diff --git a/.ci/release b/.ci/release
new file mode 100755
index 0000000..6cff663
--- /dev/null
+++ b/.ci/release
@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+'''
+Run [[file:scripts/release][scripts/release]] to deploy Python package onto [[https://pypi.org][PyPi]] and [[https://test.pypi.org][test PyPi]].
+
+The script expects =TWINE_PASSWORD= environment variable to contain the [[https://pypi.org/help/#apitoken][PyPi token]] (not the password!).
+
+The script can be run manually.
+It's also running as =pypi= job in [[file:.github/workflows/main.yml][Github Actions config]]. Packages are deployed on:
+- every master commit, onto test pypi
+- every new tag, onto production pypi
+
+You'll need to set =TWINE_PASSWORD= and =TWINE_PASSWORD_TEST= in [[https://help.github.com/en/actions/configuring-and-managing-workflows/creating-and-storing-encrypted-secrets#creating-encrypted-secrets][secrets]]
+for Github Actions deployment to work.
+'''
+
+import os
+import sys
+from pathlib import Path
+from subprocess import check_call
+import shutil
+
+is_ci = os.environ.get('CI') is not None
+
+def main() -> None:
+ import argparse
+ p = argparse.ArgumentParser()
+ p.add_argument('--test', action='store_true', help='use test pypi')
+ args = p.parse_args()
+
+ extra = []
+ if args.test:
+ extra.extend(['--repository', 'testpypi'])
+
+ root = Path(__file__).absolute().parent.parent
+ os.chdir(root) # just in case
+
+ if is_ci:
+ # see https://github.com/actions/checkout/issues/217
+ check_call('git fetch --prune --unshallow'.split())
+
+ dist = root / 'dist'
+ if dist.exists():
+ shutil.rmtree(dist)
+
+ check_call(['python3', '-m', 'build'])
+
+ TP = 'TWINE_PASSWORD'
+ password = os.environ.get(TP)
+ if password is None:
+ print(f"WARNING: no {TP} passed", file=sys.stderr)
+ import pip_secrets
+ password = pip_secrets.token_test if args.test else pip_secrets.token # meh
+
+ check_call([
+ 'python3', '-m', 'twine',
+ 'upload', *dist.iterdir(),
+ *extra,
+ ], env={
+ 'TWINE_USERNAME': '__token__',
+ TP: password,
+ **os.environ,
+ })
+
+
+if __name__ == '__main__':
+ main()
diff --git a/.ci/release-uv b/.ci/release-uv
new file mode 100755
index 0000000..4da39b7
--- /dev/null
+++ b/.ci/release-uv
@@ -0,0 +1,56 @@
+#!/usr/bin/env python3
+'''
+Deploys Python package onto [[https://pypi.org][PyPi]] or [[https://test.pypi.org][test PyPi]].
+
+- running manually
+
+ You'll need =UV_PUBLISH_TOKEN= env variable
+
+- running on Github Actions
+
+ Instead of env variable, relies on configuring github as Trusted publisher (https://docs.pypi.org/trusted-publishers/) -- both for test and regular pypi
+
+ It's running as =pypi= job in [[file:.github/workflows/main.yml][Github Actions config]].
+ Packages are deployed on:
+ - every master commit, onto test pypi
+ - every new tag, onto production pypi
+'''
+
+UV_PUBLISH_TOKEN = 'UV_PUBLISH_TOKEN'
+
+import argparse
+import os
+import shutil
+from pathlib import Path
+from subprocess import check_call
+
+is_ci = os.environ.get('CI') is not None
+
+
+def main() -> None:
+ p = argparse.ArgumentParser()
+ p.add_argument('--use-test-pypi', action='store_true')
+ args = p.parse_args()
+
+ publish_url = ['--publish-url', 'https://test.pypi.org/legacy/'] if args.use_test_pypi else []
+
+ root = Path(__file__).absolute().parent.parent
+ os.chdir(root) # just in case
+
+ # TODO ok, for now uv won't remove dist dir if it already exists
+ # https://github.com/astral-sh/uv/issues/10293
+ dist = root / 'dist'
+ if dist.exists():
+ shutil.rmtree(dist)
+
+ check_call(['uv', 'build'])
+
+ if not is_ci:
+ # CI relies on trusted publishers so doesn't need env variable
+ assert UV_PUBLISH_TOKEN in os.environ, f'no {UV_PUBLISH_TOKEN} passed'
+
+ check_call(['uv', 'publish', *publish_url])
+
+
+if __name__ == '__main__':
+ main()
diff --git a/.ci/run b/.ci/run
new file mode 100755
index 0000000..c881818
--- /dev/null
+++ b/.ci/run
@@ -0,0 +1,36 @@
+#!/bin/bash
+set -eu
+
+cd "$(dirname "$0")"
+cd .. # git root
+
+if ! command -v sudo; then
+ # CI or Docker sometimes doesn't have it, so useful to have a dummy
+ function sudo {
+ "$@"
+ }
+fi
+
+# --parallel-live to show outputs while it's running
+tox_cmd='run-parallel --parallel-live'
+if [ -n "${CI-}" ]; then
+ # install OS specific stuff here
+ case "$OSTYPE" in
+ darwin*)
+ # macos
+ :
+ ;;
+ cygwin* | msys* | win*)
+ # windows
+ # ugh. parallel stuff seems super flaky under windows, some random failures, "file used by other process" and crap like that
+ tox_cmd='run'
+ ;;
+ *)
+ # must be linux?
+ :
+ ;;
+ esac
+fi
+
+# NOTE: expects uv installed
+uv tool run --with tox-uv tox $tox_cmd "$@"
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
new file mode 100644
index 0000000..e51bcf6
--- /dev/null
+++ b/.github/workflows/main.yml
@@ -0,0 +1,114 @@
+# see https://github.com/karlicoss/pymplate for up-to-date reference
+
+name: CI
+on:
+ push:
+ branches: '*'
+ tags: 'v[0-9]+.*' # only trigger on 'release' tags for PyPi
+ # Ideally I would put this in the pypi job... but github syntax doesn't allow for regexes there :shrug:
+
+ # Needed to trigger on others' PRs.
+ # Note that people who fork it need to go to "Actions" tab on their fork and click "I understand my workflows, go ahead and enable them".
+ pull_request:
+
+ # Needed to trigger workflows manually.
+ workflow_dispatch:
+ inputs:
+ debug_enabled:
+ type: boolean
+ description: 'Run the build with tmate debugging enabled (https://github.com/marketplace/actions/debugging-with-tmate)'
+ required: false
+ default: false
+
+
+jobs:
+ build:
+ strategy:
+ fail-fast: false
+ matrix:
+ platform: [ubuntu-latest, macos-latest, windows-latest]
+ python-version: ['3.9', '3.10', '3.11', '3.12', '3.13', '3.14']
+ # vvv just an example of excluding stuff from matrix
+ # exclude: [{platform: macos-latest, python-version: '3.6'}]
+
+ runs-on: ${{ matrix.platform }}
+
+ # useful for 'optional' pipelines
+ # continue-on-error: ${{ matrix.platform == 'windows-latest' }}
+
+ steps:
+ # ugh https://github.com/actions/toolkit/blob/main/docs/commands.md#path-manipulation
+ - run: echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+ - uses: actions/checkout@v5
+ with:
+ submodules: recursive
+ fetch-depth: 0 # nicer to have all git history when debugging/for tests
+
+ - uses: actions/setup-python@v6
+ with:
+ python-version: ${{ matrix.python-version }}
+
+ - uses: astral-sh/setup-uv@v7
+ with:
+ enable-cache: false # we don't have lock files, so can't use them as cache key
+
+ - uses: mxschmitt/action-tmate@v3
+ if: ${{ github.event_name == 'workflow_dispatch' && inputs.debug_enabled }}
+
+ # explicit bash command is necessary for Windows CI runner, otherwise it thinks it's cmd...
+ - run: bash .ci/run
+ env:
+ # only compute lxml coverage on ubuntu; it crashes on windows
+ CI_MYPY_COVERAGE: ${{ matrix.platform == 'ubuntu-latest' && '--cobertura-xml-report .coverage.mypy' || '' }}
+
+ - if: matrix.platform == 'ubuntu-latest' # no need to compute coverage for other platforms
+ uses: codecov/codecov-action@v5
+ with:
+ fail_ci_if_error: true # default false
+ token: ${{ secrets.CODECOV_TOKEN }}
+ flags: mypy-${{ matrix.python-version }}
+ files: .coverage.mypy/cobertura.xml
+
+
+ pypi:
+ # Do not run it for PRs/cron schedule etc.
+ # NOTE: release tags are guarded by on: push: tags on the top.
+ if: github.event_name == 'push' && (startsWith(github.event.ref, 'refs/tags/') || (github.event.ref == format('refs/heads/{0}', github.event.repository.master_branch)))
+ # Ugh, I tried using matrix or something to explicitly generate only test pypi or prod pypi pipelines.
+ # But github actions is so shit, it's impossible to do any logic at all, e.g. doesn't support conditional matrix, if/else statements for variables etc.
+
+ needs: [build] # add all other jobs here
+
+ runs-on: ubuntu-latest
+
+ permissions:
+ # necessary for Trusted Publishing
+ id-token: write
+
+ steps:
+ # ugh https://github.com/actions/toolkit/blob/main/docs/commands.md#path-manipulation
+ - run: echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+ - uses: actions/checkout@v5
+ with:
+ submodules: recursive
+ fetch-depth: 0 # pull all commits to correctly infer vcs version
+
+ - uses: actions/setup-python@v6
+ with:
+ python-version: '3.10'
+
+ - uses: astral-sh/setup-uv@v7
+ with:
+ enable-cache: false # we don't have lock files, so can't use them as cache key
+
+ - name: 'release to test pypi'
+ # always deploy merged master to test pypi
+ if: github.event.ref == format('refs/heads/{0}', github.event.repository.master_branch)
+ run: .ci/release-uv --use-test-pypi
+
+ - name: 'release to prod pypi'
+ # always deploy tags to release pypi
+ if: startsWith(github.event.ref, 'refs/tags/')
+ run: .ci/release-uv
diff --git a/.gitignore b/.gitignore
index 0fb9476..a06322a 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,195 @@
-.tox
+
+# Created by https://www.toptal.com/developers/gitignore/api/python,emacs
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,emacs
+
+### Emacs ###
+# -*- mode: gitignore; -*-
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+auto-save-list
+tramp
+.\#*
+
+# Org-mode
+.org-id-locations
+*_archive
+
+# flymake-mode
+*_flymake.*
+
+# eshell files
+/eshell/history
+/eshell/lastdir
+
+# elpa packages
+/elpa/
+
+# reftex files
+*.rel
+
+# AUCTeX auto folder
+/auto/
+
+# cask packages
+.cask/
+dist/
+
+# Flycheck
+flycheck_*.el
+
+# server auth directory
+/server/
+
+# projectiles files
+.projectile
+
+# directory configuration
+.dir-locals.el
+
+# network security
+/network-security.data
+
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
MANIFEST
-doc/build
+
+# PyInstaller
+# Usually these files are written by a python script from a template
+# before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+pytestdebug.log
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+doc/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+# However, in case of collaboration, if having platform-specific dependencies or dependencies
+# having no cross-platform support, pipenv may install dependencies that don't work, or not
+# install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+pythonenv*
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# profiling data
+.prof
+
+# End of https://www.toptal.com/developers/gitignore/api/python,emacs
diff --git a/.travis.yml b/.travis.yml
deleted file mode 100644
index 4854e53..0000000
--- a/.travis.yml
+++ /dev/null
@@ -1,5 +0,0 @@
-language: python
-before_install:
- pip install tox
-script:
- tox
diff --git a/LICENSE b/LICENSE
new file mode 100644
index 0000000..fcdf7ba
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,25 @@
+BSD 2-Clause License
+
+Copyright (c) 2012, Takafumi Arakaki
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+ list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+ this list of conditions and the following disclaimer in the documentation
+ and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
diff --git a/Makefile b/Makefile
index b9ee208..d31c4ea 100644
--- a/Makefile
+++ b/Makefile
@@ -11,9 +11,4 @@ doc: cog
## Update files using cog.py
cog: orgparse/__init__.py
orgparse/__init__.py: README.rst
- cd orgparse && cog.py -r __init__.py
-
-
-## Upload to PyPI
-upload: cog
- python setup.py register sdist upload
+ cd src/orgparse && cog.py -r __init__.py
diff --git a/README.rst b/README.rst
index be978e2..e26fae6 100644
--- a/README.rst
+++ b/README.rst
@@ -1,35 +1,37 @@
===========================================================
- orgparse - Pyton module for reading Emacs org-mode file
+ orgparse - Python module for reading Emacs org-mode files
===========================================================
-Links:
-
-* `Documentation (at Read the Docs) `_
-* `Repository (at GitHub) `_
-* `Issue tracker (at GitHub) `_
-* `PyPI `_
-* `Travis CI `_ |build-status|
-
-.. |build-status|
- image:: https://secure.travis-ci.org/tkf/orgparse.png?branch=master
- :target: http://travis-ci.org/tkf/orgparse
- :alt: Build Status
-
+* `Documentation (Read the Docs) `_
+* `Repository (at GitHub) `_
+* `PyPI `_
+* `conda-forge `_
Install
-------
-You can install `orgparse` from PyPI_::
+You can install ``orgpase`` via PyPI
+
+.. code-block:: console
pip install orgparse
+or via conda-forge
+
+.. code-block:: console
+
+ conda install orgparse -c conda-forge
+
Usage
-----
-Loading org object
-^^^^^^^^^^^^^^^^^^
+There are pretty extensive doctests if you're interested in some specific method. Otherwise here are some example snippets:
+
+
+Load org node
+^^^^^^^^^^^^^
::
from orgparse import load, loads
@@ -72,8 +74,8 @@ Traverse org tree
* Heading 1
-Accessing to node attributes
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Accessing node attributes
+^^^^^^^^^^^^^^^^^^^^^^^^^
>>> root = loads('''
... * DONE Heading :TAG:
@@ -105,3 +107,13 @@ True
'some text'
>>> node.body
' Body texts...'
+
+
+Project status
+--------------
+
+Project is maintained by @karlicoss (myself).
+
+For my personal use, orgparse mostly has all features I need, so there hasn't been much active development lately.
+
+However, contributions are always welcome! Please provide tests along with your contribution if you're fixing bugs or adding new functionality.
diff --git a/conftest.py b/conftest.py
new file mode 100644
index 0000000..627def8
--- /dev/null
+++ b/conftest.py
@@ -0,0 +1,58 @@
+# this is a hack to monkey patch pytest so it handles tests inside namespace packages without __init__.py properly
+# without it, pytest can't discover the package root for some reason
+# also see https://github.com/karlicoss/pytest_namespace_pkgs for more
+
+import os
+import pathlib
+from typing import Optional
+
+import _pytest.main
+import _pytest.pathlib
+
+# we consider all dirs in repo/ to be namespace packages
+root_dir = pathlib.Path(__file__).absolute().parent.resolve() / 'src'
+assert root_dir.exists(), root_dir
+
+# TODO assert it contains package name?? maybe get it via setuptools..
+
+namespace_pkg_dirs = [str(d) for d in root_dir.iterdir() if d.is_dir()]
+
+# resolve_package_path is called from _pytest.pathlib.import_path
+# takes a full abs path to the test file and needs to return the path to the 'root' package on the filesystem
+resolve_pkg_path_orig = _pytest.pathlib.resolve_package_path
+
+
+def resolve_package_path(path: pathlib.Path) -> Optional[pathlib.Path]:
+ result = path # search from the test file upwards
+ for parent in result.parents:
+ if str(parent) in namespace_pkg_dirs:
+ return parent
+ if os.name == 'nt':
+ # ??? for some reason on windows it is trying to call this against conftest? but not on linux/osx
+ if path.name == 'conftest.py':
+ return resolve_pkg_path_orig(path)
+ raise RuntimeError("Couldn't determine path for ", path)
+
+
+# NOTE: seems like it's not necessary anymore?
+# keeping it for now just in case
+# after https://github.com/pytest-dev/pytest/pull/13426 we should be able to remove the whole conftest
+# _pytest.pathlib.resolve_package_path = resolve_package_path
+
+
+# without patching, the orig function returns just a package name for some reason
+# (I think it's used as a sort of fallback)
+# so we need to point it at the absolute path properly
+# not sure what are the consequences.. maybe it wouldn't be able to run against installed packages? not sure..
+search_pypath_orig = _pytest.main.search_pypath
+
+
+def search_pypath(module_name: str) -> str:
+ mpath = root_dir / module_name.replace('.', os.sep)
+ if not mpath.is_dir():
+ mpath = mpath.with_suffix('.py')
+ assert mpath.exists(), mpath # just in case
+ return str(mpath)
+
+
+_pytest.main.search_pypath = search_pypath # ty: ignore[invalid-assignment]
diff --git a/doc/source/conf.py b/doc/source/conf.py
index ed2440c..1e451e7 100644
--- a/doc/source/conf.py
+++ b/doc/source/conf.py
@@ -1,8 +1,7 @@
-# -*- coding: utf-8 -*-
-
-from os.path import dirname
import sys
-sys.path.insert(0, dirname(dirname(dirname(__file__))))
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent.parent.parent))
# -- General configuration ------------------------------------------------
extensions = [
@@ -15,14 +14,18 @@
source_suffix = '.rst'
master_doc = 'index'
+# TODO not sure I'm doing that right..
+import orgparse
+
# General information about the project.
-project = u'orgparse'
-copyright = u'2012, Takafumi Arakaki'
+project = 'orgparse'
+copyright = '2012, Takafumi Arakaki' # noqa: A001
# The short X.Y version.
-version = '0.0.1'
+# TODO use setup.py for version
+version = orgparse.__version__ # ty: ignore[unresolved-attribute]
# The full version, including alpha/beta/rc tags.
-release = '0.0.1.dev3'
+release = orgparse.__version__ # ty: ignore[unresolved-attribute]
exclude_patterns = []
@@ -39,22 +42,19 @@
# -- Options for LaTeX output ---------------------------------------------
latex_elements = {
-# The paper size ('letterpaper' or 'a4paper').
-#'papersize': 'letterpaper',
-
-# The font size ('10pt', '11pt' or '12pt').
-#'pointsize': '10pt',
-
-# Additional stuff for the LaTeX preamble.
-#'preamble': '',
+ # The paper size ('letterpaper' or 'a4paper').
+ #'papersize': 'letterpaper',
+ # The font size ('10pt', '11pt' or '12pt').
+ #'pointsize': '10pt',
+ # Additional stuff for the LaTeX preamble.
