fromscratch-pydocdb 0.3.0__tar.gz

fromscratch_pydocdb-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_pydocdb-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_pydocdb-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-pydocdb/
+    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_pydocdb-0.3.0/.gitignore

@@ -0,0 +1,11 @@
+__pycache__/
+*.pyc
+.venv/
+*.egg-info/
+dist/
+build/
+.coverage
+htmlcov/
+.ruff_cache/
+_version.py
+.hypothesis/

fromscratch_pydocdb-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_pydocdb-0.3.0/CLAUDE.md

@@ -0,0 +1,52 @@
+# 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
+
+- 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_pydocdb-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_pydocdb-0.3.0/PKG-INFO

@@ -0,0 +1,146 @@
+Metadata-Version: 2.5
+Name: fromscratch-pydocdb
+Version: 0.3.0
+Summary: An educational document store library built from scratch in Python
+Project-URL: Homepage, https://github.com/robcox2910/pydoc-db
+Project-URL: Repository, https://github.com/robcox2910/pydoc-db
+Project-URL: Issues, https://github.com/robcox2910/pydoc-db/issues
+Project-URL: Documentation, https://robcox2910.github.io/pydoc-db/
+Author: Rob Cox
+License: MIT
+License-File: LICENSE
+Keywords: database,document,education,nosql,store
+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 :: Software Development :: Libraries
+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
+
+# PyDocDB
+
+An educational document store (like MongoDB) built from scratch in Python. Part of the **PyLearn** platform for kids aged 12+.
+
+PyDocDB stores JSON-like documents without requiring a fixed schema -- each document can have different fields, just like how every index card in a filing cabinet can have different information on it.
+
+## Features
+
+- **Documents** -- Dict-like objects with auto-generated unique IDs
+- **Collections** -- Named groups of documents with full CRUD operations
+- **Query Language** -- Filter with operators: `$eq`, `$gt`, `$lt`, `$gte`, `$lte`, `$ne`, `$in`, `$exists`, `$and`, `$or`, `$not`
+- **Nested Field Access** -- Query nested fields with dot notation (e.g., `"address.city"`)
+- **Projection** -- Return only specific fields from documents
+- **Indexing** -- Create indexes on fields for faster lookups
+- **Persistence** -- Save/load collections to JSON files on disk
+- **Aggregation** -- Pipeline with `$match`, `$group`, `$sort`, `$limit`, `$count`
+
+## Quick Start
+
+```python
+from pydocdb import Collection, save_collection, load_collection, aggregate
+
+# Create a collection (like labeling a new folder in a filing cabinet)
+students = Collection("students")
+
+# Insert documents (like filing index cards)
+students.insert_one({"name": "Alice", "age": 14, "grade": "9th"})
+students.insert_one({"name": "Bob", "age": 13, "hobby": "chess"})
+students.insert_one({"name": "Charlie", "age": 15, "grade": "10th"})
+
+# Find documents with queries
+teenagers = students.find({"age": {"$gte": 13}})
+alice = students.find_one({"name": "Alice"})
+
+# Update and delete
+students.update_one({"name": "Alice"}, {"age": 15})
+students.delete_one({"name": "Bob"})
+
+# Use projection to get only specific fields
+names = students.find({}, projection={"name": 1, "_id": 0})
+
+# Aggregate data
+result = aggregate(students.to_list(), [
+    {"$group": {"_id": "$grade", "count": {"$sum": 1}}},
+    {"$sort": {"count": -1}},
+])
+
+# Save to disk and load later
+save_collection(students, "students.json")
+loaded = load_collection("students.json")
+```
+
+## Installation
+
+```bash
+uv add pydocdb
+```
+
+## Development
+
+```bash
+git clone https://github.com/robcox2910/pydoc-db.git
+cd pydoc-db
+uv sync --all-extras
+uv run pytest
+uv run ruff check src/ tests/
+uv run pyright src tests
+```
+
+## 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 -->
+
+<!-- docs:start -->
+## Documentation
+
+Full docs (with kid-friendly explanations of every idea): https://robcox2910.github.io/pydoc-db/
+<!-- docs:end -->

