cocoindex-code 0.2.35__tar.gz → 0.2.37__tar.gz

cocoindex_code-0.2.35/README.md → cocoindex_code-0.2.37/PKG-INFO

@@ -1,3 +1,47 @@
+Metadata-Version: 2.4
+Name: cocoindex-code
+Version: 0.2.37
+Summary: MCP server for indexing and querying codebases using CocoIndex
+Project-URL: Homepage, https://github.com/cocoindex-io/cocoindex-code
+Project-URL: Repository, https://github.com/cocoindex-io/cocoindex-code
+Project-URL: Issues, https://github.com/cocoindex-io/cocoindex-code/issues
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: cocoindex,codebase,indexing,mcp,vector-search
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Requires-Dist: cocoindex[litellm]<1.1.0,>=1.0.13
+Requires-Dist: einops>=0.8.2
+Requires-Dist: mcp>=1.0.0
+Requires-Dist: msgspec>=0.19.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: pathspec>=0.12.1
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: questionary>=2.0.0
+Requires-Dist: sqlite-vec>=0.1.0
+Requires-Dist: typer>=0.9.0
+Provides-Extra: dev
+Requires-Dist: cocoindex[sentence-transformers]<1.1.0,>=1.0.13; extra == 'dev'
+Requires-Dist: mypy>=1.0.0; extra == 'dev'
+Requires-Dist: prek>=0.1.0; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.21.0; extra == 'dev'
+Requires-Dist: pytest-cov>=4.0.0; extra == 'dev'
+Requires-Dist: pytest>=7.0.0; extra == 'dev'
+Requires-Dist: ruff>=0.1.0; extra == 'dev'
+Provides-Extra: embeddings-local
+Requires-Dist: cocoindex[sentence-transformers]<1.1.0,>=1.0.13; extra == 'embeddings-local'
+Provides-Extra: full
+Requires-Dist: cocoindex[sentence-transformers]<1.1.0,>=1.0.13; extra == 'full'
+Description-Content-Type: text/markdown
+
 <p align="center">
 <img width="2428" alt="cocoindex code" src="https://github.com/user-attachments/assets/d05961b4-0b7b-42ea-834a-59c3c01717ca" />
 </p>
@@ -77,6 +121,17 @@ The agent uses semantic search automatically when it would be helpful. You can a
 
 Works with [Claude Code](https://docs.anthropic.com/en/docs/claude-code) and other skill-compatible agents.
 
+#### Claude Code plugin marketplace
+
+For Claude Code users, this repository is also a [plugin marketplace](https://code.claude.com/docs/en/plugin-marketplaces). Install the skill from inside Claude Code with:
+
+```text
+/plugin marketplace add Roxabi/cocoindex-code
+/plugin install cocoindex-code@cocoindex-code
+```
+
+This bundles the same `ccc` skill, with version pinning and `/plugin marketplace update` for updates.
+
 ### MCP Server
 
 Alternatively, use `ccc mcp` to run as an MCP server:
@@ -169,6 +224,7 @@ The background daemon starts automatically on first use.
 | `ccc init` | Initialize a project — creates settings files, adds `.cocoindex_code/` to `.gitignore` |
 | `ccc index` | Build or update the index (auto-inits if needed). Shows streaming progress. |
 | `ccc search <query>` | Semantic search across the codebase |
+| `ccc grep <pattern> [path]` | Structural code search by example (no index needed) |
 | `ccc status` | Show index stats (chunk count, file count, language breakdown) |
 | `ccc mcp` | Run as MCP server in stdio mode |
 | `ccc doctor` | Run diagnostics — checks settings, daemon, model, file matching, and index health |
@@ -189,6 +245,36 @@ ccc search --refresh database schema                 # update index first, then
 
 By default, `ccc search` scopes results to your current working directory (relative to the project root). Use `--path` to override.
 
