Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(176)

Side by Side Diff: source/i18n/unicode/stsearch.h

Issue 845603002: Update ICU to 54.1 step 1 (Closed) Base URL: https://chromium.googlesource.com/chromium/deps/icu.git@master
Patch Set: remove unusued directories Created 5 years, 11 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View unified diff | Download patch
« no previous file with comments | « source/i18n/unicode/sortkey.h ('k') | source/i18n/unicode/tblcoll.h » ('j') | no next file with comments »
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
OLDNEW
1 /* 1 /*
2 ********************************************************************** 2 **********************************************************************
3 * Copyright (C) 2001-2008 IBM and others. All rights reserved. 3 * Copyright (C) 2001-2014 IBM and others. All rights reserved.
4 ********************************************************************** 4 **********************************************************************
5 * Date Name Description 5 * Date Name Description
6 * 03/22/2000 helena Creation. 6 * 03/22/2000 helena Creation.
7 ********************************************************************** 7 **********************************************************************
8 */ 8 */
9 9
10 #ifndef STSEARCH_H 10 #ifndef STSEARCH_H
11 #define STSEARCH_H 11 #define STSEARCH_H
12 12
13 #include "unicode/utypes.h" 13 #include "unicode/utypes.h"
14 14
15 /** 15 /**
16 * \file 16 * \file
17 * \brief C++ API: Service for searching text based on RuleBasedCollator. 17 * \brief C++ API: Service for searching text based on RuleBasedCollator.
18 */ 18 */
19 19
20 #if !UCONFIG_NO_COLLATION && !UCONFIG_NO_BREAK_ITERATION 20 #if !UCONFIG_NO_COLLATION && !UCONFIG_NO_BREAK_ITERATION
21 21
22 #include "unicode/tblcoll.h" 22 #include "unicode/tblcoll.h"
23 #include "unicode/coleitr.h" 23 #include "unicode/coleitr.h"
24 #include "unicode/search.h" 24 #include "unicode/search.h"
25 25
26 U_NAMESPACE_BEGIN 26 U_NAMESPACE_BEGIN
27 27
28 /** 28 /**
29 * 29 *
30 * <tt>StringSearch</tt> is a <tt>SearchIterator</tt> that provides 30 * <tt>StringSearch</tt> is a <tt>SearchIterator</tt> that provides
31 * language-sensitive text searching based on the comparison rules defined 31 * language-sensitive text searching based on the comparison rules defined
32 * in a {@link RuleBasedCollator} object. 32 * in a {@link RuleBasedCollator} object.
33 * StringSearch ensures that language eccentricity can be 33 * StringSearch ensures that language eccentricity can be
34 * handled, e.g. for the German collator, characters &szlig; and SS will be matc hed 34 * handled, e.g. for the German collator, characters &szlig; and SS will be matc hed
35 * if case is chosen to be ignored. 35 * if case is chosen to be ignored.
36 * See the <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design /collation/ICU_collation_design.htm"> 36 * See the <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design /collation/ICU_collation_design.htm">
37 * "ICU Collation Design Document"</a> for more information. 37 * "ICU Collation Design Document"</a> for more information.
38 * <p>
39 * The algorithm implemented is a modified form of the Boyer Moore's search.
40 * For more information see
41 * <a href="http://icu-project.org/docs/papers/efficient_text_searching_in_java. html">
42 * "Efficient Text Searching in Java"</a>, published in <i>Java Report</i>
43 * in February, 1999, for further information on the algorithm.
44 * <p> 38 * <p>
45 * There are 2 match options for selection:<br> 39 * There are 2 match options for selection:<br>
46 * Let S' be the sub-string of a text string S between the offsets start and 40 * Let S' be the sub-string of a text string S between the offsets start and
47 * end <start, end>. 41 * end [start, end].
48 * <br> 42 * <br>
49 * A pattern string P matches a text string S at the offsets <start, end> 43 * A pattern string P matches a text string S at the offsets [start, end]
50 * if 44 * if
51 * <pre> 45 * <pre>
52 * option 1. Some canonical equivalent of P matches some canonical equivalent 46 * option 1. Some canonical equivalent of P matches some canonical equivalent
53 * of S' 47 * of S'
54 * option 2. P matches S' and if P starts or ends with a combining mark, 48 * option 2. P matches S' and if P starts or ends with a combining mark,
55 * there exists no non-ignorable combining mark before or after S? 49 * there exists no non-ignorable combining mark before or after S?