fromscratch_pydocdb-0.3.0/README.md

@@ -0,0 +1,114 @@
+# PyDocDB
+
+An educational document store (like MongoDB) built from scratch in Python. Part of the **PyLearn** platform for kids aged 12+.
+
+PyDocDB stores JSON-like documents without requiring a fixed schema -- each document can have different fields, just like how every index card in a filing cabinet can have different information on it.
+
+## Features
+
+- **Documents** -- Dict-like objects with auto-generated unique IDs
+- **Collections** -- Named groups of documents with full CRUD operations
+- **Query Language** -- Filter with operators: `$eq`, `$gt`, `$lt`, `$gte`, `$lte`, `$ne`, `$in`, `$exists`, `$and`, `$or`, `$not`
+- **Nested Field Access** -- Query nested fields with dot notation (e.g., `"address.city"`)
+- **Projection** -- Return only specific fields from documents
+- **Indexing** -- Create indexes on fields for faster lookups
+- **Persistence** -- Save/load collections to JSON files on disk
+- **Aggregation** -- Pipeline with `$match`, `$group`, `$sort`, `$limit`, `$count`
+
+## Quick Start
+
+```python
+from pydocdb import Collection, save_collection, load_collection, aggregate
+
+# Create a collection (like labeling a new folder in a filing cabinet)
+students = Collection("students")
+
+# Insert documents (like filing index cards)
+students.insert_one({"name": "Alice", "age": 14, "grade": "9th"})
+students.insert_one({"name": "Bob", "age": 13, "hobby": "chess"})
+students.insert_one({"name": "Charlie", "age": 15, "grade": "10th"})
+
+# Find documents with queries
+teenagers = students.find({"age": {"$gte": 13}})
+alice = students.find_one({"name": "Alice"})
+
+# Update and delete
+students.update_one({"name": "Alice"}, {"age": 15})
+students.delete_one({"name": "Bob"})
+
+# Use projection to get only specific fields
+names = students.find({}, projection={"name": 1, "_id": 0})
+
+# Aggregate data
+result = aggregate(students.to_list(), [
+    {"$group": {"_id": "$grade", "count": {"$sum": 1}}},
+    {"$sort": {"count": -1}},
+])
+
+# Save to disk and load later
+save_collection(students, "students.json")
+loaded = load_collection("students.json")
+```
+
+## Installation
+
+```bash
+uv add pydocdb
+```
+
+## Development
+
+```bash
+git clone https://github.com/robcox2910/pydoc-db.git
+cd pydoc-db
+uv sync --all-extras
+uv run pytest
+uv run ruff check src/ tests/
+uv run pyright src tests
+```
+
+## 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 -->
+
+<!-- docs:start -->
+## Documentation
+
+Full docs (with kid-friendly explanations of every idea): https://robcox2910.github.io/pydoc-db/
+<!-- docs:end -->

fromscratch_pydocdb-0.3.0/conftest.py

@@ -0,0 +1,21 @@
+"""Shared Hypothesis profiles for the series.
+
+Two profiles are registered, and ``ci`` is loaded by default:
+
+- ``ci`` runs 100 examples with no deadline, a fixed seed and no example
+  database, so the same code gives the same result on every machine and a
+  green build can be trusted.
+- ``thorough`` runs 2000 examples with a random seed, to hunt for the rare
+  counterexample before a release.
+
+Run the long one with ``uv run pytest --hypothesis-profile=thorough``.
+
+This file is owned by ``series sync``. Edit it in the series home repo
+(robcox2910.github.io), not here, or the next sync will put it back.
+"""
+
+from hypothesis import settings
+
+settings.register_profile("ci", max_examples=100, deadline=None, derandomize=True, database=None)
+settings.register_profile("thorough", max_examples=2000, deadline=None, derandomize=False)
+settings.load_profile("ci")

