Merge branch 'master' of github.com:udapi/udapi-python

Author: michnov

.circleci/config.yml

@@ -15,13 +15,16 @@ orbs:
 # See: https://circleci.com/docs/2.0/configuration-reference/#jobs
 jobs:
   build-and-test: # This is the name of the job, feel free to change it to better match what you're trying to do!
+    parameters:
+      python-version:
+        type: string
     # These next lines defines a Docker executors: https://circleci.com/docs/2.0/executor-types/
     # You can specify an image from Dockerhub or use one of the convenience images from CircleCI's Developer Hub
     # A list of available CircleCI Docker convenience images are available here: https://circleci.com/developer/images/image/cimg/python
     # The executor is the environment in which the steps below will be executed - below will use a python 3.10.2 container
     # Change the version below to your required version of python
     docker:
-      - image: cimg/python:3.9
+      - image: cimg/python:<< parameters.python-version >>
     # Checkout the code as the first step. This is a dedicated CircleCI step.
     # The python orb's install-packages step will install the dependencies from a Pipfile via Pipenv by default.
     # Here we're making sure we use just use the system-wide pip. By default it uses the project root's requirements.txt.
@@ -31,15 +34,12 @@ jobs:
       - checkout
       - python/install-packages:
           pkg-manager: pip
-          # app-dir: ~/project/package-directory/  # If you're requirements.txt isn't in the root directory.
-          # pip-dependency-file: test-requirements.txt  # if you have a different name for your requirements file, maybe one that combines your runtime and test requirements.
       - run:
           name: Install Udapi
           command: pip install ".[test]"
       - run: mkdir -p test-results
       - run:
           name: Run pytest tests
-          # This assumes pytest is installed via the install-package step above
           command: pytest --junitxml=test-results/junit.xml -o junit_family=legacy
       - store_test_results:
           path: test-results
@@ -54,7 +54,9 @@ jobs:
 # Invoke jobs via workflows
 # See: https://circleci.com/docs/2.0/configuration-reference/#workflows
 workflows:
-  sample: # This is the name of the workflow, feel free to change it to better match your workflow.
-    # Inside the workflow, you define the jobs you want to run.
+  test-matrix:
     jobs:
-      - build-and-test
+      - build-and-test:
+          matrix:
+            parameters:
+              python-version: ["3.9", "3.11", "3.13"]

.github/workflows/python-publish.yml

@@ -0,0 +1,70 @@
+# This workflow will upload a Python Package to PyPI when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  release-build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+
+      - name: Build release distributions
+        run: |
+          # NOTE: put your own distribution build steps here.
+          python -m pip install build
+          python -m build
+
+      - name: Upload distributions
+        uses: actions/upload-artifact@v4
+        with:
+          name: release-dists
+          path: dist/
+
+  pypi-publish:
+    runs-on: ubuntu-latest
+    needs:
+      - release-build
+    permissions:
+      # IMPORTANT: this permission is mandatory for trusted publishing
+      id-token: write
+
+    # Dedicated environments with protections for publishing are strongly recommended.
+    # For more information, see: https://docs.github.com/en/actions/deployment/targeting-different-environments/using-environments-for-deployment#deployment-protection-rules
+    environment:
+      name: pypi
+      # OPTIONAL: uncomment and update to include your PyPI project URL in the deployment status:
+      url: https://pypi.org/p/udapi
+      #
+      # ALTERNATIVE: if your GitHub Release name is the PyPI project version string
+      # ALTERNATIVE: exactly, uncomment the following line instead:
+      # url: https://pypi.org/project/YOURPROJECT/${{ github.event.release.name }}
+
+    steps:
+      - name: Retrieve release distributions
+        uses: actions/download-artifact@v4
+        with:
+          name: release-dists
+          path: dist/
+
+      - name: Publish release distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: dist/

.gitignore

@@ -1,3 +1,5 @@
+.cache
 .idea
+*.egg-info/
 *.pyc
-.cache
+dist/

CHANGES.txt

@@ -2,7 +2,16 @@ Udapi Change Log
 ----------------
 See https://github.com/udapi/udapi-python/commits/master for details.
 