+### Structural Search (`ccc grep`)
+
+`ccc grep` finds code by **structure**, not text — you write a by-example pattern
+and it matches the syntax tree (via cocoindex's `code_match`), so formatting,
+whitespace, and intervening tokens don't matter. It runs entirely locally: no
+index, daemon, or embeddings required.
+
+```bash
+ccc grep 'def \NAME(\(ARGS*\)):'                      # every Python function def under the cwd
+ccc grep 'foo(\(ARGS*\))' src/                        # calls to foo(...) anywhere under src/
+ccc grep 'fn \NAME(\(A*\))' --lang rust               # restrict to one language
+ccc grep 'class \NAME:' --path 'tests/**'            # restrict to a path glob
+ccc grep 'TODO(\(A*\))' path/to/file.py               # a single file
+```
+
+Metavariables use the `\` sigil: `\NAME` captures one node, `\(NAME*\)` a run of
+siblings, `\_`/`\*` match anonymously. The pattern is matched per language, so a
+single invocation scans every supported source file (others are skipped). Inside
+an initialized project, `ccc grep` honors the project's include/exclude patterns
+and `.gitignore`; otherwise it scans all supported source files under the path.
+
+Results stream to the terminal file-by-file as each match is found (in completion
+order, since files are matched in parallel) rather than all at once at the end.
+Each matching file shows its matched line range; under a TTY the path is colored,
+line numbers are dimmed, and the unmatched context around a match is dimmed so the
+match stands out.
+
+> **Note:** `ccc grep` relies on cocoindex's structural `code_match` feature.
+> Until it ships in a released cocoindex, run against a local cocoindex build.
+
 ## Docker
 
 A Docker image is available for teams who want a reproducible, dependency-free
@@ -380,6 +466,8 @@ docker build -t cocoindex-code:local -f docker/Dockerfile .
 
 ## Configuration
 
+For a detailed guide on choosing and configuring embedding models, see [EMBEDDINGS.md](EMBEDDINGS.md).
+
 Configuration lives in two YAML files, both created automatically by `ccc init`.
 
 ### User Settings (`~/.cocoindex_code/global_settings.yml`)
@@ -737,6 +825,33 @@ Using uv (install or upgrade):
 uv tool install --upgrade cocoindex-code
 ```
 
+### `MDB_MAP_FULL: Environment mapsize limit reached`
+
+The index is stored in an LMDB database whose maximum size is fixed when the daemon starts. The default ceiling is **4 GiB**, which is plenty for most projects but can be exhausted by very large codebases (tens of thousands of files), especially with high-dimensional embedding models like `nomic-ai/CodeRankEmbed`.
+
+Raise the ceiling with the `COCOINDEX_LMDB_MAP_SIZE` environment variable (value in **bytes**). LMDB only grows the file as data is written, so a high limit doesn't pre-allocate disk — it's safe to set it generously:
+
+```yaml
+# ~/.cocoindex_code/global_settings.yml
+envs:
+  COCOINDEX_LMDB_MAP_SIZE: "34359738368"   # 32 GiB (= 32 * 1024^3)
+```
+
+Or, if you prefer to set it in your shell environment (the daemon inherits it):
+
+```bash
+export COCOINDEX_LMDB_MAP_SIZE=$((32 * 1024 * 1024 * 1024))   # 32 GiB
+```
+
+The map size is read when the daemon starts, so restart it to pick up the change, then re-index:
+
+```bash
+ccc daemon restart
+ccc index
+```
+
+> This manual step is temporary. Once [cocoindex#2108](https://github.com/cocoindex-io/cocoindex/issues/2108) lands, the map size grows automatically when needed and `COCOINDEX_LMDB_MAP_SIZE` won't be necessary.
+
 ## Legacy: Environment Variables
 
 If you previously configured `cocoindex-code` via environment variables, the `cocoindex-code` MCP command still reads them and auto-migrates to YAML settings on first run. We recommend switching to the YAML settings for new setups.
@@ -764,18 +879,39 @@ export COCOINDEX_DISABLE_USAGE_TRACKING=1
 ## Large codebase / Enterprise
 [CocoIndex](https://github.com/cocoindex-io/cocoindex) is an ultra efficient indexing engine that also works on large codebases at scale for enterprises. In enterprise scenarios it is a lot more efficient to share indexes with teammates when there are large or many repos. We also have advanced features like branch dedupe etc designed for enterprise users.
 
+> Indexing a very large codebase and hitting `MDB_MAP_FULL`? Raise the LMDB map size — see [`MDB_MAP_FULL: Environment mapsize limit reached`](#mdb_map_full-environment-mapsize-limit-reached) under Troubleshooting.
+
 If you need help with remote setup, please email our maintainer linghua@cocoindex.io, happy to help!
 
 ## Contributing
 
-We welcome contributions! Before you start, please install the [pre-commit](https://pre-commit.com/) hooks so that linting, formatting, type checking, and tests run automatically before each commit:
+We welcome contributions! This project uses [uv](https://docs.astral.sh/uv/getting-started/installation/) for development, and every PR is gated on the same lint, format, type-check, and test suite in CI. **Please run these checks locally before opening a PR** — failing pre-commit checks are the most common cause of red CI on incoming PRs.
+
+### 1. Install the dev dependencies
+
+After installing [uv](https://docs.astral.sh/uv/getting-started/installation/), sync the project. This installs everything the checks need — including [prek](https://github.com/j178/prek), a fast pre-commit runner, plus Ruff, mypy, and pytest:
+
+```bash
+uv sync
+```
+
+### 2. Run all checks before every PR
+
+Run the full hook suite across all files — this is exactly what CI runs:
 
