Compare commits

...

5 Commits
0.8.1 ... 0.9.0

Author SHA1 Message Date
AlexVonB
59417ab115 Merge branch 'develop' 2021-05-30 19:10:49 +02:00
AlexVonB
cec570fc49 bump to v0.9.0 2021-05-30 19:10:31 +02:00
AlexVonB
a6a31624ad add options for sub and sup tags
fixes #44
2021-05-30 19:07:43 +02:00
AlexVonB
6f3732307d restructured test files 2021-05-30 19:06:52 +02:00
AlexVonB
8f6d7e500d add option 'default_title' to links
fixes #39
2021-05-30 18:40:40 +02:00
7 changed files with 302 additions and 278 deletions

View File

@@ -62,7 +62,11 @@ convert
autolinks
A boolean indicating whether the "automatic link" style should be used when
a ``a`` tag's contents match its href. Defaults to ``True``
a ``a`` tag's contents match its href. Defaults to ``True``.
default_title
A boolean to enable setting the title of a link to its href, if no title is
given. Defaults to ``False``.
heading_style
Defines how headings should be converted. Accepted values are ``ATX``,
@@ -80,6 +84,11 @@ strong_em_symbol
*emphasized* texts. Either of these symbols can be chosen by the options
``ASTERISK`` (default) or ``UNDERSCORE`` respectively.
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^``.
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,

View File

@@ -66,13 +66,16 @@ def _todict(obj):
class MarkdownConverter(object):
class DefaultOptions:
strip = None
convert = None
autolinks = True
heading_style = UNDERLINED
bullets = '*+-' # An iterable of bullet types.
strong_em_symbol = ASTERISK
convert = None
default_title = False
heading_style = UNDERLINED
newline_style = SPACES
strip = None
strong_em_symbol = ASTERISK
sub_symbol = ''
sup_symbol = ''
class Options(DefaultOptions):
pass
@@ -198,9 +201,14 @@ class MarkdownConverter(object):
href = el.get('href')
title = el.get('title')
# For the replacement see #29: text nodes underscores are escaped
if self.options['autolinks'] and text.replace(r'\_', '_') == href and not title:
if (self.options['autolinks']
and text.replace(r'\_', '_') == href
and not title
and not self.options['default_title']):
# Shortcut syntax
return '<%s>' % href
if self.options['default_title'] and not title:
title = href
title_part = ' "%s"' % title.replace('"', r'\"') if title else ''
return '%s[%s](%s%s)%s' % (prefix, text, href, title_part, suffix) if href else text
@@ -319,6 +327,10 @@ class MarkdownConverter(object):
convert_samp = convert_code
convert_sub = abstract_inline_conversion(lambda self: self.options['sub_symbol'])
convert_sup = abstract_inline_conversion(lambda self: self.options['sup_symbol'])
def convert_table(self, el, text, convert_as_inline):
return '\n\n' + text + '\n'

View File

@@ -10,7 +10,7 @@ read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
pkgmeta = {
'__title__': 'markdownify',
'__author__': 'Matthew Tretter',
'__version__': '0.8.1',
'__version__': '0.9.0',
}

View File

@@ -1,6 +1,17 @@
from markdownify import markdownify as md
def test_chomp():
assert md(' <b></b> ') == ' '
assert md(' <b> </b> ') == ' '
assert md(' <b> </b> ') == ' '
assert md(' <b> </b> ') == ' '
assert md(' <b>s </b> ') == ' **s** '
assert md(' <b> s</b> ') == ' **s** '
assert md(' <b> s </b> ') == ' **s** '
assert md(' <b> s </b> ') == ' **s** '
def test_nested():
text = md('<p>This is an <a href="http://example.com/">example link</a>.</p>')
assert text == 'This is an [example link](http://example.com/).\n\n'

