X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=reindex_blog.py;h=33a5736dbbc1c022e04a58a65dd9ee9d167ef3e3;hb=5bfe6ea88d9f0579f7d4ed471c63c342c7b6fc1b;hp=beba7c12823ae151a8f5de6619c9776758b9d713;hpb=6922322a54539e39cbba59653868fa9d749fa274;p=phdru.name%2Fphdru.name.git
diff --git a/reindex_blog.py b/reindex_blog.py
index beba7c1..33a5736 100755
--- a/reindex_blog.py
+++ b/reindex_blog.py
@@ -1,12 +1,8 @@
#! /usr/bin/env python
# -*- coding: koi8-r -*-
-__version__ = "$Revision$"[11:-2]
-__revision__ = "$Id$"[5:-2]
-__date__ = "$Date$"[7:-2]
-__author__ = "Oleg Broytman "
-__copyright__ = "Copyright (C) 2006-2010 PhiloSoft Design"
-
+__author__ = "Oleg Broytman "
+__copyright__ = "Copyright (C) 2006-2014 PhiloSoft Design"
import sys, os
@@ -53,13 +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:])
@@ -83,7 +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:
@@ -128,7 +128,8 @@ def write_template(level, year, month, day, titles, tags=None):
new_text = ["""\
## THIS FILE IS AUTOMATICALLY GENERATED. DO NOT EDIT.
-#extends phd_pp_ru
+#encoding koi8-r
+#extends phd_site
#implements respond
"""]
@@ -180,7 +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 $Refresh = "0; URL=%s"
""" % titles[0][3])
new_text.append("""\
@@ -258,18 +259,25 @@ def write_template(level, year, month, day, titles, tags=None):
''')
max_year = int(sorted(years.keys())[-1])
- years = range(2005, max_year+1)
+ years = range(max_year, 2005, -1)
new_text.append('''
ðÏ ÇÏÄÁÍ:
''')
+
+ year_counts = {}
+ for year, month, day, file, title, lead in all_titles:
+ year_counts[year] = 0
+ for year, month, day, file, title, lead in all_titles:
+ year_counts[year] += 1
+
first_year = True
for year in years:
if first_year:
first_year = False
else:
new_text.append(' - ')
- new_text.append('%s' % (year, year))
+ new_text.append('%s (%d)' % (year, year, year_counts[str(year)]))
new_text.append('''
''')
@@ -281,7 +289,7 @@ def write_template(level, year, month, day, titles, tags=None):
new_text.append("""\
#end def
-$phd_pp_ru.respond(self)
+$phd_site.respond(self)
""")
write_if_changed(index_name, ''.join(new_text))
@@ -334,7 +342,8 @@ write_template(0, year, month, day, all_titles[-20:], all_tags)
new_text = ["""\
## THIS FILE IS AUTOMATICALLY GENERATED. DO NOT EDIT.
-#extends phd_pp_ru
+#encoding koi8-r
+#extends phd_site
#implements respond
#attr $Title = "Oleg Broytman's blog: tags"
#attr $Description = "Broytman Russian Blog Tags Index Document"
@@ -343,7 +352,29 @@ new_text = ["""\
#def body_html
ôÅÇÉ
-
+
+æÏÒÍÁ ÐÏÉÓËÁ ÐÏÚ×ÏÌÑÅÔ ÉÓËÁÔØ ÓÏÏÂÝÅÎÉÑ × ÂÌÏÇÅ, ÓÏÏÔ×ÅÔÓÔ×ÕÀÝÉÅ ×ÙÒÁÖÅÎÉÀ.
+óÉÎÔÁËÓÉÓ ×ÙÒÁÖÅÎÉÑ:
+
+ - ôÅÇ - ÅÓÌÉ ÔÁËÏÊ ÔÅÇ ÓÕÝÅÓÔ×ÕÅÔ, ÐÒÏÉÚÏÊÄ£Ô ÐÅÒÅÎÁÐÒÁ×ÌÅÎÉÅ ÎÁ ÓÔÒÁÎÉÃÕ ÔÅÇÁ.
