1#!/usr/local/bin/python
2# -*- coding: iso-8859-1 -*-
3
4# $Id$
5
6# Copyright (c) 2004, 2008 Kungliga Tekniska Högskolan
7# (Royal Institute of Technology, Stockholm, Sweden).
8# All rights reserved.
9#
10# Redistribution and use in source and binary forms, with or without
11# modification, are permitted provided that the following conditions
12# are met:
13#
14# 1. Redistributions of source code must retain the above copyright
15#    notice, this list of conditions and the following disclaimer.
16#
17# 2. Redistributions in binary form must reproduce the above copyright
18#    notice, this list of conditions and the following disclaimer in the
19#    documentation and/or other materials provided with the distribution.
20#
21# 3. Neither the name of the Institute nor the names of its contributors
22#    may be used to endorse or promote products derived from this software
23#    without specific prior written permission.
24#
25# THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND
26# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
27# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
28# ARE DISCLAIMED.  IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE
29# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
30# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
31# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
32# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
33# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
34# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
35# SUCH DAMAGE.
36
37import re
38import string
39
40def read():
41    """return a dict of tables from rfc4518"""
42
43    ret = {}
44
45#2.2.  Map
46#
47#   SOFT HYPHEN (U+00AD) and MONGOLIAN TODO SOFT HYPHEN (U+1806) code
48#   points are mapped to nothing.  COMBINING GRAPHEME JOINER (U+034F) and
49#   VARIATION SELECTORs (U+180B-180D, FF00-FE0F) code points are also
50#   mapped to nothing.  The OBJECT REPLACEMENT CHARACTER (U+FFFC) is
51#   mapped to nothing.
52
53    t = []
54    t.append(" 00AD; ; Map to nothing")
55    t.append(" 1806; ; Map to nothing")
56    t.append(" 034F; ; Map to nothing")
57
58    t.append(" 180B; ; Map to nothing")
59    t.append(" 180C; ; Map to nothing")
60    t.append(" 180D; ; Map to nothing")
61
62    t.append(" FE00; ; Map to nothing")
63    t.append(" FE01; ; Map to nothing")
64    t.append(" FE02; ; Map to nothing")
65    t.append(" FE03; ; Map to nothing")
66    t.append(" FE04; ; Map to nothing")
67    t.append(" FE05; ; Map to nothing")
68    t.append(" FE06; ; Map to nothing")
69    t.append(" FE07; ; Map to nothing")
70    t.append(" FE08; ; Map to nothing")
71    t.append(" FE09; ; Map to nothing")
72    t.append(" FE0A; ; Map to nothing")
73    t.append(" FE0B; ; Map to nothing")
74    t.append(" FE0C; ; Map to nothing")
75    t.append(" FE0D; ; Map to nothing")
76    t.append(" FE0E; ; Map to nothing")
77    t.append(" FE0F; ; Map to nothing")
78
79    t.append(" FFFC; ; Map to nothing")
80
81#   CHARACTER TABULATION (U+0009), LINE FEED (LF) (U+000A), LINE
82#   TABULATION (U+000B), FORM FEED (FF) (U+000C), CARRIAGE RETURN (CR)
83#  (U+000D), and NEXT LINE (NEL) (U+0085) are mapped to SPACE (U+0020).
84
85    t.append(" 0009; 0020 ; Map to SPACE")
86    t.append(" 000A; 0020 ; Map to SPACE")
87    t.append(" 000B; 0020 ; Map to SPACE")
88    t.append(" 000C; 0020 ; Map to SPACE")
89    t.append(" 000D; 0020 ; Map to SPACE")
90    t.append(" 0085; 0020 ; Map to SPACE")
91
92#   All other control code (e.g., Cc) points or code points with a
93#   control function (e.g., Cf) are mapped to nothing.  The following is
94#   a complete list of these code points: U+0000-0008, 000E-001F, 007F-
95#   0084, 0086-009F, 06DD, 070F, 180E, 200C-200F, 202A-202E, 2060-2063,
96#   206A-206F, FEFF, FFF9-FFFB, 1D173-1D17A, E0001, E0020-E007F.
97
98    t.append(" 0000-0008; ; Map to nothing")
99    t.append(" 000E-001F; ; Map to nothing")
100    t.append(" 007F-0084; ; Map to nothing")
101    t.append(" 0086-009F; ; Map to nothing")
102    t.append(" 06DD; ; Map to nothing")
103    t.append(" 070F; ; Map to nothing")
104    t.append(" 180E; ; Map to nothing")
105    t.append(" 200C-200F; ; Map to nothing")
106    t.append(" 202A-202E; ; Map to nothing")
107    t.append(" 2060-2063; ; Map to nothing")
108    t.append(" 206A-206F; ; Map to nothing")
109    t.append(" FEFF; ; Map to nothing")
110    t.append(" FFF9-FFFB; ; Map to nothing")
111    t.append(" 1D173-1D17A; ; Map to nothing")
112    t.append(" E0001; ; Map to nothing")
113    t.append(" E0020-E007F; ; Map to nothing")
114
115#   ZERO WIDTH SPACE (U+200B) is mapped to nothing.  All other code
116#   points with Separator (space, line, or paragraph) property (e.g., Zs,
117#   Zl, or Zp) are mapped to SPACE (U+0020).  The following is a complete
118#   list of these code points: U+0020, 00A0, 1680, 2000-200A, 2028-2029,
119#   202F, 205F, 3000.
120
121    t.append(" 200B; ; Map to nothing")
122    t.append(" 0020; 0020; Map to SPACE")
123    t.append(" 00A0; 0020; Map to SPACE")
124    t.append(" 1680; 0020; Map to SPACE")
125    t.append(" 2000-200A; 0020; Map to SPACE")
126    t.append(" 2028-2029; 0020; Map to SPACE")
127    t.append(" 202F; 0020; Map to SPACE")
128    t.append(" 205F; 0020; Map to SPACE")
129    t.append(" 3000; 0020; Map to SPACE")
130
131    ret["rfc4518-map"] = t
132
133#   For case ignore, numeric, and stored prefix string matching rules,
134#   characters are case folded per B.2 of [RFC3454].
135
136    t = []
137
138#2.4.  Prohibit
139
140#    The REPLACEMENT CHARACTER (U+FFFD) code point is prohibited.
141
142    t.append(" FFFD;")
143
144    ret["rfc4518-error"] = t
145
146    t = []
147
148
149
150    return ret
151