Absolute File Name: | /home/qt/qt5_coco/qt5/qtbase/src/corelib/tools/qstringmatcher.cpp |
Source code | Switch to Preprocessed file |
Line | Source | Count | ||||||
---|---|---|---|---|---|---|---|---|
1 | /**************************************************************************** | - | ||||||
2 | ** | - | ||||||
3 | ** Copyright (C) 2016 The Qt Company Ltd. | - | ||||||
4 | ** Contact: https://www.qt.io/licensing/ | - | ||||||
5 | ** | - | ||||||
6 | ** This file is part of the QtCore module of the Qt Toolkit. | - | ||||||
7 | ** | - | ||||||
8 | ** $QT_BEGIN_LICENSE:LGPL$ | - | ||||||
9 | ** Commercial License Usage | - | ||||||
10 | ** Licensees holding valid commercial Qt licenses may use this file in | - | ||||||
11 | ** accordance with the commercial license agreement provided with the | - | ||||||
12 | ** Software or, alternatively, in accordance with the terms contained in | - | ||||||
13 | ** a written agreement between you and The Qt Company. For licensing terms | - | ||||||
14 | ** and conditions see https://www.qt.io/terms-conditions. For further | - | ||||||
15 | ** information use the contact form at https://www.qt.io/contact-us. | - | ||||||
16 | ** | - | ||||||
17 | ** GNU Lesser General Public License Usage | - | ||||||
18 | ** Alternatively, this file may be used under the terms of the GNU Lesser | - | ||||||
19 | ** General Public License version 3 as published by the Free Software | - | ||||||
20 | ** Foundation and appearing in the file LICENSE.LGPL3 included in the | - | ||||||
21 | ** packaging of this file. Please review the following information to | - | ||||||
22 | ** ensure the GNU Lesser General Public License version 3 requirements | - | ||||||
23 | ** will be met: https://www.gnu.org/licenses/lgpl-3.0.html. | - | ||||||
24 | ** | - | ||||||
25 | ** GNU General Public License Usage | - | ||||||
26 | ** Alternatively, this file may be used under the terms of the GNU | - | ||||||
27 | ** General Public License version 2.0 or (at your option) the GNU General | - | ||||||
28 | ** Public license version 3 or any later version approved by the KDE Free | - | ||||||
29 | ** Qt Foundation. The licenses are as published by the Free Software | - | ||||||
30 | ** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3 | - | ||||||
31 | ** included in the packaging of this file. Please review the following | - | ||||||
32 | ** information to ensure the GNU General Public License requirements will | - | ||||||
33 | ** be met: https://www.gnu.org/licenses/gpl-2.0.html and | - | ||||||
34 | ** https://www.gnu.org/licenses/gpl-3.0.html. | - | ||||||
35 | ** | - | ||||||
36 | ** $QT_END_LICENSE$ | - | ||||||
37 | ** | - | ||||||
38 | ****************************************************************************/ | - | ||||||
39 | - | |||||||
40 | #include "qstringmatcher.h" | - | ||||||
41 | - | |||||||
42 | QT_BEGIN_NAMESPACE | - | ||||||
43 | - | |||||||
44 | static void bm_init_skiptable(const ushort *uc, int len, uchar *skiptable, Qt::CaseSensitivity cs) | - | ||||||
45 | { | - | ||||||
46 | int l = qMin(len, 255); | - | ||||||
47 | memset(skiptable, l, 256*sizeof(uchar)); | - | ||||||
48 | uc += len - l; | - | ||||||
49 | if (cs == Qt::CaseSensitive) { | - | ||||||
50 | while (l--) { | - | ||||||
51 | skiptable[*uc & 0xff] = l; | - | ||||||
52 | uc++; | - | ||||||
53 | } | - | ||||||
54 | } else { | - | ||||||
55 | const ushort *start = uc; | - | ||||||
56 | while (l--) { | - | ||||||
57 | skiptable[foldCase(uc, start) & 0xff] = l; | - | ||||||
58 | uc++; | - | ||||||
59 | } | - | ||||||
60 | } | - | ||||||
61 | } | - | ||||||
62 | - | |||||||
63 | static inline int bm_find(const ushort *uc, uint l, int index, const ushort *puc, uint pl, | - | ||||||
64 | const uchar *skiptable, Qt::CaseSensitivity cs) | - | ||||||
