Replace LineBreaks preprocessor with an inlinePattern and update tests. Blank lines (" \n") and headers no longer get linebreaks and the two spaces are no longer preserved.

6 files changed, 31 insertions, 50 deletions

diff --git a/markdown.py b/markdown.py
index fbaeb84..3042138 100644
--- a/markdown.py
+++ b/markdown.py
@@ -332,7 +332,7 @@ class Element :
 
         buffer += childBuffer
 
-        if self.nodeName in ['p', 'li', 'ul', 'ol',
+        if self.nodeName in ['p', 'br ', 'li', 'ul', 'ol',
                              'h1', 'h2', 'h3', 'h4'] :
             buffer += "\n"
 
@@ -464,19 +464,6 @@ class LinePreprocessor (Preprocessor):
 LINE_PREPROCESSOR = LinePreprocessor()
 
 
-class LineBreaksPreprocessor (Preprocessor):
-    """Replaces double spaces at the end of the lines with <br/ >."""
-
-    def run (self, lines) :
-        for i in range(len(lines)) :
-            if (lines[i].endswith("  ")
-                and not RE.regExp['tabbed'].match(lines[i]) ):
-                lines[i] += self.stash.store("<br />", safe=True)
-        return lines
-
-LINE_BREAKS_PREPROCESSOR = LineBreaksPreprocessor()
-
-
 class HtmlBlockPreprocessor (Preprocessor):
     """Removes html blocks from self.lines"""
     
@@ -678,6 +665,8 @@ AUTOMAIL_RE = r'<([^> \!]*@[^> ]*)>'               # <me@example.com>
 #HTML_RE = r'(\<[^\>]*\>)'                        # <...>
 HTML_RE = r'(\<[a-zA-Z/][^\>]*\>)'               # <...>
 ENTITY_RE = r'(&[\#a-zA-Z0-9]*;)'                # &amp;
+LINE_BREAK_RE = r'  \n'                     # two spaces at end of line
+LINE_BREAK_2_RE = r'  $'                    # two spaces at end of text
 
 class Pattern:
 
@@ -706,6 +695,11 @@ class SimpleTagPattern (Pattern):
         el.appendChild(doc.createTextNode(m.group(2)))
         return el
 
+class SubstituteTagPattern (SimpleTagPattern):
+
+    def handleMatch (self, m, doc) :
+        return doc.createElement(self.tag)
+
 class BacktickPattern (Pattern):
 
     def __init__ (self, pattern):
@@ -856,6 +850,9 @@ EMPHASIS_PATTERN_2      = SimpleTagPattern(EMPHASIS_2_RE, 'em')
 STRONG_EM_PATTERN       = DoubleTagPattern(STRONG_EM_RE, 'strong,em')
 STRONG_EM_PATTERN_2     = DoubleTagPattern(STRONG_EM_2_RE, 'strong,em')
 
+LINE_BREAK_PATTERN      = SubstituteTagPattern(LINE_BREAK_RE, 'br ')
+LINE_BREAK_PATTERN_2    = SubstituteTagPattern(LINE_BREAK_2_RE, 'br ')
+
 LINK_PATTERN            = LinkPattern(LINK_RE)
 LINK_ANGLED_PATTERN     = LinkPattern(LINK_ANGLED_RE)
 IMAGE_LINK_PATTERN      = ImagePattern(IMAGE_LINK_RE)
@@ -1023,7 +1020,7 @@ class CorePatterns :
         effort."""
 
     patterns = {
-        'header':          r'(#*)([^#]*)(#*)', # # A title
+        'header':          r'(#*)\s*([^#]*)(#*)', # # A title
         'reference-def' :  r'(\ ?\ ?\ ?)\[([^\]]*)\]:\s*([^ ]*)(.*)',
                            # [Google]: http://www.google.com/
         'containsline':    r'([-]*)$|^([=]*)', # -----, =====, etc.
@@ -1075,7 +1072,6 @@ class Markdown:
 
         self.preprocessors = [ HEADER_PREPROCESSOR,
                                LINE_PREPROCESSOR,
-                               LINE_BREAKS_PREPROCESSOR,
                                # A footnote preprocessor will
                                # get inserted here
                                REFERENCE_PREPROCESSOR ]
@@ -1100,6 +1096,8 @@ class Markdown:
                                 LINK_PATTERN,
                                 AUTOLINK_PATTERN,
                                 AUTOMAIL_PATTERN,
+                                LINE_BREAK_PATTERN_2,
+                                LINE_BREAK_PATTERN,
                                 HTML_PATTERN,
                                 ENTITY_PATTERN,
                                 NOT_STRONG_PATTERN,
@@ -1158,7 +1156,6 @@ class Markdown:
 
