chromium/third_party/icu/source/i18n/unicode/stsearch.h

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
*   Copyright (C) 2001-2014 IBM and others. All rights reserved.
**********************************************************************
*   Date        Name        Description
*  03/22/2000   helena      Creation.
**********************************************************************
*/

#ifndef STSEARCH_H
#define STSEARCH_H

#include "unicode/utypes.h"

#if U_SHOW_CPLUSPLUS_API

/**
 * \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"
#include "unicode/search.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 &szlig; and SS will be matched
 * if case is chosen to be ignored.
 * See the <a href="https://htmlpreview.github.io/?https://github.com/unicode-org/icu-docs/blob/main/design/collation/ICU_collation_design.htm">
 * "ICU Collation Design Document"</a> for more information.
 * <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].
 * <br>
 * 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
 *           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.
 * </pre>
 * 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 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,
 * this operation comes with some speed penalty.
 * 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
 * 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
 * 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
 *      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
 *      would be any character within a contracting sequence except the last.
 * </ul>
 * <p>
 * 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
 * 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
 * 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 <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,
 * <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 jumps over the lazy dog.");
 * UnicodeString pattern("fox");
 *
 * UErrorCode      error = U_ZERO_ERROR;
 * StringSearch iter(pattern, target, Locale::getUS(), nullptr, 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.getMatchedLength());
 * }
 * </code></pre>
 * <p>
 * Note, <tt>StringSearch</tt> is not to be subclassed.
 * </p>
 * @see SearchIterator
 * @see RuleBasedCollator
 * @since ICU 2.0
 */

class U_I18N_API StringSearch final : public SearchIterator
{};

U_NAMESPACE_END

#endif /* #if !UCONFIG_NO_COLLATION */

#endif /* U_SHOW_CPLUSPLUS_API */

#endif