objavi2.py

   1 #!/usr/bin/python
   2 #
   3 # Part of Objavi2, which turns html manuals into books
   4 #
   5 # Copyright (C) 2009 Douglas Bagnall
   6 #
   7 # This program is free software; you can redistribute it and/or modify
   8 # it under the terms of the GNU General Public License as published by
   9 # the Free Software Foundation; either version 2 of the License, or
  10 # (at your option) any later version.
  11 #
  12 # This program is distributed in the hope that it will be useful,
  13 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15 # GNU General Public License for more details.
  16 #
  17 # You should have received a copy of the GNU General Public License along
  18 # with this program; if not, write to the Free Software Foundation, Inc.,
  19 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  20
  21 """Make a pdf from the specified book."""
  22 import os, sys
  23 import cgi
  24 import re, time
  25 from urllib2 import urlopen
  26 from getopt import gnu_getopt
  27
  28 from fmbook import log, Book
  29 from fmbook import PAGE_SETTINGS, SERVER_DEFAULTS, DEFAULT_SERVER
  30
  31 import config
  32 from config import BOOK_LIST_CACHE, BOOK_LIST_CACHE_DIR
  33
  34 FORM_TEMPLATE = os.path.abspath('templates/form.html')
  35 PROGRESS_TEMPLATE = os.path.abspath('templates/progress.html')
  36
  37 # ARG_VALIDATORS is a mapping between the expected cgi arguments and
  38 # functions to validate their values. (None means no validation).
  39
  40 ARG_VALIDATORS = {
  41     "webName": re.compile(r'^(\w+/?)*\w+$').match, # can be: BlahBlah/Blah_Blah
  42     "css": None, # an url, empty (for default), or css content
  43     "title": lambda x: len(x) < 999,
  44     "header": None, # header text, UNUSED
  45     "isbn": lambda x: x.isdigit() and len(x) == 13,
  46     "license": lambda x: len(x) < 999, #should be a codename?
  47     "server": SERVER_DEFAULTS.__contains__,
  48     "engine": config.ENGINES.__contains__,
  49     "booksize": PAGE_SETTINGS.__contains__,
  50     "cgi-context": lambda x: x.lower() in '1true0false',
  51     "mode": str.isalnum,
  52     "rotate": u"rotate".__eq__,
  53 }
  54
  55 __doc__ += '\nValid arguments are: %s.\n' % ', '.join(ARG_VALIDATORS.keys())
  56
  57 def parse_args():
  58     """Read and validate CGI or commandline arguments, putting the
  59     good ones into the returned dictionary.  Command line arguments
  60     should be in the form --title='A Book'.
  61     """
  62     query = cgi.FieldStorage()
  63     options, args = gnu_getopt(sys.argv[1:], '', [x + '=' for x in ARG_VALIDATORS])
  64     options = dict(options)
  65     log(options)
  66     data = {}
  67     for key, validator in ARG_VALIDATORS.items():
  68         value = query.getfirst(key, options.get('--' + key, None))
  69         log('%s: %s' % (key, value), debug='STARTUP')
  70         if value is not None:
  71             if validator is not None and not validator(value):
  72                 log("argument '%s' is not valid ('%s')" % (key, value))
  73                 continue
  74             data[key] = value
  75
  76     log(data, debug='STARTUP')
  77     return data
  78
  79 def get_server_list():
  80     return sorted(SERVER_DEFAULTS.keys())
  81
  82
  83 def get_book_list(server):
  84     """Ask the server for a list of books.  Floss Manual TWikis keep such a list at
  85     /bin/view/TWiki/WebLeftBarWebsList?skin=text but it needs a bit of processing
  86
  87     If BOOK_LIST_CACHE is non-zero, the book list won't be re-fetched
  88     in that many seconds, rather it will be read from disk.
  89     """
  90     if BOOK_LIST_CACHE:
  91        cache_name = os.path.join(BOOK_LIST_CACHE_DIR, '%s.booklist' % server)
  92        if (os.path.exists(cache_name) and
  93            os.stat(cache_name).st_mtime + BOOK_LIST_CACHE > time.time()):
  94            f = open(cache_name)
  95            s = f.read()
  96            f.close()
  97            return s.split()
  98
  99     url = 'http://%s/bin/view/TWiki/WebLeftBarWebsList?skin=text' % server
 100     #XXX should use lxml
 101     log(url)
 102     f = urlopen(url)
 103     s = f.read()
 104     f.close()
 105     items = sorted(re.findall(r'/bin/view/([\w/]+)/WebHome', s))
 106     if BOOK_LIST_CACHE:
 107         f = open(cache_name, 'w')
 108         f.write('\n'.join(items))
 109         f.close()
 110     return items
 111
 112 def get_size_list():
 113     #XXX PAGE_SETTINGS instances are only constructed for this list.
 114     # the area and mmsizes could be calculated seperately here from PAGE_SIZE_DATA
 115
 116     #order by increasing areal size.
