Theme modifications, add a summary for the articles.

pelican/bloggenerator.py

@@ -13,6 +13,7 @@ from feedgenerator import Atom1Feed
 
 # import the directives to have pygments support
 import rstdirectives
+from utils import truncate_html_words
 
 ## Constants ##########################################################
 
@@ -58,6 +59,13 @@ def generate_blog(path=None, theme=None, output_path=None, markup=None,
     # get the list of files to parse
     if not path:
         raise Exception('you need to specify a path to search the docs on !')
+
+    # remove all the existing content from the output folder
+    try:
+        shutil.rmtree(os.path.join(output_path))
+    except:
+        pass
+
     files = []
     for root, dirs, temp_files in os.walk(path, followlinks=True):
         files.extend([os.sep.join((root, f)) for f in temp_files
@@ -119,14 +127,9 @@ def generate_blog(path=None, theme=None, output_path=None, markup=None,
     # copy static paths to output
     for path in context['STATIC_PATHS']:
         try:
-            real_output = os.path.join(output_path, path)
-            theme_path = os.path.join(theme, path)
-
-            print "updating %s" % real_output
-            shutil.rmtree(real_output)
-            shutil.copytree(theme_path, real_output)
-
-        except OSError as e:
+            shutil.copytree(os.path.join(theme, path),
+                            os.path.join(output_path, path))
+        except OSError:
             pass
 
 
@@ -304,4 +307,4 @@ class Article(object):
 
     @property
     def summary(self):
-        return self.content
+        return truncate_html_words(self.content, 50)

pelican/utils.py

@@ -0,0 +1,67 @@
+import re
+
+def truncate_html_words(s, num, end_text='...'):
+    """Truncates HTML to a certain number of words (not counting tags and
+    comments). Closes opened tags if they were correctly closed in the given
+    html. Takes an optional argument of what should be used to notify that the
+    string has been truncated, defaulting to ellipsis (...).
+
+    Newlines in the HTML are preserved.
+    From the django framework.
+    """
+    length = int(num)
+    if length <= 0:
+        return u''
+    html4_singlets = ('br', 'col', 'link', 'base', 'img', 'param', 'area', 'hr', 'input')
+    # Set up regular expressions
+    re_words = re.compile(r'&.*?;|<.*?>|(\w[\w-]*)', re.U)
+    re_tag = re.compile(r'<(/)?([^ ]+?)(?: (/)| .*?)?>')
+    # Count non-HTML words and keep note of open tags
+    pos = 0
+    end_text_pos = 0
+    words = 0
+    open_tags = []
+    while words <= length:
+        m = re_words.search(s, pos)
+        if not m:
+            # Checked through whole string
+            break
+        pos = m.end(0)
+        if m.group(1):
+            # It's an actual non-HTML word
+            words += 1
+            if words == length:
+                end_text_pos = pos
+            continue
+        # Check for tag
+        tag = re_tag.match(m.group(0))
+        if not tag or end_text_pos:
+            # Don't worry about non tags or tags after our truncate point
+            continue
+        closing_tag, tagname, self_closing = tag.groups()
+        tagname = tagname.lower()  # Element names are always case-insensitive
+        if self_closing or tagname in html4_singlets:
+            pass
+        elif closing_tag:
+            # Check for match in open tags list
+            try:
+                i = open_tags.index(tagname)
+            except ValueError:
+                pass
+            else:
+                # SGML: An end tag closes, back to the matching start tag, all unclosed intervening start tags with omitted end tags
+                open_tags = open_tags[i+1:]
+        else:
+            # Add it to the start of the open tags list
+            open_tags.insert(0, tagname)
+    if words <= length:
+        # Don't try to close tags if we don't need to truncate
+        return s
+    out = s[:end_text_pos]
+    if end_text:
+        out += ' ' + end_text
+    # Close any tags still open
+    for tag in open_tags:
+        out += '</%s>' % tag
+    # Return string
+    return out