fromscratch_pydocdb-0.3.0/docs/concepts/aggregation.md

@@ -0,0 +1,91 @@
+# Aggregation
+
+## The "Sorting and Counting Your Card Collection" Analogy
+
+Imagine you have a huge pile of trading cards. You might want to:
+
+1. **Pick out** only the rare cards (`$match`)
+2. **Group** them by type -- Fire, Water, Grass (`$group`)
+3. **Sort** the groups by how many cards each has (`$sort`)
+4. **Look at only** the top 3 groups (`$limit`)
+5. **Count** how many groups there are (`$count`)
+
+That's an aggregation pipeline! Each step transforms the data, and the output of one step becomes the input for the next.
+
+## Pipeline Stages
+
+### $match -- Filter Documents
+
+```python
+from pydocdb import Collection, aggregate
+
+products = Collection("products")
+products.insert_many([
+    {"name": "Widget", "category": "A", "price": 10},
+    {"name": "Gadget", "category": "A", "price": 20},
+    {"name": "Doohickey", "category": "B", "price": 30},
+])
+
+# Get only category A products
+result = aggregate(products.to_list(), [
+    {"$match": {"category": "A"}}
+])
+```
+
+### $group -- Group and Summarize
+
+```python
+# Group by category and sum prices
+result = aggregate(products.to_list(), [
+    {"$group": {
+        "_id": "$category",
+        "total_price": {"$sum": "$price"},
+        "count": {"$sum": 1},
+        "avg_price": {"$avg": "$price"},
+    }}
+])
+```
+
+Available accumulators: `$sum`, `$avg`, `$min`, `$max`
+
+### $sort -- Order Results
+
+```python
+# Sort by price, highest first
+result = aggregate(products.to_list(), [
+    {"$sort": {"price": -1}}  # -1 = descending, 1 = ascending
+])
+```
+
+### $limit -- Take Only N Results
+
+```python
+# Get the top 2 most expensive
+result = aggregate(products.to_list(), [
+    {"$sort": {"price": -1}},
+    {"$limit": 2}
+])
+```
+
+### $count -- Count Documents
+
+```python
+# Count how many products there are
+result = aggregate(products.to_list(), [
+    {"$count": "total_products"}
+])
+# [{"total_products": 3}]
+```
+
+## Multi-Stage Pipelines
+
+The real power comes from chaining stages together:
+
+```python
+result = aggregate(products.to_list(), [
+    {"$match": {"price": {"$gte": 15}}},     # Step 1: Filter expensive items
+    {"$group": {"_id": "$category", "total": {"$sum": "$price"}}},  # Step 2: Group by category
+    {"$sort": {"total": -1}},                  # Step 3: Sort by total, highest first
+    {"$limit": 5},                             # Step 4: Only top 5
+])
+```

fromscratch_pydocdb-0.3.0/docs/concepts/collections.md

@@ -0,0 +1,62 @@
+# Collections
+
+## The Folder in a Filing Cabinet Analogy
+
+A collection is like a **labeled folder** in a filing cabinet. The folder called "Students" holds all the student index cards. The folder called "Products" holds all the product cards. Each folder is independent -- adding a card to "Students" doesn't affect "Products."
+
+## CRUD Operations
+
+CRUD stands for **C**reate, **R**ead, **U**pdate, **D**elete -- the four basic things you can do with data.
+
+### Create (Insert)
+
+```python
+from pydocdb import Collection
+
+students = Collection("students")
+
+# Insert one document
+alice = students.insert_one({"name": "Alice", "age": 14})
+
+# Insert many at once
+students.insert_many([
+    {"name": "Bob", "age": 13},
+    {"name": "Charlie", "age": 15},
+])
+```
+
+### Read (Find)
+
+```python
+# Find all documents
+all_students = students.find()
+
+# Find with a query
+teens = students.find({"age": {"$gte": 13}})
+
+# Find just one
+alice = students.find_one({"name": "Alice"})
+
+# Find by ID
+doc = students.find_by_id("some-id-here")
+```
+
+### Update
+
+```python
+# Update one document
+students.update_one({"name": "Alice"}, {"age": 15})
+
+# Update many documents
+students.update_many({"grade": "9th"}, {"year": 2024})
+```
+
+### Delete
+
+```python
+# Delete one document
+students.delete_one({"name": "Alice"})
+
+# Delete many documents
+students.delete_many({"graduated": True})
+```