 ```bash
-pip install pre-commit
-pre-commit install
+uv run prek run --all-files
 ```
 
-This catches common issues — trailing whitespace, lint errors (Ruff), type errors (mypy), and test failures — before they reach CI.
+It runs trailing-whitespace/end-of-file fixes, Ruff lint (`--fix`) and format, `uv.lock` validation, mypy type checking, and the pytest suite. Fix anything it reports (Ruff auto-fixes most lint/format issues for you), re-run until it passes, then push.
+
+### 3. (Optional) Run automatically on each commit
+
+To have the same checks run on every `git commit`, install the git hook once:
+
+```bash
+uv run prek install
+```
 
 For more details, see our [contributing guide](https://cocoindex.io/docs/contributing/guide).
 

cocoindex_code-0.2.35/PKG-INFO → cocoindex_code-0.2.37/README.md

@@ -1,47 +1,3 @@
-Metadata-Version: 2.4
-Name: cocoindex-code
-Version: 0.2.35
-Summary: MCP server for indexing and querying codebases using CocoIndex
-Project-URL: Homepage, https://github.com/cocoindex-io/cocoindex-code
-Project-URL: Repository, https://github.com/cocoindex-io/cocoindex-code
-Project-URL: Issues, https://github.com/cocoindex-io/cocoindex-code/issues
-License-Expression: Apache-2.0
-License-File: LICENSE
-Keywords: cocoindex,codebase,indexing,mcp,vector-search
-Classifier: Development Status :: 3 - Alpha
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: >=3.11
-Requires-Dist: cocoindex[litellm]<1.1.0,>=1.0.6
-Requires-Dist: einops>=0.8.2
-Requires-Dist: mcp>=1.0.0
-Requires-Dist: msgspec>=0.19.0
-Requires-Dist: numpy>=1.24.0
-Requires-Dist: pathspec>=0.12.1
-Requires-Dist: pydantic>=2.0.0
-Requires-Dist: pyyaml>=6.0
-Requires-Dist: questionary>=2.0.0
-Requires-Dist: sqlite-vec>=0.1.0
-Requires-Dist: typer>=0.9.0
-Provides-Extra: dev
-Requires-Dist: cocoindex[sentence-transformers]<1.1.0,>=1.0.6; extra == 'dev'
-Requires-Dist: mypy>=1.0.0; extra == 'dev'
-Requires-Dist: prek>=0.1.0; extra == 'dev'
-Requires-Dist: pytest-asyncio>=0.21.0; extra == 'dev'
-Requires-Dist: pytest-cov>=4.0.0; extra == 'dev'
-Requires-Dist: pytest>=7.0.0; extra == 'dev'
-Requires-Dist: ruff>=0.1.0; extra == 'dev'
-Provides-Extra: embeddings-local
-Requires-Dist: cocoindex[sentence-transformers]<1.1.0,>=1.0.6; extra == 'embeddings-local'
-Provides-Extra: full
-Requires-Dist: cocoindex[sentence-transformers]<1.1.0,>=1.0.6; extra == 'full'
-Description-Content-Type: text/markdown
-
 <p align="center">
 <img width="2428" alt="cocoindex code" src="https://github.com/user-attachments/assets/d05961b4-0b7b-42ea-834a-59c3c01717ca" />
 </p>
@@ -121,6 +77,17 @@ The agent uses semantic search automatically when it would be helpful. You can a
 
 Works with [Claude Code](https://docs.anthropic.com/en/docs/claude-code) and other skill-compatible agents.
 
+#### Claude Code plugin marketplace
+
+For Claude Code users, this repository is also a [plugin marketplace](https://code.claude.com/docs/en/plugin-marketplaces). Install the skill from inside Claude Code with:
+
+```text
+/plugin marketplace add Roxabi/cocoindex-code
+/plugin install cocoindex-code@cocoindex-code
+```
+
+This bundles the same `ccc` skill, with version pinning and `/plugin marketplace update` for updates.
+
 ### MCP Server
 
 Alternatively, use `ccc mcp` to run as an MCP server:
@@ -213,6 +180,7 @@ The background daemon starts automatically on first use.
 | `ccc init` | Initialize a project — creates settings files, adds `.cocoindex_code/` to `.gitignore` |
 | `ccc index` | Build or update the index (auto-inits if needed). Shows streaming progress. |
 | `ccc search <query>` | Semantic search across the codebase |
+| `ccc grep <pattern> [path]` | Structural code search by example (no index needed) |
 | `ccc status` | Show index stats (chunk count, file count, language breakdown) |
 | `ccc mcp` | Run as MCP server in stdio mode |
 | `ccc doctor` | Run diagnostics — checks settings, daemon, model, file matching, and index health |
@@ -233,6 +201,36 @@ ccc search --refresh database schema                 # update index first, then
 
 By default, `ccc search` scopes results to your current working directory (relative to the project root). Use `--path` to override.
 
+### Structural Search (`ccc grep`)
+
+`ccc grep` finds code by **structure**, not text — you write a by-example pattern
+and it matches the syntax tree (via cocoindex's `code_match`), so formatting,
+whitespace, and intervening tokens don't matter. It runs entirely locally: no
+index, daemon, or embeddings required.
+
+```bash
+ccc grep 'def \NAME(\(ARGS*\)):'                      # every Python function def under the cwd
+ccc grep 'foo(\(ARGS*\))' src/                        # calls to foo(...) anywhere under src/
+ccc grep 'fn \NAME(\(A*\))' --lang rust               # restrict to one language
+ccc grep 'class \NAME:' --path 'tests/**'            # restrict to a path glob
+ccc grep 'TODO(\(A*\))' path/to/file.py               # a single file
+```
+
+Metavariables use the `\` sigil: `\NAME` captures one node, `\(NAME*\)` a run of
+siblings, `\_`/`\*` match anonymously. The pattern is matched per language, so a
+single invocation scans every supported source file (others are skipped). Inside
+an initialized project, `ccc grep` honors the project's include/exclude patterns
+and `.gitignore`; otherwise it scans all supported source files under the path.
+
+Results stream to the terminal file-by-file as each match is found (in completion
+order, since files are matched in parallel) rather than all at once at the end.
+Each matching file shows its matched line range; under a TTY the path is colored,
+line numbers are dimmed, and the unmatched context around a match is dimmed so the
+match stands out.
+
+> **Note:** `ccc grep` relies on cocoindex's structural `code_match` feature.
+> Until it ships in a released cocoindex, run against a local cocoindex build.
+
 ## Docker
 
 A Docker image is available for teams who want a reproducible, dependency-free
@@ -424,6 +422,8 @@ docker build -t cocoindex-code:local -f docker/Dockerfile .
 
 ## Configuration
 
+For a detailed guide on choosing and configuring embedding models, see [EMBEDDINGS.md](EMBEDDINGS.md).
+
 Configuration lives in two YAML files, both created automatically by `ccc init`.
 
 ### User Settings (`~/.cocoindex_code/global_settings.yml`)
@@ -781,6 +781,33 @@ Using uv (install or upgrade):
 uv tool install --upgrade cocoindex-code
 ```
 
