Cyclic0007/python-markdownify
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'develop' into para-newlines-92-98

Browse Source
This commit is contained in:
Joseph Myers
2024-09-30 18:05:32 +00:00
parent 60d86663d7 964d89fa8a
commit 4399ee75db
11 changed files with 88 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.github/workflows/python-app.yml vendored
View File

@@ -23,7 +23,10 @@ jobs:
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install tox
pip install --upgrade setuptools setuptools_scm wheel build tox
- name: Lint and test
run: |
tox
- name: Build
run: |
python -m build -nwsx .

4
.github/workflows/python-publish.yml vendored
View File

@@ -21,11 +21,11 @@ jobs:
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install setuptools wheel twine
pip install --upgrade setuptools setuptools_scm wheel build twine
- name: Build and publish
env:
TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
run: |
python setup.py sdist bdist_wheel
python -m build -nwsx .
twine upload dist/*

1
MANIFEST.in
View File

@@ -1 +1,2 @@
include README.rst
prune tests

6
README.rst
View File

@@ -87,7 +87,11 @@ strong_em_symbol
sub_symbol, sup_symbol
Define the chars that surround ``<sub>`` and ``<sup>`` text. Defaults to an
empty string, because this is non-standard behavior. Could be something like
``~`` and ``^`` to result in ``~sub~`` and ``^sup^``.
``~`` and ``^`` to result in ``~sub~`` and ``^sup^``. If the value starts
with ``<`` and ends with ``>``, it is treated as an HTML tag and a ``/`` is
inserted after the ``<`` in the string used after the text; this allows
specifying ``<sub>`` to use raw HTML in the output for subscripts, for
example.
newline_style
Defines the style of marking linebreaks (``<br>``) in markdown. The default

19
markdownify/__init__.py
View File

@@ -43,17 +43,22 @@ def abstract_inline_conversion(markup_fn):
"""
This abstracts all simple inline tags like b, em, del, ...
Returns a function that wraps the chomped text in a pair of the string
that is returned by markup_fn. markup_fn is necessary to allow for
that is returned by markup_fn, with '/' inserted in the string used after
the text if it looks like an HTML tag. markup_fn is necessary to allow for
references to self.strong_em_symbol etc.
"""
def implementation(self, el, text, convert_as_inline):
markup = markup_fn(self)
markup_prefix = markup_fn(self)
if markup_prefix.startswith('<') and markup_prefix.endswith('>'):
markup_suffix = '</' + markup_prefix[1:]
else:
markup_suffix = markup_prefix
if el.find_parent(['pre', 'code', 'kbd', 'samp']):
return text
prefix, suffix, text = chomp(text)
if not text:
return ''
return '%s%s%s%s%s' % (prefix, markup, text, markup, suffix)
return '%s%s%s%s%s' % (prefix, markup_prefix, text, markup_suffix, suffix)
return implementation
@@ -327,7 +332,7 @@ class MarkdownConverter(object):
def convert_li(self, el, text, convert_as_inline):
parent = el.parent
if parent is not None and parent.name == 'ol':
if parent.get("start"):
if parent.get("start") and str(parent.get("start")).isnumeric():
start = int(parent.get("start"))
else:
start = 1
@@ -389,13 +394,13 @@ class MarkdownConverter(object):
def convert_td(self, el, text, convert_as_inline):
colspan = 1
if 'colspan' in el.attrs:
if 'colspan' in el.attrs and el['colspan'].isdigit():
colspan = int(el['colspan'])
return ' ' + text.strip().replace("\n", " ") + ' |' * colspan
def convert_th(self, el, text, convert_as_inline):
colspan = 1
if 'colspan' in el.attrs:
if 'colspan' in el.attrs and el['colspan'].isdigit():
colspan = int(el['colspan'])
return ' ' + text.strip().replace("\n", " ") + ' |' * colspan
@@ -412,7 +417,7 @@ class MarkdownConverter(object):
# first row and is headline: print headline underline
full_colspan = 0
for cell in cells:
if "colspan" in cell.attrs:
if 'colspan' in cell.attrs and cell['colspan'].isdigit():
full_colspan += int(cell["colspan"])
else:
full_colspan += 1

45
pyproject.toml Normal file
View File

@@ -0,0 +1,45 @@
[build-system]
requires = ["setuptools>=61.2", "setuptools_scm[toml]>=3.4.3"]
build-backend = "setuptools.build_meta"
[project]
name = "markdownify"
version = "0.13.1"
authors = [{name = "Matthew Tretter", email = "m@tthewwithanm.com"}]
description = "Convert HTML to markdown."
readme = "README.rst"
classifiers = [
"Environment :: Web Environment",
"Framework :: Django",
"Intended Audience :: Developers",
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
"Programming Language :: Python :: 2.5",
"Programming Language :: Python :: 2.6",
"Programming Language :: Python :: 2.7",
"Programming Language :: Python :: 3.6",
"Programming Language :: Python :: 3.7",
"Programming Language :: Python :: 3.8",
"Topic :: Utilities",
]
dependencies = [
"beautifulsoup4>=4.9,<5",
"six>=1.15,<2"
]
[project.urls]
Homepage = "http://github.com/matthewwithanm/python-markdownify"
Download = "http://github.com/matthewwithanm/python-markdownify/tarball/master"
[project.scripts]
markdownify = "markdownify.main:main"
[tool.setuptools]
zip-safe = false
include-package-data = true
[tool.setuptools.packages.find]
include = ["markdownify", "markdownify.*"]
namespaces = false
[tool.setuptools_scm]