65 | { | - | ||||||
66 | if (pl == 0) | - | ||||||
67 | return index > (int)l ? -1 : index; | - | ||||||
68 | const uint pl_minus_one = pl - 1; | - | ||||||
69 | - | |||||||
70 | const ushort *current = uc + index + pl_minus_one; | - | ||||||
71 | const ushort *end = uc + l; | - | ||||||
72 | if (cs == Qt::CaseSensitive) { | - | ||||||
73 | while (current < end) { | - | ||||||
74 | uint skip = skiptable[*current & 0xff]; | - | ||||||
75 | if (!skip) { | - | ||||||
76 | // possible match | - | ||||||
77 | while (skip < pl) { | - | ||||||
78 | if (*(current - skip) != puc[pl_minus_one-skip]) | - | ||||||
79 | break; | - | ||||||
80 | skip++; | - | ||||||
81 | } | - | ||||||
82 | if (skip > pl_minus_one) // we have a match | - | ||||||
83 | return (current - uc) - pl_minus_one; | - | ||||||
84 | - | |||||||
85 | // in case we don't have a match we are a bit inefficient as we only skip by one | - | ||||||
86 | // when we have the non matching char in the string. | - | ||||||
87 | if (skiptable[*(current - skip) & 0xff] == pl) | - | ||||||
88 | skip = pl - skip; | - | ||||||
89 | else | - | ||||||
90 | skip = 1; | - | ||||||
91 | } | - | ||||||
92 | if (current > end - skip) | - | ||||||
93 | break; | - | ||||||
94 | current += skip; | - | ||||||
95 | } | - | ||||||
96 | } else { | - | ||||||
97 | while (current < end) { | - | ||||||
98 | uint skip = skiptable[foldCase(current, uc) & 0xff]; | - | ||||||
99 | if (!skip) { | - | ||||||
100 | // possible match | - | ||||||
101 | while (skip < pl) { | - | ||||||
102 | if (foldCase(current - skip, uc) != foldCase(puc + pl_minus_one - skip, puc)) | - | ||||||
103 | break; | - | ||||||
104 | skip++; | - | ||||||
105 | } | - | ||||||
106 | if (skip > pl_minus_one) // we have a match | - | ||||||
107 | return (current - uc) - pl_minus_one; | - | ||||||
108 | // in case we don't have a match we are a bit inefficient as we only skip by one | - | ||||||
109 | // when we have the non matching char in the string. | - | ||||||
110 | if (skiptable[foldCase(current - skip, uc) & 0xff] == pl) | - | ||||||
111 | skip = pl - skip; | - | ||||||
112 | else | - | ||||||
113 | skip = 1; | - | ||||||
114 | } | - | ||||||
115 | if (current > end - skip) | - | ||||||
116 | break; | - | ||||||
117 | current += skip; | - | ||||||
118 | } | - | ||||||
119 | } | - | ||||||
120 | return -1; // not found | - | ||||||
121 | } | - | ||||||
122 | - | |||||||
123 | /*! | - | ||||||
124 | \class QStringMatcher | - | ||||||
125 | \inmodule QtCore | - | ||||||
126 | \brief The QStringMatcher class holds a sequence of characters that | - | ||||||
127 | can be quickly matched in a Unicode string. | - | ||||||
128 | - | |||||||
129 | \ingroup tools | - | ||||||
130 | \ingroup string-processing | - | ||||||
131 | - | |||||||
132 | This class is useful when you have a sequence of \l{QChar}s that | - | ||||||
133 | you want to repeatedly match against some strings (perhaps in a | - | ||||||
134 | loop), or when you want to search for the same sequence of | - | ||||||
135 | characters multiple times in the same string. Using a matcher | - | ||||||
136 | object and indexIn() is faster than matching a plain QString with | - | ||||||
137 | QString::indexOf() if repeated matching takes place. This class | - | ||||||
138 | offers no benefit if you are doing one-off string matches. | - | ||||||
139 | - | |||||||
140 | Create the QStringMatcher with the QString you want to search | - | ||||||
141 | for. Then call indexIn() on the QString that you want to search. | - | ||||||
142 | - | |||||||
143 | \sa QString, QByteArrayMatcher, QRegExp | - | ||||||
144 | */ | - | ||||||
145 | - | |||||||
146 | /*! | - | ||||||
147 | Constructs an empty string matcher that won't match anything. | - | ||||||
