fix(devcontainer): reflect updates to pyproject.toml in #22

- Use the recommended PEP621 syntax for the pyproject.toml

.devcontainer/Dockerfile

@@ -17,9 +17,9 @@ RUN pip install --no-cache-dir --upgrade pip
 RUN pipx install poetry==${POETRY_VERSION}
 
 WORKDIR /app
-COPY pyproject.toml poetry.lock setup.py README.md ./
+COPY pyproject.toml poetry.lock README.md LICENSE.txt ./
 # pre-install dependencies
-RUN --mount=type=cache,target=/root/.cache poetry install --no-root 
+RUN --mount=type=cache,target=/root/.cache poetry install --no-root
 
 COPY notebooks /app/notebooks/
 COPY d3lta /app/d3lta/
@@ -27,4 +27,8 @@ RUN --mount=type=cache,target=/root/.cache poetry install
 
 FROM d3lta-prod AS d3lta-dev
 
-RUN --mount=type=cache,target=/root/.cache poetry install --with dev
+RUN --mount=type=cache,target=/root/.cache poetry install --with dev
+
+# install nektos/act as specified in https://nektosact.com/installation/index.html#bash-script
+# the -b flag specifies the target directory (cf. https://github.com/nektos/act/blob/61396d8085a9d812cebf94fa954f5938d48bf2b9/install.sh#L13)
+RUN curl --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/nektos/act/master/install.sh | sudo bash -s -- -b /usr/bin

.devcontainer/devcontainer.json

@@ -4,6 +4,14 @@
 	"name": "Python 3",
 	"dockerFile": "./Dockerfile",
 	"context": "..",
-	// Features to add to the dev container. More info: https://containers.dev/features.
+	"customizations": {
-	// "features": {}
+		"vscode": {
-}
+			"extensions": [
+				"github.vscode-github-actions"
+			]
+		}
+	},
+	"features": {
+		"ghcr.io/devcontainers/features/docker-in-docker:2": {}
+	}
+}

.github/workflows/publish-to-pypi.yml

@@ -1,63 +1,69 @@
 # derived from https://packaging.python.org/en/latest/guides/publishing-package-distribution-releases-using-github-actions-ci-cd-workflows/#the-whole-ci-cd-workflow
-name: Publish Python 🐍 distribution 📦 to PyPI and TestPyPI
+name: Publish Python distribution to PyPI
 
-on: push
+on:
+  release:
+    types: [published]
+
+env:
+  ACT: false  # env.ACT == true when running inside nektos/act
 
 jobs:
-  unit-test:
-    name: Run unit tests 🤾
-    runs-on: ubuntu-latest
-
-    steps:
-    - uses: actions/checkout@v4
-      with:
-        persist-credentials: false
-    - name: Set up Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: "3.11"
-    - name: Install dependencies
-      run: |
-        pip install poetry
-        poetry install --with dev 
-    - name: Build a binary wheel and a source tarball
-      run: 
-        poetry run pytest
-
   build:
-    name: Build distribution 📦
+    name: Build distribution
-    needs:
+    # based on https://stackoverflow.com/a/74318141
-    - unit-test
+    if: ${{ github.event.release.target_commitish == 'main'}}
     runs-on: ubuntu-latest
 
     steps:
     - uses: actions/checkout@v4
       with:
         persist-credentials: false
+
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
         python-version: "3.x"
-    - name: Install pypa/build
+
-      run: >-
-        python3 -m
-        pip install
-        build
-        --user
     - name: Build a binary wheel and a source tarball
-      run: python3 -m build
+      run: pipx run build
+
     - name: Store the distribution packages
       uses: actions/upload-artifact@v4
       with:
-        name: python-package-distributions
+        name: distfiles
         path: dist/
+        if-no-files-found: error
+
+  # taken from https://github.com/python-poetry/poetry/blob/b580e8aa4fbce53569420e7b42568dfd9e73519f/.github/workflows/release.yaml
+  upload-built-distribution-to-github-release:
+    name: Upload (GitHub)
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    needs: build
+    steps:
+      # Checking-out the project since the gh CLI expects to be called in the context of a git repository.
+      - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
+
+      - name: Retrieve built distribution
+        uses: actions/download-artifact@v4
+        with:
+          name: distfiles
+          path: dist/
+
+      - run: gh release upload "${TAG_NAME}" dist/*.{tar.gz,whl}
+        # skip step when debugging locally via nektos/act
+        if: ${{ !env.ACT }}
+        env:
+          GH_TOKEN: ${{ github.token }}
+          TAG_NAME: ${{ github.event.release.tag_name }}
 
