obsilink 0.1.0__tar.gz

obsilink-0.1.0/.gitignore

@@ -0,0 +1,207 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

obsilink-0.1.0/AGENTS.md

@@ -0,0 +1,67 @@
+# AGENTS.md
+
+## Project description
+This project provides a small, deterministic Python library that extracts Obsidian-style
+wikilink targets from input text.
+
+## Core behavior
+- Parse Obsidian links such as `[[Note]]`, `[[Note|Alias]]`, and `[[Folder/Note#Heading]]`.
+- Accept input as either:
+  - `str`
+  - a text file-like object with a `.read()` method that returns `str`
+- Return `list[str]` in encounter order.
+- Preserve duplicates.
+- Ignore malformed or partial wikilink syntax.
+- Include embed targets (for example `![[Note]]`) by default.
+- Raise `TypeError` for unsupported input types.
+- Propagate exceptions raised by `.read()`.
+- Raise `TypeError` if `.read()` returns non-string data.
+
+## Scope boundaries
+- This repository is extraction/parsing only.
+- Do not add filesystem resolution features (depth traversal, basename/path searching).
+- Do not add CLI/machine-output formatting concerns.
+- Do not rely on environment variables such as `PROJECT_DIR` in parser code.
+
+## API guidelines
+- Keep the public API small and predictable.
+- Main entry point:
+  - `extract_obsidian_links(source: str | TextIO) -> list[str]`
+- Optional extension point (if needed): `include_embeds: bool = True`.
+- Validate input types and provide clear error messages.
+
+## Non-goals
+Do not implement the following in this library:
+- recursive graph traversal (`depth`, BFS/DFS)
+- file discovery by basename/path
+- path escaping for shell/xargs
+- CLI machine-output payloads
+- `PROJECT_DIR` or other environment-based resolution
+
+## Development workflows
+
+### Environment and dependencies
+- Sync: `uv sync`
+- Update lockfile: `uv lock --upgrade`
+- Add/remove packages: `uv add <pkg>`, `uv remove <pkg>`
+
+### QA checks
+Prefix commands with `uv run`.
+- Format: `ruff format src/ tests/`
+- Lint: `ruff check src/ tests/`
+- Types: `mypy src/`
+- Tests: `pytest`
+- Full gate:
+  `uv run ruff format src/ tests/ && uv run ruff check src/ tests/ && uv run mypy src/ && uv run pytest`
+
+### Standards
+- Follow SemVer (`MAJOR.MINOR.PATCH`).
+- Use Conventional Commits (`feat:`, `fix:`, `chore:`, etc.).
+- Never commit autonomously; only commit when explicitly requested.
+
+## Coding standards
+- Keep behavior deterministic and side-effect free.
+- Use strict typing for `src/` and maintain `mypy` compatibility.
+- Keep line length at 100 characters (`ruff` configuration).
+- Prefer testing through the public API; avoid testing private symbols.
+- Keep imports at module top level (no inline imports in tests).

obsilink-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Christian Gröling
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

