Merge branch 'develop'

Ordered list update

README.rst

@@ -75,6 +75,18 @@ bullets
   lists are nested. Otherwise, the bullet will alternate based on nesting
   level. Defaults to ``'*+-'``.
 
+strong_em_symbol
+  In markdown, both ``*`` and ``_`` are used to encode **strong** or
+  *emphasized* texts. Either of these symbols can be chosen by the options
+  ``ASTERISK`` (default) or ``UNDERSCORE`` respectively.
+
+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
+  newline). While the latter convention is non-standard, it is commonly
+  preferred and supported by a lot of interpreters.
+
 Options may be specified as kwargs to the ``markdownify`` function, or as a
 nested ``Options`` class in ``MarkdownConverter`` subclasses.
 

markdownify/__init__.py

@@ -6,6 +6,7 @@ import six
 convert_heading_re = re.compile(r'convert_h(\d+)')
 line_beginning_re = re.compile(r'^', re.MULTILINE)
 whitespace_re = re.compile(r'[\t ]+')
+all_whitespace_re = re.compile(r'[\s]+')
 html_heading_re = re.compile(r'h[1-6]')
 
 
@@ -15,6 +16,14 @@ ATX_CLOSED = 'atx_closed'
 UNDERLINED = 'underlined'
 SETEXT = UNDERLINED
 
+# Newline style
+SPACES = 'spaces'
+BACKSLASH = 'backslash'
+
+# Strong and emphasis style
+ASTERISK = '*'
+UNDERSCORE = '_'
+
 
 def escape(text):
     if not text:
@@ -46,6 +55,8 @@ class MarkdownConverter(object):
         autolinks = True
         heading_style = UNDERLINED
         bullets = '*+-'  # An iterable of bullet types.
+        strong_em_symbol = ASTERISK
+        newline_style = SPACES
 
     class Options(DefaultOptions):
         pass
@@ -73,12 +84,18 @@ class MarkdownConverter(object):
         if not children_only and isHeading:
             convert_children_as_inline = True
 
+        # Remove whitespace-only textnodes in lists
+        if node.name in ['ol', 'ul', 'li']:
+            for el in node.children:
+                if isinstance(el, NavigableString) and six.text_type(el).strip() == '':
+                    el.extract()
+
         # Convert the children first
         for el in node.children:
             if isinstance(el, Comment):
                 continue
             elif isinstance(el, NavigableString):
-                text += self.process_text(six.text_type(el))
+                text += self.process_text(el)
             else:
                 text += self.process_tag(el, convert_children_as_inline)
 
@@ -89,7 +106,10 @@ class MarkdownConverter(object):
 
         return text
 
-    def process_text(self, text):
+    def process_text(self, el):
+        text = six.text_type(el)
+        if el.parent.name == 'li':
+            return escape(all_whitespace_re.sub(' ', text or '')).rstrip()
         return escape(whitespace_re.sub(' ', text or ''))
 
     def __getattr__(self, attr):
@@ -154,19 +174,23 @@ class MarkdownConverter(object):
         if convert_as_inline:
             return ""
 
-        return '  \n'
+        if self.options['newline_style'].lower() == BACKSLASH:
+            return '\\\n'
+        else:
+            return '  \n'
 
     def convert_em(self, el, text, convert_as_inline):
+        em_tag = self.options['strong_em_symbol']
         prefix, suffix, text = chomp(text)
         if not text:
             return ''
-        return '%s*%s*%s' % (prefix, text, suffix)
+        return '%s%s%s%s%s' % (prefix, em_tag, text, em_tag, suffix)
 
     def convert_hn(self, n, el, text, convert_as_inline):
         if convert_as_inline:
             return text
 
-        style = self.options['heading_style']
+        style = self.options['heading_style'].lower()
         text = text.rstrip()
         if style == UNDERLINED and n <= 2:
             line = '=' if n == 1 else '-'
@@ -185,6 +209,9 @@ class MarkdownConverter(object):
         # Ignoring convert_to_inline for list.
 