View File

@@ -1,179 +1,17 @@
from markdownify import markdownify as md, ATX, ATX_CLOSED, BACKSLASH, UNDERSCORE
nested_uls = """
<ul>
<li>1
<ul>
<li>a
<ul>
<li>I</li>
<li>II</li>
<li>III</li>
</ul>
</li>
<li>b</li>
<li>c</li>
</ul>
</li>
<li>2</li>
<li>3</li>
</ul>"""
nested_ols = """
<ol>
<li>1
<ol>
<li>a
<ol>
<li>I</li>
<li>II</li>
<li>III</li>
</ol>
</li>
<li>b</li>
<li>c</li>
</ol>
</li>
<li>2</li>
<li>3</li>
</ul>"""
table = """<table>
<tr>
<th>Firstname</th>
<th>Lastname</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>"""
table_with_html_content = """<table>
<tr>
<th>Firstname</th>
<th>Lastname</th>
<th>Age</th>
</tr>
<tr>
<td><b>Jill</b></td>
<td><i>Smith</i></td>
<td><a href="#">50</a></td>
</tr>
<tr>
<td>Eve</td>
<td>Jackson</td>
<td>94</td>
</tr>
</table>"""
table_with_header_column = """<table>
<tr>
<th>Firstname</th>
<th>Lastname</th>
<th>Age</th>
</tr>
<tr>
<th>Jill</th>
<td>Smith</td>
<td>50</td>
</tr>
<tr>
<th>Eve</th>
<td>Jackson</td>
<td>94</td>
</tr>
</table>"""
table_head_body = """<table>
<thead>
<tr>
<th>Firstname</th>
<th>Lastname</th>
<th>Age</th>
</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>
<th></th>
<th>Lastname</th>
<th>Age</th>
</tr>
</thead>
<tbody>
<tr>
<td>Jill</td>
<td></td>
<td>50</td>
</tr>
<tr>
<td>Eve</td>
<td>Jackson</td>
<td>94</td>
</tr>
</tbody>
</table>"""
table_missing_head = """<table>
<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>
</table>"""
def test_chomp():
assert md(' <b></b> ') == ' '
assert md(' <b> </b> ') == ' '
assert md(' <b> </b> ') == ' '
assert md(' <b> </b> ') == ' '
assert md(' <b>s </b> ') == ' **s** '
assert md(' <b> s</b> ') == ' **s** '
assert md(' <b> s </b> ') == ' **s** '
assert md(' <b> s </b> ') == ' **s** '
def inline_tests(tag, markup):
# test template for different inline tags
assert md(f'<{tag}>Hello</{tag}>') == f'{markup}Hello{markup}'
assert md(f'foo <{tag}>Hello</{tag}> bar') == f'foo {markup}Hello{markup} bar'
assert md(f'foo<{tag}> Hello</{tag}> bar') == f'foo {markup}Hello{markup} bar'
assert md(f'foo <{tag}>Hello </{tag}>bar') == f'foo {markup}Hello{markup} bar'
assert md(f'foo <{tag}></{tag}> bar') in ['foo bar', 'foo bar'] # Either is OK
def test_a():
assert md('<a href="https://google.com">Google</a>') == '[Google](https://google.com)'
assert md('<a href="https://google.com">https://google.com</a>', autolinks=False) == '[https://google.com](https://google.com)'
assert md('<a href="https://google.com">https://google.com</a>') == '<https://google.com>'
assert md('<a href="https://community.kde.org/Get_Involved">https://community.kde.org/Get_Involved</a>') == '<https://community.kde.org/Get_Involved>'
assert md('<a href="https://community.kde.org/Get_Involved">https://community.kde.org/Get_Involved</a>', autolinks=False) == '[https://community.kde.org/Get\\_Involved](https://community.kde.org/Get_Involved)'
@@ -189,6 +27,7 @@ def test_a_spaces():
def test_a_with_title():
text = md('<a href="http://google.com" title="The &quot;Goog&quot;">Google</a>')
assert text == r'[Google](http://google.com "The \"Goog\"")'
assert md('<a href="https://google.com">https://google.com</a>', default_title=True) == '[https://google.com](https://google.com "https://google.com")'
def test_a_shortcut():
@@ -197,8 +36,7 @@ def test_a_shortcut():
def test_a_no_autolinks():
text = md('<a href="http://google.com">http://google.com</a>', autolinks=False)
assert text == '[http://google.com](http://google.com)'
assert md('<a href="https://google.com">https://google.com</a>', autolinks=False) == '[https://google.com](https://google.com)'
def test_b():
@@ -220,58 +58,30 @@ def test_blockquote_with_paragraph():
assert md('<blockquote>Hello</blockquote><p>handsome</p>') == '\n> Hello\n\nhandsome\n\n'
def test_nested_blockquote():
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'
def test_br():
assert md('a<br />b<br />c') == 'a \nb \nc'
def test_em():
assert md('<em>Hello</em>') == '*Hello*'
def test_em_spaces():
assert md('foo <em>Hello</em> bar') == 'foo *Hello* bar'
assert md('foo<em> Hello</em> bar') == 'foo *Hello* bar'
assert md('foo <em>Hello </em>bar') == 'foo *Hello* bar'
assert md('foo <em></em> bar') == 'foo bar'
def inline_tests(tag, markup):
# Basically re-use test_em() and test_em_spaces(),
assert md(f'<{tag}>Hello</{tag}>') == f'{markup}Hello{markup}'
assert md(f'foo <{tag}>Hello</{tag}> bar') == f'foo {markup}Hello{markup} bar'
assert md(f'foo<{tag}> Hello</{tag}> bar') == f'foo {markup}Hello{markup} bar'
