/*
**********************************************************************
-* Copyright (C) 2001-2003 IBM and others. All rights reserved.
+* Copyright (C) 2001-2014 IBM and others. All rights reserved.
**********************************************************************
* Date Name Description
* 03/22/2000 helena Creation.
#include "unicode/utypes.h"
-#if !UCONFIG_NO_COLLATION
+/**
+ * \file
+ * \brief C++ API: Service for searching text based on RuleBasedCollator.
+ */
+
+#if !UCONFIG_NO_COLLATION && !UCONFIG_NO_BREAK_ITERATION
#include "unicode/tblcoll.h"
#include "unicode/coleitr.h"
U_NAMESPACE_BEGIN
-/**
+/**
+ *
* <tt>StringSearch</tt> is a <tt>SearchIterator</tt> that provides
* language-sensitive text searching based on the comparison rules defined
* in a {@link RuleBasedCollator} object.
- * StringSearch ensures that language eccentricity can be
- * handled, e.g. for the German collator, characters ß and SS will be matched
+ * StringSearch ensures that language eccentricity can be
+ * handled, e.g. for the German collator, characters ß and SS will be matched
* if case is chosen to be ignored.
- * See the <a href="http://oss.software.ibm.com/cvs/icu/~checkout~/icuhtml/design/collation/ICU_collation_design.htm">
+ * See the <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm">
* "ICU Collation Design Document"</a> for more information.
- * <p>
- * The algorithm implemented is a modified form of the Boyer Moore's search.
- * For more information see
- * <a href=http://oss.software.ibm.com/icu/docs/papers/text-search.html>
- * "Efficient Text Searching in Java"</a>, published in <i>Java Report</i>
- * in February, 1999, for further information on the algorithm.
* <p>
* There are 2 match options for selection:<br>
- * Let S' be the sub-string of a text string S between the offsets start and
- * end <start, end>.
+ * Let S' be the sub-string of a text string S between the offsets start and
+ * end [start, end].
* <br>
- * A pattern string P matches a text string S at the offsets <start, end>
+ * A pattern string P matches a text string S at the offsets [start, end]
* if
* <pre>
- * option 1. Some canonical equivalent of P matches some canonical equivalent
+ * option 1. Some canonical equivalent of P matches some canonical equivalent
* of S'
- * option 2. P matches S' and if P starts or ends with a combining mark,
- * there exists no non-ignorable combining mark before or after S?
- * in S respectively.
+ * option 2. P matches S' and if P starts or ends with a combining mark,
+ * there exists no non-ignorable combining mark before or after S?
+ * in S respectively.
* </pre>
- * Option 2. will be the default·
+ * Option 2. will be the default.
* <p>
* This search has APIs similar to that of other text iteration mechanisms
* such as the break iterators in <tt>BreakIterator</tt>. Using these
- * APIs, it is easy to scan through text looking for all occurances of
+ * APIs, it is easy to scan through text looking for all occurrences of
* a given pattern. This search iterator allows changing of direction by
- * calling a <tt>reset</tt> followed by a <tt>next</tt> or <tt>previous</tt>.
- * Though a direction change can occur without calling <tt>reset</tt> first,
+ * calling a <tt>reset</tt> followed by a <tt>next</tt> or <tt>previous</tt>.
+ * Though a direction change can occur without calling <tt>reset</tt> first,
* this operation comes with some speed penalty.
- * Match results in the forward direction will match the result matches in
+ * Match results in the forward direction will match the result matches in
* the backwards direction in the reverse order
* <p>
- * <tt>SearchIterator</tt> provides APIs to specify the starting position
+ * <tt>SearchIterator</tt> provides APIs to specify the starting position
* within the text string to be searched, e.g. <tt>setOffset</tt>,
- * <tt>preceding</tt> and <tt>following</tt>. Since the
- * starting position will be set as it is specified, please take note that
- * there are some danger points which the search may render incorrect
+ * <tt>preceding</tt> and <tt>following</tt>. Since the
+ * starting position will be set as it is specified, please take note that
+ * there are some danger points which the search may render incorrect
* results:
* <ul>
* <li> The midst of a substring that requires normalization.
