#!/usr/bin/env python

 # coding=UTF-8

 # Copyright (c) 2008 Geoffrey Sneddon

 #

 # Permission is hereby granted, free of charge, to any person obtaining a copy

 # of this software and associated documentation files (the "Software"), to deal

 # in the Software without restriction, including without limitation the rights

 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell

 # copies of the Software, and to permit persons to whom the Software is

 # furnished to do so, subject to the following conditions:

 #

 # The above copyright notice and this permission notice shall be included in

 # all copies or substantial portions of the Software.

 #

 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR

 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,

 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE

 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER

 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,

 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN

 # THE SOFTWARE.

 """usage: anolis [options] input output

 Post-process a document, adding cross-references, table of contents, etc.

 """

 from optparse import OptionParser, SUPPRESS_HELP

 import sys

 from lxml import etree

 from anolislib import generator, utils

 def main():

     # Create the options parser

     optParser = getOptParser()

     opts, args = optParser.parse_args()

     # Check we have enough arguments

     if len(args) >= 2:

         try:

             # Get options

             kwargs = vars(opts)

             # Get input and generate

             input = open(args[0], "rb")

             tree = generator.fromFile(input, **kwargs)

             input.close()

             # Write output

             output = open(args[1], "wb")

             generator.toFile(tree, output, **kwargs)

             output.close()

         except (utils.AnolisException, IOError, etree.XMLSyntaxError), e:

             sys.stderr.write(unicode(e) + u"\n")

             sys.exit(1)

     else:

         sys.stderr.write(u"anolis expects two arguments. Use -h for help\n")

         sys.exit(2)

 def getOptParser():

     def enable(option, opt_str, value, parser, *args, **kwargs):

         parser.values.processes.add(value)

     def disable(option, opt_str, value, parser, *args, **kwargs):

         parser.values.processes.discard(value)

     parser = OptionParser(usage = __doc__, version="%prog 1.1dev")

     parser.add_option("", "--enable", action="callback", callback=enable,

                       type="string", dest="processes",

                       help="Enable the process given as the option value")

     parser.add_option("", "--disable", action="callback", callback=disable,

                       type="string",

                       help="Disable the process given as the option value")

     parser.add_option("", "--parser", type="choice",

                       choices=("html5lib", "lxml.html"),

                       help="Choose what parser to use. Valid options: html5lib, lxml.html")

     parser.add_option("", "--serializer", type="choice",

                       choices=("html5lib", "lxml.html"),

                       help="Choose what serializer to use. Valid options: html5lib, lxml.html")

     parser.add_option("", "--newline-char", action="store", type="string",

                       dest="newline_char",

                       help="Set the newline character/string used when creating new newlines. This should match the rest of the newlines in the document.")

     parser.add_option("", "--indent-char", action="store", type="string",

                       dest="indent_char",

                       help="Set the character/string used when creating indenting new blocks of (X)HTML. This should match the rest of the indentation in the document.")

     parser.add_option("", "--force-html4-id", action="store_true",

                       dest="force_html4_id",

                       help="Force the ID generation algorithm to create HTML 4 compliant IDs regardless of the DOCTYPE.")

     parser.add_option("", "--min-depth", action="store", type="int",

                       dest="min_depth",

                       help="Highest ranking header to number/insert into TOC.")

     parser.add_option("", "--max-depth", action="store", type="int",

                       dest="max_depth",

                       help="Lowest ranking header to number/insert into TOC.")

     parser.add_option("", "--allow-duplicate-dfns", action="store_true",

                       dest="allow_duplicate_dfns",

                       help="Allow multiple definitions of terms when cross-referencing (the last instance of the term is used when referencing it).")

     parser.add_option("", "--w3c-compat", action="store_true",

                       dest="w3c_compat",

                       help="Behave in a (mostly) compatible way to the W3C CSS WG's Postprocessor (this implies all of the other --w3c-compat options with the exception of --w3c-compat-crazy-substitution, as that is too crazy).")

     parser.add_option("", "--w3c-compat-xref-elements", action="store_true",

                       dest="w3c_compat_xref_elements",

                       help="Uses the same list of elements to look for cross-references in as the W3C CSS WG's Postprocessor, even when the elements shouldn't semantically be used for cross-reference terms.")

