Merge branch 'develop'

* Fix #109 Table merge cell horizontally

* Add test case for colspan

---------

Co-authored-by: AlexVonB <AlexVonB@users.noreply.github.com>

.github/workflows/python-app.yml

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

.gitignore

@@ -9,3 +9,4 @@
 /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 an a
+  while ``BACKSLASH`` will convert a linebreak to ``\\n`` (a backslash and a
   newline). While the latter convention is non-standard, it is commonly
   preferred and supported by a lot of interpreters.
 
@@ -130,6 +130,11 @@ 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.
 
@@ -151,7 +156,12 @@ Creating Custom Converters
 
 If you have a special usecase that calls for a special conversion, you can
 always inherit from ``MarkdownConverter`` and override the method you want to
-change:
+change.
+The function that handles a HTML tag named ``abc`` is called
+``convert_abc(self, el, text, convert_as_inline)`` and returns a string
+containing the converted HTML tag.
+The ``MarkdownConverter`` object will handle the conversion based on the
+function names:
 
 .. code:: python
 
@@ -168,14 +178,32 @@ change:
     def md(html, **options):
         return ImageBlockConverter(**options).convert(html)
 
+.. code:: python
+
+    from markdownify import MarkdownConverter
+
+    class IgnoreParagraphsConverter(MarkdownConverter):
+        """
+        Create a custom MarkdownConverter that ignores paragraphs
+        """
+        def convert_p(self, el, text, convert_as_inline):
+            return ''
+
+    # Create shorthand method for conversion
+    def md(html, **options):
+        return IgnoreParagraphsConverter(**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:
-
-``python setup.py test``
-
-To lint:
-
-``python setup.py lint``
+To run tests and the linter run ``pip install tox`` once, then ``tox``.

markdownify/__init__.py

@@ -1,4 +1,5 @@
 from bs4 import BeautifulSoup, NavigableString, Comment, Doctype
+from textwrap import fill
 import re
 import six
 
@@ -75,6 +76,8 @@ class MarkdownConverter(object):
         strong_em_symbol = ASTERISK
         sub_symbol = ''
         sup_symbol = ''
+        wrap = False
+        wrap_width = 80
 
     class Options(DefaultOptions):
         pass
@@ -149,13 +152,12 @@ class MarkdownConverter(object):
     def process_text(self, el):
         text = six.text_type(el) or ''
 
-        # dont remove any whitespace when handling pre or code in pre
-        if not (el.parent.name == 'pre'
-                or (el.parent.name == 'code'
-                    and el.parent.parent.name == 'pre')):
+        # normalize whitespace if we're not inside a preformatted element
+        if not el.find_parent('pre'):
             text = whitespace_re.sub(' ', text)
 
-        if el.parent.name != 'code':
+        # escape special characters if we're not inside a preformatted or code element
+        if not el.find_parent(['pre', 'code', 'kbd', 'samp']):
             text = self.escape(text)
 
         # remove trailing whitespaces if any of the following condition is true:
@@ -235,7 +237,7 @@ class MarkdownConverter(object):
         if convert_as_inline:
             return text
 
-        return '\n' + (line_beginning_re.sub('> ', text) + '\n\n') if text else ''
+        return '\n' + (line_beginning_re.sub('> ', text.strip()) + '\n\n') if text else ''
 
     def convert_br(self, el, text, convert_as_inline):
         if convert_as_inline:
@@ -263,7 +265,7 @@ class MarkdownConverter(object):
             return text
 
         style = self.options['heading_style'].lower()
-        text = text.rstrip()
+        text = text.strip()
         if style == UNDERLINED and n <= 2:
             line = '=' if n == 1 else '-'
             return self.underline(text, line)
@@ -331,6 +333,11 @@ 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):
@@ -343,6 +350,12 @@ class MarkdownConverter(object):
 
         return '\n```%s\n%s\n```\n' % (code_language, text)
 
+    def convert_script(self, el, text, convert_as_inline):
+        return ''
+
+    def convert_style(self, el, text, convert_as_inline):
+        return ''
+
     convert_s = convert_del
 
     convert_strong = convert_b
@@ -356,20 +369,42 @@ class MarkdownConverter(object):
     def convert_table(self, el, text, convert_as_inline):
         return '\n\n' + text + '\n'
 
