You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@couchdb.apache.org by da...@apache.org on 2014/02/06 18:27:50 UTC
[08/46] support static build
http://git-wip-us.apache.org/repos/asf/couchdb-couch-collate/blob/32ffa429/platform/osx/icu/unicode/usearch.h
----------------------------------------------------------------------
diff --git a/platform/osx/icu/unicode/usearch.h b/platform/osx/icu/unicode/usearch.h
new file mode 100644
index 0000000..deaa78f
--- /dev/null
+++ b/platform/osx/icu/unicode/usearch.h
@@ -0,0 +1,766 @@
+/*
+**********************************************************************
+* Copyright (C) 2001-2008 IBM and others. All rights reserved.
+**********************************************************************
+* Date Name Description
+* 06/28/2001 synwee Creation.
+**********************************************************************
+*/
+#ifndef USEARCH_H
+#define USEARCH_H
+
+#include "unicode/utypes.h"
+
+#if !UCONFIG_NO_COLLATION && !UCONFIG_NO_BREAK_ITERATION
+
+#include "unicode/ucol.h"
+#include "unicode/ucoleitr.h"
+#include "unicode/ubrk.h"
+
+/**
+ * \file
+ * \brief C API: StringSearch
+ *
+ * C Apis for an engine that provides language-sensitive text searching based
+ * on the comparison rules defined in a <tt>UCollator</tt> data struct,
+ * see <tt>ucol.h</tt>. This 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://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://icu-project.org/docs/papers/efficient_text_searching_in_java.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>.
+ * <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>ubrk.h</tt>. Using these
+ * APIs, it is easy to scan through text looking for all occurances 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.
+ * Generally, match results in the forward direction will match the result
+ * matches in the backwards direction in the reverse order
+ * <p>
+ * <tt>usearch.h</tt> provides APIs to specify the starting position
+ * within the text string to be searched, e.g. <tt>usearch_setOffset</tt>,
+ * <tt>usearch_preceding</tt> and <tt>usearch_following</tt>. Since the
+ * starting position will be set as it is specified, please take note that
+ * there are some dangerous positions 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 breakiterator can be used if only matches at logical breaks are desired.
+ * Using a breakiterator 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>usearch_getCollator</tt> and using the APIs in <tt>ucol.h</tt>.
+ * Lastly to update String Search to the new collator attributes,
+ * usearch_reset() 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, the
+ * search mechanism does not guarantee the results for option 1.
+ *
+ * <p>
+ * Example of use:<br>
+ * <pre><code>
+ * char *tgtstr = "The quick brown fox jumped over the lazy fox";
+ * char *patstr = "fox";
+ * UChar target[64];
+ * UChar pattern[16];
+ * UErrorCode status = U_ZERO_ERROR;
+ * u_uastrcpy(target, tgtstr);
+ * u_uastrcpy(pattern, patstr);
+ *
+ * UStringSearch *search = usearch_open(pattern, -1, target, -1, "en_US",
+ * NULL, &status);
+ * if (U_SUCCESS(status)) {
+ * for (int pos = usearch_first(search, &status);
+ * pos != USEARCH_DONE;
+ * pos = usearch_next(search, &status))
+ * {
+ * printf("Found match at %d pos, length is %d\n", pos,
+ * usearch_getMatchLength(search));
+ * }
+ * }
+ *
+ * usearch_close(search);
+ * </code></pre>
+ * @stable ICU 2.4
+ */
+
+/**
+* DONE is returned by previous() and next() after all valid matches have
+* been returned, and by first() and last() if there are no matches at all.
+* @stable ICU 2.4
+*/
+#define USEARCH_DONE -1
+
+/**
+* Data structure for searching
+* @stable ICU 2.4
+*/
+struct UStringSearch;
+/**
+* Data structure for searching
+* @stable ICU 2.4
+*/
+typedef struct UStringSearch UStringSearch;
+
+/**
+* @stable ICU 2.4
+*/
+typedef enum {
+ /** Option for overlapping matches */
+ USEARCH_OVERLAP,
+ /**
+ Option for canonical matches. option 1 in header documentation.
+ The default value will be USEARCH_OFF
+ */
+ USEARCH_CANONICAL_MATCH,
+ USEARCH_ATTRIBUTE_COUNT
+} USearchAttribute;
+
+/**
+* @stable ICU 2.4
+*/
+typedef enum {
+ /** default value for any USearchAttribute */
+ USEARCH_DEFAULT = -1,
+ /** value for USEARCH_OVERLAP and USEARCH_CANONICAL_MATCH */
+ USEARCH_OFF,
+ /** value for USEARCH_OVERLAP and USEARCH_CANONICAL_MATCH */
+ USEARCH_ON,
+ USEARCH_ATTRIBUTE_VALUE_COUNT
+} USearchAttributeValue;
+
+/* open and close ------------------------------------------------------ */
+
+/**
+* Creating a search iterator data struct using the argument locale language
+* rule set. A collator will be created in the process, which will be owned by
+* this search and will be deleted in <tt>usearch_close</tt>.
+* @param pattern for matching
+* @param patternlength length of the pattern, -1 for null-termination
+* @param text text string
+* @param textlength length of the text string, -1 for null-termination
+* @param locale name of locale for the rules to be used
+* @param breakiter A BreakIterator that will be used to restrict the points
+* at which matches are detected. If a match is found, but
+* the match's start or end index is not a boundary as
+* determined by the <tt>BreakIterator</tt>, the match will
+* be rejected and another will be searched for.
+* If this parameter is <tt>NULL</tt>, no break detection is
+* attempted.
+* @param status for errors if it occurs. If pattern or text is NULL, or if
+* patternlength or textlength is 0 then an
+* U_ILLEGAL_ARGUMENT_ERROR is returned.
+* @return search iterator data structure, or NULL if there is an error.
+* @stable ICU 2.4
+*/
+U_STABLE UStringSearch * U_EXPORT2 usearch_open(const UChar *pattern,
+ int32_t patternlength,
+ const UChar *text,
+ int32_t textlength,
+ const char *locale,
+ UBreakIterator *breakiter,
+ UErrorCode *status);
+
+/**
+* Creating a search iterator data struct using the argument collator language
+* rule set. Note, user retains the ownership of this collator, thus the
+* responsibility of deletion lies with the user.
+* NOTE: string search cannot be instantiated from a collator that has
+* collate digits as numbers (CODAN) turned on.
+* @param pattern for matching
+* @param patternlength length of the pattern, -1 for null-termination
+* @param text text string
+* @param textlength length of the text string, -1 for null-termination
+* @param collator used for the language rules
+* @param breakiter A BreakIterator that will be used to restrict the points
+* at which matches are detected. If a match is found, but
+* the match's start or end index is not a boundary as
+* determined by the <tt>BreakIterator</tt>, the match will
+* be rejected and another will be searched for.
+* If this parameter is <tt>NULL</tt>, no break detection is
+* attempted.
+* @param status for errors if it occurs. If collator, pattern or text is NULL,
+* or if patternlength or textlength is 0 then an
+* U_ILLEGAL_ARGUMENT_ERROR is returned.
+* @return search iterator data structure, or NULL if there is an error.
+* @stable ICU 2.4
+*/
+U_STABLE UStringSearch * U_EXPORT2 usearch_openFromCollator(
+ const UChar *pattern,
+ int32_t patternlength,
+ const UChar *text,
+ int32_t textlength,
+ const UCollator *collator,
+ UBreakIterator *breakiter,
+ UErrorCode *status);
+
+/**
+* Destroying and cleaning up the search iterator data struct.
+* If a collator is created in <tt>usearch_open</tt>, it will be destroyed here.
+* @param searchiter data struct to clean up
+* @stable ICU 2.4
+*/
+U_STABLE void U_EXPORT2 usearch_close(UStringSearch *searchiter);
+
+/* get and set methods -------------------------------------------------- */
+
+/**
+* Sets the current position in the text string which the next search will
+* start from. Clears previous states.
+* 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.
+* Search positions that may render incorrect results are highlighted in the
+* header comments
+* @param strsrch search iterator data struct
+* @param position position to start next search from. If position is less
+* than or greater than the text range for searching,
+* an U_INDEX_OUTOFBOUNDS_ERROR will be returned
+* @param status error status if any.
+* @stable ICU 2.4
+*/
+U_STABLE void U_EXPORT2 usearch_setOffset(UStringSearch *strsrch,
+ int32_t position,
+ UErrorCode *status);
+
+/**
+* Return the current index in the string text being searched.
+* If the iteration has gone past the end of the text (or past the beginning
+* for a backwards search), <tt>USEARCH_DONE</tt> is returned.
+* @param strsrch search iterator data struct
+* @see #USEARCH_DONE
+* @stable ICU 2.4
+*/
+U_STABLE int32_t U_EXPORT2 usearch_getOffset(const UStringSearch *strsrch);
+
+/**
+* Sets the text searching attributes located in the enum USearchAttribute
+* with values from the enum USearchAttributeValue.
+* <tt>USEARCH_DEFAULT</tt> can be used for all attributes for resetting.
+* @param strsrch search iterator data struct
+* @param attribute text attribute to be set
+* @param value text attribute value
+* @param status for errors if it occurs
+* @see #usearch_getAttribute
+* @stable ICU 2.4
+*/
+U_STABLE void U_EXPORT2 usearch_setAttribute(UStringSearch *strsrch,
+ USearchAttribute attribute,
+ USearchAttributeValue value,
+ UErrorCode *status);
+
+/**
+* Gets the text searching attributes.
