From 1afa1542b43c3400cdf58b66d4c7c1e7c60c2e9a Mon Sep 17 00:00:00 2001 From: Oleg Broytman Date: Sat, 15 Jun 2024 19:09:49 +0300 Subject: [PATCH] Feat: Python 3 --- Makefile | 4 +- blog_db.py | 6 +- dotfiles2html/dotfiles2html.py | 4 +- gen-sitemap.py | 6 +- make-changed.py | 26 +- make-files | 4 +- make-news.py | 14 +- news.py | 21 +- phd.py | 15 +- phd_site.tmpl | 8 +- reindex_blog.py | 670 ++++++++++++++++----------------- remove_old_html.py | 4 +- 12 files changed, 374 insertions(+), 408 deletions(-) diff --git a/Makefile b/Makefile index def5c6c..9a402a6 100644 --- a/Makefile +++ b/Makefile @@ -11,10 +11,10 @@ %.py: %.tmpl - umask 022; python2.7 `which cheetah` compile --encoding=koi8-r --settings='encoding="koi8-r"' --nobackup $< && compyle $@ && chmod +x $@ + umask 022; python3 -m Cheetah.CheetahWrapper compile --encoding=koi8-r --settings='encoding="koi8-r"' --nobackup $< && python3 -m compileall $@ && chmod +x $@ %.html: %.tmpl phd.py phd_site.py - umask 022; PYTHONPATH=. PYTHONIOENCODING=koi8-r:replace python2.7 `which cheetah` fill --encoding=koi8-r --settings='encoding="koi8-r"' --nobackup --stdout $< | iconv -c -f utf-8 -t koi8-r >$@ + umask 022; PYTHONPATH=. PYTHONIOENCODING=koi8-r:replace python3 -m Cheetah.CheetahWrapper fill --encoding=koi8-r --settings='encoding="koi8-r"' --nobackup $< .PHONY: fast diff --git a/blog_db.py b/blog_db.py index 3f23ac5..a4d6f83 100644 --- a/blog_db.py +++ b/blog_db.py @@ -1,7 +1,7 @@ -import sys, os +import os __author__ = "Oleg Broytman " -__copyright__ = "Copyright (C) 2017 PhiloSoft Design" +__copyright__ = "Copyright (C) 2017-2024 PhiloSoft Design" blog_data_root = os.path.dirname(__file__) blog_root = os.path.join(blog_data_root, '../htdocs/phdru.name/Russian/blog') @@ -12,6 +12,7 @@ try: except ImportError: import pickle + def load_blog(): try: blog_file = open(blog_filename, "rb") @@ -22,6 +23,7 @@ def load_blog(): blog_file.close() return blog + def save_blog(blog): blog_file = open(blog_filename, "wb") pickle.dump(blog, blog_file, pickle.HIGHEST_PROTOCOL) diff --git a/dotfiles2html/dotfiles2html.py b/dotfiles2html/dotfiles2html.py index af0076e..e4c96ec 100755 --- a/dotfiles2html/dotfiles2html.py +++ b/dotfiles2html/dotfiles2html.py @@ -1,7 +1,7 @@ -#! /usr/bin/env python +#! /usr/bin/env python3 __author__ = "Oleg Broytman " -__copyright__ = "Copyright (C) 2004-2023 PhiloSoft Design" +__copyright__ = "Copyright (C) 2004-2024 PhiloSoft Design" import filecmp import os diff --git a/gen-sitemap.py b/gen-sitemap.py index 32c729d..7978010 100755 --- a/gen-sitemap.py +++ b/gen-sitemap.py @@ -1,4 +1,4 @@ -#! /usr/bin/env python +#! /usr/bin/env python3 import argparse from fnmatch import fnmatch @@ -43,12 +43,13 @@ for dirpath, dirs, files in sorted(os.walk(fullpath)): elif level > save_level: assert level - save_level == 1 current_subtree = current_subtree[-1][1] - #else: # level == save_level: + # else: # level == save_level: current_subtree.append((parts[-1], [])) save_level = level except StopIteration: pass + def _tree2html(tree, path='', level=0): subparts = [] indent = " " * (level + 1) @@ -73,6 +74,7 @@ def _tree2html(tree, path='', level=0): return "\n".join(parts) + sitemap_tmpl = ["""\ #extends phd_site #implements respond diff --git a/make-changed.py b/make-changed.py index 2464394..80af089 100755 --- a/make-changed.py +++ b/make-changed.py @@ -1,4 +1,4 @@ -#! /usr/bin/env python +#! /usr/bin/env python3 import sys, os @@ -6,17 +6,17 @@ main_prog_mtime = os.path.getmtime("phd.py") main_tmpl_mtime = os.path.getmtime("phd_site.tmpl") for line in sys.stdin: - line = line.strip() - src_mtime = os.path.getmtime(line) + line = line.strip() + src_mtime = os.path.getmtime(line) - dest = line.replace(".tmpl", ".html") - try: - dest_mtime = os.path.getmtime(dest) - except OSError: - make = True - else: - make = (src_mtime > dest_mtime) or \ - (main_prog_mtime > dest_mtime) or (main_tmpl_mtime > dest_mtime) + dest = line.replace(".tmpl", ".html") + try: + dest_mtime = os.path.getmtime(dest) + except OSError: + make = True + else: + make = (src_mtime > dest_mtime) or \ + (main_prog_mtime > dest_mtime) or (main_tmpl_mtime > dest_mtime) - if make: - print line + if make: + print(line) diff --git a/make-files b/make-files index a43d782..fce39a7 100755 --- a/make-files +++ b/make-files @@ -6,7 +6,7 @@ PYTHONIOENCODING=koi8-r:replace export PYTHONPATH PYTHONIOENCODING if [ \! -e phd_site.py -o phd_site.tmpl -nt phd_site.py ]; then - python2.7 `which cheetah` compile --encoding=koi8-r --settings='encoding="koi8-r"' --nobackup phd_site.tmpl && + python3 -m Cheetah.CheetahWrapper compile --encoding=koi8-r --settings='encoding="koi8-r"' --nobackup phd_site.tmpl && compyle phd_site.py fi && @@ -14,7 +14,7 @@ for tmpl in "$@"; do dir="`dirname \"$tmpl\"`" outfile="`basename \"$tmpl\" .tmpl`.html" echo "$tmpl => $dir/$outfile" - python2.7 `which cheetah` fill --encoding=koi8-r --settings='encoding="koi8-r"' \ + python3 -m Cheetah.CheetahWrapper fill --encoding=koi8-r --settings='encoding="koi8-r"' \ --nobackup --stdout "$tmpl" | iconv -c -f utf-8 -t koi8-r >"$dir/$outfile" || exit 1 done diff --git a/make-news.py b/make-news.py index 35cf42d..d120b30 100755 --- a/make-news.py +++ b/make-news.py @@ -1,8 +1,8 @@ -#! /usr/bin/env python +#! /usr/bin/env python3 # -*- coding: koi8-r -*- __author__ = "Oleg Broytman " -__copyright__ = "Copyright (C) 2006-2017 PhiloSoft Design" +__copyright__ = "Copyright (C) 2006-2024 PhiloSoft Design" import sys, os from news import get_news, write_if_changed @@ -89,14 +89,8 @@ for item in news_items: atom_tmpl = atom_10(searchList=[namespace]) rss_tmpl = rss_20(searchList=[namespace]) -try: - unicode -except NameError: # PY3 - atom_tmpl = str(atom_tmpl) - rss_tmpl = str(rss_tmpl) -else: - atom_tmpl = unicode(atom_tmpl).encode('koi8-r') - rss_tmpl = unicode(rss_tmpl).encode('koi8-r') +atom_tmpl = str(atom_tmpl) +rss_tmpl = str(rss_tmpl) write_if_changed(os.path.join(root, "atom_10.xml"), atom_tmpl) write_if_changed(os.path.join(root, "rss_20.xml"), rss_tmpl) diff --git a/news.py b/news.py index 4f62778..c090592 100644 --- a/news.py +++ b/news.py @@ -3,24 +3,19 @@ from __future__ import print_function __author__ = "Oleg Broytman " -__copyright__ = "Copyright (C) 2006-2017 PhiloSoft Design" +__copyright__ = "Copyright (C) 2006-2024 PhiloSoft Design" __docformat__ = "epytext en" __all__ = ["get_news", "write_if_changed"] from datetime import date -try: - from urlparse import urljoin -except ImportError: - from urllib.parse import urljoin - -try: - unicode -except NameError: # PY3 - std_open = open - def open(fname, mode): - return std_open(fname, mode, encoding='koi8-r') +from urllib.parse import urljoin + +std_open = open +def open(fname, mode): + return std_open(fname, mode, encoding='koi8-r') + class NewsItem(object): baseURL = "https://phdru.name/" @@ -49,6 +44,7 @@ def get_news_header(lang): return header + def get_news_items(lang): news_items_file = open("news_%s" % lang, 'r') news_text = news_items_file.read() @@ -62,6 +58,7 @@ def get_news_items(lang): return news_items + def get_news(lang): """Get news diff --git a/phd.py b/phd.py index 0a6a4e5..5b90ae6 100644 --- a/phd.py +++ b/phd.py @@ -1,10 +1,9 @@ import os, re, time -try: - from urllib import quote as url_quote -except ImportError: - from urllib.parse import quote as url_quote +from urllib.parse import quote as url_quote + from Cheetah.Template import Template from Cheetah.compat import PY2 + from blog_db import load_blog @@ -63,8 +62,6 @@ class phd(Template): new_paras = [] for p in paragraphs: - if PY2 and not isinstance(p, bytes): - p = p.encode('utf-8') parts = p.split("\n ") parts[0] = parts[0].strip() new_paras.append('\n

