first commit

5 files changed, 529 insertions, 0 deletions

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
new file mode 100644
index 0000000..24f06e1
--- /dev/null
+++ b/.github/workflows/ci.yml
@@ -0,0 +1,72 @@
+name: CI
+
+on:
+  release:
+    types: [created]
+  push:
+  schedule:
+    # Runs every Thursday at 20:23 GMT to avoid bit rot
+    - cron: "20 23 * * 4"
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v1
+
+      - name: Install latest nightly
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: nightly
+          override: true
+
+      - name: Lint with rustfmt
+        uses: actions-rs/cargo@v1
+        with:
+          command: fmt
+
+      - name: Lint with clippy
+        uses: actions-rs/cargo@v1
+        with:
+          command: clippy
+          args: --all-targets --all-features
+
+  build:
+    runs-on: ${{ matrix.os }}
+    needs: lint
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: [3.5, 3.6, 3.7, 3.8]
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        exclude:
+          # There is a known issue where Python C extensions
+          # can not be built on Python 3.5 on Windows.
+          # https://github.com/actions/virtual-environments/issues/34
+          # Therefore, ujson can't be compiled and the build would fail.
+          - os: windows-latest
+            python-version: 3.5
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v1
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v1
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install poetry
+          poetry install
+      - name: Install latest nightly
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: nightly
+          override: true
+
+      - name: Build Python package
+        run: poetry run maturin develop --release
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..fb366a8
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,243 @@
+# -- Rust --
+/target
+Cargo.lock
+
+# -- Editors --
+# Created by https://www.gitignore.io/api/vim,emacs,visualstudiocode
+# Edit at https://www.gitignore.io/?templates=vim,emacs,visualstudiocode
+
+### Emacs ###
+# -*- mode: gitignore; -*-
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+auto-save-list
+tramp
+.\#*
+
+# Org-mode
+.org-id-locations
+*_archive
+
+# flymake-mode
+*_flymake.*
+
+# eshell files
+/eshell/history
+/eshell/lastdir
+
+# elpa packages
+/elpa/
+
+# reftex files
+*.rel
+
+# AUCTeX auto folder
+/auto/
+
+# cask packages
+.cask/
+dist/
+
+# Flycheck
+flycheck_*.el
+
+# server auth directory
+/server/
+
+# projectiles files
+.projectile
+
+# directory configuration
+.dir-locals.el
+
+# network security
+/network-security.data
+
+
+### Vim ###
+# Swap
+[._]*.s[a-v][a-z]
+[._]*.sw[a-p]
+[._]s[a-rt-v][a-z]
+[._]ss[a-gi-z]
+[._]sw[a-p]
+
+# Session
+Session.vim
+Sessionx.vim
+
+# Temporary
+.netrwhist
+
+# Auto-generated tag files
+tags
+
+# Persistent undo
+[._]*.un~
+
+# Coc configuration directory
+.vim
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+
+# End of https://www.gitignore.io/api/vim,emacs,visualstudiocode
+
+# -- Python --
+# Python virtual environment
+.env
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.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/
+
+# static files generated from Django application using `collectstatic`
+media
+static
diff --git a/Cargo.toml b/Cargo.toml
new file mode 100644
index 0000000..334176d
--- /dev/null
+++ b/Cargo.toml
@@ -0,0 +1,18 @@
+[package]
+name = "python-adblock"
+version = "0.1.0"
+authors = ["Árni Dagur <arni@dagur.eu"]
+edition = "2018"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+pyo3 = "0.9"
+adblock = "0.2"
+
+[lib]
+name="adblock"
+crate-type = ["rlib", "cdylib"]
+
+[features]
+default = ["pyo3/extension-module"]
\ No newline at end of file
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..79fd056
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,15 @@
+[tool.poetry]
+name = "adblock"
+version = "0.1.0"
+description = "Brave's adblocking in Python"
+authors = ["Árni Dagur <arni@dagur.eu>"]
+license = "Apache-2.0"
+readme = "README.md"
+repository = "https://github.com/ArniDagur/python-adblock"
+keywords = []
+
+[tool.poetry.dependencies]
+python = "^3.5"
+
+[tool.poetry.dev-dependencies]
+maturin = "*"
diff --git a/src/lib.rs b/src/lib.rs
new file mode 100644
index 0000000..86512f7
--- /dev/null
+++ b/src/lib.rs
@@ -0,0 +1,181 @@
+//! Python bindings for Brave's adblocking library, which is written in Rust.
+#![deny(
+    future_incompatible,
+    nonstandard_style,
+    rust_2018_idioms,
+    missing_copy_implementations,
+    trivial_casts,
+    trivial_numeric_casts,
+    unsafe_code,
+    unused_qualifications
+)]
+
+use pyo3::class::PyObjectProtocol;
+use pyo3::prelude::*;
+
+use adblock::blocker::BlockerResult as RustBlockerResult;
+use adblock::engine::Engine as RustEngine;
+
+/// Brave's adblocking library in Python!
