Port to Python 3 and Plone 6

.editorconfig

@@ -0,0 +1,35 @@
+
+# EditorConfig Configuration file, for more details see:
+# https://EditorConfig.org
+# EditorConfig is a convention description, that could be interpreted
+# by multiple editors to enforce common coding conventions for specific
+# file types
+
+# top-most EditorConfig file:
+# Will ignore other EditorConfig files in Home directory or upper tree level.
+root = true
+
+
+[*]  # For All Files
+# Unix-style newlines with a newline ending every file
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+# Set default charset
+charset = utf-8
+# Indent style default
+indent_style = space
+
+[*.{py,cfg,ini}]
+# 4 space indentation
+indent_size = 4
+
+[*.{html,dtml,pt,zpt,xml,zcml,js,json,ts,less,scss,css,sass,yml,yaml}]
+# 2 space indentation
+indent_size = 2
+
+[{Makefile,.gitmodules}]
+# Tab indentation (no size specified, but view as 4 spaces)
+indent_style = tab
+indent_size = unset
+tab_width = unset

.github/workflows/plone-package.yml

@@ -0,0 +1,82 @@
+name: Plone package
+
+# Every action is pinned to a full commit SHA of a release that has been out
+# for at least two weeks (cooldown). The comment after each SHA is the tag.
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  # Cancel superseded runs of the same PR only.
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
+        with:
+          python-version: '3.12'
+      - name: Install tox
+        run: python -m pip install tox
+      - name: Ruff
+        run: tox -e ruff-check
+
+  test:
+    runs-on: ubuntu-latest
+    needs: lint
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - {python-version: '3.10', tox-env: 'py310-Plone60'}
+          - {python-version: '3.11', tox-env: 'py311-Plone60'}
+          - {python-version: '3.12', tox-env: 'py312-Plone60'}
+          - {python-version: '3.13', tox-env: 'py313-Plone60'}
+          - {python-version: '3.10', tox-env: 'py310-Plone61'}
+          - {python-version: '3.11', tox-env: 'py311-Plone61'}
+          - {python-version: '3.12', tox-env: 'py312-Plone61'}
+          - {python-version: '3.13', tox-env: 'py313-Plone61'}
+          - {python-version: '3.10', tox-env: 'py310-Plone62'}
+          - {python-version: '3.11', tox-env: 'py311-Plone62'}
+          - {python-version: '3.12', tox-env: 'py312-Plone62'}
+          - {python-version: '3.13', tox-env: 'py313-Plone62'}
+          - {python-version: '3.14', tox-env: 'py314-Plone62'}
+    env:
+      # Fail instead of skipping the tests that need java.
+      C2_TRANSFORM_MSOFFICE_REQUIRE_JAVA: '1'
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
+        with:
+          python-version: ${{ matrix.python-version }}
+      # The runner has several JDKs already; this pins the one on PATH.
+      - uses: actions/setup-java@de7274f081f381c8f8158605e0321c36c376e2e6 # v6.0.1
+        with:
+          distribution: temurin
+          java-version: '21'
+      - name: Install tox
+        run: python -m pip install tox
+      - name: Test with tox
+        run: |
+          set -o pipefail
+          tox -e ${{ matrix.tox-env }} | tee tox.log
+      - name: Check that no test was skipped
+        run: |
+          if grep -E '^SKIPPED|[0-9]+ skipped' tox.log; then
+            echo "::error::Some tests were skipped"
+            exit 1
+          fi

.gitignore

@@ -0,0 +1,51 @@
+# python related
+*.egg-info
+*.pyc
+*.pyo
+
+# tools related
+__pycache__/
+.coverage
+.coverage.*
+.mypy_cache
+.pytest_cache
+.ruff_cache
+/build/
+coverage.xml
+dist/
+docs/_build
+node_modules/
+
+# venv / buildout related
+.eggs/
+.installed.cfg
+.mr.developer.cfg
+.venv/
+bin/
+develop-eggs/
+eggs/
+etc/
+include/
+lib/
+lib64
+parts/
+pyvenv.cfg
+var/
+
+# mxdev
+.installed.txt
+.lock
+/.mxdev_cache/
+/.make-sentinels/
+/*-mxdev.txt
+/instance/
+/reports/
+/sources/
+/venv/
+# mxdev generated
+constraints.txt
+constraints-mxdev.txt
+requirements.txt
+requirements-mxdev.txt
+
+.tox/