\n

\n'.join(parts)) @@ -95,8 +92,6 @@ class phd(Template): for part in (title, subtitle, body): if not part: continue - if PY2 and not isinstance(part, bytes): - part = part.encode('utf-8') parts.append(part) return "\n\n".join(parts) @@ -171,8 +166,4 @@ class phd(Template): def quote_string(s, to_encoding="utf-8", ext_safe=''): - if isinstance(s, bytes): - s = s.decode("utf-8") - if PY2: - s = s.encode(to_encoding) return url_quote(s, '/' + ext_safe) diff --git a/phd_site.tmpl b/phd_site.tmpl index 67eb341..5ad7cea 100644 --- a/phd_site.tmpl +++ b/phd_site.tmpl @@ -115,11 +115,11 @@ $style #set $prev_key, $prev_blog_post, $next_key, $next_blog_post = $find_near_blog_posts() #if $prev_blog_post #set $prev_href = $root + "Russian/blog/" + '/'.join($prev_key + ($prev_blog_post[0].replace('.tmpl', '.html'),)) -#set $prev_title = $prev_blog_post[1].decode('koi8-r') +#set $prev_title = $prev_blog_post[1] #end if #if $next_blog_post #set $next_href = $root + "Russian/blog/" + '/'.join($next_key + ($next_blog_post[0].replace('.tmpl', '.html'),)) -#set $next_title = $next_blog_post[1].decode('koi8-r') +#set $next_title = $next_blog_post[1] #end if
@@ -139,9 +139,9 @@ $style #end if

