Index: source/common/unicode/ubrk.h |
diff --git a/source/common/unicode/ubrk.h b/source/common/unicode/ubrk.h |
index 9bdb4d5d9de3188e3fed72e39efeb752b5da5b04..3c26663ec961d983488bced551656bdaad85e705 100644 |
--- a/source/common/unicode/ubrk.h |
+++ b/source/common/unicode/ubrk.h |
@@ -1,6 +1,6 @@ |
/* |
****************************************************************************** |
-* Copyright (C) 1996-2014, International Business Machines Corporation and others. |
+* Copyright (C) 1996-2015, International Business Machines Corporation and others. |
* All Rights Reserved. |
****************************************************************************** |
*/ |
@@ -45,10 +45,20 @@ |
* 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 |
@@ -202,7 +212,9 @@ 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. |