Copyright 2013

[phdru.name/phdru.name.git] / reindex_blog.py

diff --git a/reindex_blog.py b/reindex_blog.py
index f2872c17861574f57f724eb8cdf236543770189f..197c1c6956db3b3972f1a41a01791b607a3fc1b8 100755 (executable)
--- a/reindex_blog.py
+++ b/reindex_blog.py
@@ -2,7 +2,7 @@
 # -*- coding: koi8-r -*-
 
 __author__ = "Oleg Broytman <phd@phdru.name>"
-__copyright__ = "Copyright (C) 2006-2012 PhiloSoft Design"
+__copyright__ = "Copyright (C) 2006-2013 PhiloSoft Design"
 
 import sys, os
 
@@ -49,13 +49,14 @@ for dirpath, dirs, files in os.walk(blog_root):
          continue
       fullpath = os.path.join(dirpath, file)
       template = Template(file=fullpath)
-      title_parts = template.Title.split()
+      title_parts = template.Title.decode('utf-8').encode('koi8-r').split()
       title = ' '.join(title_parts[6:])
-      lead = template.Lead
+      lead = template.Lead.decode('utf-8').encode('koi8-r')
 
       tags = template.Tag
       if isinstance(tags, basestring):
          tags = (tags,)
+      tags = [tag.decode('utf-8').encode('koi8-r') for tag in tags]
 
       if title:
          key = year, month, day = tuple(dirpath[len(blog_root):].split(os.sep)[1:])
@@ -79,7 +80,10 @@ for dirpath, dirs, files in os.walk(blog_root):
 
          file = file[:-len("tmpl")] + "html"
          key = (year, month, day, file)
-         bodies[key] = template.body()
+         body = template.body()
+         if isinstance(body, unicode):
+            body = body.encode('koi8-r')
+         bodies[key] = body
 
 # Need to save the blog?
 if blog <> old_blog:
@@ -177,7 +181,7 @@ def write_template(level, year, month, day, titles, tags=None):
 
       if len(titles) == 1:
          new_text.append("""\
-#attr $refresh = "0; URL=%s"
+#attr $Refresh = "0; URL=%s"
 """ % titles[0][3])
 
       new_text.append("""\
@@ -480,6 +484,19 @@ class AbsURLHTMLParser(_HTMLParser):
    def end_a(self):
       self.accumulator += '</a>'
 
+   def start_img(self, attrs):
+      self.accumulator += '<img'
+      for attrname, value in attrs:
+         value = cgi.escape(value, True)
+         if attrname == 'src':
+            self.accumulator += ' src="%s"' % urljoin(self.base, value)
+         else:
+            self.accumulator += ' %s="%s"' % (attrname, value)
+      self.accumulator += '>'
+
+   def end_img(self):
+       pass
+
 def absolute_urls(body, base):
    parser = AbsURLHTMLParser(base)
 
@@ -508,6 +525,8 @@ else:
 items = []
 for item in tuple(reversed(all_titles_tags))[:10]:
    year, month, day, file, title, lead, tags = item
+   lead = lead.decode('koi8-r').encode('utf-8')
+   title = title.decode('koi8-r').encode('utf-8')
    url_path = "%s/%s/%s/%s" % (year, month, day, file)
    item = NewsItem(
       "%s-%s-%s" % (year, month, day),
@@ -518,6 +537,7 @@ for item in tuple(reversed(all_titles_tags))[:10]:
    item.categoryList = tags
    body = bodies[(year, month, day, file)]
    body = absolute_urls(body, baseURL + url_path)
+   body = body.decode('koi8-r').encode('utf-8')
    item.body = body
    item.excerpt = get_first_p(body)
 
@@ -536,23 +556,23 @@ namespace = {
 # For english dates
 locale.setlocale(locale.LC_TIME, 'C')
 
-atom_tmpl = str(atom_10(searchList=[namespace]))
+atom_tmpl = unicode(atom_10(searchList=[namespace])).encode('koi8-r')
 write_if_changed(os.path.join(blog_root, "atom_10.xml"), atom_tmpl)
-rss_tmpl = str(rss_20(searchList=[namespace]))
+rss_tmpl = unicode(rss_20(searchList=[namespace])).encode('koi8-r')
 write_if_changed(os.path.join(blog_root, "rss_20.xml"), rss_tmpl)
 
 for item in items:
     item.excerpt = None
 
-atom_tmpl = str(atom_10(searchList=[namespace]))
+atom_tmpl = unicode(atom_10(searchList=[namespace])).encode('koi8-r')
 write_if_changed(os.path.join(blog_root, "atom_10_titles.xml"), atom_tmpl)
-rss_tmpl = str(rss_20(searchList=[namespace]))
+rss_tmpl = unicode(rss_20(searchList=[namespace])).encode('koi8-r')
 write_if_changed(os.path.join(blog_root, "rss_20_titles.xml"), rss_tmpl)
 
 for item in items:
     item.content = item.body
 
-atom_tmpl = str(atom_10(searchList=[namespace]))
+atom_tmpl = unicode(atom_10(searchList=[namespace])).encode('koi8-r')
 write_if_changed(os.path.join(blog_root, "atom_10_full.xml"), atom_tmpl)
-rss_tmpl = str(rss_20(searchList=[namespace]))
+rss_tmpl = unicode(rss_20(searchList=[namespace])).encode('koi8-r')
 write_if_changed(os.path.join(blog_root, "rss_20_full.xml"), rss_tmpl)