$body -#from urllib import quote +#from urllib.parse import quote #def encode_tag(tag): -$quote(tag.decode('utf-8').encode('koi8-r').replace(' ', '_')) +$quote(tag.replace(' ', '_')) #end def #def link_tag($tag) $tag diff --git a/reindex_blog.py b/reindex_blog.py index 0b7c2a6..bc34887 100755 --- a/reindex_blog.py +++ b/reindex_blog.py @@ -1,18 +1,23 @@ -#! /usr/bin/env python +#! /usr/bin/env python3 # -*- coding: koi8-r -*- __author__ = "Oleg Broytman " __copyright__ = "Copyright (C) 2006-2024 PhiloSoft Design" +from calendar import _localized_month +import cgi +import locale import sys, os -try: - from urllib.parse import quote -except ImportError: - from urllib import quote +from urllib.parse import quote, urljoin from Cheetah.Template import Template from Cheetah.compat import string_type +from m_lib.net.www.html import HTMLParser as _HTMLParser + +from atom_10 import atom_10 from blog_db import blog_root, load_blog, save_blog +from news import NewsItem, write_if_changed +from rss_20 import rss_20 old_blog = load_blog() @@ -29,59 +34,54 @@ bodies = {} # Walk the directory recursively for dirpath, dirs, files in os.walk(blog_root): - d = os.path.basename(dirpath) - if not d.startswith("20") and not d.isdigit(): - continue - for file in files: - if not file.endswith(".tmpl"): - continue - fullpath = os.path.join(dirpath, file) - template = Template(file=fullpath) - title_parts = template.Title.decode('utf-8').encode('koi8-r').split() - title = ' '.join(title_parts[6:]) - lead = template.Lead.decode('utf-8').encode('koi8-r') - - tags = template.Tag - 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:]) - if key in blog: - days = blog[key] - else: - days = blog[key] = [] - days.append((file, title, lead, tags)) - - if year in years: - months = years[year] - else: - months = years[year] = {} - - if month in months: - days = months[month] - else: - days = months[month] = [] - - if day not in days: days.append(day) - - file = file[:-len("tmpl")] + "html" - key = (year, month, day, file) - body = template.body() - if isinstance(body, unicode): - body = body.encode('koi8-r') - bodies[key] = body + d = os.path.basename(dirpath) + if not d.startswith("20") and not d.isdigit(): + continue + for file in files: + if not file.endswith(".tmpl"): + continue + fullpath = os.path.join(dirpath, file) + template = Template(file=fullpath) + title_parts = template.Title.split() + title = ' '.join(title_parts[6:]) + lead = template.Lead + + tags = template.Tag + if isinstance(tags, string_type): + tags = (tags,) + + if title: + key = year, month, day = \ + tuple(dirpath[len(blog_root):].split(os.sep)[1:]) + if key in blog: + days = blog[key] + else: + days = blog[key] = [] + days.append((file, title, lead, tags)) + + if year in years: + months = years[year] + else: + months = years[year] = {} + + if month in months: + days = months[month] + else: + days = months[month] = [] + + if day not in days: days.append(day) + + file = file[:-len("tmpl")] + "html" + key = (year, month, day, file) + body = template.body() + bodies[key] = body # Need to save the blog? 