         HTML_BLOCK_PREPROCESSOR.stash = self.htmlStash
         LINE_PREPROCESSOR.stash = self.htmlStash
-        LINE_BREAKS_PREPROCESSOR.stash = self.htmlStash
         REFERENCE_PREPROCESSOR.references = self.references
         HTML_PATTERN.stash = self.htmlStash
         ENTITY_PATTERN.stash = self.htmlStash
diff --git a/tests/markdown-test/markdown-documentation-basics.html b/tests/markdown-test/markdown-documentation-basics.html
index fdfc33b..1dafe24 100644
--- a/tests/markdown-test/markdown-documentation-basics.html
+++ b/tests/markdown-test/markdown-documentation-basics.html
@@ -1,5 +1,3 @@
-
-
 <h1>Markdown: Basics</h1>
 <ul id="ProjectSubmenu">
     <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li>
@@ -103,9 +101,7 @@ Some of these words &lt;em&gt;are emphasized also&lt;/em&gt;.&lt;/p&gt;
 
 &lt;p&gt;Use two asterisks for &lt;strong&gt;strong emphasis&lt;/strong&gt;.
 Or, if you prefer, &lt;strong&gt;use two underscores instead&lt;/strong&gt;.&lt;/p&gt;
-</code></pre><p>   <br />
-</p>
-
+</code></pre>
 <h2>Lists</h2>
 <p>Unordered (bulleted) lists use asterisks, pluses, and hyphens (<code>*</code>,
    <code>+</code>, and <code>-</code>) as list markers. These three markers are
@@ -262,5 +258,4 @@ you've got to put paragraph tags in your blockquotes:&lt;/p&gt;
     &amp;lt;p&amp;gt;For example.&amp;lt;/p&amp;gt;
 &amp;lt;/blockquote&amp;gt;
 &lt;/code&gt;&lt;/pre&gt;
-</code></pre>
-
+</code></pre>
\ No newline at end of file
diff --git a/tests/misc/headers.html b/tests/misc/headers.html
index 306eb65..61bc266 100644
--- a/tests/misc/headers.html
+++ b/tests/misc/headers.html
@@ -1,14 +1,10 @@
-
-
 <h3>Hello world</h3>
 <p>Line 2
    Line 3
 </p>
 
-<h1>[Markdown][5]  <br /></h1>
+<h1>[Markdown][5]</h1>
 
 <h1><a href="http://some.link.com/">Markdown</a></h1>
 
-<h1>[5]: http://foo.com/</h1>
-
-
+<h1>[5]: http://foo.com/</h1>
\ No newline at end of file
diff --git a/tests/misc/html.html b/tests/misc/html.html
index 6db122a..1209112 100644
--- a/tests/misc/html.html
+++ b/tests/misc/html.html
@@ -1,13 +1,10 @@
-
 <h1>Block level html</h1>
 
-<p>Some inline <b>stuff<b>.  <br />
+<p>Some inline <b>stuff<b>.<br />
 </p>
 <p>Now some <arbitrary>arbitrary tags</arbitrary>.
 </p>
 <p>And of course <script>blah</script>.
 </p>
 <p><a href="script&gt;stuff&lt;/script">this <script>link</a>
-</p>
-
-
+</p>
\ No newline at end of file
diff --git a/tests/misc/some-test.html b/tests/misc/some-test.html
index 9a6655e..646482e 100644
--- a/tests/misc/some-test.html
+++ b/tests/misc/some-test.html
@@ -1,4 +1,3 @@
-
 <hr />
 
 <ul>
@@ -66,12 +65,13 @@
  <li><p>Python is
    ok
    Or not?
-      <br />
-   Here is a normal paragraph
 </p>
 
  </li>
-
+</ul>
+<p>Here is a normal paragraph
+</p>
+<ol>
  <li><p>Another list
    with a bunch of items
 </p>
@@ -91,7 +91,7 @@
 </ol>
 
  </li>
-</ul>
+</ol>
 <p>asdfasdfasd
 </p>
 <pre><code># This is a code example
@@ -101,5 +101,4 @@ Another code example
 * Lists and similar stuff
 
 &gt; Should be ignored
-</code></pre>
-
+</code></pre>
\ No newline at end of file
diff --git a/tests/misc/two-spaces.html b/tests/misc/two-spaces.html
index 10f8483..e66fe43 100644
--- a/tests/misc/two-spaces.html
+++ b/tests/misc/two-spaces.html
@@ -1,9 +1,6 @@
-
-<p>This line has two spaces at the end  <br />
-   but this one has none
-   but this line has three   <br />
-   and this is the second from last line
+<p>This line has two spaces at the end<br />
+but this one has none
+   but this line has three <br />
+and this is the second from last line
    in this test message
-</p>
-
-
+</p>
\ No newline at end of file