+ #'preamble': '',
}
# Grouping the document tree into LaTeX files. List of tuples
# (source start file, target name, title,
# author, documentclass [howto/manual]).
latex_documents = [
- ('index', 'orgparse.tex', u'orgparse Documentation',
- u'Takafumi Arakaki', 'manual'),
+ ('index', 'orgparse.tex', 'orgparse Documentation', 'Takafumi Arakaki', 'manual'),
]
@@ -62,12 +62,11 @@
# One entry per manual page. List of tuples
# (source start file, name, description, authors, manual section).
man_pages = [
- ('index', 'orgparse', u'orgparse Documentation',
- [u'Takafumi Arakaki'], 1)
+ ('index', 'orgparse', 'orgparse Documentation', ['Takafumi Arakaki'], 1),
]
# If true, show URL addresses after external links.
-#man_show_urls = False
+# man_show_urls = False
# -- Options for Texinfo output -------------------------------------------
@@ -75,9 +74,15 @@
# (source start file, target name, title, author,
# dir menu entry, description, category)
texinfo_documents = [
- ('index', 'orgparse', u'orgparse Documentation',
- u'Takafumi Arakaki', 'orgparse', 'One line description of project.',
- 'Miscellaneous'),
+ (
+ 'index',
+ 'orgparse',
+ 'orgparse Documentation',
+ 'Takafumi Arakaki',
+ 'orgparse',
+ 'One line description of project.',
+ 'Miscellaneous',
+ ),
]
@@ -89,4 +94,4 @@
autodoc_member_order = 'bysource'
autodoc_default_flags = ['members']
-inheritance_graph_attrs = dict(rankdir="TB")
+inheritance_graph_attrs = {'rankdir': "TB"}
diff --git a/mypy.ini b/mypy.ini
new file mode 100644
index 0000000..7b1e535
--- /dev/null
+++ b/mypy.ini
@@ -0,0 +1,18 @@
+[mypy]
+pretty = True
+show_error_context = True
+show_column_numbers = True
+show_error_end = True
+
+check_untyped_defs = True
+
+# see https://mypy.readthedocs.io/en/stable/error_code_list2.html
+warn_redundant_casts = True
+strict_equality = True
+warn_unused_ignores = True
+enable_error_code = deprecated,redundant-expr,possibly-undefined,truthy-bool,truthy-iterable,ignore-without-code,unused-awaitable
+
+
+# an example of suppressing
+# [mypy-my.config.repos.pdfannots.pdfannots]
+# ignore_errors = True
diff --git a/orgparse/tests/data/00_simple.py b/orgparse/tests/data/00_simple.py
deleted file mode 100644
index 8f7da41..0000000
--- a/orgparse/tests/data/00_simple.py
+++ /dev/null
@@ -1,30 +0,0 @@
-def nodedict(i, level, todo=None, shallow_tags=set([]), tags=set([])):
- return dict(
- heading="Heading {0}".format(i),
- level=level,
- todo=todo,
- shallow_tags=shallow_tags,
- tags=tags,
- )
-
-
-def tags(nums):
- return set(map('TAG{0}'.format, nums))
-
-
-data = [
- nodedict(i, *vals) for (i, vals) in enumerate([
- [1, 'TODO1', tags([1]), tags(range(1, 2))],
- [2, 'TODO2', tags([2]), tags(range(1, 3))],
- [3, 'TODO3', tags([3]), tags(range(1, 4))],
- [4, 'TODO4', tags([4]), tags(range(1, 5))],
- [2, None, tags([]), tags([1])],
- [2, None, tags([]), tags([1])],
- [1, None, tags([2]), tags([2])],
- [2, None, tags([2]), tags([2])],
- [3, None, tags([]), tags([2])],
- [5, None, tags([3, 4]), tags([2, 3, 4])],
- [4, None, tags([1]), tags([1, 2])],
- [2, None, tags([]), tags([2])],
- [1],
- ])]
diff --git a/orgparse/tests/data/01_attributes.py b/orgparse/tests/data/01_attributes.py
deleted file mode 100644
index 498766c..0000000
--- a/orgparse/tests/data/01_attributes.py
+++ /dev/null
@@ -1,41 +0,0 @@
-from orgparse.date import (
- OrgDate, OrgDateScheduled, OrgDateDeadline, OrgDateClosed,
- OrgDateClock,
-)
-
-node1 = dict(
- heading="A node with a lot of attributes",
- priority='A',
- scheduled=OrgDateScheduled((2010, 8, 6)),
- deadline=OrgDateDeadline((2010, 8, 10)),
- closed=OrgDateClosed((2010, 8, 8, 18, 0)),
- clock=[
- OrgDateClock((2010, 8, 8, 17, 40), (2010, 8, 8, 17, 50), 10),
- OrgDateClock((2010, 8, 8, 17, 00), (2010, 8, 8, 17, 30), 30),
- ],
- properties=dict(Effort=70),
- datelist=[OrgDate((2010, 8, 16))],
- rangelist=[
- OrgDate((2010, 8, 7), (2010, 8, 8)),
- OrgDate((2010, 8, 9, 0, 30), (2010, 8, 10, 13, 20)),
- ],
- body="""\
- - <2010-08-16 Mon> DateList
- - <2010-08-07 Sat>--<2010-08-08 Sun>
- - <2010-08-09 Mon 00:30>--<2010-08-10 Tue 13:20> RangeList"""
-)
-
-node2 = dict(
- heading="A node without any attributed",
- priority=None,
- scheduled=OrgDate(None),
- deadline=OrgDate(None),
- closed=OrgDate(None),
- clock=[],
- properties={},
- datelist=[],
- rangelist=[],
- body="",
-)
-
-data = [node1, node2, node1]
diff --git a/orgparse/tests/test_data.py b/orgparse/tests/test_data.py
deleted file mode 100644
index 857d5d4..0000000
--- a/orgparse/tests/test_data.py
+++ /dev/null
@@ -1,82 +0,0 @@
-import os
-from glob import glob
-import pickle
-from nose.tools import eq_
-
-from .. import load
-from ..utils.py3compat import execfile
-
-
-DATADIR = os.path.join(os.path.dirname(__file__), 'data')
-
-
-def load_data(path):
- """Load data from python file"""
- ns = {}
- execfile(path, ns)
- return ns['data']
-
-
-def value_from_data_key(node, key):
- """
- Helper function for check_data. Get value from Orgnode by key.
- """
- if key == 'tags_inher':
- return node.tags
- elif key == 'children_heading':
- return [c.heading for c in node.children]
- elif key in ('parent_heading',
- 'previous_same_level_heading',
- 'next_same_level_heading',
- ):
- othernode = getattr(node, key.rsplit('_', 1)[0])
- if othernode and not othernode.is_root():
- return othernode.heading
- else:
- return
- else:
- return getattr(node, key)
-
-
-def data_path(dataname, ext):
- return os.path.join(DATADIR, '{0}.{1}'.format(dataname, ext))
-
-
-def get_datanames():
- for oname in sorted(glob(os.path.join(DATADIR, '*.org'))):
- yield os.path.splitext(os.path.basename(oname))[0]
-
-
-def check_data(dataname):
- """
- Compare parsed data from 'data/*.org' and its correct answer 'data/*.py'
- """
- oname = data_path(dataname, "org")
- data = load_data(data_path(dataname, "py"))
- root = load(oname)
-
- for (i, (node, kwds)) in enumerate(zip(root[1:], data)):
- for key in kwds:
- val = value_from_data_key(node, key)
- eq_(kwds[key], val,
- msg=('check value of {0}-th node of key "{1}" from "{2}".'
- '\n\nParsed:\n{3}\n\nReal:\n{4}'
- ).format(i, key, dataname, val, kwds[key]))
-
- eq_(root.env.filename, oname)
-
-
-def test_data():
- for dataname in get_datanames():
- yield (check_data, dataname)
-
-
-def check_picklable(dataname):
- oname = data_path(dataname, "org")
- root = load(oname)
- pickle.dumps(root)
-
-
-def test_picklable():
- for dataname in get_datanames():
- yield (check_picklable, dataname)
diff --git a/orgparse/tests/test_hugedata.py b/orgparse/tests/test_hugedata.py
deleted file mode 100644
index b72e27f..0000000
--- a/orgparse/tests/test_hugedata.py
+++ /dev/null
@@ -1,36 +0,0 @@
-try:
- import cPickle as pickle
-except ImportError:
- import pickle
-
-from nose.tools import eq_
-
-from .. import loadi
-
-
-def generate_org_lines(num_top_nodes, depth=3, nodes_per_level=1, _level=1):
- if depth == 0:
- return
- for i in range(num_top_nodes):
- yield ("*" * _level) + ' {0}-th heading of level {1}'.format(i, _level)
- for child in generate_org_lines(
- nodes_per_level, depth - 1, nodes_per_level, _level + 1):
- yield child
-
-
-def num_generate_org_lines(num_top_nodes, depth=3, nodes_per_level=1):
- if depth == 0:
- return 0
- return num_top_nodes * (
- 1 + num_generate_org_lines(
- nodes_per_level, depth - 1, nodes_per_level))
-
-
-def test_picklable():
- num = 1000
- depth = 3
- nodes_per_level = 1
- root = loadi(generate_org_lines(num, depth, nodes_per_level))
- eq_(sum(1 for _ in root),
- num_generate_org_lines(num, depth, nodes_per_level) + 1)
- pickle.dumps(root) # should not fail
diff --git a/orgparse/utils/_py3compat.py b/orgparse/utils/_py3compat.py
deleted file mode 100644
index 820e310..0000000
--- a/orgparse/utils/_py3compat.py
+++ /dev/null
@@ -1,9 +0,0 @@
-"""
-Python 3 compatibility code which is loaded only when from Python 3.
-"""
-
-
-def execfile(filename, *args):
- return exec(
- compile(open(filename).read(), filename, 'exec'),
- *args)
diff --git a/orgparse/utils/py3compat.py b/orgparse/utils/py3compat.py
deleted file mode 100644
index 6a9059e..0000000
--- a/orgparse/utils/py3compat.py
+++ /dev/null
@@ -1,18 +0,0 @@
-import sys
-
-PY3 = (sys.version_info[0] >= 3)
-
-try:
- # Python 2
- unicode = unicode
- basestring = basestring
-except NameError:
- # Python 3
- basestring = unicode = str
-
-PY3 = (sys.version_info[0] >= 3)
-
-if PY3:
- from ._py3compat import execfile
-else:
- execfile = execfile
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..0aa9ba0
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,53 @@
+[project]
+dynamic = ["version"] # version is managed by build backend
+name = "orgparse"
+dependencies = [
+]
+requires-python = ">=3.9"
+description = "orgparse - Emacs org-mode parser in Python"
+license = {file = "LICENSE"}
+authors = [
+ {name = "Takafumi Arakaki (@tkf)", email = "aka.tkf@gmail.com"},
+ {name = "Dmitrii Gerasimov (@karlicoss)", email = "karlicoss@gmail.com"},
+]
+maintainers = [
+ {name = "Dmitrii Gerasimov (@karlicoss)", email = "karlicoss@gmail.com"},
+]
+keywords = ["org", "org-mode", "emacs"]
+# see: http://pypi.python.org/pypi?%3Aaction=list_classifiers
+classifiers = [
+ "Development Status :: 5 - Production/Stable",
+ "License :: OSI Approved :: BSD License",
+ "Topic :: Text Processing :: Markup",
+]
+# TODO add it back later, perhaps via ast?
+# long_description=orgparse.__doc__,
+
+[project.urls]
+Homepage = "https://github.com/karlicoss/orgparse"
+
+[project.optional-dependencies]
+[dependency-groups]
+testing = [
+ "pytest",
+ "ruff",
+ "mypy",
+ "lxml", # for mypy html coverage
+ "ty>=0.0.1a25",
+]
+
+
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+# unfortunately have to duplicate project name here atm, see https://github.com/pypa/hatch/issues/1894
+[tool.hatch.build.targets.wheel]
+packages = ["src/orgparse"]
+
+[tool.hatch.version]
+source = "vcs"
+
+[tool.hatch.version.raw-options]
+version_scheme = "python-simplified-semver"
+local_scheme = "dirty-tag"
diff --git a/pytest.ini b/pytest.ini
new file mode 100644
index 0000000..226488b
--- /dev/null
+++ b/pytest.ini
@@ -0,0 +1,20 @@
+[pytest]
+# discover files that don't follow test_ naming. Useful to keep tests along with the source code
+python_files = *.py
+
+# this setting only impacts package/module naming under pytest, not the discovery
+consider_namespace_packages = true
+
+addopts =
+ # prevent pytest cache from being created... it craps into project dir and I never use it anyway
+ -p no:cacheprovider
+
+ # -rap to print tests summary even when they are successful
+ -rap
+ --verbose
+
+ # otherwise it won't discover doctests
+ --doctest-modules
+
+ # show all test durations (unless they are too short)
+ --durations=0
diff --git a/ruff.toml b/ruff.toml
new file mode 100644
index 0000000..e05c3b4
--- /dev/null
+++ b/ruff.toml
@@ -0,0 +1,102 @@
+line-length = 120 # impacts import sorting
+
+lint.extend-select = [
+ "ALL",
+]
+
+# Preserve types, even if a file imports `from __future__ import annotations`
+# we need this for cachew to work with HPI types on 3.9
+# can probably remove after 3.10?
+lint.pyupgrade.keep-runtime-typing = true
+
+lint.ignore = [
+ "D", # annoying nags about docstrings
+ "N", # pep naming
+ "TCH", # type checking rules, mostly just suggests moving imports under TYPE_CHECKING
+ "S", # bandit (security checks) -- tends to be not very useful, lots of nitpicks
+ "DTZ", # datetimes checks -- complaining about missing tz and mostly false positives
+ "FIX", # complains about fixmes/todos -- annoying
+ "TD", # complains about todo formatting -- too annoying
+ "ANN", # missing type annotations? seems way to strict though
+ "EM" , # suggests assigning all exception messages into a variable first... pretty annoying
+
+### too opinionated style checks
+ "E501", # too long lines
+ "E731", # assigning lambda instead of using def
+ "E741", # Ambiguous variable name: `l`
+ "E742", # Ambiguous class name: `O
+ "E401", # Multiple imports on one line
+ "F403", # import *` used; unable to detect undefined names
+###
+
+###
+ "E722", # Do not use bare `except` ## Sometimes it's useful for defensive imports and that sort of thing..
+ "F811", # Redefinition of unused # this gets in the way of pytest fixtures (e.g. in cachew)
+
+## might be nice .. but later and I don't wanna make it strict
+ "E402", # Module level import not at top of file
+
+### these are just nitpicky, we usually know better
+ "PLR0911", # too many return statements
+ "PLR0912", # too many branches
+ "PLR0913", # too many function arguments
+ "PLR0915", # too many statements
+ "PLR1714", # consider merging multiple comparisons
+ "PLR2044", # line with empty comment
+ "PLR5501", # use elif instead of else if
+ "PLR2004", # magic value in comparison -- super annoying in tests
+###
+ "PLR0402", # import X.Y as Y -- TODO maybe consider enabling it, but double check
+
+ "B009", # calling gettattr with constant attribute -- this is useful to convince mypy
+ "B010", # same as above, but setattr
+ "B017", # pytest.raises(Exception)
+ "B023", # seems to result in false positives?
+
+ # complains about useless pass, but has sort of a false positive if the function has a docstring?
+ # this is common for click entrypoints (e.g. in __main__), so disable
+ "PIE790",
+
+ # a bit too annoying, offers to convert for loops to list comprehension
+ # , which may heart readability
+ "PERF401",
+
+ # suggests no using exception in for loops
+ # we do use this technique a lot, plus in 3.11 happy path exception handling is "zero-cost"
+ "PERF203",
+
+ "RET504", # unnecessary assignment before returning -- that can be useful for readability
+ "RET505", # unnecessary else after return -- can hurt readability
+
+ "PLW0603", # global variable update.. we usually know why we are doing this
+ "PLW2901", # for loop variable overwritten, usually this is intentional
+
+ "PT011", # pytest raises is too broad
+
+ "COM812", # trailing comma missing -- mostly just being annoying with long multiline strings
+
+ "TRY003", # suggests defining exception messages in exception class -- kinda annoying
+ "TRY201", # raise without specifying exception name -- sometimes hurts readability
+ "TRY400", # a bit dumb, and results in false positives (see https://github.com/astral-sh/ruff/issues/18070)
+ "TRY401", # redundant exception in logging.exception call? TODO double check, might result in excessive logging
+
+ "TID252", # Prefer absolute imports over relative imports from parent modules
+
+ ## too annoying
+ "T20", # just complains about prints and pprints (TODO maybe consider later?)
+ "Q", # flake quotes, too annoying
+ "C90", # some complexity checking
+ "G004", # logging statement uses f string
+ "ERA001", # commented out code
+ "SLF001", # private member accessed
+ "BLE001", # do not catch 'blind' Exception
+ "INP001", # complains about implicit namespace packages
+ "SIM102", # if statements collapsing, often hurts readability
+ "SIM103", # multiple conditions collapsing, often hurts readability
+ "SIM105", # suggests using contextlib.suppress instad of try/except -- this wouldn't be mypy friendly
+ "SIM108", # suggests using ternary operation instead of if -- hurts readability
+ "SIM110", # suggests using any(...) instead of for look/return -- hurts readability
+ "SIM117", # suggests using single with statement instead of nested -- doesn't work in tests
+ "RSE102", # complains about missing parens in exceptions
+ ##
+]
diff --git a/setup.py b/setup.py
deleted file mode 100644
index dfcf8ad..0000000
--- a/setup.py
+++ /dev/null
@@ -1,35 +0,0 @@
-from distutils.core import setup
-
-import orgparse
-
-setup(
- name='orgparse',
- version=orgparse.__version__,
- packages=[
- 'orgparse',
- 'orgparse.utils',
- 'orgparse.tests',
- 'orgparse.tests.data',
- ],
- package_data={
- 'orgparse.tests.data': ['*.org'],
- },
- author=orgparse.__author__,
- author_email='aka.tkf@gmail.com',
- url='https://github.com/tkf/orgparse',
- license=orgparse.__license__,
- description='orgparse - Emacs org-mode parser in Python',
- long_description=orgparse.__doc__,
- keywords='org-mode, Emacs, parser',
- classifiers=[
- "Development Status :: 3 - Alpha",
- 'License :: OSI Approved :: BSD License',
- 'Programming Language :: Python',
- 'Programming Language :: Python :: 2',
- 'Programming Language :: Python :: 2.6',
- 'Programming Language :: Python :: 2.7',
- 'Programming Language :: Python :: 3',
- 'Programming Language :: Python :: 3.2',
- # see: http://pypi.python.org/pypi?%3Aaction=list_classifiers
- ],
-)
diff --git a/orgparse/__init__.py b/src/orgparse/__init__.py
similarity index 55%
rename from orgparse/__init__.py
rename to src/orgparse/__init__.py
index cb3741d..110c474 100644
--- a/orgparse/__init__.py
+++ b/src/orgparse/__init__.py
@@ -1,41 +1,32 @@
# Import README.rst using cog
# [[[cog
# from cog import out
-# out('"""\n{0}\n"""'.format(file('../README.rst').read()))
+# out('"""\n{0}\n"""'.format(open('../README.rst').read()))
# ]]]
"""
===========================================================
- orgparse - Pyton module for reading Emacs org-mode file
+ orgparse - Python module for reading Emacs org-mode files
===========================================================
-Links:
-
-* `Documentation (at Read the Docs) `_
-* `Repository (at GitHub) `_
-* `Issue tracker (at GitHub) `_
-* `PyPI `_
-* `Travis CI `_ |build-status|
-
-.. |build-status|
- image:: https://secure.travis-ci.org/tkf/orgparse.png?branch=master
- :target: http://travis-ci.org/tkf/orgparse
- :alt: Build Status
-
+* `Documentation (Read the Docs) `_
+* `Repository (at GitHub) `_
+* `PyPI `_
Install
-------
-You can install `orgparse` from PyPI_::
-
pip install orgparse
Usage
-----
-Loading org object
-^^^^^^^^^^^^^^^^^^
+There are pretty extensive doctests if you're interested in some specific method. Otherwise here are some example snippets:
+
+
+Load org node
+^^^^^^^^^^^^^
::
from orgparse import load, loads
@@ -78,8 +69,8 @@
* Heading 1
-Accessing to node attributes
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Accessing node attributes
+^^^^^^^^^^^^^^^^^^^^^^^^^
>>> root = loads('''
... * DONE Heading :TAG:
@@ -115,52 +106,60 @@
"""
# [[[end]]]
-import codecs
+from collections.abc import Iterable
+from pathlib import Path
+from typing import Optional, TextIO, Union
-from .node import parse_lines
-from .utils.py3compat import basestring
+from .node import OrgEnv, OrgNode, parse_lines # todo basenode??