+    def convert_caption(self, el, text, convert_as_inline):
+        return text + '\n'
+
+    def convert_figcaption(self, el, text, convert_as_inline):
+        return '\n\n' + text + '\n\n'
+
     def convert_td(self, el, text, convert_as_inline):
-        return ' ' + text + ' |'
+        colspan = 1
+        if 'colspan' in el.attrs:
+            colspan = int(el['colspan'])
+        return ' ' + text.strip().replace("\n", " ") + ' |' * colspan
 
     def convert_th(self, el, text, convert_as_inline):
-        return ' ' + text + ' |'
+        colspan = 1
+        if 'colspan' in el.attrs:
+            colspan = int(el['colspan'])
+        return ' ' + text.strip().replace("\n", " ") + ' |' * colspan
 
     def convert_tr(self, el, text, convert_as_inline):
         cells = el.find_all(['td', 'th'])
-        is_headrow = all([cell.name == 'th' for cell in cells])
+        is_headrow = (
+            all([cell.name == 'th' for cell in cells])
+            or (not el.previous_sibling and not el.parent.name == 'tbody')
+            or (not el.previous_sibling and el.parent.name == 'tbody' and len(el.parent.parent.find_all(['thead'])) < 1)
+        )
         overline = ''
         underline = ''
         if is_headrow and not el.previous_sibling:
             # first row and is headline: print headline underline
-            underline += '| ' + ' | '.join(['---'] * len(cells)) + ' |' + '\n'
+            full_colspan = 0
+            for cell in cells:
+                if "colspan" in cell.attrs:
+                    full_colspan += int(cell["colspan"])
+                else:
+                    full_colspan += 1
+            underline += '| ' + ' | '.join(['---'] * full_colspan) + ' |' + '\n'
         elif (not el.previous_sibling
               and (el.parent.name == 'table'
                    or (el.parent.name == 'tbody'

markdownify/main.py

@@ -0,0 +1,73 @@
+#!/usr/bin/env python
+
+import argparse
+import sys
+
+from markdownify import markdownify, ATX, ATX_CLOSED, UNDERLINED, \
+    SPACES, BACKSLASH, ASTERISK, UNDERSCORE
+
+
+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', default=UNDERLINED,
+                        choices=(ATX, ATX_CLOSED, 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('--strong-em-symbol', default=ASTERISK,
+                        choices=(ASTERISK, UNDERSCORE),
+                        help="Use * or _ to convert strong and italics text"),
+    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('--newline-style', default=SPACES,
+                        choices=(SPACES, BACKSLASH),
+                        help="Defines the style of <br> conversions: two spaces "
+                        "or backslash at the and of the line thet should break.")
+    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

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

setup.py

@@ -2,7 +2,6 @@
 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()
@@ -10,52 +9,10 @@ read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.11.1',
+    '__version__': '0.12.1',
 }
 
-
-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)
-
+read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 
 setup(
     name='markdownify',
@@ -69,14 +26,9 @@ 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', 'six>=1.15,<2'
+        'beautifulsoup4>=4.9,<5',
+        'six>=1.15,<2',
     ],
     classifiers=[
         'Environment :: Web Environment',
@@ -92,8 +44,9 @@ setup(
         'Programming Language :: Python :: 3.8',
         'Topic :: Utilities'
     ],
-    cmdclass={
-        'test': PyTest,
-        'lint': LintCommand,
-    },
+    entry_points={
+        'console_scripts': [
+            'markdownify = markdownify.main:main'
+        ]
+    }
 )

shell.nix

@@ -0,0 +1,10 @@
+{ pkgs ? import <nixpkgs> {} }:
+pkgs.mkShell {
+  name = "python-shell";
+  buildInputs = with pkgs; [
+    python38
+    python38Packages.tox
+    python38Packages.setuptools
+    python38Packages.virtualenv
+  ];
+}

tests/test_conversions.py

@@ -52,6 +52,12 @@ def test_b_spaces():
 
 def test_blockquote():
     assert md('<blockquote>Hello</blockquote>') == '\n> Hello\n\n'
+    assert md('<blockquote>\nHello\n</blockquote>') == '\n> Hello\n\n'
+
+
+def test_blockquote_with_nested_paragraph():
+    assert md('<blockquote><p>Hello</p></blockquote>') == '\n> Hello\n\n'
+    assert md('<blockquote><p>Hello</p><p>Hello again</p></blockquote>') == '\n> Hello\n> \n> Hello again\n\n'
 
 
 def test_blockquote_with_paragraph():
@@ -60,7 +66,7 @@ def test_blockquote_with_paragraph():
 
 def test_blockquote_nested():
     text = md('<blockquote>And she was like <blockquote>Hello</blockquote></blockquote>')
-    assert text == '\n> And she was like \n> > Hello\n> \n> \n\n'
+    assert text == '\n> And she was like \n> > Hello\n\n'
 
 
 def test_br():
@@ -68,9 +74,19 @@ def test_br():
     assert md('a<br />b<br />c', newline_style=BACKSLASH) == 'a\\\nb\\\nc'
 