   publish-to-pypi:
-    name: >-
+    name: Publish Python distribution to PyPI
-      Publish Python 🐍 distribution 📦 to PyPI
+    needs: build
-    if: startsWith(github.ref, 'refs/tags/')  # only publish to PyPI on tag pushes
-    needs:
-    - build
     runs-on: ubuntu-latest
     environment:
       name: pypi
@@ -66,77 +72,15 @@ jobs:
       id-token: write  # IMPORTANT: mandatory for trusted publishing
 
     steps:
-    - name: Download all the dists
+      - name: Retrieve built distribution
-      uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v4
-      with:
+        with:
-        name: python-package-distributions
+          name: distfiles
-        path: dist/
+          path: dist/
-    - name: Publish distribution 📦 to PyPI
-      uses: pypa/gh-action-pypi-publish@release/v1
 
-  github-release:
+      - name: Publish distribution to PyPI
-    name: >-
+        # skip step when debugging locally via nektos/act
-      Sign the Python 🐍 distribution 📦 with Sigstore
+        if: ${{ !env.ACT }}
-      and upload them to GitHub Release
+        uses: pypa/gh-action-pypi-publish@release/v1
-    needs:
+        with:
-    - publish-to-pypi
+          print-hash: true
-    runs-on: ubuntu-latest
-
-    permissions:
-      contents: write  # IMPORTANT: mandatory for making GitHub Releases
-      id-token: write  # IMPORTANT: mandatory for sigstore
-
-    steps:
-    - name: Download all the dists
-      uses: actions/download-artifact@v4
-      with:
-        name: python-package-distributions
-        path: dist/
-    - name: Sign the dists with Sigstore
-      uses: sigstore/gh-action-sigstore-python@v3.0.0
-      with:
-        inputs: >-
-          ./dist/*.tar.gz
-          ./dist/*.whl
-    - name: Create GitHub Release
-      env:
-        GITHUB_TOKEN: ${{ github.token }}
-      run: >-
-        gh release create
-        "$GITHUB_REF_NAME"
-        --repo "$GITHUB_REPOSITORY"
-        --notes ""
-    - name: Upload artifact signatures to GitHub Release
-      env:
-        GITHUB_TOKEN: ${{ github.token }}
-      # Upload to GitHub Release using the `gh` CLI.
-      # `dist/` contains the built packages, and the
-      # sigstore-produced signatures and certificates.
-      run: >-
-        gh release upload
-        "$GITHUB_REF_NAME" dist/**
-        --repo "$GITHUB_REPOSITORY"
-
-  publish-to-testpypi:
-    name: Publish Python 🐍 distribution 📦 to TestPyPI
-    needs:
-    - build
-    runs-on: ubuntu-latest
-
-    environment:
-      name: testpypi
-      url: https://test.pypi.org/p/d3lta  # pypi is case insensitive so d3lta == D3lta
-
-    permissions:
-      id-token: write  # IMPORTANT: mandatory for trusted publishing
-
-    steps:
-    - name: Download all the dists
-      uses: actions/download-artifact@v4
-      with:
-        name: python-package-distributions
-        path: dist/
-    - name: Publish distribution 📦 to TestPyPI
-      uses: pypa/gh-action-pypi-publish@release/v1
-      with:
-        repository-url: https://test.pypi.org/legacy/

.github/workflows/test.yml

@@ -0,0 +1,28 @@
+name: Run tests
+
+on: push
+
+jobs:
+  unit-test:
+    name: Run unit tests
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        persist-credentials: false
+
+    - name: Install poetry
+      run: pipx install poetry
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.11"
+        cache: poetry
+
+    - name: Install dependencies
+      run: poetry install --with dev
+
+    - name: Run tests
+      run: poetry run pytest

.gitignore

@@ -228,4 +228,5 @@ pyrightconfig.json
 *.ftz
 use_model_kaggle/
 include/
-.benchmarks
+.benchmarks
+.act-event.json

