fromscratch-pysearch 0.3.0__tar.gz

fromscratch_pysearch-0.3.0/.github/workflows/ci.yml

@@ -0,0 +1,14 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+jobs:
+  ci:
+    uses: robcox2910/robcox2910.github.io/.github/workflows/python-ci.yml@v1

fromscratch_pysearch-0.3.0/.github/workflows/docs.yml

@@ -0,0 +1,16 @@
+name: Deploy Docs
+
+on:
+  push:
+    branches: [main]
+  workflow_dispatch: {}
+
+jobs:
+  docs:
+    uses: robcox2910/robcox2910.github.io/.github/workflows/docs.yml@v1
+    permissions:
+      contents: read
+      pages: write
+      id-token: write
+    with:
+      coverage-report: false

fromscratch_pysearch-0.3.0/.github/workflows/release.yml

@@ -0,0 +1,58 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: write
+  id-token: write
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          fetch-depth: 0
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          version: "latest"
+
+      - name: Set up Python
+        run: uv python install 3.14
+
+      - name: Build distributions
+        run: uv build
+
+      - name: Upload build artifacts
+        uses: actions/upload-artifact@v7
+        with:
+          name: dist
+          path: dist/
+
+      - name: Upload to GitHub Release
+        uses: softprops/action-gh-release@v3
+        with:
+          files: dist/*
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/project/fromscratch-pysearch/
+    permissions:
+      id-token: write
+    steps:
+      - name: Download build artifacts
+        uses: actions/download-artifact@v8
+        with:
+          name: dist
+          path: dist/
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

fromscratch_pysearch-0.3.0/.gitignore

@@ -0,0 +1,14 @@
+__pycache__/
+*.py[cod]
+*.egg-info/
+dist/
+build/
+.venv/
+.pytest_cache/
+htmlcov/
+.coverage
+.pyright/
+.DS_Store
+src/pysearch/_version.py
+site/
+.hypothesis/

fromscratch_pysearch-0.3.0/.pre-commit-config.yaml

@@ -0,0 +1,56 @@
+default_language_version:
+  python: python3.14
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      # Pages paste real pytest output, trailing spaces included.
+      - id: trailing-whitespace
+        exclude: ^docs/property-testing\.md$
+      - id: end-of-file-fixer
+        exclude: ^docs/property-testing\.md$
+      - id: check-yaml
+        args: ['--unsafe']
+      - id: check-added-large-files
+      - id: check-json
+      - id: check-toml
+      - id: check-merge-conflict
+      - id: debug-statements
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.15.4
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+      - id: ruff-format
+
+  - repo: https://github.com/RobertCraigie/pyright-python
+    rev: v1.1.408
+    hooks:
+      - id: pyright
+
+  - repo: local
+    hooks:
+      - id: pip-audit
+        name: pip-audit
+        language: system
+        pass_filenames: false
+        files: ^(pyproject\.toml|uv\.lock)$
+        entry: >-
+          bash -c 'f=$(mktemp) &&
+          uv export --frozen --no-emit-project --all-extras --no-hashes -o "$f" >/dev/null &&
+          uvx pip-audit==2.10.0 -r "$f" --disable-pip --no-deps;
+          status=$?; rm -f "$f"; exit $status'
+
+  - repo: https://github.com/rhysd/actionlint
+    rev: v1.7.7
+    hooks:
+      - id: actionlint
+
+  - repo: https://github.com/commitizen-tools/commitizen
+    rev: v4.13.8
+    hooks:
+      - id: commitizen
+        stages: [commit-msg]
+        additional_dependencies: [typing_extensions]

