1 files changed, 50 insertions, 21 deletions

diff --git a/panfry/page.py b/panfry/page.py
index 27b4cb1..2c82e04 100755
--- a/panfry/page.py
+++ b/panfry/page.py
@@ -1,18 +1,35 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 import re
-from panfry.utils import get_lines
 
 
-class Page:
+class TextFile:
     '''
-    Represents single source file.
+    Basic text file class
     '''
     def __init__(self, filename, source):
         self.filename = filename
         self.source = source
 
     @property
+    def lines(self):
+        '''
+        Returns list of lines from source.
+        Leading and trailing blank lines are removed.
+        '''
+        return self.source.strip().split('\n')
+
+    @property
+    def firstline(self):
+        return self.lines[0]
+
+
+class Page(TextFile):
+    '''
+    Represents single page source file.
+    '''
+
+    @property
     def title(self):
         '''
         Returns a tuple containing a string representing the page title
@@ -32,27 +49,39 @@ class Page:
         the filename is returned as the title with underscores changed
         to spaces.
         '''
-        title = ''
-        for line in get_lines(self.source):
-            if line.startswith('% '):
-                title = line.split(' ', 1)[1].strip()
-                if '(' and ')' in line:
-                    num = line.split('(')[1][0]
-                    return 'man(%s) %s' % (num, title.split('(')[0].strip())
-                else:
-                    return (title, 1)
-            if re.match('[=]{2}', line):
-                return (title, 1)
-            if re.match('[-]{2}', line):
-                return (title, 2)
+        if self.lines[0].startswith('%'):
+            title = (self.lines[0].split(' ', 1)[1].strip(), 1)
+        elif self.toc:
+            title = self.toc[0]
+        else:
+            title = (self.filename.replace('_', ' '), 1)
+
+        return title
+
+    @property
+    def toc(self):
+        '''
+        Returns a list of tuples representing the headings/sub-heading
+        structure of the page.
+        The first element of each tuple is the heading text.
+        The second element of each tuple is the heading level.
+        '''
+        toc = []
+        heading = ''
+        for line in self.lines:
+            if heading and re.match('[=]{2}', line):
+                toc.append((heading, 1))
+                continue
+            if heading and re.match('[-]{2}', line):
+                toc.append((heading, 2))
+                continue
             if re.match('#+.+[A-z|0-9]', line):
                 level = len(re.match('#+', line).group())
-                return (line.split(' ', 1)[1].strip(), level)
-            title = line.strip()
-
-        title = self.filename.replace('_', ' ')
+                toc.append((line.split(' ', 1)[1].strip(), level))
+                continue
+            heading = line.strip()
 
-        return (title, 1)
+        return toc
 
     @property
     def htmlfile(self):