         nested = False
+        before_paragraph = False
+        if el.next_sibling and el.next_sibling.name not in ['ul', 'ol']:
+            before_paragraph = True
         while el:
             if el.name == 'li':
                 nested = True
@@ -193,7 +220,7 @@ class MarkdownConverter(object):
         if nested:
             # remove trailing newline if nested
             return '\n' + self.indent(text, 1).rstrip()
-        return '\n' + text + '\n'
+        return text + ('\n' if before_paragraph else '')
 
     convert_ul = convert_list
     convert_ol = convert_list
@@ -222,10 +249,11 @@ class MarkdownConverter(object):
         return '%s\n\n' % text if text else ''
 
     def convert_strong(self, el, text, convert_as_inline):
+        strong_tag = 2 * self.options['strong_em_symbol']
         prefix, suffix, text = chomp(text)
         if not text:
             return ''
-        return '%s**%s**%s' % (prefix, text, suffix)
+        return '%s%s%s%s%s' % (prefix, strong_tag, text, strong_tag, suffix)
 
     def convert_img(self, el, text, convert_as_inline):
         alt = el.attrs.get('alt', None) or ''
@@ -237,6 +265,26 @@ class MarkdownConverter(object):
 
         return '![%s](%s%s)' % (alt, src, title_part)
 
+    def convert_table(self, el, text, convert_as_inline):
+        rows = el.find_all('tr')
+        text_data = []
+        for row in rows:
+            headers = row.find_all('th')
+            columns = row.find_all('td')
+            if len(headers) > 0:
+                headers = [head.text.strip() for head in headers]
+                text_data.append('| ' + ' | '.join(headers) + ' |')
+                text_data.append('| ' + ' | '.join(['---'] * len(headers)) + ' |')
+            elif len(columns) > 0:
+                columns = [colm.text.strip() for colm in columns]
+                text_data.append('| ' + ' | '.join(columns) + ' |')
+            else:
+                continue
+        return '\n'.join(text_data)
+
+    def convert_hr(self, el, text, convert_as_inline):
+        return '\n\n---\n\n'
+
 
 def markdownify(html, **options):
     return MarkdownConverter(**options).convert(html)

setup.py

@@ -10,7 +10,7 @@ read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.6.5',
+    '__version__': '0.7.2',
 }
 
 

tests/test_conversions.py

@@ -1,8 +1,8 @@
-from markdownify import markdownify as md, ATX, ATX_CLOSED
+from markdownify import markdownify as md, ATX, ATX_CLOSED, BACKSLASH, UNDERSCORE
 import re
 
 
-nested_uls = re.sub(r'\s+', '', """
+nested_uls = """
     <ul>
         <li>1
             <ul>
@@ -19,7 +19,96 @@ nested_uls = re.sub(r'\s+', '', """
         </li>
         <li>2</li>
         <li>3</li>
-    </ul>""")
+    </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 = re.sub(r'\s+', '', """
+<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_head_body = re.sub(r'\s+', '', """
+<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 = re.sub(r'\s+', '', """
+<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>
+""")
 
 
 def test_chomp():
@@ -159,7 +248,9 @@ def test_hn_nested_img():
 
 
 def test_hr():
-    assert md('<hr>hr</hr>') == '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_head():
@@ -181,8 +272,8 @@ def test_i():
 
 
 def test_ol():
-    assert md('<ol><li>a</li><li>b</li></ol>') == '\n1. a\n2. b\n\n'
+    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>') == '\n3. a\n4. b\n\n'
+    assert md('<ol start="3"><li>a</li><li>b</li></ol>') == '3. a\n4. b\n'
 
 
 def test_p():
@@ -194,11 +285,15 @@ def test_strong():
 
 
 def test_ul():
-    assert md('<ul><li>a</li><li>b</li></ul>') == '\n* a\n* b\n\n'
+    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\n* a\n* b\n\nbar\n\n'
+    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():
@@ -206,11 +301,11 @@ 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\n'
+    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\n'
+    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_img():
@@ -220,3 +315,20 @@ def test_img():
 
 def test_div():
     assert md('Hello</div> World') == 'Hello World'
+
+
+def test_table():
+    assert md(table) == '| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |'
+    assert md(table_head_body) == '| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |'
+    assert md(table_missing_text) == '|  | Lastname | Age |\n| --- | --- | --- |\n| Jill |  | 50 |\n| Eve | Jackson | 94 |'
+
+
+def test_strong_em_symbol():
+    assert md('<strong>Hello</strong>', strong_em_symbol=UNDERSCORE) == '__Hello__'
+    assert md('<b>Hello</b>', strong_em_symbol=UNDERSCORE) == '__Hello__'
+    assert md('<em>Hello</em>', strong_em_symbol=UNDERSCORE) == '_Hello_'
+    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'