ICU-551.24.tar.gz

[apple/icu.git] / icuSources / common / unicode / ubrk.h

diff --git a/icuSources/common/unicode/ubrk.h b/icuSources/common/unicode/ubrk.h
index e9c0ef627b67279f86e46044bf0f257102e0c6cd..dfa2fe71279dab5cbf599410a9a157335f6d6334 100644 (file)
--- a/icuSources/common/unicode/ubrk.h
+++ b/icuSources/common/unicode/ubrk.h
@@ -1,6 +1,6 @@
 /*
 ******************************************************************************
-* Copyright (C) 1996-2013, International Business Machines Corporation and others.
+* Copyright (C) 1996-2015, International Business Machines Corporation and others.
 * All Rights Reserved.
 ******************************************************************************
 */
@@ -45,10 +45,22 @@
  * when line-wrapping. The mechanism correctly handles punctuation and
  * hyphenated words.
  * <p>
+ * Note: The locale keyword "lb" can be used to modify line break
+ * behavior according to the CSS level 3 line-break options, see
+ * <http://dev.w3.org/csswg/css-text/#line-breaking>. For example:
+ * "ja@lb=strict", "zh@lb=loose".
+ * <p>
  * Sentence boundary analysis allows selection with correct
  * interpretation of periods within numbers and abbreviations, and
  * trailing punctuation marks such as quotation marks and parentheses.
  * <p>
+ * Note: The locale keyword "ss" can be used to enable use of
+ * segmentation suppression data (preventing breaks in English after
+ * abbreviations such as "Mr." or "Est.", for example), as follows:
+ * "en@ss=standard". However, use of the suppression data is
+ * currently supported only for ubrk_next; ubrk_previous, ubrk_following,
+ * and ubrk_preceding will ignore the suppression data.
+ * <p>
  * Word boundary analysis is used by search and replace functions, as
  * well as within text editing applications that allow the user to
  * select words with a double click. Word selection provides correct
@@ -202,7 +214,9 @@ typedef enum USentenceBreakTag {
  * and sentence breaks in text.
  * @param type The type of UBreakIterator to open: one of UBRK_CHARACTER, UBRK_WORD,
  * UBRK_LINE, UBRK_SENTENCE
- * @param locale The locale specifying the text-breaking conventions.
+ * @param locale The locale specifying the text-breaking conventions. Note that
+ * locale keys such as "lb" and "ss" may be used to modify text break behavior,
+ * see general discussion of BreakIterator C API.
  * @param text The text to be iterated over.
  * @param textLength The number of characters in text, or -1 if null-terminated.
  * @param status A UErrorCode to receive any errors.
@@ -378,10 +392,9 @@ U_STABLE int32_t U_EXPORT2
 ubrk_previous(UBreakIterator *bi);
 
 /**
- * Set the iterator position to the index of the first character in the text being scanned.
- * This is not always the same as index 0 of the text.
+ * Set the iterator position to zero, the start of the text being scanned.
  * @param bi The break iterator to use.
- * @return The character index of the first character in the text being scanned.
+ * @return The new iterator position (zero).
  * @see ubrk_last
  * @stable ICU 2.0
  */