 
+def test_caption():
+    assert md('TEXT<figure><figcaption>Caption</figcaption><span>SPAN</span></figure>') == 'TEXT\n\nCaption\n\nSPAN'
+    assert md('<figure><span>SPAN</span><figcaption>Caption</figcaption></figure>TEXT') == 'SPAN\n\nCaption\n\nTEXT'
+
+
 def test_code():
     inline_tests('code', '`')
-    assert md('<code>this_should_not_escape</code>') == '`this_should_not_escape`'
+    assert md('<code>*this_should_not_escape*</code>') == '`*this_should_not_escape*`'
+    assert md('<kbd>*this_should_not_escape*</kbd>') == '`*this_should_not_escape*`'
+    assert md('<samp>*this_should_not_escape*</samp>') == '`*this_should_not_escape*`'
+    assert md('<code><span>*this_should_not_escape*</span></code>') == '`*this_should_not_escape*`'
+    assert md('<code>this  should\t\tnormalize</code>') == '`this should normalize`'
+    assert md('<code><span>this  should\t\tnormalize</span></code>') == '`this should normalize`'
 
 
 def test_del():
@@ -85,6 +101,14 @@ def test_em():
     inline_tests('em', '*')
 
 
+def test_header_with_space():
+    assert md('<h3>\n\nHello</h3>') == '### Hello\n\n'
+    assert md('<h4>\n\nHello</h4>') == '#### Hello\n\n'
+    assert md('<h5>\n\nHello</h5>') == '##### Hello\n\n'
+    assert md('<h5>\n\nHello\n\n</h5>') == '##### Hello\n\n'
+    assert md('<h5>\n\nHello   \n\n</h5>') == '##### Hello\n\n'
+
+
 def test_h1():
     assert md('<h1>Hello</h1>') == 'Hello\n=====\n\n'
 
@@ -177,11 +201,28 @@ 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```\n*this_should_not_escape*\n```\n'
+    assert md('<pre><span>*this_should_not_escape*</span></pre>') == '\n```\n*this_should_not_escape*\n```\n'
+    assert md('<pre>\t\tthis  should\t\tnot  normalize</pre>') == '\n```\n\t\tthis  should\t\tnot  normalize\n```\n'
+    assert md('<pre><span>\t\tthis  should\t\tnot  normalize</span></pre>') == '\n```\n\t\tthis  should\t\tnot  normalize\n```\n'
+
+
+def test_script():
+    assert md('foo <script>var foo=42;</script> bar') == 'foo  bar'
+
+
+def test_style():
+    assert md('foo <style>h1 { font-size: larger }</style> bar') == 'foo  bar'
 
 
 def test_s():

tests/test_tables.py

@@ -57,6 +57,26 @@ table_with_paragraphs = """<table>
     </tr>
 </table>"""
 
+table_with_linebreaks = """<table>
+    <tr>
+        <th>Firstname</th>
+        <th>Lastname</th>
+        <th>Age</th>
+    </tr>
+    <tr>
+        <td>Jill</td>
+        <td>Smith
+        Jackson</td>
+        <td>50</td>
+    </tr>
+    <tr>
+        <td>Eve</td>
+        <td>Jackson
+        Smith</td>
+        <td>94</td>
+    </tr>
+</table>"""
+
 
 table_with_header_column = """<table>
     <tr>
@@ -99,6 +119,28 @@ table_head_body = """<table>
     </tbody>
 </table>"""
 
+table_head_body_missing_head = """<table>
+    <thead>
+        <tr>
+            <td>Firstname</td>
+            <td>Lastname</td>
+            <td>Age</td>
+        </tr>
+    </thead>
+    <tbody>
+        <tr>
+            <td>Jill</td>
+            <td>Smith</td>
+            <td>50</td>
+        </tr>
+        <tr>
+            <td>Eve</td>
+            <td>Jackson</td>
+            <td>94</td>
+        </tr>
+    </tbody>
+</table>"""
+
 table_missing_text = """<table>
     <thead>
         <tr>
@@ -159,13 +201,42 @@ table_body = """<table>
     </tbody>
 </table>"""
 
+table_with_caption = """TEXT<table><caption>Caption</caption>
+    <tbody><tr><td>Firstname</td>
+            <td>Lastname</td>
+            <td>Age</td>
+        </tr>
+    </tbody>
+</table>"""
+
+table_with_colspan = """<table>
+    <tr>
+        <th colspan="2">Name</th>
+        <th>Age</th>
+    </tr>
+    <tr>
+        <td>Jill</td>
+        <td>Smith</td>
+        <td>50</td>
+    </tr>
+    <tr>
+        <td>Eve</td>
+        <td>Jackson</td>
+        <td>94</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'
     assert md(table_with_html_content) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| **Jill** | *Smith* | [50](#) |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_with_paragraphs) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
+    assert md(table_with_linebreaks) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith  Jackson | 50 |\n| Eve | Jackson  Smith | 94 |\n\n'
     assert md(table_with_header_column) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_head_body) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
+    assert md(table_head_body_missing_head) == '\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'
+    assert md(table_missing_head) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
+    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'

tox.ini

@@ -0,0 +1,15 @@
+[tox]
+envlist = py38
+
+[testenv]
+passenv = PYTHONPATH
+deps =
+	pytest
+	flake8
+	restructuredtext_lint
+	Pygments
+commands =
+	pytest
+	flake8 --ignore=E501,W503 markdownify tests
+	restructuredtext-lint README.rst
+