+#[pymodule]
+fn adblock(_py: Python<'_>, m: &PyModule) -> PyResult<()> {
+    m.add("__version__", env!("CARGO_PKG_VERSION"))?;
+    m.add_class::<Engine>()?;
+    Ok(())
+}
+
+#[pyclass]
+pub struct BlockerResult {
+    #[pyo3(get)]
+    pub matched: bool,
+    #[pyo3(get)]
+    pub explicit_cancel: bool,
+    #[pyo3(get)]
+    pub important: bool,
+    #[pyo3(get)]
+    pub redirect: Option<String>,
+    #[pyo3(get)]
+    pub exception: Option<String>,
+    #[pyo3(get)]
+    pub filter: Option<String>,
+    #[pyo3(get)]
+    pub error: Option<String>,
+}
+
+impl Into<BlockerResult> for RustBlockerResult {
+    fn into(self) -> BlockerResult {
+        BlockerResult {
+            matched: self.matched,
+            explicit_cancel: self.explicit_cancel,
+            important: self.important,
+            redirect: self.redirect,
+            exception: self.exception,
+            filter: self.filter,
+            error: self.error,
+        }
+    }
+}
+
+#[pyproto]
+impl PyObjectProtocol for BlockerResult {
+    fn __repr__(&self) -> PyResult<String> {
+        Ok(format!(
+            "BlockerResult({}, {}, {}, {:?}, {:?}, {:?}, {:?})",
+            self.matched,
+            self.explicit_cancel,
+            self.important,
+            self.redirect,
+            self.exception,
+            self.filter,
+            self.error
+        ))
+    }
+}
+
+#[pyclass]
+pub struct Engine {
+    engine: RustEngine,
+}
+
+#[pymethods]
+impl Engine {
+    #[new]
+    pub fn from_rules(network_filters: Vec<String>) -> Self {
+        let engine = RustEngine::from_rules(&network_filters);
+        Self { engine }
+    }
+
+    /// ## Request types
+    /// Examples of valid `request_type` parameters include:
+    /// * `beacon`
+    /// * `csp_report`
+    /// * `document`
+    /// * `font`
+    /// * `media`
+    /// * `object`
+    /// * `script`
+    /// * `stylesheet`
+    /// * and et cetera...
+    pub fn check_network_urls(
+        &self,
+        url: &str,
+        source_url: &str,
+        request_type: &str,
+    ) -> BlockerResult {
+        let blocker_result = self
+            .engine
+            .check_network_urls(url, source_url, request_type);
+        blocker_result.into()
+    }
+
+    pub fn check_network_urls_with_hostnames(
+        &self,
+        url: &str,
+        hostname: &str,
+        source_hostname: &str,
+        request_type: &str,
+        third_party_request: Option<bool>,
+    ) -> BlockerResult {
+        let blocker_result = self.engine.check_network_urls_with_hostnames(
+            url,
+            hostname,
+            source_hostname,
+            request_type,
+            third_party_request,
+        );
+        blocker_result.into()
+    }
+
+    pub fn check_network_urls_with_hostnames_subset(
+        &self,
+        url: &str,
+        hostname: &str,
+        source_hostname: &str,
+        request_type: &str,
+        third_party_request: Option<bool>,
+        previously_matched_rule: bool,
+        force_check_exceptions: bool,
+    ) -> BlockerResult {
+        let blocker_result = self.engine.check_network_urls_with_hostnames_subset(
+            url,
+            hostname,
+            source_hostname,
+            request_type,
+            third_party_request,
+            previously_matched_rule,
+            force_check_exceptions,
+        );
+        blocker_result.into()
+    }
+
+    pub fn filter_exists(&self, filter: &str) -> bool {
+        self.engine.filter_exists(filter)
+    }
+
+    pub fn tags_enable(&mut self, tags: Vec<&str>) {
+        self.engine.tags_enable(&tags);
+    }
+
+    pub fn tags_disable(&mut self, tags: Vec<&str>) {
+        self.engine.tags_disable(&tags);
+    }
+
+    pub fn tag_exists(&self, tag: &str) -> bool {
+        self.engine.tag_exists(tag)
+    }
+
+    // pub fn hidden_class_id_selectors(
+    //     &self,
+    //     classes: Vec<String>,
+    //     ids: Vec<String>,
+    //     exceptions: &PySet,
+    // ) -> PyResult<Vec<String>> {
+    //     let mut exception_hashset: HashSet<String> = HashSet::new();
+    //     for exception in exceptions.iter() {
+    //         let exception_pystr = PyString::from(exception);
+    //         exception_hashset.insert(exception.to_string());
+    //     }
+    //     Ok(self.engine
+    //         .hidden_class_id_selectors(&classes, &ids, &exception_hashset))
+    // }
+}