148 | Call setPattern() to give it a pattern to match. | - | ||||||
149 | */ | - | ||||||
150 | QStringMatcher::QStringMatcher() | - | ||||||
151 | : d_ptr(0), q_cs(Qt::CaseSensitive) | - | ||||||
152 | { | - | ||||||
153 | memset(q_data, 0, sizeof(q_data)); | - | ||||||
154 | } | - | ||||||
155 | - | |||||||
156 | /*! | - | ||||||
157 | Constructs a string matcher that will search for \a pattern, with | - | ||||||
158 | case sensitivity \a cs. | - | ||||||
159 | - | |||||||
160 | Call indexIn() to perform a search. | - | ||||||
161 | */ | - | ||||||
162 | QStringMatcher::QStringMatcher(const QString &pattern, Qt::CaseSensitivity cs) | - | ||||||
163 | : d_ptr(0), q_pattern(pattern), q_cs(cs) | - | ||||||
164 | { | - | ||||||
165 | p.uc = pattern.unicode(); | - | ||||||
166 | p.len = pattern.size(); | - | ||||||
167 | bm_init_skiptable((const ushort *)p.uc, p.len, p.q_skiptable, cs); | - | ||||||
168 | } | - | ||||||
169 | - | |||||||
170 | /*! | - | ||||||
171 | \fn QStringMatcher::QStringMatcher(const QChar *uc, int length, Qt::CaseSensitivity cs) | - | ||||||
172 | \since 4.5 | - | ||||||
173 | - | |||||||
174 | Constructs a string matcher that will search for the pattern referred to | - | ||||||
175 | by \a uc with the given \a length and case sensitivity specified by \a cs. | - | ||||||
176 | */ | - | ||||||
177 | QStringMatcher::QStringMatcher(const QChar *uc, int len, Qt::CaseSensitivity cs) | - | ||||||
178 | : d_ptr(0), q_cs(cs) | - | ||||||
179 | { | - | ||||||
180 | p.uc = uc; | - | ||||||
181 | p.len = len; | - | ||||||
182 | bm_init_skiptable((const ushort *)p.uc, len, p.q_skiptable, cs); | - | ||||||
183 | } | - | ||||||
184 | - | |||||||
185 | /*! | - | ||||||
186 | Copies the \a other string matcher to this string matcher. | - | ||||||
187 | */ | - | ||||||
188 | QStringMatcher::QStringMatcher(const QStringMatcher &other) | - | ||||||
189 | : d_ptr(0) | - | ||||||
190 | { | - | ||||||
191 | operator=(other); | - | ||||||
192 | } | - | ||||||
193 | - | |||||||
194 | /*! | - | ||||||
195 | Destroys the string matcher. | - | ||||||
196 | */ | - | ||||||
197 | QStringMatcher::~QStringMatcher() | - | ||||||
198 | { | - | ||||||
199 | Q_UNUSED(d_ptr); | - | ||||||
200 | } | - | ||||||
201 | - | |||||||
202 | /*! | - | ||||||
203 | Assigns the \a other string matcher to this string matcher. | - | ||||||
204 | */ | - | ||||||
205 | QStringMatcher &QStringMatcher::operator=(const QStringMatcher &other) | - | ||||||
206 | { | - | ||||||
207 | if (this != &other) { | - | ||||||
208 | q_pattern = other.q_pattern; | - | ||||||
209 | q_cs = other.q_cs; | - | ||||||
210 | memcpy(q_data, other.q_data, sizeof(q_data)); | - | ||||||
211 | } | - | ||||||
212 | return *this; | - | ||||||
213 | } | - | ||||||
214 | - | |||||||
215 | /*! | - | ||||||
216 | Sets the string that this string matcher will search for to \a | - | ||||||
217 | pattern. | - | ||||||
218 | - | |||||||
219 | \sa pattern(), setCaseSensitivity(), indexIn() | - | ||||||
220 | */ | - | ||||||
221 | void QStringMatcher::setPattern(const QString &pattern) | - | ||||||
222 | { | - | ||||||
223 | q_pattern = pattern; | - | ||||||
224 | p.uc = pattern.unicode(); | - | ||||||
225 | p.len = pattern.size(); | - | ||||||
226 | bm_init_skiptable((const ushort *)pattern.unicode(), pattern.size(), p.q_skiptable, q_cs); | - | ||||||
227 | } | - | ||||||
228 | - | |||||||
229 | /*! | - | ||||||
230 | \fn QString QStringMatcher::pattern() const | - | ||||||
231 | - | |||||||
232 | Returns the string pattern that this string matcher will search | - | ||||||
233 | for. | - | ||||||
234 | - | |||||||
235 | \sa setPattern() | - | ||||||
236 | */ | - | ||||||
237 | - | |||||||
238 | QString QStringMatcher::pattern() const | - | ||||||
239 | { | - | ||||||
240 | if (!q_pattern.isEmpty()) | - | ||||||