obsilink-0.1.0/PKG-INFO

@@ -0,0 +1,88 @@
+Metadata-Version: 2.4
+Name: obsilink
+Version: 0.1.0
+Summary: Extract Obsidian-style wikilink targets from text
+Project-URL: Homepage, https://github.com/chgroeling/obsilink
+Project-URL: Repository, https://github.com/chgroeling/obsilink
+Project-URL: Issues, https://github.com/chgroeling/obsilink/issues
+License-File: LICENSE
+Keywords: markdown,obsidian,parser,text-processing,wikilink
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+
+# AGENTS.md
+
+## Project description
+This project provides a small, deterministic Python library that extracts Obsidian-style
+wikilink targets from input text.
+
+## Core behavior
+- Parse Obsidian links such as `[[Note]]`, `[[Note|Alias]]`, and `[[Folder/Note#Heading]]`.
+- Accept input as either:
+  - `str`
+  - a text file-like object with a `.read()` method that returns `str`
+- Return `list[str]` in encounter order.
+- Preserve duplicates.
+- Ignore malformed or partial wikilink syntax.
+- Include embed targets (for example `![[Note]]`) by default.
+- Raise `TypeError` for unsupported input types.
+- Propagate exceptions raised by `.read()`.
+- Raise `TypeError` if `.read()` returns non-string data.
+
+## Scope boundaries
+- This repository is extraction/parsing only.
+- Do not add filesystem resolution features (depth traversal, basename/path searching).
+- Do not add CLI/machine-output formatting concerns.
+- Do not rely on environment variables such as `PROJECT_DIR` in parser code.
+
+## API guidelines
+- Keep the public API small and predictable.
+- Main entry point:
+  - `extract_obsidian_links(source: str | TextIO) -> list[str]`
+- Optional extension point (if needed): `include_embeds: bool = True`.
+- Validate input types and provide clear error messages.
+
+## Non-goals
+Do not implement the following in this library:
+- recursive graph traversal (`depth`, BFS/DFS)
+- file discovery by basename/path
+- path escaping for shell/xargs
+- CLI machine-output payloads
+- `PROJECT_DIR` or other environment-based resolution
+
+## Development workflows
+
+### Environment and dependencies
+- Sync: `uv sync`
+- Update lockfile: `uv lock --upgrade`
+- Add/remove packages: `uv add <pkg>`, `uv remove <pkg>`
+
+### QA checks
+Prefix commands with `uv run`.
+- Format: `ruff format src/ tests/`
+- Lint: `ruff check src/ tests/`
+- Types: `mypy src/`
+- Tests: `pytest`
+- Full gate:
+  `uv run ruff format src/ tests/ && uv run ruff check src/ tests/ && uv run mypy src/ && uv run pytest`
+
+### Standards
+- Follow SemVer (`MAJOR.MINOR.PATCH`).
+- Use Conventional Commits (`feat:`, `fix:`, `chore:`, etc.).
+- Never commit autonomously; only commit when explicitly requested.
+
+## Coding standards
+- Keep behavior deterministic and side-effect free.
+- Use strict typing for `src/` and maintain `mypy` compatibility.
+- Keep line length at 100 characters (`ruff` configuration).
+- Prefer testing through the public API; avoid testing private symbols.
+- Keep imports at module top level (no inline imports in tests).

obsilink-0.1.0/README.md

@@ -0,0 +1,150 @@
+# obsilink
+
+[![PyPI](https://img.shields.io/pypi/v/obsilink?logo=pypi)](https://pypi.org/project/obsilink/)
+[![Python](https://img.shields.io/pypi/pyversions/obsilink?logo=python)](https://pypi.org/project/obsilink/)
+[![License](https://img.shields.io/pypi/l/obsilink?logo=法律)](LICENSE)
+
+`obsilink` is a small, deterministic Python library for extracting links from Markdown text.
+
+It supports:
+
+- Obsidian wikilinks like `[[Note]]`, `[[Note|Alias]]`, and `![[Embedded]]`
+- Markdown links like `[Docs](https://example.com)` and embeds like `![Logo](logo.png)`
+- Plain URLs like `https://example.com`, `ftp://files.example.com`, and `mailto:user@example.com`
+
+The parser returns structured `Link` objects in encounter order and preserves duplicates.
+
+## Features
+
+- Deterministic parsing with stable ordering
+- One public extraction function: `extract_links(...)`
+- Accepts either raw `str` or file-like input with `.read()`
+- Preserves duplicates instead of deduplicating
+- Strict, typed API compatible with `mypy` strict mode
+
+## Installation
+
+### With uv (recommended)
+
+```bash
+uv add obsilink
+```
+
+### With pip
+
+```bash
+pip install obsilink
+```
+
+### From source
+
+```bash
+git clone https://github.com/chgroeling/obsilink.git
+cd obsilink
+uv sync
+```
+
+If the package is not yet published to your package index, use the source install method.
+
+## Quick start
+
+```python
+from obsilink import extract_links
+
+text = """
+See [[Project/Plan#Milestones|Roadmap]],
+![Logo](assets/logo.png),
+and https://example.com.
+"""
+
+links = extract_links(text)
+
+for link in links:
+    print(link.type.value, link.target, link.alias)
+```
+
+### More complex Obsidian wikilink example
+
+```python
+from obsilink import extract_links
+
+text = """
+[[Project/Plan#Milestones|Roadmap]]
+![[Assets/Diagrams/System Overview#v2]]
+[[People/Ada Lovelace#Biography^early-life|Ada]]
+[[Project/Plan#Milestones|Roadmap]]
+[[Malformed
+"""
+
+links = extract_links(text)
+
+for link in links:
+    print(
+        link.type.value,
+        link.target,
+        link.alias,
+        link.heading,
+        link.blockid,
+    )
+
+# Encounter order is preserved, duplicates are kept, and malformed
+# wikilinks (like "[[Malformed") are ignored.
+```
+
+## API
+
+### `extract_links(source)`
+
+Extracts links from:
+
+- `str`
+- text file-like object with `.read()` returning `str`
+
+Returns:
+
+- `list[Link]` in encounter order
+
+Raises:
+
+- `TypeError` for unsupported source types
+- `TypeError` if `.read()` returns non-string data
+- Any exception raised by `.read()` is propagated
+
+### `Link`
+
+`Link` is a frozen dataclass with these fields:
+
+- `type: LinkType`
+- `target: str`
+- `alias: str | None`
+- `heading: str | None`
+- `blockid: str | None`
+
+Convenience properties:
+
+- `link.is_url` -> `True` for URL targets (`http`, `https`, `ftp`, `file`, `mailto`)
+- `link.as_path` -> `pathlib.Path` for non-URL targets (raises `ValueError` for URLs)
+
+## Supported link types
+
+- `LinkType.WIKILINK`
+- `LinkType.WIKILINK_EMBED`
+- `LinkType.MARKDOWN_LINK`
+- `LinkType.MARKDOWN_EMBED`
+- `LinkType.PLAIN_URL`
+
+## Development
+
+This project uses `uv`, `ruff`, `mypy`, and `pytest`.
+
+```bash
+uv sync
+uv run ruff format src/ tests/
+uv run ruff check src/ tests/
+uv run mypy src/
+uv run pytest
+```
+
+## License
+
+This project is licensed under the MIT License. See [LICENSE](LICENSE).

