]> git.phdru.name Git - phdru.name/phdru.name.git/blob - phd.py
Fix a bug -- encode html to utf-8
[phdru.name/phdru.name.git] / phd.py
1 import os, re, time, urllib
2 from Cheetah.Template import Template
3
4
5 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/]"
6
7 def _url2href(match):
8    url = match.group(0)
9    return '<a href="%s">%s</a>' % (url, url)
10
11
12 full_dirs = len(os.getcwd().split('/')) + 1
13
14 class phd(Template):
15    def __init__(self, *args, **kw):
16       if not hasattr(self, "_fileBaseName"):
17          self._fileDirName, self._fileBaseName = os.path.split(os.path.abspath(self._CHEETAH_src))
18       Template.__init__(self, *args, **kw)
19       directories = self._fileDirName.split('/')[full_dirs:] # remove directories up to "./files"
20       dirs_to_root = len(directories)
21       if dirs_to_root:
22          root = "../"*dirs_to_root
23       else:
24          root = ''
25       self.root = root
26       path = '/'.join(directories) + '/' + \
27          self._fileBaseName.replace(".tmpl", ".html")
28       if path[0] <> '/': path = '/' + path
29       self.path = path
30
31    def copyright(self, start_year):
32       this_year = time.localtime()[0]
33       if start_year >= this_year:
34          return this_year
35       if start_year == this_year - 1:
36          return "%s, %s" % (start_year, this_year)
37       return "%s-%s" % (start_year, this_year)
38
39
40    def body(self):
41       if hasattr(self, "body_html"):
42          return self.body_html().encode('utf-8')
43       if hasattr(self, "body_text"):
44          return self.text2html()
45       if hasattr(self, "body_rst"):
46          return self.rst2html()
47       if hasattr(self, "body_mkd"):
48          return self.mkd2html()
49
50    def text2html(self):
51       body = re.sub(url_re, _url2href, self.body_text())
52
53       paragraphs = body.split("\n\n")
54
55       new_paras = []
56       for p in paragraphs:
57          if isinstance(p, unicode):
58             p = p.encode('utf-8')
59          parts = p.split("\n   ")
60          parts[0] = parts[0].strip()
61          new_paras.append('\n</p>\n<p>\n'.join(parts))
62
63       if self.Title:
64          title = "<h1>%s</h1>\n\n" % self.Title
65       else:
66          title = ''
67
68       body = '\n</p>\n\n<p class="head">\n'.join(new_paras)
69       return "%s<p>%s</p>" % (title, body)
70
71    def rst2html(self):
72       from docutils.core import publish_parts
73
74       parts = publish_parts(self.body_rst(), writer_name="html")
75
76       title = parts["title"] or self.Title
77       if title:
78          title = "<h1>%s</h1>" % title
79
80       subtitle = parts["subtitle"]
81       if subtitle:
82          subtitle = "<h2>%s</h2>" % subtitle
83
84       body = parts["body"]
85       parts = []
86       for part in (title, subtitle, body):
87           if not part:
88               continue
89           if isinstance(part, unicode):
90               part = part.encode('utf-8')
91           parts.append(part)
92       return "\n\n".join(parts)
93
94    def mkd2html(self):
95       from markdown import markdown
96       return markdown(self.body_mkd(), output_format="html")
97
98    def img_thumbnail_800_1024(self, img_name):
99       return """\
100 <img src="%(img_name)s-thumbnail.jpg" alt="%(img_name)s-thumbnail.jpg" /><br />
101 <a href="%(img_name)s-800x600.jpg">800x600</a>, <a href="%(img_name)s-1024x800.jpg">1024x800</a>""" % {"img_name": img_name}
102
103    def wikipedia(self, query):
104       return "http://en.wikipedia.org/wiki/%s" % quote_string(query.replace(' ', '_'), ext_safe=',')
105
106    def wikipedia_ru(self, query):
107       return "http://ru.wikipedia.org/wiki/%s" % quote_string(query.replace(' ', '_'), ext_safe=',')
108
109    def nigma(self, query):
110        return "http://www.nigma.ru/index.php?s=%s" % quote_string(query)
111
112    search = nigma
113
114    def yandex(self, query):
115       return "http://www.yandex.ru/yandsearch?text=%s&rpt=rad" % quote_string(query, "cp1251")
116
117    def google(self, query):
118       return "http://www.google.com/search?hl=en&ie=utf-8&oe=utf-8&q=%s" % quote_string(query)
119
120    def google_ru(self, query):
121       return "http://www.google.ru/search?hl=ru&ie=utf-8&oe=utf-8&q=%s" % quote_string(query)
122
123 def quote_string(s, to_encoding="utf-8", ext_safe=''):
124    return urllib.quote(unicode(s, "utf-8").encode(to_encoding), '/' + ext_safe)