From 331965859222bca39a7fc251cdc93830620c8a4a Mon Sep 17 00:00:00 2001 From: Oleg Broytman Date: Mon, 27 Mar 2017 02:23:43 +0300 Subject: [PATCH] Adapted to Python3 and Cheetah3 --- Makefile | 6 +- make-files | 10 ++- make-news.py | 78 +++++++++-------- news.py | 106 +++++++++++++---------- phd.py | 221 +++++++++++++++++++++++++----------------------- phd_site.tmpl | 3 +- reindex_blog.py | 5 +- 7 files changed, 234 insertions(+), 195 deletions(-) diff --git a/Makefile b/Makefile index 7e58241..7e55241 100644 --- a/Makefile +++ b/Makefile @@ -3,7 +3,7 @@ # This file is a part of phdru.name homepage/blog/news generator scripts. # __author__ = "Oleg Broytman " -# __copyright__ = "Copyright (C) 2006-2016 PhiloSoft Design" +# __copyright__ = "Copyright (C) 2006-2017 PhiloSoft Design" .SUFFIXES: # Clear the suffix list @@ -11,10 +11,10 @@ %.py: %.tmpl - umask 022; cheetah compile --nobackup $< && compyle $@ + umask 022; cheetah compile --encoding=koi8-r --settings='encoding="koi8-r"' --nobackup $< && compyle $@ %.html: %.tmpl - umask 022; PYTHONPATH=. cheetah fill --nobackup --stdout $< | iconv -f utf-8 > $@ + umask 022; PYTHONPATH=. PYTHONIOENCODING=koi8-r:replace cheetah fill --encoding=koi8-r --settings='encoding="koi8-r"' --nobackup --stdout $< | iconv -f utf-8 -t koi8-r >$@ .PHONY: fast diff --git a/make-files b/make-files index ec02398..e5aa6d5 100755 --- a/make-files +++ b/make-files @@ -2,15 +2,19 @@ umask 022 PYTHONPATH=. -export PYTHONPATH +PYTHONIOENCODING=koi8-r:replace +export PYTHONPATH PYTHONIOENCODING if [ phd_site.tmpl -nt phd_site.py ]; then - cheetah compile --nobackup phd_site.tmpl && compyle phd_site.py + cheetah compile --encoding=koi8-r --settings='encoding="koi8-r"' --nobackup phd_site.tmpl && + compyle phd_site.py fi && for tmpl in "$@"; do dir="`dirname \"$tmpl\"`" outfile="`basename \"$tmpl\" .tmpl`.html" echo "$tmpl => $dir/$outfile" - cheetah fill --nobackup --stdout "$tmpl" | iconv -f utf-8 >"$dir/$outfile" || exit 1 + cheetah fill --encoding=koi8-r --settings='encoding="koi8-r"' \ + --nobackup --stdout "$tmpl" | iconv -f utf-8 -t koi8-r >"$dir/$outfile" || exit 1 done + diff --git a/make-news.py b/make-news.py index f6929c7..6d6ab7d 100755 --- a/make-news.py +++ b/make-news.py @@ -2,11 +2,14 @@ # -*- coding: koi8-r -*- __author__ = "Oleg Broytman " -__copyright__ = "Copyright (C) 2006-2014 PhiloSoft Design" +__copyright__ = "Copyright (C) 2006-2017 PhiloSoft Design" import sys, os from news import get_news, write_if_changed +from atom_10 import atom_10 +from rss_20 import rss_20 + lang = sys.argv[1] root = sys.argv[2] @@ -19,7 +22,8 @@ new_text.append(""" """) for item in news_items: - new_text.append('
  • %s - %s
    • \n' % (item.rel_link, item.date, item.title)) + new_text.append('
  • %s - %s
    • \n' + % (item.rel_link, item.date, item.title)) new_text.append("""\ @@ -28,7 +32,7 @@ new_text.append("""\ """) if lang == "en": - new_text.append("""\ + new_text.append("""\ News are also available in Atom 1.0 and RSS 2.0 @@ -36,7 +40,7 @@ formats. """) elif lang == "ru": - new_text.append("""\ + new_text.append("""\ îÏ×ÏÓÔÅ×ÁÑ ÌÅÎÔÁ × ÆÏÒÍÁÔÁÈ Atom 1.0 É RSS 2.0 . @@ -51,40 +55,48 @@ $phd_site.respond(self) write_if_changed(os.path.join(root, "news.tmpl"), ''.join(new_text)) -from atom_10 import atom_10 -from rss_20 import rss_20 - namespace = { - "title": "Oleg Broytman's Personal Page - News", - "baseURL": "http://phdru.name/", - "indexFile": "news.html", - "description": "", - "lang": lang, - "author": "Oleg Broytman", - "email": "phd@phdru.name", - "generator": os.path.basename(sys.argv[0]), - "posts": news_items, + "title": "Oleg Broytman's Personal Page - News", + "baseURL": "http://phdru.name/", + "indexFile": "news.html", + "description": "", + "lang": lang, + "author": "Oleg Broytman", + "email": "phd@phdru.name", + "generator": os.path.basename(sys.argv[0]), + "posts": news_items, } if lang == "ru": - namespace["title"] = "Oleg Broytman's Personal Page - Russian News" - namespace["baseURL"] = baseURL = "http://phdru.name/Russian/" - for item in news_items: - item.baseURL = baseURL - item.title = item.title.decode('koi8-r').encode('utf-8') + namespace["title"] = "Oleg Broytman's Personal Page - Russian News" + namespace["baseURL"] = baseURL = "http://phdru.name/Russian/" + for item in news_items: + item.baseURL = baseURL + if isinstance(item.title, bytes): + item.title = item.title.decode('koi8-r').encode('utf-8') for item in news_items: - href_parts = item.rel_link.split('/') - if href_parts: - if href_parts[0] == '.': - category = "Home page" - elif href_parts[0] == "..": - category = href_parts[1] - else: - category = href_parts[0] - if category: item.categoryList = [category] - -atom_tmpl = unicode(atom_10(searchList=[namespace])).encode('koi8-r') + href_parts = item.rel_link.split('/') + if href_parts: + if href_parts[0] == '.': + category = "Home page" + elif href_parts[0] == "..": + category = href_parts[1] + else: + category = href_parts[0] + if category: item.categoryList = [category] + +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') + write_if_changed(os.path.join(root, "atom_10.xml"), atom_tmpl) -rss_tmpl = unicode(rss_20(searchList=[namespace])).encode('koi8-r') write_if_changed(os.path.join(root, "rss_20.xml"), rss_tmpl) diff --git a/news.py b/news.py index 3e03851..82c5c10 100644 --- a/news.py +++ b/news.py @@ -1,76 +1,88 @@ """News""" +from __future__ import print_function + __author__ = "Oleg Broytman " -__copyright__ = "Copyright (C) 2006-2012 PhiloSoft Design" +__copyright__ = "Copyright (C) 2006-2017 PhiloSoft Design" __docformat__ = "epytext en" __all__ = ["get_news", "write_if_changed"] from datetime import date -from urlparse import urljoin +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') class NewsItem(object): - baseURL = "http://phdru.name/" - excerpt = None - content = None - categoryList = [] + baseURL = "http://phdru.name/" + excerpt = None + content = None + categoryList = [] - def __init__(self, date, title, rel_link): - self.date = date - self.title = title - self.rel_link = rel_link + def __init__(self, date, title, rel_link): + self.date = date + self.title = title + self.rel_link = rel_link - def URL(self): - return urljoin(self.baseURL, self.rel_link) + def URL(self): + return urljoin(self.baseURL, self.rel_link) - def rfc822_date(self): - y, m, d = self.date.split('-') - d = date(int(y), int(m), int(d)) - return d.strftime("%a, %d %b %Y %H:%M:%S +0300") + def rfc822_date(self): + y, m, d = self.date.split('-') + d = date(int(y), int(m), int(d)) + return d.strftime("%a, %d %b %Y %H:%M:%S +0300") def get_news_header(lang): - news_tmpl_file = open("news.tmpl-%s" % lang, 'r') - header = news_tmpl_file.read() - news_tmpl_file.close() + news_tmpl_file = open("news.tmpl-%s" % lang, 'r') + header = news_tmpl_file.read() + news_tmpl_file.close() - return header + return header def get_news_items(lang): - news_items_file = open("news_%s" % lang, 'r') - news_text = news_items_file.read() - news_items_file.close() + news_items_file = open("news_%s" % lang, 'r') + news_text = news_items_file.read() + news_items_file.close() - news_items = [] - for line in news_text.split('\n'): - if not line: continue - date, rel_link, title = line.split(None, 2) - news_items.append(NewsItem(date, title, rel_link)) + news_items = [] + for line in news_text.split('\n'): + if not line: continue + date, rel_link, title = line.split(None, 2) + news_items.append(NewsItem(date, title, rel_link)) - return news_items + return news_items def get_news(lang): - """Get news + """Get news - @param lang: langauge - @type lang: a string 'en' or 'ru' - @return: a tuple of (lnaguge-dependent header, a list of new items) + @param lang: langauge + @type lang: a string 'en' or 'ru' + @return: a tuple of (lnaguge-dependent header, a list of new items) - """ - return get_news_header(lang), get_news_items(lang) + """ + return get_news_header(lang), get_news_items(lang) def write_if_changed(filename, new_text): - try: - infile = open(filename, 'r') - old_text = infile.read() - infile.close() - except IOError: - old_text = None - - if old_text <> new_text: - print "Writing", filename - outfile = open(filename, 'w') - outfile.write(new_text) - outfile.close() + try: + infile = open(filename, 'r') + old_text = infile.read() + infile.close() + except IOError: + old_text = None + + if old_text != new_text: + print("Writing", filename) + outfile = open(filename, 'w') + outfile.write(new_text) + outfile.close() diff --git a/phd.py b/phd.py index 3c2e0dd..4e13617 100644 --- a/phd.py +++ b/phd.py @@ -1,130 +1,139 @@ -import os, re, time, urllib +import os, re, time +try: + from urllib import quote as url_quote +except ImportError: + from urllib.parse import quote as url_quote from Cheetah.Template import Template +from Cheetah.compat import PY2 url_re = r"(((https?|ftp|gopher|telnet)://|(mailto|file|news|about|ed2k|irc|sip|magnet):)[^' \t<>\"]+|(www|web|w3)[A-Za-z0-9_-]*\.[A-Za-z0-9._-]+\.[^' \t<>\"]+)[A-Za-z0-9/]" def _url2href(match): - url = match.group(0) - return '%s' % (url, url) + url = match.group(0) + return '%s' % (url, url) full_dirs = len(os.getcwd().split('/')) + 1 class phd(Template): - def __init__(self, *args, **kw): - if not hasattr(self, "_fileBaseName"): - self._fileDirName, self._fileBaseName = os.path.split(os.path.abspath(self._CHEETAH_src)) - Template.__init__(self, *args, **kw) - directories = self._fileDirName.split('/')[full_dirs:] # remove directories up to "./files" - dirs_to_root = len(directories) - if dirs_to_root: - root = "../"*dirs_to_root - else: - root = '' - self.root = root - path = '/'.join(directories) + '/' + \ - self._fileBaseName.replace(".tmpl", ".html") - if path[0] <> '/': path = '/' + path - self.path = path - - def copyright(self, start_year): - this_year = time.localtime()[0] - if start_year >= this_year: - return this_year - if start_year == this_year - 1: - return "%s, %s" % (start_year, this_year) - return "%s-%s" % (start_year, this_year) - - - def body(self): - if hasattr(self, "body_html"): - return self.body_html().encode('utf-8') - if hasattr(self, "body_text"): - return self.text2html() - if hasattr(self, "body_rst"): - return self.rst2html() - if hasattr(self, "body_mkd"): - return self.mkd2html() - - def text2html(self): - body = re.sub(url_re, _url2href, self.body_text()) - - paragraphs = body.split("\n\n") - - new_paras = [] - for p in paragraphs: - if isinstance(p, unicode): - p = p.encode('utf-8') - parts = p.split("\n ") - parts[0] = parts[0].strip() - new_paras.append('\n

