[3365] | 1 | /**************************************************************************
|
---|
| 2 | *
|
---|
| 3 | * words.cpp -- Functions for parsing out words from the source text
|
---|
| 4 | * Copyright (C) 1999 Rodger McNab
|
---|
| 5 | *
|
---|
| 6 | * This program is free software; you can redistribute it and/or modify
|
---|
| 7 | * it under the terms of the GNU General Public License as published by
|
---|
| 8 | * the Free Software Foundation; either version 2 of the License, or
|
---|
| 9 | * (at your option) any later version.
|
---|
| 10 | *
|
---|
| 11 | * This program is distributed in the hope that it will be useful,
|
---|
| 12 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 13 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 14 | * GNU General Public License for more details.
|
---|
| 15 | *
|
---|
| 16 | * You should have received a copy of the GNU General Public License
|
---|
| 17 | * along with this program; if not, write to the Free Software
|
---|
| 18 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 19 | *
|
---|
| 20 | **************************************************************************/
|
---|
| 21 |
|
---|
| 22 | // need this to avoid bizarre compiler problems under VC++ 6.0
|
---|
| 23 | #if defined (__WIN32__) && !defined (GSDL_USE_IOS_H)
|
---|
| 24 | # include <iostream>
|
---|
| 25 | #endif
|
---|
| 26 |
|
---|
| 27 | #include "words.h"
|
---|
| 28 |
|
---|
| 29 |
|
---|
| 30 | /* Takes the place of the old INAWORD macro. It determines
|
---|
| 31 | whether a given place in a UTF-8 encoded Unicode string
|
---|
| 32 | is part of a word. */
|
---|
| 33 | int inaword (const u_char *here, const u_char *end) {
|
---|
| 34 | unsigned short c;
|
---|
| 35 | if (parse_utf8_char(here, end, &c) > 0) return is_unicode_letdig (c);
|
---|
| 36 | return 0;
|
---|
| 37 | }
|
---|
| 38 |
|
---|
[8692] | 39 | /* It determines whether a given place in a UTF-8 encoded Unicode string is a unicode space. */
|
---|
| 40 | int isaspace (const u_char *here, const u_char *end)
|
---|
| 41 | {
|
---|
| 42 | unsigned short c;
|
---|
| 43 | if (parse_utf8_char(here, end, &c) > 0) return is_unicode_space(c);
|
---|
| 44 | return 0;
|
---|
| 45 | }
|
---|
| 46 |
|
---|
| 47 | /* Return a the UTF-8 encoded Unicode string with begining
|
---|
| 48 | unicode spaces skippend. */
|
---|
| 49 | u_char *skipspace(u_char *here, u_char *end)
|
---|
| 50 | {
|
---|
| 51 | unsigned short c;
|
---|
| 52 | int length;
|
---|
| 53 | while(here != end) {
|
---|
| 54 | length = parse_utf8_char(here, end, &c);
|
---|
| 55 | if (length == 0 || !is_unicode_space(c)) break;
|
---|
| 56 | here += length;
|
---|
| 57 | }
|
---|
| 58 | return here;
|
---|
| 59 | }
|
---|
| 60 |
|
---|
[3365] | 61 | const unsigned char *ParseIndexWord (const unsigned char *textHere,
|
---|
| 62 | const unsigned char *textEnd,
|
---|
| 63 | UCArray &word) {
|
---|
| 64 | word.erase (word.begin(), word.end());
|
---|
| 65 |
|
---|
| 66 | register int charlength = 0;
|
---|
| 67 | register int length = 0;
|
---|
| 68 | register int numeric = 0;
|
---|
| 69 | unsigned short c;
|
---|
| 70 |
|
---|
| 71 | charlength = parse_utf8_char (textHere, textEnd, &c);
|
---|
| 72 |
|
---|
| 73 | while (length+charlength <= MAXSTEMLEN && charlength > 0 &&
|
---|
| 74 | (is_unicode_letter(c) || (is_unicode_digit(c) &&
|
---|
| 75 | ++numeric <= MAXNUMERIC))) {
|
---|
| 76 | while (charlength-- > 0) {
|
---|
[8692] | 77 | word.push_back (*textHere++); ++length;
|
---|
[3365] | 78 | }
|
---|
| 79 | charlength = parse_utf8_char (textHere, textEnd, &c);
|
---|
| 80 | }
|
---|
| 81 |
|
---|
| 82 | return textHere;
|
---|
| 83 | }
|
---|
| 84 |
|
---|
| 85 | const unsigned char *ParseIndexMGWord (const unsigned char *textHere,
|
---|
| 86 | const unsigned char *textEnd,
|
---|
| 87 | unsigned char *mgWord) {
|
---|
| 88 | register int charlength = 0;
|
---|
| 89 | register int length = 0;
|
---|
| 90 | register int numeric = 0;
|
---|
| 91 | unsigned short c;
|
---|
| 92 |
|
---|
| 93 | charlength = parse_utf8_char (textHere, textEnd, &c);
|
---|
| 94 |
|
---|
| 95 | while (length+charlength <= MAXSTEMLEN && charlength > 0 &&
|
---|
| 96 | (is_unicode_letter(c) || (is_unicode_digit(c) &&
|
---|
| 97 | ++numeric <= MAXNUMERIC))) {
|
---|
| 98 | while (charlength-- > 0) {
|
---|
| 99 | mgWord[++length] = *textHere++;
|
---|
| 100 | }
|
---|
| 101 | charlength = parse_utf8_char (textHere, textEnd, &c);
|
---|
| 102 | }
|
---|
| 103 |
|
---|
| 104 | mgWord[0] = length;
|
---|
| 105 |
|
---|
| 106 | return textHere;
|
---|
| 107 | }
|
---|
| 108 |
|
---|
| 109 | const unsigned char *ParseNonindexWord (const unsigned char *textHere,
|
---|
| 110 | const unsigned char *textEnd) {
|
---|
| 111 | register int charlength = 0;
|
---|
| 112 | unsigned short c;
|
---|
| 113 |
|
---|
| 114 | charlength = parse_utf8_char(textHere, textEnd, &c);
|
---|
| 115 |
|
---|
| 116 | while (charlength > 0 && !is_unicode_letdig(c)) {
|
---|
| 117 | textHere += charlength;
|
---|
| 118 | charlength = parse_utf8_char (textHere, textEnd, &c);
|
---|
| 119 | }
|
---|
| 120 |
|
---|
| 121 | return textHere;
|
---|
| 122 | }
|
---|