-0.4.0 2024-03-28
+0.5.1 2025-11-05
+ - make udapy compatible with Python 3.13
+
+0.5.0 2025-10-18
+ - added mwt.feats
+ - added root.prev_tree and root.next_tree
+ - .github/workflows/python-publish.yml
+ - edits by Dan Zeman in block.ud.*
+
+0.4.0 2025-03-28
  - support for CorefUD 1.3
  - edits by Dan Zeman in block.ud.*
  - requires Python 3.9+ (difficult to test older versions in Circle-CI)

README.md

@@ -6,28 +6,24 @@ Python framework for processing Universal Dependencies data
 [![Documentation Status](https://readthedocs.org/projects/udapi/badge/)](http://udapi.readthedocs.io)
 
 ## Requirements
-- You need Python 3.6 or higher.
-- If the [ufal.udpipe](https://pypi.python.org/pypi/ufal.udpipe/) parser is needed,
-  make sure you have a C++11 compiler (e.g. [g++ 4.7 or newer](.travis.yml#L9))
-  and install UDPipe with `pip3 install --user --upgrade ufal.udpipe`.
+- You need Python 3.9 or higher.
+- It is recommended to install Udapi in a Python virtual environment.
+- If you need the [ufal.udpipe](https://pypi.python.org/pypi/ufal.udpipe/) parser (to be used from Udapi)
+  install it (with `pip install --upgrade ufal.udpipe`).
 
 ## Install Udapi for developers
-Let's clone the git repo to `~/udapi-python/`, install dependencies
-and setup `$PATH` and `$PYTHONPATH` accordingly.
+Let's clone the git repo e.g. to `~/udapi-python/` and make an [editable installation](https://setuptools.pypa.io/en/latest/userguide/development_mode.html)
 ```bash
 cd
 git clone https://github.com/udapi/udapi-python.git
-pip3 install --user -r udapi-python/requirements.txt
-echo '## Use Udapi from ~/udapi-python/ ##'                >> ~/.bashrc
-echo 'export PATH="$HOME/udapi-python/bin:$PATH"'          >> ~/.bashrc
-echo 'export PYTHONPATH="$HOME/udapi-python/:$PYTHONPATH"' >> ~/.bashrc
-source ~/.bashrc # or open new bash
+cd udapi-python
+pip install -e .
 ```
 
 ## Install Udapi for users
 This is similar to the above, but installs Udapi from PyPI to the standard (user) Python paths.
 ```
-pip3 install --user --upgrade udapi
+pip install --upgrade udapi
 ```
 Try `udapy -h` to check it is installed correctly.
 If it fails, make sure your `PATH` includes the directory where `pip3` installed the `udapy` script.

bin/udapy

@@ -1,136 +1,7 @@
 #!/usr/bin/env python3
-import os
-import gc
+"""Thin wrapper for backward compatibility.  Calls udapi.cli.main()."""
 import sys
-import atexit
-import logging
-import argparse
+from udapi.cli import main
 
