Merge branch 'master' into fix/1089

.bumpversion.cfg

@@ -0,0 +1,6 @@
+[bumpversion]
+current_version = 1.2.0
+commit = True
+tag = True
+
+[bumpversion:file:dateparser/__init__.py]

.flake8

@@ -0,0 +1,7 @@
+[flake8]
+
+max-line-length = 119
+ignore = W503, E203, E501, E722, F401, E701, E704
+
+exclude =
+    docs/conf.py

.git-blame-ignore-revs

@@ -0,0 +1,2 @@
+# Apply the auto-formatter black
+24c1637dcc77aac006db8ebcfbf5199fa7abac5d

.github/workflows/cifuzz.yml

@@ -0,0 +1,35 @@
+name: CIFuzz
+on: [pull_request]
+permissions: {}
+jobs:
+  Fuzzing:
+    runs-on: ubuntu-latest
+    permissions:
+      security-events: write
+    steps:
+    - name: Build Fuzzers
+      id: build
+      uses: google/oss-fuzz/infra/cifuzz/actions/build_fuzzers@master
+      with:
+        oss-fuzz-project-name: 'dateparser'
+        language: python
+    - name: Run Fuzzers
+      uses: google/oss-fuzz/infra/cifuzz/actions/run_fuzzers@master
+      with:
+        oss-fuzz-project-name: 'dateparser'
+        language: python
+        fuzz-seconds: 600
+        output-sarif: true
+    - name: Upload Crash
+      uses: actions/upload-artifact@v3
+      if: failure() && steps.build.outcome == 'success'
+      with:
+        name: artifacts
+        path: ./out/artifacts
+    - name: Upload Sarif
+      if: always() && steps.build.outcome == 'success'
+      uses: github/codeql-action/upload-sarif@v2
+      with:
+        # Path to SARIF file relative to the root of the repository
+        sarif_file: cifuzz-sarif/results.sarif
+        checkout_path: cifuzz-sarif

.github/workflows/main.yml

@@ -14,15 +14,9 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - python-version: 3.8
+          - python-version: 3.9
             env:
               TOXENV: flake8
-          - python-version: 3.7
-            env:
-              TOXENV: py
-          - python-version: 3.8
-            env:
-              TOXENV: py
           - python-version: 3.9
             env:
               TOXENV: py
@@ -38,18 +32,44 @@ jobs:
           - python-version: "3.11"
             env:
               TOXENV: latest
+          - python-version: "3.12"
+            env:
+              TOXENV: py
+          - python-version: "3.12"
+            env:
+              TOXENV: latest
+          - python-version: "3.13"
+            env:
+              TOXENV: py
+          - python-version: "3.13"
+            env:
+              TOXENV: latest
+          - python-version: "3.13"
+            env:
+              TOXENV: twinecheck
+          - python-version: "3.12"  # Keep in sync with tox.ini
+            env:
+              TOXENV: docs
     steps:
       - uses: actions/checkout@v3
       - name: 'Set up Python ${{ matrix.python-version }}'
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
-          python-version: '${{ matrix.python-version }}'
+          python-version: ${{ matrix.python-version }}
       - name: Install language-pack-fr
-        run: sudo apt-get update && sudo apt-get install language-pack-fr
-      - name: Install python dependencies
-        run: pip install tox
-      - name: tox
-        run: tox -e py
+        run: sudo apt-get update && sudo apt-get install -y language-pack-fr build-essential
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install tox
+      - name: Run tests
+        run: tox -e ${{ matrix.env.TOXENV }}
       - name: Upload coverage.xml to codecov
-        if: ${{ matrix.python-version == '3.9' && matrix.env.TOXENV == 'latest'}}
+        if: ${{ matrix.env.python-version == '3.9' && matrix.env.TOXENV == 'latest' }}
         uses: codecov/codecov-action@v3
+
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: pre-commit/[email protected]

.github/workflows/publish.yml

@@ -11,7 +11,7 @@ jobs:
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: "3.x"
       - name: Install dependencies

.isort.cfg

@@ -0,0 +1,2 @@
+[settings]
+profile = black

.pre-commit-config.yaml

@@ -0,0 +1,15 @@
+repos:
+- repo: https://github.com/PyCQA/flake8
+  rev: 6.0.0  # 6.0.0 drops Python 3.7 support
+  hooks:
+  - id: flake8
+    args: ['--config=.flake8']
+- repo: https://github.com/psf/black.git
+  rev: 23.3.0
+  hooks:
+  - id: black
+    exclude: ^dateparser/data/date_translation_data/
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0  # 5.12 drops Python 3.7 support
+  hooks:
+  - id: isort

.readthedocs.yml

@@ -0,0 +1,17 @@
+version: 2
+formats: all
+sphinx:
+  configuration: docs/conf.py
+  fail_on_warning: true
+
+build:
+  os: ubuntu-20.04
+  tools:
+    # For available versions, see:
+    # https://docs.readthedocs.io/en/stable/config-file/v2.html#build-tools-python
+    python: "3.11"  # Keep in sync with .github/workflows/checks.yml
+
+python:
+  install:
+    - requirements: docs/requirements.txt
+    - path: .

