X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;ds=sidebyside;f=reindex_blog.py;h=0b7c2a6dd9fbf39af81f038f172c0b998470b84b;hb=0c0058d611f55ddae8c08726acb9952e5984f8da;hp=6b7af352f8d582410fec70f4bd6cebfcb57fec15;hpb=91da0eaa057dff4d082d67f9ad655c1d9d7daa75;p=phdru.name%2Fphdru.name.git
diff --git a/reindex_blog.py b/reindex_blog.py
index 6b7af35..0b7c2a6 100755
--- a/reindex_blog.py
+++ b/reindex_blog.py
@@ -1,37 +1,21 @@
#! /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) 2006-2011 PhiloSoft Design"
-
+__copyright__ = "Copyright (C) 2006-2024 PhiloSoft Design"
import sys, os
-
-blog_data_root = sys.argv[1]
-blog_root = sys.argv[2]
-blog_filename = os.path.join(blog_data_root, "blog_dict.pickle")
-
try:
- import cPickle as pickle
+ from urllib.parse import quote
except ImportError:
- import pickle
+ from urllib import quote
from Cheetah.Template import Template
+from Cheetah.compat import string_type
+from blog_db import blog_root, load_blog, save_blog
-# Load old blog
-
-try:
- blog_file = open(blog_filename, "rb")
-except IOError:
- old_blog = {}
-else:
- old_blog = pickle.load(blog_file)
- blog_file.close()
-
+old_blog = load_blog()
# blog is a dictionary mapping
# (year, month, day) => [list of (file, title, lead, tags)]
@@ -53,13 +37,14 @@ 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):
+ if isinstance(tags, string_type):
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:])
@@ -83,26 +68,27 @@ 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:
- blog_file = open(blog_filename, "wb")
- pickle.dump(blog, blog_file, pickle.HIGHEST_PROTOCOL)
- blog_file.close()
+if blog != old_blog:
+ save_blog(blog)
# Localized month names
import locale
locale.setlocale(locale.LC_ALL, "ru_RU.KOI8-R")
-from calendar import _localized_day, _localized_month
+from calendar import _localized_month
locale.setlocale(locale.LC_TIME, 'C')
months_names_en = list(_localized_month('%B'))
months_abbrs_en = list(_localized_month('%b'))
locale.setlocale(locale.LC_TIME, "ru_RU.KOI8-R")
-#months_names_ru = list(_localized_month('%B'))
+# months_names_ru = list(_localized_month('%B'))
months_names_ru = ['', "ÑÎ×ÁÒÑ", "ÆÅ×ÒÁÌÑ", "ÍÁÒÔÁ", "ÁÐÒÅÌÑ", "ÍÁÑ", "ÉÀÎÑ",
"ÉÀÌÑ", "Á×ÇÕÓÔÁ", "ÓÅÎÔÑÂÒÑ", "ÏËÔÑÂÒÑ", "ÎÏÑÂÒÑ", "ÄÅËÁÂÒÑ"
@@ -114,6 +100,8 @@ months_names_ru0 = ['', "
from news import write_if_changed
+def encode_tag(tag):
+ return quote(tag.replace(' ', '_'))
def write_template(level, year, month, day, titles, tags=None):
path = [blog_root]
@@ -181,7 +169,7 @@ 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("""\
@@ -213,7 +201,7 @@ def write_template(level, year, month, day, titles, tags=None):
href.append(file)
href = '/'.join(href)
if day[0] == '0': day = day[1:]
- if save_date <> (year, month, day):
+ if save_date != (year, month, day):
if level == 0:
new_text.append('\n%s %s %s
' % (day, months_names_ru[int(month)], year))
else:
@@ -253,7 +241,8 @@ def write_template(level, year, month, day, titles, tags=None):
first_tag = False
else:
new_text.append(' - ')
- new_text.append("""%s (%d)""" % (tag, tag, count))
+ new_text.append("""%s (%d)""" % (
+ encode_tag(tag), tag, count))
new_text.append('''
''')
@@ -264,13 +253,20 @@ def write_template(level, year, month, day, titles, tags=None):
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('''
''')
@@ -345,14 +341,36 @@ 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.
+
+
+
+
+
+
"""]
for i, (count, tag, links) in enumerate(all_tags):
new_text.append("""\
- %s (%d)
-""" % (tag, tag, count))
+""" % (encode_tag(tag), tag, count))
first = all_tags[0][1]
if i == 0:
@@ -398,7 +416,6 @@ for i, (count, tag, links) in enumerate(all_tags):
#def body_html
%s
-
""" % tag)
@@ -415,15 +432,15 @@ for i, (count, tag, links) in enumerate(all_tags):
tag_text.append("""\
-
#end def
$phd_site.respond(self)
""")
- write_if_changed(os.path.join(blog_root, "tags", tag+".tmpl"), ''.join(tag_text))
+ write_if_changed(os.path.join(blog_root, "tags",
+ tag.replace(' ', '_') + ".tmpl"),
+ ''.join(tag_text))
new_text.append("""\
-
#end def
$phd_site.respond(self)
""")
@@ -475,6 +492,8 @@ class AbsURLHTMLParser(_HTMLParser):
self.accumulator += ''
+ def start_img(self, attrs):
+ self.accumulator += ''
+
+ def end_img(self):
+ pass
+
def absolute_urls(body, base):
parser = AbsURLHTMLParser(base)
@@ -505,13 +537,17 @@ from rss_20 import rss_20
from news import NewsItem
if blog_root:
- baseURL = "http://phdru.name/%s/" % blog_root
+ blog_root_url = blog_root[
+ blog_root.find('/htdocs/phdru.name/') + len('/htdocs/phdru.name/'):]
+ baseURL = "https://phdru.name/%s/" % blog_root_url
else:
- baseURL = "http://phdru.name/"
+ baseURL = "https://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),
@@ -519,11 +555,20 @@ for item in tuple(reversed(all_titles_tags))[:10]:
url_path)
items.append(item)
item.baseURL = baseURL
- item.categoryList = tags
+ item.categoryList = [t.decode('koi8-r').encode('utf-8') for t in tags]
body = bodies[(year, month, day, file)]
body = absolute_urls(body, baseURL + url_path)
+ try:
+ body.decode('utf-8')
+ except UnicodeDecodeError:
+ body = body.decode('koi8-r').encode('utf-8')
item.body = body
- item.excerpt = get_first_p(body)
+ excerpt = get_first_p(body)
+ try:
+ excerpt.decode('utf-8')
+ except UnicodeDecodeError:
+ excerpt = excerpt.decode('koi8-r').encode('utf-8')
+ item.excerpt = excerpt
namespace = {
"title": "Oleg Broytman's blog",
@@ -540,23 +585,23 @@ 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)