Merge branch 'develop'

.github/workflows/python-app.yml

@@ -23,7 +23,11 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install tox
+        pip install flake8==3.8.4 pytest
-    - name: Lint and test
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Lint with flake8
       run: |
-        tox
+        python setup.py lint
+    - name: Test with pytest
+      run: |
+        python setup.py test

.gitignore

@@ -9,4 +9,3 @@
 /venv
 build/
 .vscode/settings.json
-.tox/

README.rst

@@ -92,7 +92,7 @@ sub_symbol, sup_symbol
 newline_style
   Defines the style of marking linebreaks (``<br>``) in markdown. The default
   value ``SPACES`` of this option will adopt the usual two spaces and a newline,
-  while ``BACKSLASH`` will convert a linebreak to ``\\n`` (a backslash and a
+  while ``BACKSLASH`` will convert a linebreak to ``\\n`` (a backslash an a
   newline). While the latter convention is non-standard, it is commonly
   preferred and supported by a lot of interpreters.
 
@@ -130,11 +130,6 @@ keep_inline_images_in
   that should be allowed to contain inline images, for example ``['td']``.
   Defaults to an empty list.
 
-wrap, wrap_width
-  If ``wrap`` is set to ``True``, all text paragraphs are wrapped at
-  ``wrap_width`` characters. Defaults to ``False`` and ``80``.
-  Use with ``newline_style=BACKSLASH`` to keep line breaks in paragraphs.
-
 Options may be specified as kwargs to the ``markdownify`` function, or as a
 nested ``Options`` class in ``MarkdownConverter`` subclasses.
 
@@ -174,16 +169,13 @@ change:
         return ImageBlockConverter(**options).convert(html)
 
 
-Command Line Interface
-=====================
-
-Use ``markdownify example.html > example.md`` or pipe input from stdin
-(``cat example.html | markdownify > example.md``).
-Call ``markdownify -h`` to see all available options.
-They are the same as listed above and take the same arguments.
-
-
 Development
 ===========
 
-To run tests and the linter run ``pip install tox`` once, then ``tox``.
+To run tests:
+
+``python setup.py test``
+
+To lint:
+
+``python setup.py lint``

markdownify/__init__.py

@@ -1,5 +1,4 @@
 from bs4 import BeautifulSoup, NavigableString, Comment, Doctype
-from textwrap import fill
 import re
 import six
 
@@ -76,8 +75,6 @@ class MarkdownConverter(object):
         strong_em_symbol = ASTERISK
         sub_symbol = ''
         sup_symbol = ''
-        wrap = False
-        wrap_width = 80
 
     class Options(DefaultOptions):
         pass
@@ -158,7 +155,7 @@ class MarkdownConverter(object):
                     and el.parent.parent.name == 'pre')):
             text = whitespace_re.sub(' ', text)
 
-        if el.parent.name != 'code' and el.parent.name != 'pre':
+        if el.parent.name != 'code':
             text = self.escape(text)
 
         # remove trailing whitespaces if any of the following condition is true:
@@ -334,11 +331,6 @@ class MarkdownConverter(object):
     def convert_p(self, el, text, convert_as_inline):
         if convert_as_inline:
             return text
-        if self.options['wrap']:
-            text = fill(text,
-                        width=self.options['wrap_width'],
-                        break_long_words=False,
-                        break_on_hyphens=False)
         return '%s\n\n' % text if text else ''
 
     def convert_pre(self, el, text, convert_as_inline):
@@ -378,13 +370,8 @@ class MarkdownConverter(object):
         if is_headrow and not el.previous_sibling:
             # first row and is headline: print headline underline
             underline += '| ' + ' | '.join(['---'] * len(cells)) + ' |' + '\n'
-        elif (not el.previous_sibling
+        elif not el.previous_sibling and not el.parent.name != 'table':
-              and (el.parent.name == 'table'
+            # first row, not headline, and the parent is sth. like tbody:
-                   or (el.parent.name == 'tbody'
-                       and not el.parent.previous_sibling))):
-            # first row, not headline, and:
-            # - the parent is table or
-            # - the parent is tbody at the beginning of a table.
             # print empty headline above this row
             overline += '| ' + ' | '.join([''] * len(cells)) + ' |' + '\n'
             overline += '| ' + ' | '.join(['---'] * len(cells)) + ' |' + '\n'