-__version__ = '0.0.1.dev3'
-__author__ = 'Takafumi Arakaki'
-__license__ = 'BSD License'
-__all__ = ["load", "loads", "loadi"]
+__all__ = ["load", "loadi", "loads"]
-def load(path):
+def load(path: Union[str, Path, TextIO], env: Optional[OrgEnv] = None) -> OrgNode:
"""
Load org-mode document from a file.
:type path: str or file-like
- :arg path: Path to org file or file-like object of a org document.
+ :arg path: Path to org file or file-like object of an org document.
:rtype: :class:`orgparse.node.OrgRootNode`
"""
- if isinstance(path, basestring):
- orgfile = codecs.open(path, encoding='utf8')
- filename = path
- else:
- orgfile = path
- filename = path.name if hasattr(path, 'name') else ''
- return loadi((l.rstrip('\n') for l in orgfile.readlines()),
- filename=filename)
+ # Make sure it is a Path object.
+ if isinstance(path, str):
+ path = Path(path)
+
+ # if it is a Path
+ if isinstance(path, Path):
+ # open that Path
+ with path.open('r', encoding='utf8') as orgfile:
+ # try again loading
+ return load(orgfile, env)
+
+ # We assume it is a file-like object (e.g. io.StringIO)
+ all_lines = (line.rstrip('\n') for line in path)
+
+ # get the filename
+ filename = path.name if hasattr(path, 'name') else ''
+
+ return loadi(all_lines, filename=filename, env=env)
-def loads(string, filename=''):
+def loads(string: str, filename: str = '', env: Optional[OrgEnv] = None) -> OrgNode:
"""
Load org-mode document from a string.
:rtype: :class:`orgparse.node.OrgRootNode`
"""
- return loadi(string.splitlines(), filename=filename)
+ return loadi(string.splitlines(), filename=filename, env=env)
-def loadi(lines, filename=''):
+def loadi(lines: Iterable[str], filename: str = '', env: Optional[OrgEnv] = None) -> OrgNode:
"""
Load org-mode document from an iterative object.
:rtype: :class:`orgparse.node.OrgRootNode`
"""
- return parse_lines(lines, filename=filename)
+ return parse_lines(lines, filename=filename, env=env)
diff --git a/orgparse/date.py b/src/orgparse/date.py
similarity index 54%
rename from orgparse/date.py
rename to src/orgparse/date.py
index 2600b19..1685f32 100644
--- a/orgparse/date.py
+++ b/src/orgparse/date.py
@@ -1,21 +1,26 @@
+from __future__ import annotations
+
import datetime
import re
+from datetime import timedelta
+from typing import Optional, Union
+
+DateIsh = Union[datetime.date, datetime.datetime]
-def total_seconds(td):
+def total_seconds(td: timedelta) -> float:
"""Equivalent to `datetime.timedelta.total_seconds`."""
- return float(td.microseconds +
- (td.seconds + td.days * 24 * 3600) * 10 ** 6) / 10 ** 6
+ return float(td.microseconds + (td.seconds + td.days * 24 * 3600) * 10**6) / 10**6
-def total_minutes(td):
+def total_minutes(td: timedelta) -> float:
"""Alias for ``total_seconds(td) / 60``."""
return total_seconds(td) / 60
-def gene_timestamp_regex(brtype, prefix=None, nocookie=False):
+def gene_timestamp_regex(brtype: str, prefix: str | None = None, *, nocookie: bool = False) -> str:
"""
- Generate timetamp regex for active/inactive/nobrace brace type
+ Generate timestamp regex for active/inactive/nobrace brace type
:type brtype: {'active', 'inactive', 'nobrace'}
:arg brtype:
@@ -44,12 +49,15 @@ def gene_timestamp_regex(brtype, prefix=None, nocookie=False):
>>> '{year}-{month}-{day}'.format(**m.groupdict())
'2010-06-21'
>>> m = timestamp_re.match('<2005-10-01 Sat 12:30 +7m -3d>')
- >>> m.groupdict() == {
- ... 'year': '2005', 'month': '10', 'day': '01',
- ... 'hour': '12', 'min': '30',
- ... 'repeatpre': '+', 'repeatnum': '7', 'repeatdwmy': 'm',
- ... 'warnpre': '-', 'warnnum': '3', 'warndwmy': 'd'}
- True
+ >>> from collections import OrderedDict
+ >>> sorted(m.groupdict().items())
+ ... # doctest: +NORMALIZE_WHITESPACE
+ [('day', '01'),
+ ('end_hour', None), ('end_min', None),
+ ('hour', '12'), ('min', '30'),
+ ('month', '10'),
+ ('repeatdwmy', 'm'), ('repeatnum', '7'), ('repeatpre', '+'),
+ ('warndwmy', 'd'), ('warnnum', '3'), ('warnpre', '-'), ('year', '2005')]
When ``brtype = 'nobrace'``, cookie part cannot be retrieved.
@@ -63,11 +71,12 @@ def gene_timestamp_regex(brtype, prefix=None, nocookie=False):
>>> '{year}-{month}-{day}'.format(**m.groupdict())
'2010-06-21'
>>> m = timestamp_re.match('2005-10-01 Sat 12:30 +7m -3d')
- >>> m.groupdict() == {
- ... 'year': '2005', 'month': '10', 'day': '01',
- ... 'hour': '12', 'min': '30'}
- True
-
+ >>> sorted(m.groupdict().items())
+ ... # doctest: +NORMALIZE_WHITESPACE
+ [('day', '01'),
+ ('end_hour', None), ('end_min', None),
+ ('hour', '12'), ('min', '30'),
+ ('month', '10'), ('year', '2005')]
"""
if brtype == 'active':
@@ -77,15 +86,15 @@ def gene_timestamp_regex(brtype, prefix=None, nocookie=False):
elif brtype == 'nobrace':
(bo, bc) = ('', '')
else:
- raise ValueError("brtype='{0!r}' is invalid".format(brtype))
+ raise ValueError(f"brtype='{brtype!r}' is invalid")
if brtype == 'nobrace':
ignore = r'[\s\w]'
else:
- ignore = '[^{bc}]'.format(bc=bc)
+ ignore = f'[^{bc}]'
if prefix is None:
- prefix = '{0}_'.format(brtype)
+ prefix = f'{brtype}_'
regex_date_time = r"""
(?P<{prefix}year>\d{{4}}) -
@@ -95,6 +104,11 @@ def gene_timestamp_regex(brtype, prefix=None, nocookie=False):
({ignore}+?)
(?P<{prefix}hour>\d{{2}}) :
(?P<{prefix}min>\d{{2}})
+ ( # optional end time range
+ --?
+ (?P<{prefix}end_hour>\d{{2}}) :
+ (?P<{prefix}end_min>\d{{2}})
+ )?
)?
"""
regex_cookie = r"""
@@ -102,37 +116,65 @@ def gene_timestamp_regex(brtype, prefix=None, nocookie=False):
({ignore}+?)
(?P<{prefix}repeatpre> [\.\+]{{1,2}})
(?P<{prefix}repeatnum> \d+)
- (?P<{prefix}repeatdwmy> [dwmy])
+ (?P<{prefix}repeatdwmy> [hdwmy])
)?
( # optional warning
({ignore}+?)
(?P<{prefix}warnpre> \-)
(?P<{prefix}warnnum> \d+)
- (?P<{prefix}warndwmy> [dwmy])
+ (?P<{prefix}warndwmy> [hdwmy])
)?
"""
- # http://www.pythonregex.com/
regex = ''.join([
bo,
regex_date_time,
regex_cookie if nocookie or brtype != 'nobrace' else '',
'({ignore}*?)',
- bc])
+ bc,
+ ]) # fmt: skip
return regex.format(prefix=prefix, ignore=ignore)
+def date_time_format(date: DateIsh) -> str:
+ """
+ Format a date or datetime in default org format
+
+ @param date The date
+
+ @return Formatted date(time)
+ """
+ default_format_date = "%Y-%m-%d %a"
+ default_format_datetime = "%Y-%m-%d %a %H:%M"
+ is_datetime = isinstance(date, datetime.datetime)
+
+ return date.strftime(default_format_datetime if is_datetime else default_format_date)
+
+
+def is_same_day(date0, date1) -> bool:
+ """
+ Check if two dates or datetimes are on the same day
+ """
+ return OrgDate._date_to_tuple(date0)[:3] == OrgDate._date_to_tuple(date1)[:3]
+
+
TIMESTAMP_NOBRACE_RE = re.compile(
gene_timestamp_regex('nobrace', prefix=''),
- re.VERBOSE)
+ re.VERBOSE,
+)
TIMESTAMP_RE = re.compile(
- '|'.join((gene_timestamp_regex('active'),
- gene_timestamp_regex('inactive'))),
- re.VERBOSE)
+ '|'.join((
+ gene_timestamp_regex('active'),
+ gene_timestamp_regex('inactive'),
+ )),
+ re.VERBOSE,
+) # fmt: skip
+
+_Repeater = tuple[str, int, str]
-class OrgDate(object):
+class OrgDate:
_active_default = True
"""
The default active value.
@@ -142,7 +184,22 @@ class OrgDate(object):
"""
- def __init__(self, start, end=None, active=None):
+ """
+ When formatting the date to string via __str__, and there is an end date on
+ the same day as the start date, allow formatting in the short syntax
+ <2021-09-03 Fri 16:01--17:30>? Otherwise the string represenation would be
+ <2021-09-03 Fri 16:01>--<2021-09-03 Fri 17:30>
+ """
+ _allow_short_range = True
+
+ def __init__(
+ self,
+ start,
+ end=None,
+ active: bool | None = None, # noqa: FBT001
+ repeater: _Repeater | None = None,
+ warning: _Repeater | None = None,
+ ) -> None:
"""
Create :class:`OrgDate` object
@@ -155,6 +212,10 @@ def __init__(self, start, end=None, active=None):
:arg active: Active/inactive flag.
None means using its default value, which
may be different for different subclasses.
+ :type repeater: tuple or None
+ :arg repeater: Repeater interval.
+ :type warning: tuple or None
+ :arg warning: Deadline warning interval.
>>> OrgDate(datetime.date(2012, 2, 10))
OrgDate((2012, 2, 10))
@@ -180,9 +241,12 @@ def __init__(self, start, end=None, active=None):
self._start = self._to_date(start)
self._end = self._to_date(end)
self._active = self._active_default if active is None else active
+ # repeater and warning are tuples of (prefix, number, interval)
+ self._repeater = repeater
+ self._warning = warning
@staticmethod
- def _to_date(date):
+ def _to_date(date) -> DateIsh:
if isinstance(date, (tuple, list)):
if len(date) == 3:
return datetime.date(*date)
@@ -192,51 +256,79 @@ def _to_date(date):
raise ValueError(
"Automatic conversion to the datetime object "
"requires at least 3 elements in the tuple. "
- "Only {0} elements are in the given tuple '{1}'."
- .format(len(date), date))
+ f"Only {len(date)} elements are in the given tuple '{date}'."
+ )
elif isinstance(date, (int, float)):
return datetime.datetime.fromtimestamp(date)
else:
return date
@staticmethod
- def _date_to_tuple(date):
+ def _date_to_tuple(date: DateIsh) -> tuple[int, ...]:
if isinstance(date, datetime.datetime):
return tuple(date.timetuple()[:6])
elif isinstance(date, datetime.date):
return tuple(date.timetuple()[:3])
+ else:
+ raise TypeError(f"can't happen: {date} {type(date)}")
- def __repr__(self):
+ def __repr__(self) -> str:
args = [
self.__class__.__name__,
self._date_to_tuple(self.start),
self._date_to_tuple(self.end) if self.has_end() else None,
None if self._active is self._active_default else self._active,
+ self._repeater,
+ self._warning,
]
- if args[2] is None and args[3] is None:
- return '{0}({1!r})'.format(*args)
- elif args[3] is None:
- return '{0}({1!r}, {2!r})'.format(*args)
- else:
- return '{0}({1!r}, {2!r}, {3!r})'.format(*args)
+ while args[-1] is None:
+ args.pop()
+ if len(args) > 3 and args[3] is None:
+ args[3] = self._active_default
+ return '{}({})'.format(args[0], ', '.join(map(repr, args[1:])))
+
+ def __str__(self) -> str:
+ fence = ("<", ">") if self.is_active() else ("[", "]")
+
+ start = date_time_format(self.start)
+ end = None
+
+ if self.has_end():
+ if self._allow_short_range and is_same_day(self.start, self.end):
+ start += "--{}".format(self.end.strftime("%H:%M"))
+ else:
+ end = date_time_format(self.end)
+
+ if self._repeater is not None:
+ (x, y, z) = self._repeater
+ start += f" {x}{y}{z}"
+ if self._warning is not None:
+ (x, y, z) = self._warning
+ start += f" {x}{y}{z}"
+ ret = f"{fence[0]}{start}{fence[1]}"
+ if end:
+ ret += f"--{fence[0]}{end}{fence[1]}"
- def __nonzero__(self):
+ return ret
+
+ def __bool__(self) -> bool:
return bool(self._start)
- __bool__ = __nonzero__ # PY3
+ def __hash__(self) -> int:
+ return hash((self._start, self._end, self._active, self._repeater, self._warning))
- def __eq__(self, other):
- if (isinstance(other, OrgDate) and
- self._start is None and
- other._start is None):
+ def __eq__(self, other) -> bool:
+ if isinstance(other, OrgDate) and self._start is None and other._start is None:
return True
- return (isinstance(other, self.__class__) and
- self._start == other._start and
- self._end == other._end and
- self._active == other._active)
+ return (
+ isinstance(other, self.__class__)
+ and self._start == other._start
+ and self._end == other._end
+ and self._active == other._active
+ )
@property
- def start(self):
+ def start(self) -> DateIsh:
"""
Get date or datetime object
@@ -249,7 +341,7 @@ def start(self):
return self._start
@property
- def end(self):
+ def end(self) -> DateIsh:
"""
Get date or datetime object
@@ -261,15 +353,15 @@ def end(self):
"""
return self._end
- def is_active(self):
+ def is_active(self) -> bool:
"""Return true if the date is active"""
return self._active
- def has_end(self):
+ def has_end(self) -> bool:
"""Return true if it has the end date"""
return bool(self._end)
- def has_time(self):
+ def has_time(self) -> bool:
"""
Return true if the start date has time field
@@ -281,7 +373,7 @@ def has_time(self):
"""
return isinstance(self._start, datetime.datetime)
- def has_overlap(self, other):
+ def has_overlap(self, other) -> bool:
"""
Test if it has overlap with other :class:`OrgDate` instance
@@ -303,11 +395,10 @@ def has_overlap(self, other):
if not isinstance(other, OrgDate):
other = OrgDate(other)
if self.has_end():
- return (self._datetime_in_range(other.start) or
- self._datetime_in_range(other.end))
+ return self._datetime_in_range(other.start) or self._datetime_in_range(other.end)
elif other.has_end():
return other._datetime_in_range(self.start)
- elif self.start == other.get_start:
+ elif self.start == other.start:
return True
else:
return False
@@ -321,18 +412,32 @@ def _datetime_in_range(self, date):
return False
@staticmethod
- def _as_datetime(date):
- if isinstance(date, datetime.date):
+ def _as_datetime(date) -> datetime.datetime:
+ """
+ Convert the given date into datetime (if it already is, return it
+ unmodified
+ """
+ if not isinstance(date, datetime.datetime):
return datetime.datetime(*date.timetuple()[:3])
return date
@staticmethod
- def _datetuple_from_groupdict(dct, prefix=''):
- keys = ['year', 'month', 'day', 'hour', 'min']
- return list(map(int, filter(None, (dct[prefix + k] for k in keys))))
+ def _daterange_from_groupdict(dct, prefix='') -> tuple[list, Optional[list]]:
+ start_keys = ['year', 'month', 'day', 'hour' , 'min'] # fmt: skip
+ end_keys = ['year', 'month', 'day', 'end_hour', 'end_min'] # fmt: skip
+ start_range = list(map(int, filter(None, (dct[prefix + k] for k in start_keys))))
+ end_range: Optional[list]
+ end_range = list(map(int, filter(None, (dct[prefix + k] for k in end_keys))))
+ if len(end_range) < len(end_keys):
+ end_range = None
+ return (start_range, end_range)
+
+ @classmethod
+ def _datetuple_from_groupdict(cls, dct, prefix=''):
+ return cls._daterange_from_groupdict(dct, prefix=prefix)[0]
@classmethod
- def list_from_str(cls, string):
+ def list_from_str(cls, string: str) -> list[OrgDate]:
"""
Parse string and return a list of :class:`OrgDate` objects
@@ -344,11 +449,13 @@ def list_from_str(cls, string):
[OrgDate((2012, 2, 10)), OrgDate((2012, 2, 12), None, False)]
>>> OrgDate.list_from_str("this is not timestamp")
[]
-
+ >>> OrgDate.list_from_str("<2012-02-11 Sat 10:11--11:20>")
+ [OrgDate((2012, 2, 11, 10, 11, 0), (2012, 2, 11, 11, 20, 0))]
"""
+ cookie_suffix = ['pre', 'num', 'dwmy']
match = TIMESTAMP_RE.search(string)
if match:
- rest = string[match.end():]
+ rest = string[match.end() :]
mdict = match.groupdict()
if mdict['active_year']:
prefix = 'active_'
@@ -358,27 +465,39 @@ def list_from_str(cls, string):
prefix = 'inactive_'
active = False
rangedash = '--['
+ repeater: Optional[tuple[str, int, str]] = None
+ warning: Optional[tuple[str, int, str]] = None
+ if mdict[prefix + 'repeatpre'] is not None:
+ keys = [prefix + 'repeat' + suffix for suffix in cookie_suffix]
+ values = [mdict[k] for k in keys]
+ repeater = (values[0], int(values[1]), values[2])
+ if mdict[prefix + 'warnpre'] is not None:
+ keys = [prefix + 'warn' + suffix for suffix in cookie_suffix]
+ values = [mdict[k] for k in keys]
+ warning = (values[0], int(values[1]), values[2])
has_rangedash = rest.startswith(rangedash)
match2 = TIMESTAMP_RE.search(rest) if has_rangedash else None
if has_rangedash and match2:
- rest = rest[match2.end():]
+ rest = rest[match2.end() :]
# no need for check activeness here because of the rangedash
mdict2 = match2.groupdict()
odate = cls(
cls._datetuple_from_groupdict(mdict, prefix),
cls._datetuple_from_groupdict(mdict2, prefix),
- active=active)
+ active=active,
+ repeater=repeater,
+ warning=warning,
+ )
else:
odate = cls(
- cls._datetuple_from_groupdict(mdict, prefix),
- active=active)
- # FIXME: treat "repeater" and "warn"
- return [odate] + cls.list_from_str(rest)
+ *cls._daterange_from_groupdict(mdict, prefix), active=active, repeater=repeater, warning=warning
+ )
+ return [odate, *cls.list_from_str(rest)]
else:
return []
@classmethod
- def from_str(cls, string):
+ def from_str(cls, string: str) -> OrgDate:
"""
Parse string and return an :class:`OrgDate` objects.