+* @param strsrch search iterator data struct
+* @param attribute text attribute to be retrieve
+* @return text attribute value
+* @see #usearch_setAttribute
+* @stable ICU 2.4
+*/
+U_STABLE USearchAttributeValue U_EXPORT2 usearch_getAttribute(
+ const UStringSearch *strsrch,
+ USearchAttribute attribute);
+
+/**
+* Returns the index to the match in the text string that was searched.
+* This call returns a valid result only after a successful call to
+* <tt>usearch_first</tt>, <tt>usearch_next</tt>, <tt>usearch_previous</tt>,
+* or <tt>usearch_last</tt>.
+* Just after construction, or after a searching method returns
+* <tt>USEARCH_DONE</tt>, this method will return <tt>USEARCH_DONE</tt>.
+* <p>
+* Use <tt>usearch_getMatchedLength</tt> to get the matched string length.
+* @param strsrch search iterator data struct
+* @return index to a substring within the text string that is being
+* searched.
+* @see #usearch_first
+* @see #usearch_next
+* @see #usearch_previous
+* @see #usearch_last
+* @see #USEARCH_DONE
+* @stable ICU 2.4
+*/
+U_STABLE int32_t U_EXPORT2 usearch_getMatchedStart(
+ const UStringSearch *strsrch);
+
+/**
+* Returns the length of text in the string which matches the search pattern.
+* This call returns a valid result only after a successful call to
+* <tt>usearch_first</tt>, <tt>usearch_next</tt>, <tt>usearch_previous</tt>,
+* or <tt>usearch_last</tt>.
+* Just after construction, or after a searching method returns
+* <tt>USEARCH_DONE</tt>, this method will return 0.
+* @param strsrch search iterator data struct
+* @return The length of the match in the string text, or 0 if there is no
+* match currently.
+* @see #usearch_first
+* @see #usearch_next
+* @see #usearch_previous
+* @see #usearch_last
+* @see #USEARCH_DONE
+* @stable ICU 2.4
+*/
+U_STABLE int32_t U_EXPORT2 usearch_getMatchedLength(
+ const UStringSearch *strsrch);
+
+/**
+* Returns the text that was matched by the most recent call to
+* <tt>usearch_first</tt>, <tt>usearch_next</tt>, <tt>usearch_previous</tt>,
+* or <tt>usearch_last</tt>.
+* If the iterator is not pointing at a valid match (e.g. just after
+* construction or after <tt>USEARCH_DONE</tt> has been returned, returns
+* an empty string. If result is not large enough to store the matched text,
+* result will be filled with the partial text and an U_BUFFER_OVERFLOW_ERROR
+* will be returned in status. result will be null-terminated whenever
+* possible. If the buffer fits the matched text exactly, a null-termination
+* is not possible, then a U_STRING_NOT_TERMINATED_ERROR set in status.
+* Pre-flighting can be either done with length = 0 or the API
+* <tt>usearch_getMatchLength</tt>.
+* @param strsrch search iterator data struct
+* @param result UChar buffer to store the matched string
+* @param resultCapacity length of the result buffer
+* @param status error returned if result is not large enough
+* @return exact length of the matched text, not counting the null-termination
+* @see #usearch_first
+* @see #usearch_next
+* @see #usearch_previous
+* @see #usearch_last
+* @see #USEARCH_DONE
+* @stable ICU 2.4
+*/
+U_STABLE int32_t U_EXPORT2 usearch_getMatchedText(const UStringSearch *strsrch,
+ UChar *result,
+ int32_t resultCapacity,
+ UErrorCode *status);
+
+#if !UCONFIG_NO_BREAK_ITERATION
+
+/**
+* Set the BreakIterator that will be used to restrict the points at which
+* matches are detected.
+* @param strsrch search iterator data struct
+* @param breakiter A BreakIterator that will be used to restrict the points
+* at which matches are detected. If a match is found, but
+* the match's start or end index is not a boundary as
+* determined by the <tt>BreakIterator</tt>, the match will
+* be rejected and another will be searched for.
+* If this parameter is <tt>NULL</tt>, no break detection is
+* attempted.
+* @param status for errors if it occurs
+* @see #usearch_getBreakIterator
+* @stable ICU 2.4
+*/
+U_STABLE void U_EXPORT2 usearch_setBreakIterator(UStringSearch *strsrch,
+ UBreakIterator *breakiter,
+ UErrorCode *status);
+
+/**
+* Returns the BreakIterator that is used to restrict the points at which
+* matches are detected. This will be the same object that was passed to the
+* constructor or to <tt>usearch_setBreakIterator</tt>. Note that
+* <tt>NULL</tt>
+* is a legal value; it means that break detection should not be attempted.
+* @param strsrch search iterator data struct
+* @return break iterator used
+* @see #usearch_setBreakIterator
+* @stable ICU 2.4
+*/
+U_STABLE const UBreakIterator * U_EXPORT2 usearch_getBreakIterator(
+ const UStringSearch *strsrch);
+
+#endif
+
+/**
+* Set the string 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 strsrch search iterator data struct
+* @param text new string to look for match
+* @param textlength length of the new string, -1 for null-termination
+* @param status for errors if it occurs. If text is NULL, or textlength is 0
+* then an U_ILLEGAL_ARGUMENT_ERROR is returned with no change
+* done to strsrch.
+* @see #usearch_getText
+* @stable ICU 2.4
+*/
+U_STABLE void U_EXPORT2 usearch_setText( UStringSearch *strsrch,
+ const UChar *text,
+ int32_t textlength,
+ UErrorCode *status);
+
+/**
+* Return the string text to be searched.
+* @param strsrch search iterator data struct
+* @param length returned string text length
+* @return string text
+* @see #usearch_setText
+* @stable ICU 2.4
+*/
+U_STABLE const UChar * U_EXPORT2 usearch_getText(const UStringSearch *strsrch,
+ int32_t *length);
+
+/**
+* Gets the collator used for the language rules.
+* <p>
+* Deleting the returned <tt>UCollator</tt> before calling
+* <tt>usearch_close</tt> would cause the string search to fail.
+* <tt>usearch_close</tt> will delete the collator if this search owns it.
+* @param strsrch search iterator data struct
+* @return collator
+* @stable ICU 2.4
+*/
+U_STABLE UCollator * U_EXPORT2 usearch_getCollator(
+ const UStringSearch *strsrch);
+
+/**
+* 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.
+* @param strsrch search iterator data struct
+* @param collator to be used
+* @param status for errors if it occurs
+* @stable ICU 2.4
+*/
+U_STABLE void U_EXPORT2 usearch_setCollator( UStringSearch *strsrch,
+ const UCollator *collator,
+ UErrorCode *status);
+
+/**
+* Sets the pattern used for matching.
+* Internal data like the Boyer Moore table will be recalculated, but the
+* iterator's position is unchanged.
+* @param strsrch search iterator data struct
+* @param pattern string
+* @param patternlength pattern length, -1 for null-terminated string
+* @param status for errors if it occurs. If text is NULL, or textlength is 0
+* then an U_ILLEGAL_ARGUMENT_ERROR is returned with no change
+* done to strsrch.
+* @stable ICU 2.4
+*/
+U_STABLE void U_EXPORT2 usearch_setPattern( UStringSearch *strsrch,
+ const UChar *pattern,
+ int32_t patternlength,
+ UErrorCode *status);
+
+/**
+* Gets the search pattern
+* @param strsrch search iterator data struct
+* @param length return length of the pattern, -1 indicates that the pattern
+* is null-terminated
+* @return pattern string
+* @stable ICU 2.4
+*/
+U_STABLE const UChar * U_EXPORT2 usearch_getPattern(
+ const UStringSearch *strsrch,
+ int32_t *length);
+
+/* methods ------------------------------------------------------------- */
+
+/**
+* Returns the first index at which the string text matches the search
+* pattern.
+* The iterator is adjusted so that its current index (as returned by
+* <tt>usearch_getOffset</tt>) is the match position if one was found.
+* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
+* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt>.
+* @param strsrch search iterator data struct
+* @param status for errors if it occurs
+* @return The character index of the first match, or
+* <tt>USEARCH_DONE</tt> if there are no matches.
+* @see #usearch_getOffset
+* @see #USEARCH_DONE
+* @stable ICU 2.4
+*/
+U_STABLE int32_t U_EXPORT2 usearch_first(UStringSearch *strsrch,
+ UErrorCode *status);
+
+/**
+* Returns the first index greater than <tt>position</tt> at which the string
+* text
+* matches the search pattern. The iterator is adjusted so that its current
+* index (as returned by <tt>usearch_getOffset</tt>) is the match position if
+* one was found.
+* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
+* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt>
+* <p>
+* Search positions that may render incorrect results are highlighted in the
+* header comments. If position is less than or greater than the text range
+* for searching, an U_INDEX_OUTOFBOUNDS_ERROR will be returned
+* @param strsrch search iterator data struct
+* @param position to start the search at
+* @param status for errors if it occurs
+* @return The character index of the first match following <tt>pos</tt>,
+* or <tt>USEARCH_DONE</tt> if there are no matches.
+* @see #usearch_getOffset
+* @see #USEARCH_DONE
+* @stable ICU 2.4
+*/
+U_STABLE int32_t U_EXPORT2 usearch_following(UStringSearch *strsrch,
+ int32_t position,
+ UErrorCode *status);
+
+/**
+* Returns the last index in the target text at which it matches the search
+* pattern. The iterator is adjusted so that its current
+* index (as returned by <tt>usearch_getOffset</tt>) is the match position if
+* one was found.
+* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
+* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt>.
+* @param strsrch search iterator data struct
+* @param status for errors if it occurs
+* @return The index of the first match, or <tt>USEARCH_DONE</tt> if there
+* are no matches.
+* @see #usearch_getOffset
+* @see #USEARCH_DONE
+* @stable ICU 2.4
+*/
+U_STABLE int32_t U_EXPORT2 usearch_last(UStringSearch *strsrch,
+ UErrorCode *status);
+
+/**
+* Returns the first index less than <tt>position</tt> at which the string text
+* matches the search pattern. The iterator is adjusted so that its current
+* index (as returned by <tt>usearch_getOffset</tt>) is the match position if
+* one was found.
+* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
+* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt>
+* <p>
+* Search positions that may render incorrect results are highlighted in the
+* header comments. If position is less than or greater than the text range
+* for searching, an U_INDEX_OUTOFBOUNDS_ERROR will be returned
+* @param strsrch search iterator data struct
+* @param position index position the search is to begin at
+* @param status for errors if it occurs
+* @return The character index of the first match preceding <tt>pos</tt>,
+* or <tt>USEARCH_DONE</tt> if there are no matches.
+* @see #usearch_getOffset
+* @see #USEARCH_DONE
+* @stable ICU 2.4
+*/
+U_STABLE int32_t U_EXPORT2 usearch_preceding(UStringSearch *strsrch,
+ int32_t position,
+ UErrorCode *status);
+
+/**
+* Returns the index of the next point at which the string text matches the
+* search pattern, starting from the current position.
+* The iterator is adjusted so that its current
+* index (as returned by <tt>usearch_getOffset</tt>) is the match position if
+* one was found.
+* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
+* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt>
+* @param strsrch search iterator data struct
+* @param status for errors if it occurs
+* @return The index of the next match after the current position, or
+* <tt>USEARCH_DONE</tt> if there are no more matches.
+* @see #usearch_first
+* @see #usearch_getOffset
+* @see #USEARCH_DONE
+* @stable ICU 2.4
+*/
+U_STABLE int32_t U_EXPORT2 usearch_next(UStringSearch *strsrch,
+ UErrorCode *status);
+
+/**
+* Returns the index of the previous point at which the string text matches
+* the search pattern, starting at the current position.
+* The iterator is adjusted so that its current
+* index (as returned by <tt>usearch_getOffset</tt>) is the match position if
+* one was found.
+* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
+* the iterator will be adjusted to the index <tt>USEARCH_DONE</tt>
+* @param strsrch search iterator data struct
+* @param status for errors if it occurs
+* @return The index of the previous match before the current position,
+* or <tt>USEARCH_DONE</tt> if there are no more matches.
+* @see #usearch_last
+* @see #usearch_getOffset
+* @see #USEARCH_DONE
+* @stable ICU 2.4
+*/
+U_STABLE int32_t U_EXPORT2 usearch_previous(UStringSearch *strsrch,
+ UErrorCode *status);
+
+/**
+* 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.
+* @param strsrch search iterator data struct
+* @see #usearch_first
+* @stable ICU 2.4
+*/
+U_STABLE void U_EXPORT2 usearch_reset(UStringSearch *strsrch);
+
+/**
+ * Simple forward search for the pattern, starting at a specified index,
+ * and using using a default set search options.
+ *
+ * This is an experimental function, and is not an official part of the
+ * ICU API.
+ *
+ * The collator options, such as UCOL_STRENGTH and UCOL_NORMALIZTION, are honored.
+ *
+ * The UStringSearch options USEARCH_CANONICAL_MATCH, USEARCH_OVERLAP and
+ * any Break Iterator are ignored.
+ *
+ * Matches obey the following constraints:
+ *
+ * Characters at the start or end positions of a match that are ignorable
+ * for collation are not included as part of the match, unless they
+ * are part of a combining sequence, as described below.
+ *
+ * A match will not include a partial combining sequence. Combining
+ * character sequences are considered to be inseperable units,
+ * and either match the pattern completely, or are considered to not match
+ * at all. Thus, for example, an A followed a combining accent mark will
+ * not be found when searching for a plain (unaccented) A. (unless
+ * the collation strength has been set to ignore all accents).
+ *
+ * When beginning a search, the initial starting position, startIdx,
+ * is assumed to be an acceptable match boundary with respect to
+ * combining characters. A combining sequence that spans across the
+ * starting point will not supress a match beginning at startIdx.
+ *
+ * Characters that expand to multiple collation elements
+ * (German sharp-S becoming 'ss', or the composed forms of accented
+ * characters, for example) also must match completely.
+ * Searching for a single 's' in a string containing only a sharp-s will
+ * find no match.
+ *
+ *
+ * @param strsrch the UStringSearch struct, which references both
+ * the text to be searched and the pattern being sought.
+ * @param startIdx The index into the text to begin the search.
+ * @param matchStart An out parameter, the starting index of the matched text.
+ * This parameter may be NULL.
+ * A value of -1 will be returned if no match was found.
+ * @param matchLimit Out parameter, the index of the first position following the matched text.
+ * The matchLimit will be at a suitable position for beginning a subsequent search
+ * in the input text.
+ * This parameter may be NULL.
+ * A value of -1 will be returned if no match was found.
+ *
+ * @param status Report any errors. Note that no match found is not an error.
+ * @return TRUE if a match was found, FALSE otherwise.
+ *
+ * @internal
+ */
+U_INTERNAL UBool U_EXPORT2 usearch_search(UStringSearch *strsrch,
+ int32_t startIdx,
+ int32_t *matchStart,
+ int32_t *matchLimit,
+ UErrorCode *status);
+
+/**
+ * Simple backwards search for the pattern, starting at a specified index,
+ * and using using a default set search options.
+ *
+ * This is an experimental function, and is not an official part of the
+ * ICU API.
+ *
+ * The collator options, such as UCOL_STRENGTH and UCOL_NORMALIZTION, are honored.
+ *
+ * The UStringSearch options USEARCH_CANONICAL_MATCH, USEARCH_OVERLAP and
+ * any Break Iterator are ignored.
+ *
+ * Matches obey the following constraints:
+ *
+ * Characters at the start or end positions of a match that are ignorable
+ * for collation are not included as part of the match, unless they
+ * are part of a combining sequence, as described below.
+ *
+ * A match will not include a partial combining sequence. Combining
+ * character sequences are considered to be inseperable units,
+ * and either match the pattern completely, or are considered to not match
+ * at all. Thus, for example, an A followed a combining accent mark will
+ * not be found when searching for a plain (unaccented) A. (unless
+ * the collation strength has been set to ignore all accents).
+ *
+ * When beginning a search, the initial starting position, startIdx,
+ * is assumed to be an acceptable match boundary with respect to
+ * combining characters. A combining sequence that spans across the
+ * starting point will not supress a match beginning at startIdx.
+ *
+ * Characters that expand to multiple collation elements
+ * (German sharp-S becoming 'ss', or the composed forms of accented
+ * characters, for example) also must match completely.
+ * Searching for a single 's' in a string containing only a sharp-s will
+ * find no match.
+ *
+ *
+ * @param strsrch the UStringSearch struct, which references both
+ * the text to be searched and the pattern being sought.
+ * @param startIdx The index into the text to begin the search.
+ * @param matchStart An out parameter, the starting index of the matched text.
+ * This parameter may be NULL.
+ * A value of -1 will be returned if no match was found.
+ * @param matchLimit Out parameter, the index of the first position following the matched text.
+ * The matchLimit will be at a suitable position for beginning a subsequent search
+ * in the input text.
+ * This parameter may be NULL.
+ * A value of -1 will be returned if no match was found.
+ *
+ * @param status Report any errors. Note that no match found is not an error.
+ * @return TRUE if a match was found, FALSE otherwise.
+ *
+ * @internal
+ */
+U_INTERNAL UBool U_EXPORT2 usearch_searchBackwards(UStringSearch *strsrch,
+ int32_t startIdx,
+ int32_t *matchStart,
+ int32_t *matchLimit,
+ UErrorCode *status);
+
+#endif /* #if !UCONFIG_NO_COLLATION && !UCONFIG_NO_BREAK_ITERATION */
+
+#endif
http://git-wip-us.apache.org/repos/asf/couchdb-couch-collate/blob/32ffa429/platform/osx/icu/unicode/uset.h
----------------------------------------------------------------------
diff --git a/platform/osx/icu/unicode/uset.h b/platform/osx/icu/unicode/uset.h
new file mode 100644
index 0000000..2bbfd7a
--- /dev/null
+++ b/platform/osx/icu/unicode/uset.h
@@ -0,0 +1,1052 @@
+/*
+*******************************************************************************
+*
+* Copyright (C) 2002-2008, International Business Machines
+* Corporation and others. All Rights Reserved.
+*
+*******************************************************************************
+* file name: uset.h
+* encoding: US-ASCII
+* tab size: 8 (not used)
+* indentation:4
+*
+* created on: 2002mar07
+* created by: Markus W. Scherer
+*
+* C version of UnicodeSet.
