golden hour

/opt/alt/libicu/usr/include/unicode

File/Folder	Size	Actions
alphaindex.h	26.42 KB
appendable.h	8.43 KB
basictz.h	8.84 KB
brkiter.h	27.53 KB
bytestream.h	9.54 KB
bytestrie.h	19.26 KB
bytestriebuilder.h	7.02 KB
calendar.h	105.06 KB
caniter.h	7.37 KB
casemap.h	25.26 KB
char16ptr.h	7.16 KB
chariter.h	24 KB
choicfmt.h	23.85 KB
coleitr.h	13.7 KB
coll.h	55.59 KB
compactdecimalformat.h	6.81 KB
curramt.h	3.69 KB
currpinf.h	7.24 KB
currunit.h	3.52 KB
datefmt.h	40.37 KB
dbbi.h	1.11 KB
dcfmtsym.h	20.1 KB
decimfmt.h	86.4 KB
docmain.h	6.72 KB
dtfmtsym.h	37.64 KB
dtintrv.h	3.76 KB
dtitvfmt.h	42.87 KB
dtitvinf.h	18.46 KB
dtptngen.h	25.03 KB
dtrule.h	8.62 KB
edits.h	20.67 KB
enumset.h	2.08 KB
errorcode.h	4.78 KB
fieldpos.h	8.63 KB
filteredbrk.h	5.24 KB
fmtable.h	24.36 KB
format.h	12.44 KB
fpositer.h	2.98 KB
gender.h	3.27 KB
gregocal.h	31.57 KB
icudataver.h	1.03 KB
icuplug.h	11.88 KB
idna.h	12.63 KB
listformatter.h	6.18 KB
localpointer.h	16.88 KB
locdspnm.h	7.05 KB
locid.h	44.92 KB
measfmt.h	12.01 KB
measunit.h	38.5 KB
measure.h	4.26 KB
messagepattern.h	33.65 KB
msgfmt.h	43.36 KB
normalizer2.h	33.97 KB
normlzr.h	30.74 KB
nounit.h	2.63 KB
numberformatter.h	87.07 KB
numberrangeformatter.h	28.74 KB
numfmt.h	49.14 KB
numsys.h	6.73 KB
parseerr.h	3.08 KB
parsepos.h	5.45 KB
platform.h	27.1 KB
plurfmt.h	25.18 KB
plurrule.h	17.42 KB
ptypes.h	3.49 KB
putil.h	6.33 KB
rbbi.h	26.41 KB
rbnf.h	49.79 KB
rbtz.h	15.47 KB
regex.h	84.91 KB
region.h	9.12 KB
reldatefmt.h	14.46 KB
rep.h	9.5 KB
resbund.h	18.01 KB
schriter.h	6.26 KB
scientificnumberformatter.h	6.32 KB
search.h	22.21 KB
selfmt.h	14.24 KB
simpleformatter.h	11.43 KB
simpletz.h	45.3 KB
smpdtfmt.h	70.74 KB
sortkey.h	11.12 KB
std_string.h	1015 B
strenum.h	10.04 KB
stringoptions.h	5.79 KB
stringpiece.h	6.46 KB
stringtriebuilder.h	15.27 KB
stsearch.h	21.29 KB
symtable.h	4.21 KB
tblcoll.h	36.4 KB
timezone.h	40.88 KB
tmunit.h	3.29 KB
tmutamt.h	4.8 KB
tmutfmt.h	7.79 KB
translit.h	65.76 KB
tzfmt.h	42.82 KB
tznames.h	16.79 KB
tzrule.h	35.32 KB
tztrans.h	6.07 KB
ubidi.h	89.56 KB
ubiditransform.h	12.65 KB
ubrk.h	23.97 KB
ucal.h	55.2 KB
ucasemap.h	15.18 KB
ucat.h	5.36 KB
uchar.h	139.96 KB
ucharstrie.h	21.06 KB
ucharstriebuilder.h	7.14 KB
uchriter.h	13.14 KB
uclean.h	11.21 KB
ucnv.h	83.09 KB
ucnv_cb.h	6.59 KB
ucnv_err.h	20.99 KB
ucnvsel.h	6.14 KB
ucol.h	61.39 KB
ucoleitr.h	9.46 KB
uconfig.h	11.67 KB
ucpmap.h	5.58 KB
ucptrie.h	22.29 KB
ucsdet.h	14.67 KB
ucurr.h	15.57 KB
udat.h	60.13 KB
udata.h	15.53 KB
udateintervalformat.h	6.79 KB
udatpg.h	26.04 KB
udisplaycontext.h	5.89 KB
uenum.h	7.78 KB
ufieldpositer.h	4.36 KB
uformattable.h	10.94 KB
ugender.h	2 KB
uidna.h	33.37 KB
uiter.h	22.77 KB
uldnames.h	10.45 KB
ulistformatter.h	5.03 KB
uloc.h	50.75 KB
ulocdata.h	11.26 KB
umachine.h	13.19 KB
umisc.h	1.33 KB
umsg.h	24.23 KB
umutablecptrie.h	8.28 KB
unifilt.h	3.63 KB
unifunct.h	3.98 KB
unimatch.h	6.04 KB
unirepl.h	3.32 KB
uniset.h	64.25 KB
unistr.h	174.4 KB
unorm.h	20.45 KB
unorm2.h	24.66 KB
unum.h	53.38 KB
unumberformatter.h	23.76 KB
unumsys.h	7.14 KB
uobject.h	10.7 KB
upluralrules.h	6.72 KB
uregex.h	72.05 KB
uregion.h	9.84 KB
ureldatefmt.h	12.22 KB
urename.h	127.73 KB
urep.h	5.38 KB
ures.h	36.53 KB
uscript.h	26.52 KB
usearch.h	38.12 KB
uset.h	40 KB
usetiter.h	9.49 KB
ushape.h	18 KB
uspoof.h	66.03 KB
usprep.h	8.14 KB
ustdio.h	38.54 KB
ustream.h	1.8 KB
ustring.h	72.47 KB
ustringtrie.h	3.15 KB
utext.h	58.11 KB
utf.h	7.86 KB
utf16.h	22.33 KB
utf32.h	763 B
utf8.h	30.01 KB
utf_old.h	43.78 KB
utmscale.h	13.78 KB
utrace.h	13.89 KB
utrans.h	25.54 KB
utypes.h	30.48 KB
uvernum.h	6.06 KB
uversion.h	6.7 KB
vtzone.h	20.17 KB

