Merge branch 'develop'

Author: AlexVonB

README.rst

@@ -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,

markdownify/__init__.py

@@ -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 @@ def convert_a(self, el, text, convert_as_inline):
         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 @@ def convert_pre(self, el, text, convert_as_inline):
 
     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'
 

setup.py

@@ -10,7 +10,7 @@
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.8.1',
+    '__version__': '0.9.0',
 }
 
 

tests/test_advanced.py

@@ -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'