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_month locale.setlocale(locale.LC_TIME, 'C') months_names_en = list(_localized_month('%B')) @@ -90,56 +90,58 @@ 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 = ['', "ÑÎ×ÁÒÑ", "ÆÅ×ÒÁÌÑ", "ÍÁÒÔÁ", "ÁÐÒÅÌÑ", "ÍÁÑ", "ÉÀÎÑ", - "ÉÀÌÑ", "Á×ÇÕÓÔÁ", "ÓÅÎÔÑÂÒÑ", "ÏËÔÑÂÒÑ", "ÎÏÑÂÒÑ", "ÄÅËÁÂÒÑ" +months_names_ru = [ + '', "ÑÎ×ÁÒÑ", "ÆÅ×ÒÁÌÑ", "ÍÁÒÔÁ", "ÁÐÒÅÌÑ", "ÍÁÑ", "ÉÀÎÑ", + "ÉÀÌÑ", "Á×ÇÕÓÔÁ", "ÓÅÎÔÑÂÒÑ", "ÏËÔÑÂÒÑ", "ÎÏÑÂÒÑ", "ÄÅËÁÂÒÑ" ] -months_names_ru0 = ['', "ÑÎ×ÁÒØ", "ÆÅ×ÒÁÌØ", "ÍÁÒÔ", "ÁÐÒÅÌØ", "ÍÁÊ", "ÉÀÎØ", - "ÉÀÌØ", "Á×ÇÕÓÔ", "ÓÅÎÔÑÂÒØ", "ÏËÔÑÂÒØ", "ÎÏÑÂÒØ", "ÄÅËÁÂÒØ" +months_names_ru0 = [ + '', "ÑÎ×ÁÒØ", "ÆÅ×ÒÁÌØ", "ÍÁÒÔ", "ÁÐÒÅÌØ", "ÍÁÊ", "ÉÀÎØ", + "ÉÀÌØ", "Á×ÇÕÓÔ", "ÓÅÎÔÑÂÒØ", "ÏËÔÑÂÒØ", "ÎÏÑÂÒØ", "ÄÅËÁÂÒØ" ] -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] - if level >= 1: - path.append(year) - if level >= 2: - path.append(month) - if level == 3: - path.append(day) - path.append("index.tmpl") - index_name = os.path.join(*path) - - new_text = ["""\ + path = [blog_root] + if level >= 1: + path.append(year) + if level >= 2: + path.append(month) + if level == 3: + path.append(day) + path.append("index.tmpl") + index_name = os.path.join(*path) + + new_text = ["""\ ## THIS FILE IS AUTOMATICALLY GENERATED. DO NOT EDIT. #encoding koi8-r #extends phd_site #implements respond """] - if level == 0: - new_text.append("""\ + if level == 0: + new_text.append("""\ #attr $Title = "Oleg Broytman's blog" #attr $Description = "Broytman Russian Blog Index Document" #attr $Copyright = %(cyear)s #attr $alternates = (("îÏ×ÏÓÔÉ [Atom 1.0] ÔÏÌØËÏ ÚÁÇÏÌÏ×ËÉ", "application/atom+xml", "atom_10_titles.xml"), - ("îÏ×ÏÓÔÉ [Atom 1.0]", "application/atom+xml", "atom_10.xml"), - ("îÏ×ÏÓÔÉ [Atom 1.0] ÐÏÌÎÙÅ ÔÅËÓÔÙ", "application/atom+xml", "atom_10_full.xml"), - ("îÏ×ÏÓÔÉ [RSS 2.0] ÔÏÌØËÏ ÚÁÇÏÌÏ×ËÉ", "application/rss+xml", "rss_20_titles.xml"), - ("îÏ×ÏÓÔÉ [RSS 2.0]", "application/rss+xml", "rss_20.xml"), - ("îÏ×ÏÓÔÉ [RSS 2.0] ÐÏÌÎÙÅ ÔÅËÓÔÙ", "application/rss+xml", "rss_20_full.xml"), + ("îÏ×ÏÓÔÉ [Atom 1.0]", "application/atom+xml", "atom_10.xml"), + ("îÏ×ÏÓÔÉ [Atom 1.0] ÐÏÌÎÙÅ ÔÅËÓÔÙ", "application/atom+xml", "atom_10_full.xml"), + ("îÏ×ÏÓÔÉ [RSS 2.0] ÔÏÌØËÏ ÚÁÇÏÌÏ×ËÉ", "application/rss+xml", "rss_20_titles.xml"), + ("îÏ×ÏÓÔÉ [RSS 2.0]", "application/rss+xml", "rss_20.xml"), + ("îÏ×ÏÓÔÉ [RSS 2.0] ÐÏÌÎÙÅ ÔÅËÓÔÙ", "application/rss+xml", "rss_20_full.xml"), ) ## #def body_html

