jbparse/jbparse/kanjidic_common.py

   1 # -*- coding: utf-8 -*-
   2
   3 # Copyright (c) 2009, Paul Goins
   4 # All rights reserved.
   5 #
   6 # Redistribution and use in source and binary forms, with or without
   7 # modification, are permitted provided that the following conditions
   8 # are met:
   9 #
  10 #     * Redistributions of source code must retain the above copyright
  11 #       notice, this list of conditions and the following disclaimer.
  12 #     * Redistributions in binary form must reproduce the above
  13 #       copyright notice, this list of conditions and the following
  14 #       disclaimer in the documentation and/or other materials provided
  15 #       with the distribution.
  16 #
  17 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  18 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  19 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
  20 # FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
  21 # COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
  22 # INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
  23 # BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
  24 # LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
  25 # CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  26 # LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
  27 # ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
  28 # POSSIBILITY OF SUCH DAMAGE.
  29
  30 """Helper functions for KANJIDIC and KANJIDIC2 parsers.
  31
  32 This module is not intended to be used by itself.
  33
  34 """
  35
  36 def jstring_convert(s):
  37     """Convert's from Jim Breen's -x.xx- notation to 〜x(xx)〜 notation."""
  38     s = s.replace(u'-', u'〜')
  39     parts = s.split(u'.', 1)
  40     if len(parts) == 1:
  41         return s
  42     return u"%s(%s)" % tuple(parts)
  43
  44 def kanjidic2_key_to_str(dkey):
  45     """Converts KANJIDIC2 dictionary keys to dictionary names.
  46
  47     If unable to find a KANJIDIC2 key, returns the original key.
  48
  49     """
  50     d = {
  51         "halpern_njecd":
  52         _(u"New Japanese-English Character Dictionary (Halpern)"),
  53         "nelson_c":
  54         _(u"Modern Reader's Japanese-English Character Dictionary (Nelson)"),
  55         "nelson_n":
  56         _(u"The New Nelson Japanese-English Character Dictionary (Haig)"),
  57         "sh_kk": _(u"Kanji and Kana (Spahn/Hadamitzky)"),
  58         "moro": _(u"Morohashi Daikanwajiten"),
  59         "henshall":
  60         _(u"A Guide To Remembering Japanese Characters (Henshall)"),
  61         "gakken": _(u"A New Dictionary of Kanji Usage (Gakken)"),
  62         "heisig": _(u"Remembering the Kanji (Heisig)"),
  63         "oneill_names": _(u"Japanese Names (O'Neill)"),
  64         "busy_people": _(u"Japanese For Busy People (AJLT)"),
  65         "crowley": _(u"The Kanji Way to Japanese Language Power (Crowley)"),
  66         "jf_cards": _(u"Japanese Kanji Flashcards (Hodges/Okazaki)"),
  67         "kodansha_compact": _(u"Kodansha Compact Kanji Guide"),
  68         "henshall3": _(u"A Guide To Reading and Writing Japanese (Henshall)"),
  69         "kanji_in_context": _(u"Kanji in Context (Nishiguchi/Kono)"),
  70         "halpern_kkld": _(u"Kodansha Kanji Learners Dictionary (Halpern)"),
  71         "oneill_kk": _(u"Essential Kanji (O'Neill)"),
  72         "sakade": _(u"A Guide To Reading and Writing Japanese (Sakade)"),
  73         "tutt_cards": _(u"Tuttle Kanji Cards (Kask)"),
  74         "maniette": _(u"French version of Heisig (Maniette)")
  75         }
  76     return d.get(dkey, dkey)
  77
  78 def qcode_to_desc(qkey):
  79     d = {
  80         u'skip': u'SKIP',
  81         u'deroo': u'De Roo',
  82         u'sh_desc': u'Spahn/Hadamitzky Kanji Dictionary',
  83         u'four_corner': u'Four Corner'
  84         }
  85     return d.get(qkey, qkey)