+*/
+
+
+/**
+ * \file
+ * \brief C API: Unicode Set
+ *
+ * <p>This is a C wrapper around the C++ UnicodeSet class.</p>
+ */
+
+#ifndef __USET_H__
+#define __USET_H__
+
+#include "unicode/utypes.h"
+#include "unicode/uchar.h"
+
+#ifndef UCNV_H
+struct USet;
+/**
+ * A UnicodeSet. Use the uset_* API to manipulate. Create with
+ * uset_open*, and destroy with uset_close.
+ * @stable ICU 2.4
+ */
+typedef struct USet USet;
+#endif
+
+/**
+ * Bitmask values to be passed to uset_openPatternOptions() or
+ * uset_applyPattern() taking an option parameter.
+ * @stable ICU 2.4
+ */
+enum {
+ /**
+ * Ignore white space within patterns unless quoted or escaped.
+ * @stable ICU 2.4
+ */
+ USET_IGNORE_SPACE = 1,
+
+ /**
+ * Enable case insensitive matching. E.g., "[ab]" with this flag
+ * will match 'a', 'A', 'b', and 'B'. "[^ab]" with this flag will
+ * match all except 'a', 'A', 'b', and 'B'. This performs a full
+ * closure over case mappings, e.g. U+017F for s.
+ *
+ * The resulting set is a superset of the input for the code points but
+ * not for the strings.
+ * It performs a case mapping closure of the code points and adds
+ * full case folding strings for the code points, and reduces strings of
+ * the original set to their full case folding equivalents.
+ *
+ * This is designed for case-insensitive matches, for example
+ * in regular expressions. The full code point case closure allows checking of
+ * an input character directly against the closure set.
+ * Strings are matched by comparing the case-folded form from the closure
+ * set with an incremental case folding of the string in question.
+ *
+ * The closure set will also contain single code points if the original
+ * set contained case-equivalent strings (like U+00DF for "ss" or "Ss" etc.).
+ * This is not necessary (that is, redundant) for the above matching method
+ * but results in the same closure sets regardless of whether the original
+ * set contained the code point or a string.
+ *
+ * @stable ICU 2.4
+ */
+ USET_CASE_INSENSITIVE = 2,
+
+ /**
+ * Enable case insensitive matching. E.g., "[ab]" with this flag
+ * will match 'a', 'A', 'b', and 'B'. "[^ab]" with this flag will
+ * match all except 'a', 'A', 'b', and 'B'. This adds the lower-,
+ * title-, and uppercase mappings as well as the case folding
+ * of each existing element in the set.
+ * @stable ICU 3.2
+ */
+ USET_ADD_CASE_MAPPINGS = 4,
+
+ /**
+ * Enough for any single-code point set
+ * @internal
+ */
+ USET_SERIALIZED_STATIC_ARRAY_CAPACITY=8
+};
+
+/**
+ * Argument values for whether span() and similar functions continue while
+ * the current character is contained vs. not contained in the set.
+ *
+ * The functionality is straightforward for sets with only single code points,
+ * without strings (which is the common case):
+ * - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE
+ * work the same.
+ * - span() and spanBack() partition any string the same way when
+ * alternating between span(USET_SPAN_NOT_CONTAINED) and
+ * span(either "contained" condition).
+ * - Using a complemented (inverted) set and the opposite span conditions
+ * yields the same results.
+ *
+ * When a set contains multi-code point strings, then these statements may not
+ * be true, depending on the strings in the set (for example, whether they
+ * overlap with each other) and the string that is processed.
+ * For a set with strings:
+ * - The complement of the set contains the opposite set of code points,
+ * but the same set of strings.
+ * Therefore, complementing both the set and the span conditions
+ * may yield different results.
+ * - When starting spans at different positions in a string
+ * (span(s, ...) vs. span(s+1, ...)) the ends of the spans may be different
+ * because a set string may start before the later position.
+ * - span(USET_SPAN_SIMPLE) may be shorter than
+ * span(USET_SPAN_CONTAINED) because it will not recursively try
+ * all possible paths.
+ * For example, with a set which contains the three strings "xy", "xya" and "ax",
+ * span("xyax", USET_SPAN_CONTAINED) will return 4 but
+ * span("xyax", USET_SPAN_SIMPLE) will return 3.
+ * span(USET_SPAN_SIMPLE) will never be longer than
+ * span(USET_SPAN_CONTAINED).
+ * - With either "contained" condition, span() and spanBack() may partition
+ * a string in different ways.
+ * For example, with a set which contains the two strings "ab" and "ba",
+ * and when processing the string "aba",
+ * span() will yield contained/not-contained boundaries of { 0, 2, 3 }
+ * while spanBack() will yield boundaries of { 0, 1, 3 }.
+ *
+ * Note: If it is important to get the same boundaries whether iterating forward
+ * or backward through a string, then either only span() should be used and
+ * the boundaries cached for backward operation, or an ICU BreakIterator
+ * could be used.
+ *
+ * Note: Unpaired surrogates are treated like surrogate code points.
+ * Similarly, set strings match only on code point boundaries,
+ * never in the middle of a surrogate pair.
+ * Illegal UTF-8 sequences are treated like U+FFFD.
+ * When processing UTF-8 strings, malformed set strings
+ * (strings with unpaired surrogates which cannot be converted to UTF-8)
+ * are ignored.
+ *
+ * @stable ICU 4.0
+ */
+typedef enum USetSpanCondition {
+ /**
+ * Continue a span() while there is no set element at the current position.
+ * Stops before the first set element (character or string).
+ * (For code points only, this is like while contains(current)==FALSE).
+ *
+ * When span() returns, the substring between where it started and the position
+ * it returned consists only of characters that are not in the set,
+ * and none of its strings overlap with the span.
+ *
+ * @stable ICU 4.0
+ */
+ USET_SPAN_NOT_CONTAINED = 0,
+ /**
+ * Continue a span() while there is a set element at the current position.
+ * (For characters only, this is like while contains(current)==TRUE).
+ *
+ * When span() returns, the substring between where it started and the position
+ * it returned consists only of set elements (characters or strings) that are in the set.
+ *
+ * If a set contains strings, then the span will be the longest substring
+ * matching any of the possible concatenations of set elements (characters or strings).
+ * (There must be a single, non-overlapping concatenation of characters or strings.)
+ * This is equivalent to a POSIX regular expression for (OR of each set element)*.
+ *
+ * @stable ICU 4.0
+ */
+ USET_SPAN_CONTAINED = 1,
+ /**
+ * Continue a span() while there is a set element at the current position.
+ * (For characters only, this is like while contains(current)==TRUE).
+ *
+ * When span() returns, the substring between where it started and the position
+ * it returned consists only of set elements (characters or strings) that are in the set.
+ *
+ * If a set only contains single characters, then this is the same
+ * as USET_SPAN_CONTAINED.
+ *
+ * If a set contains strings, then the span will be the longest substring
+ * with a match at each position with the longest single set element (character or string).
+ *
+ * Use this span condition together with other longest-match algorithms,
+ * such as ICU converters (ucnv_getUnicodeSet()).
+ *
+ * @stable ICU 4.0
+ */
+ USET_SPAN_SIMPLE = 2,
+ /**
+ * One more than the last span condition.
+ * @stable ICU 4.0
+ */
+ USET_SPAN_CONDITION_COUNT
+} USetSpanCondition;
+
+/**
+ * A serialized form of a Unicode set. Limited manipulations are
+ * possible directly on a serialized set. See below.
+ * @stable ICU 2.4
+ */
+typedef struct USerializedSet {
+ /**
+ * The serialized Unicode Set.
+ * @stable ICU 2.4
+ */
+ const uint16_t *array;
+ /**
+ * The length of the array that contains BMP characters.
+ * @stable ICU 2.4
+ */
+ int32_t bmpLength;
+ /**
+ * The total length of the array.
+ * @stable ICU 2.4
+ */
+ int32_t length;
+ /**
+ * A small buffer for the array to reduce memory allocations.
+ * @stable ICU 2.4
+ */
+ uint16_t staticArray[USET_SERIALIZED_STATIC_ARRAY_CAPACITY];
+} USerializedSet;
+
+/*********************************************************************
+ * USet API
+ *********************************************************************/
+
+/**
+ * Creates a USet object that contains the range of characters
+ * start..end, inclusive. If <code>start > end</code>
+ * then an empty set is created.
+ * @param start first character of the range, inclusive
+ * @param end last character of the range, inclusive
+ * @return a newly created USet. The caller must call uset_close() on
+ * it when done.
+ * @stable ICU 2.4
+ */
+U_STABLE USet* U_EXPORT2
+uset_open(UChar32 start, UChar32 end);
+
+/**
+ * Creates a set from the given pattern. See the UnicodeSet class
+ * description for the syntax of the pattern language.
+ * @param pattern a string specifying what characters are in the set
+ * @param patternLength the length of the pattern, or -1 if null
+ * terminated
+ * @param ec the error code
+ * @stable ICU 2.4
+ */
+U_STABLE USet* U_EXPORT2
+uset_openPattern(const UChar* pattern, int32_t patternLength,
+ UErrorCode* ec);
+
+/**
+ * Creates a set from the given pattern. See the UnicodeSet class
+ * description for the syntax of the pattern language.
+ * @param pattern a string specifying what characters are in the set
+ * @param patternLength the length of the pattern, or -1 if null
+ * terminated
+ * @param options bitmask for options to apply to the pattern.
+ * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE.
+ * @param ec the error code
+ * @stable ICU 2.4
+ */
+U_STABLE USet* U_EXPORT2
+uset_openPatternOptions(const UChar* pattern, int32_t patternLength,
+ uint32_t options,
+ UErrorCode* ec);
+
+/**
+ * Disposes of the storage used by a USet object. This function should
+ * be called exactly once for objects returned by uset_open().