assert md(f'foo <{tag}>Hello </{tag}>bar') == f'foo {markup}Hello{markup} bar'
assert md(f'foo <{tag}></{tag}> bar') in ['foo bar', 'foo bar'] # Either is OK
assert md('a<br />b<br />c', newline_style=BACKSLASH) == 'a\\\nb\\\nc'
def test_code():
inline_tests('code', '`')
def test_samp():
inline_tests('samp', '`')
def test_kbd():
inline_tests('kbd', '`')
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'
def test_del():
inline_tests('del', '~~')
def test_s():
inline_tests('s', '~~')
def test_div():
assert md('Hello</div> World') == 'Hello World'
def test_em():
inline_tests('em', '*')
def test_h1():
@@ -284,6 +94,8 @@ def test_h2():
def test_hn():
assert md('<h3>Hello</h3>') == '### Hello\n\n'
assert md('<h4>Hello</h4>') == '#### Hello\n\n'
assert md('<h5>Hello</h5>') == '##### Hello\n\n'
assert md('<h6>Hello</h6>') == '###### Hello\n\n'
@@ -330,87 +142,58 @@ def test_hn_nested_img():
assert md('<h3>A <img src="/path/to/img.jpg " ' + image_attributes + '/> B</h3>') == '### A ' + markdown + ' B\n\n'
def test_hr():
assert md('Hello<hr>World') == 'Hello\n\n---\n\nWorld'
assert md('Hello<hr />World') == 'Hello\n\n---\n\nWorld'
assert md('<p>Hello</p>\n<hr>\n<p>World</p>') == 'Hello\n\n\n\n\n---\n\n\nWorld\n\n'
def test_hn_atx_headings():
assert md('<h1>Hello</h1>', heading_style=ATX) == '# Hello\n\n'
assert md('<h2>Hello</h2>', heading_style=ATX) == '## Hello\n\n'
def test_hn_atx_closed_headings():
assert md('<h1>Hello</h1>', heading_style=ATX_CLOSED) == '# Hello #\n\n'
assert md('<h2>Hello</h2>', heading_style=ATX_CLOSED) == '## Hello ##\n\n'
def test_head():
assert md('<head>head</head>') == 'head'
def test_atx_headings():
assert md('<h1>Hello</h1>', heading_style=ATX) == '# Hello\n\n'
assert md('<h2>Hello</h2>', heading_style=ATX) == '## Hello\n\n'
def test_atx_closed_headings():
assert md('<h1>Hello</h1>', heading_style=ATX_CLOSED) == '# Hello #\n\n'
assert md('<h2>Hello</h2>', heading_style=ATX_CLOSED) == '## Hello ##\n\n'
def test_hr():
assert md('Hello<hr>World') == 'Hello\n\n---\n\nWorld'
assert md('Hello<hr />World') == 'Hello\n\n---\n\nWorld'
assert md('<p>Hello</p>\n<hr>\n<p>World</p>') == 'Hello\n\n\n\n\n---\n\n\nWorld\n\n'
def test_i():
assert md('<i>Hello</i>') == '*Hello*'
def test_ol():
assert md('<ol><li>a</li><li>b</li></ol>') == '1. a\n2. b\n'
assert md('<ol start="3"><li>a</li><li>b</li></ol>') == '3. a\n4. b\n'
def test_p():
assert md('<p>hello</p>') == 'hello\n\n'
def test_strong():
assert md('<strong>Hello</strong>') == '**Hello**'
def test_ul():
assert md('<ul><li>a</li><li>b</li></ul>') == '* a\n* b\n'
def test_nested_ols():
assert md(nested_ols) == '\n1. 1\n\t1. a\n\t\t1. I\n\t\t2. II\n\t\t3. III\n\t2. b\n\t3. c\n2. 2\n3. 3\n'
def test_inline_ul():
assert md('<p>foo</p><ul><li>a</li><li>b</li></ul><p>bar</p>') == 'foo\n\n* a\n* b\n\nbar\n\n'
def test_nested_uls():
"""
Nested ULs should alternate bullet characters.
"""
assert md(nested_uls) == '\n* 1\n\t+ a\n\t\t- I\n\t\t- II\n\t\t- III\n\t+ b\n\t+ c\n* 2\n* 3\n'
def test_bullets():
assert md(nested_uls, bullets='-') == '\n- 1\n\t- a\n\t\t- I\n\t\t- II\n\t\t- III\n\t- b\n\t- c\n- 2\n- 3\n'
def test_li_text():
assert md('<ul><li>foo <a href="#">bar</a></li><li>foo bar </li><li>foo <b>bar</b> <i>space</i>.</ul>') == '* foo [bar](#)\n* foo bar\n* foo **bar** *space*.\n'
def test_img():
assert md('<img src="/path/to/img.jpg" alt="Alt text" title="Optional title" />') == '![Alt text](/path/to/img.jpg "Optional title")'
assert md('<img src="/path/to/img.jpg" alt="Alt text" />') == '![Alt text](/path/to/img.jpg)'
def test_div():
assert md('Hello</div> World') == 'Hello World'
def test_kbd():
inline_tests('kbd', '`')
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_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_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'
def test_p():
assert md('<p>hello</p>') == 'hello\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'
def test_s():
inline_tests('s', '~~')
def test_samp():
inline_tests('samp', '`')
def test_strong():
assert md('<strong>Hello</strong>') == '**Hello**'
def test_strong_em_symbol():
@@ -420,5 +203,11 @@ def test_strong_em_symbol():
assert md('<i>Hello</i>', strong_em_symbol=UNDERSCORE) == '_Hello_'
def test_newline_style():
assert md('a<br />b<br />c', newline_style=BACKSLASH) == 'a\\\nb\\\nc'
def test_sub():
assert md('<sub>foo</sub>') == 'foo'
assert md('<sub>foo</sub>', sub_symbol='~') == '~foo~'
def test_sup():
assert md('<sup>foo</sup>') == 'foo'
assert md('<sup>foo</sup>', sup_symbol='^') == '^foo^'

