booki-twiki-gateway.cgi

   1 #!/usr/bin/python
   2 #
   3 # Part of Objavi2, which turns html manuals into books.  This emulates
   4 # the Booki-epub-Espri interface for old TWiki books.
   5 #
   6 # Copyright (C) 2009 Douglas Bagnall
   7 #
   8 # This program is free software; you can redistribute it and/or modify
   9 # it under the terms of the GNU General Public License as published by
  10 # the Free Software Foundation; either version 2 of the License, or
  11 # (at your option) any later version.
  12 #
  13 # This program is distributed in the hope that it will be useful,
  14 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16 # GNU General Public License for more details.
  17 #
  18 # You should have received a copy of the GNU General Public License along
  19 # with this program; if not, write to the Free Software Foundation, Inc.,
  20 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  21
  22 import os, sys
  23 import re, time, traceback
  24 from pprint import pformat
  25
  26 from objavi.twiki_wrapper import TWikiBook, get_chapter_html, get_book_list
  27 from objavi.cgi_utils import parse_args, optionise, shift_file, output_blob_and_exit, log, make_book_name
  28 from objavi import config
  29
  30 from booki.xhtml_utils import EpubChapter
  31 from booki.bookizip import BookiZip
  32
  33
  34 def make_booki_package(server, bookid, clean=False, use_cache=False):
  35     """Extract all chapters from the specified book, as well as
  36     associated images and metadata, and zip it all up for conversion
  37     to epub.
  38
  39     If clean is True, the chapters will be cleaned up and converted to
  40     XHTML 1.1.  If cache is true, images that have been fetched on
  41     previous runs will be reused.
  42     """
  43     if clean:
  44         bookname = make_book_name(bookid, server, '-clean.zip')
  45     else:
  46         bookname = make_book_name(bookid, server, '.zip')
  47
  48     book = TWikiBook(bookid, server, bookname)
  49     zfn = book.filepath(bookname)
  50     md = book.get_twiki_metadata()
  51     log(pformat(md))
  52     bz = BookiZip(zfn, md)
  53
  54     all_images = set()
  55     for chapter in bz.info['spine']:
  56         contents = get_chapter_html(server, bookid, chapter, wrapped=True)
  57         c = EpubChapter(server, bookid, chapter, contents,
  58                         use_cache=use_cache)
  59         images = c.localise_links()
  60         all_images.update(images)
  61         if clean:
  62             c.remove_bad_tags()
  63             bz.add_to_package(chapter, chapter + '.xhtml', c.as_xhtml())
  64         else:
  65             bz.add_to_package(chapter, chapter + '.html', c.as_html())
  66
  67     # Add images afterwards, to sift out duplicates
  68     for image in all_images:
  69         imgdata = c.image_cache.read_local_url(image)
  70         bz.add_to_package(image, image, imgdata)
  71
  72     bz.finish()
  73     return bz.filename
  74
  75
  76 # ARG_VALIDATORS is a mapping between the expected cgi arguments and
  77 # functions to validate their values. (None means no validation).
  78 ARG_VALIDATORS = {
  79     "book": re.compile(r'^(\w+/?)*\w+$').match, # can be: BlahBlah/Blah_Blah
  80     "server": config.SERVER_DEFAULTS.__contains__,
  81     "use-cache": None,
  82     "clean": None,
  83     'mode': ('zip', 'html').__contains__,
  84     "all": ['all', 'skip-existing'].__contains__,
  85 }
  86
  87 if __name__ == '__main__':
  88
  89     args = parse_args(ARG_VALIDATORS)
  90     clean = bool(args.get('clean', False))
  91     use_cache = args.get('use-cache')
  92     if use_cache is None:
  93         use_cache = (os.environ.get('HTTP_HOST') in config.USE_IMG_CACHE_ALWAYS_HOSTS)
  94
  95     make_all = args.get('all')
  96     if 'server' in args and 'book' in args:
  97         zfn = make_booki_package(args['server'], args['book'], clean, use_cache)
  98         fn = shift_file(zfn, config.BOOKI_BOOK_DIR)
  99         ziplink = '<p><a href="%s">%s zip file.</a></p>' % (fn, args['book'])
 100
 101         mode = args.get('mode', 'html')
 102         if mode == 'zip':
 103             f = open(fn)
 104             data = f.read()
 105             f.close()
 106             output_blob_and_exit(data, 'application/x-booki+zip', args['book'] + '.zip')
 107
 108     elif 'server' in args and make_all is not None:
 109         links = []
 110         for book in get_book_list(args['server']):
 111             if make_all == 'skip-existing' and book + '.zip' in os.listdir(config.BOOKI_BOOK_DIR):
 112                 log("skipping %s" % book)
 113                 continue
 114             try:
 115                 zfn = make_booki_package(args['server'], book, use_cache=use_cache)
 116                 fn = shift_file(zfn, config.BOOKI_BOOK_DIR)
 117                 links.append('<a href="%s">%s</a> ' % (fn, book))
 118             except Exception:
 119                 log('FAILED to make book "%s"' % book)
 120                 traceback.print_exc()
 121         ziplink = ''.join(links)
 122     else:
 123         ziplink = ''
 124
 125     print "Content-type: text/html; charset=utf-8\n"
 126     f = open('templates/booki-twiki-gateway.html')
 127     template = f.read()
 128     f.close()
 129
 130     print template % {'ziplink': ziplink,
 131                       'server-list': optionise(sorted(config.SERVER_DEFAULTS.keys()))}
 132