fromscratch_pysearch-0.3.0/CLAUDE.md

@@ -0,0 +1,53 @@
+# Claude Code Instructions
+
+<!-- standard:start -->
+## Code Style
+
+- All public functions, methods, classes, and modules **must** have a docstring
+- Use imperative mood: "Return the result." not "Returns the result."
+- One-line docstrings for simple functions; multi-line with summary + details for complex ones
+- Follow the Google docstring convention (D211, D212 selected via ruff)
+
+## Linting
+
+- Ruff enforces a comprehensive rule set -- run `uv run ruff check .` before committing
+- Pyright runs in strict mode -- run `uv run pyright src tests` before committing
+- All violations must be fixed, not ignored. Exceptions are the repo-owned `ignore` and `per-file-ignores` lists in `pyproject.toml`, which belong to this repo; the series sync never edits them
+
+## Testing
+
+- TDD workflow: Red-Green-Refactor
+- Coverage is enforced by pytest-cov; the floor in `pyproject.toml` is repo-owned
+- Test classes and methods also require docstrings
+- Use named constants instead of magic values (PLR2004)
+- Run `uv run pytest` before committing
+- Property-based tests (Hypothesis) live in `tests/test_properties.py` and `tests/test_model.py`; the shared profiles are in the root `conftest.py` (owned by `series sync`). Run `uv run pytest --hypothesis-profile=thorough` before a release.
+
+## Commits
+
+- Use conventional commits: `feat:`, `fix:`, `refactor:`, `test:`, `docs:`, `ci:`, `chore:`
+- All changes go via PR from a feature branch (main is protected); merge when CI is green
+
+## Dependencies
+
+- Package manager: uv
+- Run `uv sync --all-extras` after modifying dependencies
+- `uv.lock` is committed; CI and pre-commit audit it with pip-audit through `uvx`, so pip-audit is not a project dependency
+- Sibling projects, where used, are pinned release tags in `[tool.uv.sources]` (git + tag); never use `path` sources
+
+## Releasing
+
+- A release is a `vX.Y.Z` tag on main after the PR is merged
+- Docs-only and tooling-only changes do not get a release tag
+- Docs are built with `mkdocs build --strict` and deployed to GitHub Pages by the docs workflow
+<!-- standard:end -->
+
+## Project notes
+
+- Use imperative mood: "Return the response." not "Returns the response."
+- Pyright in strict mode -- run `uv run pyright src tests` before committing
+- All violations must be fixed, not ignored (except D203/D213 incompatible pair)
+- Minimum 80% coverage enforced by pytest-cov
+- Use conventional commits (enforced by commitizen): `feat:`, `fix:`, `refactor:`, `test:`, `docs:`, `ci:`, `chore:`
+- All changes go via PR from a feature branch (main is protected)
+- Add production deps to `[project.dependencies]`