README.md

@@ -1,43 +1,22 @@
-<h2 align="center"> <a href="https://arxiv.org/abs/2312.17338">D3lta</a></h2>
+# D3lta
 
-<h5 align="center"> 
+[![PyPI - Version](https://img.shields.io/pypi/v/d3lta?style=flat&logo=pypi&logoColor=%233775A9&label=PyPI)](https://pypi.org/project/d3lta/)
-
+[![arXiv](https://img.shields.io/badge/Arxiv-2312.17338-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2312.17338)
-If you like our project, please give us a star ⭐ on GitHub for the latest update.  </h2>
-
-</h5>
-
-<div align=center>
-  
-[![arXiv](https://img.shields.io/badge/Arxiv-2312.17338-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2312.17338) 
 
 This repository is the official implementation of D3lta, a library for detecting duplicate verbatim contents within a vast amount of documents.
 
 It distinguishes 3 types of duplicate contents : copypasta (almost exact duplicates), rewording and translation. You can run it on CPU.
-</div>
 
 ---
 
 <img style="display: block; margin: auto;" src="https://github.com/VIGINUM-FR/D3lta/raw/main/static/graph.gif"/>
 
 
-## 💻 Installing 
+## 💻 Installation
-
-Clone the repository
 
 ```bash
-git clone https://github.com/VIGINUM-FR/D3lta
+# PyPI is case insensitive, so d3lta == D3lta
-```
+pip install d3lta
-
-Navigate to the project
-
-```bash
-cd D3lta
-```
-
-Install the package
-
-```bash
-pip install -e .
 ```
 
