1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
|
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2003-2014, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
*
* File prscmnts.cpp
*
* Modification History:
*
* Date Name Description
* 08/22/2003 ram Creation.
*******************************************************************************
*/
// Safer use of UnicodeString.
#ifndef UNISTR_FROM_CHAR_EXPLICIT
# define UNISTR_FROM_CHAR_EXPLICIT explicit
#endif
// Less important, but still a good idea.
#ifndef UNISTR_FROM_STRING_EXPLICIT
# define UNISTR_FROM_STRING_EXPLICIT explicit
#endif
#include "unicode/regex.h"
#include "unicode/unistr.h"
#include "unicode/parseerr.h"
#include "prscmnts.h"
#include <stdio.h>
#include <stdlib.h>
U_NAMESPACE_USE
#if UCONFIG_NO_REGULAR_EXPRESSIONS==0 /* donot compile when RegularExpressions not available */
#define MAX_SPLIT_STRINGS 20
const char *patternStrings[UPC_LIMIT]={
"^translate\\s*(.*)",
"^note\\s*(.*)"
};
U_CFUNC int32_t
removeText(UChar *source, int32_t srcLen,
UnicodeString patString,uint32_t options,
UnicodeString replaceText, UErrorCode *status){
if(status == NULL || U_FAILURE(*status)){
return 0;
}
UnicodeString src(source, srcLen);
RegexMatcher myMatcher(patString, src, options, *status);
if(U_FAILURE(*status)){
return 0;
}
UnicodeString dest;
dest = myMatcher.replaceAll(replaceText,*status);
return dest.extract(source, srcLen, *status);
}
U_CFUNC int32_t
trim(UChar *src, int32_t srcLen, UErrorCode *status){
srcLen = removeText(src, srcLen, UnicodeString("^[ \\r\\n]+ "), 0, UnicodeString(), status); // remove leading new lines
srcLen = removeText(src, srcLen, UnicodeString("^\\s+"), 0, UnicodeString(), status); // remove leading spaces
srcLen = removeText(src, srcLen, UnicodeString("\\s+$"), 0, UnicodeString(), status); // remvoe trailing spcaes
return srcLen;
}
U_CFUNC int32_t
removeCmtText(UChar* source, int32_t srcLen, UErrorCode* status){
srcLen = trim(source, srcLen, status);
UnicodeString patString("^\\s*?\\*\\s*?"); // remove pattern like " * " at the begining of the line
srcLen = removeText(source, srcLen, patString, UREGEX_MULTILINE, UnicodeString(), status);
return removeText(source, srcLen, UnicodeString("[ \\r\\n]+"), 0, UnicodeString(" "), status);// remove new lines;
}
U_CFUNC int32_t
getText(const UChar* source, int32_t srcLen,
UChar** dest, int32_t destCapacity,
UnicodeString patternString,
UErrorCode* status){
if(status == NULL || U_FAILURE(*status)){
return 0;
}
UnicodeString stringArray[MAX_SPLIT_STRINGS];
RegexPattern *pattern = RegexPattern::compile(UnicodeString("@"), 0, *status);
UnicodeString src (source,srcLen);
if (U_FAILURE(*status)) {
return 0;
}
pattern->split(src, stringArray, MAX_SPLIT_STRINGS, *status);
RegexMatcher matcher(patternString, UREGEX_DOTALL, *status);
if (U_FAILURE(*status)) {
return 0;
}
for(int32_t i=0; i<MAX_SPLIT_STRINGS; i++){
matcher.reset(stringArray[i]);
if(matcher.lookingAt(*status)){
UnicodeString out = matcher.group(1, *status);
return out.extract(*dest, destCapacity,*status);
}
}
return 0;
}
#define AT_SIGN 0x0040
U_CFUNC int32_t
getDescription( const UChar* source, int32_t srcLen,
UChar** dest, int32_t destCapacity,
UErrorCode* status){
if(status == NULL || U_FAILURE(*status)){
return 0;
}
UnicodeString stringArray[MAX_SPLIT_STRINGS];
RegexPattern *pattern = RegexPattern::compile(UnicodeString("@"), UREGEX_MULTILINE, *status);
UnicodeString src(source, srcLen);
if (U_FAILURE(*status)) {
return 0;
}
pattern->split(src, stringArray,MAX_SPLIT_STRINGS , *status);
if(stringArray[0].indexOf((UChar)AT_SIGN)==-1){
int32_t destLen = stringArray[0].extract(*dest, destCapacity, *status);
return trim(*dest, destLen, status);
}
return 0;
}
U_CFUNC int32_t
getCount(const UChar* source, int32_t srcLen,
UParseCommentsOption option, UErrorCode *status){
if(status == NULL || U_FAILURE(*status)){
return 0;
}
UnicodeString stringArray[MAX_SPLIT_STRINGS];
RegexPattern *pattern = RegexPattern::compile(UnicodeString("@"), UREGEX_MULTILINE, *status);
UnicodeString src (source, srcLen);
if (U_FAILURE(*status)) {
return 0;
}
int32_t retLen = pattern->split(src, stringArray, MAX_SPLIT_STRINGS, *status);
UnicodeString patternString(patternStrings[option]);
RegexMatcher matcher(patternString, UREGEX_DOTALL, *status);
if (U_FAILURE(*status)) {
return 0;
}
int32_t count = 0;
for(int32_t i=0; i<retLen; i++){
matcher.reset(stringArray[i]);
if(matcher.lookingAt(*status)){
count++;
}
}
if(option == UPC_TRANSLATE && count > 1){
fprintf(stderr, "Multiple @translate tags cannot be supported.\n");
exit(U_UNSUPPORTED_ERROR);
}
return count;
}
U_CFUNC int32_t
getAt(const UChar* source, int32_t srcLen,
UChar** dest, int32_t destCapacity,
int32_t index,
UParseCommentsOption option,
UErrorCode* status){
if(status == NULL || U_FAILURE(*status)){
return 0;
}
UnicodeString stringArray[MAX_SPLIT_STRINGS];
RegexPattern *pattern = RegexPattern::compile(UnicodeString("@"), UREGEX_MULTILINE, *status);
UnicodeString src (source, srcLen);
if (U_FAILURE(*status)) {
return 0;
}
int32_t retLen = pattern->split(src, stringArray, MAX_SPLIT_STRINGS, *status);
UnicodeString patternString(patternStrings[option]);
RegexMatcher matcher(patternString, UREGEX_DOTALL, *status);
if (U_FAILURE(*status)) {
return 0;
}
int32_t count = 0;
for(int32_t i=0; i<retLen; i++){
matcher.reset(stringArray[i]);
if(matcher.lookingAt(*status)){
if(count == index){
UnicodeString out = matcher.group(1, *status);
return out.extract(*dest, destCapacity,*status);
}
count++;
}
}
return 0;
}
U_CFUNC int32_t
getTranslate( const UChar* source, int32_t srcLen,
UChar** dest, int32_t destCapacity,
UErrorCode* status){
UnicodeString notePatternString("^translate\\s*?(.*)");
int32_t destLen = getText(source, srcLen, dest, destCapacity, notePatternString, status);
return trim(*dest, destLen, status);
}
U_CFUNC int32_t
getNote(const UChar* source, int32_t srcLen,
UChar** dest, int32_t destCapacity,
UErrorCode* status){
UnicodeString notePatternString("^note\\s*?(.*)");
int32_t destLen = getText(source, srcLen, dest, destCapacity, notePatternString, status);
return trim(*dest, destLen, status);
}
#endif /* UCONFIG_NO_REGULAR_EXPRESSIONS */
|