    \n

    \n'.join(parts)) - - if self.Title: - title = "

    %s

    \n\n" % self.Title - else: - title = '' - - body = '\n

    \n\n

    \n'.join(new_paras) - return "%s

    %s

    " % (title, body) - - def rst2html(self): - from docutils.core import publish_parts - - parts = publish_parts(self.body_rst(), writer_name="html") - - title = parts["title"] or self.Title - if title: - title = "

    %s

    " % title - - subtitle = parts["subtitle"] - if subtitle: - subtitle = "

    %s

    " % subtitle - - body = parts["body"] - parts = [] - for part in (title, subtitle, body): - if not part: - continue - if isinstance(part, unicode): - part = part.encode('utf-8') - parts.append(part) - return "\n\n".join(parts) - - def mkd2html(self): - from markdown import markdown - return markdown(self.body_mkd(), output_format="html") - - def img_thumbnail_800_1024(self, img_name): - return """\ + def __init__(self, *args, **kw): + if not hasattr(self, "_fileBaseName"): + self._fileDirName, self._fileBaseName = os.path.split(os.path.abspath(self._CHEETAH_src)) + Template.__init__(self, *args, **kw) + directories = self._fileDirName.split('/')[full_dirs:] # remove directories up to "./files" + dirs_to_root = len(directories) + if dirs_to_root: + root = "../"*dirs_to_root + else: + root = '' + self.root = root + path = '/'.join(directories) + '/' + \ + self._fileBaseName.replace(".tmpl", ".html") + if path[0] != '/': path = '/' + path + self.path = path + + def copyright(self, start_year): + this_year = time.localtime()[0] + if start_year >= this_year: + return this_year + if start_year == this_year - 1: + return "%s, %s" % (start_year, this_year) + return "%s-%s" % (start_year, this_year) + + + def body(self): + if hasattr(self, "body_html"): + return self.body_html() + if hasattr(self, "body_text"): + return self.text2html() + if hasattr(self, "body_rst"): + return self.rst2html() + if hasattr(self, "body_mkd"): + return self.mkd2html() + + def text2html(self): + body = re.sub(url_re, _url2href, self.body_text()) + + paragraphs = body.split("\n\n") + + 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)) + + if self.Title: + title = "

