boulder-oracle-sprint: Merged to trunk [4692].

git-svn-id: http://code.djangoproject.com/svn/django/branches/boulder-oracle-sprint@4695 bcc190cf-cafb-0310-a4f2-bffc1f526a37

4 files changed, 93 insertions, 5 deletions

diff --git a/django/utils/datastructures.py b/django/utils/datastructures.py
index 9bec7a5df7..e924e4edbc 100644
--- a/django/utils/datastructures.py
+++ b/django/utils/datastructures.py
@@ -16,8 +16,11 @@ class MergeDict(object):
 
     def __contains__(self, key):
         return self.has_key(key)
+        
+    def __copy__(self): 
+        return self.__class__(*self.dicts) 
 
-    def get(self, key, default):
+    def get(self, key, default=None):
         try:
             return self[key]
         except KeyError:
@@ -42,6 +45,10 @@ class MergeDict(object):
             if dict.has_key(key):
                 return True
         return False
+        
+    def copy(self): 
+        """ returns a copy of this object""" 
+        return self.__copy__()
 
 class SortedDict(dict):
     "A dictionary that keeps its keys in the order in which they're inserted."
@@ -85,6 +92,13 @@ class SortedDict(dict):
         "Returns the value of the item at the given zero-based index."
         return self[self.keyOrder[index]]
 
+    def copy(self):
+        "Returns a copy of this object."
+        # This way of initialising the copy means it works for subclasses, too.
+        obj = self.__class__(self)
+        obj.keyOrder = self.keyOrder
+        return obj
+
 class MultiValueDictKeyError(KeyError):
     pass
 
diff --git a/django/utils/dateformat.py b/django/utils/dateformat.py
index 00eb9fe617..e3712175af 100644
--- a/django/utils/dateformat.py
+++ b/django/utils/dateformat.py
@@ -16,7 +16,7 @@ from django.utils.tzinfo import LocalTimezone
 from calendar import isleap, monthrange
 import re, time
 
-re_formatchars = re.compile(r'(?<!\\)([aABdDfFgGhHiIjlLmMnNOPrsStTUwWyYzZ])')
+re_formatchars = re.compile(r'(?<!\\)([aAbBdDfFgGhHiIjlLmMnNOPrsStTUwWyYzZ])')
 re_escaped = re.compile(r'\\(.)')
 
 class Formatter(object):
@@ -110,6 +110,10 @@ class DateFormat(TimeFormat):
         if hasattr(self.data, 'hour') and not self.timezone:
             self.timezone = LocalTimezone(dt)
 
+    def b(self):
+        "Month, textual, 3 letters, lowercase; e.g. 'jan'"
+        return MONTHS_3[self.data.month]
+
     def d(self):
         "Day of the month, 2 digits with leading zeros; i.e. '01' to '31'"
         return '%02d' % self.data.day
diff --git a/django/utils/feedgenerator.py b/django/utils/feedgenerator.py
index 2eb27a40b7..9397789d6a 100644
--- a/django/utils/feedgenerator.py
+++ b/django/utils/feedgenerator.py
@@ -40,7 +40,7 @@ class SyndicationFeed(object):
     "Base class for all syndication feeds. Subclasses should provide write()"
     def __init__(self, title, link, description, language=None, author_email=None,
             author_name=None, author_link=None, subtitle=None, categories=None,
-            feed_url=None):
+            feed_url=None, feed_copyright=None):
         self.feed = {
             'title': title,
             'link': link,
@@ -52,12 +52,13 @@ class SyndicationFeed(object):
             'subtitle': subtitle,
             'categories': categories or (),
             'feed_url': feed_url,
+            'feed_copyright': feed_copyright,
         }
         self.items = []
 
     def add_item(self, title, link, description, author_email=None,
         author_name=None, author_link=None, pubdate=None, comments=None,
-        unique_id=None, enclosure=None, categories=()):
+        unique_id=None, enclosure=None, categories=(), item_copyright=None):
         """
         Adds an item to the feed. All args are expected to be Python Unicode
         objects except pubdate, which is a datetime.datetime object, and
@@ -75,6 +76,7 @@ class SyndicationFeed(object):
             'unique_id': unique_id,
             'enclosure': enclosure,
             'categories': categories or (),
+            'item_copyright': item_copyright,
         })
 
     def num_items(self):
@@ -128,6 +130,8 @@ class RssFeed(SyndicationFeed):
             handler.addQuickElement(u"language", self.feed['language'])
         for cat in self.feed['categories']:
             handler.addQuickElement(u"category", cat)
+        if self.feed['feed_copyright'] is not None:
+            handler.addQuickElement(u"copyright", self.feed['feed_copyright'])
         self.write_items(handler)
         self.endChannelElement(handler)
         handler.endElement(u"rss")
@@ -212,6 +216,8 @@ class Atom1Feed(SyndicationFeed):
             handler.addQuickElement(u"subtitle", self.feed['subtitle'])
         for cat in self.feed['categories']:
             handler.addQuickElement(u"category", "", {u"term": cat})
+        if self.feed['feed_copyright'] is not None:
+            handler.addQuickElement(u"rights", self.feed['feed_copyright'])
         self.write_items(handler)
         handler.endElement(u"feed")
 
@@ -252,10 +258,14 @@ class Atom1Feed(SyndicationFeed):
                      u"length": item['enclosure'].length,
                      u"type": item['enclosure'].mime_type})
 
-            # Categories:
+            # Categories.
             for cat in item['categories']:
                 handler.addQuickElement(u"category", u"", {u"term": cat})
 
+            # Rights.
+            if item['item_copyright'] is not None:
+                handler.addQuickElement(u"rights", item['item_copyright'])
+
             handler.endElement(u"entry")
 
 # This isolates the decision of what the system default is, so calling code can
diff --git a/django/utils/text.py b/django/utils/text.py
index 217f42491b..1c1c456e2d 100644
--- a/django/utils/text.py
+++ b/django/utils/text.py
@@ -41,6 +41,66 @@ def truncate_words(s, num):
             words.append('...')
     return ' '.join(words)
 
+def truncate_html_words(s, num):
+    """
+    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.
+    """
+    length = int(num)
+    if length <= 0:
+        return ''
+    html4_singlets = ('br', 'col', 'link', 'base', 'img', 'param', 'area', 'hr', 'input')
+    # Set up regular expressions
+    re_words = re.compile(r'&.*?;|<.*?>|([A-Za-z0-9][\w-]*)')
+    re_tag = re.compile(r'<(/)?([^ ]+?)(?: (/)| .*?)?>')
+    # Count non-HTML words and keep note of open tags
+    pos = 0
+    ellipsis_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:
+                ellipsis_pos = pos
+            continue
+        # Check for tag
+        tag = re_tag.match(m.group(0))
+        if not tag or ellipsis_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[:ellipsis_pos] + ' ...'
+    # Close any tags still open
+    for tag in open_tags:
+        out += '</%s>' % tag
+    # Return string
+    return out
+
 def get_valid_filename(s):
     """
     Returns the given string converted to a string that can be used for a clean