderay watch --repo . [--debounce N]` | Watch for file changes, re-index automatically |
+| `coderay search "query" [--top-k N]` | Semantic search |
+| `coderay list [--by-file]` | List indexed chunks |
+| `coderay status` | Index state, branch, commit, chunk count |
+| `coderay maintain --repo .` | Compact index, reclaim space |
+| `coderay skeleton FILE` | Print file skeleton |
+| `coderay graph --kind calls\|imports` | List graph edges |
+
+## Configuration
+
+Optional `config.yaml` in the index directory:
+
+```yaml
+embedder:
+  provider: local           # local | openai
+  model: all-MiniLM-L6-v2
+  dimensions: 384
+
+search:
+  boost_rules:
+    "tests/": 0.5
+    "src/core/": 1.2
+
+graph:
+  exclude_callees:
+    - "our_sdk_helper"
+  include_callees:
+    - "isinstance"
+
+watch:
+  debounce_seconds: 2
+  branch_switch_threshold: 50
+  exclude_patterns:
+    - "*.log"
+```
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+make test
+make lint
+make format
+```
+
+Requires Python >= 3.10 and Git.

coderay-1.0.0.dist-info/RECORD

@@ -0,0 +1,42 @@
+coderay/__init__.py,sha256=J-j-u0itpEFT6irdmWmixQqYMadNl1X91TxUmoiLHMI,22
+coderay/chunking/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+coderay/chunking/chunker.py,sha256=eTmrdXGRXFGfQIoLR0wpsxoP5g-jQFa8slVnqk7-iTA,4367
+coderay/chunking/registry.py,sha256=0w-oPmVJnjCs-XDxFNuKCsdTudtko2iOpFws2yUPo0E,5513
+coderay/cli/__init__.py,sha256=E2mlFoZoEETEb5D3eZRfWSx1cwRDcRyZtRojFl792Q4,70
+coderay/cli/commands.py,sha256=T7Hh0dCNvUFypUts_2ae2NLhILgECLK8uzVT4tY4KLk,14540
+coderay/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+coderay/core/config.py,sha256=_Pt_UhWxKmfnFm2XujLTqepK-ben0K6RiLZz-cDC4Zo,2098
+coderay/core/lock.py,sha256=mYvz98uObmE2xB9WBGLnKMsjHtNiROFPIycXq6NHVqE,1009
+coderay/core/models.py,sha256=dA4kpnu1Y5CngX-C9q5OOF0mZ4W7bpocdJxEkPekE4M,1544
+coderay/core/timing.py,sha256=zushfkPk2ZW2aexuJjAtjkJMZtPuWB3XVOiIt7qtKT4,1206
+coderay/core/utils.py,sha256=mS7l95e0CHWQyYoCKHbXNutovMrZmM-MuGJsd7q45ps,1007
+coderay/embedding/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+coderay/embedding/base.py,sha256=NfVZYXta8LtQkLxGQnXooO3mvkrDE8c8l_8-SnFZxzo,1898
+coderay/embedding/local.py,sha256=kWD3xxGnyh9jESruzGVnfkpwvHBk2s_IOIEDOf0CrqQ,2270
+coderay/embedding/openai.py,sha256=YV-s_54vg6gmtsgqY_mkazwKsTNpBmG-ewUlsL9POPM,2664
+coderay/graph/__init__.py,sha256=n7xjWW75ixceMYDiFey-rWA0gnv9EiacN9gxC6IW24k,390
+coderay/graph/builder.py,sha256=jLrIeoBZlHowk7LukOXrKt-9EinXiEDG_k2owCykUpk,4178
+coderay/graph/code_graph.py,sha256=K2ot0xTEzr2OnkNZ98r-ENQNI6dtbGuBttSsuVi-aJU,11834
+coderay/graph/extractor.py,sha256=tVYU6DRwuR3Sg5yEWhmwqVvHoFjUu0LuDRkoPenb2WQ,11374
+coderay/mcp_server/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+coderay/mcp_server/server.py,sha256=FPkQeP0GMMipzb2WE8b1uW8jgfS3ckJLFxDh9UUucbk,5266
+coderay/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+coderay/pipeline/indexer.py,sha256=OQoclLmiccp8fePIQZ-EgX_E4GlIzMWmQmqpOylY158,14562
+coderay/pipeline/watcher.py,sha256=qcaf1qn4laWlKPqfnpPj-o8BOVQMB9Llo7D9cvhx7y4,10819
+coderay/retrieval/__init__.py,sha256=wSvm8oqG2cDJ4ZwU6C3Nr53-X6peTKWTjMJ8ppvUoSM,72
+coderay/retrieval/boosting.py,sha256=Dt155PUx6jpNyC-uJXC32aN3U-tSUoYxUyrMM6UjGkw,2708
+coderay/retrieval/search.py,sha256=8HcDxI4ETn68dTTxH-SkcG1rI-u13zvIgvt0YMqAl8c,4082
+coderay/skeleton/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+coderay/skeleton/extractor.py,sha256=8Sj5uRK3aD2N5xodSADyuE1n7Lk-QnY6UgaZaEByOu0,4327
+coderay/state/__init__.py,sha256=S-jhUo2d3MHUpA-iZ7-aBsZpfOiLKZyjiHx5_kXiTMI,170
+coderay/state/machine.py,sha256=9ZLp_ipELbl8zuudt1OkBOHLRd_j8Jd0ZIlDr7nbz6s,8080
+coderay/state/version.py,sha256=7lhm_5P-BZorRWDjdRA6WPsbYd8c6sTyFLgcAVqFeW0,1460
+coderay/storage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+coderay/storage/lancedb.py,sha256=ObI4FZImt4tliXES9r1ZMBUiXglf8y86b_lAGGpffHQ,9106
+coderay/vcs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+coderay/vcs/git.py,sha256=7BXSD6WiN6x00y1L-AfsmGCluGrADkZBd-PnkMGwK3Q,6873
+coderay-1.0.0.dist-info/METADATA,sha256=KEjusMfKk54wD4mEczTtxOdxEME3OcKTBEr_bMqte1o,4572
+coderay-1.0.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+coderay-1.0.0.dist-info/entry_points.txt,sha256=65dwbAFCsgaWMOU_2t96DdRPQpR8FKS0aNVRpP-z8R8,99
+coderay-1.0.0.dist-info/top_level.txt,sha256=cSLZvS3I0PUDfAXcHaWDg2hqt5GonzlqCBoSaPM7Dxg,8
+coderay-1.0.0.dist-info/RECORD,,

coderay-1.0.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

coderay-1.0.0.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+coderay = coderay.cli.commands:main
+coderay-mcp = coderay.mcp_server.server:main

coderay-1.0.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+coderay