markdownify/main.py

@@ -1,65 +0,0 @@
-#!/usr/bin/env python
-
-import argparse
-import sys
-
-from markdownify import markdownify
-
-
-def main(argv=sys.argv[1:]):
-    parser = argparse.ArgumentParser(
-        prog='markdownify',
-        description='Converts html to markdown.',
-    )
-
-    parser.add_argument('html', nargs='?', type=argparse.FileType('r'),
-                        default=sys.stdin,
-                        help="The html file to convert. Defaults to STDIN if not "
-                        "provided.")
-    parser.add_argument('-s', '--strip', nargs='*',
-                        help="A list of tags to strip. This option can't be used with "
-                        "the --convert option.")
-    parser.add_argument('-c', '--convert', nargs='*',
-                        help="A list of tags to convert. This option can't be used with "
-                        "the --strip option.")
-    parser.add_argument('-a', '--autolinks', action='store_true',
-                        help="A boolean indicating whether the 'automatic link' style "
-                        "should be used when a 'a' tag's contents match its href.")
-    parser.add_argument('--default-title', action='store_false',
-                        help="A boolean to enable setting the title of a link to its "
-                        "href, if no title is given.")
-    parser.add_argument('--heading-style',
-                        choices=('ATX', 'ATX_CLOSED', 'SETEXT', 'UNDERLINED'),
-                        help="Defines how headings should be converted.")
-    parser.add_argument('-b', '--bullets', default='*+-',
-                        help="A string of bullet styles to use; the bullet will "
-                        "alternate based on nesting level.")
-    parser.add_argument('--sub-symbol', default='',
-                        help="Define the chars that surround '<sub>'.")
-    parser.add_argument('--sup-symbol', default='',
-                        help="Define the chars that surround '<sup>'.")
-    parser.add_argument('--code-language', default='',
-                        help="Defines the language that should be assumed for all "
-                        "'<pre>' sections.")
-    parser.add_argument('--no-escape-asterisks', dest='escape_asterisks',
-                        action='store_false',
-                        help="Do not escape '*' to '\\*' in text.")
-    parser.add_argument('--no-escape-underscores', dest='escape_underscores',
-                        action='store_false',
-                        help="Do not escape '_' to '\\_' in text.")
-    parser.add_argument('-i', '--keep-inline-images-in', nargs='*',
-                        help="Images are converted to their alt-text when the images are "
-                        "located inside headlines or table cells. If some inline images "
-                        "should be converted to markdown images instead, this option can "
-                        "be set to a list of parent tags that should be allowed to "
-                        "contain inline images.")
-    parser.add_argument('-w', '--wrap', action='store_true',
-                        help="Wrap all text paragraphs at --wrap-width characters.")
-    parser.add_argument('--wrap-width', type=int, default=80)
-
-    args = parser.parse_args(argv)
-    print(markdownify(**vars(args)))
-
-
-if __name__ == '__main__':
-    main()

setup.cfg

@@ -0,0 +1,2 @@
+[flake8]
+ignore = E501 W503

setup.py

@@ -2,6 +2,7 @@
 import codecs
 import os
 from setuptools import setup, find_packages
+from setuptools.command.test import test as TestCommand, Command
 
 
 read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
@@ -9,10 +10,52 @@ read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.11.2',
+    '__version__': '0.11.0',
 }
 
-read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
+
+class PyTest(TestCommand):
+    def finalize_options(self):
+        TestCommand.finalize_options(self)
+        self.test_args = ['tests', '-s']
+        self.test_suite = True
+
+    def run_tests(self):
+        import pytest
+        errno = pytest.main(self.test_args)
+        raise SystemExit(errno)
+
+
+class LintCommand(Command):
+    """
+    A copy of flake8's Flake8Command
+
+    """
+    description = "Run flake8 on modules registered in setuptools"
+    user_options = []
+
+    def initialize_options(self):
+        pass
+
+    def finalize_options(self):
+        pass
+
+    def distribution_files(self):
+        if self.distribution.packages:
+            for package in self.distribution.packages:
+                yield package.replace(".", os.path.sep)
+
+        if self.distribution.py_modules:
+            for filename in self.distribution.py_modules:
+                yield "%s.py" % filename
+
+    def run(self):
+        from flake8.api.legacy import get_style_guide
+        flake8_style = get_style_guide(config_file='setup.cfg')
+        paths = self.distribution_files()
+        report = flake8_style.check_files(paths)
+        raise SystemExit(report.total_errors > 0)
+
 