+### `MDB_MAP_FULL: Environment mapsize limit reached`
+
+The index is stored in an LMDB database whose maximum size is fixed when the daemon starts. The default ceiling is **4 GiB**, which is plenty for most projects but can be exhausted by very large codebases (tens of thousands of files), especially with high-dimensional embedding models like `nomic-ai/CodeRankEmbed`.
+
+Raise the ceiling with the `COCOINDEX_LMDB_MAP_SIZE` environment variable (value in **bytes**). LMDB only grows the file as data is written, so a high limit doesn't pre-allocate disk — it's safe to set it generously:
+
+```yaml
+# ~/.cocoindex_code/global_settings.yml
+envs:
+  COCOINDEX_LMDB_MAP_SIZE: "34359738368"   # 32 GiB (= 32 * 1024^3)
+```
+
+Or, if you prefer to set it in your shell environment (the daemon inherits it):
+
+```bash
+export COCOINDEX_LMDB_MAP_SIZE=$((32 * 1024 * 1024 * 1024))   # 32 GiB
+```
+
+The map size is read when the daemon starts, so restart it to pick up the change, then re-index:
+
+```bash
+ccc daemon restart
+ccc index
+```
+
+> This manual step is temporary. Once [cocoindex#2108](https://github.com/cocoindex-io/cocoindex/issues/2108) lands, the map size grows automatically when needed and `COCOINDEX_LMDB_MAP_SIZE` won't be necessary.
+
 ## Legacy: Environment Variables
 