+ * @param set the object to dispose of
+ * @stable ICU 2.4
+ */
+U_STABLE void U_EXPORT2
+uset_close(USet* set);
+
+/**
+ * Returns a copy of this object.
+ * If this set is frozen, then the clone will be frozen as well.
+ * Use uset_cloneAsThawed() for a mutable clone of a frozen set.
+ * @param set the original set
+ * @return the newly allocated copy of the set
+ * @see uset_cloneAsThawed
+ * @stable ICU 4.0
+ */
+U_DRAFT USet * U_EXPORT2
+uset_clone(const USet *set);
+
+/**
+ * Determines whether the set has been frozen (made immutable) or not.
+ * See the ICU4J Freezable interface for details.
+ * @param set the set
+ * @return TRUE/FALSE for whether the set has been frozen
+ * @see uset_freeze
+ * @see uset_cloneAsThawed
+ * @stable ICU 4.0
+ */
+U_DRAFT UBool U_EXPORT2
+uset_isFrozen(const USet *set);
+
+/**
+ * Freeze the set (make it immutable).
+ * Once frozen, it cannot be unfrozen and is therefore thread-safe
+ * until it is deleted.
+ * See the ICU4J Freezable interface for details.
+ * Freezing the set may also make some operations faster, for example
+ * uset_contains() and uset_span().
+ * A frozen set will not be modified. (It remains frozen.)
+ * @param set the set
+ * @return the same set, now frozen
+ * @see uset_isFrozen
+ * @see uset_cloneAsThawed
+ * @stable ICU 4.0
+ */
+U_DRAFT void U_EXPORT2
+uset_freeze(USet *set);
+
+/**
+ * Clone the set and make the clone mutable.
+ * See the ICU4J Freezable interface for details.
+ * @param set the set
+ * @return the mutable clone
+ * @see uset_freeze
+ * @see uset_isFrozen
+ * @see uset_clone
+ * @stable ICU 4.0
+ */
+U_DRAFT USet * U_EXPORT2
+uset_cloneAsThawed(const USet *set);
+
+/**
+ * Causes the USet object to represent the range <code>start - end</code>.
+ * If <code>start > end</code> then this USet is set to an empty range.
+ * A frozen set will not be modified.
+ * @param set the object to set to the given range
+ * @param start first character in the set, inclusive
+ * @param end last character in the set, inclusive
+ * @stable ICU 3.2
+ */
+U_STABLE void U_EXPORT2
+uset_set(USet* set,
+ UChar32 start, UChar32 end);
+
+/**
+ * Modifies the set to represent the set specified by the given
+ * pattern. See the UnicodeSet class description for the syntax of
+ * the pattern language. See also the User Guide chapter about UnicodeSet.
+ * <em>Empties the set passed before applying the pattern.</em>
+ * A frozen set will not be modified.
+ * @param set The set to which the pattern is to be applied.
+ * @param pattern A pointer to UChar string specifying what characters are in the set.
+ * The character at pattern[0] must be a '['.
+ * @param patternLength The length of the UChar string. -1 if NUL terminated.
+ * @param options A bitmask for options to apply to the pattern.
+ * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE.
+ * @param status Returns an error if the pattern cannot be parsed.
+ * @return Upon successful parse, the value is either
+ * the index of the character after the closing ']'
+ * of the parsed pattern.
+ * If the status code indicates failure, then the return value
+ * is the index of the error in the source.
+ *
+ * @stable ICU 2.8
+ */
+U_STABLE int32_t U_EXPORT2
+uset_applyPattern(USet *set,
+ const UChar *pattern, int32_t patternLength,
+ uint32_t options,
+ UErrorCode *status);
+
+/**
+ * Modifies the set to contain those code points which have the given value
+ * for the given binary or enumerated property, as returned by
+ * u_getIntPropertyValue. Prior contents of this set are lost.
+ * A frozen set will not be modified.
+ *
+ * @param set the object to contain the code points defined by the property
+ *
+ * @param prop a property in the range UCHAR_BIN_START..UCHAR_BIN_LIMIT-1
+ * or UCHAR_INT_START..UCHAR_INT_LIMIT-1
+ * or UCHAR_MASK_START..UCHAR_MASK_LIMIT-1.
+ *
+ * @param value a value in the range u_getIntPropertyMinValue(prop)..
+ * u_getIntPropertyMaxValue(prop), with one exception. If prop is
+ * UCHAR_GENERAL_CATEGORY_MASK, then value should not be a UCharCategory, but
+ * rather a mask value produced by U_GET_GC_MASK(). This allows grouped
+ * categories such as [:L:] to be represented.
+ *
+ * @param ec error code input/output parameter
+ *
+ * @stable ICU 3.2
+ */
+U_STABLE void U_EXPORT2
+uset_applyIntPropertyValue(USet* set,
+ UProperty prop, int32_t value, UErrorCode* ec);
+
+/**
+ * Modifies the set to contain those code points which have the
+ * given value for the given property. Prior contents of this
+ * set are lost.
+ * A frozen set will not be modified.
+ *
+ * @param set the object to contain the code points defined by the given
+ * property and value alias
+ *
+ * @param prop a string specifying a property alias, either short or long.
+ * The name is matched loosely. See PropertyAliases.txt for names and a
+ * description of loose matching. If the value string is empty, then this
+ * string is interpreted as either a General_Category value alias, a Script
+ * value alias, a binary property alias, or a special ID. Special IDs are
+ * matched loosely and correspond to the following sets:
+ *
+ * "ANY" = [\\u0000-\\U0010FFFF],
+ * "ASCII" = [\\u0000-\\u007F],
+ * "Assigned" = [:^Cn:].
+ *
+ * @param propLength the length of the prop, or -1 if NULL
+ *
+ * @param value a string specifying a value alias, either short or long.
+ * The name is matched loosely. See PropertyValueAliases.txt for names
+ * and a description of loose matching. In addition to aliases listed,
+ * numeric values and canonical combining classes may be expressed
+ * numerically, e.g., ("nv", "0.5") or ("ccc", "220"). The value string
+ * may also be empty.
+ *
+ * @param valueLength the length of the value, or -1 if NULL
+ *
+ * @param ec error code input/output parameter
+ *
+ * @stable ICU 3.2
+ */
+U_STABLE void U_EXPORT2
+uset_applyPropertyAlias(USet* set,
+ const UChar *prop, int32_t propLength,
+ const UChar *value, int32_t valueLength,
+ UErrorCode* ec);
+
+/**
+ * Return true if the given position, in the given pattern, appears
+ * to be the start of a UnicodeSet pattern.
+ *
+ * @param pattern a string specifying the pattern
+ * @param patternLength the length of the pattern, or -1 if NULL
+ * @param pos the given position
+ * @stable ICU 3.2
+ */
+U_STABLE UBool U_EXPORT2
+uset_resemblesPattern(const UChar *pattern, int32_t patternLength,
+ int32_t pos);
+
+/**
+ * Returns a string representation of this set. If the result of
+ * calling this function is passed to a uset_openPattern(), it
+ * will produce another set that is equal to this one.
+ * @param set the set
+ * @param result the string to receive the rules, may be NULL
+ * @param resultCapacity the capacity of result, may be 0 if result is NULL
+ * @param escapeUnprintable if TRUE then convert unprintable
+ * character to their hex escape representations, \\uxxxx or
+ * \\Uxxxxxxxx. Unprintable characters are those other than
+ * U+000A, U+0020..U+007E.
+ * @param ec error code.
+ * @return length of string, possibly larger than resultCapacity
+ * @stable ICU 2.4
+ */
+U_STABLE int32_t U_EXPORT2
+uset_toPattern(const USet* set,
+ UChar* result, int32_t resultCapacity,
+ UBool escapeUnprintable,
+ UErrorCode* ec);
+
+/**
+ * Adds the given character to the given USet. After this call,
+ * uset_contains(set, c) will return TRUE.
+ * A frozen set will not be modified.
+ * @param set the object to which to add the character
+ * @param c the character to add
+ * @stable ICU 2.4
+ */
+U_STABLE void U_EXPORT2
+uset_add(USet* set, UChar32 c);
+
+/**
+ * Adds all of the elements in the specified set to this set if
+ * they're not already present. This operation effectively
+ * modifies this set so that its value is the <i>union</i> of the two
+ * sets. The behavior of this operation is unspecified if the specified
+ * collection is modified while the operation is in progress.
+ * A frozen set will not be modified.
+ *
+ * @param set the object to which to add the set
+ * @param additionalSet the source set whose elements are to be added to this set.
+ * @stable ICU 2.6
+ */
+U_STABLE void U_EXPORT2
+uset_addAll(USet* set, const USet *additionalSet);
+
+/**
+ * Adds the given range of characters to the given USet. After this call,
+ * uset_contains(set, start, end) will return TRUE.
+ * A frozen set will not be modified.
+ * @param set the object to which to add the character
+ * @param start the first character of the range to add, inclusive
+ * @param end the last character of the range to add, inclusive
+ * @stable ICU 2.2
+ */
+U_STABLE void U_EXPORT2
+uset_addRange(USet* set, UChar32 start, UChar32 end);
+
+/**
+ * Adds the given string to the given USet. After this call,
+ * uset_containsString(set, str, strLen) will return TRUE.