öÕÒÎÁÌ

""" % {"cyear": year or 2005}) - elif level == 1: - new_text.append("""\ + elif level == 1: + new_text.append("""\ #attr $Title = "Oleg Broytman's blog: %(year)s" #attr $Description = "Broytman Russian Blog %(year)s Index Document" #attr $Copyright = %(cyear)s @@ -148,9 +150,9 @@ def write_template(level, year, month, day, titles, tags=None):

öÕÒÎÁÌ: %(year)s

""" % {"year": year, "cyear": year or 2005}) - elif level == 2: - imonth = int(month) - new_text.append("""\ + elif level == 2: + imonth = int(month) + new_text.append("""\ #attr $Title = "Oleg Broytman's blog: %(month_abbr_en)s %(year)s" #attr $Description = "Broytman Russian Blog %(month_name_en)s %(year)s Index Document" #attr $Copyright = %(cyear)s @@ -158,21 +160,21 @@ def write_template(level, year, month, day, titles, tags=None): #def body_html

öÕÒÎÁÌ: %(month_name_ru0)s %(year)s

""" % { - "year": year, "cyear": year or 2005, - "month_abbr_en": months_abbrs_en[imonth], "month_name_en": months_names_en[imonth], - "month_name_ru0": months_names_ru0[imonth], - }) + "year": year, "cyear": year or 2005, + "month_abbr_en": months_abbrs_en[imonth], "month_name_en": months_names_en[imonth], + "month_name_ru0": months_names_ru0[imonth], + }) - elif level == 3: - iday = int(day) - imonth = int(month) + elif level == 3: + iday = int(day) + imonth = int(month) - if len(titles) == 1: - new_text.append("""\ + if len(titles) == 1: + new_text.append("""\ #attr $Refresh = "0; URL=%s" """ % titles[0][3]) - new_text.append("""\ + new_text.append("""\ #attr $Title = "Oleg Broytman's blog: %(day)d %(month_abbr_en)s %(year)s" #attr $Description = "Broytman Russian Blog %(day)d %(month_name_en)s %(year)s Index Document" #attr $Copyright = %(cyear)s @@ -180,41 +182,41 @@ def write_template(level, year, month, day, titles, tags=None): #def body_html

öÕÒÎÁÌ: %(day)d %(month_name_ru)s %(year)s

""" % { - "year": year, "cyear": year or 2005, - "month_abbr_en": months_abbrs_en[imonth], "month_name_en": months_names_en[imonth], - "month_name_ru": months_names_ru[imonth], - "day": iday - }) - - save_titles = titles[:] - titles.reverse() - - save_date = None - for year, month, day, file, title, lead in titles: - href = [] - if level == 0: - href.append(year) - if level <= 1: - href.append(month) - if level <= 2: - href.append(day) - href.append(file) - href = '/'.join(href) - if day[0] == '0': day = day[1:] - if save_date != (year, month, day): - if level == 0: - new_text.append('\n

%s %s %s

' % (day, months_names_ru[int(month)], year)) - else: - new_text.append('\n

%s %s

' % (day, months_names_ru[int(month)])) - save_date = year, month, day - new_text.append(''' + "year": year, "cyear": year or 2005, + "month_abbr_en": months_abbrs_en[imonth], "month_name_en": months_names_en[imonth], + "month_name_ru": months_names_ru[imonth], + "day": iday + }) + + save_titles = titles[:] + titles.reverse() + + save_date = None + for year, month, day, file, title, lead in titles: + href = [] + if level == 0: + href.append(year) + if level <= 1: + href.append(month) + if level <= 2: + href.append(day) + href.append(file) + href = '/'.join(href) + if day[0] == '0': day = day[1:] + if save_date != (year, month, day): + if level == 0: + new_text.append('\n

%s %s %s

' % (day, months_names_ru[int(month)], year)) + else: + new_text.append('\n

%s %s

' % (day, months_names_ru[int(month)])) + save_date = year, month, day + new_text.append('''

- %s%s. + %s%s.

''' % (lead+' ' if lead else '', href, title)) - if level == 0: - new_text.append(""" + if level == 0: + new_text.append("""

îÏ×ÏÓÔÅ×ÁÑ ÌÅÎÔÁ × ÆÏÒÍÁÔÁÈ @@ -229,59 +231,59 @@ def write_template(level, year, month, day, titles, tags=None):

""") - years = {} - for year, month, day, file, title, lead in save_titles: - years[year] = True - new_text.append(''' + years = {} + for year, month, day, file, title, lead in save_titles: + years[year] = True + new_text.append('''