fromscratch_pysearch-0.3.0/CONTRIBUTING.md

@@ -0,0 +1,199 @@
+# Contributing to PySearch
+
+Thanks for your interest in contributing! This guide covers everything you need
+to get started.
+
+## Prerequisites
+
+| Tool | Version | Install |
+|------|---------|---------|
+| Python | 3.14+ | [python.org](https://www.python.org/downloads/) |
+| uv | latest | `curl -LsSf https://astral.sh/uv/install.sh \| sh` |
+| git | 2.x+ | [git-scm.com](https://git-scm.com/) |
+
+## Setup
+
+```bash
+# Clone the repo
+git clone https://github.com/robcox2910/pysearch.git
+cd pysearch
+
+# Install all dependencies (including dev tools)
+uv sync --all-extras
+
+# Install pre-commit hooks (linting + commit message validation)
+uv run pre-commit install
+uv run pre-commit install --hook-type commit-msg
+```
+
+Verify everything works:
+
+```bash
+uv run pytest --cov          # tests pass, >= 80% coverage
+uv run ruff check src/ tests/  # no lint errors
+uv run pyright src tests       # no type errors
+```
+
+## TDD Workflow
+
+We follow **Red-Green-Refactor** for every code change:
+
+1. **Red** -- Write a failing test that describes the behaviour you want.
+2. **Green** -- Write the simplest code that makes the test pass.
+3. **Refactor** -- Clean up while keeping all tests green.
+
+Never skip the red step. If you can't write a failing test first, take a moment
+to think about what the code should actually do.
+
+## Branch Naming
+
+Create a branch from `main` using one of these prefixes:
+
+| Prefix | When to use |
+|--------|-------------|
+| `feat/` | New search feature or algorithm |
+| `fix/` | Bug fix |
+| `refactor/` | Restructuring without behaviour change |
+| `test/` | Test-only changes |
+| `docs/` | Documentation updates |
+| `ci/` | CI/CD workflow changes |
+| `chore/` | Dependency bumps, config tweaks |
+
+Example: `feat/phrase-search`, `fix/tokenizer-unicode`
+
+## Conventional Commits
+
+Every commit message must follow [Conventional Commits](https://www.conventionalcommits.org/):
+
+```
+<type>: <short description in imperative mood>
+
+Optional longer explanation.
+```
+
+Types match the branch prefixes: `feat:`, `fix:`, `refactor:`, `test:`,
+`docs:`, `ci:`, `chore:`.
+
+Good examples:
+
+```
+feat: add TF-IDF ranking to search results
+fix: resolve tokenizer handling of hyphens
+docs: add inverted index concept page
+```
+
+Bad examples:
+
+```
+updated stuff          # no type, vague description
+feat: adds ranking     # not imperative mood ("adds" -> "add")
+```
+
+## Code Style
+
+### Modern Python
+
+Use Python 3.14 idioms everywhere:
+
+- `X | Y` for union types (not `Union[X, Y]` or `Optional[X]`)
+- `StrEnum` for string enumerations
+- `match/case` instead of if/elif chains where appropriate
+- Direct imports: `from enum import StrEnum` not `import enum`
+
+### Docstrings
+
+Every public function, method, class, and module needs a docstring:
+
+- Use **imperative mood**: "Return the record." not "Returns the record."
+- One-liner for simple functions, multi-line (Google style) for complex ones.
+
+```python
+def tokenize(text: str) -> list[str]:
+    """Split text into lowercase tokens with stop words removed."""
+
+def compute_tfidf(
+    term: str,
+    doc_id: str,
+    index: InvertedIndex,
+) -> float:
+    """Compute the TF-IDF score for a term in a document.
+
+    Args:
+        term: The search term.
+        doc_id: The document identifier.
+        index: The inverted index to query.
+
+    Returns:
+        The product of TF and IDF.
+    """
+```
+
+### Named Constants
+
+Use named constants instead of magic numbers in tests and source code. Ruff
+rule PLR2004 enforces this.
+
+```python
+# Good
+EXPECTED_TOKEN_COUNT = 3
+assert len(result) == EXPECTED_TOKEN_COUNT
+
+# Bad
+assert len(result) == 3
+```
+
+## Linting and Type Checking
+
+Run these before every commit (pre-commit hooks enforce them automatically):
+
+```bash
+uv run ruff check src/ tests/   # lint
+uv run ruff format src/ tests/   # format (or --check to verify)
+uv run pyright src tests          # type check (strict mode)
+```
+
+Fix all violations. Inline `# noqa:` is acceptable only when tools genuinely
+conflict (e.g., ARG002 vs pyright protocol parameter names).
+
+## Testing
+
+```bash
+uv run pytest                # run all tests
+uv run pytest --cov          # with coverage report
+uv run pytest tests/test_x.py  # run a specific file
+uv run pytest -k "test_name"   # run tests matching a pattern
+```
+
+- Minimum **80% coverage** is enforced.
+- Test classes and methods need docstrings too.
+- Use `pytest.raises` as a context manager for exception testing.
+
+## Documentation Style
+
+Our docs target a **12-year-old with an interest in computing**. Keep language
+simple, use analogies, and avoid jargon without explanation.
+
+Good:
+
+> An inverted index is like a notebook where the librarian writes down which
+> books mention each word. Instead of reading every book, she just flips to
+> the right page.
+
+Bad:
+
+> An inverted index is a data structure mapping terms to their postings lists,
+> enabling sublinear-time retrieval via hash-based lookups.
+
+## Pull Request Process
+
+1. Create a feature branch from `main`.
+2. Make your changes following TDD.
+3. Ensure all checks pass: `uv run ruff check .`, `uv run pyright src tests`,
+   `uv run pytest --cov`.
+4. Push your branch and open a PR against `main`.
+5. PRs are squash-merged to keep history clean.
+
+## Questions?
+
+Open an issue on [GitHub](https://github.com/robcox2910/pysearch/issues) --
+we're happy to help!

fromscratch_pysearch-0.3.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Rob Cox
+
+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.

