1#
2# $Id: README,v 1.1 1999/09/21 15:45:17 mleisher Exp $
3#
4# Copyright 1997, 1998, 1999 Computing Research Labs,
5# New Mexico State University
6#
7# Permission is hereby granted, free of charge, to any person obtaining a
8# copy of this software and associated documentation files (the "Software"),
9# to deal in the Software without restriction, including without limitation
10# the rights to use, copy, modify, merge, publish, distribute, sublicense,
11# and/or sell copies of the Software, and to permit persons to whom the
12# Software is furnished to do so, subject to the following conditions:
13#
14# The above copyright notice and this permission notice shall be included in
15# all copies or substantial portions of the Software.
16#
17# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
18# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
19# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
20# THE COMPUTING RESEARCH LAB OR NEW MEXICO STATE UNIVERSITY BE LIABLE FOR ANY
21# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT
22# OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR
23# THE USE OR OTHER DEALINGS IN THE SOFTWARE.
24#
25
26 Unicode and Boyer-Moore Searching
27 Version 0.2
28
29UTBM (Unicode Tuned Boyer-Moore) is a simple package that provides tuned
30Boyer-Moore searches on Unicode UCS2 text (handles high and low surrogates).
31
32---------------------------------------------------------------------------
33
34Assumptions:
35
36 o Search pattern and text already normalized in some fasion.
37
38 o Upper, lower, and title case conversions are one-to-one.
39
40 o For conversions between upper, lower, and title case, UCS2 characters
41 always convert to other UCS2 characters, and UTF-16 characters always
42 convert to other UTF-16 characters.
43
44Flags:
45
46 UTBM provides three processing flags:
47
48 o UTBM_CASEFOLD - search in a case-insensitive manner.
49
50 o UTBM_IGNORE_NONSPACING - ignore non-spacing characters in the pattern and
51 the text.
52
53 o UTBM_SPACE_COMPRESS - view as a *single space*, sequential groups of
54 U+2028, U+2029, '\n', '\r', '\t', and any
55 character identified as a space by the Unicode
56 support on the platform.
57
58 This flag also causes all characters identified
59 as control by the Unicode support on the
60 platform to be ignored (except for '\n', '\r',
61 and '\t').
62
63---------------------------------------------------------------------------
64
65Before using UTBM
66-----------------
67Before UTBM is used, some functions need to be created. The "utbmstub.c" file
68contains stubs that need to be rewritten so they work with the Unicode support
69on the platform on which this package is being used.
70
71Using UTBM
72----------
73
74Sample pseudo-code fragment.
75
76 utbm_pattern_t pat;
77 ucs2_t *pattern, *text;
78 unsigned long patternlen, textlen;
79 unsigned long flags, match_start, match_end;
80
81 /*
82 * Allocate the dynamic storage needed for a search pattern.
83 */
84 pat = utbm_create_pattern();
85
86 /*
87 * Set the search flags desired.
88 */
89 flags = UTBM_CASEFOLD|UTBM_IGNORE_NONSPACING;
90
91 /*
92 * Compile the search pattern.
93 */
94 utbm_compile(pattern, patternlen, flags, pat);
95
96 /*
97 * Find the first occurance of the search pattern in the text.
98 */
99 if (utbm_exec(pat, text, textlen, &match_start, &match_end))
100 printf("MATCH: %ld %ld\n", match_start, match_end);
101
102 /*
103 * Free the dynamic storage used for the search pattern.
104 */
105 ure_free_pattern(pat);
106
107---------------------------------------------------------------------------
108
109Mark Leisher <mleisher@crl.nmsu.edu>
1102 May 1997
111
112===========================================================================
113
114CHANGES
115-------
116
117Version: 0.2
118Date : 21 September 1999
119==========================
120 1. Added copyright stuff and put in CVS.
121
122