Merge branch 'release/0.5.0'

.docker/docker-compose.ci-test.yml

@@ -6,7 +6,7 @@
 version: "3"
 services:
   tika:
-    image: ghcr.io/paperless-ngx/tika:latest
+    image: docker.io/apache/tika:latest
     hostname: tika
     container_name: tika
     network_mode: host

.github/workflows/ci.yml

@@ -23,7 +23,7 @@ jobs:
       contents: read
     steps:
       -
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       -
         name: Set up Python 3.10
         uses: actions/setup-python@v4
@@ -52,11 +52,11 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12-dev', 'pypy3.8', 'pypy3.9']
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12', 'pypy3.8', 'pypy3.9', 'pypy3.10']
 
     steps:
       -
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       -
         name: Start containers
         run: |
@@ -74,6 +74,10 @@ jobs:
         name: Install Hatch
         run: |
           pip3 --quiet install --upgrade hatch
+      -
+        name: List installed dependencies
+        run: |
+          hatch run pip-list
       -
         name: Run tests
         run: |
@@ -101,7 +105,7 @@ jobs:
       - lint
     steps:
       -
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       -
         name: Set up Python 3.10
         uses: actions/setup-python@v4
@@ -119,7 +123,7 @@ jobs:
       -
         uses: actions/upload-artifact@v3
         with:
-            name: artifacts
+            name: build-artifacts
             path: dist/*
             if-no-files-found: error
             retention-days: 7
@@ -135,11 +139,11 @@ jobs:
       - test
     steps:
       -
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       -
         uses: actions/download-artifact@v3
         with:
-          name: artifacts
+          name: build-artifacts
           path: dist
       -
         name: Get latest release info
@@ -173,8 +177,8 @@ jobs:
       -
         uses: actions/download-artifact@v3
         with:
-          name: artifacts
+          name: build-artifacts
           path: dist
       -
         name: Publish build to PyPI
-        uses: pypa/[email protected].8
+        uses: pypa/[email protected].10

.github/workflows/codeql.yml

@@ -43,7 +43,7 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL

.pre-commit-config.yaml

@@ -5,7 +5,7 @@
 repos:
   # General hooks
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v4.5.0
     hooks:
       - id: check-docstring-first
       - id: check-json
@@ -27,7 +27,7 @@ repos:
       - id: check-case-conflict
       - id: detect-private-key
   - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: 'v3.0.0'
+    rev: 'v3.0.3'
     hooks:
       - id: prettier
         types_or:
@@ -36,11 +36,11 @@ repos:
           - markdown
         exclude: "(^Pipfile\\.lock$)"
   # Python hooks
-  - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: 'v0.0.280'
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: 'v0.1.4'
     hooks:
       - id: ruff
   - repo: https://github.com/psf/black
-    rev: 23.7.0
+    rev: 23.10.1
     hooks:
       - id: black

CHANGELOG.md

@@ -5,6 +5,20 @@ 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).
 
+## [0.5.0] - 2023-11-07
+
+### Added
+
+- Testing on PyPy 3.10
+- Testing on released Python 3.12
+
+### Changed
+
+- `.github` and `.docker` folders are no longer included in the source distribution
+- Changed the license to Mozilla Public License Version 2.0
+- `pypa/gh-action-pypi-publish` updated to v1.8.10
+- CI testing now uses the official Apache Tika image (minimal) instead of the paperless-ngx image
+
 ## [0.4.0] - 2023-07-27
 
 ### Added

pyproject.toml

@@ -5,17 +5,17 @@ build-backend = "hatchling.build"
 [project]
 name = "tika-client"
 dynamic = ["version"]
-description = 'A modern REST client for Apache Tika server'
+description = "A modern REST client for Apache Tika server"
 readme = "README.md"
 requires-python = ">=3.8"
-license = "GPL-3.0-only"
+license = "MPL-2.0"
 keywords = []
 authors = [
-  { name = "Trenton H", email = "[email protected].com" },
+  { name = "Trenton H", email = "rda0128ou@mozmail.com" },
 ]
 classifiers = [
   "Development Status :: 4 - Beta",
-  "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
+  "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
   "Operating System :: OS Independent",
   "Intended Audience :: Developers",
   "Environment :: Web Environment",
@@ -30,7 +30,10 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy"
 ]
-dependencies = ["httpx ~= 0.24"]
+dependencies = [
+  "httpx ~= 0.25; python_version >= '3.9'",
+  "httpx ~= 0.24; python_version < '3.9'"
+]
 