Edit: 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"

/**
 * \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="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm">
 * "ICU Collation Design Document"</a> for more information.
 * 
 * There are 2 match options for selection: 
 * Let S' be the sub-string of a text string S between the offsets start and
 * end [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
 * 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.
 * 
 * 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
 * 
 * <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>
 * 
 * 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.
 * 
 * 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.
 * 
 * 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.
 * 
 * Restriction: 
 * 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.
 * 
 * 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(), 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>
 * 
 * Note, <tt>StringSearch</tt> is not to be subclassed.
 * 
 * @see SearchIterator
 * @see RuleBasedCollator
 * @since ICU 2.0
 */

class U_I18N_API StringSearch U_FINAL : public SearchIterator
{
public:

// public constructors and destructors --------------------------------

/**
 * Creating a <tt>StringSearch</tt> instance using the argument locale 
 * language rule set. A collator will be created in the process, which 
 * will be owned by this instance and will be deleted during 
 * destruction
 * @param pattern The text for which this object will search.
 * @param text The text in which to search for the pattern.
 * @param locale A locale which defines the language-sensitive 
 * comparison rules used to determine whether text in the 
 * pattern and target matches. 
 * @param breakiter A <tt>BreakIterator</tt> object used to constrain 
 * the matches that are found. Matches whose start and end 
 * indices in the target text are not boundaries as 
 * determined by the <tt>BreakIterator</tt> are 
 * ignored. If this behavior is not desired, 
 * <tt>NULL</tt> can be passed in instead.
 * @param status for errors if any. If pattern or text is NULL, or if
 * either the length of pattern or text is 0 then an 
 * U_ILLEGAL_ARGUMENT_ERROR is returned.
 * @stable ICU 2.0
 */
 StringSearch(const UnicodeString &pattern, const UnicodeString &text,
 const Locale &locale, 
 BreakIterator *breakiter,
 UErrorCode &status);

/**
 * Creating a <tt>StringSearch</tt> instance using the argument collator 
 * language rule set. Note, user retains the ownership of this collator, 
 * it does not get destroyed during this instance's destruction.
 * @param pattern The text for which this object will search.
 * @param text The text in which to search for the pattern.
 * @param coll A <tt>RuleBasedCollator</tt> object which defines 
 * the language-sensitive comparison rules used to 
 * determine whether text in the pattern and target 
 * matches. User is responsible for the clearing of this
 * object.
 * @param breakiter A <tt>BreakIterator</tt> object used to constrain 
 * the matches that are found. Matches whose start and end 
 * indices in the target text are not boundaries as 
 * determined by the <tt>BreakIterator</tt> are 
 * ignored. If this behavior is not desired, 
 * <tt>NULL</tt> can be passed in instead.
 * @param status for errors if any. If either the length of pattern or 
 * text is 0 then an U_ILLEGAL_ARGUMENT_ERROR is returned.
 * @stable ICU 2.0
 */
 StringSearch(const UnicodeString &pattern, 
 const UnicodeString &text,
 RuleBasedCollator *coll, 
 BreakIterator *breakiter,
 UErrorCode &status);