ôÅÇÉ: ''') - first_tag = True - for count, tag, links in all_tags: - if first_tag: - first_tag = False - else: - new_text.append(' - ') - new_text.append("""%s (%d)""" % ( - encode_tag(tag), tag, count)) - new_text.append(''' + first_tag = True + for count, tag, links in all_tags: + if first_tag: + first_tag = False + else: + new_text.append(' - ') + new_text.append("""%s (%d)""" % ( + encode_tag(tag), tag, count)) + new_text.append('''

''') - max_year = int(sorted(years.keys())[-1]) - years = range(max_year, 2005, -1) + max_year = int(sorted(years.keys())[-1]) + years = range(max_year, 2005, -1) - new_text.append(''' + 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 (%d)' % (year, year, year_counts[str(year)])) - new_text.append(''' + 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 (%d)' % (year, year, year_counts[str(year)])) + new_text.append('''

''') - new_text.append(""" + new_text.append("""

öö """) - new_text.append("""\ + new_text.append("""\ #end def $phd_site.respond(self) """) - write_if_changed(index_name, ''.join(new_text)) + write_if_changed(index_name, ''.join(new_text)) all_tags = {} @@ -289,43 +291,40 @@ all_titles = [] all_titles_tags = [] for year in sorted(years.keys()): - year_titles = [] - months = years[year] - for month in sorted(months.keys()): - month_titles = [] - for day in sorted(months[month]): - day_titles = [] - key = year, month, day - if key in blog: - for file, title, lead, tags in blog[key]: - if file.endswith(".tmpl"): file = file[:-len("tmpl")] + "html" - value = (year, month, day, file, title, lead) - all_titles_tags.append((year, month, day, file, title, lead, tags)) - all_titles.append(value) - year_titles.append(value) - month_titles.append(value) - day_titles.append(value) - for tag in tags: - if tag in all_tags: - tag_links = all_tags[tag] - else: - tag_links = all_tags[tag] = [] - tag_links.append(value) - write_template(3, year, month, day, day_titles) - write_template(2, year, month, day, month_titles) - write_template(1, year, month, day, year_titles) - -def by_count_rev_tag_link(t1, t2): - """Sort all_tags by count in descending order, - and by tags and links in ascending order - """ - r = cmp(t1[0], t2[0]) - if r: - return -r - return cmp((t1[1], t1[2]), (t2[1], t2[2])) + year_titles = [] + months = years[year] + for month in sorted(months.keys()): + month_titles = [] + for day in sorted(months[month]): + day_titles = [] + key = year, month, day + if key in blog: + for file, title, lead, tags in blog[key]: + if file.endswith(".tmpl"): file = file[:-len("tmpl")] + "html" + value = (year, month, day, file, title, lead) + all_titles_tags.append((year, month, day, file, title, lead, tags)) + all_titles.append(value) + year_titles.append(value) + month_titles.append(value) + day_titles.append(value) + for tag in tags: + if tag in all_tags: + tag_links = all_tags[tag] + else: + tag_links = all_tags[tag] = [] + tag_links.append(value) + write_template(3, year, month, day, day_titles) + write_template(2, year, month, day, month_titles) + write_template(1, year, month, day, year_titles) + +def by_count_rev_tag_link(tag): + """Sort all_tags by count in descending order, + and by tags and links in ascending order + """ + return tag[:3] all_tags = [(len(links), tag, links) for (tag, links) in all_tags.items()] -all_tags.sort(by_count_rev_tag_link) +all_tags.sort(key=by_count_rev_tag_link) write_template(0, year, month, day, all_titles[-20:], all_tags) @@ -345,11 +344,11 @@ new_text = ["""\ 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.
  • +
  • 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 @@ -359,8 +358,8 @@ linux