 117     ordered = [x[1] for x in
 118                sorted((v.area, v) for v in PAGE_SETTINGS.values())]
 119     return [(v.name, '%s (%dmm x %dmm)' % (v.name, v.mmsize[0], v.mmsize[1]))
 120             for v in ordered]
 121
 122
 123 def optionise(items, default=None):
 124     options = []
 125     for x in items:
 126         if isinstance(x, str):
 127             if x == default:
 128                 options.append('<option selected="selected">%s</option>' % x)
 129             else:
 130                 options.append('<option>%s</option>' % x)
 131         else:
 132             log(x, x[0])
 133             # couple: value, name
 134             if x[0] == default:
 135                 options.append('<option selected="selected" value="%s">%s</option>' % x)
 136             else:
 137                 options.append('<option value="%s">%s</option>' % x)
 138
 139     return '\n'.join(options)
 140
 141 def get_default_css(server=DEFAULT_SERVER):
 142     log(server)
 143     cssfile = SERVER_DEFAULTS[server]['css']
 144     log(cssfile)
 145     f = open(cssfile)
 146     s = f.read()
 147     f.close()
 148     #log(s)
 149     return s
 150
 151 def font_links():
 152     """Links to various example pdfs."""
 153     links = []
 154     for script in os.listdir(config.FONT_EXAMPLE_SCRIPT_DIR):
 155         if not script.isalnum():
 156             log("warning: font-sample %s won't work; skipping" % script)
 157             continue
 158         links.append('<a href="%s?script=%s">%s</a>' % (config.FONT_LIST_URL, script, script))
 159     return ', '.join(links)
 160
 161
 162 def show_form(args, server, webname, size='COMICBOOK', engine='webkit'):
 163     f = open(FORM_TEMPLATE)
 164     template = f.read()
 165     f.close()
 166     f = open(config.FONT_LIST_INCLUDE)
 167     font_list = f.read()
 168     f.close()
 169     d = {
 170         'server_options': optionise(get_server_list(), default=server),
 171         'book_options': optionise(get_book_list(server), default=webname),
 172         'size_options': optionise(get_size_list(), default=size),
 173         'engines': optionise(config.ENGINES.keys(), default=engine),
 174         'css': get_default_css(server),
 175         'font_links': font_links(),
 176         'font_list': font_list,
 177     }
 178     print template % d
 179
 180
 181 def make_progress_page(webname, bookname):
 182     f = open(PROGRESS_TEMPLATE)
 183     template = f.read()
 184     f.close()
 185     d = {
 186         'webname': webname,
 187         'bookname': bookname,
 188     }
 189     print template % d
 190     def progress_notifier(message):
 191         print ('<script type="text/javascript">\n'
 192                'objavi_show_progress("%s");\n'
 193                '</script>' % message
 194                )
 195         if message == 'finished':
 196             print '</body></html>'
 197         sys.stdout.flush()
 198     return progress_notifier
 199
 200 def print_progress(message):
 201     print '******* got message "%s"' %message
 202
 203 def make_book_name(webname, server):
 204     lang = SERVER_DEFAULTS.get(server, SERVER_DEFAULTS[DEFAULT_SERVER])['lang']
 205     webname = ''.join(x for x in webname if x.isalnum())
 206     return '%s-%s-%s.pdf' % (webname, lang,
 207                              time.strftime('%Y.%m.%d-%H.%M.%S'))
 208
 209 if __name__ == '__main__':
 210     args = parse_args()
 211     webname = args.get('webName')
 212     server = args.get('server', config.DEFAULT_SERVER)
 213     size = args.get('booksize', config.DEFAULT_SIZE)
 214     engine = args.get('engine', config.DEFAULT_ENGINE)
 215     mode = args.get('mode')
 216
 217     cgi_context = 'SERVER_NAME' in os.environ or args.get('cgi-context', 'NO').lower() in '1true'
 218     if cgi_context:
 219         print "Content-type: text/html; charset=utf-8\n"
 220
 221     if mode == 'booklist':
 222         print optionise(get_book_list(server), default=webname)
 223         sys.exit()
 224     if mode == 'css':
 225         #XX sending as text/html, but it doesn't really matter
 226         print get_default_css(server=server)
 227         sys.exit()
 228
 229     if not webname or not server:
 230         if cgi_context:
 231             show_form(args, server, webname, size)
 232         else:
 233             print __doc__
 234         sys.exit()
 235
 236     # so we're making a book.
 237     bookname = make_book_name(webname, server)
 238     if cgi_context:
 239         progress_bar = make_progress_page(webname, bookname)
 240     else:
 241         progress_bar = print_progress
 242
 243     #XXX could use 'with Book() as book': to makesure cleanup happens
 244     # (or try ... finally)
 245
 246     book = Book(webname, server, bookname, pagesize=size, engine=engine,
 247                 watcher=progress_bar
 248                 )
 249
 250     if cgi_context:
 251         book.spawn_x()
 252
 253     book.load()
 254
 255     book.set_title(args.get('title'))
 256     book.add_css(args.get('css'))
 257
 258     book.compose_inside_cover(args.get('license'), args.get('isbn'))
 259
 260     book.add_section_titles()
 261
 262     book.make_pdf()
 263
 264     if "rotate" in args:
 265         book.rotate180()
 266
 267     book.publish_pdf()
 268
 269     book.cleanup()
 270
 271     book.notify_watcher('finished')