@@ -391,8 +510,7 @@ def from_str(cls, string):
match = cls._from_str_re.match(string)
if match:
mdict = match.groupdict()
- return cls(cls._datetuple_from_groupdict(mdict),
- active=cls._active_default)
+ return cls(cls._datetuple_from_groupdict(mdict), active=cls._active_default)
else:
return cls(None)
@@ -402,54 +520,77 @@ def from_str(cls, string):
def compile_sdc_re(sdctype):
brtype = 'inactive' if sdctype == 'CLOSED' else 'active'
return re.compile(
- r'{0}:\s+{1}'.format(
+ r'^(?!\#).*{}:\s+{}'.format(
sdctype,
- gene_timestamp_regex(brtype, prefix='', nocookie=True)),
- re.VERBOSE)
+ gene_timestamp_regex(brtype, prefix='', nocookie=True),
+ ),
+ re.VERBOSE,
+ )
class OrgDateSDCBase(OrgDate):
-
_re = None # override this!
# FIXME: use OrgDate.from_str
@classmethod
def from_str(cls, string):
- match = cls._re.search(string)
+ rgx = cls._re
+ assert rgx is not None
+ match = rgx.search(string)
if match:
mdict = match.groupdict()
- return cls(cls._datetuple_from_groupdict(mdict),
- active=cls._active_default)
+ start = cls._datetuple_from_groupdict(mdict)
+ end = None
+ end_hour = mdict['end_hour']
+ end_min = mdict['end_min']
+ if end_hour is not None and end_min is not None:
+ end_dict = {}
+ end_dict.update(mdict)
+ end_dict.update({'hour': end_hour, 'min': end_min})
+ end = cls._datetuple_from_groupdict(end_dict)
+ cookie_suffix = ['pre', 'num', 'dwmy']
+ repeater: Optional[tuple[str, int, str]] = None
+ warning: Optional[tuple[str, int, str]] = None
+ prefix = ''
+ if mdict[prefix + 'repeatpre'] is not None:
+ keys = [prefix + 'repeat' + suffix for suffix in cookie_suffix]
+ values = [mdict[k] for k in keys]
+ repeater = (values[0], int(values[1]), values[2])
+ if mdict[prefix + 'warnpre'] is not None:
+ keys = [prefix + 'warn' + suffix for suffix in cookie_suffix]
+ values = [mdict[k] for k in keys]
+ warning = (values[0], int(values[1]), values[2])
+ return cls(start, end, active=cls._active_default, repeater=repeater, warning=warning)
else:
return cls(None)
class OrgDateScheduled(OrgDateSDCBase):
"""Date object to represent SCHEDULED attribute."""
+
_re = compile_sdc_re('SCHEDULED')
_active_default = True
class OrgDateDeadline(OrgDateSDCBase):
"""Date object to represent DEADLINE attribute."""
+
_re = compile_sdc_re('DEADLINE')
_active_default = True
class OrgDateClosed(OrgDateSDCBase):
"""Date object to represent CLOSED attribute."""
+
_re = compile_sdc_re('CLOSED')
_active_default = False
def parse_sdc(string):
- return (OrgDateScheduled.from_str(string),
- OrgDateDeadline.from_str(string),
- OrgDateClosed.from_str(string))
+ return (OrgDateScheduled.from_str(string), OrgDateDeadline.from_str(string), OrgDateClosed.from_str(string))
class OrgDateClock(OrgDate):
-
"""
Date object to represent CLOCK attributes.
@@ -461,11 +602,13 @@ class OrgDateClock(OrgDate):
_active_default = False
- def __init__(self, start, end, duration=None, active=None):
+ _allow_short_range = False
+
+ def __init__(self, start, end=None, duration=None, active=None):
"""
Create OrgDateClock object
"""
- super(OrgDateClock, self).__init__(start, end, active=active)
+ super().__init__(start, end, active=active)
self._duration = duration
@property
@@ -476,8 +619,8 @@ def duration(self):
>>> duration = OrgDateClock.from_str(
... 'CLOCK: [2010-08-08 Sun 17:00]--[2010-08-08 Sun 17:30] => 0:30'
... ).duration
- >>> duration
- datetime.timedelta(0, 1800)
+ >>> duration.seconds
+ 1800
>>> total_minutes(duration)
30.0
@@ -498,11 +641,10 @@ def is_duration_consistent(self):
False
"""
- return (self._duration is None or
- self._duration == total_minutes(self.duration))
+ return self._duration is None or self._duration == total_minutes(self.duration)
@classmethod
- def from_str(cls, line):
+ def from_str(cls, line: str) -> OrgDateClock:
"""
Get CLOCK from given string.
@@ -513,51 +655,67 @@ def from_str(cls, line):
match = cls._re.search(line)
if not match:
return cls(None, None)
- groups = [int(d) for d in match.groups()]
- ymdhm1 = groups[:5]
- ymdhm2 = groups[5:10]
- hm3 = groups[10:]
+
+ ymdhm1 = [int(d) for d in match.groups()[:5]]
+
+ # second part starting with "--", does not exist for open clock dates
+ has_end = bool(match.group(6))
+ ymdhm2_dt: Optional[datetime.datetime]
+ len_min: Optional[int]
+ if has_end:
+ ymdhm2 = [int(d) for d in match.groups()[6:11]]
+ hm3 = [int(d) for d in match.groups()[11:]]
+
+ ymdhm2_dt = datetime.datetime(*ymdhm2) # type: ignore[arg-type]
+ len_min = hm3[0] * 60 + hm3[1]
+ else:
+ ymdhm2_dt = None
+ len_min = None
+
return cls(
- datetime.datetime(*ymdhm1),
- datetime.datetime(*ymdhm2),
- hm3[0] * 60 + hm3[1],
+ datetime.datetime(*ymdhm1), # type: ignore[arg-type]
+ ymdhm2_dt,
+ len_min,
)
_re = re.compile(
- r'CLOCK:\s+'
- r'\[(\d+)\-(\d+)\-(\d+)[^\]\d]*(\d+)\:(\d+)\]--'
- r'\[(\d+)\-(\d+)\-(\d+)[^\]\d]*(\d+)\:(\d+)\]\s+=>\s+(\d+)\:(\d+)'
- )
+ r'^(?!#).*CLOCK:\s+'
+ r'\[(\d+)\-(\d+)\-(\d+)[^\]\d]*(\d+)\:(\d+)\]'
+ r'(--\[(\d+)\-(\d+)\-(\d+)[^\]\d]*(\d+)\:(\d+)\]\s+=>\s+(\d+)\:(\d+))?'
+ )
class OrgDateRepeatedTask(OrgDate):
-
"""
Date object to represent repeated tasks.
"""
_active_default = False
- def __init__(self, start, before, after, active=None):
- super(OrgDateRepeatedTask, self).__init__(start, active=active)
+ def __init__(self, start, before: str, after: str, active=None) -> None:
+ super().__init__(start, active=active)
self._before = before
self._after = after
- def __repr__(self):
- args = [self._date_to_tuple(self.start), self.before, self.after]
+ def __repr__(self) -> str:
+ args: list = [self._date_to_tuple(self.start), self.before, self.after]
if self._active is not self._active_default:
args.append(self._active)
- return '{0}({1})'.format(
- self.__class__.__name__, ', '.join(map(repr, args)))
+ return '{}({})'.format(self.__class__.__name__, ', '.join(map(repr, args)))
+
+ def __hash__(self) -> int:
+ return hash((self._before, self._after))
- def __eq__(self, other):
- return super(OrgDateRepeatedTask, self).__eq__(other) and \
- isinstance(other, self.__class__) and \
- self._before == other._before and \
- self._after == other._after
+ def __eq__(self, other) -> bool:
+ return (
+ super().__eq__(other)
+ and isinstance(other, self.__class__)
+ and self._before == other._before
+ and self._after == other._after
+ )
@property
- def before(self):
+ def before(self) -> str:
"""
The state of task before marked as done.
@@ -569,7 +727,7 @@ def before(self):
return self._before
@property
- def after(self):
+ def after(self) -> str:
"""
The state of task after marked as done.
diff --git a/src/orgparse/extra.py b/src/orgparse/extra.py
new file mode 100644
index 0000000..e89343e
--- /dev/null
+++ b/src/orgparse/extra.py
@@ -0,0 +1,122 @@
+from __future__ import annotations
+
+import re
+from collections.abc import Iterator, Sequence
+from typing import Optional, Union
+
+RE_TABLE_SEPARATOR = re.compile(r'\s*\|(\-+\+)*\-+\|')
+RE_TABLE_ROW = re.compile(r'\s*\|([^|]+)+\|')
+STRIP_CELL_WHITESPACE = True
+
+
+Row = Sequence[str]
+
+
+class Table:
+ def __init__(self, lines: list[str]) -> None:
+ self._lines = lines
+
+ @property
+ def blocks(self) -> Iterator[Sequence[Row]]:
+ group: list[Row] = []
+ first = True
+ for r in self._pre_rows():
+ if r is None:
+ if not first or len(group) > 0:
+ yield group
+ first = False
+ group = []
+ else:
+ group.append(r)
+ if len(group) > 0:
+ yield group
+
+ def __iter__(self) -> Iterator[Row]:
+ return self.rows
+
+ @property
+ def rows(self) -> Iterator[Row]:
+ for r in self._pre_rows():
+ if r is not None:
+ yield r
+
+ def _pre_rows(self) -> Iterator[Optional[Row]]:
+ for l in self._lines:
+ if RE_TABLE_SEPARATOR.match(l):
+ yield None
+ else:
+ pr = l.strip().strip('|').split('|')
+ if STRIP_CELL_WHITESPACE:
+ pr = [x.strip() for x in pr]
+ yield pr
+ # TODO use iparse helper?
+
+ @property
+ def as_dicts(self) -> AsDictHelper:
+ bl = list(self.blocks)
+ if len(bl) != 2:
+ raise RuntimeError('Need two-block table to non-ambiguously guess column names')
+ hrows = bl[0]
+ if len(hrows) != 1:
+ raise RuntimeError(f'Need single row heading to guess column names, got: {hrows}')
+ columns = hrows[0]
+ assert len(set(columns)) == len(columns), f'Duplicate column names: {columns}'
+ return AsDictHelper(
+ columns=columns,
+ rows=bl[1],
+ )
+
+
+class AsDictHelper:
+ def __init__(self, columns: Sequence[str], rows: Sequence[Row]) -> None:
+ self.columns = columns
+ self._rows = rows
+
+ def __iter__(self) -> Iterator[dict[str, str]]:
+ for x in self._rows:
+ yield dict(zip(self.columns, x))
+
+
+class Gap:
+ # todo later, add indices etc
+ pass
+
+
+Rich = Union[Table, Gap]
+
+
+def to_rich_text(text: str) -> Iterator[Rich]:
+ '''
+ Convert an org-mode text into a 'rich' text, e.g. tables/lists/etc, interleaved by gaps.
+ NOTE: you shouldn't rely on the number of items returned by this function,
+ it might change in the future when more types are supported.
+
+ At the moment only tables are supported.
+ '''
+ lines = text.splitlines(keepends=True)
+ group: list[str] = []
+ last: type[Rich] = Gap
+
+ def emit() -> Rich:
+ nonlocal group, last
+ if last is Gap:
+ res = Gap()
+ elif last is Table:
+ res = Table(group) # type: ignore[assignment]
+ else:
+ raise RuntimeError(f'Unexpected type {last}')
+ group = []
+ return res
+
+ for line in lines:
+ if RE_TABLE_ROW.match(line) or RE_TABLE_SEPARATOR.match(line):
+ cur = Table
+ else:
+ cur = Gap # type: ignore[assignment]
+ if cur is not last:
+ if len(group) > 0:
+ yield emit()
+ last = cur
+ group.append(line)
+ if len(group) > 0:
+ yield emit()
diff --git a/orgparse/inline.py b/src/orgparse/inline.py
similarity index 87%
rename from orgparse/inline.py
rename to src/orgparse/inline.py
index 043c99d..a2057fc 100644
--- a/orgparse/inline.py
+++ b/src/orgparse/inline.py
@@ -25,9 +25,7 @@ def to_plain_text(org_text):
See also: info:org#Link format
"""
- return RE_LINK.sub(
- lambda m: m.group('desc0') or m.group('desc1'),
- org_text)
+ return RE_LINK.sub(lambda m: m.group('desc0') or m.group('desc1'), org_text)
RE_LINK = re.compile(
@@ -45,4 +43,5 @@ def to_plain_text(org_text):
\] \]
)
""",
- re.VERBOSE)
+ re.VERBOSE,
+)
diff --git a/orgparse/node.py b/src/orgparse/node.py
similarity index 64%
rename from orgparse/node.py
rename to src/orgparse/node.py
index bd3afc3..5794b43 100644
--- a/orgparse/node.py
+++ b/src/orgparse/node.py
@@ -1,17 +1,30 @@
-import re
-import itertools
-try:
- from collections import Sequence
-except ImportError:
- from collections.abc import Sequence
+from __future__ import annotations
-from .date import OrgDate, OrgDateClock, OrgDateRepeatedTask, parse_sdc
+import itertools
+import re
+from collections.abc import Iterable, Iterator, Sequence
+from typing import (
+ Any,
+ Optional,
+ Union,
+ cast,
+)
+
+from .date import (
+ OrgDate,
+ OrgDateClock,
+ OrgDateClosed,
+ OrgDateDeadline,
+ OrgDateRepeatedTask,
+ OrgDateScheduled,
+ parse_sdc,
+)
+from .extra import Rich, to_rich_text
from .inline import to_plain_text
-from .utils.py3compat import PY3, unicode
-def lines_to_chunks(lines):
- chunk = []
+def lines_to_chunks(lines: Iterable[str]) -> Iterable[list[str]]:
+ chunk: list[str] = []
for l in lines:
if RE_NODE_HEADER.search(l):
yield chunk
@@ -19,10 +32,11 @@ def lines_to_chunks(lines):
chunk.append(l)
yield chunk
+
RE_NODE_HEADER = re.compile(r"^\*+ ")
-def parse_heading_level(heading):
+def parse_heading_level(heading: str) -> tuple[str, int] | None:
"""
Get star-stripped heading and its level
@@ -30,17 +44,21 @@ def parse_heading_level(heading):
('Heading', 1)
>>> parse_heading_level('******** Heading')
('Heading', 8)
+ >>> parse_heading_level('*') # None since no space after star
+ >>> parse_heading_level('*bold*') # None
>>> parse_heading_level('not heading') # None
"""
- match = RE_HEADING_STARS.search(heading)
- if match:
- return (match.group(2), len(match.group(1)))
+ m = RE_HEADING_STARS.search(heading)
+ if m is not None:
+ return (m.group(2), len(m.group(1)))
+ return None
+
-RE_HEADING_STARS = re.compile('^(\*+)\s*(.*?)\s*$')
+RE_HEADING_STARS = re.compile(r'^(\*+)\s+(.*?)\s*$')
-def parse_heading_tags(heading):
+def parse_heading_tags(heading: str) -> tuple[str, list[str]]:
"""
Get first tags and heading without tags
@@ -71,10 +89,12 @@ def parse_heading_tags(heading):
tags = []
return (heading, tags)
-RE_HEADING_TAGS = re.compile(r'(.*?)\s*:([a-zA-Z0-9@_:]+):\s*$')
+# Tags are normal words containing letters, numbers, '_', and '@'. https://orgmode.org/manual/Tags.html
+RE_HEADING_TAGS = re.compile(r'(.*?)\s*:([\w@:]+):\s*$')
-def parse_heading_todos(heading, todo_candidates):
+
+def parse_heading_todos(heading: str, todo_candidates: list[str]) -> tuple[str, Optional[str]]:
"""
Get TODO keyword and heading without TODO keyword.
@@ -86,15 +106,16 @@ def parse_heading_todos(heading, todo_candidates):
"""
for todo in todo_candidates:
- todows = '{0} '.format(todo)
- if heading.startswith(todows):
- return (heading[len(todows):], todo)
+ if heading == todo:
+ return ('', todo)
+ if heading.startswith(todo + ' '):
+ return (heading[len(todo) + 1 :], todo)
return (heading, None)
def parse_heading_priority(heading):
"""
- Get priority and heading without priority field..
+ Get priority and heading without priority field.
>>> parse_heading_priority('HEADING')
('HEADING', None)
@@ -112,10 +133,13 @@ def parse_heading_priority(heading):
else:
return (heading, None)
+
RE_HEADING_PRIORITY = re.compile(r'^\s*\[#([A-Z0-9])\] ?(.*)$')
+PropertyValue = Union[str, int, float]
+
-def parse_property(line):
+def parse_property(line: str) -> tuple[Optional[str], Optional[PropertyValue]]:
"""
Get property from given string.
@@ -126,33 +150,165 @@ def parse_property(line):
"""
prop_key = None
- prop_val = None
+ prop_val: Optional[Union[str, int, float]] = None
match = RE_PROP.search(line)
if match:
prop_key = match.group(1)
prop_val = match.group(2)
if prop_key == 'Effort':
- (h, m) = prop_val.split(":", 2)
- if h.isdigit() and m.isdigit():
- prop_val = int(h) * 60 + int(m)
+ prop_val = parse_duration_to_minutes(prop_val)
return (prop_key, prop_val)
-RE_PROP = re.compile('^\s*:(.*?):\s*(.*?)\s*$')
+RE_PROP = re.compile(r'^\s*:(.*?):\s*(.*?)\s*$')
+
+
+def parse_duration_to_minutes(duration: str) -> Union[float, int]:
+ """
+ Parse duration minutes from given string.
+ Convert to integer if number has no decimal points
+
+ >>> parse_duration_to_minutes('3:12')
+ 192
+ >>> parse_duration_to_minutes('1:23:45')
+ 83.75
+ >>> parse_duration_to_minutes('1y 3d 3h 4min')
+ 530464
+ >>> parse_duration_to_minutes('1d3h5min')
+ 1625
+ >>> parse_duration_to_minutes('3d 13:35')
+ 5135
+ >>> parse_duration_to_minutes('2.35h')
+ 141
+ >>> parse_duration_to_minutes('10')
+ 10
+ >>> parse_duration_to_minutes('10.')
+ 10
+ >>> parse_duration_to_minutes('1 h')
+ 60
+ >>> parse_duration_to_minutes('')
+ 0
+ """
+
+ minutes = parse_duration_to_minutes_float(duration)
+ return int(minutes) if minutes.is_integer() else minutes
-def parse_comment(line):
+
+def parse_duration_to_minutes_float(duration: str) -> float:
+ """
+ Parse duration minutes from given string.
+ The following code is fully compatible with the 'org-duration-to-minutes' function in org mode:
+ https://github.com/emacs-mirror/emacs/blob/master/lisp/org/org-duration.el
+
+ >>> parse_duration_to_minutes_float('3:12')
+ 192.0
+ >>> parse_duration_to_minutes_float('1:23:45')
+ 83.75
+ >>> parse_duration_to_minutes_float('1y 3d 3h 4min')
+ 530464.0
+ >>> parse_duration_to_minutes_float('1d3h5min')
+ 1625.0
+ >>> parse_duration_to_minutes_float('3d 13:35')
+ 5135.0
+ >>> parse_duration_to_minutes_float('2.35h')
+ 141.0
+ >>> parse_duration_to_minutes_float('10')
+ 10.0
+ >>> parse_duration_to_minutes_float('10.')