 ## 🚀 Quick start
@@ -163,11 +142,10 @@ matches, df_clusters = semantic_faiss(
 matches
 ```
 
-
-
 ## 📚 Synthetic dataset
 
-The dataset is available in the release `1.0.0`. It contains the following files:
+The dataset is available in the [`1.0.0` release](https://github.com/VIGINUM-FR/D3lta/releases/tag/1.0.0).
+It contains the following files:
 
 ### `synthetic_dataset_documents.csv`:
 
@@ -205,10 +183,30 @@ Column details:
 
 ## Notebooks
 
-In folder the [`notebooks`](./notebooks/), you can find: 
+In the [`notebooks`](./notebooks/) directory, you can find: 
-- [`example_synthetic_dataset.ipynb`](./notebooks/example_synthetic_dataset.ipynb): Example of applying threedelta methodology to the synthetic dataset, with a comparison to the true labels.
+- [`example_synthetic_dataset.ipynb`](./notebooks/example_synthetic_dataset.ipynb): example of applying the D3lta methodology to the synthetic dataset, with a comparison to the true labels.
 
 
+## 👩‍💻 Developing
+
+Clone the repository
+
+```bash
+git clone https://github.com/VIGINUM-FR/D3lta
+```
+
+Navigate to the project
+
+```bash
+cd D3lta
+```
+
+Install the package
+
+```bash
+pip install -e .
+```
+
 ## Citation
 
 If you find our paper and code useful in your research, please consider giving a star 🌟  and a citation 📝:

d3lta/emojis_remover.py

@@ -3,8 +3,6 @@ from abc import ABC, abstractmethod
 from dataclasses import dataclass
 from typing import final
 
-import demoji
-
 
 @dataclass
 class EmojisRemover(ABC):
@@ -96,8 +94,3 @@ class ExplicitUnicodeBlocksEmojisRemover(EmojisRemover):
 
     def _remove_symbols_implementation(self, text: str) -> str:
         return self.SYMBOLS_REGEX.sub(r"", text)
-
-
-class DemojiEmojisRemover(EmojisRemover):
-    def _remove_symbols_implementation(self, text: str) -> str:
-        return demoji.replace(text)

poetry.lock

@@ -155,21 +155,6 @@ files = [
 ]
 markers = {main = "platform_system == \"Windows\"", dev = "sys_platform == \"win32\""}
 
-[[package]]
-name = "demoji"
-version = "1.1.0"
-description = "Accurately remove and replace emojis in text strings"
-optional = false
-python-versions = ">=3.6"
-groups = ["main"]
-files = [
-    {file = "demoji-1.1.0-py3-none-any.whl", hash = "sha256:6d3256c909aea299e97fe984f827a2a060c2a8f8bfcbafa7ec9659967c5df50f"},
-    {file = "demoji-1.1.0.tar.gz", hash = "sha256:072efaeca725e6f63ab59d83abeb55b178842538ed9256455a82ebbd055ff216"},
-]
-
-[package.extras]
-ujson = ["ujson"]
-
 [[package]]
 name = "exceptiongroup"
 version = "1.3.0"
@@ -1060,18 +1045,6 @@ files = [
     {file = "protobuf-5.29.4.tar.gz", hash = "sha256:4f1dfcd7997b31ef8f53ec82781ff434a28bf71d9102ddde14d076adcfc78c99"},
 ]
 
-[[package]]
-name = "py-cpuinfo"
-version = "9.0.0"
-description = "Get CPU info with pure Python"
-optional = false
-python-versions = "*"
-groups = ["dev"]
-files = [
-    {file = "py-cpuinfo-9.0.0.tar.gz", hash = "sha256:3cdbbf3fac90dc6f118bfd64384f309edeadd902d7c8fb17f02ffa1fc3f49690"},
-    {file = "py_cpuinfo-9.0.0-py3-none-any.whl", hash = "sha256:859625bc251f64e21f077d099d4162689c762b5d6a4c3c97553d56241c9674d5"},
-]
-
 [[package]]
 name = "pybind11"
 version = "2.13.6"
@@ -1125,27 +1098,6 @@ tomli = {version = ">=1", markers = "python_version < \"3.11\""}
 [package.extras]
 dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
 
-[[package]]
-name = "pytest-benchmark"
-version = "5.1.0"
-description = "A ``pytest`` fixture for benchmarking code. It will group the tests into rounds that are calibrated to the chosen timer."
-optional = false
-python-versions = ">=3.9"
-groups = ["dev"]
-files = [
-    {file = "pytest-benchmark-5.1.0.tar.gz", hash = "sha256:9ea661cdc292e8231f7cd4c10b0319e56a2118e2c09d9f50e1b3d150d2aca105"},
-    {file = "pytest_benchmark-5.1.0-py3-none-any.whl", hash = "sha256:922de2dfa3033c227c96da942d1878191afa135a29485fb942e85dff1c592c89"},
-]
-
-[package.dependencies]
-py-cpuinfo = "*"
-pytest = ">=8.1"
-
-[package.extras]
-aspect = ["aspectlib"]
-elasticsearch = ["elasticsearch"]
-histogram = ["pygal", "pygaljs", "setuptools"]
-
 [[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"
@@ -1291,6 +1243,28 @@ files = [
     {file = "six-1.17.0.tar.gz", hash = "sha256:ff70335d468e7eb6ec65b95b99d3a2836546063f63acc5171de367e834932a81"},
 ]
 
+[[package]]
+name = "smart-open"
+version = "5.1.0"