+ * A frozen set will not be modified.
+ * @param set the object to which to add the character
+ * @param str the string to add
+ * @param strLen the length of the string or -1 if null terminated.
+ * @stable ICU 2.4
+ */
+U_STABLE void U_EXPORT2
+uset_addString(USet* set, const UChar* str, int32_t strLen);
+
+/**
+ * Adds each of the characters in this string to the set. Thus "ch" => {"c", "h"}
+ * If this set already any particular character, it has no effect on that character.
+ * A frozen set will not be modified.
+ * @param set the object to which to add the character
+ * @param str the source string
+ * @param strLen the length of the string or -1 if null terminated.
+ * @stable ICU 3.4
+ */
+U_STABLE void U_EXPORT2
+uset_addAllCodePoints(USet* set, const UChar *str, int32_t strLen);
+
+/**
+ * Removes the given character from the given USet. After this call,
+ * uset_contains(set, c) will return FALSE.
+ * A frozen set will not be modified.
+ * @param set the object from which to remove the character
+ * @param c the character to remove
+ * @stable ICU 2.4
+ */
+U_STABLE void U_EXPORT2
+uset_remove(USet* set, UChar32 c);
+
+/**
+ * Removes the given range of characters from the given USet. After this call,
+ * uset_contains(set, start, end) will return FALSE.
+ * A frozen set will not be modified.
+ * @param set the object to which to add the character
+ * @param start the first character of the range to remove, inclusive
+ * @param end the last character of the range to remove, inclusive
+ * @stable ICU 2.2
+ */
+U_STABLE void U_EXPORT2
+uset_removeRange(USet* set, UChar32 start, UChar32 end);
+
+/**
+ * Removes the given string to the given USet. After this call,
+ * uset_containsString(set, str, strLen) will return FALSE.
+ * A frozen set will not be modified.
+ * @param set the object to which to add the character
+ * @param str the string to remove
+ * @param strLen the length of the string or -1 if null terminated.
+ * @stable ICU 2.4
+ */
+U_STABLE void U_EXPORT2
+uset_removeString(USet* set, const UChar* str, int32_t strLen);
+
+/**
+ * Removes from this set all of its elements that are contained in the
+ * specified set. This operation effectively modifies this
+ * set so that its value is the <i>asymmetric set difference</i> of
+ * the two sets.
+ * A frozen set will not be modified.
+ * @param set the object from which the elements are to be removed
+ * @param removeSet the object that defines which elements will be
+ * removed from this set
+ * @stable ICU 3.2
+ */
+U_STABLE void U_EXPORT2
+uset_removeAll(USet* set, const USet* removeSet);
+
+/**
+ * Retain only the elements in this set that are contained in the
+ * specified range. If <code>start > end</code> then an empty range is
+ * retained, leaving the set empty. This is equivalent to
+ * a boolean logic AND, or a set INTERSECTION.
+ * A frozen set will not be modified.
+ *
+ * @param set the object for which to retain only the specified range
+ * @param start first character, inclusive, of range to be retained
+ * to this set.
+ * @param end last character, inclusive, of range to be retained
+ * to this set.
+ * @stable ICU 3.2
+ */
+U_STABLE void U_EXPORT2
+uset_retain(USet* set, UChar32 start, UChar32 end);
+
+/**
+ * Retains only the elements in this set that are contained in the
+ * specified set. In other words, removes from this set all of
+ * its elements that are not contained in the specified set. This
+ * operation effectively modifies this set so that its value is
+ * the <i>intersection</i> of the two sets.
+ * A frozen set will not be modified.
+ *
+ * @param set the object on which to perform the retain
+ * @param retain set that defines which elements this set will retain
+ * @stable ICU 3.2
+ */
+U_STABLE void U_EXPORT2
+uset_retainAll(USet* set, const USet* retain);
+
+/**
+ * Reallocate this objects internal structures to take up the least
+ * possible space, without changing this object's value.
+ * A frozen set will not be modified.
+ *
+ * @param set the object on which to perfrom the compact
+ * @stable ICU 3.2
+ */
+U_STABLE void U_EXPORT2
+uset_compact(USet* set);
+
+/**
+ * Inverts this set. This operation modifies this set so that
+ * its value is its complement. This operation does not affect
+ * the multicharacter strings, if any.
+ * A frozen set will not be modified.
+ * @param set the set
+ * @stable ICU 2.4
+ */
+U_STABLE void U_EXPORT2
+uset_complement(USet* set);
+
+/**
+ * Complements in this set all elements contained in the specified
+ * set. Any character in the other set will be removed if it is
+ * in this set, or will be added if it is not in this set.
+ * A frozen set will not be modified.
+ *
+ * @param set the set with which to complement
+ * @param complement set that defines which elements will be xor'ed
+ * from this set.
+ * @stable ICU 3.2
+ */
+U_STABLE void U_EXPORT2
+uset_complementAll(USet* set, const USet* complement);
+
+/**
+ * Removes all of the elements from this set. This set will be
+ * empty after this call returns.
+ * A frozen set will not be modified.
+ * @param set the set
+ * @stable ICU 2.4
+ */
+U_STABLE void U_EXPORT2
+uset_clear(USet* set);
+
+/**
+ * Returns TRUE if the given USet contains no characters and no
+ * strings.
+ * @param set the set
+ * @return true if set is empty
+ * @stable ICU 2.4
+ */
+U_STABLE UBool U_EXPORT2
+uset_isEmpty(const USet* set);
+
+/**
+ * Returns TRUE if the given USet contains the given character.
+ * This function works faster with a frozen set.
+ * @param set the set
+ * @param c The codepoint to check for within the set
+ * @return true if set contains c
+ * @stable ICU 2.4
+ */
+U_STABLE UBool U_EXPORT2
+uset_contains(const USet* set, UChar32 c);
+
+/**
+ * Returns TRUE if the given USet contains all characters c
+ * where start <= c && c <= end.
+ * @param set the set
+ * @param start the first character of the range to test, inclusive
+ * @param end the last character of the range to test, inclusive
+ * @return TRUE if set contains the range
+ * @stable ICU 2.2
+ */
+U_STABLE UBool U_EXPORT2
+uset_containsRange(const USet* set, UChar32 start, UChar32 end);
+
+/**
+ * Returns TRUE if the given USet contains the given string.
+ * @param set the set
+ * @param str the string
+ * @param strLen the length of the string or -1 if null terminated.
+ * @return true if set contains str
+ * @stable ICU 2.4
+ */
+U_STABLE UBool U_EXPORT2
+uset_containsString(const USet* set, const UChar* str, int32_t strLen);
+
+/**
+ * Returns the index of the given character within this set, where
+ * the set is ordered by ascending code point. If the character
+ * is not in this set, return -1. The inverse of this method is
+ * <code>charAt()</code>.
+ * @param set the set
+ * @param c the character to obtain the index for
+ * @return an index from 0..size()-1, or -1
+ * @stable ICU 3.2
+ */
+U_STABLE int32_t U_EXPORT2
+uset_indexOf(const USet* set, UChar32 c);
+
+/**
+ * Returns the character at the given index within this set, where
+ * the set is ordered by ascending code point. If the index is
+ * out of range, return (UChar32)-1. The inverse of this method is
+ * <code>indexOf()</code>.
+ * @param set the set
+ * @param index an index from 0..size()-1 to obtain the char for
+ * @return the character at the given index, or (UChar32)-1.
+ * @stable ICU 3.2
+ */
+U_STABLE UChar32 U_EXPORT2
+uset_charAt(const USet* set, int32_t index);
+
+/**
+ * Returns the number of characters and strings contained in the given
+ * USet.
+ * @param set the set
+ * @return a non-negative integer counting the characters and strings
+ * contained in set
+ * @stable ICU 2.4
+ */
+U_STABLE int32_t U_EXPORT2
+uset_size(const USet* set);
+
+/**
+ * Returns the number of items in this set. An item is either a range
+ * of characters or a single multicharacter string.
+ * @param set the set
+ * @return a non-negative integer counting the character ranges
+ * and/or strings contained in set
+ * @stable ICU 2.4
+ */
+U_STABLE int32_t U_EXPORT2
+uset_getItemCount(const USet* set);
+
+/**
+ * Returns an item of this set. An item is either a range of
+ * characters or a single multicharacter string.
+ * @param set the set
+ * @param itemIndex a non-negative integer in the range 0..
+ * uset_getItemCount(set)-1
+ * @param start pointer to variable to receive first character
+ * in range, inclusive
+ * @param end pointer to variable to receive last character in range,
+ * inclusive
+ * @param str buffer to receive the string, may be NULL
+ * @param strCapacity capacity of str, or 0 if str is NULL
+ * @param ec error code
+ * @return the length of the string (>= 2), or 0 if the item is a
+ * range, in which case it is the range *start..*end, or -1 if
+ * itemIndex is out of range
+ * @stable ICU 2.4
+ */
+U_STABLE int32_t U_EXPORT2
+uset_getItem(const USet* set, int32_t itemIndex,
+ UChar32* start, UChar32* end,
+ UChar* str, int32_t strCapacity,
+ UErrorCode* ec);
+
+/**
+ * Returns true if set1 contains all the characters and strings
+ * of set2. It answers the question, 'Is set1 a superset of set2?'