+ 10.0
+ >>> parse_duration_to_minutes_float('1 h')
+ 60.0
+ >>> parse_duration_to_minutes_float('')
+ 0.0
+ """
+
+ match: Optional[Any]
+ if duration == "":
+ return 0.0
+ if isinstance(duration, float):
+ return float(duration)
+ if RE_ORG_DURATION_H_MM.fullmatch(duration):
+ hours, minutes, *seconds_ = map(float, duration.split(":"))
+ seconds = seconds_[0] if seconds_ else 0
+ return seconds / 60.0 + minutes + 60 * hours
+ if RE_ORG_DURATION_FULL.fullmatch(duration):
+ minutes = 0
+ for match in RE_ORG_DURATION_UNIT.finditer(duration):
+ value = float(match.group(1))
+ unit = match.group(2)
+ minutes += value * ORG_DURATION_UNITS[unit]
+ return float(minutes)
+ match = RE_ORG_DURATION_MIXED.fullmatch(duration)
+ if match:
+ units_part = match.groupdict()['A']
+ hms_part = match.groupdict()['B']
+ return parse_duration_to_minutes_float(units_part) + parse_duration_to_minutes_float(hms_part)
+ if RE_FLOAT.fullmatch(duration):
+ return float(duration)
+ raise ValueError(f"Invalid duration format {duration}")
+
+
+# Conversion factor to minutes for a duration.
+ORG_DURATION_UNITS = {
+ "min": 1,
+ "h": 60,
+ "d": 60 * 24,
+ "w": 60 * 24 * 7,
+ "m": 60 * 24 * 30,
+ "y": 60 * 24 * 365.25,
+}
+# Regexp matching for all units.
+ORG_DURATION_UNITS_RE = r'({})'.format(r'|'.join(ORG_DURATION_UNITS.keys()))
+# Regexp matching a duration expressed with H:MM or H:MM:SS format.
+# Hours can use any number of digits.
+ORG_DURATION_H_MM_RE = r'[ \t]*[0-9]+(?::[0-9]{2}){1,2}[ \t]*'
+RE_ORG_DURATION_H_MM = re.compile(ORG_DURATION_H_MM_RE)
+# Regexp matching a duration with an unit.
+# Allowed units are defined in ORG_DURATION_UNITS.
+# Match group 1 contains the bare number.
+# Match group 2 contains the unit.
+ORG_DURATION_UNIT_RE = r'([0-9]+(?:[.][0-9]*)?)[ \t]*' + ORG_DURATION_UNITS_RE
+RE_ORG_DURATION_UNIT = re.compile(ORG_DURATION_UNIT_RE)
+# Regexp matching a duration expressed with units.
+# Allowed units are defined in ORG_DURATION_UNITS.
+ORG_DURATION_FULL_RE = rf'(?:[ \t]*{ORG_DURATION_UNIT_RE})+[ \t]*'
+RE_ORG_DURATION_FULL = re.compile(ORG_DURATION_FULL_RE)
+# Regexp matching a duration expressed with units and H:MM or H:MM:SS format.
+# Allowed units are defined in ORG_DURATION_UNITS.
+# Match group A contains units part.
+# Match group B contains H:MM or H:MM:SS part.
+ORG_DURATION_MIXED_RE = rf'(?P([ \t]*{ORG_DURATION_UNIT_RE})+)[ \t]*(?P[0-9]+(?::[0-9][0-9]){{1,2}})[ \t]*'
+RE_ORG_DURATION_MIXED = re.compile(ORG_DURATION_MIXED_RE)
+# Regexp matching float numbers.
+RE_FLOAT = re.compile(r'[0-9]+([.][0-9]*)?')
+
+
+# -> Optional[Tuple[str, Sequence[str]]]: # todo wtf?? it says 'ABCMeta isn't subscriptable??'
+def parse_comment(line: str):
"""
Parse special comment such as ``#+SEQ_TODO``
>>> parse_comment('#+SEQ_TODO: TODO | DONE')
- ('SEQ_TODO', 'TODO | DONE')
+ ('SEQ_TODO', ['TODO | DONE'])
>>> parse_comment('# not a special comment') # None
+ >>> parse_comment('#+FILETAGS: :tag1:tag2:')
+ ('FILETAGS', ['tag1', 'tag2'])
"""
- if line.startswith('#+'):
- comment = line.lstrip('#+').split(':', 1)
- if len(comment) == 2:
- return (comment[0], comment[1].strip())
+ match = re.match(r'\s*#\+', line)
+ if match:
+ end = match.end(0)
+ comment = line[end:].split(':', maxsplit=1)
+ if len(comment) >= 2:
+ key = comment[0]
+ value = comment[1].strip()
+ if key.upper() == 'FILETAGS':
+ # just legacy behaviour; it seems like filetags is the only one that separated by ':'
+ # see https://orgmode.org/org.html#In_002dbuffer-Settings
+ return (key, [c.strip() for c in value.split(':') if len(c.strip()) > 0])
+ else:
+ return (key, [value])
+ return None
def parse_seq_todo(line):
@@ -180,26 +336,35 @@ def parse_seq_todo(line):
else:
(todos, dones) = (line, '')
strip_fast_access_key = lambda x: x.split('(', 1)[0]
- return (list(map(strip_fast_access_key, todos.split())),
- list(map(strip_fast_access_key, dones.split())))
-
+ return (
+ list(map(strip_fast_access_key, todos.split())),
+ list(map(strip_fast_access_key, dones.split())),
+ )
-class OrgEnv(object):
+class OrgEnv:
"""
Information global to the file (e.g, TODO keywords).
"""
- def __init__(self, todos=['TODO'], dones=['DONE'],
- filename=''):
+ def __init__(
+ self,
+ todos: Sequence[str] | None = None,
+ dones: Sequence[str] | None = None,
+ filename: str = '',
+ ) -> None:
+ if dones is None:
+ dones = ['DONE']
+ if todos is None:
+ todos = ['TODO']
self._todos = list(todos)
self._dones = list(dones)
self._todo_not_specified_in_comment = True
self._filename = filename
- self._nodes = []
+ self._nodes: list[OrgBaseNode] = []
@property
- def nodes(self):
+ def nodes(self) -> list[OrgBaseNode]:
"""
A list of org nodes.
@@ -265,15 +430,12 @@ def all_todo_keys(self):
return self._todos + self._dones
@property
- def filename(self):
+ def filename(self) -> str:
"""
Return a path to the source file or similar information.
If the org objects are not loaded from a file, this value
will be a string of the form ````.
-
- :rtype: str
-
"""
return self._filename
@@ -286,7 +448,6 @@ def from_chunks(self, chunks):
class OrgBaseNode(Sequence):
-
"""
Base class for :class:`OrgRootNode` and :class:`OrgNode`
@@ -323,7 +484,7 @@ class OrgBaseNode(Sequence):
*** Heading 3
* Heading 4
- It also support sequence protocol.
+ It also supports sequence protocol.
>>> print(root[1])
* Heading 1
@@ -340,20 +501,24 @@ class OrgBaseNode(Sequence):
** Heading 2
*** Heading 3
- """
+ Nodes remember the line number information (1-indexed):
- def __init__(self, env, index=None):
- """
- Create a :class:`OrgBaseNode` object.
+ >>> print(root.children[1].linenumber)
+ 5
+ """
- :type env: :class:`OrgEnv`
- :arg env: This will be set to the :attr:`env` attribute.
+ _body_lines: list[str] # set by the child classes
- """
+ def __init__(self, env: OrgEnv, index: int | None = None) -> None:
self.env = env
+ self.linenumber = cast(int, None) # set in parse_lines
+
# content
- self._lines = []
+ self._lines: list[str] = []
+
+ self._properties: dict[str, PropertyValue] = {}
+ self._timestamps: list[OrgDate] = []
# FIXME: use `index` argument to set index. (Currently it is
# done externally in `parse_lines`.)
@@ -374,45 +539,45 @@ def __init__(self, env, index=None):
def __iter__(self):
yield self
level = self.level
- for node in self.env._nodes[self._index + 1:]:
+ for node in self.env._nodes[self._index + 1 :]:
if node.level > level:
yield node
+ else:
+ break
- def __len__(self):
+ def __len__(self) -> int:
return sum(1 for _ in self)
- def __nonzero__(self):
+ def __bool__(self) -> bool:
# As self.__len__ returns non-zero value always this is not
# needed. This function is only for performance.
return True
- __bool__ = __nonzero__ # PY3
-
def __getitem__(self, key):
if isinstance(key, slice):
return itertools.islice(self, key.start, key.stop, key.step)
elif isinstance(key, int):
if key < 0:
key += len(self)
- for (i, node) in enumerate(self):
+ for i, node in enumerate(self):
if i == key:
return node
- raise IndexError("Out of range {0}".format(key))
+ raise IndexError(f"Out of range {key}")
else:
- raise TypeError("Inappropriate type {0} for {1}"
- .format(type(key), type(self)))
+ raise TypeError(f"Inappropriate type {type(key)} for {type(self)}")
# tree structure
- def _find_same_level(self, iterable):
+ def _find_same_level(self, iterable) -> OrgBaseNode | None:
for node in iterable:
if node.level < self.level:
- return
+ return None
if node.level == self.level:
return node
+ return None
@property
- def previous_same_level(self):
+ def previous_same_level(self) -> OrgBaseNode | None:
"""
Return previous node if exists or None otherwise.
@@ -431,10 +596,10 @@ def previous_same_level(self):
True
"""
- return self._find_same_level(reversed(self.env._nodes[:self._index]))
+ return self._find_same_level(reversed(self.env._nodes[: self._index]))
@property
- def next_same_level(self):
+ def next_same_level(self) -> OrgBaseNode | None:
"""
Return next node if exists or None otherwise.
@@ -453,15 +618,16 @@ def next_same_level(self):
True
"""
- return self._find_same_level(self.env._nodes[self._index + 1:])
+ return self._find_same_level(self.env._nodes[self._index + 1 :])
# FIXME: cache parent node
def _find_parent(self):
- for node in reversed(self.env._nodes[:self._index]):
+ for node in reversed(self.env._nodes[: self._index]):
if node.level < self.level:
return node
+ return None
- def get_parent(self, max_level=None):
+ def get_parent(self, max_level: int | None = None):
"""
Return a parent node.
@@ -470,9 +636,9 @@ def get_parent(self, max_level=None):
of the ancestor node to return. For example,
``get_parent(max_level=0)`` returns a root node.
- In general case, it specify a maximum level of the
+ In the general case, it specify a maximum level of the
desired ancestor node. If there is no ancestor node
- which level is equal to ``max_level``, this function
+ whose level is equal to ``max_level``, this function
try to find an ancestor node which level is smaller
than ``max_level``.
@@ -547,8 +713,11 @@ def parent(self):
# FIXME: cache children nodes
def _find_children(self):
- nodeiter = iter(self.env._nodes[self._index + 1:])
- node = next(nodeiter)
+ nodeiter = iter(self.env._nodes[self._index + 1 :])
+ try:
+ node = next(nodeiter)
+ except StopIteration:
+ return
if node.level <= self.level:
return
yield node
@@ -579,7 +748,7 @@ def children(self):
>>> c2 is n4
True
- Note the difference to ``n1[1:]``, which returns the Node 3 also.:
+ Note the difference to ``n1[1:]``, which returns the Node 3 also:
>>> (m1, m2, m3) = list(n1[1:])
>>> m2 is n3
@@ -607,6 +776,37 @@ def root(self):
return root
root = parent
+ @property
+ def properties(self) -> dict[str, PropertyValue]:
+ """
+ Node properties as a dictionary.
+
+ >>> from orgparse import loads
+ >>> root = loads('''
+ ... * Node
+ ... :PROPERTIES:
+ ... :SomeProperty: value
+ ... :END:
+ ... ''')
+ >>> root.children[0].properties['SomeProperty']
+ 'value'
+
+ """
+ return self._properties
+
+ def get_property(self, key, val=None) -> Optional[PropertyValue]:
+ """
+ Return property named ``key`` if exists or ``val`` otherwise.
+
+ :arg str key:
+ Key of property.
+
+ :arg val:
+ Default value to return.
+
+ """
+ return self._properties.get(key, val)
+
# parser
@classmethod
@@ -617,46 +817,59 @@ def from_chunk(cls, env, lines):
return self
def _parse_comments(self):
- special_comments = {}
+ special_comments: dict[str, list[str]] = {}
for line in self._lines:
parsed = parse_comment(line)
if parsed:
- (key, val) = parsed
- special_comments.setdefault(key, []).append(val)
+ (key, vals) = parsed
+ key = key.upper() # case insensitive, so keep as uppercase
+ special_comments.setdefault(key, []).extend(vals)
self._special_comments = special_comments
# parse TODO keys and store in OrgEnv
for todokey in ['TODO', 'SEQ_TODO', 'TYP_TODO']:
for val in special_comments.get(todokey, []):
self.env.add_todo_keys(*parse_seq_todo(val))
+ def _iparse_properties(self, ilines: Iterator[str]) -> Iterator[str]:
+ self._properties = {}
+ in_property_field = False
+ for line in ilines:
+ if in_property_field:
+ if line.find(":END:") >= 0:
+ break
+ else:
+ (key, val) = parse_property(line)
+ if key is not None and val is not None:
+ self._properties.update({key: val})
+ elif line.find(":PROPERTIES:") >= 0:
+ in_property_field = True
+ else:
+ yield line
+ for line in ilines:
+ yield line
+
# misc
@property
- def level(self):
+ def level(self) -> int:
"""
Level of this node.
-
- :rtype: int
-
"""
- raise NotImplemented
+ raise NotImplementedError
- def _get_tags(self, inher=False):
+ def _get_tags(self, *, inher: bool = False) -> set[str]: # noqa: ARG002
"""
Return tags
- :arg bool inher:
+ :arg inher:
Mix with tags of all ancestor nodes if ``True``.
-
- :rtype: set
-
"""
return set()
@property
- def tags(self):
+ def tags(self) -> set[str]:
"""
- Tag of this and parents node.
+ Tags of this and parent's node.
>>> from orgparse import loads
>>> n2 = loads('''
@@ -670,7 +883,7 @@ def tags(self):
return self._get_tags(inher=True)
@property
- def shallow_tags(self):
+ def shallow_tags(self) -> set[str]:
"""
Tags defined for this node (don't look-up parent nodes).
@@ -685,6 +898,40 @@ def shallow_tags(self):
"""
return self._get_tags(inher=False)
+ @staticmethod
+ def _get_text(text, format: str = 'plain'): # noqa: A002
+ if format == 'plain':
+ return to_plain_text(text)
+ elif format == 'raw':
+ return text
+ elif format == 'rich':
+ return to_rich_text(text)
+ else:
+ raise ValueError(f'format={format} is not supported.')
+
+ def get_body(self, format: str = 'plain') -> str: # noqa: A002
+ """
+ Return a string of body text.
+
+ See also: :meth:`get_heading`.
+
+ """
+ return self._get_text('\n'.join(self._body_lines), format) if self._lines else ''
+
+ @property
+ def body(self) -> str:
+ """Alias of ``.get_body(format='plain')``."""
+ return self.get_body()
+
+ @property
+ def body_rich(self) -> Iterator[Rich]:
+ r = self.get_body(format='rich')
+ return cast(Iterator[Rich], r) # meh..
+
+ @property
+ def heading(self) -> str:
+ raise NotImplementedError
+
def is_root(self):
"""
Return ``True`` when it is a root node.
@@ -700,42 +947,180 @@ def is_root(self):
"""
return False
- def __unicode__(self):
- return unicode("\n").join(self._lines)
+ def get_timestamps(self, active=False, inactive=False, range=False, point=False): # noqa: FBT002,A002 # will fix later
+ """
+ Return a list of timestamps in the body text.
- if PY3:
- __str__ = __unicode__
- else:
- def __str__(self):
- return unicode(self).encode('utf-8')
+ :type active: bool
+ :arg active: Include active type timestamps.
+ :type inactive: bool
+ :arg inactive: Include inactive type timestamps.
+ :type range: bool
+ :arg range: Include timestamps which has end date.
+ :type point: bool
+ :arg point: Include timestamps which has no end date.
+ :rtype: list of :class:`orgparse.date.OrgDate` subclasses
-class OrgRootNode(OrgBaseNode):
+ Consider the following org node:
+
+ >>> from orgparse import loads
+ >>> node = loads('''
+ ... * Node
+ ... CLOSED: [2012-02-26 Sun 21:15] SCHEDULED: <2012-02-26 Sun>
+ ... CLOCK: [2012-02-26 Sun 21:10]--[2012-02-26 Sun 21:15] => 0:05
+ ... Some inactive timestamp [2012-02-23 Thu] in body text.
+ ... Some active timestamp <2012-02-24 Fri> in body text.
+ ... Some inactive time range [2012-02-25 Sat]--[2012-02-27 Mon].
+ ... Some active time range <2012-02-26 Sun>--<2012-02-28 Tue>.
+ ... ''').children[0]
+
+ The default flags are all off, so it does not return anything.
+
+ >>> node.get_timestamps()
+ []
+
+ You can fetch appropriate timestamps using keyword arguments.
+
+ >>> node.get_timestamps(inactive=True, point=True)
+ [OrgDate((2012, 2, 23), None, False)]
+ >>> node.get_timestamps(active=True, point=True)
+ [OrgDate((2012, 2, 24))]
+ >>> node.get_timestamps(inactive=True, range=True)
+ [OrgDate((2012, 2, 25), (2012, 2, 27), False)]
+ >>> node.get_timestamps(active=True, range=True)
+ [OrgDate((2012, 2, 26), (2012, 2, 28))]
+
+ This is more complex example. Only active timestamps,
+ regardless of range/point type.
+
+ >>> node.get_timestamps(active=True, point=True, range=True)
+ [OrgDate((2012, 2, 24)), OrgDate((2012, 2, 26), (2012, 2, 28))]
+
+ """
+ return [
+ ts
+ for ts in self._timestamps
+ if (
+ ((active and ts.is_active()) or (inactive and not ts.is_active()))
+ and ((range and ts.has_end()) or (point and not ts.has_end()))
+ )
+ ]
+
+ @property
+ def datelist(self):
+ """
+ Alias of ``.get_timestamps(active=True, inactive=True, point=True)``.
+
+ :rtype: list of :class:`orgparse.date.OrgDate` subclasses
+
+ >>> from orgparse import loads
+ >>> root = loads('''
+ ... * Node with point dates <2012-02-25 Sat>
+ ... CLOSED: [2012-02-25 Sat 21:15]
+ ... Some inactive timestamp [2012-02-26 Sun] in body text.
+ ... Some active timestamp <2012-02-27 Mon> in body text.
+ ... ''')
+ >>> root.children[0].datelist # doctest: +NORMALIZE_WHITESPACE
+ [OrgDate((2012, 2, 25)),
+ OrgDate((2012, 2, 26), None, False),
+ OrgDate((2012, 2, 27))]
+
+ """
+ return self.get_timestamps(active=True, inactive=True, point=True)
+
+ @property
+ def rangelist(self):
+ """
+ Alias of ``.get_timestamps(active=True, inactive=True, range=True)``.
