code-metadata 0.1.0__tar.gz

code_metadata-0.1.0/.claude/settings.local.json

@@ -0,0 +1,5 @@
+{
+  "enabledMcpjsonServers": [
+    "claude-flow"
+  ]
+}

code_metadata-0.1.0/.gitignore

@@ -0,0 +1,8 @@
+__pycache__/
+*.pyc
+*.pyo
+.coverage
+.pytest_cache/
+dist/
+*.egg-info/
+.ruff_cache/

code_metadata-0.1.0/.serena/.gitignore

@@ -0,0 +1,2 @@
+/cache
+/project.local.yml

code_metadata-0.1.0/.serena/project.local.yml

@@ -0,0 +1,5 @@
+# This file allows you to locally override settings in project.yml for development purposes.
+#
+# Use the same keys as in project.yml here. Any setting you specify will override the corresponding
+# setting in project.yml, allowing you to customise the configuration for your local development environment
+# without affecting the project configuration in project.yml (which is intended to be versioned).

code_metadata-0.1.0/.serena/project.yml

@@ -0,0 +1,169 @@
+# the name by which the project can be referenced within Serena/when chatting with the LLM.
+project_name: "code-metadata-extractor"
+
+# list of language servers to start when using the LSP backend; choose from:
+#   ada                    al                     angular                ansible                bash
+#   bsl                    clojure                cpp                    cpp_ccls               crystal
+#   csharp                 csharp_omnisharp       cue                    dart                   deno
+#   elixir                 elm                    erlang                 fortran                fsharp
+#   gdscript               gleam                  go                     groovy                 haskell
+#   haxe                   hlsl                   html                   java                   json
+#   julia                  julia_fatou            kotlin                 latex                  lean4
+#   lua                    luau                   markdown               matlab                 msl
+#   nextflow               nix                    ocaml                  pascal                 perl
+#   php                    php_phpactor           php_phpantom           powershell             python
+#   python_basedpyright    python_jedi            python_pyrefly         python_ty              qml
+#   r                      rego                   ruby                   ruby_solargraph        rust
+#   scala                  scss                   solidity               svelte                 swift
+#   systemverilog          terraform              toml                   typescript             typescript_vts
+#   vue                    wolfram                yaml                   zig
+#   (This list may be outdated; generated with scripts/print_language_list.py;
+#   For the current list, see values of the LanguageServerId enum here:
+#   https://github.com/oraios/serena/blob/main/src/solidlsp/ls_config.py)
+# For some languages, there are several alternative language servers, e.g. csharp_omnisharp, ruby_solargraph.)
+# Note:
+#   - For C, use cpp
+#   - For JavaScript, use typescript
+#   - For Angular projects, use angular (subsumes typescript+html; requires `npm install` in the project root)
+#   - For Svelte projects, use svelte (subsumes typescript/javascript for .svelte projects; requires npm)
+#   - For Deno projects, use deno (serves the same .ts/.js files as typescript; requires the deno CLI on PATH)
+#   - For SCSS / Sass / plain CSS, use scss (some-sass-language-server handles all three)
+#   - For Free Pascal/Lazarus, use pascal
+# Special requirements:
+#   Some language servers require additional setup/installations.
+#   See here for details: https://oraios.github.io/serena/01-about/020_programming-languages.html#language-servers
+# When using multiple language servers, the first language server that supports a given file will be used for that file.
+# The first language server is the default language and the respective language server will be used as a fallback.
+# Note that when using the JetBrains backend, language servers are not used and this list is correspondingly ignored.
+language_servers:
+- python
+
+# the encoding used by text files in the project
+# For a list of possible encodings, see https://docs.python.org/3.11/library/codecs.html#standard-encodings
+encoding: "utf-8"
+
+# optional shell command to run before the language backend (LSP or JetBrains) is initialised.
+# the command runs in the project root directory and is only executed if the project is trusted
+# (see trusted_project_path_patterns in the global configuration).
+# serena waits for the command to exit: a non-zero exit code is logged as an error but does not
+# abort activation. a per-project timeout (activation_command_timeout, default 180s) is the safety
+# backstop for non-terminating commands; on expiry the process is killed and activation continues.
+# example: activation_command: "npx nx run-many -t build"
+activation_command:
+
+# maximum time in seconds to wait for activation_command to complete before killing it (default 180s).
+# must be a positive number.
+activation_command_timeout: 180.0
+
+# line ending convention to use when writing source files.
+# Possible values: unset (use global setting), "lf", "crlf", or "native" (platform default)
+# This does not affect Serena's own files (e.g. memories and configuration files), which always use native line endings.