* <li> If the following match is to be found, the position should not be the
- * second character which requires to be swapped with the preceding
- * character. Vice versa, if the preceding match is to be found,
- * position to search from should not be the first character which
+ * second character which requires to be swapped with the preceding
+ * character. Vice versa, if the preceding match is to be found,
+ * position to search from should not be the first character which
* requires to be swapped with the next character. E.g certain Thai and
* Lao characters require swapping.
- * <li> If a following pattern match is to be found, any position within a
- * contracting sequence except the first will fail. Vice versa if a
- * preceding pattern match is to be found, a invalid starting point
+ * <li> If a following pattern match is to be found, any position within a
+ * contracting sequence except the first will fail. Vice versa if a
+ * preceding pattern match is to be found, a invalid starting point
* would be any character within a contracting sequence except the last.
* </ul>
* <p>
- * A breakiterator can be used if only matches at logical breaks are desired.
- * Using a breakiterator will only give you results that exactly matches the
+ * A <tt>BreakIterator</tt> can be used if only matches at logical breaks are desired.
+ * Using a <tt>BreakIterator</tt> will only give you results that exactly matches the
* boundaries given by the breakiterator. For instance the pattern "e" will
* not be found in the string "\u00e9" if a character break iterator is used.
* <p>
- * Options are provided to handle overlapping matches.
- * E.g. In English, overlapping matches produces the result 0 and 2
- * for the pattern "abab" in the text "ababab", where else mutually
+ * Options are provided to handle overlapping matches.
+ * E.g. In English, overlapping matches produces the result 0 and 2
+ * for the pattern "abab" in the text "ababab", where else mutually
* exclusive matches only produce the result of 0.
* <p>
- * Though collator attributes will be taken into consideration while
- * performing matches, there are no APIs here for setting and getting the
+ * Though collator attributes will be taken into consideration while
+ * performing matches, there are no APIs here for setting and getting the
* attributes. These attributes can be set by getting the collator
* from <tt>getCollator</tt> and using the APIs in <tt>coll.h</tt>.
- * Lastly to update StringSearch to the new collator attributes,
- * reset() has to be called.
+ * Lastly to update <tt>StringSearch</tt> to the new collator attributes,
+ * <tt>reset</tt> has to be called.
* <p>
* Restriction: <br>
* Currently there are no composite characters that consists of a
- * character with combining class > 0 before a character with combining
- * class == 0. However, if such a character exists in the future,
- * StringSearch does not guarantee the results for option 1.
+ * character with combining class > 0 before a character with combining
+ * class == 0. However, if such a character exists in the future,
+ * <tt>StringSearch</tt> does not guarantee the results for option 1.
* <p>
* Consult the <tt>SearchIterator</tt> documentation for information on
* and examples of how to use instances of this class to implement text
* searching.
* <pre><code>
- * UnicodeString target("The quick brown fox jumped over the lazy fox");
+ * UnicodeString target("The quick brown fox jumps over the lazy dog.");
* UnicodeString pattern("fox");
*
- * SearchIterator *iter = new StringSearch(pattern, target);
* UErrorCode error = U_ZERO_ERROR;
- * for (int pos = iter->first(error); pos != USEARCH_DONE;
- * pos = iter->next(error)) {
+ * StringSearch iter(pattern, target, Locale::getUS(), NULL, status);
+ * for (int pos = iter.first(error);
+ * pos != USEARCH_DONE;
+ * pos = iter.next(error))
+ * {
* printf("Found match at %d pos, length is %d\n", pos,
* iter.getMatchLength());
* }
* </code></pre>
* <p>
- * Note, StringSearch is not to be subclassed.
+ * Note, <tt>StringSearch</tt> is not to be subclassed.
* </p>
* @see SearchIterator
* @see RuleBasedCollator
*/
virtual ~StringSearch(void);
+ /**
+ * Clone this object.
+ * Clones can be used concurrently in multiple threads.
+ * If an error occurs, then NULL is returned.
+ * The caller must delete the clone.
+ *
+ * @return a clone of this object
+ *
+ * @see getDynamicClassID
+ * @stable ICU 2.8
+ */
+ StringSearch *clone() const;
+
// operator overloading ---------------------------------------------
/**
* string accordingly without checking if the index is pointing to a
* valid starting point to begin searching.