/**
 * Creating a <tt>StringSearch</tt> instance using the argument locale 
 * language rule set. A collator will be created in the process, which 
 * will be owned by this instance and will be deleted during 
 * destruction
 * 
 * Note: No parsing of the text within the <tt>CharacterIterator</tt> 
 * will be done during searching for this version. The block of text 
 * in <tt>CharacterIterator</tt> will be used as it is.
 * @param pattern The text for which this object will search.
 * @param text The text iterator in which to search for the pattern.
 * @param locale A locale which defines the language-sensitive 
 * comparison rules used to determine whether text in the 
 * pattern and target matches. User is responsible for 
 * the clearing of this object.
 * @param breakiter A <tt>BreakIterator</tt> object used to constrain 
 * the matches that are found. Matches whose start and end 
 * indices in the target text are not boundaries as 
 * determined by the <tt>BreakIterator</tt> are 
 * ignored. If this behavior is not desired, 
 * <tt>NULL</tt> can be passed in instead.
 * @param status for errors if any. If either the length of pattern or 
 * text is 0 then an U_ILLEGAL_ARGUMENT_ERROR is returned.
 * @stable ICU 2.0
 */
 StringSearch(const UnicodeString &pattern, CharacterIterator &text,
 const Locale &locale, 
 BreakIterator *breakiter,
 UErrorCode &status);

/**
 * Creating a <tt>StringSearch</tt> instance using the argument collator 
 * language rule set. Note, user retains the ownership of this collator, 
 * it does not get destroyed during this instance's destruction.
 * 
 * Note: No parsing of the text within the <tt>CharacterIterator</tt> 
 * will be done during searching for this version. The block of text 
 * in <tt>CharacterIterator</tt> will be used as it is.
 * @param pattern The text for which this object will search.
 * @param text The text in which to search for the pattern.
 * @param coll A <tt>RuleBasedCollator</tt> object which defines 
 * the language-sensitive comparison rules used to 
 * determine whether text in the pattern and target 
 * matches. User is responsible for the clearing of this
 * object.
 * @param breakiter A <tt>BreakIterator</tt> object used to constrain 
 * the matches that are found. Matches whose start and end 
 * indices in the target text are not boundaries as 
 * determined by the <tt>BreakIterator</tt> are 
 * ignored. If this behavior is not desired, 
 * <tt>NULL</tt> can be passed in instead.
 * @param status for errors if any. If either the length of pattern or 
 * text is 0 then an U_ILLEGAL_ARGUMENT_ERROR is returned.
 * @stable ICU 2.0
 */
 StringSearch(const UnicodeString &pattern, CharacterIterator &text,
 RuleBasedCollator *coll, 
 BreakIterator *breakiter,
 UErrorCode &status);

/**
     * Copy constructor that creates a StringSearch instance with the same 
     * behavior, and iterating over the same text.
     * @param that StringSearch instance to be copied.
     * @stable ICU 2.0
     */
    StringSearch(const StringSearch &that);

/**
    * Destructor. Cleans up the search iterator data struct.
    * If a collator is created in the constructor, it will be destroyed here.
    * @stable ICU 2.0
    */
    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 ---------------------------------------------

/**
     * Assignment operator. Sets this iterator to have the same behavior,
     * and iterate over the same text, as the one passed in.
     * @param that instance to be copied.
     * @stable ICU 2.0
     */
    StringSearch & operator=(const StringSearch &that);

/**
     * Equality operator. 
     * @param that instance to be compared.
     * @return TRUE if both instances have the same attributes, 
     *         breakiterators, collators and iterate over the same text 
     *         while looking for the same pattern.
     * @stable ICU 2.0
     */
    virtual UBool operator==(const SearchIterator &that) const;

// public get and set methods ----------------------------------------

/**
 * Sets the index to point to the given position, and clears any state 
 * that's affected.
 * 
 * This method takes the argument index and sets the position in the text 
 * 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, 
 * an U_INDEX_OUTOFBOUNDS_ERROR will be returned
 * @param status for errors if it occurs
 * @stable ICU 2.0
 */
 virtual void setOffset(int32_t position, UErrorCode &status);

/**
     * Return the current index in the text being searched.
     * If the iteration has gone past the end of the text
     * (or past the beginning for a backwards search), USEARCH_DONE
     * is returned.
     * @return current index in the text being searched.
     * @stable ICU 2.0
     */
    virtual int32_t getOffset(void) const;