+line_ending:
+
+# The language backend to use for this project.
+# If not set, the global setting from serena_config.yml is used.
+# Valid values: LSP, JetBrains
+# Note: the backend is fixed at startup. If a project with a different backend
+# is activated post-init, an error will be returned.
+language_backend:
+
+# whether to use project's .gitignore files to ignore files
+ignore_all_files_in_gitignore: true
+
+# advanced configuration option allowing to configure language server-specific options.
+# Maps the language key to the options.
+# The settings are considered only if the project is trusted (see global configuration to define trusted projects).
+# See https://oraios.github.io/serena/02-usage/050_configuration.html#language-server-specific-settings
+ls_specific_settings: {}
+
+# list of workspace folder paths (LSP backend only).
+# These folders will be used to build up Serena's symbol index.
+# Paths must be within the project root and should thus be relative to the project root.
+# Furthermore, the paths should not be filtered by ignore settings.
+# Default setting: The entire project root folder (".") is considered.
+# In (large) monorepos, this can be used to index only subfolders of the project root, e.g.
+#   ls_workspace_folders:
+#     - "./subproject1"
+#     - "./subproject2"
+ls_workspace_folders:
+- "."
+
+# list of additional workspace folder paths for cross-package reference support.
+# Paths can be absolute or relative to the project root.
+# Each folder is registered as an LSP workspace folder, enabling language servers to discover
+# symbols and references across package boundaries, but these folders are not indexed by Serena,
+# i.e. the respective symbols will not be found using Serena's symbol search tools.
+# Example:
+#   additional_workspace_folders:
+#     - ../sibling-package
+#     - ../shared-lib
+ls_additional_workspace_folders: []
+
+# list of additional paths to ignore in this project.
+# Same syntax as gitignore, so you can use * and **.
+# Important: quote patterns that start with `*`, otherwise YAML treats them as aliases.
+# Example:
+#   ignored_paths:
+#     - "examples/**"
+#     - ".worktrees/**"
+#     - "**/bin/**"
+#     - "**/obj/**"
+# Note: global ignored_paths from serena_config.yml are also applied additively.
+ignored_paths: []
+
+# whether the project is in read-only mode
+# If set to true, all editing tools will be disabled and attempts to use them will result in an error
+# Added on 2025-04-18
+read_only: false
+
+# list of tool names to exclude.
+# This extends the existing exclusions (e.g. from the global configuration)
+# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
+excluded_tools: []
+
+# list of tools to include that would otherwise be disabled (particularly optional tools that are disabled by default).
+# This extends the existing inclusions (e.g. from the global configuration).
+# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
+included_optional_tools: []
+
+# fixed set of tools to use as the base tool set (if non-empty), replacing Serena's default set of tools.
+# This cannot be combined with non-empty excluded_tools or included_optional_tools.
+# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
+fixed_tools: []
+
+# list of mode names that are to be activated by default, overriding the setting in the global configuration.
+# The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes.
+# If the setting is undefined/empty, the default_modes from the global configuration (serena_config.yml) apply.
+# Otherwise, this overrides the setting from the global configuration (serena_config.yml).
+# Therefore, you can set this to [] if you do not want the default modes defined in the global config to apply
+# for this project.
+# This setting can, in turn, be overridden by CLI parameters (--mode).
+# See https://oraios.github.io/serena/02-usage/050_configuration.html#modes
+default_modes:
+
+# list of mode names to be activated additionally for this project, e.g. ["query-projects"]
+# The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes.
+# See https://oraios.github.io/serena/02-usage/050_configuration.html#modes
+added_modes:
+
+# initial prompt for the project. It will always be given to the LLM upon activating the project
+# (contrary to the memories, which are loaded on demand).
+initial_prompt: ""
+
+# time budget (seconds) per tool call for the retrieval of additional symbol information
+# such as docstrings or parameter information.
+# This overrides the corresponding setting in the global configuration; see the documentation there.
+# If null or missing, use the setting from the global configuration.
+symbol_info_budget:
+
+# list of regex patterns which, when matched, mark a memory entry as read‑only.
+# Extends the list from the global configuration, merging the two lists.
+read_only_memory_patterns: []
+
+# list of regex patterns for memories to completely ignore.
+# Matching memories will not appear in list_memories or activate_project output
+# and cannot be accessed via read_memory or write_memory.
+# To access ignored memory files, use the read_file tool on the raw file path.
+# Extends the list from the global configuration, merging the two lists.
+# Example: ["_archive/.*", "_episodes/.*"]
+ignored_memory_patterns: []

