simplifying link parsing

src/markdown_headers.py

@@ -1,6 +1,8 @@
 from collections import OrderedDict
+from re import compile
 
 class MarkdownHeader:
+    pattern = compile('(=+)(.*?)(=+)')
     head = "="
     config = {
         '======': 1,
@@ -11,13 +13,9 @@ class MarkdownHeader:
     }
 
     def convert(self, text):
-        config = OrderedDict(sorted(MarkdownHeader.config.items(), key = lambda t : t[1]))
+        result = text
-
+        for regex_head in MarkdownHeader.pattern.findall(text):
-        for key, val in config.items():
+            orig_header = regex_head[0] + regex_head[1] + regex_head[2]
-            if text.startswith(key):
+            new_header = ('#' * MarkdownHeader.config[regex_head[0]]) + regex_head[1]
-                return ('#' * val) + self.strip(text)
+            result = result.replace(orig_header, new_header)
-        return text
+        return result
-
-
-    def strip(self, text):
-        return text.replace(MarkdownHeader.head, "")

src/markdown_links.py

@@ -3,17 +3,17 @@ from os import walk
 import re
 
 class MarkdownLinks:
-    known_shortcodes = ('wp')
+    # see http://pythex.org/
-    pattern = re.compile('\[\[(.*?)\]\]')
+    pattern = re.compile('(\[\[)(.*?)(\]\])')
 
     def convert(self, text):
         result = text
         for regex_link in MarkdownLinks.pattern.findall(text):
-            origlink = "[[" + regex_link + "]]"
+            origlink = ''.join(regex_link)
             convertedlink = ""
-            if "http" in regex_link or "www" in regex_link:
+            if "http" in origlink or "www" in origlink:
                 convertedlink = self.convert_as_external_link(origlink)
-            elif ">" in regex_link:
+            elif ">" in origlink:
                 convertedlink = self.convert_as_interwiki_link(origlink)
             else:
                 convertedlink = self.convert_as_internal_link(origlink)