 If you previously configured `cocoindex-code` via environment variables, the `cocoindex-code` MCP command still reads them and auto-migrates to YAML settings on first run. We recommend switching to the YAML settings for new setups.
@@ -808,18 +835,39 @@ export COCOINDEX_DISABLE_USAGE_TRACKING=1
 ## Large codebase / Enterprise
 [CocoIndex](https://github.com/cocoindex-io/cocoindex) is an ultra efficient indexing engine that also works on large codebases at scale for enterprises. In enterprise scenarios it is a lot more efficient to share indexes with teammates when there are large or many repos. We also have advanced features like branch dedupe etc designed for enterprise users.
 
+> Indexing a very large codebase and hitting `MDB_MAP_FULL`? Raise the LMDB map size — see [`MDB_MAP_FULL: Environment mapsize limit reached`](#mdb_map_full-environment-mapsize-limit-reached) under Troubleshooting.
+
 If you need help with remote setup, please email our maintainer linghua@cocoindex.io, happy to help!
 
 ## Contributing
 
-We welcome contributions! Before you start, please install the [pre-commit](https://pre-commit.com/) hooks so that linting, formatting, type checking, and tests run automatically before each commit:
+We welcome contributions! This project uses [uv](https://docs.astral.sh/uv/getting-started/installation/) for development, and every PR is gated on the same lint, format, type-check, and test suite in CI. **Please run these checks locally before opening a PR** — failing pre-commit checks are the most common cause of red CI on incoming PRs.
+
+### 1. Install the dev dependencies
+
+After installing [uv](https://docs.astral.sh/uv/getting-started/installation/), sync the project. This installs everything the checks need — including [prek](https://github.com/j178/prek), a fast pre-commit runner, plus Ruff, mypy, and pytest:
+
+```bash
+uv sync
+```
+
+### 2. Run all checks before every PR
+
+Run the full hook suite across all files — this is exactly what CI runs:
 
 ```bash
-pip install pre-commit
-pre-commit install
+uv run prek run --all-files
 ```
 
-This catches common issues — trailing whitespace, lint errors (Ruff), type errors (mypy), and test failures — before they reach CI.
+It runs trailing-whitespace/end-of-file fixes, Ruff lint (`--fix`) and format, `uv.lock` validation, mypy type checking, and the pytest suite. Fix anything it reports (Ruff auto-fixes most lint/format issues for you), re-run until it passes, then push.
+
+### 3. (Optional) Run automatically on each commit
+
+To have the same checks run on every `git commit`, install the git hook once:
+
+```bash
+uv run prek install
+```
 
 For more details, see our [contributing guide](https://cocoindex.io/docs/contributing/guide).
 

