X-Git-Url: https://git.phdru.name/?p=phdru.name%2Fphdru.name.git;a=blobdiff_plain;f=reindex_blog.py;h=197c1c6956db3b3972f1a41a01791b607a3fc1b8;hp=f6505421239d531233636126b7f9ad1a91da68cb;hb=de7b8fd4faef91c9cb69be86e18697752ef89fe5;hpb=c16fedde035dea3d7e94ea3389d2de54d095cea1 diff --git a/reindex_blog.py b/reindex_blog.py index f650542..197c1c6 100755 --- a/reindex_blog.py +++ b/reindex_blog.py @@ -1,17 +1,14 @@ -#! /usr/local/bin/python -O +#! /usr/bin/env python # -*- coding: koi8-r -*- -__version__ = "$Revision$"[11:-2] -__revision__ = "$Id$"[5:-2] -__date__ = "$Date$"[7:-2] -__author__ = "Oleg BroytMann " -__copyright__ = "Copyright (C) 2006 PhiloSoft Design" - +__author__ = "Oleg Broytman " +__copyright__ = "Copyright (C) 2006-2013 PhiloSoft Design" import sys, os -blog_filename = sys.argv[1] +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 @@ -38,24 +35,28 @@ else: blog = {} years = {} +# bodies is a dictionary mapping file => body + +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: - # Ignore index.tmpl and *.html files; supose all other files are *.tmpl - if file == "index.tmpl" or file.endswith(".html"): + if not file.endswith(".tmpl"): 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 = getattr(template, "Lead", None) + lead = template.Lead.decode('utf-8').encode('koi8-r') - tags = getattr(template, "Tag", None) + 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:]) @@ -77,6 +78,12 @@ for dirpath, dirs, files in os.walk(blog_root): 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 # Need to save the blog? if blog <> old_blog: @@ -84,19 +91,22 @@ if blog <> old_blog: pickle.dump(blog, blog_file, pickle.HIGHEST_PROTOCOL) blog_file.close() - # Localized month names import locale -locale.setlocale(locale.LC_ALL, '') +locale.setlocale(locale.LC_ALL, "ru_RU.KOI8-R") from calendar import _localized_day, _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, '') -months_names_ru = [month.lower() for month in _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_ru0 = ['', "ÑÎ×ÁÒØ", "ÆÅ×ÒÁÌØ", "ÍÁÒÔ", "ÁÐÒÅÌØ", "ÍÁÊ", "ÉÀÎØ", "ÉÀÌØ", "Á×ÇÕÓÔ", "ÓÅÎÔÑÂÒØ", "ÏËÔÑÂÒØ", "ÎÏÑÂÒØ", "ÄÅËÁÂÒØ" @@ -118,42 +128,47 @@ 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 """] if level == 0: new_text.append("""\ -#attr $Title = "Oleg BroytMann's blog" -#attr $Description = "BroytMann Russian Blog Index Document" +#attr $Title = "Oleg Broytman's blog" +#attr $Description = "Broytman Russian Blog Index Document" #attr $Copyright = %(cyear)s -#attr $alternates = (("application/atom+xml", "News [Atom 1.0]", "atom_10.xml"), - ("application/rss+xml", "News [RSS 2.0]", "rss_20.xml") +#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"), ) ## #def body_html -

öÕÒÎÁÌ

+

öÕÒÎÁÌ

""" % {"cyear": year or 2005}) elif level == 1: new_text.append("""\ -#attr $Title = "Oleg BroytMann's blog: %(year)s" -#attr $Description = "BroytMann Russian Blog %(year)s Index Document" +#attr $Title = "Oleg Broytman's blog: %(year)s" +#attr $Description = "Broytman Russian Blog %(year)s Index Document" #attr $Copyright = %(cyear)s ## #def body_html -

öÕÒÎÁÌ: %(year)s

+

öÕÒÎÁÌ: %(year)s

""" % {"year": year, "cyear": year or 2005}) elif level == 2: imonth = int(month) new_text.append("""\ -#attr $Title = "Oleg BroytMann's blog: %(month_abbr_en)s %(year)s" -#attr $Description = "BroytMann Russian Blog %(month_name_en)s %(year)s Index Document" +#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 ## #def body_html -