obsilink-0.1.0/pyproject.toml

@@ -0,0 +1,48 @@
+[project]
+name = "obsilink"
+version = "0.1.0"
+description = "Extract Obsidian-style wikilink targets from text"
+readme = "AGENTS.md"
+requires-python = ">=3.12"
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Developers",
+  "License :: OSI Approved :: MIT License",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.12",
+  "Topic :: Software Development :: Libraries :: Python Modules",
+  "Topic :: Text Processing",
+]
+keywords = ["obsidian", "wikilink", "parser", "text-processing", "markdown"]
+dependencies = []
+
+[project.urls]
+Homepage = "https://github.com/chgroeling/obsilink"
+Repository = "https://github.com/chgroeling/obsilink"
+Issues = "https://github.com/chgroeling/obsilink/issues"
+
+[build-system]
+requires = ["hatchling>=1.24.0"]
+build-backend = "hatchling.build"
+
+[dependency-groups]
+dev = [
+  "mypy>=1.10.0",
+  "pytest>=8.2.0",
+  "ruff>=0.5.0",
+]
+
+[tool.ruff]
+line-length = 100
+target-version = "py312"
+
+[tool.mypy]
+python_version = "3.12"
+strict = true
+mypy_path = ["src"]
+
+[tool.pytest.ini_options]
+pythonpath = ["src"]
+testpaths = ["tests"]

obsilink-0.1.0/src/obsilink/__init__.py

@@ -0,0 +1,6 @@
+"""Public API for extracting links from Obsidian and Markdown text."""
+
+from .models import Link, LinkType
+from .parser import extract_links
+
+__all__ = ["Link", "LinkType", "extract_links"]

obsilink-0.1.0/src/obsilink/models.py

@@ -0,0 +1,48 @@
+"""Data models for parsed Obsidian and Markdown links."""
+
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass
+from enum import Enum
+from pathlib import Path
+
+
+class LinkType(Enum):
+    """Type of parsed link."""
+
+    WIKILINK = "wikilink"
+    WIKILINK_EMBED = "wikilink_embed"
+    MARKDOWN_LINK = "markdown_link"
+    MARKDOWN_EMBED = "markdown_embed"
+    PLAIN_URL = "plain_url"
+
+
+@dataclass(frozen=True, slots=True)
+class Link:
+    """Structured representation of a parsed link."""
+
+    type: LinkType
+    target: str
+    alias: str | None
+    heading: str | None
+    blockid: str | None
+
+    @property
+    def is_url(self) -> bool:
+        """Check if the target is a URL."""
+        return bool(re.match(r"^(https?|ftp|file)://", self.target)) or bool(
+            re.match(r"^mailto:", self.target)
+        )
+
+    @property
+    def as_path(self) -> Path:
+        """Return the target as a Path object.
+
+        Raises:
+            ValueError: If the target is a URL.
+        """
+        if self.is_url:
+            msg = f"Cannot convert URL target to Path: {self.target!r}"
+            raise ValueError(msg)
+        return Path(self.target)