241 | return q_pattern; | - | ||||||
242 | return QString(p.uc, p.len); | - | ||||||
243 | } | - | ||||||
244 | - | |||||||
245 | /*! | - | ||||||
246 | Sets the case sensitivity setting of this string matcher to \a | - | ||||||
247 | cs. | - | ||||||
248 | - | |||||||
249 | \sa caseSensitivity(), setPattern(), indexIn() | - | ||||||
250 | */ | - | ||||||
251 | void QStringMatcher::setCaseSensitivity(Qt::CaseSensitivity cs) | - | ||||||
252 | { | - | ||||||
253 | if (cs == q_cs)
| 2-3 | ||||||
254 | return; executed 3 times by 1 test: return; Executed by:
| 3 | ||||||
255 | bm_init_skiptable((const ushort *)pq_pattern.uc, punicode(), q_pattern.len,size(), p.q_skiptable, cs); | - | ||||||
256 | q_cs = cs; | - | ||||||
257 | } executed 2 times by 1 test: end of block Executed by:
| 2 | ||||||
258 | - | |||||||
259 | /*! | - | ||||||
260 | Searches the string \a str from character position \a from | - | ||||||
261 | (default 0, i.e. from the first character), for the string | - | ||||||
262 | pattern() that was set in the constructor or in the most recent | - | ||||||
263 | call to setPattern(). Returns the position where the pattern() | - | ||||||
264 | matched in \a str, or -1 if no match was found. | - | ||||||
265 | - | |||||||
266 | \sa setPattern(), setCaseSensitivity() | - | ||||||
267 | */ | - | ||||||
268 | int QStringMatcher::indexIn(const QString &str, int from) const | - | ||||||
269 | { | - | ||||||
270 | if (from < 0) | - | ||||||
271 | from = 0; | - | ||||||
272 | return bm_find((const ushort *)str.unicode(), str.size(), from, | - | ||||||
273 | (const ushort *)p.uc, p.len, | - | ||||||
274 | p.q_skiptable, q_cs); | - | ||||||
275 | } | - | ||||||
276 | - | |||||||
277 | /*! | - | ||||||
278 | \since 4.5 | - | ||||||
279 | - | |||||||
280 | Searches the string starting at \a str (of length \a length) from | - | ||||||
281 | character position \a from (default 0, i.e. from the first | - | ||||||
282 | character), for the string pattern() that was set in the | - | ||||||
283 | constructor or in the most recent call to setPattern(). Returns | - | ||||||
284 | the position where the pattern() matched in \a str, or -1 if no | - | ||||||
285 | match was found. | - | ||||||
286 | - | |||||||
287 | \sa setPattern(), setCaseSensitivity() | - | ||||||
288 | */ | - | ||||||
289 | int QStringMatcher::indexIn(const QChar *str, int length, int from) const | - | ||||||
290 | { | - | ||||||
291 | if (from < 0) | - | ||||||
292 | from = 0; | - | ||||||
293 | return bm_find((const ushort *)str, length, from, | - | ||||||
294 | (const ushort *)p.uc, p.len, | - | ||||||
295 | p.q_skiptable, q_cs); | - | ||||||
296 | } | - | ||||||
297 | - | |||||||
298 | /*! | - | ||||||
299 | \fn Qt::CaseSensitivity QStringMatcher::caseSensitivity() const | - | ||||||
300 | - | |||||||
301 | Returns the case sensitivity setting for this string matcher. | - | ||||||
302 | - | |||||||
303 | \sa setCaseSensitivity() | - | ||||||
304 | */ | - | ||||||
305 | - | |||||||
306 | /*! | - | ||||||
307 | \internal | - | ||||||
308 | */ | - | ||||||
309 | - | |||||||
310 | int qFindStringBoyerMoore( | - | ||||||
311 | const QChar *haystack, int haystackLen, int haystackOffset, | - | ||||||
312 | const QChar *needle, int needleLen, Qt::CaseSensitivity cs) | - | ||||||
313 | { | - | ||||||
314 | uchar skiptable[256]; | - | ||||||
315 | bm_init_skiptable((const ushort *)needle, needleLen, skiptable, cs); | - | ||||||
316 | if (haystackOffset < 0) | - | ||||||
317 | haystackOffset = 0; | - | ||||||
318 | return bm_find((const ushort *)haystack, haystackLen, haystackOffset, | - | ||||||
319 | (const ushort *)needle, needleLen, skiptable, cs); | - | ||||||
320 | } | - | ||||||
321 | - | |||||||
322 | QT_END_NAMESPACE | - | ||||||
Source code | Switch to Preprocessed file |