+
+ :rtype: list of :class:`orgparse.date.OrgDate` subclasses
+
+ >>> from orgparse import loads
+ >>> root = loads('''
+ ... * Node with range dates <2012-02-25 Sat>--<2012-02-28 Tue>
+ ... CLOCK: [2012-02-26 Sun 21:10]--[2012-02-26 Sun 21:15] => 0:05
+ ... Some inactive time range [2012-02-25 Sat]--[2012-02-27 Mon].
+ ... Some active time range <2012-02-26 Sun>--<2012-02-28 Tue>.
+ ... Some time interval <2012-02-27 Mon 11:23-12:10>.
+ ... ''')
+ >>> root.children[0].rangelist # doctest: +NORMALIZE_WHITESPACE
+ [OrgDate((2012, 2, 25), (2012, 2, 28)),
+ OrgDate((2012, 2, 25), (2012, 2, 27), False),
+ OrgDate((2012, 2, 26), (2012, 2, 28)),
+ OrgDate((2012, 2, 27, 11, 23, 0), (2012, 2, 27, 12, 10, 0))]
+
+ """
+ return self.get_timestamps(active=True, inactive=True, range=True)
+
+ def __str__(self) -> str:
+ return "\n".join(self._lines)
+
+ # todo hmm, not sure if it really belongs here and not to OrgRootNode?
+ def get_file_property_list(self, property: str): # noqa: A002
+ """
+ Return a list of the selected property
+ """
+ vals = self._special_comments.get(property.upper(), None)
+ return [] if vals is None else vals
+
+ def get_file_property(self, property: str): # noqa: A002
+ """
+ Return a single element of the selected property or None if it doesn't exist
+ """
+ vals = self._special_comments.get(property.upper(), None)
+ if vals is None:
+ return None
+ elif len(vals) == 1:
+ return vals[0]
+ else:
+ raise RuntimeError(f'Multiple values for property {property}: {vals}')
+
+
+class OrgRootNode(OrgBaseNode):
"""
- Node to represent a file
+ Node to represent a file. Its body contains all lines before the first
+ headline
See :class:`OrgBaseNode` for other available functions.
-
"""
- # getter
+ @property
+ def heading(self) -> str:
+ return ''
+
+ def _get_tags(self, *, inher: bool = False) -> set[str]: # noqa: ARG002
+ filetags = self.get_file_property_list('FILETAGS')
+ return set(filetags)
@property
- def level(self):
+ def level(self) -> int:
return 0
- def get_parent(self, max_level=None):
+ def get_parent(self, max_level=None): # noqa: ARG002
return None
- # misc
-
- def is_root(self):
+ def is_root(self) -> bool:
return True
+ # parsers
-class OrgNode(OrgBaseNode):
+ def _parse_pre(self):
+ """Call parsers which must be called before tree structuring"""
+ ilines: Iterator[str] = iter(self._lines)
+ ilines = self._iparse_properties(ilines)
+ ilines = self._iparse_timestamps(ilines)
+ self._body_lines = list(ilines)
+ def _iparse_timestamps(self, ilines: Iterator[str]) -> Iterator[str]:
+ self._timestamps = []
+ for line in ilines:
+ self._timestamps.extend(OrgDate.list_from_str(line))
+ yield line
+
+
+class OrgNode(OrgBaseNode):
"""
Node to represent normal org node
@@ -743,21 +1128,20 @@ class OrgNode(OrgBaseNode):
"""
- def __init__(self, *args, **kwds):
- super(OrgNode, self).__init__(*args, **kwds)
- self._heading = None
- self._level = None
- self._tags = None
- self._todo = None
+ def __init__(self, *args, **kwds) -> None:
+ super().__init__(*args, **kwds)
+ # fixme instead of casts, should organize code in such a way that they aren't necessary
+ self._heading = cast(str, None)
+ self._level: int | None = None
+ self._tags = cast(list[str], None)
+ self._todo: Optional[str] = None
self._priority = None
- self._properties = {}
- self._scheduled = OrgDate(None)
- self._deadline = OrgDate(None)
- self._closed = OrgDate(None)
- self._timestamps = []
- self._clocklist = []
- self._body_lines = []
- self._repeated_tasks = []
+ self._scheduled = OrgDateScheduled(None)
+ self._deadline = OrgDateDeadline(None)
+ self._closed = OrgDateClosed(None)
+ self._clocklist: list[OrgDateClock] = []
+ self._body_lines: list[str] = []
+ self._repeated_tasks: list[OrgDateRepeatedTask] = []
# parser
@@ -765,8 +1149,11 @@ def _parse_pre(self):
"""Call parsers which must be called before tree structuring"""
self._parse_heading()
# FIXME: make the following parsers "lazy"
- ilines = iter(self._lines)
- next(ilines) # skip heading
+ ilines: Iterator[str] = iter(self._lines)
+ try:
+ next(ilines) # skip heading
+ except StopIteration:
+ return
ilines = self._iparse_sdc(ilines)
ilines = self._iparse_clock(ilines)
ilines = self._iparse_properties(ilines)
@@ -774,12 +1161,13 @@ def _parse_pre(self):
ilines = self._iparse_timestamps(ilines)
self._body_lines = list(ilines)
- def _parse_heading(self):
+ def _parse_heading(self) -> None:
heading = self._lines[0]
- (heading, self._level) = parse_heading_level(heading)
+ heading_level = parse_heading_level(heading)
+ if heading_level is not None:
+ (heading, self._level) = heading_level
(heading, self._tags) = parse_heading_tags(heading)
- (heading, self._todo) = parse_heading_todos(
- heading, self.env.all_todo_keys)
+ (heading, self._todo) = parse_heading_todos(heading, self.env.all_todo_keys)
(heading, self._priority) = parse_heading_priority(heading)
self._heading = heading
@@ -789,60 +1177,43 @@ def _parse_heading(self):
# If the item returned by the input iterator must be dedicated to
# the parser, do not yield the item or yield it as-is otherwise.
- def _iparse_sdc(self, ilines):
+ def _iparse_sdc(self, ilines: Iterator[str]) -> Iterator[str]:
"""
Parse SCHEDULED, DEADLINE and CLOSED time tamps.
They are assumed be in the first line.
"""
- line = next(ilines)
+ try:
+ line = next(ilines)
+ except StopIteration:
+ return
(self._scheduled, self._deadline, self._closed) = parse_sdc(line)
- if not (self._scheduled or
- self._deadline or
- self._closed):
+ if not (self._scheduled or self._deadline or self._closed):
yield line # when none of them were found
for line in ilines:
yield line
- def _iparse_clock(self, ilines):
- self._clocklist = clocklist = []
+ def _iparse_clock(self, ilines: Iterator[str]) -> Iterator[str]:
+ self._clocklist = []
for line in ilines:
cl = OrgDateClock.from_str(line)
if cl:
- clocklist.append(cl)
+ self._clocklist.append(cl)
else:
yield line
- def _iparse_timestamps(self, ilines):
- self._timestamps = timestamps = []
- timestamps.extend(OrgDate.list_from_str(self._heading))
+ def _iparse_timestamps(self, ilines: Iterator[str]) -> Iterator[str]:
+ self._timestamps = []
+ self._timestamps.extend(OrgDate.list_from_str(self._heading))
for l in ilines:
- timestamps.extend(OrgDate.list_from_str(l))
+ self._timestamps.extend(OrgDate.list_from_str(l))
yield l
- def _iparse_properties(self, ilines):
- self._properties = properties = {}
- in_property_field = False
- for line in ilines:
- if in_property_field:
- if line.find(":END:") >= 0:
- break
- else:
- (key, val) = parse_property(line)
- if key:
- properties.update({key: val})
- elif line.find(":PROPERTIES:") >= 0:
- in_property_field = True
- else:
- yield line
- for line in ilines:
- yield line
-
- def _iparse_repeated_tasks(self, ilines):
- self._repeated_tasks = repeated_tasks = []
+ def _iparse_repeated_tasks(self, ilines: Iterator[str]) -> Iterator[str]:
+ self._repeated_tasks = []
for line in ilines:
match = self._repeated_tasks_re.search(line)
if match:
@@ -851,31 +1222,20 @@ def _iparse_repeated_tasks(self, ilines):
done_state = mdict['done']
todo_state = mdict['todo']
date = OrgDate.from_str(mdict['date'])
- repeated_tasks.append(
- OrgDateRepeatedTask(date.start, todo_state, done_state))
+ self._repeated_tasks.append(OrgDateRepeatedTask(date.start, todo_state, done_state))
else:
yield line
_repeated_tasks_re = re.compile(
r'''
- \s+ - \s+
+ \s*- \s+
State \s+ "(?P [^"]+)" \s+
from \s+ "(?P [^"]+)" \s+
\[ (?P [^\]]+) \]''',
- re.VERBOSE)
-
- # getter
+ re.VERBOSE,
+ )
- @staticmethod
- def _get_text(text, format='plain'):
- if format == 'plain':
- return to_plain_text(text)
- elif format == 'raw':
- return text
- else:
- raise ValueError('format={0} is not supported.'.format(format))
-
- def get_heading(self, format='plain'):
+ def get_heading(self, format: str = 'plain') -> str: # noqa: A002
"""
Return a string of head text without tags and TODO keywords.
@@ -897,29 +1257,13 @@ def get_heading(self, format='plain'):
"""
return self._get_text(self._heading, format)
- def get_body(self, format='plain'):
- """
- Return a string of body text.
-
- See also: :meth:`get_heading`.
-
- """
- return self._get_text(
- '\n'.join(self._body_lines), format) if self._lines else ''
-
@property
- def heading(self):
+ def heading(self) -> str:
"""Alias of ``.get_heading(format='plain')``."""
return self.get_heading()
- @property
- def body(self):
- """Alias of ``.get_body(format='plain')``."""
- return self.get_body()
-
@property
def level(self):
- return self._level
"""
Level attribute of this node. Top level node is level 1.
@@ -928,7 +1272,7 @@ def level(self):
... * Node 1
... ** Node 2
... ''')
- >>> (n1, n2) = root.children
+ >>> (n1, n2) = list(root[1:])
>>> root.level
0
>>> n1.level
@@ -937,9 +1281,10 @@ def level(self):
2
"""
+ return self._level
@property
- def priority(self):
+ def priority(self) -> str | None:
"""
Priority attribute of this node. It is None if undefined.
@@ -956,7 +1301,7 @@ def priority(self):
"""
return self._priority
- def _get_tags(self, inher=False):
+ def _get_tags(self, *, inher: bool = False) -> set[str]:
tags = set(self._tags)
if inher:
parent = self.get_parent()
@@ -965,7 +1310,7 @@ def _get_tags(self, inher=False):
return tags
@property
- def todo(self):
+ def todo(self) -> Optional[str]:
"""
A TODO keyword of this node if exists or None otherwise.
@@ -977,37 +1322,6 @@ def todo(self):
"""
return self._todo
- def get_property(self, key, val=None):
- """
- Return property named ``key`` if exists or ``val`` otherwise.
-
- :arg str key:
- Key of property.
-
- :arg val:
- Default value to return.
-
- """
- return self._properties.get(key, val)
-
- @property
- def properties(self):
- """
- Node properties as a dictionary.
-
- >>> from orgparse import loads
- >>> root = loads('''
- ... * Node
- ... :PROPERTIES:
- ... :SomeProperty: value
- ... :END:
- ... ''')
- >>> root.children[0].properties['SomeProperty']
- 'value'
-
- """
- return self._properties
-
@property
def scheduled(self):
"""
@@ -1080,123 +1394,16 @@ def clock(self):
"""
return self._clocklist
- def get_timestamps(self, active=False, inactive=False,
- range=False, point=False):
- """
- Return a list of timestamps in the body text.
-
- :type active: bool
- :arg active: Include active type timestamps.
- :type inactive: bool
- :arg inactive: Include inactive type timestamps.
- :type range: bool
- :arg range: Include timestamps which has end date.
- :type point: bool
- :arg point: Include timestamps which has no end date.
-
- :rtype: list of :class:`orgparse.date.OrgDate` subclasses
-
-
- Consider the following org node:
-
- >>> from orgparse import loads
- >>> node = loads('''
- ... * Node
- ... CLOSED: [2012-02-26 Sun 21:15] SCHEDULED: <2012-02-26 Sun>
- ... CLOCK: [2012-02-26 Sun 21:10]--[2012-02-26 Sun 21:15] => 0:05
- ... Some inactive timestamp [2012-02-23 Thu] in body text.
- ... Some active timestamp <2012-02-24 Fri> in body text.
- ... Some inactive time range [2012-02-25 Sat]--[2012-02-27 Mon].
- ... Some active time range <2012-02-26 Sun>--<2012-02-28 Tue>.
- ... ''').children[0]
-
- The default flags are all off, so it does not return anything.
-
- >>> node.get_timestamps()
- []
-
- You can fetch appropriate timestamps using keyword arguments.
-
- >>> node.get_timestamps(inactive=True, point=True)
- [OrgDate((2012, 2, 23), None, False)]
- >>> node.get_timestamps(active=True, point=True)
- [OrgDate((2012, 2, 24))]
- >>> node.get_timestamps(inactive=True, range=True)
- [OrgDate((2012, 2, 25), (2012, 2, 27), False)]
- >>> node.get_timestamps(active=True, range=True)
- [OrgDate((2012, 2, 26), (2012, 2, 28))]
-
- This is more complex example. Only active timestamps,
- regardless of range/point type.
-
- >>> node.get_timestamps(active=True, point=True, range=True)
- [OrgDate((2012, 2, 24)), OrgDate((2012, 2, 26), (2012, 2, 28))]
-
- """
- return [
- ts for ts in self._timestamps if
- (((active and ts.is_active()) or
- (inactive and not ts.is_active())) and
- ((range and ts.has_end()) or
- (point and not ts.has_end())))]
-
- @property
- def datelist(self):
- """
- Alias of ``.get_timestamps(active=True, inactive=True, point=True)``.
-
- :rtype: list of :class:`orgparse.date.OrgDate` subclasses
-
- >>> from orgparse import loads
- >>> root = loads('''
- ... * Node with point dates <2012-02-25 Sat>
- ... CLOSED: [2012-02-25 Sat 21:15]
- ... Some inactive timestamp [2012-02-26 Sun] in body text.
- ... Some active timestamp <2012-02-27 Mon> in body text.
- ... ''')
- >>> root.children[0].datelist # doctest: +NORMALIZE_WHITESPACE
- [OrgDate((2012, 2, 25)),
- OrgDate((2012, 2, 26), None, False),
- OrgDate((2012, 2, 27))]
-
- """
- return self.get_timestamps(active=True, inactive=True, point=True)
-
- @property
- def rangelist(self):
- """
- Alias of ``.get_timestamps(active=True, inactive=True, range=True)``.
-
- :rtype: list of :class:`orgparse.date.OrgDate` subclasses
-
- >>> from orgparse import loads
- >>> root = loads('''
- ... * Node with range dates <2012-02-25 Sat>--<2012-02-28 Tue>
- ... CLOCK: [2012-02-26 Sun 21:10]--[2012-02-26 Sun 21:15] => 0:05
- ... Some inactive time range [2012-02-25 Sat]--[2012-02-27 Mon].
- ... Some active time range <2012-02-26 Sun>--<2012-02-28 Tue>.
- ... ''')
- >>> root.children[0].rangelist # doctest: +NORMALIZE_WHITESPACE
- [OrgDate((2012, 2, 25), (2012, 2, 28)),
- OrgDate((2012, 2, 25), (2012, 2, 27), False),
- OrgDate((2012, 2, 26), (2012, 2, 28))]
-
- """
- return self.get_timestamps(active=True, inactive=True, range=True)
-
def has_date(self):
"""
Return ``True`` if it has any kind of timestamp
"""
- return (self.scheduled or
- self.deadline or
- self.datelist or
- self.rangelist)
+ return self.scheduled or self.deadline or self.datelist or self.rangelist
@property
def repeated_tasks(self):
"""
- Get repeated tasks marked DONE in a entry having repeater.
+ Get repeated tasks marked DONE in an entry having repeater.
