Merge branch 'release/0.8.0'

.github/workflows/ci.yml

@@ -25,10 +25,10 @@ jobs:
       -
         uses: actions/checkout@v4
       -
-        name: Set up Python 3.10
+        name: Set up Python 3.11
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.11'
           cache: 'pip'
       -
         name: Install Hatch
@@ -58,7 +58,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12', '3.13', 'pypy3.8', 'pypy3.9', 'pypy3.10']
+        python-version: [ '3.9', '3.10', '3.11', '3.12', '3.13', 'pypy3.9', 'pypy3.10']
 
     steps:
       -
@@ -70,6 +70,10 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
           cache: 'pip'
+      -
+        name: Pull Docker images
+        run: |
+          docker compose --file tests/docker/docker-compose.ci-test.yml pull
       -
         name: Install Hatch
         run: |
@@ -83,15 +87,20 @@ jobs:
       -
         name: Run tests
         run: |
-          hatch test --cover --python ${{ matrix.python-version }}
-          ls -ahl .
+          hatch test --cover --junitxml=junit.xml -o junit_family=legacy --python ${{ matrix.python-version }}
       -
         name: Upload coverage to Codecov
-        if: matrix.python-version == '3.10'
-        uses: codecov/codecov-action@v4
+        if: matrix.python-version == '3.11'
+        uses: codecov/codecov-action@v5
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+      -
+        name: Upload test results to Codecov
+        if: ${{ !cancelled() }}
+        uses: codecov/test-results-action@v1
         with:
-          # not required for public repos, but intermittently fails otherwise
           token: ${{ secrets.CODECOV_TOKEN }}
+          flags: python-${{ matrix.python-version }}
 
   build:
     name: Build
@@ -104,10 +113,10 @@ jobs:
       -
         uses: actions/checkout@v4
       -
-        name: Set up Python 3.10
+        name: Set up Python 3.11
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.11'
           cache: 'pip'
       -
         name: Install Hatch
@@ -180,4 +189,4 @@ jobs:
           path: dist
       -
         name: Publish build to PyPI
-        uses: pypa/gh-action-pypi-publish@v1.10.2
+        uses: pypa/gh-action-pypi-publish@v1.12.2

.pre-commit-config.yaml

@@ -28,7 +28,7 @@ repos:
       - id: detect-private-key
     # See https://github.com/prettier/prettier/issues/15742 for the fork reason
   - repo: https://github.com/rbubley/mirrors-prettier
-    rev: "v3.3.3"
+    rev: "v3.4.2"
     hooks:
       - id: prettier
         types_or:
@@ -41,13 +41,13 @@ repos:
       - id: codespell
   # Python hooks
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.6.9'
+    rev: 'v0.8.2'
     hooks:
       # Run the linter.
       - id: ruff
       # Run the formatter.
       - id: ruff-format
   - repo: https://github.com/tox-dev/pyproject-fmt
-    rev: "2.2.4"
+    rev: "v2.5.0"
     hooks:
       - id: pyproject-fmt

CHANGELOG.md

@@ -5,6 +5,26 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.8.0] - 2024-12-17
+
+### Breaking Change
+
+- Dropped support for Python 3.8 ([#36](https://github.com/stumpylog/tika-client/pull/36))
+
+### Fixed
+
+- Tests failed when run with Tika v3 ([#28](https://github.com/stumpylog/tika-client/pull/28))
+- Relaxed version restriction on `httpx`
+
+### Changed
+
+- Bump pypa/gh-action-pypi-publish from 1.10.2 to 1.12.2 (by [@dependabot](https://github.com/apps/dependabot) in [#33](https://github.com/stumpylog/tika-client/pull/33))
+- Bump codecov/codecov-action from 4 to 5 by (by [@dependabot](https://github.com/apps/dependabot)) ([#32](https://github.com/stumpylog/tika-client/pull/32))
+
+### Added
+
+- Integrated Codecov test analytics ([#34](https://github.com/stumpylog/tika-client/pull/34))
+
 ## [0.7.0] - 2024-10-09
 
 ### Added

README.md

@@ -6,7 +6,7 @@
 
 ---
 
-**Table of Contents**
+## Table of Contents
 
 - [Features](#features)
 - [Installation](#installation)
@@ -17,7 +17,7 @@
 ## Features
 
 - Simplified: No need to worry about XML or JSON responses, downloading a Tika jar file or Python 2
-- Support for Tika 2+ only
+- Support for Tika 2+ only (including Tika v3, which didn't change the API)
 - Based on the modern [httpx](https://github.com/encode/httpx) library
 - Full support for type hinting
 - Nearly full test coverage run against an actual Tika server for multiple Python and PyPy versions
@@ -39,7 +39,7 @@ from tika_client import TikaClient
 test_file = Path("sample.docx")
 
 
-with TikaClient("http://localhost:9998") as client
+with TikaClient("http://localhost:9998") as client:
 
     # Extract a document's metadata
     metadata = client.metadata.from_file(test_file)

pyproject.toml

@@ -16,7 +16,7 @@ license = "MPL-2.0"
 authors = [
   { name = "Trenton H", email = "[email protected]" },
 ]
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 classifiers = [
   "Development Status :: 4 - Beta",
   "Environment :: Web Environment",
@@ -25,7 +25,6 @@ classifiers = [
   "Operating System :: OS Independent",
   "Programming Language :: Python",
   "Programming Language :: Python :: 3 :: Only",
-  "Programming Language :: Python :: 3.8",
   "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
@@ -36,8 +35,7 @@ classifiers = [
 ]
 dynamic = [ "version" ]
 dependencies = [
-  "httpx~=0.24; python_version<'3.9'",
-  "httpx~=0.27; python_version>='3.9'",
+  "httpx>=0.27",
   "typing-extensions; python_version<'3.11'",
 ]
 