fromscratch_pysearch-0.3.0/PKG-INFO

@@ -0,0 +1,188 @@
+Metadata-Version: 2.5
+Name: fromscratch-pysearch
+Version: 0.3.0
+Summary: An educational full-text search engine built from scratch in Python
+Project-URL: Homepage, https://github.com/robcox2910/pysearch
+Project-URL: Repository, https://github.com/robcox2910/pysearch
+Project-URL: Issues, https://github.com/robcox2910/pysearch/issues
+Project-URL: Documentation, https://robcox2910.github.io/pysearch/
+Author: Rob Cox
+License: MIT
+License-File: LICENSE
+Keywords: education,inverted-index,search,tfidf
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Education
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Education
+Classifier: Topic :: Text Processing :: Indexing
+Classifier: Typing :: Typed
+Requires-Python: >=3.14
+Provides-Extra: dev
+Requires-Dist: commitizen>=4.4.0; extra == 'dev'
+Requires-Dist: hypothesis>=6.170; extra == 'dev'
+Requires-Dist: pip-audit>=2.10.0; extra == 'dev'
+Requires-Dist: pre-commit>=4.0.1; extra == 'dev'
+Requires-Dist: pyright>=1.1.400; extra == 'dev'
+Requires-Dist: pytest-cov>=6.0.0; extra == 'dev'
+Requires-Dist: pytest>=8.3.4; extra == 'dev'
+Requires-Dist: ruff>=0.9.3; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# PySearch
+
+**An educational full-text search engine built from scratch in Python.**
+
+## The Librarian Who Read Every Book
+
+Imagine a librarian who has read every single book in the library. When you ask
+her "Which books mention *dinosaurs*?", she doesn't need to open a single book.
+She already knows the answer because she kept notes while reading.
+
+For every word she encountered, she wrote down which book it was in and how many
+times it appeared. Her notebook is called an **inverted index**, and it lets her
+answer your question in the blink of an eye.
+
+But what if ten books mention dinosaurs? Which one should you read first? The
+librarian uses a clever trick called **TF-IDF** -- she ranks the books so the
+ones that talk about dinosaurs *the most* (and about other things *the least*)
+float to the top.
+
+PySearch teaches you how to build this librarian from scratch.
+
+## Examples
+
+### Adding Documents and Searching
+
+```python
+from pysearch.engine import SearchEngine
+
+# Create a search engine and add some documents
+engine = SearchEngine()
+engine.add("doc1", "Python is a great programming language")
+engine.add("doc2", "Java is also a popular language")
+engine.add("doc3", "Python and Java are both used for web development")
+
+# Search for a single term -- results ranked by relevance
+results = engine.search("python")
+for doc_id, score in results:
+    print(f"{doc_id}: {score:.4f}")
+
+# Boolean queries
+results = engine.search("python AND java")   # documents with both
+results = engine.search("python OR java")    # documents with either
+```
+
+### Using the Tokenizer Directly
+
+```python
+from pysearch.tokenizer import tokenize, simple_stem
+
+tokens = tokenize("The quick brown foxes are running!")
+print(tokens)  # ['quick', 'brown', 'fox', 'runn']
+
+print(simple_stem("running"))  # 'runn'
+print(simple_stem("played"))   # 'play'
+print(simple_stem("quickly"))  # 'quick'
+```
+
+### Building an Inverted Index
+
+```python
+from pysearch.index import InvertedIndex
+
+index = InvertedIndex()
+index.add_document("doc1", "cats and dogs")
+index.add_document("doc2", "cats and birds")
+index.add_document("doc3", "dogs and birds")
+
+print(index.search("cat"))            # ['doc1', 'doc2']
+print(index.search_and(["cat", "dog"]))  # ['doc1']
+print(index.search_or(["cat", "dog"]))   # ['doc1', 'doc2', 'doc3']
+```
+
+## Features
+
+- **Tokenizer** -- Split text into searchable words, remove stop words, and
+  apply simple stemming
+- **Inverted Index** -- Map every word to the documents that contain it for
+  instant lookups
+- **TF-IDF Ranking** -- Score and rank results so the most relevant documents
+  come first
+- **Boolean Queries** -- Combine search terms with AND and OR operators