:rtype: list of :class:`orgparse.date.OrgDateRepeatedTask`
@@ -1240,13 +1447,26 @@ def repeated_tasks(self):
return self._repeated_tasks
-def parse_lines(lines, filename):
- env = OrgEnv(filename=filename)
+def parse_lines(lines: Iterable[str], filename, env=None) -> OrgNode:
+ if not env:
+ env = OrgEnv(filename=filename)
+ elif env.filename != filename:
+ raise ValueError('If env is specified, filename must match')
+
# parse into node of list (environment will be parsed)
- nodelist = list(env.from_chunks(lines_to_chunks(lines)))
+ ch1, ch2 = itertools.tee(lines_to_chunks(lines))
+ linenos = itertools.accumulate(itertools.chain([0], (len(c) for c in ch1)))
+ nodes = env.from_chunks(ch2)
+ nodelist = []
+ for lineno, node in zip(linenos, nodes):
+ lineno += 1 # in text editors lines are 1-indexed
+ node.linenumber = lineno
+ nodelist.append(node)
# parse headings (level, TODO, TAGs, and heading)
nodelist[0]._index = 0
- for (i, node) in enumerate(nodelist[1:], 1): # nodes except root node
+ # parse the root node
+ nodelist[0]._parse_pre()
+ for i, node in enumerate(nodelist[1:], 1): # nodes except root node
node._index = i
node._parse_pre()
env._nodes = nodelist
diff --git a/orgparse/tests/__init__.py b/src/orgparse/py.typed
similarity index 100%
rename from orgparse/tests/__init__.py
rename to src/orgparse/py.typed
diff --git a/orgparse/tests/data/__init__.py b/src/orgparse/tests/__init__.py
similarity index 100%
rename from orgparse/tests/data/__init__.py
rename to src/orgparse/tests/__init__.py
diff --git a/orgparse/tests/data/00_simple.org b/src/orgparse/tests/data/00_simple.org
similarity index 100%
rename from orgparse/tests/data/00_simple.org
rename to src/orgparse/tests/data/00_simple.org
diff --git a/src/orgparse/tests/data/00_simple.py b/src/orgparse/tests/data/00_simple.py
new file mode 100644
index 0000000..23ad86c
--- /dev/null
+++ b/src/orgparse/tests/data/00_simple.py
@@ -0,0 +1,38 @@
+from typing import Any
+
+
+def nodedict(i, level, todo=None, shallow_tags=None, tags=None) -> dict[str, Any]:
+ if tags is None:
+ tags = set()
+ if shallow_tags is None:
+ shallow_tags = set()
+ return {
+ "heading": f"Heading {i}",
+ "level": level,
+ "todo": todo,
+ "shallow_tags": shallow_tags,
+ "tags": tags,
+ }
+
+
+def tags(nums) -> set[str]:
+ return set(map('TAG{0}'.format, nums))
+
+
+data = [
+ nodedict(i, *vals) for (i, vals) in enumerate([ # type: ignore[misc]
+ [1, 'TODO1', tags([1]) , tags(range(1, 2))],
+ [2, 'TODO2', tags([2]) , tags(range(1, 3))],
+ [3, 'TODO3', tags([3]) , tags(range(1, 4))],
+ [4, 'TODO4', tags([4]) , tags(range(1, 5))],
+ [2, None , tags([]) , tags([1]) ],
+ [2, None , tags([]) , tags([1]) ],
+ [1, None , tags([2]) , tags([2]) ],
+ [2, None , tags([2]) , tags([2]) ],
+ [3, None , tags([]) , tags([2]) ],
+ [5, None , tags([3, 4]), tags([2, 3, 4]) ],
+ [4, None , tags([1]) , tags([1, 2]) ],
+ [2, None , tags([]) , tags([2]) ],
+ [1],
+ ])
+] # fmt: skip
diff --git a/orgparse/tests/data/01_attributes.org b/src/orgparse/tests/data/01_attributes.org
similarity index 82%
rename from orgparse/tests/data/01_attributes.org
rename to src/orgparse/tests/data/01_attributes.org
index 9d737d9..99e202b 100644
--- a/orgparse/tests/data/01_attributes.org
+++ b/src/orgparse/tests/data/01_attributes.org
@@ -9,6 +9,7 @@
- <2010-08-16 Mon> DateList
- <2010-08-07 Sat>--<2010-08-08 Sun>
- <2010-08-09 Mon 00:30>--<2010-08-10 Tue 13:20> RangeList
+ - <2019-08-10 Sat 16:30-17:30> TimeRange
* A node without any attributed
* DONE [#A] A node with a lot of attributes
SCHEDULED: <2010-08-06 Fri> DEADLINE: <2010-08-10 Tue> CLOSED: [2010-08-08 Sun 18:00]
@@ -20,3 +21,9 @@
- <2010-08-16 Mon> DateList
- <2010-08-07 Sat>--<2010-08-08 Sun>
- <2010-08-09 Mon 00:30>--<2010-08-10 Tue 13:20> RangeList
+ - <2019-08-10 Sat 16:30-17:30> TimeRange
+* range in deadline
+DEADLINE: <2019-09-06 Fri 10:00--11:20>
+ body
+* node with a second line but no date
+body
diff --git a/src/orgparse/tests/data/01_attributes.py b/src/orgparse/tests/data/01_attributes.py
new file mode 100644
index 0000000..467df02
--- /dev/null
+++ b/src/orgparse/tests/data/01_attributes.py
@@ -0,0 +1,76 @@
+from typing import Any
+
+from orgparse.date import (
+ OrgDate,
+ OrgDateClock,
+ OrgDateClosed,
+ OrgDateDeadline,
+ OrgDateScheduled,
+)
+
+Raw = dict[str, Any]
+
+node1: Raw = {
+ "heading": "A node with a lot of attributes",
+ "priority": 'A',
+ "scheduled": OrgDateScheduled((2010, 8, 6)),
+ "deadline": OrgDateDeadline((2010, 8, 10)),
+ "closed": OrgDateClosed((2010, 8, 8, 18, 0)),
+ "clock": [
+ OrgDateClock((2010, 8, 8, 17, 40), (2010, 8, 8, 17, 50), 10),
+ OrgDateClock((2010, 8, 8, 17, 00), (2010, 8, 8, 17, 30), 30),
+ ],
+ "properties": {"Effort": 70},
+ "datelist": [OrgDate((2010, 8, 16))],
+ "rangelist": [
+ OrgDate((2010, 8, 7), (2010, 8, 8)),
+ OrgDate((2010, 8, 9, 0, 30), (2010, 8, 10, 13, 20)),
+ OrgDate((2019, 8, 10, 16, 30, 0), (2019, 8, 10, 17, 30, 0)),
+ ],
+ "body": """\
+ - <2010-08-16 Mon> DateList
+ - <2010-08-07 Sat>--<2010-08-08 Sun>
+ - <2010-08-09 Mon 00:30>--<2010-08-10 Tue 13:20> RangeList
+ - <2019-08-10 Sat 16:30-17:30> TimeRange""",
+}
+
+node2: Raw = {
+ "heading": "A node without any attributed",
+ "priority": None,
+ "scheduled": OrgDateScheduled(None),
+ "deadline": OrgDateDeadline(None),
+ "closed": OrgDateClosed(None),
+ "clock": [],
+ "properties": {},
+ "datelist": [],
+ "rangelist": [],
+ "body": "",
+}
+
+node3: Raw = {
+ "heading": "range in deadline",
+ "priority": None,
+ "scheduled": OrgDateScheduled(None),
+ "deadline": OrgDateDeadline((2019, 9, 6, 10, 0), (2019, 9, 6, 11, 20)),
+ "closed": OrgDateClosed(None),
+ "clock": [],
+ "properties": {},
+ "datelist": [],
+ "rangelist": [],
+ "body": " body",
+}
+
+node4: Raw = {
+ "heading": "node with a second line but no date",
+ "priority": None,
+ "scheduled": OrgDateScheduled(None),
+ "deadline": OrgDateDeadline(None),
+ "closed": OrgDateClosed(None),
+ "clock": [],
+ "properties": {},
+ "datelist": [],
+ "rangelist": [],
+ "body": "body",
+}
+
+data = [node1, node2, node1, node3, node4]
diff --git a/orgparse/tests/data/02_tree_struct.org b/src/orgparse/tests/data/02_tree_struct.org
similarity index 100%
rename from orgparse/tests/data/02_tree_struct.org
rename to src/orgparse/tests/data/02_tree_struct.org
diff --git a/orgparse/tests/data/02_tree_struct.py b/src/orgparse/tests/data/02_tree_struct.py
similarity index 66%
rename from orgparse/tests/data/02_tree_struct.py
rename to src/orgparse/tests/data/02_tree_struct.py
index 17e876e..86b6314 100644
--- a/orgparse/tests/data/02_tree_struct.py
+++ b/src/orgparse/tests/data/02_tree_struct.py
@@ -1,8 +1,15 @@
-def nodedict(parent, children=[], previous=None, next=None):
- return dict(parent_heading=parent,
- children_heading=children,
- previous_same_level_heading=previous,
- next_same_level_heading=next)
+from typing import Any
+
+
+def nodedict(parent, children=None, previous=None, next_=None) -> dict[str, Any]:
+ if children is None:
+ children = []
+ return {
+ 'parent_heading': parent,
+ 'children_heading': children,
+ 'previous_same_level_heading': previous,
+ 'next_same_level_heading': next_,
+ }
data = [nodedict(*args) for args in [
@@ -36,4 +43,6 @@ def nodedict(parent, children=[], previous=None, next=None):
('G6-H2',),
('G6-H2',),
('G6-H1', [], 'G6-H2'),
-]]
+ # G7
+ (None, [], 'G6-H1'),
+]] # fmt: skip
diff --git a/orgparse/tests/data/03_repeated_tasks.org b/src/orgparse/tests/data/03_repeated_tasks.org
similarity index 100%
rename from orgparse/tests/data/03_repeated_tasks.org
rename to src/orgparse/tests/data/03_repeated_tasks.org
diff --git a/orgparse/tests/data/03_repeated_tasks.py b/src/orgparse/tests/data/03_repeated_tasks.py
similarity index 50%
rename from orgparse/tests/data/03_repeated_tasks.py
rename to src/orgparse/tests/data/03_repeated_tasks.py
index 18cfe12..17336e0 100644
--- a/orgparse/tests/data/03_repeated_tasks.py
+++ b/src/orgparse/tests/data/03_repeated_tasks.py
@@ -1,13 +1,12 @@
-from orgparse.date import OrgDateRepeatedTask, OrgDateDeadline
+from orgparse.date import OrgDateDeadline, OrgDateRepeatedTask
-
-data = [dict(
- heading='Pay the rent',
- todo='TODO',
- deadline=OrgDateDeadline((2005, 10, 1)),
- repeated_tasks=[
+data = [{
+ 'heading': 'Pay the rent',
+ 'todo': 'TODO',
+ 'deadline': OrgDateDeadline((2005, 10, 1)),
+ 'repeated_tasks': [
OrgDateRepeatedTask((2005, 9, 1, 16, 10, 0), 'TODO', 'DONE'),
OrgDateRepeatedTask((2005, 8, 1, 19, 44, 0), 'TODO', 'DONE'),
OrgDateRepeatedTask((2005, 7, 1, 17, 27, 0), 'TODO', 'DONE'),
]
-)]
+}] # fmt: skip
diff --git a/orgparse/tests/data/04_logbook.org b/src/orgparse/tests/data/04_logbook.org
similarity index 88%
rename from orgparse/tests/data/04_logbook.org
rename to src/orgparse/tests/data/04_logbook.org
index 9155470..e89ec26 100644
--- a/orgparse/tests/data/04_logbook.org
+++ b/src/orgparse/tests/data/04_logbook.org
@@ -1,5 +1,6 @@
* LOGBOOK drawer test
:LOGBOOK:
+ CLOCK: [2012-10-26 Fri 16:01]
CLOCK: [2012-10-26 Fri 14:50]--[2012-10-26 Fri 15:00] => 0:10
CLOCK: [2012-10-26 Fri 14:30]--[2012-10-26 Fri 14:40] => 0:10
CLOCK: [2012-10-26 Fri 14:10]--[2012-10-26 Fri 14:20] => 0:10
diff --git a/orgparse/tests/data/04_logbook.py b/src/orgparse/tests/data/04_logbook.py
similarity index 67%
rename from orgparse/tests/data/04_logbook.py
rename to src/orgparse/tests/data/04_logbook.py
index 4c05a15..2443683 100644
--- a/orgparse/tests/data/04_logbook.py
+++ b/src/orgparse/tests/data/04_logbook.py
@@ -1,10 +1,11 @@
from orgparse.date import OrgDateClock
-data = [dict(
- heading='LOGBOOK drawer test',
- clock=[
+data = [{
+ 'heading': 'LOGBOOK drawer test',
+ 'clock': [
+ OrgDateClock((2012, 10, 26, 16, 1)),
OrgDateClock((2012, 10, 26, 14, 50), (2012, 10, 26, 15, 00)),
OrgDateClock((2012, 10, 26, 14, 30), (2012, 10, 26, 14, 40)),
OrgDateClock((2012, 10, 26, 14, 10), (2012, 10, 26, 14, 20)),
]
-)]
+}] # fmt: skip
diff --git a/orgparse/tests/data/05_tags.org b/src/orgparse/tests/data/05_tags.org
similarity index 88%
rename from orgparse/tests/data/05_tags.org
rename to src/orgparse/tests/data/05_tags.org
index 9e6ca2a..651d7e0 100644
--- a/orgparse/tests/data/05_tags.org
+++ b/src/orgparse/tests/data/05_tags.org
@@ -6,3 +6,4 @@
* Node 5 :@_:
* Node 6 :_tag_:
* Heading: :with:colon: :tag:
+* unicode :ёж:tag:háček:
diff --git a/orgparse/tests/data/05_tags.py b/src/orgparse/tests/data/05_tags.py
similarity index 50%
rename from orgparse/tests/data/05_tags.py
rename to src/orgparse/tests/data/05_tags.py
index 85a4db2..19447f4 100644
--- a/orgparse/tests/data/05_tags.py
+++ b/src/orgparse/tests/data/05_tags.py
@@ -1,8 +1,8 @@
def nodedict(i, tags):
- return dict(
- heading="Node {0}".format(i),
- tags=set(tags),
- )
+ return {
+ "heading": f"Node {i}",
+ "tags": set(tags),
+ }
data = [
@@ -15,5 +15,7 @@ def nodedict(i, tags):
[["@_"]],
[["_tag_"]],
])] + [
- dict(heading='Heading: :with:colon:', tags=set(["tag"])),
- ]
+ {"heading": 'Heading: :with:colon:', "tags": {"tag"}},
+ ] + [
+ {"heading": 'unicode', "tags": {'ёж', 'tag', 'háček'}},
+ ] # fmt: skip
diff --git a/orgparse/utils/__init__.py b/src/orgparse/tests/data/__init__.py
similarity index 100%
rename from orgparse/utils/__init__.py
rename to src/orgparse/tests/data/__init__.py
diff --git a/src/orgparse/tests/test_data.py b/src/orgparse/tests/test_data.py
new file mode 100644
index 0000000..c271273
--- /dev/null
+++ b/src/orgparse/tests/test_data.py
@@ -0,0 +1,157 @@
+import pickle
+from collections.abc import Iterator
+from pathlib import Path
+
+import pytest
+
+from .. import load, loads
+
+DATADIR = Path(__file__).parent / 'data'
+
+
+def load_data(path: Path):
+ """Load data from python file"""
+ ns = {} # type: ignore[var-annotated]
+ # read_bytes() and compile hackery to avoid encoding issues (e.g. see 05_tags)
+ exec(compile(path.read_bytes(), path, 'exec'), ns)
+ return ns['data']
+
+
+def value_from_data_key(node, key):
+ """
+ Helper function for check_data. Get value from Orgnode by key.
+ """
+ if key == 'tags_inher':
+ return node.tags
+ elif key == 'children_heading':
+ return [c.heading for c in node.children]
+ elif key in (
+ 'parent_heading',
+ 'previous_same_level_heading',
+ 'next_same_level_heading',
+ ):
+ othernode = getattr(node, key.rsplit('_', 1)[0])
+ if othernode and not othernode.is_root():
+ return othernode.heading
+ else:
+ return None
+ else:
+ return getattr(node, key)
+
+
+def data_path(dataname: str, ext: str) -> Path:
+ return DATADIR / f'{dataname}.{ext}'
+
+
+def get_datanames() -> Iterator[str]:
+ for oname in sorted(DATADIR.glob('*.org')):
+ yield oname.stem
+
+
+@pytest.mark.parametrize('dataname', get_datanames())
+def test_data(dataname):
+ """
+ Compare parsed data from 'data/*.org' and its correct answer 'data/*.py'
+ """
+ oname = data_path(dataname, "org")
+ data = load_data(data_path(dataname, "py"))
+ root = load(oname)
+
+ for i, (node, kwds) in enumerate(zip(root[1:], data)):
+ for key in kwds:
+ val = value_from_data_key(node, key)
+ assert kwds[key] == val, (
+ f'check value of {i}-th node of key "{key}" from "{dataname}".\n\nParsed:\n{val}\n\nReal:\n{kwds[key]}'
+ )
+ assert type(kwds[key]) == type(val), ( # noqa: E721
+ f'check type of {i}-th node of key "{key}" from "{dataname}".\n\nParsed:\n{type(val)}\n\nReal:\n{type(kwds[key])}'
+ )
+
+ assert root.env.filename == str(oname)
+
+
+@pytest.mark.parametrize('dataname', get_datanames())
+def test_picklable(dataname):
+ oname = data_path(dataname, "org")
+ root = load(oname)
+ pickle.dumps(root)
+
+
+def test_iter_node():
+ root = loads("""
+* H1
+** H2
+*** H3
+* H4
+** H5
+""")
+ node = root[1]
+ assert node.heading == 'H1'
+
+ by_iter = [n.heading for n in node]
+ assert by_iter == ['H1', 'H2', 'H3']
+
+
+def test_commented_headings_do_not_appear_as_children():
+ root = loads("""\
+* H1
+#** H2
+** H3
+#* H4
+#** H5
+* H6
+""")
+ assert root.linenumber == 1
+ top_level = root.children
+ assert len(top_level) == 2
+
+ h1 = top_level[0]
+ assert h1.heading == "H1"
+ assert h1.get_body() == "#** H2"
+ assert h1.linenumber == 1
+
+ [h3] = h1.children
+ assert h3.heading == "H3"
+ assert h3.get_body() == "#* H4\n#** H5"
+ assert h3.linenumber == 3
+
+ h6 = top_level[1]
+ assert h6.heading == "H6"
+ assert len(h6.children) == 0
+ assert h6.linenumber == 6
+
+
+def test_commented_clock_entries_are_ignored_by_node_clock():
+ root = loads("""\
+* Heading
+# * Floss
+# SCHEDULED: <2019-06-22 Sat 08:30 .+1w>
+# :LOGBOOK:
+# CLOCK: [2019-06-04 Tue 16:00]--[2019-06-04 Tue 17:00] => 1:00
+# :END:
+""")
+ [node] = root.children[0]
+ assert node.heading == "Heading"
+ assert node.clock == []
+
+
+def test_commented_scheduled_marker_is_ignored_by_node_scheduled():
+ root = loads("""\
+* Heading
+# SCHEDULED: <2019-06-22 Sat 08:30 .+1w>
+""")
+ [node] = root.children[0]
+ assert node.heading == "Heading"
+ assert node.scheduled.start is None
+
+
+def test_commented_property_is_ignored_by_node_get_property():
+ root = loads("""\
+* Heading
+# :PROPERTIES:
+# :PROPER-TEA: backup
+# :END:
+""")
+ [node] = root.children[0]
+ assert node.heading == "Heading"
+ assert node.get_property("PROPER-TEA") is None
diff --git a/src/orgparse/tests/test_date.py b/src/orgparse/tests/test_date.py
new file mode 100644
index 0000000..9764f97
--- /dev/null
+++ b/src/orgparse/tests/test_date.py
@@ -0,0 +1,48 @@
+import datetime
+
+from orgparse.date import (
+ OrgDate,
+ OrgDateClock,
+ OrgDateClosed,
+ OrgDateDeadline,
+ OrgDateScheduled,
+)
+
+
+def test_date_as_string() -> None:
+ testdate = datetime.date(2021, 9, 3)
+ testdate2 = datetime.date(2021, 9, 5)
+ testdatetime = datetime.datetime(2021, 9, 3, 16, 19, 13)
+ testdatetime2 = datetime.datetime(2021, 9, 3, 17, 0, 1)
+ testdatetime_nextday = datetime.datetime(2021, 9, 4, 0, 2, 1)
+
+ assert str(OrgDate(testdate)) == "<2021-09-03 Fri>"
+ assert str(OrgDate(testdatetime)) == "<2021-09-03 Fri 16:19>"
+ assert str(OrgDate(testdate, active=False)) == "[2021-09-03 Fri]"
+ assert str(OrgDate(testdatetime, active=False)) == "[2021-09-03 Fri 16:19]"
+
+ assert str(OrgDate(testdate, testdate2)) == "<2021-09-03 Fri>--<2021-09-05 Sun>"
+ assert str(OrgDate(testdate, testdate2)) == "<2021-09-03 Fri>--<2021-09-05 Sun>"
+ assert str(OrgDate(testdatetime, testdatetime2)) == "<2021-09-03 Fri 16:19--17:00>"
+ assert str(OrgDate(testdate, testdate2, active=False)) == "[2021-09-03 Fri]--[2021-09-05 Sun]"
+ assert str(OrgDate(testdate, testdate2, active=False)) == "[2021-09-03 Fri]--[2021-09-05 Sun]"
+ assert str(OrgDate(testdatetime, testdatetime2, active=False)) == "[2021-09-03 Fri 16:19--17:00]"
+
+ assert str(OrgDateScheduled(testdate)) == "<2021-09-03 Fri>"
+ assert str(OrgDateScheduled(testdatetime)) == "<2021-09-03 Fri 16:19>"
+ assert str(OrgDateDeadline(testdate)) == "<2021-09-03 Fri>"
+ assert str(OrgDateDeadline(testdatetime)) == "<2021-09-03 Fri 16:19>"
+ assert str(OrgDateClosed(testdate)) == "[2021-09-03 Fri]"
+ assert str(OrgDateClosed(testdatetime)) == "[2021-09-03 Fri 16:19]"
+
+ assert str(OrgDateClock(testdatetime, testdatetime2)) == "[2021-09-03 Fri 16:19]--[2021-09-03 Fri 17:00]"
+ assert str(OrgDateClock(testdatetime, testdatetime_nextday)) == "[2021-09-03 Fri 16:19]--[2021-09-04 Sat 00:02]"
+ assert str(OrgDateClock(testdatetime)) == "[2021-09-03 Fri 16:19]"
+
+
+def test_date_as_datetime() -> None:
+ testdate = (2021, 9, 3)
+ testdatetime = (2021, 9, 3, 16, 19, 13)
+
+ assert OrgDate._as_datetime(datetime.date(*testdate)) == datetime.datetime(*testdate, 0, 0, 0)
+ assert OrgDate._as_datetime(datetime.datetime(*testdatetime)) == datetime.datetime(*testdatetime)
diff --git a/src/orgparse/tests/test_hugedata.py b/src/orgparse/tests/test_hugedata.py
new file mode 100644
index 0000000..b97a178
--- /dev/null
+++ b/src/orgparse/tests/test_hugedata.py
@@ -0,0 +1,26 @@
+import pickle
+
+from .. import loadi
+
+
+def generate_org_lines(num_top_nodes, depth=3, nodes_per_level=1, _level=1):
+ if depth == 0:
+ return
+ for i in range(num_top_nodes):
+ yield ("*" * _level) + f' {i}-th heading of level {_level}'
+ yield from generate_org_lines(nodes_per_level, depth - 1, nodes_per_level, _level + 1)
+
+
+def num_generate_org_lines(num_top_nodes, depth=3, nodes_per_level=1):
+ if depth == 0:
+ return 0
+ return num_top_nodes * (1 + num_generate_org_lines(nodes_per_level, depth - 1, nodes_per_level))
+
+
+def test_picklable() -> None:
+ num = 1000
+ depth = 3
+ nodes_per_level = 1
+ root = loadi(generate_org_lines(num, depth, nodes_per_level))
+ assert sum(1 for _ in root) == num_generate_org_lines(num, depth, nodes_per_level) + 1
+ pickle.dumps(root) # should not fail
diff --git a/src/orgparse/tests/test_misc.py b/src/orgparse/tests/test_misc.py
new file mode 100644
index 0000000..bb1382e
--- /dev/null
+++ b/src/orgparse/tests/test_misc.py
@@ -0,0 +1,304 @@
+import io
+
+import pytest
+
+from orgparse.date import OrgDate
+
+from .. import load, loads
+from ..node import OrgEnv
+
+
+def test_empty_heading() -> None:
+ root = loads('''
+* TODO :sometag:
+ has no heading but still a todo?