     parser.add_option("", "--w3c-compat-xref-a-placement", action="store_true",

                       dest="w3c_compat_xref_a_placement",

                       help="When cross-referencing elements apart from span, put the a element inside the element instead of outside the element.")

     parser.add_option("", "--w3c-compat-xref-normalization", action="store_true",

                       dest="w3c_compat_xref_normalization",

                       help="Only use ASCII letters, numbers, and spaces in comparison of cross-reference terms.")

     parser.add_option("", "--w3c-compat-class-toc", action="store_true",

                       dest="w3c_compat_class_toc",

                       help="Add @class='toc' on every ol element in the table of contents (instead of only the root ol element).")

     parser.add_option("", "--w3c-compat-substitutions", action="store_true",

                       dest="w3c_compat_substitutions",

                       help="Do W3C specific substitutions.")

     parser.add_option("", "--w3c-compat-crazy-substitutions", action="store_true",

                       dest="w3c_compat_crazy_substitutions",

                       help="Do crazy W3C specific substitutions, which may cause unexpected behaviour (i.e., replacing random strings within the document with no special marker).")

     profile = True

     try:

         import cProfile

         import pstats

     except ImportError:

         try:

             import hotshot

             import hotshot.stats

         except ImportError:

             profile = False

     if profile:

         parser.add_option("", "--profile", action="store_true",

             dest="profile", help=SUPPRESS_HELP)

     parser.add_option("", "--inject-meta-charset", action="store_true",

                       dest="inject_meta_charset", help=SUPPRESS_HELP)

     parser.add_option("", "--strip-whitespace", action="store_true",

                       dest="strip_whitespace", help=SUPPRESS_HELP)

     parser.add_option("", "--omit-optional-tags", action="store_true",

                       dest="omit_optional_tags", help=SUPPRESS_HELP)

     parser.add_option("", "--quote-attr-values", action="store_true",

                       dest="quote_attr_values", help=SUPPRESS_HELP)

     parser.add_option("", "--use-best-quote-char", action="store_true",

                       dest="use_best_quote_char", help=SUPPRESS_HELP)

     parser.add_option("", "--no-minimize-boolean-attributes",

                       action="store_false",

                       dest="minimize_boolean_attributes", help=SUPPRESS_HELP)

     parser.add_option("", "--use-trailing-solidus", action="store_true",

                       dest="use_trailing_solidus", help=SUPPRESS_HELP)

     parser.add_option("", "--space-before-trailing-solidus",

                       action="store_true",

                       dest="space_before_trailing_solidus", help=SUPPRESS_HELP)

     parser.add_option("", "--escape-lt-in-attrs", action="store_true",

                       dest="escape_lt_in_attrs", help=SUPPRESS_HELP)

     parser.add_option("", "--escape-rcdata", action="store_true",

                       dest="escape_rcdata", help=SUPPRESS_HELP)

     parser.add_option("", "--output-encoding", action="store", type=str,

                       dest="output_encoding", help="Output encoding")

     parser.set_defaults(

         processes=set(["sub", "xref", "toc"]),

         parser="html5lib",

         serializer="html5lib",

         newline_char=u"\n",

         indent_char=u" ",

         force_html4_id=False,

         min_depth=2,

         max_depth=6,

         allow_duplicate_dfns=False,

         w3c_compat=False,

         w3c_compat_xref_elements=False,

         w3c_compat_xref_a_placement=False,

         w3c_compat_xref_normalization=False,

         w3c_compat_class_toc=False,

         w3c_compat_substitutions=False,

         w3c_compat_crazy_substitutions=False,

         profile=False,

         inject_meta_charset=False,

         omit_optional_tags=False,

         quote_attr_values=False,

         use_best_quote_char=False,

         minimize_boolean_attributes=False,

         use_trailing_solidus=False,

         space_before_trailing_solidus=False,

         escape_lt_in_attrs=False,

         escape_rcdata=False,

         output_encoding="utf-8"

     )

     return parser

 if __name__ == "__main__":

     main()