1# sgml.tcl --
2#
3#       This file provides generic parsing services for SGML-based
4#       languages, namely HTML and XML.
5#       This file supports Tcl 8.1 characters and regular expressions.
6#
7#       NB.  It is a misnomer.  There is no support for parsing
8#       arbitrary SGML as such.
9#
10# Copyright (c) 1998-2001 Zveno Pty Ltd
11# http://www.zveno.com/
12#
13# Zveno makes this software available free of charge for any purpose.
14# Copies may be made of this software but all of this notice must be included
15# on any copy.
16#
17# The software was developed for research purposes only and Zveno does not
18# warrant that it is error free or fit for any purpose.  Zveno disclaims any
19# liability for all claims, expenses, losses, damages and costs any user may
20# incur as a result of using, copying or modifying this software.
21#
22# Copyright (c) 1997 ANU and CSIRO on behalf of the
23# participants in the CRC for Advanced Computational Systems ('ACSys').
24#
25# ACSys makes this software and all associated data and documentation
26# ('Software') available free of charge for any purpose.  You may make copies
27# of the Software but you must include all of this notice on any copy.
28#
29# The Software was developed for research purposes and ACSys does not warrant
30# that it is error free or fit for any purpose.  ACSys disclaims any
31# liability for all claims, expenses, losses, damages and costs any user may
32# incur as a result of using, copying or modifying the Software.
33#
34# $Id$
35
36package require Tcl 8.1
37
38package provide sgml 1.8
39
40namespace eval sgml {
41
42    # Convenience routine
43    proc cl x {
44        return "\[$x\]"
45    }
46
47    # Define various regular expressions
48
49    # Character classes
50    variable Char \t\n\r\ -\uD7FF\uE000-\uFFFD\u10000-\u10FFFF
51    variable BaseChar \u0041-\u005A\u0061-\u007A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u0131\u0134-\u013E\u0141-\u0148\u014A-\u017E\u0180-\u01C3\u01CD-\u01F0\u01F4-\u01F5\u01FA-\u0217\u0250-\u02A8\u02BB-\u02C1\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03CE\u03D0-\u03D6\u03DA\u03DC\u03DE\u03E0\u03E2-\u03F3\u0401-\u040C\u040E-\u044F\u0451-\u045C\u045E-\u0481\u0490-\u04C4\u04C7-\u04C8\u04CB-\u04CC\u04D0-\u04EB\u04EE-\u04F5\u04F8-\u04F9\u0531-\u0556\u0559\u0561-\u0586\u05D0-\u05EA\u05F0-\u05F2\u0621-\u063A\u0641-\u064A\u0671-\u06B7\u06BA-\u06BE\u06C0-\u06CE\u06D0-\u06D3\u06D5\u06E5-\u06E6\u0905-\u0939\u093D\u0958-\u0961\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09DC-\u09DD\u09DF-\u09E1\u09F0-\u09F1\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABD\u0AE0\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3D\u0B5C-\u0B5D\u0B5F-\u0B61\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C60-\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CDE\u0CE0-\u0CE1\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D60-\u0D61\u0E01-\u0E2E\u0E30\u0E32-\u0E33\u0E40-\u0E45\u0E81-\u0E82\u0E84\u0E87-\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA-\u0EAB\u0EAD-\u0EAE\u0EB0\u0EB2-\u0EB3\u0EBD\u0EC0-\u0EC4\u0F40-\u0F47\u0F49-\u0F69\u10A0-\u10C5\u10D0-\u10F6\u1100\u1102-\u1103\u1105-\u1107\u1109\u110B-\u110C\u110E-\u1112\u113C\u113E\u1140\u114C\u114E\u1150\u1154-\u1155\u1159\u115F-\u1161\u1163\u1165\u1167\u1169\u116D-\u116E\u1172-\u1173\u1175\u119E\u11A8\u11AB\u11AE-\u11AF\u11B7-\u11B8\u11BA\u11BC-\u11C2\u11EB\u11F0\u11F9\u1E00-\u1E9B\u1EA0-\u1EF9\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2126\u212A-\u212B\u212E\u2180-\u2182\u3041-\u3094\u30A1-\u30FA\u3105-\u312C\uAC00-\uD7A3
52    variable Ideographic \u4E00-\u9FA5\u3007\u3021-\u3029