{cocoindex_code-0.2.35 → cocoindex_code-0.2.37}/pyproject.toml

@@ -23,7 +23,7 @@ classifiers = [
 
 dependencies = [
     "mcp>=1.0.0",
-    "cocoindex[litellm]>=1.0.6,<1.1.0",
+    "cocoindex[litellm]>=1.0.13,<1.1.0",
     "sqlite-vec>=0.1.0",
     "pydantic>=2.0.0",
     "numpy>=1.24.0",
@@ -39,7 +39,7 @@ dependencies = [
 # `embeddings-local` is the primary feature extra: it pulls in
 # `sentence-transformers` (via cocoindex) so local embeddings work without
 # an API key.
-embeddings-local = ["cocoindex[sentence-transformers]>=1.0.6,<1.1.0"]
+embeddings-local = ["cocoindex[sentence-transformers]>=1.0.13,<1.1.0"]
 # `full` is the umbrella "batteries-included" alias. Today it's just
 # `embeddings-local`, but we expect to bundle more optional niceties under
 # it over time — users who want everything can keep using `[full]` and pick
@@ -47,7 +47,7 @@ embeddings-local = ["cocoindex[sentence-transformers]>=1.0.6,<1.1.0"]
 # `:full` image variant for consistency across install paths. Contents are
 # inlined rather than self-referencing `cocoindex-code[embeddings-local]`
 # to avoid resolver edge cases with older pip.
-full = ["cocoindex[sentence-transformers]>=1.0.6,<1.1.0"]
+full = ["cocoindex[sentence-transformers]>=1.0.13,<1.1.0"]
 dev = [
     "pytest>=7.0.0",
     "pytest-asyncio>=0.21.0",
@@ -55,7 +55,7 @@ dev = [
     "ruff>=0.1.0",
     "mypy>=1.0.0",
     "prek>=0.1.0",
-    "cocoindex[sentence-transformers]>=1.0.6,<1.1.0",
+    "cocoindex[sentence-transformers]>=1.0.13,<1.1.0",
 ]
 
 [project.scripts]
@@ -89,7 +89,7 @@ dev = [
     "mypy>=1.0.0",
     "prek>=0.1.0",
     "types-pyyaml>=6.0.12.20250915",
-    "cocoindex[sentence-transformers]>=1.0.7,<1.1.0",
+    "cocoindex[sentence-transformers]>=1.0.13,<1.1.0",
 ]
 
 [tool.ruff]

{cocoindex_code-0.2.35 → cocoindex_code-0.2.37}/src/cocoindex_code/__init__.py

@@ -2,7 +2,6 @@
 
 from __future__ import annotations
 
-import logging
 import os
 from typing import TYPE_CHECKING, Any
 
@@ -11,8 +10,6 @@ from typing import TYPE_CHECKING, Any
 # init time). See cocoindex-io/cocoindex#1992.
 os.environ.setdefault("COCOINDEX_APPLICATION_FOR_TRACKING", "cocoindex-code")
 
-logging.basicConfig(level=logging.WARNING)
-
 from ._version import __version__  # noqa: E402
 
 if TYPE_CHECKING:

{cocoindex_code-0.2.35 → cocoindex_code-0.2.37}/src/cocoindex_code/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.2.35'
-__version_tuple__ = version_tuple = (0, 2, 35)
+__version__ = version = '0.2.37'
+__version_tuple__ = version_tuple = (0, 2, 37)
 
 __commit_id__ = commit_id = None

{cocoindex_code-0.2.35 → cocoindex_code-0.2.37}/src/cocoindex_code/cli.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import functools
 import os
 import sys
+import threading
 from collections.abc import Callable
 from pathlib import Path
 from typing import TYPE_CHECKING, TypeVar
@@ -12,6 +13,7 @@ from typing import TYPE_CHECKING, TypeVar
 import typer as _typer
 
 if TYPE_CHECKING:
+    from .grep import FileMatches, GrepWarning
     from .protocol import (
         DoctorCheckResult,
         IndexingProgress,
@@ -657,6 +659,79 @@ def search(
     print_search_results(resp)
 
