Merge branch 'develop'

Adds newlines after blockquotes, allowing for paragraphs after a
blockquote.

Due to merging problems with @lucafrance 's code I had to quickly copy
and paste their code. Thanks for the contribution!

markdownify/__init__.py

@@ -1,11 +1,11 @@
-from bs4 import BeautifulSoup, NavigableString
+from bs4 import BeautifulSoup, NavigableString, Comment
 import re
 import six
 
 
 convert_heading_re = re.compile(r'convert_h(\d+)')
 line_beginning_re = re.compile(r'^', re.MULTILINE)
-whitespace_re = re.compile(r'[\r\n\s\t ]+')
+whitespace_re = re.compile(r'[\t ]+')
 html_heading_re = re.compile(r'h[1-6]')
 
 
@@ -75,7 +75,9 @@ class MarkdownConverter(object):
 
         # Convert the children first
         for el in node.children:
-            if isinstance(el, NavigableString):
+            if isinstance(el, Comment):
+                continue
+            elif isinstance(el, NavigableString):
                 text += self.process_text(six.text_type(el))
             else:
                 text += self.process_tag(el, convert_children_as_inline)
@@ -131,7 +133,8 @@ class MarkdownConverter(object):
             return text
         href = el.get('href')
         title = el.get('title')
-        if self.options['autolinks'] and text == href and not title:
+        # For the replacement see #29: text nodes underscores are escaped
+        if self.options['autolinks'] and text.replace(r'\_', '_') == href and not title:
             # Shortcut syntax
             return '<%s>' % href
         title_part = ' "%s"' % title.replace('"', r'\"') if title else ''
@@ -145,7 +148,7 @@ class MarkdownConverter(object):
         if convert_as_inline:
             return text
 
-        return '\n' + line_beginning_re.sub('> ', text) if text else ''
+        return '\n' + (line_beginning_re.sub('> ', text) + '\n\n') if text else ''
 
     def convert_br(self, el, text, convert_as_inline):
         if convert_as_inline:

setup.py

@@ -10,7 +10,7 @@ read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.6.0',
+    '__version__': '0.6.4',
 }
 
 

tests/test_advanced.py

@@ -4,3 +4,13 @@ from markdownify import markdownify as md
 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'
+
+
+def test_ignore_comments():
+    text = md("<!-- This is a comment -->")
+    assert text == ""
+
+
+def test_ignore_comments_with_other_tags():
+    text = md("<!-- This is a comment --><a href='http://example.com/'>example link</a>")
+    assert text == "[example link](http://example.com/)"

tests/test_basic.py

@@ -10,4 +10,4 @@ def test_soup():
 
 
 def test_whitespace():
-    assert md(' a  b \n\n c ') == ' a b c '
+    assert md(' a  b \t\t c ') == ' a b c '

tests/test_conversions.py

@@ -34,7 +34,11 @@ def test_chomp():
 
 
 def test_a():
-    assert md('<a href="http://google.com">Google</a>') == '[Google](http://google.com)'
+    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)'
 
 
 def test_a_spaces():
@@ -71,12 +75,16 @@ def test_b_spaces():
 
 
 def test_blockquote():
-    assert md('<blockquote>Hello</blockquote>').strip() == '> Hello'
+    assert md('<blockquote>Hello</blockquote>') == '\n> Hello\n\n'
+
+
+def test_blockquote_with_paragraph():
+    assert md('<blockquote>Hello</blockquote><p>handsome</p>') == '\n> Hello\n\nhandsome\n\n'
 
 
 def test_nested_blockquote():
-    text = md('<blockquote>And she was like <blockquote>Hello</blockquote></blockquote>').strip()
+    text = md('<blockquote>And she was like <blockquote>Hello</blockquote></blockquote>')
-    assert text == '> And she was like \n> > Hello'
+    assert text == '\n> And she was like \n> > Hello\n> \n> \n\n'
 
 
 def test_br():
@@ -107,6 +115,11 @@ def test_hn():
     assert md('<h6>Hello</h6>') == '###### Hello\n\n'
 
 
+def test_hn_chained():
+    assert md('<h1>First</h1>\n<h2>Second</h2>\n<h3>Third</h3>', heading_style=ATX) == '# First\n\n\n## Second\n\n\n### Third\n\n'
+    assert md('X<h1>First</h1>', heading_style=ATX) == 'X# First\n\n'
+
+
 def test_hn_nested_tag_heading_style():
     assert md('<h1>A <p>P</p> C </h1>', heading_style=ATX_CLOSED) == '# A P C #\n\n'
     assert md('<h1>A <p>P</p> C </h1>', heading_style=ATX) == '# A P C\n\n'