ICU 56 update step 1

source/common/unicode/ubrk.h

 /*
 ******************************************************************************
-* Copyright (C) 1996-2014, International Business Machines Corporation and others.
+* Copyright (C) 1996-2015, International Business Machines Corporation and others.
 * All Rights Reserved.
 ******************************************************************************
 */
 
 #ifndef UBRK_H
 #define UBRK_H
 
 #include "unicode/utypes.h"
 #include "unicode/uloc.h"
 #include "unicode/utext.h"
@@ skipping 24 matching lines @@
  *
  * The BreakIterator C API defines  methods for finding the location
  * of boundaries in text. Pointer to a UBreakIterator maintain a
  * current position and scan over text returning the index of characters
  * where boundaries occur.
  * <p>
  * Line boundary analysis determines where a text string can be broken
  * 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".
+ * <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
  * interpretation of punctuation marks within and following
  * words. Characters that are not part of a word, such as symbols or
  * punctuation marks, have word-breaks on both sides.
  * <p>
  * Character boundary analysis identifies the boundaries of
  * "Extended Grapheme Clusters", which are groupings of codepoints
  * that should be treated as character-like units for many text operations.
@@ skipping 133 matching lines @@
     /** Tag value for a hard, or mandatory line break  */
 } USentenceBreakTag;
 
 
 /**
  * Open a new UBreakIterator for locating text boundaries for a specified locale.
  * A UBreakIterator may be used for detecting character, line, word,
  * 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.
  * @return A UBreakIterator for the specified locale.
  * @see ubrk_openRules
  * @stable ICU 2.0
  */
 U_STABLE UBreakIterator* U_EXPORT2
 ubrk_open(UBreakIteratorType type,
       const char *locale,
@@ skipping 315 matching lines @@
   * @stable ICU 49
   */
 U_STABLE void U_EXPORT2
 ubrk_refreshUText(UBreakIterator *bi,
                        UText          *text,
                        UErrorCode     *status);
 
 #endif /* #if !UCONFIG_NO_BREAK_ITERATION */
 
 #endif