 
+@app.command()
+def grep(
+    pattern: str = _typer.Argument(
+        ...,
+        help=r"By-example structural pattern; use \ for metavariables, "
+        r"e.g. 'def \NAME(\(ARGS*\)):' or 'foo(\(ARGS*\))'.",
+    ),
+    path: str = _typer.Argument(
+        ".", help="File or directory to search (default: current directory)."
+    ),
+    lang: list[str] = _typer.Option(
+        [], "--lang", help="Only match files of these languages (e.g. python, rust, cpp)."
+    ),
+    path_glob: str | None = _typer.Option(
+        None, "--path", help="Only match files whose path matches this glob (globset syntax)."
+    ),
+    no_color: bool = _typer.Option(False, "--no-color", help="Disable colored output."),
+) -> None:
+    r"""Structurally grep code by example (no index or daemon required).
+
+    Compiles the pattern per language and matches every supported source file
+    under PATH in parallel. Inside an initialized project it honors the project's
+    include/exclude and .gitignore rules; otherwise it scans all supported source
+    files.
+    """
+    from . import grep as _grep
+
+    target = Path(path)
+    if not target.exists():
+        _typer.echo(f"Error: path not found: {path}", err=True)
+        raise _typer.Exit(code=1)
+
+    req = _grep.GrepRequest(
+        pattern=pattern,
+        root=target,
+        languages=frozenset(lang_name.lower() for lang_name in lang) or None,
+        path_glob=path_glob,
+    )
+    use_color = not no_color and sys.stdout.isatty() and not os.environ.get("NO_COLOR")
+    grep_run = _grep.Grep(req)
+    matched = 0
+    # `run` calls `_emit` from several worker threads at once; the lock keeps one
+    # file's output (and the `matched` bookkeeping) from interleaving with another's.
+    output_lock = threading.Lock()
+
+    def _emit(item: FileMatches | GrepWarning) -> None:
+        nonlocal matched
+        if isinstance(item, _grep.GrepWarning):
+            with output_lock:
+                _typer.echo(f"warning: {item.message}", err=True)
+            return
+        block = _grep.render_file(item, color=use_color)  # render outside the lock
+        with output_lock:
+            if matched:
+                _typer.echo()  # blank line between files
+            _typer.echo(block)
+            matched += 1
+
+    grep_run.run(_emit)
+
+    # The "unusable everywhere" verdict needs the whole walk, so it's known only
+    # once the run is done — report it before exiting.
+    if grep_run.unusable:
+        langs = ", ".join(grep_run.failed_languages)
+        _typer.echo(
+            f"Error: the pattern did not compile for any of the languages found ({langs}).",
+            err=True,
+        )
+        raise _typer.Exit(code=1)
+    if matched == 0:
+        _typer.echo("No matches found.")
+
+
 @app.command()
 @_catch_daemon_start_error
 def status() -> None:

{cocoindex_code-0.2.35 → cocoindex_code-0.2.37}/src/cocoindex_code/daemon.py

@@ -372,10 +372,8 @@ async def _check_file_walk(project_root_str: str) -> DoctorCheckResult:
     """Walk project files and report counts + gitignore paths."""
     from pathlib import PurePath
 
-    from cocoindex.resources.file import PatternFilePathMatcher
-
-    from .indexer import GitignoreAwareMatcher
-    from .settings import load_gitignore_spec, load_project_settings
+    from .file_walk import build_matcher
+    from .settings import load_project_settings
 
     project_root = Path(project_root_str)
     try:
@@ -383,12 +381,7 @@ async def _check_file_walk(project_root_str: str) -> DoctorCheckResult:
     except FileNotFoundError as e:
         return DoctorCheckResult(name="File Walk", ok=False, details=[], errors=[str(e)])
 
-    gitignore_spec = load_gitignore_spec(project_root)
-    base_matcher = PatternFilePathMatcher(
-        included_patterns=ps.include_patterns,
-        excluded_patterns=ps.exclude_patterns,
-    )
-    matcher = GitignoreAwareMatcher(base_matcher, gitignore_spec, project_root)
+    matcher = build_matcher(project_root, ps.include_patterns, ps.exclude_patterns)
 
     counts_by_ext: dict[str, int] = {}
     gitignore_dirs: list[str] = []