code_metadata-0.1.0/CLAUDE.md

@@ -0,0 +1,70 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+# code-metadata-extractor
+
+Python-only repository metadata extraction tool. AST-based, no LLM in MVP.
+
+## Stack
+
+- Python 3.11+
+- `radon` — cyclomatic complexity + LOC
+- `gitpython` — git blame (author, date, commit count)
+- `pydantic` v2 — schema / validation
+- `typer` + `rich` — CLI
+- `ruff` — lint/format
+- `pytest` + `pytest-cov` — tests (target: 80%+, currently 95 tests / 94.6%)
+
+## Commands
+
+```bash
+# Setup
+pip install -e ".[dev]"
+
+# Run all tests (coverage enforced via pyproject addopts, fails under 80%)
+pytest
+
+# Run a single test file / test
+pytest tests/test_parser.py
+pytest tests/test_parser.py::test_parses_function_params -v
+
+# Lint / format
+ruff check src/
+ruff format src/ tests/
+
+# Run the CLI locally
+code-metadata extract /path/to/repo --format json
+code-metadata extract /path/to/repo --format csv --output out.csv
+code-metadata extract /path/to/repo --no-git   # skip git blame, works on non-git dirs
+```
+
+## Architecture
+
+The extractor is a linear enrichment pipeline, orchestrated by `extract_repo()` in `cli.py`. Each `.py` file under the target repo flows through the same sequence of mutation passes before being validated into the final Pydantic schema:
+
+```
+parser.parse_file(path)            → raw dict: functions/classes/imports/total_lines (per file, AST-only)
+  → analyzer.enrich_file(parsed, source, test_index)  → adds complexity (radon), LOC, has_test/test_files
+  → docstring_scorer.enrich_docstrings(parsed)        → adds docstring style + quality_score (0-1)
+  → git_utils.enrich_git(parsed)                      → adds git_metadata (or None if --no-git / non-git repo)
+  → cli._to_file_metadata(parsed)                     → validates into schema.FileMetadata (Pydantic)
+```
+
+Key points for working in this codebase:
+
+- **Dicts until the end.** `parser.py`, `analyzer.py`, `docstring_scorer.py`, and `git_utils.py` all mutate plain `dict` structures in place (functions/classes as nested dicts with a `methods` list). Pydantic validation (`schema.py` models) only happens once, at the very end, in `cli._to_file_metadata` / `_to_class_metadata` / `_to_function_metadata`. Don't introduce schema objects earlier in the pipeline — the enrichment stages are intentionally schema-agnostic.
+- **`build_test_index(root)` runs once per repo** (in `analyzer.py`), before the per-file loop, and is passed into every `enrich_file` call — it scans all `test_*.py`/`*_test.py` files up front so each function lookup for `has_test` is a dict lookup, not a re-scan.
+- **Git blame is cached per file**, not per function/method — `git_utils.py` calls `git blame` once per file and slices results per line range, keeping cost linear in files rather than functions.
+- **Errors are contained per-file.** A file that fails Pydantic validation in `extract_repo` is caught and skipped with a console warning (`cli.py`), not aborted — the run always produces output for whatever parsed successfully. A file with a Python `SyntaxError` is not skipped outright; `parser.parse_file` returns it with empty functions/classes and a `parse_error` field instead of raising.
+- **Docstring scoring is heuristic, not semantic** (`docstring_scorer.py`): style detection (numpy/google/sphinx/unstructured/none) plus presence of args/returns/example sections, no LLM. This is called out in design decisions below because it's the most likely thing a future contributor will assume is "just a stub" — it's the intended MVP behavior.
+- **Test coverage is inferred, not measured**: `analyzer.py` looks for a `test_<funcname>` symbol in `test_*.py`/`*_test.py` files, it does not run the target repo's test suite or read coverage data.
+- **Exporters (`exporters.py`) consume the fully-validated `RepositoryMetadata`** — CSV flattening logic (methods promoted to top-level rows with `parent_class` set) lives only there, not upstream.
+
+## Design decisions
+
+- Git integration is optional: non-git repos produce `git_metadata: null`, no crash.
+- Blame is cached per file (one call per file, not per function line).
+- Docstring style detection: numpy / google / sphinx / unstructured / none — heuristic, no LLM.
+- Test coverage is *inferred*: presence of `test_<funcname>` in `test_*.py` or `*_test.py`.
+- No domain-agnostic abstraction in MVP — code domain only, generalize after shipping.