56 * in S respectively. 50 * in S respectively.
57 * </pre> 51 * </pre>
58 * Option 2. will be the default. 52 * Option 2. will be the default.
59 * <p> 53 * <p>
60 * This search has APIs similar to that of other text iteration mechanisms 54 * This search has APIs similar to that of other text iteration mechanisms
61 * such as the break iterators in <tt>BreakIterator</tt>. Using these 55 * such as the break iterators in <tt>BreakIterator</tt>. Using these
62 * APIs, it is easy to scan through text looking for all occurances of 56 * APIs, it is easy to scan through text looking for all occurrences of
63 * a given pattern. This search iterator allows changing of direction by 57 * a given pattern. This search iterator allows changing of direction by
64 * calling a <tt>reset</tt> followed by a <tt>next</tt> or <tt>previous</tt>. 58 * calling a <tt>reset</tt> followed by a <tt>next</tt> or <tt>previous</tt>.
65 * Though a direction change can occur without calling <tt>reset</tt> first, 59 * Though a direction change can occur without calling <tt>reset</tt> first,
66 * this operation comes with some speed penalty. 60 * this operation comes with some speed penalty.
67 * Match results in the forward direction will match the result matches in 61 * Match results in the forward direction will match the result matches in
68 * the backwards direction in the reverse order 62 * the backwards direction in the reverse order
69 * <p> 63 * <p>
70 * <tt>SearchIterator</tt> provides APIs to specify the starting position 64 * <tt>SearchIterator</tt> provides APIs to specify the starting position
71 * within the text string to be searched, e.g. <tt>setOffset</tt>, 65 * within the text string to be searched, e.g. <tt>setOffset</tt>,
72 * <tt>preceding</tt> and <tt>following</tt>. Since the 66 * <tt>preceding</tt> and <tt>following</tt>. Since the
73 * starting position will be set as it is specified, please take note that 67 * starting position will be set as it is specified, please take note that
74 * there are some danger points which the search may render incorrect 68 * there are some danger points which the search may render incorrect
75 * results: 69 * results:
76 * <ul> 70 * <ul>
77 * <li> The midst of a substring that requires normalization. 71 * <li> The midst of a substring that requires normalization.
78 * <li> If the following match is to be found, the position should not be the 72 * <li> If the following match is to be found, the position should not be the
79 * second character which requires to be swapped with the preceding 73 * second character which requires to be swapped with the preceding
80 * character. Vice versa, if the preceding match is to be found, 74 * character. Vice versa, if the preceding match is to be found,
81 * position to search from should not be the first character which 75 * position to search from should not be the first character which
82 * requires to be swapped with the next character. E.g certain Thai and 76 * requires to be swapped with the next character. E.g certain Thai and
83 * Lao characters require swapping. 77 * Lao characters require swapping.
84 * <li> If a following pattern match is to be found, any position within a 78 * <li> If a following pattern match is to be found, any position within a
85 * contracting sequence except the first will fail. Vice versa if a 79 * contracting sequence except the first will fail. Vice versa if a
86 * preceding pattern match is to be found, a invalid starting point 80 * preceding pattern match is to be found, a invalid starting point
87 * would be any character within a contracting sequence except the last. 81 * would be any character within a contracting sequence except the last.
88 * </ul> 82 * </ul>
89 * <p> 83 * <p>
90 * A breakiterator can be used if only matches at logical breaks are desired. 84 * A <tt>BreakIterator</tt> can be used if only matches at logical breaks are de sired.
91 * Using a breakiterator will only give you results that exactly matches the 85 * Using a <tt>BreakIterator</tt> will only give you results that exactly matche s the
92 * boundaries given by the breakiterator. For instance the pattern "e" will 86 * boundaries given by the breakiterator. For instance the pattern "e" will
93 * not be found in the string "\u00e9" if a character break iterator is used. 87 * not be found in the string "\u00e9" if a character break iterator is used.
94 * <p> 88 * <p>
95 * Options are provided to handle overlapping matches. 89 * Options are provided to handle overlapping matches.
