Merge branch 'master' of https://git.eseb.ovh/DemiSel/Messenger_1Million_Stats into DEV-Mael

.drone.yml

@@ -0,0 +1,20 @@
+kind: pipeline
+type: docker
+name: run_tests
+
+volumes:
+- name: docker_sock
+  host:
+    path: /var/run/docker.sock
+
+steps:
+- name: build and test in docker image
+  image: docker
+  volumes:
+  - name: docker_sock
+    path: /var/run/docker.sock
+  commands:
+  - docker build --build-arg STAGE=test -t mytestimage .
+  - docker run mytestimage python -m pytest test
+  when:
+    event: [push]

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.11-buster
+
+
+RUN pip install poetry
+
+COPY pyproject.toml poetry.lock ./
+COPY ./million ./million
+COPY ./test ./test
+
+RUN poetry config virtualenvs.create false \
+    && poetry install --no-interaction --no-ansi

million/analyze/word_finder.py

@@ -0,0 +1,11 @@
+import re
+from typing import List
+from million.model.message import Message
+
+
+def _wordFilter(msg: Message, words: List[str]) -> bool:
+    rgx = r"(\b"+ r'\b|\b'.join(words) + r"\b)"
+    return msg.content and re.search(rgx, msg.content, re.I)
+
+def findWords(messages: List[Message], words: List[str]) -> List[Message]:
+    return filter(lambda m: _wordFilter(m, words), messages)

poetry.lock

@@ -12,6 +12,17 @@ files = [
 ]
 
 [[package]]
+name = "colorama"
+version = "0.4.6"
+description = "Cross-platform colored terminal text."
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+files = [
+    {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
+    {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
+]
+
+[[package]]
 name = "contourpy"
 version = "1.2.0"
 description = "Python library for calculating contours of 2D quadrilateral grids"
@@ -90,6 +101,20 @@ docs = ["ipython", "matplotlib", "numpydoc", "sphinx"]
 tests = ["pytest", "pytest-cov", "pytest-xdist"]
 
 [[package]]
+name = "exceptiongroup"
+version = "1.2.0"
+description = "Backport of PEP 654 (exception groups)"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "exceptiongroup-1.2.0-py3-none-any.whl", hash = "sha256:4bfd3996ac73b41e9b9628b04e079f193850720ea5945fc96a08633c66912f14"},
+    {file = "exceptiongroup-1.2.0.tar.gz", hash = "sha256:91f5c769735f051a4290d52edd0858999b57e5876e9f85937691bd4c9fa3ed68"},
+]
+
+[package.extras]
+test = ["pytest (>=6)"]
+
+[[package]]
 name = "fonttools"
 version = "4.49.0"
 description = "Tools to manipulate font files"
@@ -155,6 +180,17 @@ unicode = ["unicodedata2 (>=15.1.0)"]
 woff = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "zopfli (>=0.1.4)"]
 
 [[package]]
+name = "iniconfig"
+version = "2.0.0"
+description = "brain-dead simple config-ini parsing"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"},
+    {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
+]
+
+[[package]]
 name = "kiwisolver"
 version = "1.4.5"
 description = "A fast implementation of the Cassowary constraint solver"
@@ -529,6 +565,21 @@ typing = ["typing-extensions"]
 xmp = ["defusedxml"]
 
 [[package]]
+name = "pluggy"
+version = "1.4.0"
+description = "plugin and hook calling mechanisms for python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "pluggy-1.4.0-py3-none-any.whl", hash = "sha256:7db9f7b503d67d1c5b95f59773ebb58a8c1c288129a88665838012cfb07b8981"},
+    {file = "pluggy-1.4.0.tar.gz", hash = "sha256:8c85c2876142a764e5b7548e7d9a0e0ddb46f5185161049a79b7e974454223be"},
+]
+
+[package.extras]
+dev = ["pre-commit", "tox"]
+testing = ["pytest", "pytest-benchmark"]
+
+[[package]]
 name = "pydantic"
 version = "2.6.1"
 description = "Data validation using Python type hints"
@@ -653,6 +704,28 @@ files = [
 diagrams = ["jinja2", "railroad-diagrams"]
 