 [project.urls]
 Documentation = "https://github.com/stumpylog/tika-rest-client#readme"
@@ -40,14 +43,21 @@ Source = "https://github.com/stumpylog/tika-rest-client"
 [tool.hatch.version]
 path = "src/tika_client/__about__.py"
 
+[tool.hatch.build.targets.sdist]
+exclude = [
+  ".github",
+  ".docker"
+]
+
 [tool.hatch.envs.default]
 dependencies = [
-  "coverage[toml]>=6.5",
-  "pytest",
+  "coverage[toml] >= 7.3",
+  "pytest >= 7.4",
   "pytest-sugar",
   "pytest-cov",
   "pytest-xdist",
-  "pytest-httpx",
+  "pytest-httpx ~= 0.26; python_version >= '3.9'",
+  "pytest-httpx ~= 0.22; python_version < '3.9'",
   "python-magic",
 ]
 
@@ -69,16 +79,17 @@ cov = [
   "cov-report",
   "cov-json"
 ]
+pip-list = "pip list"
 
 [[tool.hatch.envs.all.matrix]]
 python = ["3.8", "3.9", "3.10", "3.11"]
 
 [tool.hatch.envs.lint]
 detached = true
 dependencies = [
-  "black>=23.1.0",
-  "mypy>=1.0.0",
-  "ruff>=0.0.243",
+  "black>=23.10.0",
+  "mypy>=1.5.0",
+  "ruff>=0.1.3",
   "httpx",
 ]
 
@@ -103,43 +114,56 @@ target-version = ["py38"]
 line-length = 120
 
 [tool.ruff]
-# https://beta.ruff.rs/docs/settings/
+# https://docs.astral.sh/ruff/settings/
 fix = true
-format = "grouped"
+output-format = "grouped"
 target-version = "py38"
 line-length = 120
-# https://beta.ruff.rs/docs/rules/
+# https://docs.astral.sh/ruff/rules/
 extend-select = [
   "A",
   "ARG",
   "B",
   "C",
-	"COM",
+  "C4",
+  "COM",
   "DTZ",
   "E",
   "EM",
-	"EXE",
+  "ERA",
+  "EXE",
   "F",
   "FBT",
+  "FLY",
   "I",
   "ICN",
-	"INP",
+  "INP",
+  "INT",
   "ISC",
   "N",
-	"PIE",
-	"PTH",
+  "PERF",
+  "PIE",
+  "PGH",
+  "PTH",
+  "PL",
   "PLC",
   "PLE",
   "PLR",
   "PLW",
   "PT",
   "Q",
-	"RSE",
+  "RSE",
   "RUF",
   "S",
-	"SIM",
+  "SIM",
+  "SLF",
   "T",
+  "T10",
+  "T20",
+  "TCH",
+  "TD",
   "TID",
+  "TRY",
   "UP",
   "W",
   "YTT",

src/tika_client/__about__.py

@@ -1 +1 @@
-__version__ = "0.4.0"
+__version__ = "0.5.0"

src/tika_client/_resource_recursive.py

@@ -22,10 +22,7 @@ def _common_call(
         """
         Given a specific endpoint and a file, do a multipart put to the endpoint
         """
-        documents: List[TikaResponse] = []
-        for item in self._put_multipart(endpoint, filepath, mime_type):
-            documents.append(self._decoded_response(item))
-        return documents
+        return [self._decoded_response(item) for item in self._put_multipart(endpoint, filepath, mime_type)]
 
 
 class _RecursiveMetaHtml(_TikaRmetaBase):

src/tika_client/_utils.py

@@ -29,7 +29,7 @@ def _put_multipart(self, endpoint: str, filepath: Path, mime_type: MimeType = No
             if mime_type is not None:
                 files = {"upload-file": (filepath.name, handle, mime_type)}
             else:
-                files = {"upload-file": (filepath.name, handle)}  # type: ignore
+                files = {"upload-file": (filepath.name, handle)}  # type: ignore [dict-item]
             try:
                 # Filename is valid ASCII, use it
                 filepath.name.encode("ascii")

src/tika_client/data_models.py

@@ -12,6 +12,7 @@
 # Based on https://cwiki.apache.org/confluence/display/TIKA/Metadata+Overview
 
 logger = logging.getLogger("tika-client.data")
+
 _TIME_RE = re.compile(
     r"(?P<year>\d{4})-"
     r"(?P<month>\d{2})-"
@@ -87,7 +88,6 @@ def __init__(self, data: Dict) -> None:
         self.title = self.get_optional_string(DublinCoreKey.Title)
 
         # Xmp keys
-        # TODO: Implement more of these
         self.xmp_created = self.get_optional_datetime(XmpKey.Created)
         self.page_count = self.get_optional_int(XmpKey.NumPages)