52
setup.py
View File

@@ -1,52 +0,0 @@
#/usr/bin/env python
import codecs
import os
from setuptools import setup, find_packages
read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
pkgmeta = {
'__title__': 'markdownify',
'__author__': 'Matthew Tretter',
'__version__': '0.12.1',
}
read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
setup(
name='markdownify',
description='Convert HTML to markdown.',
long_description=read(os.path.join(os.path.dirname(__file__), 'README.rst')),
version=pkgmeta['__version__'],
author=pkgmeta['__author__'],
author_email='m@tthewwithanm.com',
url='http://github.com/matthewwithanm/python-markdownify',
download_url='http://github.com/matthewwithanm/python-markdownify/tarball/master',
packages=find_packages(),
zip_safe=False,
include_package_data=True,
install_requires=[
'beautifulsoup4>=4.9,<5',
'six>=1.15,<2',
],
classifiers=[
'Environment :: Web Environment',
'Framework :: Django',
'Intended Audience :: Developers',
'License :: OSI Approved :: MIT License',
'Operating System :: OS Independent',
'Programming Language :: Python :: 2.5',
'Programming Language :: Python :: 2.6',
'Programming Language :: Python :: 2.7',
'Programming Language :: Python :: 3.6',
'Programming Language :: Python :: 3.7',
'Programming Language :: Python :: 3.8',
'Topic :: Utilities'
],
entry_points={
'console_scripts': [
'markdownify = markdownify.main:main'
]
}
)

2
tests/test_conversions.py
View File

@@ -271,11 +271,13 @@ def test_strong_em_symbol():
def test_sub():
assert md('<sub>foo</sub>') == 'foo'
assert md('<sub>foo</sub>', sub_symbol='~') == '~foo~'
assert md('<sub>foo</sub>', sub_symbol='<sub>') == '<sub>foo</sub>'
def test_sup():
assert md('<sup>foo</sup>') == 'foo'
assert md('<sup>foo</sup>', sup_symbol='^') == '^foo^'
assert md('<sup>foo</sup>', sup_symbol='<sup>') == '<sup>foo</sup>'
def test_lang():

3
tests/test_lists.py
View File

@@ -44,6 +44,9 @@ def test_ol():
assert md('<ol><li>a</li><li>b</li></ol>') == '\n\n1. a\n2. b\n'
assert md('<ol start="3"><li>a</li><li>b</li></ol>') == '\n\n3. a\n4. b\n'
assert md('foo<ol start="3"><li>a</li><li>b</li></ol>bar') == 'foo\n\n3. a\n4. b\n\nbar'
assert md('<ol start="-1"><li>a</li><li>b</li></ol>') == '\n\n1. a\n2. b\n'
assert md('<ol start="foo"><li>a</li><li>b</li></ol>') == '\n\n1. a\n2. b\n'
assert md('<ol start="1.5"><li>a</li><li>b</li></ol>') == '\n\n1. a\n2. b\n'
def test_nested_ols():

14
tests/test_tables.py
View File

@@ -215,7 +215,7 @@ table_with_colspan = """<table>
<th>Age</th>
</tr>
<tr>
<td>Jill</td>
<td colspan="1">Jill</td>
<td>Smith</td>
<td>50</td>
</tr>
@@ -226,6 +226,17 @@ table_with_colspan = """<table>
</tr>
</table>"""
table_with_undefined_colspan = """<table>
<tr>
<th colspan="undefined">Name</th>
<th>Age</th>
</tr>
<tr>
<td colspan="-1">Jill</td>
<td>Smith</td>
</tr>
</table>"""
def test_table():
assert md(table) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
@@ -240,3 +251,4 @@ def test_table():
assert md(table_body) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
assert md(table_with_caption) == 'TEXT\n\nCaption\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n\n'
assert md(table_with_colspan) == '\n\n| Name | | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
assert md(table_with_undefined_colspan) == '\n\n| Name | Age |\n| --- | --- |\n| Jill | Smith |\n\n'

2
tox.ini
View File

@@ -4,7 +4,7 @@ envlist = py38
[testenv]
passenv = PYTHONPATH
deps =
pytest
pytest==8
flake8
restructuredtext_lint
Pygments