 [[package]]
+name = "pytest"
+version = "8.0.2"
+description = "pytest: simple powerful testing with Python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "pytest-8.0.2-py3-none-any.whl", hash = "sha256:edfaaef32ce5172d5466b5127b42e0d6d35ebbe4453f0e3505d96afd93f6b096"},
+    {file = "pytest-8.0.2.tar.gz", hash = "sha256:d4051d623a2e0b7e51960ba963193b09ce6daeb9759a451844a21e4ddedfc1bd"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "sys_platform == \"win32\""}
+exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
+iniconfig = "*"
+packaging = "*"
+pluggy = ">=1.3.0,<2.0"
+tomli = {version = ">=1.0.0", markers = "python_version < \"3.11\""}
+
+[package.extras]
+testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
+
+[[package]]
 name = "python-dateutil"
 version = "2.8.2"
 description = "Extensions to the standard Python datetime module"
@@ -689,6 +762,17 @@ files = [
 ]
 
 [[package]]
+name = "tomli"
+version = "2.0.1"
+description = "A lil' TOML parser"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
+    {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
+]
+
+[[package]]
 name = "typing-extensions"
 version = "4.9.0"
 description = "Backported and Experimental Type Hints for Python 3.8+"
@@ -713,4 +797,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "2f3cf452fb668f0f7dc134643e52cee57a754cb616cd4525addbb07d985a24d8"
+content-hash = "6cc1be4150b37f0fea2143e00fd6378e4db08d286a551fb6d6981593638cba5a"

pyproject.toml

@@ -13,6 +13,9 @@ pydantic = "^2.6.1"
 pandas = "^2.2.0"
 
 
+[tool.poetry.group.test.dependencies]
+pytest = "^8.0.2"
+
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"

pytest.ini

@@ -0,0 +1,2 @@
+[pytest]
+python_files = *_test.py

scripts/find_gromots.py

@@ -0,0 +1,44 @@
+from datetime import datetime
+from million.analyze.word_finder import findWords
+from million.parse.fb_exports import FacebookExportParser
+
+
+DATA_PATH = './data/'
+
+parser = FacebookExportParser()
+
+export = parser.parse(DATA_PATH)
+
+gros_mots = [
+    '.*merde.*',
+    'sexe',
+    'pute',
+    'pé?dé?',
+    'putain',
+    'bite',
+    'encul.*',
+    'cul',
+    'nichon',
+    'gueule',
+    'con(ne)?',
+    'chatte',
+    'niqu.*',
+    'chi(é|e).*',
+    'bais.*'
+    ]
+
+msg_gros_mots = findWords(export.messages, gros_mots)
+
+msg_gros_mots_grp = {}
+
+for msg in msg_gros_mots:
+    if msg.sender_name not in msg_gros_mots_grp: msg_gros_mots_grp[msg.sender_name] = []
+    msg_gros_mots_grp[msg.sender_name].append(msg)
+
+for name in sorted(msg_gros_mots_grp, key = lambda k: len(msg_gros_mots_grp[k])):
+    print(name)
+
+    for msg in msg_gros_mots_grp[name]:
+        time = datetime.fromtimestamp(msg.timestamp_ms / 1000)
+        time_str = time.strftime("%d/%m/%Y %H:%M:%S")
+        print(f"\t{time_str} : {msg.content}")

test/TestCase.py

@@ -0,0 +1,9 @@
+
+import unittest
+
+from million.model.message import Message
+
+
+class TestCase(unittest.TestCase):
+    def _message_with_text(self, text: str):
+        return Message(content=text, sender_name="test", timestamp_ms=0)

test/model/message_test.py

@@ -0,0 +1,27 @@
+
+
+from million.model.message import Message
+from test.TestCase import TestCase
+
+
+class MessageTest(TestCase):
+
+    def test_message_nominal(self, overrides=None, exclude=None):
+        message = self._message_with_text("1")
+
+        assert 1 == message.get_counted_value()
+
+    def test_message_with_text(self, overrides=None, exclude=None):
+        message = self._message_with_text("1 text")
+
+        assert 1 == message.get_counted_value()
+
+    def test_message_floored_dot(self, overrides=None, exclude=None):
+        message = self._message_with_text("1.5")
+
+        assert 1 == message.get_counted_value()
+
+    def test_message_floored_comma(self, overrides=None, exclude=None):
+        message = self._message_with_text("1,5")
+
+        assert 1 == message.get_counted_value()