+description = "Utils for streaming large files (S3, HDFS, GCS, Azure Blob Storage, gzip, bz2...)"
+optional = false
+python-versions = ">=3.6.*"
+groups = ["main"]
+markers = "python_version >= \"3.12\""
+files = [
+    {file = "smart_open-5.1.0-py3-none-any.whl", hash = "sha256:2059b07f530c8c9e2158e4e1575309aacb74bd813da2325c1f348015d04f3bd6"},
+    {file = "smart_open-5.1.0.tar.gz", hash = "sha256:e4dc1350b240ef0759e343e4e2f361bfd4e5477bb2619866e97f80240652e92e"},
+]
+
+[package.extras]
+all = ["azure-common", "azure-core", "azure-storage-blob", "boto3", "google-cloud-storage", "requests"]
+azure = ["azure-common", "azure-core", "azure-storage-blob"]
+gcs = ["google-cloud-storage"]
+http = ["requests"]
+s3 = ["boto3"]
+test = ["azure-common", "azure-core", "azure-storage-blob", "boto3", "google-cloud-storage", "moto[server] (==1.3.14)", "parameterizedtestcase", "paramiko", "pathlib2", "pytest", "pytest-rerunfailures", "requests", "responses"]
+webhdfs = ["requests"]
+
 [[package]]
 name = "smart-open"
 version = "7.1.0"
@@ -1298,6 +1272,7 @@ description = "Utils for streaming large files (S3, HDFS, GCS, Azure Blob Storag
 optional = false
 python-versions = "<4.0,>=3.7"
 groups = ["main"]
+markers = "python_version <= \"3.11\""
 files = [
     {file = "smart_open-7.1.0-py3-none-any.whl", hash = "sha256:4b8489bb6058196258bafe901730c7db0dcf4f083f316e97269c66f45502055b"},
     {file = "smart_open-7.1.0.tar.gz", hash = "sha256:a4f09f84f0f6d3637c6543aca7b5487438877a21360e7368ccf1f704789752ba"},
@@ -1747,5 +1722,5 @@ files = [
 
 [metadata]
 lock-version = "2.1"
-python-versions = "^3.10"
+python-versions = ">=3.10"
-content-hash = "2a469cf6cd729d58a4315152a037a242fdc09dba63fe3adfe00bbb88c3f16863"
+content-hash = "3315c4aedc40f50a78569149ca711d514b9a06b30c9c3b5a6f1402e5abf7e032"

pyproject.toml

@@ -1,32 +1,32 @@
-[tool.poetry]
+[project]
 name = "d3lta"
-version = "1.0.0.post2"
+version = "1.0.2"
 description = "A library for detecting verbatim-duplicated contents within a vast amount of documents"
 readme = "README.md"
-authors = ["Viginum"]
+authors = [{ name = "VIGINUM" }]
+license = { file = "LICENSE.txt" }
+requires-python = ">=3.10"
+dependencies = [
+    "faiss-cpu==1.9.0.post1",
+    "fasttext==0.9.3",
+    "gensim==4.3.3",
+    "networkx==2.8.8",
+    "pandas==2.2.3",
+    "polyleven==0.8",
+    "scipy==1.12.0",
+    "tensorflow==2.18.0",
+    "tensorflow-hub==0.16.1",
+    "tensorflow-text==2.18.1",
+    "tqdm==4.67.1",
+]
 
-[tool.poetry.dependencies]
-python = "^3.10"
-demoji = "^1.1.0"
-faiss-cpu = "1.9.0.post1"
-fasttext = "0.9.3"
-gensim = "4.3.3"
-networkx = "2.8.8"
-pandas = "2.2.3"
-polyleven = "0.8"
-scipy = "1.12.0"
-tensorflow = "2.18.0"
-tensorflow-hub = "0.16.1"
-tensorflow-text = "2.18.1"
-tqdm = "4.67.1"
 
 [tool.poetry.group.dev]
 optional = true
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.3.5"
-pytest-benchmark = "^5.1.0"
 
 [build-system]
-requires = ["setuptools", "poetry-core"]
+requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"

setup.py

@@ -1,4 +0,0 @@
-#!/usr/bin/env python
-from setuptools import setup
-
-setup()

tests/emojis_remover_test.py

@@ -6,9 +6,6 @@ from get_unicode_emojis_list import (
     EMOJI_TESTFILE_FILENAME,
     get_all_emojis_from_latest_unicode_emojis_specification_with_download,
 )
-from pytest_benchmark.fixture import (
-    BenchmarkFixture,
-)
 
 import d3lta.emojis_remover
 
@@ -17,13 +14,6 @@ import d3lta.emojis_remover
     name="emojis_remover",
     params=[
         d3lta.emojis_remover.ExplicitUnicodeBlocksEmojisRemover,
-        pytest.param(
-            d3lta.emojis_remover.DemojiEmojisRemover,
-            marks=pytest.mark.xfail(
-                reason="`demoji`'s detection engine does not detect all emojis in the Unicode specification",
-                strict=True,
-            ),
-        ),
     ],
 )
 def fixture_emojis_remover(
@@ -108,11 +98,8 @@ In consequence whereof, the National 🏞️  Assembly 👩‍🏭👨‍🏭  r
 def test_on_text_sample(
     emojis_remover: d3lta.emojis_remover.EmojisRemover,
     sample_text_with_emojipasta: str,
-    sample_text: str,
+    sample_text: str
-    benchmark: BenchmarkFixture,
 ):
-    processed = benchmark(
+    assert emojis_remover.remove_symbols(
-        emojis_remover.remove_symbols,
         sample_text_with_emojipasta,
-    )
+    ) == sample_text
-    assert processed == sample_text