@@ -64,7 +62,7 @@ installer = "uv"
 
 [tool.hatch.envs.hatch-static-analysis]
 # https://hatch.pypa.io/latest/config/internal/static-analysis/
-dependencies = [ "ruff ~= 0.6" ]
+dependencies = [ "ruff ~= 0.8" ]
 config-path = "none"
 
 [tool.hatch.envs.hatch-test]
@@ -74,17 +72,15 @@ randomize = true
 dependencies = [
   "coverage-enable-subprocess == 1.0",
   "coverage[toml] ~= 7.6",
-  "pytest < 8.0; python_version < '3.9'",
-  "pytest ~= 8.3; python_version >= '3.9'",
+  "pytest ~= 8.3",
   "pytest-mock ~= 3.14",
   "pytest-randomly ~= 3.15",
-  "pytest-rerunfailures ~= 14.0",
+  "pytest-rerunfailures ~= 15.0",
   "pytest-xdist[psutil] ~= 3.6",
 ]
 extra-dependencies = [
   "pytest-sugar",
-  "pytest-httpx == 0.30.0; python_version >= '3.9'",
-  "pytest-httpx ~= 0.22; python_version < '3.9'",
+  "pytest-httpx ~= 0.33",
   "python-magic",
   "pytest-docker ~= 3.1",
 ]
@@ -109,15 +105,15 @@ cov-report = [
 ]
 
 [[tool.hatch.envs.hatch-test.matrix]]
-python = [ "3.8", "3.9", "3.10", "3.11", "3.12", "3.13", "pypy3.8", "pypy3.9", "pypy3.10" ]
+python = [ "3.9", "3.10", "3.11", "3.12", "3.13", "pypy3.8", "pypy3.9", "pypy3.10" ]
 
 #
 # Custom Environments
 #
 [tool.hatch.envs.typing]
 detached = true
 dependencies = [
-  "mypy ~= 1.11",
+  "mypy ~= 1.13",
   "httpx",
 ]
 
@@ -144,7 +140,7 @@ update = [ "pre-commit autoupdate" ]
 #
 
 [tool.ruff]
-target-version = "py38"
+target-version = "py39"
 line-length = 120
 
 # https://docs.astral.sh/ruff/settings/
@@ -239,7 +235,7 @@ lint.isort.known-first-party = [ "tika_client" ]
 max_supported_python = "3.13"
 
 [tool.pytest.ini_options]
-minversion = "7.0"
+minversion = "8.0"
 testpaths = [ "tests" ]
 
 [tool.coverage.run]

src/tika_client/__about__.py

@@ -1,4 +1,4 @@
 # SPDX-FileCopyrightText: 2023-present Trenton H <[email protected]>
 #
 # SPDX-License-Identifier: MPL-2.0
-__version__ = "0.7.0"
+__version__ = "0.8.0"

src/tika_client/__init__.py

@@ -7,4 +7,4 @@
 from tika_client.data_models import TikaKey
 from tika_client.data_models import XmpKey
 
-__all__ = ["TikaClient", "TikaKey", "XmpKey", "DublinCoreKey"]
+__all__ = ["DublinCoreKey", "TikaClient", "TikaKey", "XmpKey"]

src/tika_client/data_models.py

@@ -25,13 +25,26 @@
 
 
 class TikaKey(str, Enum):
+    """
+    Based on
+      - https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=235835139#MetadataOverview-TikaProcess
+      - https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=235835139#MetadataOverview-TikaGeneral
+    """
+
     Parsers = "X-TIKA:Parsed-By"
+    Parser_Full = "X-TIKA:Parsed-By-Full-Set"
+    Parse_Time = "X-TIKA:parse_time_millis"
     ContentType = "Content-Type"
     ContentLength = "Content-Length"
     Content = "X-TIKA:content"
 
 
 class DublinCoreKey(str, Enum):
+    """
+    Based on:
+      - https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=235835139#MetadataOverview-DublinCore
+    """
+
     Creator = "dc:creator"
     Created = "dcterms:created"
     Modified = "dcterms:modified"
@@ -49,6 +62,11 @@ class DublinCoreKey(str, Enum):
 
 
 class XmpKey(str, Enum):
+    """
+    Based on:
+      - https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=235835139#MetadataOverview-XMP(eXtensibleMetadataPlatform)
+    """
+
     About = "xmp:About"
     Created = "xmp:CreateDate"
     NumPages = "xmpTPg:NPages"

tests/conftest.py

@@ -1,6 +1,6 @@
 import logging
+from collections.abc import Generator
 from pathlib import Path
-from typing import Generator
 
 import pytest
 from pytest_docker.plugin import Services

tests/test_resource_tika.py

@@ -146,7 +146,7 @@ def test_html_document_from_string_buffer(self, tika_client: TikaClient, sample_
         resp = tika_client.tika.as_text.from_buffer(buffer)
 
         assert resp.type == "text/html; charset=UTF-8"
-        assert resp.parsers == ["org.apache.tika.parser.DefaultParser", "org.apache.tika.parser.html.HtmlParser"]
+        assert resp.parsers == ["org.apache.tika.parser.DefaultParser", "org.apache.tika.parser.html.JSoupParser"]
         assert "Hello world! This is HTML5 content in a file for" in resp.data["X-TIKA:content"]
         assert resp.data["dc:title"] == "This Is A Test"
         assert resp.data["description"] == "A sample HTML file"