öÕÒÎÁÌ: %(month_name_ru0)s %(year)s

+

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], @@ -164,34 +179,29 @@ def write_template(level, year, month, day, titles, tags=None): iday = int(day) imonth = int(month) - new_text.append("""\ -#attr $Next = "%s" -""" % titles[0][3]) - - if len(titles) == 1: new_text.append("""\ -#attr $refresh = "0; URL=%s" +#attr $Refresh = "0; URL=%s" """ % titles[0][3]) new_text.append("""\ -#attr $Title = "Oleg BroytMann's blog: %(day)d %(month_abbr_en)s %(year)s" -#attr $Description = "BroytMann Russian Blog %(day)d %(month_name_en)s %(year)s Index Document" +#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 ## #def body_html -

öÕÒÎÁÌ: %(day)d %(month_name_ru0)s %(year)s

+

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_ru0": months_names_ru0[imonth], + "month_name_ru": months_names_ru[imonth], "day": iday }) save_titles = titles[:] titles.reverse() - save_day = None + save_date = None for year, month, day, file, title, lead in titles: href = [] if level == 0: @@ -203,29 +213,31 @@ 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_day <> 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: new_text.append('\n

%s %s

' % (day, months_names_ru[int(month)])) - save_day = day - if lead: - lead = lead + ' ' - else: - lead = '' + save_date = year, month, day new_text.append('''

%s%s.

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

îÏ×ÏÓÔÅ×ÁÑ ÌÅÎÔÁ × ÆÏÒÍÁÔÁÈ -Atom 1.0 -É RSS 2.0 . + +Atom 1.0 ÔÏÌØËÏ ÚÁÇÏÌÏ×ËÉ / +Atom 1.0 / +Atom 1.0 ÐÏÌÎÙÅ ÔÅËÓÔÙ +É +RSS 2.0 ÔÏÌØËÏ ÚÁÇÏÌÏ×ËÉ / +RSS 2.0 / +RSS 2.0 ÐÏÌÎÙÅ ÔÅËÓÔÙ.

""") @@ -246,11 +258,14 @@ def write_template(level, year, month, day, titles, tags=None):

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

ðÏ ÇÏÄÁÍ: ''') first_year = True - for year in sorted(years.keys()): + for year in years: if first_year: first_year = False else: @@ -260,9 +275,14 @@ def write_template(level, year, month, day, titles, tags=None):

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

öö +""") + new_text.append("""\ #end def -$phd_pp_ru.respond(self) +$phd_site.respond(self) """) write_if_changed(index_name, ''.join(new_text)) @@ -315,47 +335,77 @@ 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 BroytMann's blog: tags" -#attr $Description = "BroytMann Russian Blog Tags Index Document" +#attr $Title = "Oleg Broytman's blog: tags" +#attr $Description = "Broytman Russian Blog Tags Index Document" #attr $Copyright = 2006 ## #def body_html -

ôÅÇÉ

+

ôÅÇÉ

"""] -for count, tag, links in all_tags: +for i, (count, tag, links) in enumerate(all_tags): new_text.append("""\
%s (%d)
""" % (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 = ["""\ ## THIS FILE IS AUTOMATICALLY GENERATED. DO NOT EDIT. -#extends phd_pp_ru +#encoding koi8-r +#extends phd_site #implements respond -#attr $Title = "Oleg BroytMann's blog: tag %s" -#attr $Description = "BroytMann Russian Blog Tag %s Index Document" +#attr $Title = "Oleg Broytman's blog: tag %s" +#attr $Description = "Broytman Russian Blog Tag %s Index Document" +""" % (tag, tag)] + + tag_text.append("""\ +#attr $First = "%s" +""" % first) + + if prev: + tag_text.append("""\ +#attr $Prev = "%s" +""" % prev) + + if next: + tag_text.append("""\ +#attr $Next = "%s" +""" % next) + + tag_text.append("""\ +#attr $Last = "%s" +""" % last) + + tag_text.append("""\ #attr $Copyright = 2006 ## #def body_html -

%s

+

%s

    -""" % (tag, tag, tag)] +""" % tag) count = 0 for year, month, day, filename, title, lead in reversed(links): - if lead: - lead = lead + ' ' - else: - lead = '' link = "../%s/%s/%s/%s" % (year, month, day, filename) - item_text = """
  • %s/%s/%s: %s%s
    • """ % (link, year, month, day, lead, title) + item_text = """
  • %s/%s/%s: %s%s
    • """ % (link, year, month, day, lead+' ' if lead else '', title) count += 1 if count <= 5: @@ -367,7 +417,7 @@ for count, tag, links in all_tags:

#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)) @@ -375,41 +425,130 @@ 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)) +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 start_p(self, attrs): + self.accumulator = '

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

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