X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=reindex_blog.py;h=fd82c1839111ae59ddcd7a7e86eace33d7b9a715;hb=c6eb1e00be821ab12e0edaa622e75eff1ec8abd2;hp=975b4ea40ffdb2f6962abf0ac312b9fbc8436c4c;hpb=06f2f8f2be7e4d01235c166335ccc11c5798ea82;p=phdru.name%2Fphdru.name.git
diff --git a/reindex_blog.py b/reindex_blog.py
index 975b4ea..fd82c18 100755
--- a/reindex_blog.py
+++ b/reindex_blog.py
@@ -1,17 +1,18 @@
-#! /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) 2006-2010 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
@@ -38,14 +39,18 @@ else:
blog = {}
years = {}
+# excerpts nd bodies are dictionaries mapping file => excerpt/body
+
+excerpts = {}
+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)
@@ -53,7 +58,7 @@ for dirpath, dirs, files in os.walk(blog_root):
title = ' '.join(title_parts[6:])
lead = getattr(template, "Lead", None)
- tags = getattr(template, "Tag", None)
+ tags = template.Tag
if isinstance(tags, basestring):
tags = (tags,)
@@ -77,6 +82,10 @@ 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)
+ excerpts[key] = template.get_first_p()
+ bodies[key] = template.Body
# Need to save the blog?
if blog <> old_blog:
@@ -84,19 +93,22 @@ 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"
@@ -124,33 +136,40 @@ def write_template(level, year, month, day, titles, tags=None):
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 = (("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],
@@ -161,34 +180,29 @@ 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"
""" % 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:
@@ -200,12 +214,12 @@ 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
+ save_date = year, month, day
if lead:
lead = lead + ' '
else:
@@ -221,8 +235,14 @@ def write_template(level, year, month, day, titles, tags=None):
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.
""")
@@ -243,11 +263,14 @@ def write_template(level, year, month, day, titles, tags=None):
''')
+ max_year = int(sorted(years.keys())[-1])
+ years = range(2005, max_year+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:
@@ -257,6 +280,11 @@ def write_template(level, year, month, day, titles, tags=None):
''')
+ new_text.append("""
+
+öö
+""")
+
new_text.append("""\
#end def
$phd_pp_ru.respond(self)
@@ -296,8 +324,17 @@ for year in sorted(years.keys()):
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]))
+
all_tags = [(len(links), tag, links) for (tag, links) in all_tags.items()]
-all_tags.sort()
+all_tags.sort(by_count_rev_tag_link)
write_template(0, year, month, day, all_titles[-20:], all_tags)
@@ -305,36 +342,68 @@ new_text = ["""\
## THIS FILE IS AUTOMATICALLY GENERATED. DO NOT EDIT.
#extends phd_pp_ru
#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
#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):
@@ -372,7 +441,10 @@ from atom_10 import atom_10
from rss_20 import rss_20
from news import NewsItem
-baseURL = "http://phd.pp.ru/Russian/blog/"
+if blog_root:
+ baseURL = "http://phd.pp.ru/%s/" % blog_root
+else:
+ baseURL = "http://phd.pp.ru/"
items = []
for item in tuple(reversed(all_titles_tags))[:10]:
@@ -389,15 +461,18 @@ for item in tuple(reversed(all_titles_tags))[:10]:
items.append(item)
item.baseURL = baseURL
item.categoryList = tags
+ item.excerpt = excerpts[(year, month, day, file)]
+ item.body = bodies[(year, month, day, file)]
namespace = {
- "title": "Oleg Broytmann's blog",
+ "title": "Oleg Broytman's blog",
"baseURL": baseURL,
"indexFile": "",
"description": "",
"lang": "ru",
- "author": "Oleg Broytmann",
+ "author": "Oleg Broytman",
"email": "phd@phd.pp.ru",
+ "generator": os.path.basename(sys.argv[0]),
"posts": items,
}
@@ -408,3 +483,19 @@ atom_tmpl = str(atom_10(searchList=[namespace]))
write_if_changed(os.path.join(blog_root, "atom_10.xml"), atom_tmpl)
rss_tmpl = str(rss_20(searchList=[namespace]))
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]))
+write_if_changed(os.path.join(blog_root, "atom_10_titles.xml"), atom_tmpl)
+rss_tmpl = str(rss_20(searchList=[namespace]))
+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]))
+write_if_changed(os.path.join(blog_root, "atom_10_full.xml"), atom_tmpl)
+rss_tmpl = str(rss_20(searchList=[namespace]))
+write_if_changed(os.path.join(blog_root, "rss_20_full.xml"), rss_tmpl)