73
tests/test_lists.py Normal file
View File

@@ -0,0 +1,73 @@
from markdownify import markdownify as md
nested_uls = """
<ul>
<li>1
<ul>
<li>a
<ul>
<li>I</li>
<li>II</li>
<li>III</li>
</ul>
</li>
<li>b</li>
<li>c</li>
</ul>
</li>
<li>2</li>
<li>3</li>
</ul>"""
nested_ols = """
<ol>
<li>1
<ol>
<li>a
<ol>
<li>I</li>
<li>II</li>
<li>III</li>
</ol>
</li>
<li>b</li>
<li>c</li>
</ol>
</li>
<li>2</li>
<li>3</li>
</ul>"""
def test_ol():
assert md('<ol><li>a</li><li>b</li></ol>') == '1. a\n2. b\n'
assert md('<ol start="3"><li>a</li><li>b</li></ol>') == '3. a\n4. b\n'
def test_nested_ols():
assert md(nested_ols) == '\n1. 1\n\t1. a\n\t\t1. I\n\t\t2. II\n\t\t3. III\n\t2. b\n\t3. c\n2. 2\n3. 3\n'
def test_ul():
assert md('<ul><li>a</li><li>b</li></ul>') == '* a\n* b\n'
def test_inline_ul():
assert md('<p>foo</p><ul><li>a</li><li>b</li></ul><p>bar</p>') == 'foo\n\n* a\n* b\n\nbar\n\n'
def test_nested_uls():
"""
Nested ULs should alternate bullet characters.
"""
assert md(nested_uls) == '\n* 1\n\t+ a\n\t\t- I\n\t\t- II\n\t\t- III\n\t+ b\n\t+ c\n* 2\n* 3\n'
def test_bullets():
assert md(nested_uls, bullets='-') == '\n- 1\n\t- a\n\t\t- I\n\t\t- II\n\t\t- III\n\t- b\n\t- c\n- 2\n- 3\n'
def test_li_text():
assert md('<ul><li>foo <a href="#">bar</a></li><li>foo bar </li><li>foo <b>bar</b> <i>space</i>.</ul>') == '* foo [bar](#)\n* foo bar\n* foo **bar** *space*.\n'

130
tests/test_tables.py Normal file
View File

@@ -0,0 +1,130 @@
from markdownify import markdownify as md
table = """<table>
<tr>
<th>Firstname</th>
<th>Lastname</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>"""
table_with_html_content = """<table>
<tr>
<th>Firstname</th>
<th>Lastname</th>
<th>Age</th>
</tr>
<tr>
<td><b>Jill</b></td>
<td><i>Smith</i></td>
<td><a href="#">50</a></td>
</tr>
<tr>
<td>Eve</td>
<td>Jackson</td>
<td>94</td>
</tr>
</table>"""
table_with_header_column = """<table>
<tr>
<th>Firstname</th>
<th>Lastname</th>
<th>Age</th>
</tr>
<tr>
<th>Jill</th>
<td>Smith</td>
<td>50</td>
</tr>
<tr>
<th>Eve</th>
<td>Jackson</td>
<td>94</td>
</tr>
</table>"""
table_head_body = """<table>
<thead>
<tr>
<th>Firstname</th>
<th>Lastname</th>
<th>Age</th>
</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>
<th></th>
<th>Lastname</th>
<th>Age</th>
</tr>
</thead>
<tbody>
<tr>
<td>Jill</td>
<td></td>
<td>50</td>
</tr>
<tr>
<td>Eve</td>
<td>Jackson</td>
<td>94</td>
</tr>
</tbody>
</table>"""
table_missing_head = """<table>
<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>
</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_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_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'