+ it's a bit unclear, but seems to be highligted by emacs..
+''')
+ [h] = root.children
+ assert h.todo == 'TODO'
+ assert h.heading == ''
+ assert h.tags == {'sometag'}
+
+
+def test_root() -> None:
+ root = loads(
+ '''
+#+STARTUP: hidestars
+Whatever
+# comment
+* heading 1
+ '''.strip()
+ )
+ assert len(root.children) == 1
+ # todo not sure if should strip special comments??
+ assert root.body.endswith('Whatever\n# comment')
+ assert root.heading == ''
+
+
+def test_stars():
+ # https://github.com/karlicoss/orgparse/issues/7#issuecomment-533732660
+ root = loads("""
+* Heading with text (A)
+
+The following line is not a heading, because it begins with a
+star but has no spaces afterward, just a newline:
+
+*
+
+** Subheading with text (A1)
+
+*this_is_just*
+
+ *some_bold_text*
+
+This subheading is a child of (A).
+
+The next heading has no text, but it does have a space after
+the star, so it's a heading:
+
+*
+
+This text is under the "anonymous" heading above, which would be (B).
+
+** Subheading with text (B1)
+
+This subheading is a child of the "anonymous" heading (B), not of heading (A).
+ """) # noqa: W291
+ [h1, h2] = root.children
+ assert h1.heading == 'Heading with text (A)'
+ assert h2.heading == ''
+
+
+def test_parse_custom_todo_keys():
+ todo_keys = ['TODO', 'CUSTOM1', 'ANOTHER_KEYWORD']
+ done_keys = ['DONE', 'A']
+ filename = '' # default for loads
+ content = """
+* TODO Heading with a default todo keyword
+
+* DONE Heading with a default done keyword
+
+* CUSTOM1 Heading with a custom todo keyword
+
+* ANOTHER_KEYWORD Heading with a long custom todo keyword
+
+* A Heading with a short custom done keyword
+ """
+
+ env = OrgEnv(todos=todo_keys, dones=done_keys, filename=filename)
+ root = loads(content, env=env)
+
+ assert root.env.all_todo_keys == ['TODO', 'CUSTOM1', 'ANOTHER_KEYWORD', 'DONE', 'A']
+ assert len(root.children) == 5
+ assert root.children[0].todo == 'TODO'
+ assert root.children[1].todo == 'DONE'
+ assert root.children[2].todo == 'CUSTOM1'
+ assert root.children[3].todo == 'ANOTHER_KEYWORD'
+ assert root.children[4].todo == 'A'
+
+
+def test_add_custom_todo_keys():
+ todo_keys = ['CUSTOM_TODO']
+ done_keys = ['CUSTOM_DONE']
+ filename = '' # default for loads
+ content = """#+TODO: COMMENT_TODO | COMMENT_DONE
+ """
+
+ env = OrgEnv(filename=filename)
+ env.add_todo_keys(todos=todo_keys, dones=done_keys)
+
+ # check that only the custom keys are know before parsing
+ assert env.all_todo_keys == ['CUSTOM_TODO', 'CUSTOM_DONE']
+
+ # after parsing, all keys are set
+ root = loads(content, filename, env)
+ assert root.env.all_todo_keys == ['CUSTOM_TODO', 'COMMENT_TODO', 'CUSTOM_DONE', 'COMMENT_DONE']
+
+
+def test_get_file_property() -> None:
+ content = """#+TITLE: Test: title
+ * Node 1
+ test 1
+ * Node 2
+ test 2
+ """
+
+ # after parsing, all keys are set
+ root = loads(content)
+ assert root.get_file_property('Nosuchproperty') is None
+ assert root.get_file_property_list('TITLE') == ['Test: title']
+ # also it's case insensitive
+ assert root.get_file_property('title') == 'Test: title'
+ assert root.get_file_property_list('Nosuchproperty') == []
+
+
+def test_get_file_property_multivalued() -> None:
+ content = """ #+TITLE: Test
+ #+OTHER: Test title
+ #+title: alternate title
+
+ * Node 1
+ test 1
+ * Node 2
+ test 2
+ """
+
+ # after parsing, all keys are set
+ root = loads(content)
+
+ assert root.get_file_property_list('TITLE') == ['Test', 'alternate title']
+ with pytest.raises(RuntimeError):
+ # raises because there are multiple of them
+ root.get_file_property('TITLE')
+
+
+def test_filetags_are_tags() -> None:
+ content = '''
+#+FILETAGS: :f1:f2:
+
+* heading :h1:
+** child :f2:
+ '''.strip()
+ root = loads(content)
+ # breakpoint()
+ assert root.tags == {'f1', 'f2'}
+ child = root.children[0].children[0]
+ assert child.tags == {'f1', 'f2', 'h1'}
+
+
+def test_load_filelike() -> None:
+ stream = io.StringIO('''
+* heading1
+* heading 2
+''')
+ root = load(stream)
+ assert len(root.children) == 2
+ assert root.env.filename == ''
+
+
+def test_level_0_properties() -> None:
+ content = '''
+foo bar
+
+:PROPERTIES:
+:PROP-FOO: Bar
+:PROP-BAR: Bar bar
+:END:
+
+* heading :h1:
+:PROPERTIES:
+:HEADING-PROP: foo
+:END:
+** child :f2:
+ '''.strip()
+ root = loads(content)
+ assert root.get_property('PROP-FOO') == 'Bar'
+ assert root.get_property('PROP-BAR') == 'Bar bar'
+ assert root.get_property('PROP-INVALID') is None
+ assert root.get_property('HEADING-PROP') is None
+ assert root.children[0].get_property('HEADING-PROP') == 'foo'
+
+
+def test_level_0_timestamps() -> None:
+ content = '''
+foo bar
+
+ - <2010-08-16 Mon> DateList
+ - <2010-08-07 Sat>--<2010-08-08 Sun>
+ - <2010-08-09 Mon 00:30>--<2010-08-10 Tue 13:20> RangeList
+ - <2019-08-10 Sat 16:30-17:30> TimeRange"
+
+* heading :h1:
+** child :f2:
+ '''.strip()
+ root = loads(content)
+ assert root.datelist == [OrgDate((2010, 8, 16))]
+ assert root.rangelist == [
+ OrgDate((2010, 8, 7), (2010, 8, 8)),
+ OrgDate((2010, 8, 9, 0, 30), (2010, 8, 10, 13, 20)),
+ OrgDate((2019, 8, 10, 16, 30, 0), (2019, 8, 10, 17, 30, 0)),
+ ]
+
+
+def test_date_with_cookies() -> None:
+ testcases = [
+ ('<2010-06-21 Mon +1y>',
+ "OrgDate((2010, 6, 21), None, True, ('+', 1, 'y'))"),
+ ('<2005-10-01 Sat +1m>',
+ "OrgDate((2005, 10, 1), None, True, ('+', 1, 'm'))"),
+ ('<2005-10-01 Sat +1m -3d>',
+ "OrgDate((2005, 10, 1), None, True, ('+', 1, 'm'), ('-', 3, 'd'))"),
+ ('<2005-10-01 Sat -3d>',
+ "OrgDate((2005, 10, 1), None, True, None, ('-', 3, 'd'))"),
+ ('<2008-02-10 Sun ++1w>',
+ "OrgDate((2008, 2, 10), None, True, ('++', 1, 'w'))"),
+ ('<2008-02-08 Fri 20:00 ++1d>',
+ "OrgDate((2008, 2, 8, 20, 0, 0), None, True, ('++', 1, 'd'))"),
+ ('<2019-04-05 Fri 08:00 .+1h>',
+ "OrgDate((2019, 4, 5, 8, 0, 0), None, True, ('.+', 1, 'h'))"),
+ ('[2019-04-05 Fri 08:00 .+1h]',
+ "OrgDate((2019, 4, 5, 8, 0, 0), None, False, ('.+', 1, 'h'))"),
+ ('<2007-05-16 Wed 12:30 +1w>',
+ "OrgDate((2007, 5, 16, 12, 30, 0), None, True, ('+', 1, 'w'))"),
+ ] # fmt: skip
+ for inp, expected in testcases:
+ root = loads(inp)
+ output = root[0].datelist[0]
+ assert str(output) == inp
+ assert repr(output) == expected
+ testcases = [
+ ('<2006-11-02 Thu 20:00-22:00 +1w>',
+ "OrgDate((2006, 11, 2, 20, 0, 0), (2006, 11, 2, 22, 0, 0), True, ('+', 1, 'w'))"),
+ ('<2006-11-02 Thu 20:00--22:00 +1w>',
+ "OrgDate((2006, 11, 2, 20, 0, 0), (2006, 11, 2, 22, 0, 0), True, ('+', 1, 'w'))"),
+ ] # fmt: skip
+ for inp, expected in testcases:
+ root = loads(inp)
+ output = root[0].rangelist[0]
+ assert str(output) == "<2006-11-02 Thu 20:00--22:00 +1w>"
+ assert repr(output) == expected
+ # DEADLINE and SCHEDULED
+ testcases2 = [
+ ('* TODO Pay the rent\nDEADLINE: <2005-10-01 Sat +1m>',
+ "<2005-10-01 Sat +1m>",
+ "OrgDateDeadline((2005, 10, 1), None, True, ('+', 1, 'm'))"),
+ ('* TODO Pay the rent\nDEADLINE: <2005-10-01 Sat +1m -3d>',
+ "<2005-10-01 Sat +1m -3d>",
+ "OrgDateDeadline((2005, 10, 1), None, True, ('+', 1, 'm'), ('-', 3, 'd'))"),
+ ('* TODO Pay the rent\nDEADLINE: <2005-10-01 Sat -3d>',
+ "<2005-10-01 Sat -3d>",
+ "OrgDateDeadline((2005, 10, 1), None, True, None, ('-', 3, 'd'))"),
+ ('* TODO Pay the rent\nDEADLINE: <2005-10-01 Sat ++1m>',
+ "<2005-10-01 Sat ++1m>",
+ "OrgDateDeadline((2005, 10, 1), None, True, ('++', 1, 'm'))"),
+ ('* TODO Pay the rent\nDEADLINE: <2005-10-01 Sat .+1m>',
+ "<2005-10-01 Sat .+1m>",
+ "OrgDateDeadline((2005, 10, 1), None, True, ('.+', 1, 'm'))"),
+ ] # fmt: skip
+ for inp, expected_str, expected_repr in testcases2:
+ root = loads(inp)
+ output = root[1].deadline
+ assert str(output) == expected_str
+ assert repr(output) == expected_repr
+ testcases2 = [
+ ('* TODO Pay the rent\nSCHEDULED: <2005-10-01 Sat +1m>',
+ "<2005-10-01 Sat +1m>",
+ "OrgDateScheduled((2005, 10, 1), None, True, ('+', 1, 'm'))"),
+ ('* TODO Pay the rent\nSCHEDULED: <2005-10-01 Sat +1m -3d>',
+ "<2005-10-01 Sat +1m -3d>",
+ "OrgDateScheduled((2005, 10, 1), None, True, ('+', 1, 'm'), ('-', 3, 'd'))"),
+ ('* TODO Pay the rent\nSCHEDULED: <2005-10-01 Sat -3d>',
+ "<2005-10-01 Sat -3d>",
+ "OrgDateScheduled((2005, 10, 1), None, True, None, ('-', 3, 'd'))"),
+ ('* TODO Pay the rent\nSCHEDULED: <2005-10-01 Sat ++1m>',
+ "<2005-10-01 Sat ++1m>",
+ "OrgDateScheduled((2005, 10, 1), None, True, ('++', 1, 'm'))"),
+ ('* TODO Pay the rent\nSCHEDULED: <2005-10-01 Sat .+1m>',
+ "<2005-10-01 Sat .+1m>",
+ "OrgDateScheduled((2005, 10, 1), None, True, ('.+', 1, 'm'))"),
+ ] # fmt: skip
+ for inp, expected_str, expected_repr in testcases2:
+ root = loads(inp)
+ output = root[1].scheduled
+ assert str(output) == expected_str
+ assert repr(output) == expected_repr
diff --git a/src/orgparse/tests/test_rich.py b/src/orgparse/tests/test_rich.py
new file mode 100644
index 0000000..5171bb0
--- /dev/null
+++ b/src/orgparse/tests/test_rich.py
@@ -0,0 +1,89 @@
+'''
+Tests for rich formatting: tables etc.
+'''
+
+import pytest
+
+from .. import loads
+from ..extra import Table
+
+
+def test_table() -> None:
+ root = loads('''
+| | | |
+| | "heading" | |
+| | | |
+|-------+-----------+-----|
+| reiwf | fef | |
+|-------+-----------+-----|
+|-------+-----------+-----|
+| aba | caba | 123 |
+| yeah | | X |
+
+ |------------------------+-------|
+ | when | count |
+ | datetime | int |
+ |------------------------+-------|
+ | | -1 |
+ | [2020-11-05 Thu 23:44] | |
+ | [2020-11-06 Fri 01:00] | 1 |
+ |------------------------+-------|
+
+some irrelevant text
+
+| simple |
+|--------|
+| value1 |
+| value2 |
+ ''')
+
+ [_gap1, t1, _gap2, t2, _gap3, t3, _gap4] = root.body_rich
+
+ t1 = Table(root._lines[1:10])
+ t2 = Table(root._lines[11:19])
+ t3 = Table(root._lines[22:26])
+
+ assert ilen(t1.blocks) == 4
+ assert list(t1.blocks)[2] == []
+ assert ilen(t1.rows) == 6
+
+ with pytest.raises(RuntimeError):
+ list(t1.as_dicts) # not sure what should it be
+
+ assert ilen(t2.blocks) == 2
+ assert ilen(t2.rows) == 5
+ assert list(t2.rows)[3] == ['[2020-11-05 Thu 23:44]', '']
+
+ assert ilen(t3.blocks) == 2
+ assert list(t3.rows) == [['simple'], ['value1'], ['value2']]
+ assert t3.as_dicts.columns == ['simple']
+ assert list(t3.as_dicts) == [{'simple': 'value1'}, {'simple': 'value2'}]
+
+
+def test_table_2() -> None:
+ root = loads('''
+* item
+
+#+tblname: something
+| date | value | comment |
+|----------------------+-------+-------------------------------|
+| 14.04.17 | 11 | aaaa |
+| May 26 2017 08:00 | 12 | what + about + pluses? |
+| May 26 09:00 - 10:00 | 13 | time is |
+
+ some comment
+
+#+BEGIN_SRC python :var fname="plot.png" :var table=something :results file
+fig.savefig(fname)
+return fname
+#+END_SRC
+
+#+RESULTS:
+[[file:plot.png]]
+''')
+ [_, t, _] = root.children[0].body_rich
+ assert ilen(t.as_dicts) == 3
+
+
+def ilen(x) -> int:
+ return len(list(x))
diff --git a/tox.ini b/tox.ini
index 212aac4..a31cbab 100644
--- a/tox.ini
+++ b/tox.ini
@@ -1,7 +1,67 @@
[tox]
-envlist = py26, py27, py32
+minversion = 3.21
+# relies on the correct version of Python installed
+envlist = ruff,tests,mypy,ty
+# https://github.com/tox-dev/tox/issues/20#issuecomment-247788333
+# hack to prevent .tox from crapping to the project directory
+toxworkdir = {env:TOXWORKDIR_BASE:}{toxinidir}/.tox
+
[testenv]
-deps =
- nose
-commands = nosetests --with-doctest orgparse
-changedir = {envtmpdir}
+# TODO how to get package name from setuptools?
+package_name = "orgparse"
+pass_env =
+# useful for tests to know they are running under ci
+ CI
+ CI_*
+# respect user's cache dirs to prevent tox from crapping into project dir
+ PYTHONPYCACHEPREFIX
+ MYPY_CACHE_DIR
+ RUFF_CACHE_DIR
+
+set_env =
+# do not add current working directory to pythonpath
+# generally this is more robust and safer, prevents weird issues later on
+ PYTHONSAFEPATH=1
+
+# default is 'editable', in which tox builds wheel first for some reason? not sure if makes much sense
+package = uv-editable
+
+
+[testenv:ruff]
+skip_install = true
+dependency_groups = testing
+commands =
+ {envpython} -m ruff check \
+ {posargs}
+
+
+[testenv:tests]
+dependency_groups = testing
+commands =
+ # posargs allow test filtering, e.g. tox ... -- -k test_name
+ {envpython} -m pytest \
+ --pyargs {[testenv]package_name} \
+ {posargs}
+
+
+[testenv:mypy]
+dependency_groups = testing
+commands =
+ {envpython} -m mypy --no-install-types \
+ -p {[testenv]package_name} \
+ --txt-report .coverage.mypy \
+ --html-report .coverage.mypy \
+ # this is for github actions to upload to codecov.io
+ # sadly xml coverage crashes on windows... so we need to disable it
+ {env:CI_MYPY_COVERAGE} \
+ {posargs}
+
+
+[testenv:ty]
+dependency_groups = testing
+extras = optional
+deps = # any other dependencies (if needed)
+commands =
+ {envpython} -m ty \
+ check \
+ {posargs}