+- **100% Typed** -- Full type annotations with strict Pyright checking
+
+## Quick Start
+
+```bash
+# Install from source
+git clone https://github.com/robcox2910/pysearch.git
+cd pysearch
+uv sync --all-extras
+
+# Run the tests
+uv run pytest
+
+# Try it in a Python shell
+uv run python -c "
+from pysearch.engine import SearchEngine
+engine = SearchEngine()
+engine.add('doc1', 'hello world')
+print(engine.search('hello'))
+"
+```
+
+## Concepts
+
+Saving an engine to disk and loading it back: [Saving Your Index](docs/concepts/saving.md).
+
+<!-- docs:start -->
+## Documentation
+
+Full docs (with kid-friendly explanations of every idea): https://robcox2910.github.io/pysearch/
+<!-- docs:end -->
+
+## Releasing
+
+Other projects in the series ([PyStack](https://github.com/robcox2910/pystack)) use a pinned release of this one,
+not whatever is on `main`. To publish a change for them:
+
+1. Merge the change to `main`.
+2. Tag it: `git tag -a vX.Y.Z -m vX.Y.Z && git push origin vX.Y.Z`.
+   A change to the public API bumps the minor version (`v0.1.0` → `v0.2.0`);
+   anything else bumps the patch (`v0.1.0` → `v0.1.1`).
+3. In each project that uses it, edit the tag in `[tool.uv.sources]`, run
+   `uv lock --upgrade-package <name>`, and open a pull request so CI checks
+   the pair together.
+
+<!-- series:start -->
+## Related Projects
+
+This project is one of a series that builds real systems "from scratch in Python" to teach how they work. See the [series home](https://robcox2910.github.io/) for the full story.
+
+| Project | What it teaches | Repository | Docs |
+| --- | --- | --- | --- |
+| PyOS | Operating systems | [py-os](https://github.com/robcox2910/py-os) | [Docs](https://robcox2910.github.io/py-os/) |
+| Pebble | Compilers and programming languages | [pebble-lang](https://github.com/robcox2910/pebble-lang) | [Docs](https://robcox2910.github.io/pebble-lang/) |
+| PyDB | Relational databases | [pydb](https://github.com/robcox2910/pydb) | [Docs](https://robcox2910.github.io/pydb/) |
+| PyKV | Key-value stores | [pykv](https://github.com/robcox2910/pykv) | [Docs](https://robcox2910.github.io/pykv/) |
+| PyDocDB | Document databases | [pydoc-db](https://github.com/robcox2910/pydoc-db) | [Docs](https://robcox2910.github.io/pydoc-db/) |
+| PyGraphDB | Graph databases | [pygraphdb](https://github.com/robcox2910/pygraphdb) | [Docs](https://robcox2910.github.io/pygraphdb/) |
+| PyTSDB | Time-series databases | [pytsdb](https://github.com/robcox2910/pytsdb) | [Docs](https://robcox2910.github.io/pytsdb/) |
+| PyVecDB | Vector databases | [pyvecdb](https://github.com/robcox2910/pyvecdb) | [Docs](https://robcox2910.github.io/pyvecdb/) |
+| PyColDB | Column-family databases | [pycoldb](https://github.com/robcox2910/pycoldb) | [Docs](https://robcox2910.github.io/pycoldb/) |
+| PyCrypt | Cryptography | [pycrypt](https://github.com/robcox2910/pycrypt) | [Docs](https://robcox2910.github.io/pycrypt/) |
+| PyNet | Computer networking | [pynet](https://github.com/robcox2910/pynet) | [Docs](https://robcox2910.github.io/pynet/) |
+| PyWeb | HTTP web servers | [pyweb](https://github.com/robcox2910/pyweb) | [Docs](https://robcox2910.github.io/pyweb/) |
+| PyGit | Version control | [pygit](https://github.com/robcox2910/pygit) | [Docs](https://robcox2910.github.io/pygit/) |
+| **PySearch** | **Search engines** | [pysearch](https://github.com/robcox2910/pysearch) | [Docs](https://robcox2910.github.io/pysearch/) |
+| PyMQ | Message queues | [pymq](https://github.com/robcox2910/pymq) | [Docs](https://robcox2910.github.io/pymq/) |
+| PyLLM | Language models (the brain) | [pyllm](https://github.com/robcox2910/pyllm) | [Docs](https://robcox2910.github.io/pyllm/) |
+| PyScheduler | Job scheduling | [pyscheduler](https://github.com/robcox2910/pyscheduler) | [Docs](https://robcox2910.github.io/pyscheduler/) |
+| PyStack | Full-stack integration | [pystack](https://github.com/robcox2910/pystack) | [Docs](https://robcox2910.github.io/pystack/) |
+<!-- series:end -->
+
+## License
+
+MIT -- see [LICENSE](LICENSE) for details.