code_metadata-0.1.0/PKG-INFO

@@ -0,0 +1,16 @@
+Metadata-Version: 2.5
+Name: code-metadata
+Version: 0.1.0
+Summary: Python repository metadata extractor — AST-based, no LLM
+Requires-Python: >=3.11
+Requires-Dist: gitpython>=3.1
+Requires-Dist: pydantic>=2.0
+Requires-Dist: radon>=6.0
+Requires-Dist: rich>=13.0
+Requires-Dist: typer>=0.12
+Provides-Extra: dev
+Requires-Dist: pytest-cov>=5.0; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: ruff>=0.4; extra == 'dev'
+Provides-Extra: llm
+Requires-Dist: anthropic>=0.34; extra == 'llm'

code_metadata-0.1.0/README.md

@@ -0,0 +1,122 @@
+# code-metadata-extractor
+
+Extract rich metadata from Python repositories — no LLM, no API keys, fully deterministic.
+
+Walks every `.py` file via AST and produces structured data on functions, methods, and classes: complexity, docstring quality, git history, and inferred test coverage.
+
+## Features
+
+| Metadata | Source |
+|---|---|
+| Cyclomatic complexity | `radon` |
+| Lines of code | `radon` |
+| Docstring quality score (0–1) | Heuristic: style detection + section presence |
+| Docstring style | numpy / google / sphinx / unstructured / none |
+| Git blame (author, date, commit count) | `gitpython` — cached per file |
+| Test coverage (inferred) | Detect `test_<funcname>` in `test_*.py` / `*_test.py` |
+| Type hints, decorators, async flag | `ast` |
+| Import-level dependencies per function | `ast` call-site analysis |
+
+## Install
+
+```bash
+pip install -e ".[dev]"
+```
+
+Requires Python 3.11+.
+
+## Usage
+
+```bash
+# JSON to stdout
+code-metadata extract /path/to/repo
+
+# CSV to file
+code-metadata extract /path/to/repo --format csv --output metadata.csv
+
+# Skip git blame (faster, works on non-git directories)
+code-metadata extract /path/to/repo --no-git
+```
+
+## Output shape (JSON)
+
+```json
+{
+  "repository_path": "/path/to/repo",
+  "analyzed_at": "2026-09-10T12:00:00Z",
+  "total_files": 12,
+  "total_functions": 84,
+  "total_classes": 9,
+  "files": [
+    {
+      "file_path": "/path/to/repo/module.py",
+      "total_lines": 120,
+      "import_count": 5,
+      "functions": [
+        {
+          "name": "parse_record",
+          "line_number": 14,
+          "end_line_number": 38,
+          "is_async": false,
+          "is_method": false,
+          "return_type": "dict",
+          "params": [{"name": "raw", "type_hint": "str"}],
+          "complexity": {
+            "cyclomatic_complexity": 4,
+            "lines_of_code": 25,
+            "has_test": true,
+            "test_files": ["tests/test_module.py"],
+            "dependencies": ["json.loads", "re.match"]
+          },
+          "docstring_quality": {
+            "presence": true,
+            "style": "google",
+            "has_args_section": true,
+            "has_return_section": true,
+            "has_example": false,
+            "quality_score": 0.7
+          },
+          "git_metadata": {
+            "author": "Alice",
+            "author_email": "alice@example.com",
+            "last_modified": "2026-08-01T09:30:00Z",
+            "commit_count": 7
+          }
+        }
+      ],
+      "classes": []
+    }
+  ]
+}
+```
+
+## CSV columns
+
+`file_path`, `name`, `line_number`, `end_line_number`, `is_method`, `is_async`, `parent_class`, `decorators`, `return_type`, `cyclomatic_complexity`, `lines_of_code`, `docstring_lines`, `has_test`, `has_docstring`, `docstring_score`, `docstring_style`, `git_author`, `git_last_modified`, `git_commit_count`
+
+## Development
+
+```bash
+# Run tests with coverage
+pytest
+
+# Lint
+ruff check src/
+
+# Format
+ruff format src/ tests/
+```
+
+95 tests, 94.6% coverage.
+
+## Design notes
+
+- **No LLM in MVP** — all extraction is deterministic and free. LLM-based semantic docstring scoring is a planned post-MVP addition.
+- **Git is optional** — non-git directories produce `git_metadata: null`, no crash.
+- **Blame is cached per file** — one `git blame` call per file, not per function line.
+- **Test coverage is inferred** — presence of `test_<funcname>` in test files, not actual execution coverage.
+- **Single domain first** — code only; generalise to other domains after shipping value.
+
+## License
+
+MIT