 setup(
     name='markdownify',
@@ -26,9 +69,14 @@ setup(
     packages=find_packages(),
     zip_safe=False,
     include_package_data=True,
+    setup_requires=[
+        'flake8>=3.8,<5',
+    ],
+    tests_require=[
+        'pytest>=6.2,<7',
+    ],
     install_requires=[
-        'beautifulsoup4>=4.9,<5',
+        'beautifulsoup4>=4.9,<5', 'six>=1.15,<2'
-        'six>=1.15,<2',
     ],
     classifiers=[
         'Environment :: Web Environment',
@@ -44,9 +92,8 @@ setup(
         'Programming Language :: Python :: 3.8',
         'Topic :: Utilities'
     ],
-    entry_points={
+    cmdclass={
-        'console_scripts': [
+        'test': PyTest,
-            'markdownify = markdownify.main:main'
+        'lint': LintCommand,
-        ]
+    },
-    }
 )

tests/test_conversions.py

@@ -177,17 +177,11 @@ def test_kbd():
 
 def test_p():
     assert md('<p>hello</p>') == 'hello\n\n'
-    assert md('<p>123456789 123456789</p>') == '123456789 123456789\n\n'
-    assert md('<p>123456789 123456789</p>', wrap=True, wrap_width=10) == '123456789\n123456789\n\n'
-    assert md('<p><a href="https://example.com">Some long link</a></p>', wrap=True, wrap_width=10) == '[Some long\nlink](https://example.com)\n\n'
-    assert md('<p>12345<br />67890</p>', wrap=True, wrap_width=10, newline_style=BACKSLASH) == '12345\\\n67890\n\n'
-    assert md('<p>12345678901<br />12345</p>', wrap=True, wrap_width=10, newline_style=BACKSLASH) == '12345678901\\\n12345\n\n'
 
 
 def test_pre():
     assert md('<pre>test\n    foo\nbar</pre>') == '\n```\ntest\n    foo\nbar\n```\n'
     assert md('<pre><code>test\n    foo\nbar</code></pre>') == '\n```\ntest\n    foo\nbar\n```\n'
-    assert md('<pre>this_should_not_escape</pre>') == '\n```\nthis_should_not_escape\n```\n'
 
 
 def test_s():

tests/test_tables.py

@@ -139,26 +139,6 @@ table_missing_head = """<table>
     </tr>
 </table>"""
 
-table_body = """<table>
-    <tbody>
-        <tr>
-            <td>Firstname</td>
-            <td>Lastname</td>
-            <td>Age</td>
-        </tr>
-        <tr>
-            <td>Jill</td>
-            <td>Smith</td>
-            <td>50</td>
-        </tr>
-        <tr>
-            <td>Eve</td>
-            <td>Jackson</td>
-            <td>94</td>
-        </tr>
-    </tbody>
-</table>"""
-
 
 def test_table():
     assert md(table) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
@@ -168,4 +148,3 @@ def test_table():
     assert md(table_head_body) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_missing_text) == '\n\n|  | Lastname | Age |\n| --- | --- | --- |\n| Jill |  | 50 |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_missing_head) == '\n\n|  |  |  |\n| --- | --- | --- |\n| Firstname | Lastname | Age |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
-    assert md(table_body) == '\n\n|  |  |  |\n| --- | --- | --- |\n| Firstname | Lastname | Age |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'

tox.ini

@@ -1,10 +0,0 @@
-[tox]
-envlist = py38
-
-[testenv]
-deps =
-	flake8
-	pytest
-commands =
-	flake8 --ignore=E501,W503 markdownify tests
-	pytest