/**
 * Set the target text to be searched.
 * Text iteration will hence begin at the start of the text string. 
 * This method is 
 * useful if you want to re-use an iterator to search for the same 
 * pattern within a different body of text.
 * @param text text string to be searched
 * @param status for errors if any. If the text length is 0 then an 
 * U_ILLEGAL_ARGUMENT_ERROR is returned.
 * @stable ICU 2.0
 */
 virtual void setText(const UnicodeString &text, UErrorCode &status);
 
 /**
 * Set the target text to be searched.
 * Text iteration will hence begin at the start of the text string. 
 * This method is 
 * useful if you want to re-use an iterator to search for the same 
 * pattern within a different body of text.
 * Note: No parsing of the text within the <tt>CharacterIterator</tt> 
 * will be done during searching for this version. The block of text 
 * in <tt>CharacterIterator</tt> will be used as it is.
 * @param text text string to be searched
 * @param status for errors if any. If the text length is 0 then an 
 * U_ILLEGAL_ARGUMENT_ERROR is returned.
 * @stable ICU 2.0
 */
 virtual void setText(CharacterIterator &text, UErrorCode &status);

/**
 * Gets the collator used for the language rules.
 * 
 * Caller may modify but must not 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.
 * @return collator used for string search
 * @stable ICU 2.0
 */
 RuleBasedCollator * getCollator() const;
 
 /**
 * Sets the collator used for the language rules. User retains the 
 * ownership of this collator, thus the responsibility of deletion lies 
 * 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
 */
 void setCollator(RuleBasedCollator *coll, UErrorCode &status);
 
 /**
 * Sets the pattern used for matching.
 * 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.
 * @stable ICU 2.0
 */
 void setPattern(const UnicodeString &pattern, UErrorCode &status);
 
 /**
 * Gets the search pattern.
 * @return pattern used for matching
 * @stable ICU 2.0
 */
 const UnicodeString & getPattern() const;

// public methods ----------------------------------------------------

/** 
     * Reset the iteration.
     * Search will begin at the start of the text string if a forward 
     * iteration is initiated before a backwards iteration. Otherwise if 
     * a backwards iteration is initiated before a forwards iteration, the 
     * search will begin at the end of the text string.
     * @stable ICU 2.0
     */
    virtual void reset();

/**
     * Returns a copy of StringSearch with the same behavior, and 
     * iterating over the same text, as this one. Note that all data will be
     * replicated, except for the user-specified collator and the
     * breakiterator.
     * @return cloned object
     * @stable ICU 2.0
     */
    virtual SearchIterator * safeClone(void) const;
    
    /**
     * ICU "poor man's RTTI", returns a UClassID for the actual class.
     *
     * @stable ICU 2.2
     */
    virtual UClassID getDynamicClassID() const;

/**
     * ICU "poor man's RTTI", returns a UClassID for this class.
     *
     * @stable ICU 2.2
     */
    static UClassID U_EXPORT2 getStaticClassID();

protected:

// protected method -------------------------------------------------

/**
 * Search forward for matching text, starting at a given location.
 * Clients should not call this method directly; instead they should 
 * call {@link SearchIterator#next }.
 * 
 * If a match is found, this method returns the index at which the match
 * 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>.
 * 
 * The <tt>StringSearch</tt> is adjusted so that its current index 
 * (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.
 * @param position The index in the target text at which the search 
 * starts
 * @param status for errors if any occurs
 * @return The index at which the matched text in the target starts, or 
 * USEARCH_DONE if no match was found.
 * @stable ICU 2.0
 */
 virtual int32_t handleNext(int32_t position, UErrorCode &status);

/**
 * Search backward for matching text, starting at a given location.
 * Clients should not call this method directly; instead they should call
 * <tt>SearchIterator.previous()</tt>, which this method overrides.
 * 
 * If a match is found, this method returns the index at which the match
 * 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>.
 * 
 * The <tt>StringSearch</tt> is adjusted so that its current index 
 * (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.
 * @param position The index in the target text at which the search 
 * starts.
 * @param status for errors if any occurs
 * @return The index at which the matched text in the target starts, or 
 * USEARCH_DONE if no match was found.
 * @stable ICU 2.0
 */
 virtual int32_t handlePrev(int32_t position, UErrorCode &status);
 
private :
 StringSearch(); // default constructor not implemented

// private data members ----------------------------------------------

/**
    * Pattern text
    * @stable ICU 2.0
    */
    UnicodeString      m_pattern_;
    /**
    * String search struct data
    * @stable ICU 2.0
    */
    UStringSearch     *m_strsrch_;

};

U_NAMESPACE_END

#endif /* #if !UCONFIG_NO_COLLATION */

#endif