+ - ïÐÅÒÁÔÏÒ '!' (NOT, not) - ÉÝÅÔ ÚÁÐÉÓÉ, × ËÏÔÏÒÙÈ ÎÅÔ ÜÔÏÇÏ ÔÅÇÁ.
+ - ïÐÅÒÁÔÏÒ '&' (AND, and) - ÉÝÅÔ ÚÁÐÉÓÉ, × ËÏÔÏÒÙÈ ÅÓÔØ ÏÂÁ ÔÅÇÁ.
+ - ïÐÅÒÁÔÏÒ '|' (OR, or) - ÉÝÅÔ ÚÁÐÉÓÉ, × ËÏÔÏÒÙÈ ÅÓÔØ ÌÀÂÙÅ ÉÚ ÔÅÇÏ×.
+ - ðÒÉÏÒÉÔÅÔ ÏÐÅÒÁÃÉÊ ÓÔÁÎÄÁÒÔÎÙÊ: NOT > AND > OR. óËÏÂËÉ '()' ÐÏÚ×ÏÌÑÀÔ ÏÂßÅÄÉÎÑÔØ ×ÙÒÁÖÅÎÉÑ.
+
+
+ðÒÉÍÅÒÙ ×ÙÒÁÖÅÎÉÊ: linux - ÐÒÏÉÚÏÊÄ£Ô ÐÅÒÅÎÁÐÒÁ×ÌÅÎÉÅ
+ÎÁ ÓÔÒÁÎÉÃÕ linux.html; linux&!audio - ÉÓËÁÔØ ÚÁÐÉÓÉ × ËÏÔÏÒÙÈ ÅÓÔØ ÔÅÇ
+linux É ÎÅÔ ÔÅÇÁ audio; linux and not audio - ÔÏ ÖÅ ÓÁÍÏÅ.
+
+
+
+
+
+
"""]
@@ -365,7 +396,8 @@ for i, (count, tag, links) in enumerate(all_tags):
tag_text = ["""\
## THIS FILE IS AUTOMATICALLY GENERATED. DO NOT EDIT.
-#extends phd_pp_ru
+#encoding koi8-r
+#extends phd_site
#implements respond
#attr $Title = "Oleg Broytman's blog: tag %s"
#attr $Description = "Broytman Russian Blog Tag %s Index Document"
@@ -395,7 +427,6 @@ for i, (count, tag, links) in enumerate(all_tags):
#def body_html
%s
-
""" % tag)
@@ -412,17 +443,15 @@ for i, (count, tag, links) in enumerate(all_tags):
tag_text.append("""\
-
#end def
-$phd_pp_ru.respond(self)
+$phd_site.respond(self)
""")
write_if_changed(os.path.join(blog_root, "tags", tag+".tmpl"), ''.join(tag_text))
new_text.append("""\
-
#end def
-$phd_pp_ru.respond(self)
+$phd_site.respond(self)
""")
write_if_changed(os.path.join(blog_root, "tags", "index.tmpl"), ''.join(new_text))
@@ -481,6 +510,19 @@ class AbsURLHTMLParser(_HTMLParser):
def end_a(self):
self.accumulator += ''
+ def start_img(self, attrs):
+ self.accumulator += '
'
+
+ def end_img(self):
+ pass
+
def absolute_urls(body, base):
parser = AbsURLHTMLParser(base)
@@ -502,13 +544,15 @@ from rss_20 import rss_20
from news import NewsItem
if blog_root:
- baseURL = "http://phd.pp.ru/%s/" % blog_root
+ baseURL = "http://phdru.name/%s/" % blog_root
else:
- baseURL = "http://phd.pp.ru/"
+ baseURL = "http://phdru.name/"
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),
@@ -529,7 +573,7 @@ namespace = {
"description": "",
"lang": "ru",
"author": "Oleg Broytman",
- "email": "phd@phd.pp.ru",
+ "email": "phd@phdru.name",
"generator": os.path.basename(sys.argv[0]),
"posts": items,
}
@@ -537,23 +581,23 @@ 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)