+ * @param set1 set to be checked for containment
+ * @param set2 set to be checked for containment
+ * @return true if the test condition is met
+ * @stable ICU 3.2
+ */
+U_STABLE UBool U_EXPORT2
+uset_containsAll(const USet* set1, const USet* set2);
+
+/**
+ * Returns true if this set contains all the characters
+ * of the given string. This is does not check containment of grapheme
+ * clusters, like uset_containsString.
+ * @param set set of characters to be checked for containment
+ * @param str string containing codepoints to be checked for containment
+ * @param strLen the length of the string or -1 if null terminated.
+ * @return true if the test condition is met
+ * @stable ICU 3.4
+ */
+U_STABLE UBool U_EXPORT2
+uset_containsAllCodePoints(const USet* set, const UChar *str, int32_t strLen);
+
+/**
+ * Returns true if set1 contains none of the characters and strings
+ * of set2. It answers the question, 'Is set1 a disjoint set of set2?'
+ * @param set1 set to be checked for containment
+ * @param set2 set to be checked for containment
+ * @return true if the test condition is met
+ * @stable ICU 3.2
+ */
+U_STABLE UBool U_EXPORT2
+uset_containsNone(const USet* set1, const USet* set2);
+
+/**
+ * Returns true if set1 contains some of the characters and strings
+ * of set2. It answers the question, 'Does set1 and set2 have an intersection?'
+ * @param set1 set to be checked for containment
+ * @param set2 set to be checked for containment
+ * @return true if the test condition is met
+ * @stable ICU 3.2
+ */
+U_STABLE UBool U_EXPORT2
+uset_containsSome(const USet* set1, const USet* set2);
+
+/**
+ * Returns the length of the initial substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Similar to the strspn() C library function.
+ * Unpaired surrogates are treated according to contains() of their surrogate code points.
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param set the set
+ * @param s start of the string
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the length of the initial substring according to the spanCondition;
+ * 0 if the start of the string does not fit the spanCondition
+ * @stable ICU 4.0
+ * @see USetSpanCondition
+ */
+U_DRAFT int32_t U_EXPORT2
+uset_span(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition);
+
+/**
+ * Returns the start of the trailing substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Unpaired surrogates are treated according to contains() of their surrogate code points.
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param set the set
+ * @param s start of the string
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the start of the trailing substring according to the spanCondition;
+ * the string length if the end of the string does not fit the spanCondition
+ * @stable ICU 4.0
+ * @see USetSpanCondition
+ */
+U_DRAFT int32_t U_EXPORT2
+uset_spanBack(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition);
+
+/**
+ * Returns the length of the initial substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Similar to the strspn() C library function.
+ * Malformed byte sequences are treated according to contains(0xfffd).
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param set the set
+ * @param s start of the string (UTF-8)
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the length of the initial substring according to the spanCondition;
+ * 0 if the start of the string does not fit the spanCondition
+ * @stable ICU 4.0
+ * @see USetSpanCondition
+ */
+U_DRAFT int32_t U_EXPORT2
+uset_spanUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition);
+
+/**
+ * Returns the start of the trailing substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Malformed byte sequences are treated according to contains(0xfffd).
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param set the set
+ * @param s start of the string (UTF-8)
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the start of the trailing substring according to the spanCondition;
+ * the string length if the end of the string does not fit the spanCondition
+ * @stable ICU 4.0
+ * @see USetSpanCondition
+ */
+U_DRAFT int32_t U_EXPORT2
+uset_spanBackUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition);
+
+/**
+ * Returns true if set1 contains all of the characters and strings
+ * of set2, and vis versa. It answers the question, 'Is set1 equal to set2?'
+ * @param set1 set to be checked for containment
+ * @param set2 set to be checked for containment
+ * @return true if the test condition is met
+ * @stable ICU 3.2
+ */
+U_STABLE UBool U_EXPORT2
+uset_equals(const USet* set1, const USet* set2);
+
+/*********************************************************************
+ * Serialized set API
+ *********************************************************************/
+
+/**
+ * Serializes this set into an array of 16-bit integers. Serialization
+ * (currently) only records the characters in the set; multicharacter
+ * strings are ignored.
+ *
+ * The array
+ * has following format (each line is one 16-bit integer):
+ *
+ * length = (n+2*m) | (m!=0?0x8000:0)
+ * bmpLength = n; present if m!=0
+ * bmp[0]
+ * bmp[1]
+ * ...
+ * bmp[n-1]
+ * supp-high[0]
+ * supp-low[0]
+ * supp-high[1]
+ * supp-low[1]
+ * ...
+ * supp-high[m-1]
+ * supp-low[m-1]
+ *
+ * The array starts with a header. After the header are n bmp
+ * code points, then m supplementary code points. Either n or m
+ * or both may be zero. n+2*m is always <= 0x7FFF.
+ *
+ * If there are no supplementary characters (if m==0) then the
+ * header is one 16-bit integer, 'length', with value n.
+ *
+ * If there are supplementary characters (if m!=0) then the header
+ * is two 16-bit integers. The first, 'length', has value
+ * (n+2*m)|0x8000. The second, 'bmpLength', has value n.
+ *
+ * After the header the code points are stored in ascending order.
+ * Supplementary code points are stored as most significant 16
+ * bits followed by least significant 16 bits.
+ *
+ * @param set the set
+ * @param dest pointer to buffer of destCapacity 16-bit integers.
+ * May be NULL only if destCapacity is zero.
+ * @param destCapacity size of dest, or zero. Must not be negative.
+ * @param pErrorCode pointer to the error code. Will be set to
+ * U_INDEX_OUTOFBOUNDS_ERROR if n+2*m > 0x7FFF. Will be set to
+ * U_BUFFER_OVERFLOW_ERROR if n+2*m+(m!=0?2:1) > destCapacity.
+ * @return the total length of the serialized format, including
+ * the header, that is, n+2*m+(m!=0?2:1), or 0 on error other
+ * than U_BUFFER_OVERFLOW_ERROR.
+ * @stable ICU 2.4
+ */
+U_STABLE int32_t U_EXPORT2
+uset_serialize(const USet* set, uint16_t* dest, int32_t destCapacity, UErrorCode* pErrorCode);
+
+/**
+ * Given a serialized array, fill in the given serialized set object.
+ * @param fillSet pointer to result
+ * @param src pointer to start of array
+ * @param srcLength length of array
+ * @return true if the given array is valid, otherwise false
+ * @stable ICU 2.4
+ */
+U_STABLE UBool U_EXPORT2
+uset_getSerializedSet(USerializedSet* fillSet, const uint16_t* src, int32_t srcLength);
+
+/**
+ * Set the USerializedSet to contain the given character (and nothing
+ * else).
+ * @param fillSet pointer to result
+ * @param c The codepoint to set
+ * @stable ICU 2.4
+ */
+U_STABLE void U_EXPORT2
+uset_setSerializedToOne(USerializedSet* fillSet, UChar32 c);
+
+/**
+ * Returns TRUE if the given USerializedSet contains the given
+ * character.
+ * @param set the serialized set
+ * @param c The codepoint to check for within the set
+ * @return true if set contains c
+ * @stable ICU 2.4
+ */
+U_STABLE UBool U_EXPORT2
+uset_serializedContains(const USerializedSet* set, UChar32 c);
+
+/**
+ * Returns the number of disjoint ranges of characters contained in
+ * the given serialized set. Ignores any strings contained in the
+ * set.
+ * @param set the serialized set
+ * @return a non-negative integer counting the character ranges
+ * contained in set
+ * @stable ICU 2.4
+ */
+U_STABLE int32_t U_EXPORT2
+uset_getSerializedRangeCount(const USerializedSet* set);
+
+/**
+ * Returns a range of characters contained in the given serialized
+ * set.
+ * @param set the serialized set
+ * @param rangeIndex a non-negative integer in the range 0..
+ * uset_getSerializedRangeCount(set)-1
+ * @param pStart pointer to variable to receive first character
+ * in range, inclusive
+ * @param pEnd pointer to variable to receive last character in range,
+ * inclusive
+ * @return true if rangeIndex is valid, otherwise false
+ * @stable ICU 2.4
+ */
+U_STABLE UBool U_EXPORT2
+uset_getSerializedRange(const USerializedSet* set, int32_t rangeIndex,
+ UChar32* pStart, UChar32* pEnd);
+
+#endif
http://git-wip-us.apache.org/repos/asf/couchdb-couch-collate/blob/32ffa429/platform/osx/icu/unicode/usetiter.h
----------------------------------------------------------------------
diff --git a/platform/osx/icu/unicode/usetiter.h b/platform/osx/icu/unicode/usetiter.h
new file mode 100644
index 0000000..defa75c
--- /dev/null
+++ b/platform/osx/icu/unicode/usetiter.h
@@ -0,0 +1,318 @@
+/*
+**********************************************************************
+* Copyright (c) 2002-2006, International Business Machines
+* Corporation and others. All Rights Reserved.
+**********************************************************************
+*/
+#ifndef USETITER_H
+#define USETITER_H
+
+#include "unicode/utypes.h"
+#include "unicode/uobject.h"
+#include "unicode/unistr.h"
+
+/**
+ * \file
+ * \brief C++ API: UnicodeSetIterator iterates over the contents of a UnicodeSet.
+ */
+
+U_NAMESPACE_BEGIN
+
+class UnicodeSet;
+class UnicodeString;
+
+/**
+ *
+ * UnicodeSetIterator iterates over the contents of a UnicodeSet. It
+ * iterates over either code points or code point ranges. After all
+ * code points or ranges have been returned, it returns the
+ * multicharacter strings of the UnicodSet, if any.
