fix silly regression on pre formatting

[rss2maildir.git] / rss2maildir.py

diff --git a/rss2maildir.py b/rss2maildir.py
index b91428674ab036254d65a9cefb63fd04aa2db9c7..e8883b1200dd5fd80d58ec890a7cbb733d15877d 100755 (executable)
--- a/rss2maildir.py
+++ b/rss2maildir.py
@@ -99,6 +99,7 @@ class HTML2Text(HTMLParser):
         self.ignorenodata = False
         self.listcount = []
         self.urls = []
         self.ignorenodata = False
         self.listcount = []
         self.urls = []

+        self.images = {}

         HTMLParser.__init__(self)
 
     def handle_starttag(self, tag, attrs):
         HTMLParser.__init__(self)
 
     def handle_starttag(self, tag, attrs):


@@ -151,7 +152,7 @@ class HTML2Text(HTMLParser):
             elif tag_name == u'a':
                 for attr in attrs:
                     if attr[0].lower() == u'href':
             elif tag_name == u'a':
                 for attr in attrs:
                     if attr[0].lower() == u'href':

-                        self.urls.append(attr[1])
+                        self.urls.append(attr[1].decode('utf-8'))

                 self.curdata = self.curdata + u'`'
                 self.opentags.append(tag_name)
                 return
                 self.curdata = self.curdata + u'`'
                 self.opentags.append(tag_name)
                 return


@@ -187,16 +188,31 @@ class HTML2Text(HTMLParser):
             elif attr[0] == 'src':
                 url = attr[1].decode('utf-8')
         if url:
             elif attr[0] == 'src':
                 url = attr[1].decode('utf-8')
         if url:

-            self.curdata = self.curdata \
-                + u' [img:' \
-                + url

             if alt:
             if alt:

-                self.curdata = self.curdata \
-                    + u'(' \
-                    + alt \
-                    + u')'
-            self.curdata = self.curdata \
-                + u']'
+                if self.images.has_key(alt):
+                    if self.images[alt]["url"] == url:
+                        self.curdata = self.curdata \
+                            + u'|%s|' %(alt,)
+                    else:
+                        while self.images.has_key(alt):
+                            alt = alt + "_"
+                        self.images[alt]["url"] = url
+                        self.curdata = self.curdata \
+                            + u'|%s|' %(alt,)
+                else:
+                    self.images[alt] = {}
+                    self.images[alt]["url"] = url
+                    self.curdata = self.curdata \
+                        + u'|%s|' %(alt,)
+            else:
+                if self.images.has_key(url):
+                    self.curdata = self.curdata \
+                        + u'|%s|' %(url,)
+                else:
+                    self.images[url] = {}
+                    self.images[url]["url"] =url
+                    self.curdata = self.curdata \
+                        + u'|%s|' %(url,)

 
     def handle_curdata(self):
 
 
     def handle_curdata(self):
 


@@ -235,7 +251,7 @@ class HTML2Text(HTMLParser):
         if tag_thats_done in ["h1", "h2", "h3", "h4", "h5", "h6"]:
             underline = u''
             underlinechar = u'='
         if tag_thats_done in ["h1", "h2", "h3", "h4", "h5", "h6"]:
             underline = u''
             underlinechar = u'='

-            headingtext = self.curdata
+            headingtext = " ".join(self.curdata.split())

             seperator = u'\n' + u' '*self.indentlevel
             headingtext = seperator.join( \
                 textwrap.wrap( \
             seperator = u'\n' + u' '*self.indentlevel
             headingtext = seperator.join( \
                 textwrap.wrap( \


@@ -260,7 +276,8 @@ class HTML2Text(HTMLParser):
                 + underline
         elif tag_thats_done in [u'p', u'div']:
             paragraph = unicode( \
                 + underline
         elif tag_thats_done in [u'p', u'div']:
             paragraph = unicode( \

-                self.curdata.strip().encode("utf-8"), "utf-8")
+                " ".join(self.curdata.strip().encode("utf-8").split()), \
+                "utf-8")

             seperator = u'\n' + u' ' * self.indentlevel
             self.text = self.text \
                 + u' ' * self.indentlevel \
             seperator = u'\n' + u' ' * self.indentlevel
             self.text = self.text \
                 + u' ' * self.indentlevel \


@@ -272,7 +289,8 @@ class HTML2Text(HTMLParser):
                 self.curdata.encode("utf-8"), "utf-8")
         elif tag_thats_done == u'blockquote':
             quote = unicode( \
                 self.curdata.encode("utf-8"), "utf-8")
         elif tag_thats_done == u'blockquote':
             quote = unicode( \

-                self.curdata.encode("utf-8").strip(), "utf-8")
+                " ".join(self.curdata.encode("utf-8").strip().split()), \
+                "utf-8")

             seperator = u'\n' + u' ' * self.indentlevel + u'> '
             if len(self.text) > 0 and self.text[-1] != u'\n':
                 self.text = self.text + u'\n'
             seperator = u'\n' + u' ' * self.indentlevel + u'> '
             if len(self.text) > 0 and self.text[-1] != u'\n':
                 self.text = self.text + u'\n'


@@ -324,7 +342,9 @@ class HTML2Text(HTMLParser):
                 )
             self.curdata = u''
         elif tag_thats_done == u'dt':
                 )
             self.curdata = u''
         elif tag_thats_done == u'dt':

-            definition = unicode(self.curdata.encode("utf-8").strip(), "utf-8")
+            definition = unicode(" ".join( \
+                    self.curdata.encode("utf-8").strip().split()), \
+                "utf-8")

             if len(self.text) > 0 and self.text[-1] != u'\n':
                 self.text = self.text + u'\n\n'
             elif len(self.text) > 1 and self.text[-2] != u'\n':
             if len(self.text) > 0 and self.text[-1] != u'\n':
                 self.text = self.text + u'\n\n'
             elif len(self.text) > 1 and self.text[-2] != u'\n':


@@ -337,7 +357,9 @@ class HTML2Text(HTMLParser):
                         self.textwidth - self.indentlevel - 1))
             self.curdata = u''
         elif tag_thats_done == u'dd':
                         self.textwidth - self.indentlevel - 1))
             self.curdata = u''
         elif tag_thats_done == u'dd':

-            definition = unicode(self.curdata.encode("utf-8").strip(), "utf-8")
+            definition = unicode(" ".join( \
+                    self.curdata.encode("utf-8").strip().split()),
+                "utf-8")

             if len(definition) > 0:
                 if len(self.text) > 0 and self.text[-1] != u'\n':
                     self.text = self.text + u'\n'
             if len(definition) > 0:
                 if len(self.text) > 0 and self.text[-1] != u'\n':
                     self.text = self.text + u'\n'


@@ -438,6 +460,12 @@ class HTML2Text(HTMLParser):
         if len(self.urls) > 0:
             self.text = self.text + u'\n__ ' + u'\n__ '.join(self.urls) + u'\n'
             self.urls = []
         if len(self.urls) > 0:
             self.text = self.text + u'\n__ ' + u'\n__ '.join(self.urls) + u'\n'
             self.urls = []

+        if len(self.images.keys()) > 0:
+            self.text = self.text + u'\n.. ' \
+                + u'.. '.join( \
+                    ["|%s| image:: %s" %(a, self.images[a]["url"]) \
+                for a in self.images.keys()]) + u'\n'
+            self.images = {}

         return self.text
 
 def open_url(method, url):
         return self.text
 
 def open_url(method, url):