53    variable CombiningChar \u0300-\u0345\u0360-\u0361\u0483-\u0486\u0591-\u05A1\u05A3-\u05B9\u05BB-\u05BD\u05BF\u05C1-\u05C2\u05C4\u064B-\u0652\u0670\u06D6-\u06DC\u06DD-\u06DF\u06E0-\u06E4\u06E7-\u06E8\u06EA-\u06ED\u0901-\u0903\u093C\u093E-\u094C\u094D\u0951-\u0954\u0962-\u0963\u0981-\u0983\u09BC\u09BE\u09BF\u09C0-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09E2-\u09E3\u0A02\u0A3C\u0A3E\u0A3F\u0A40-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A70-\u0A71\u0A81-\u0A83\u0ABC\u0ABE-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0B01-\u0B03\u0B3C\u0B3E-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B82-\u0B83\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0C01-\u0C03\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C82-\u0C83\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0D02-\u0D03\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0E31\u0E34-\u0E3A\u0E47-\u0E4E\u0EB1\u0EB4-\u0EB9\u0EBB-\u0EBC\u0EC8-\u0ECD\u0F18-\u0F19\u0F35\u0F37\u0F39\u0F3E\u0F3F\u0F71-\u0F84\u0F86-\u0F8B\u0F90-\u0F95\u0F97\u0F99-\u0FAD\u0FB1-\u0FB7\u0FB9\u20D0-\u20DC\u20E1\u302A-\u302F\u3099\u309A
54    variable Digit \u0030-\u0039\u0660-\u0669\u06F0-\u06F9\u0966-\u096F\u09E6-\u09EF\u0A66-\u0A6F\u0AE6-\u0AEF\u0B66-\u0B6F\u0BE7-\u0BEF\u0C66-\u0C6F\u0CE6-\u0CEF\u0D66-\u0D6F\u0E50-\u0E59\u0ED0-\u0ED9\u0F20-\u0F29
55    variable Extender \u00B7\u02D0\u02D1\u0387\u0640\u0E46\u0EC6\u3005\u3031-\u3035\u309D-\u309E\u30FC-\u30FE
56    variable Letter $BaseChar|$Ideographic
57
58    # white space
59    variable Wsp " \t\r\n"
60    variable noWsp [cl ^$Wsp]
61
62    # Various XML names
63    variable NameChar \[-$Letter$Digit._:$CombiningChar$Extender\]
64    variable Name \[_:$BaseChar$Ideographic\]$NameChar*
65    variable Names ${Name}(?:$Wsp$Name)*
66    variable Nmtoken $NameChar+
67    variable Nmtokens ${Nmtoken}(?:$Wsp$Nmtoken)*
68
69    # table of predefined entities for XML
70
71    variable EntityPredef
72    array set EntityPredef {
73        lt <   gt >   amp &   quot \"   apos '
74    }
75
76}
77
78# These regular expressions are defined here once for better performance
79
80namespace eval sgml {
81    variable Wsp
82
83    # Watch out for case-sensitivity
84
85    set attlist_exp [cl $Wsp]*([cl ^$Wsp]+)[cl $Wsp]*([cl ^$Wsp]+)[cl $Wsp]*(#REQUIRED|#IMPLIED)
86    set attlist_enum_exp [cl $Wsp]*([cl ^$Wsp]+)[cl $Wsp]*\\(([cl ^)]*)\\)[cl $Wsp]*("([cl ^")]*)")? ;# "
87    set attlist_fixed_exp [cl $Wsp]*([cl ^$Wsp]+)[cl $Wsp]*([cl ^$Wsp]+)[cl $Wsp]*(#FIXED)[cl $Wsp]*([cl ^$Wsp]+)
88
89    set param_entity_exp [cl $Wsp]*([cl ^$Wsp]+)[cl $Wsp]*([cl ^"$Wsp]*)[cl $Wsp]*"([cl ^"]*)"
90
91    set notation_exp [cl $Wsp]*([cl ^$Wsp]+)[cl $Wsp]*(.*)
92
93}
94
95### Utility procedures
96
97# sgml::noop --
98#
99#       A do-nothing proc
100#
101# Arguments:
102#       args        arguments
103#
104# Results:
105#       Nothing.
106
107proc sgml::noop args {
108    return 0
109}
110
111# sgml::identity --
112#
113#       Identity function.
114#
115# Arguments:
116#       a           arbitrary argument
117#
118# Results:
119#       $a
120
121proc sgml::identity a {
122    return $a
123}
124
125# sgml::Error --
126#
127#       Throw an error
128#
129# Arguments:
130#       args        arguments
131#
132# Results:
133#       Error return condition.
134
135proc sgml::Error args {
136    uplevel return -code error [list $args]
137}
138
139### Following procedures are based on html_library
140
141# sgml::zapWhite --
142#
143#       Convert multiple white space into a single space.
144#
145# Arguments:
146#       data        plain text
147#
148# Results:
149#       As above
150
151proc sgml::zapWhite data {
152    regsub -all "\[ \t\r\n\]+" $data { } data
153    return $data
154}
155
156proc sgml::Boolean value {
157    regsub {1|true|yes|on} $value 1 value
158    regsub {0|false|no|off} $value 0 value
159    return $value
160}
161
162# vim:ft=tcl:ts=8:sw=4:sts=4:et
163