* @param position within the text to be set. If position is less
- * than or greater than the text range for searching,
+ * than or greater than the text range for searching,
* an U_INDEX_OUTOFBOUNDS_ERROR will be returned
* @param status for errors if it occurs
* @stable ICU 2.0
* Gets the collator used for the language rules.
* <p>
* Caller may modify but <b>must not</b> delete the <tt>RuleBasedCollator</tt>!
- * Modifications to this collator will affect the original collator passed in to
- * the <tt>StringSearch>/tt> constructor or to setCollator, if any.
+ * Modifications to this collator will affect the original collator passed in to
+ * the <tt>StringSearch></tt> constructor or to setCollator, if any.
* @return collator used for string search
* @stable ICU 2.0
*/
/**
* Sets the collator used for the language rules. User retains the
* ownership of this collator, thus the responsibility of deletion lies
- * with the user. This method causes internal data such as Boyer-Moore
- * shift tables to be recalculated, but the iterator's position is
- * unchanged.
+ * with the user. The iterator's position will not be changed by this method.
* @param coll collator
* @param status for errors if any
* @stable ICU 2.0
/**
* Sets the pattern used for matching.
- * Internal data like the Boyer Moore table will be recalculated, but
- * the iterator's position is unchanged.
+ * The iterator's position will not be changed by this method.
* @param pattern search pattern to be found
* @param status for errors if any. If the pattern length is 0 then an
* U_ILLEGAL_ARGUMENT_ERROR is returned.
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
- * @draft ICU 2.2
+ * @stable ICU 2.2
*/
- virtual inline UClassID getDynamicClassID() const;
+ virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
- * @draft ICU 2.2
+ * @stable ICU 2.2
*/
- static inline UClassID getStaticClassID();
+ static UClassID U_EXPORT2 getStaticClassID();
protected:
/**
* Search forward for matching text, starting at a given location.
* Clients should not call this method directly; instead they should
- * call {@link SearchIterator#next}.
+ * call {@link SearchIterator#next }.
* <p>
* If a match is found, this method returns the index at which the match
- * starts and calls {@link SearchIterator#setMatchLength} with the number
+ * starts and calls {@link SearchIterator#setMatchLength } with the number
* of characters in the target text that make up the match. If no match
* is found, the method returns <tt>USEARCH_DONE</tt>.
* <p>
* The <tt>StringSearch</tt> is adjusted so that its current index
- * (as returned by {@link #getOffset()}) is the match position if one was
+ * (as returned by {@link #getOffset }) is the match position if one was
* found.
* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
* the <tt>StringSearch</tt> will be adjusted to the index USEARCH_DONE.
* <tt>SearchIterator.previous()</tt>, which this method overrides.
* <p>
* If a match is found, this method returns the index at which the match
- * starts and calls {@link SearchIterator#setMatchLength} with the number
+ * starts and calls {@link SearchIterator#setMatchLength } with the number
* of characters in the target text that make up the match. If no match
* is found, the method returns <tt>USEARCH_DONE</tt>.
* <p>
* The <tt>StringSearch</tt> is adjusted so that its current index
- * (as returned by {@link #getOffset()}) is the match position if one was
+ * (as returned by {@link #getOffset }) is the match position if one was
* found.
* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
* the <tt>StringSearch</tt> will be adjusted to the index USEARCH_DONE.
// private data members ----------------------------------------------
- /**
- * RuleBasedCollator, contains exactly the same UCollator * in m_strsrch_
- * @stable ICU 2.0
- */
- RuleBasedCollator m_collator_;
/**
* Pattern text
* @stable ICU 2.0
*/
UnicodeString m_pattern_;
/**
- * Corresponding collation rules
- * @stable ICU 2.0
- */
- UnicodeString m_collation_rules_;
- /**
* String search struct data
* @stable ICU 2.0
*/
UStringSearch *m_strsrch_;
- /**
- * The address of this static class variable serves as this class's ID
- * for ICU "poor man's RTTI".
- */
- static const char fgClassID;
};
-inline UClassID
-StringSearch::getStaticClassID()
-{ return (UClassID)&fgClassID; }
-
-inline UClassID
-StringSearch::getDynamicClassID() const
-{ return StringSearch::getStaticClassID(); }
-
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_COLLATION */
projects / apple / icu.git / blobdiff