96 * E.g. In English, overlapping matches produces the result 0 and 2 90 * E.g. In English, overlapping matches produces the result 0 and 2
97 * for the pattern "abab" in the text "ababab", where else mutually 91 * for the pattern "abab" in the text "ababab", where else mutually
98 * exclusive matches only produce the result of 0. 92 * exclusive matches only produce the result of 0.
99 * <p> 93 * <p>
100 * Though collator attributes will be taken into consideration while 94 * Though collator attributes will be taken into consideration while
101 * performing matches, there are no APIs here for setting and getting the 95 * performing matches, there are no APIs here for setting and getting the
102 * attributes. These attributes can be set by getting the collator 96 * attributes. These attributes can be set by getting the collator
103 * from <tt>getCollator</tt> and using the APIs in <tt>coll.h</tt>. 97 * from <tt>getCollator</tt> and using the APIs in <tt>coll.h</tt>.
104 * Lastly to update StringSearch to the new collator attributes, 98 * Lastly to update <tt>StringSearch</tt> to the new collator attributes,
105 * reset() has to be called. 99 * <tt>reset</tt> has to be called.
106 * <p> 100 * <p>
107 * Restriction: <br> 101 * Restriction: <br>
108 * Currently there are no composite characters that consists of a 102 * Currently there are no composite characters that consists of a
109 * character with combining class > 0 before a character with combining 103 * character with combining class > 0 before a character with combining
110 * class == 0. However, if such a character exists in the future, 104 * class == 0. However, if such a character exists in the future,
111 * StringSearch does not guarantee the results for option 1. 105 * <tt>StringSearch</tt> does not guarantee the results for option 1.
112 * <p> 106 * <p>
113 * Consult the <tt>SearchIterator</tt> documentation for information on 107 * Consult the <tt>SearchIterator</tt> documentation for information on
114 * and examples of how to use instances of this class to implement text 108 * and examples of how to use instances of this class to implement text
115 * searching. 109 * searching.
116 * <pre><code> 110 * <pre><code>
117 * UnicodeString target("The quick brown fox jumps over the lazy dog."); 111 * UnicodeString target("The quick brown fox jumps over the lazy dog.");
118 * UnicodeString pattern("fox"); 112 * UnicodeString pattern("fox");
119 * 113 *
120 * UErrorCode error = U_ZERO_ERROR; 114 * UErrorCode error = U_ZERO_ERROR;
121 * StringSearch iter(pattern, target, Locale::getUS(), NULL, status); 115 * StringSearch iter(pattern, target, Locale::getUS(), NULL, status);
122 * for (int pos = iter.first(error); 116 * for (int pos = iter.first(error);
123 * pos != USEARCH_DONE; 117 * pos != USEARCH_DONE;
124 * pos = iter.next(error)) 118 * pos = iter.next(error))
125 * { 119 * {
126 * printf("Found match at %d pos, length is %d\n", pos, 120 * printf("Found match at %d pos, length is %d\n", pos,
127 * iter.getMatchLength()); 121 * iter.getMatchLength());
128 * } 122 * }
129 * </code></pre> 123 * </code></pre>
130 * <p> 124 * <p>
131 * Note, StringSearch is not to be subclassed. 125 * Note, <tt>StringSearch</tt> is not to be subclassed.
132 * </p> 126 * </p>
133 * @see SearchIterator 127 * @see SearchIterator
134 * @see RuleBasedCollator 128 * @see RuleBasedCollator
135 * @since ICU 2.0 129 * @since ICU 2.0
136 */ 130 */
137 131
138 class U_I18N_API StringSearch : public SearchIterator 132 class U_I18N_API StringSearch U_FINAL : public SearchIterator
139 { 133 {
140 public: 134 public:
141 135
142 // public constructors and destructors -------------------------------- 136 // public constructors and destructors --------------------------------
143 137
144 /** 138 /**
145 * Creating a <tt>StringSearch</tt> instance using the argument locale 139 * Creating a <tt>StringSearch</tt> instance using the argument locale
146 * language rule set. A collator will be created in the process, which 140 * language rule set. A collator will be created in the process, which
147 * will be owned by this instance and will be deleted during 141 * will be owned by this instance and will be deleted during
148 * destruction 142 * destruction
(...skipping 216 matching lines...) Expand 10 before | Expand all | Expand 10 after
365 * Modifications to this collator will affect the original collator passed i n to 359 * Modifications to this collator will affect the original collator passed i n to
366 * the <tt>StringSearch></tt> constructor or to setCollator, if any. 360 * the <tt>StringSearch></tt> constructor or to setCollator, if any.