    %s

    \n\n" % self.Title + else: + title = '' + + body = '\n

    \n\n

    \n'.join(new_paras) + return "%s

    %s

    " % (title, body) + + def rst2html(self): + from docutils.core import publish_parts + + parts = publish_parts(self.body_rst(), writer_name="html") + + title = parts["title"] or self.Title + if title: + title = "

    %s

    " % title + + subtitle = parts["subtitle"] + if subtitle: + subtitle = "

    %s

    " % subtitle + + body = parts["body"] + parts = [] + 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) + + def mkd2html(self): + from markdown import markdown + return markdown(self.body_mkd(), output_format="html") + + def img_thumbnail_800_1024(self, img_name): + return """\ %(img_name)s-thumbnail.jpg
    800x600, 1024x800""" % {"img_name": img_name} - def wikipedia(self, query): - return "https://en.wikipedia.org/wiki/%s" % quote_string(query.replace(' ', '_'), ext_safe=',') + def wikipedia(self, query): + return "https://en.wikipedia.org/wiki/%s" % quote_string(query.replace(' ', '_'), ext_safe=',') - def wikipedia_ru(self, query): - return "https://ru.wikipedia.org/wiki/%s" % quote_string(query.replace(' ', '_'), ext_safe=',') + def wikipedia_ru(self, query): + return "https://ru.wikipedia.org/wiki/%s" % quote_string(query.replace(' ', '_'), ext_safe=',') - def startpage(self, query): - return "https://startpage.com/do/search?q=%s" % quote_string(query) + def startpage(self, query): + return "https://startpage.com/do/search?q=%s" % quote_string(query) - search = startpage + search = startpage - def nigma(self, query): - return "http://www.nigma.ru/index.php?s=%s" % quote_string(query) + def nigma(self, query): + return "http://www.nigma.ru/index.php?s=%s" % quote_string(query) - def yandex(self, query): - return "http://www.yandex.ru/yandsearch?text=%s&rpt=rad" % quote_string(query, "cp1251") + def yandex(self, query): + return "http://www.yandex.ru/yandsearch?text=%s&rpt=rad" % quote_string(query, "cp1251") - def google(self, query): - return "http://www.google.com/search?hl=en&ie=utf-8&oe=utf-8&q=%s" % quote_string(query) + def google(self, query): + return "http://www.google.com/search?hl=en&ie=utf-8&oe=utf-8&q=%s" % quote_string(query) - def google_ru(self, query): - return "http://www.google.ru/search?hl=ru&ie=utf-8&oe=utf-8&q=%s" % quote_string(query) + def google_ru(self, query): + return "http://www.google.ru/search?hl=ru&ie=utf-8&oe=utf-8&q=%s" % quote_string(query) - def lurkmoar(self, query): - return "https://lurkmore.to/%s" % quote_string(query.replace(' ', '_'), ext_safe=',') + def lurkmoar(self, query): + return "https://lurkmore.to/%s" % quote_string(query.replace(' ', '_'), ext_safe=',') def quote_string(s, to_encoding="utf-8", ext_safe=''): - return urllib.quote(unicode(s, "utf-8").encode(to_encoding), '/' + 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 d176f0e..0388f0b 100644 --- a/phd_site.tmpl +++ b/phd_site.tmpl @@ -120,7 +120,8 @@ $body #end def #if $Tag
    -#if isinstance($Tag, basestring) +#from Cheetah.compat import string_type +#if isinstance($Tag, string_type) #if $path.startswith("/Russian/") ôÅÇ: #else diff --git a/reindex_blog.py b/reindex_blog.py index 33a5736..c2a87c6 100755 --- a/reindex_blog.py +++ b/reindex_blog.py @@ -2,9 +2,10 @@ # -*- coding: koi8-r -*- __author__ = "Oleg Broytman " -__copyright__ = "Copyright (C) 2006-2014 PhiloSoft Design" +__copyright__ = "Copyright (C) 2006-2017 PhiloSoft Design" import sys, os +from Cheetah.compat import string_type blog_data_root = sys.argv[1] blog_root = sys.argv[2] @@ -54,7 +55,7 @@ for dirpath, dirs, files in os.walk(blog_root): 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] -- 2.39.5