+ *
+ * This class is not intended to be subclassed. Consider any fields
+ * or methods declared as "protected" to be private. The use of
+ * protected in this class is an artifact of history.
+ *
+ * <p>To iterate over code points and strings, use a loop like this:
+ * <pre>
+ * UnicodeSetIterator it(set);
+ * while (set.next()) {
+ * processItem(set.getString());
+ * }
+ * </pre>
+ * <p>Each item in the set is accessed as a string. Set elements
+ * consisting of single code points are returned as strings containing
+ * just the one code point.
+ *
+ * <p>To iterate over code point ranges, instead of individual code points,
+ * use a loop like this:
+ * <pre>
+ * UnicodeSetIterator it(set);
+ * while (it.nextRange()) {
+ * if (it.isString()) {
+ * processString(it.getString());
+ * } else {
+ * processCodepointRange(it.getCodepoint(), it.getCodepointEnd());
+ * }
+ * }
+ * </pre>
+ * @author M. Davis
+ * @stable ICU 2.4
+ */
+class U_COMMON_API UnicodeSetIterator : public UObject {
+
+ protected:
+
+ /**
+ * Value of <tt>codepoint</tt> if the iterator points to a string.
+ * If <tt>codepoint == IS_STRING</tt>, then examine
+ * <tt>string</tt> for the current iteration result.
+ * @stable ICU 2.4
+ */
+ enum { IS_STRING = -1 };
+
+ /**
+ * Current code point, or the special value <tt>IS_STRING</tt>, if
+ * the iterator points to a string.
+ * @stable ICU 2.4
+ */
+ UChar32 codepoint;
+
+ /**
+ * When iterating over ranges using <tt>nextRange()</tt>,
+ * <tt>codepointEnd</tt> contains the inclusive end of the
+ * iteration range, if <tt>codepoint != IS_STRING</tt>. If
+ * iterating over code points using <tt>next()</tt>, or if
+ * <tt>codepoint == IS_STRING</tt>, then the value of
+ * <tt>codepointEnd</tt> is undefined.
+ * @stable ICU 2.4
+ */
+ UChar32 codepointEnd;
+
+ /**
+ * If <tt>codepoint == IS_STRING</tt>, then <tt>string</tt> points
+ * to the current string. If <tt>codepoint != IS_STRING</tt>, the
+ * value of <tt>string</tt> is undefined.
+ * @stable ICU 2.4
+ */
+ const UnicodeString* string;
+
+ public:
+
+ /**
+ * Create an iterator over the given set. The iterator is valid
+ * only so long as <tt>set</tt> is valid.
+ * @param set set to iterate over
+ * @stable ICU 2.4
+ */
+ UnicodeSetIterator(const UnicodeSet& set);
+
+ /**
+ * Create an iterator over nothing. <tt>next()</tt> and
+ * <tt>nextRange()</tt> return false. This is a convenience
+ * constructor allowing the target to be set later.
+ * @stable ICU 2.4
+ */
+ UnicodeSetIterator();
+
+ /**
+ * Destructor.
+ * @stable ICU 2.4
+ */
+ virtual ~UnicodeSetIterator();
+
+ /**
+ * Returns true if the current element is a string. If so, the
+ * caller can retrieve it with <tt>getString()</tt>. If this
+ * method returns false, the current element is a code point or
+ * code point range, depending on whether <tt>next()</tt> or
+ * <tt>nextRange()</tt> was called.
+ * Elements of types string and codepoint can both be retrieved
+ * with the function <tt>getString()</tt>.
+ * Elements of type codepoint can also be retrieved with
+ * <tt>getCodepoint()</tt>.
+ * For ranges, <tt>getCodepoint()</tt> returns the starting codepoint
+ * of the range, and <tt>getCodepointEnd()</tt> returns the end
+ * of the range.
+ * @stable ICU 2.4
+ */
+ inline UBool isString() const;
+
+ /**
+ * Returns the current code point, if <tt>isString()</tt> returned
+ * false. Otherwise returns an undefined result.
+ * @stable ICU 2.4
+ */
+ inline UChar32 getCodepoint() const;
+
+ /**
+ * Returns the end of the current code point range, if
+ * <tt>isString()</tt> returned false and <tt>nextRange()</tt> was
+ * called. Otherwise returns an undefined result.
+ * @stable ICU 2.4
+ */
+ inline UChar32 getCodepointEnd() const;
+
+ /**
+ * Returns the current string, if <tt>isString()</tt> returned
+ * true. If the current iteration item is a code point, a UnicodeString
+ * containing that single code point is returned.
+ *
+ * Ownership of the returned string remains with the iterator.
+ * The string is guaranteed to remain valid only until the iterator is
+ * advanced to the next item, or until the iterator is deleted.
+ *
+ * @stable ICU 2.4
+ */
+ const UnicodeString& getString();
+
+ /**
+ * Advances the iteration position to the next element in the set,
+ * which can be either a single code point or a string.
+ * If there are no more elements in the set, return false.
+ *
+ * <p>
+ * If <tt>isString() == TRUE</tt>, the value is a
+ * string, otherwise the value is a
+ * single code point. Elements of either type can be retrieved
+ * with the function <tt>getString()</tt>, while elements of
+ * consisting of a single code point can be retrieved with
+ * <tt>getCodepoint()</tt>
+ *
+ * <p>The order of iteration is all code points in sorted order,
+ * followed by all strings sorted order. Do not mix
+ * calls to <tt>next()</tt> and <tt>nextRange()</tt> without
+ * calling <tt>reset()</tt> between them. The results of doing so
+ * are undefined.
+ *
+ * @return true if there was another element in the set.
+ * @stable ICU 2.4
+ */
+ UBool next();
+
+ /**
+ * Returns the next element in the set, either a code point range
+ * or a string. If there are no more elements in the set, return
+ * false. If <tt>isString() == TRUE</tt>, the value is a
+ * string and can be accessed with <tt>getString()</tt>. Otherwise the value is a
+ * range of one or more code points from <tt>getCodepoint()</tt> to
+ * <tt>getCodepointeEnd()</tt> inclusive.
+ *
+ * <p>The order of iteration is all code points ranges in sorted
+ * order, followed by all strings sorted order. Ranges are
+ * disjoint and non-contiguous. The value returned from <tt>getString()</tt>
+ * is undefined unless <tt>isString() == TRUE</tt>. Do not mix calls to
+ * <tt>next()</tt> and <tt>nextRange()</tt> without calling
+ * <tt>reset()</tt> between them. The results of doing so are
+ * undefined.
+ *
+ * @return true if there was another element in the set.
+ * @stable ICU 2.4
+ */
+ UBool nextRange();
+
+ /**
+ * Sets this iterator to visit the elements of the given set and
+ * resets it to the start of that set. The iterator is valid only
+ * so long as <tt>set</tt> is valid.
+ * @param set the set to iterate over.
+ * @stable ICU 2.4
+ */
+ void reset(const UnicodeSet& set);
+
+ /**
+ * Resets this iterator to the start of the set.
+ * @stable ICU 2.4
+ */
+ void reset();
+
+ /**
+ * ICU "poor man's RTTI", returns a UClassID for this class.
+ *
+ * @stable ICU 2.4
+ */
+ static UClassID U_EXPORT2 getStaticClassID();
+
+ /**
+ * ICU "poor man's RTTI", returns a UClassID for the actual class.
+ *
+ * @stable ICU 2.4
+ */
+ virtual UClassID getDynamicClassID() const;
+
+ // ======================= PRIVATES ===========================
+
+ protected:
+
+ // endElement and nextElements are really UChar32's, but we keep
+ // them as signed int32_t's so we can do comparisons with
+ // endElement set to -1. Leave them as int32_t's.
+ /** The set
+ * @stable ICU 2.4
+ */
+ const UnicodeSet* set;
+ /** End range
+ * @stable ICU 2.4
+ */
+ int32_t endRange;
+ /** Range
+ * @stable ICU 2.4
+ */
+ int32_t range;
+ /** End element
+ * @stable ICU 2.4
+ */
+ int32_t endElement;
+ /** Next element
+ * @stable ICU 2.4
+ */
+ int32_t nextElement;
+ //UBool abbreviated;
+ /** Next string
+ * @stable ICU 2.4
+ */
+ int32_t nextString;
+ /** String count
+ * @stable ICU 2.4
+ */
+ int32_t stringCount;
+
+ /**
+ * Points to the string to use when the caller asks for a
+ * string and the current iteration item is a code point, not a string.
+ * @internal
+ */
+ UnicodeString *cpString;
+
+ /** Copy constructor. Disallowed.
+ * @stable ICU 2.4
+ */
+ UnicodeSetIterator(const UnicodeSetIterator&); // disallow
+
+ /** Assignment operator. Disallowed.
+ * @stable ICU 2.4
+ */
+ UnicodeSetIterator& operator=(const UnicodeSetIterator&); // disallow
+
+ /** Load range
+ * @stable ICU 2.4
+ */
+ virtual void loadRange(int32_t range);
+
+};
+
+inline UBool UnicodeSetIterator::isString() const {
+ return codepoint == (UChar32)IS_STRING;
+}
+
+inline UChar32 UnicodeSetIterator::getCodepoint() const {
+ return codepoint;
+}
+
+inline UChar32 UnicodeSetIterator::getCodepointEnd() const {
+ return codepointEnd;
+}
+
+
+U_NAMESPACE_END
+
+#endif