367 * @return collator used for string search 361 * @return collator used for string search
368 * @stable ICU 2.0 362 * @stable ICU 2.0
369 */ 363 */
370 RuleBasedCollator * getCollator() const; 364 RuleBasedCollator * getCollator() const;
371 365
372 /** 366 /**
373 * Sets the collator used for the language rules. User retains the 367 * Sets the collator used for the language rules. User retains the
374 * ownership of this collator, thus the responsibility of deletion lies 368 * ownership of this collator, thus the responsibility of deletion lies
375 * with the user. This method causes internal data such as Boyer-Moore 369 * with the user. The iterator's position will not be changed by this method .
376 * shift tables to be recalculated, but the iterator's position is
377 * unchanged.
378 * @param coll collator 370 * @param coll collator
379 * @param status for errors if any 371 * @param status for errors if any
380 * @stable ICU 2.0 372 * @stable ICU 2.0
381 */ 373 */
382 void setCollator(RuleBasedCollator *coll, UErrorCode &status); 374 void setCollator(RuleBasedCollator *coll, UErrorCode &status);
383 375
384 /** 376 /**
385 * Sets the pattern used for matching. 377 * Sets the pattern used for matching.
386 * Internal data like the Boyer Moore table will be recalculated, but 378 * The iterator's position will not be changed by this method.
387 * the iterator's position is unchanged.
388 * @param pattern search pattern to be found 379 * @param pattern search pattern to be found
389 * @param status for errors if any. If the pattern length is 0 then an 380 * @param status for errors if any. If the pattern length is 0 then an
390 * U_ILLEGAL_ARGUMENT_ERROR is returned. 381 * U_ILLEGAL_ARGUMENT_ERROR is returned.
391 * @stable ICU 2.0 382 * @stable ICU 2.0
392 */ 383 */
393 void setPattern(const UnicodeString &pattern, UErrorCode &status); 384 void setPattern(const UnicodeString &pattern, UErrorCode &status);
394 385
395 /** 386 /**
396 * Gets the search pattern. 387 * Gets the search pattern.
397 * @return pattern used for matching 388 * @return pattern used for matching
(...skipping 88 matching lines...) Expand 10 before | Expand all | Expand 10 after
486 * @stable ICU 2.0 477 * @stable ICU 2.0
487 */ 478 */
488 virtual int32_t handlePrev(int32_t position, UErrorCode &status); 479 virtual int32_t handlePrev(int32_t position, UErrorCode &status);
489 480
490 private : 481 private :
491 StringSearch(); // default constructor not implemented 482 StringSearch(); // default constructor not implemented
492 483
493 // private data members ---------------------------------------------- 484 // private data members ----------------------------------------------
494 485
495 /** 486 /**
496 * RuleBasedCollator, contains exactly the same UCollator * in m_strsrch_
497 * @stable ICU 2.0
498 */
499 RuleBasedCollator m_collator_;
500 /**
501 * Pattern text 487 * Pattern text
502 * @stable ICU 2.0 488 * @stable ICU 2.0
503 */ 489 */
504 UnicodeString m_pattern_; 490 UnicodeString m_pattern_;
505 /** 491 /**
506 * String search struct data 492 * String search struct data
507 * @stable ICU 2.0 493 * @stable ICU 2.0
508 */ 494 */
509 UStringSearch *m_strsrch_; 495 UStringSearch *m_strsrch_;
510 496
511 }; 497 };
512 498
513 U_NAMESPACE_END 499 U_NAMESPACE_END
514 500
515 #endif /* #if !UCONFIG_NO_COLLATION */ 501 #endif /* #if !UCONFIG_NO_COLLATION */
516 502
517 #endif 503 #endif
518 504
OLDNEW
« no previous file with comments | « source/i18n/unicode/sortkey.h ('k') | source/i18n/unicode/tblcoll.h » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698