AGENTS.md

@@ -0,0 +1,60 @@
+# Notes for contributors and coding agents
+
+## Rules
+
+- This is a public package. Write code, comments, documentation, commit
+  messages and pull requests in English.
+- Do not add design documents, specs or plans to the repository.
+- Record user-facing changes as towncrier fragments in `news/`
+  (`news/+<name>.<type>` or `news/<issue>.<type>`, types as in
+  `pyproject.toml`), not in `CHANGELOG.md`.
+
+## Layout
+
+- `src/c2/transform/msoffice/`: the package. `c2` and `c2.transform` are
+  PEP 420 namespace packages, so they have no `__init__.py`.
+  - `transform.py`: the `msoffice_to_text` transform that runs the jar.
+  - `config.py`: MIME types; importing it adds them to `mimetypes`.
+  - `setuphandlers.py`: install and uninstall (`post_handler`s).
+  - `msdoc2txt.jar`: the bundled Java program (Apache POI 3.17).
+- `tests/`: pytest tests (not shipped in the wheel).
+  - `test_transform.py`, `test_config.py`: unit tests; `java` is replaced.
+  - `test_setup.py`: install and uninstall in a Plone site.
+  - `test_java.py`: runs the real jar on the files in `tests/samples/`.
+
+## Development
+
+Run the tests and the linters with tox:
+
+```shell
+tox -e py314-Plone62      # one Python and Plone version
+tox -e ruff-check         # lint and format check
+tox -e ruff-fix           # fix and format
+tox                       # the whole matrix
+```
+
+Extra arguments go to pytest, for example
+`tox -e py314-Plone62 -- tests/test_transform.py`.
+
+`tests/test_java.py` needs `java` on `PATH`. Without it the tests are
+skipped; set `C2_TRANSFORM_MSOFFICE_REQUIRE_JAVA=1` to make them fail
+instead, as CI does. Write expected values in tests as literals.
+
+## Test samples
+
+All files in `tests/samples/` were made for this package; do not add
+documents of unknown origin. The `.docx`, `.doc`, `.xlsx`, `.xls` and `.pptx`
+files were converted with LibreOffice in headless mode from short text and
+CSV files (`soffice --headless --convert-to docx document.txt`, the CSV
+with `--infilter="CSV:44,34,76,1"`, and the presentation by converting a PDF
+of the text with `--infilter=impress_pdf_import`); `<cp:revision>` was then
+removed from `docProps/core.xml` of the OOXML files, because the jar prints
+it as text. `empty.docx` is a converted empty text file.
+
+The `.ppt` file was written with the Apache POI classes in the bundled jar
+(`HSLFSlideShow` with one text box), because it is much smaller than the one
+LibreOffice writes; the jar cannot read either of them (see the known issues
+in `README.md`). POI's empty template names a person as the last editor in
+the Current User stream, so the name was cleared with
+`getSlideShowImpl().getCurrentUserAtom().setLastEditUsername("")`. Check new
+samples for names in their metadata before adding them.

CHANGELOG.md

@@ -0,0 +1,65 @@
+# Changelog
+
+<!--
+   You should *NOT* be adding new change log entries to this file.
+   You should create a file in the news directory instead.
+   For helpful instructions, please see:
+   https://github.com/plone/plone.releaser/blob/master/ADD-A-NEWS-ITEM.rst
+-->
+
+<!-- towncrier release notes start -->
+
+## 1.0b6 (2018-04-02)
+
+- change from POI 3.6 to POI 3.17 with Java 8 [Tetsuya Morimoto]
+
+## 1.0b5 (2018-02-28)
+
+- modify setup.py for target Plone [terapyon]
+- tested Plone 5.1
+
+## 1.0b4 (2013-03-16)
+
+- modify kill process for Popen [Takayuki Nagai]
+
+## 1.0b3 (2010-10-06)
+
+- adding terminated suspicious zombie process [terapyon]
+
+## 1.0b2 (2010-02-19)
+
+- remove the copyright in the files [terapyon]
+
+## 1.0b1 (2010-02-01)
+
+- modify getting from metadata and note in the msoffice file [terapyon]
+- no support for Windows [terapyon]
+
+## 0.3.2 (2010-01-19)
+
+- setting some mimetypes [terapyon]
+
+## 0.3.1 (2009-12-22)
+
+- bug fix for Windows [terapyon]
+
+## 0.3 (2009-12-22)
+
+- support Windows OS
+
+## 0.2 (2009-12-21)
+
+- support Plone 4.x [terapyon]
+
+## 0.1.2 (2009-12-17)
+
+- modify typo
+
+## 0.1.1 (2009-12-16)
+
+- modify exception code
+- adding java args for big size file
+
+## 0.1 (2009-12-16)
+
+- Initial release

MANIFEST.in

@@ -1,3 +1,8 @@
-recursive-include c2 *
-recursive-include docs *
-global-exclude *pyc *pyo
+graft src/c2
+include *.md
+include pyproject.toml
+exclude tox.ini
+exclude *.txt
+global-exclude *.pyc
+include LICENSE.GPL
+include LICENSE.txt