-from udapi.core.run import Run
-
-# Parse command line arguments.
-argparser = argparse.ArgumentParser(
-    formatter_class=argparse.RawTextHelpFormatter,
-    usage="udapy [optional_arguments] scenario",
-    epilog="See http://udapi.github.io",
-    description="udapy - Python interface to Udapi - API for Universal Dependencies\n\n"
-                "Examples of usage:\n"
-                "  udapy -s read.Sentences udpipe.En < in.txt > out.conllu\n"
-                "  udapy -T < sample.conllu | less -R\n"
-                "  udapy -HAM ud.MarkBugs < sample.conllu > bugs.html\n")
-argparser.add_argument(
-    "-q", "--quiet", action="store_true",
-    help="Warning, info and debug messages are suppressed. Only fatal errors are reported.")
-argparser.add_argument(
-    "-v", "--verbose", action="store_true",
-    help="Warning, info and debug messages are printed to the STDERR.")
-argparser.add_argument(
-    "-s", "--save", action="store_true",
-    help="Add write.Conllu to the end of the scenario")
-argparser.add_argument(
-    "-T", "--save_text_mode_trees", action="store_true",
-    help="Add write.TextModeTrees color=1 to the end of the scenario")
-argparser.add_argument(
-    "-H", "--save_html", action="store_true",
-    help="Add write.TextModeTreesHtml color=1 to the end of the scenario")
-argparser.add_argument(
-    "-A", "--save_all_attributes", action="store_true",
-    help="Add attributes=form,lemma,upos,xpos,feats,deprel,misc (to be used after -T and -H)")
-argparser.add_argument(
-    "-C", "--save_comments", action="store_true",
-    help="Add print_comments=1 (to be used after -T and -H)")
-argparser.add_argument(
-    "-M", "--marked_only", action="store_true",
-    help="Add marked_only=1 to the end of the scenario (to be used after -T and -H)")
-argparser.add_argument(
-    "-N", "--no_color", action="store_true",
-    help="Add color=0 to the end of the scenario, this overrides color=1 of -T and -H")
-argparser.add_argument(
-    "-X", "--extra", action="append",
-    help="Add a specified parameter (or a block name) to the end of the scenario\n"
-         "For example 'udapy -TNX attributes=form,misc -X layout=align < my.conllu'")
-argparser.add_argument(
-    "--gc", action="store_true",
-    help="By default, udapy disables Python garbage collection and at-exit cleanup\n"
-         "to speed up everything (especially reading CoNLL-U files). In edge cases,\n"
-         "when processing many files and running out of memory, you can disable this\n"
-         "optimization (i.e. enable garbage collection) with 'udapy --gc'.")
-argparser.add_argument(
-    'scenario', nargs=argparse.REMAINDER, help="A sequence of blocks and their parameters.")
-
-args = argparser.parse_args()
-
-# Set the level of logs according to parameters.
-if args.verbose:
-    level = logging.DEBUG
-elif args.quiet:
-    level = logging.CRITICAL
-else:
-    level = logging.INFO
-
-logging.basicConfig(format='%(asctime)-15s [%(levelname)7s] %(funcName)s - %(message)s',
-                    level=level)
-
-# Global flag to track if an unhandled exception occurred
-_unhandled_exception_occurred = False
-
-def _custom_excepthook(exc_type, exc_value, traceback):
-    global _unhandled_exception_occurred
-    _unhandled_exception_occurred = True
-
-    # Call the default excepthook to allow normal error reporting
-    sys.__excepthook__(exc_type, exc_value, traceback)
-
-# Override the default excepthook
-sys.excepthook = _custom_excepthook
-
-
-# Process and provide the scenario.
 if __name__ == "__main__":
-
-    # Disabling garbage collections makes the whole processing much faster.
-    # Similarly, we can save several seconds by partially disabling the at-exit Python cleanup
-    # (atexit hooks are called in reversed order of their registration,
-    # so flushing stdio buffers etc. will be still done before the os._exit(0) call).
-    # See https://instagram-engineering.com/dismissing-python-garbage-collection-at-instagram-4dca40b29172
-    # Is it safe to disable GC?
-    # OS will free the memory allocated by this process after it ends anyway.
-    # The udapy wrapper is aimed for one-time tasks, not a long-running server,
-    # so in a typical case a document is loaded and almost no memory is freed before the end.
-    # Udapi documents have a many cyclic references, so running GC is quite slow.
-    if not args.gc:
-        gc.disable()
-        # When an exception/error has happened, udapy should exit with a non-zero exit code,
-        # so that users can use `udapy ... || echo "Error detected"` (or Makefile reports errors).
-        # However, we cannot use `atexit.register(lambda: os._exit(1 if sys.exc_info()[0] else 0))`
-        # because the Python has already exited the exception-handling block
-        # (the exception/error has been already reported and sys.exc_info()[0] is None).
-        # We thus keep record whether _unhandled_exception_occurred.
-        atexit.register(lambda: os._exit(1 if _unhandled_exception_occurred else 0))
-        atexit.register(sys.stderr.flush)
-    if args.save:
-        args.scenario = args.scenario + ['write.Conllu']
-    if args.save_text_mode_trees:
-        args.scenario = args.scenario + ['write.TextModeTrees', 'color=1']
-    if args.save_html:
-        args.scenario = args.scenario + ['write.TextModeTreesHtml', 'color=1']
-    if args.save_all_attributes:
-        args.scenario = args.scenario + ['attributes=form,lemma,upos,xpos,feats,deprel,misc']
-    if args.save_comments:
-        args.scenario = args.scenario + ['print_comments=1']
-    if args.marked_only:
-        args.scenario = args.scenario + ['marked_only=1']
-    if args.no_color:
-        args.scenario = args.scenario + ['color=0']
-    if args.extra:
-        args.scenario += args.extra
-
-    runner = Run(args)
-    # udapy is often piped to head etc., e.g.
-    # `seq 1000 | udapy -s read.Sentences | head`
-    # Let's prevent Python from reporting (with distracting stacktrace)
-    # "BrokenPipeError: [Errno 32] Broken pipe"
-    try:
-        runner.execute()
-    except BrokenPipeError:
-        pass
+    sys.exit(main())

pyproject.toml

@@ -1,6 +1,36 @@
 [build-system]
-requires = [
-    "setuptools>=42",
-    "wheel"
-]
+requires = ["setuptools>=42", "wheel"]
 build-backend = "setuptools.build_meta"
+
+[project]
+name = "udapi"
+version = "0.5.2"
+description = "Python framework for processing Universal Dependencies data"
+readme = "README.md"
+requires-python = ">=3.9"
+license = "GPL-3.0-or-later"
+authors = [
+    {name = "Martin Popel", email = "popel@ufal.mff.cuni.cz"}
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "colorama",
+    "termcolor",
+]
+
+[project.urls]
+Homepage = "https://github.com/udapi/udapi-python"
+
+[project.optional-dependencies]
+test = ["pytest"]
+udpipe = ["ufal.udpipe"]
+
+[project.scripts]
+udapy = "udapi.cli:main"
+
+[tool.setuptools]
+packages = {find = {}}
+include-package-data = true