- - + +
@@ -368,22 +367,22 @@ linux """] for i, (count, tag, links) in enumerate(all_tags): - new_text.append("""\ -
%s (%d)
+ new_text.append("""\ +
%s (%d)
""" % (encode_tag(tag), tag, count)) - first = all_tags[0][1] - if i == 0: - prev = None - else: - prev = all_tags[i-1][1] - if i >= len(all_tags)-1: - next = None - else: - next = all_tags[i+1][1] - last = all_tags[-1][1] - - tag_text = ["""\ + first = all_tags[0][1] + if i == 0: + prev = None + else: + prev = all_tags[i-1][1] + if i >= len(all_tags)-1: + next = None + else: + next = all_tags[i+1][1] + last = all_tags[-1][1] + + tag_text = ["""\ ## THIS FILE IS AUTOMATICALLY GENERATED. DO NOT EDIT. #encoding koi8-r #extends phd_site @@ -392,25 +391,25 @@ for i, (count, tag, links) in enumerate(all_tags): #attr $Description = "Broytman Russian Blog Tag %s Index Document" """ % (tag, tag)] - tag_text.append("""\ + tag_text.append("""\ #attr $First = "%s" """ % first) - if prev: - tag_text.append("""\ + if prev: + tag_text.append("""\ #attr $Prev = "%s" """ % prev) - if next: - tag_text.append("""\ + if next: + tag_text.append("""\ #attr $Next = "%s" """ % next) - tag_text.append("""\ + tag_text.append("""\ #attr $Last = "%s" """ % last) - tag_text.append("""\ + tag_text.append("""\ #attr $Copyright = 2006 ## #def body_html @@ -419,25 +418,25 @@ for i, (count, tag, links) in enumerate(all_tags):
    """ % tag) - count = 0 - for year, month, day, filename, title, lead in reversed(links): - link = "../%s/%s/%s/%s" % (year, month, day, filename) - item_text = """
  • %s/%s/%s: %s%s
  • """ % (link, year, month, day, lead+' ' if lead else '', title) + count = 0 + for year, month, day, filename, title, lead in reversed(links): + link = "../%s/%s/%s/%s" % (year, month, day, filename) + item_text = """
  • %s/%s/%s: %s%s
  • """ % (link, year, month, day, lead+' ' if lead else '', title) - count += 1 - if count <= 5: - new_text.append("
    %s
    \n" % item_text) + count += 1 + if count <= 5: + new_text.append("
    %s
    \n" % item_text) - tag_text.append(" %s\n" % item_text) + tag_text.append(" %s\n" % item_text) - tag_text.append("""\ + tag_text.append("""\
#end def $phd_site.respond(self) """) - write_if_changed(os.path.join(blog_root, "tags", - tag.replace(' ', '_') + ".tmpl"), - ''.join(tag_text)) + write_if_changed(os.path.join(blog_root, "tags", + tag.replace(' ', '_') + ".tmpl"), + ''.join(tag_text)) new_text.append("""\ @@ -447,161 +446,142 @@ $phd_site.respond(self) write_if_changed(os.path.join(blog_root, "tags", "index.tmpl"), ''.join(new_text)) -from HTMLParser import HTMLParseError -import cgi -from urlparse import urljoin -from m_lib.net.www.html import HTMLParser as _HTMLParser - class HTMLDone(Exception): pass class FirstPHTMLParser(_HTMLParser): - def __init__(self): - _HTMLParser.__init__(self) - self.first_p = None + def __init__(self): + _HTMLParser.__init__(self) + self.first_p = None - def start_p(self, attrs): - self.accumulator = '

' + def start_p(self, attrs): + self.accumulator = '

' - def end_p(self): - self.first_p = self.accumulator + '

' - raise HTMLDone() + def end_p(self): + self.first_p = self.accumulator + '

' + raise HTMLDone() def get_first_p(body): - parser = FirstPHTMLParser() + parser = FirstPHTMLParser() - try: - parser.feed(body) - except (HTMLParseError, HTMLDone): - pass + try: + parser.feed(body) + except HTMLDone: + pass - try: - parser.close() - except (HTMLParseError, HTMLDone): - pass + try: + parser.close() + except HTMLDone: + pass - return parser.first_p + return parser.first_p class AbsURLHTMLParser(_HTMLParser): - def __init__(self, base): - _HTMLParser.__init__(self) - self.base = base - - def start_a(self, attrs): - self.accumulator += '