HISTORY.rst

@@ -3,6 +3,76 @@
 History
 =======
 
+1.2.0 (2023-11-17)
+------------------
+
+New features:
+
+- New ``PREFER_MONTH_OF_YEAR`` setting (#1146)
+
+Fixes:
+
+- Absolute years in Russian are no longer being treated as a number of years in
+  the past (#1129)
+
+Cleanups and internal improvements:
+
+- Removed the use of ``datetime.utcnow``, deprecated on Python 3.12 (#1179)
+- Applied Black formatting to the code base (#1158)
+- Initial integration with OSSFuzz (#1198)
+- Extended test cases (#1191)
+
+
+1.1.8 (2023-03-22)
+------------------
+
+Improvements:
+
+- Improved date parsing for Chinese (#1148)
+- Improved date parsing for Czech (#1151)
+- Reorder language by popularity (#1152)
+- Fix leak of memory in cache (#1140)
+- Add support for "\d units later" (#1154)
+- Move modification in CLDR data to yaml (#1153)
+- Add support to use timezone via settings to get PREFER_DATES_FROM result (#1155)
+
+
+1.1.7 (2023-02-02)
+------------------
+
+Improvements:
+
+- Add an “ago” synonym for Arabic (#1128)
+- Improved date parsing for Czech (#1131)
+- Improved date parsing for Indonesian (#1134)
+
+
+1.1.6 (2023-01-12)
+------------------
+
+Improvements:
+
+- Fix the bug where Monday is parsed as a month (#1121)
+- Prevent ReDoS in Spanish sentence splitting regex (#1084)
+
+
+1.1.5 (2022-12-29)
+------------------
+
+Improvements:
+
+- Parse short versions of day, month, and year (#1103)
+- Add a test for “in 1d” (#1104)
+- Update languages_info (#1107)
+- Add a workaround for zipimporter not having exec_module before Python 3.10 (#1069)
+- Stabilize tests at midnight (#1111)
+- Add a test case for French (#1110)
+
+Cleanups:
+
+- Remove the requirements-build file (#1113)
+
+
 1.1.4 (2022-11-21)
 ------------------
 

MANIFEST.in

@@ -5,7 +5,6 @@ include LICENSE
 include README.rst
 include dateparser_data/settings.py
 include requirements.txt
-include requirements-build.txt
 
 recursive-include tests *
 recursive-exclude * __pycache__

README.rst

@@ -50,7 +50,7 @@ Key Features
    locales <https://dateparser.readthedocs.io/en/latest/supported_locales.html>`__.
 -  Language autodetection
 -  Customizable behavior through
-   `settings <https://dateparser.readthedocs.io/en/latest/usage.html#settings>`__.
+   `settings <https://dateparser.readthedocs.io/en/latest/settings.html>`__.
 -  Support for `non-Gregorian calendar
    systems <https://dateparser.readthedocs.io/en/latest/introduction.html#supported-calendars>`__.
 -  Support for dates with timezones abbreviations or UTC offsets
@@ -144,8 +144,8 @@ For that reason it is important that the input is a valid date, otherwise it cou
 
 To reduce the possibility of receiving false positives, make sure that:
 
-- The input string it's a valid date and it doesn't contain any other words or numbers.
-- If you know the language or languages beforehand you add them through the ``languages`` or ``locales`` properties.
+- The input string is a valid date and doesn't contain any other words or numbers.
+- If you know the language or languages beforehand, you add them through the ``languages`` or ``locales`` properties.
 
 
 On the other hand, if you want to exclude any of the default parsers
@@ -156,7 +156,7 @@ are executed, you can do so through the
 Installation
 ------------
 
-Dateparser supports Python >= 3.7. You can install it by doing:
+Dateparser supports Python >= 3.9. You can install it by doing:
 
 ::
 
@@ -172,7 +172,7 @@ If you want to use the jalali or hijri calendar, you need to install the
 Common use cases
 ----------------
 
-**dateparser** can be used with a really different number of purposes,
+**dateparser** can be used for a wide variety of purposes,
 but it stands out when it comes to:
 
 Consuming data from different sources:
@@ -191,7 +191,7 @@ Offering natural interaction with users:
 
 -  **Tooling and CLI**: allow users to write “3 days ago” to retrieve
    information.
--  **Search engine**: allow people to search by date in an easiest /
+-  **Search engine**: allow people to search by date in an easy /
    natural format.
 -  **Bots**: allow users to interact with a bot easily
 

conftest.py

@@ -2,7 +2,8 @@ def pytest_collection_modifyitems(session, config, items):
     # Avoid executing tests when executing `--flake8` flag (pytest-flake8)
     try:
         from pytest_flake8 import Flake8Item
-        if config.getoption('--flake8'):
+
+        if config.getoption("--flake8"):
             items[:] = [item for item in items if isinstance(item, Flake8Item)]
     except ImportError:
         pass

dateparser/__init__.py

@@ -1,14 +1,21 @@
-__version__ = '1.1.4'
+__version__ = "1.2.0"
 
-from .date import DateDataParser
 from .conf import apply_settings
+from .date import DateDataParser
 
 _default_parser = DateDataParser()
 
 
 @apply_settings
-def parse(date_string, date_formats=None, languages=None, locales=None,
-          region=None, settings=None, detect_languages_function=None):
+def parse(
+    date_string,
+    date_formats=None,
+    languages=None,
+    locales=None,
+    region=None,
+    settings=None,
+    detect_languages_function=None,
+):
     """Parse date and time from given date string.
 
     :param date_string:
@@ -54,11 +61,22 @@ def parse(date_string, date_formats=None, languages=None, locales=None,
     """
     parser = _default_parser
 
-    if languages or locales or region or detect_languages_function or not settings._default:
-        parser = DateDataParser(languages=languages, locales=locales,
-                                region=region, settings=settings, detect_languages_function=detect_languages_function)
+    if (
+        languages
+        or locales
+        or region
+        or detect_languages_function
+        or not settings._default
+    ):
+        parser = DateDataParser(
+            languages=languages,
+            locales=locales,
+            region=region,
+            settings=settings,
+            detect_languages_function=detect_languages_function,
+        )
 
     data = parser.get_date_data(date_string, date_formats)
 
     if data:
-        return data['date_obj']
+        return data["date_obj"]