tasn pushed a commit to branch master.

commit 4185694ecbe5293fad72f7eb9dd971900decb778
Author: Tom Hacohen <[email protected]>
Date:   Wed Aug 7 11:56:46 2013 +0100

    Synced libunibreak local copy with upstream.
---
 src/static_libs/libunibreak/wordbreak.c     |  39 +++++----
 src/static_libs/libunibreak/wordbreakdata.c | 121 ++++++++++++++++++++++++----
 src/static_libs/libunibreak/wordbreakdef.h  |  31 +++----
 3 files changed, 146 insertions(+), 45 deletions(-)

diff --git a/src/static_libs/libunibreak/wordbreak.c 
b/src/static_libs/libunibreak/wordbreak.c
index 60db99e..f2996c0 100644
--- a/src/static_libs/libunibreak/wordbreak.c
+++ b/src/static_libs/libunibreak/wordbreak.c
@@ -40,7 +40,7 @@
  * Implementation of the word breaking algorithm as described in Unicode
  * Standard Annex 29.
  *
- * @version    2.2, 2012/02/04
+ * @version    2.3, 2013/05/14
  * @author     Tom Hacohen
  */
 
@@ -188,7 +188,7 @@ static void set_wordbreaks(
 
                switch (wbcCur)
                {
-           case WBP_CR:
+               case WBP_CR:
                        /* WB3b */
                        set_brks_to(s, brks, posLast, posCur, len,
                                                WORDBREAK_BREAK, get_next_char);
@@ -196,7 +196,7 @@ static void set_wordbreaks(
                        posLast = posCur;
                        break;
 
-           case WBP_LF:
+               case WBP_LF:
                        if (wbcSeqStart == WBP_CR) /* WB3 */
                        {
                                set_brks_to(s, brks, posLast, posCur, len,
@@ -207,7 +207,7 @@ static void set_wordbreaks(
                        }
                        /* Fall off */
 
-           case WBP_Newline:
+               case WBP_Newline:
                        /* WB3a,3b */
                        set_brks_to(s, brks, posLast, posCur, len,
                                                WORDBREAK_BREAK, get_next_char);
@@ -215,8 +215,8 @@ static void set_wordbreaks(
                        posLast = posCur;
                        break;
 
-           case WBP_Extend:
-           case WBP_Format:
+               case WBP_Extend:
+               case WBP_Format:
                        /* WB4 - If not the first char/after a newline 
(WB3a,3b), skip
                         * this class, set it to be the same as the prev, and 
mark
                         * brks not to break before them. */
@@ -235,7 +235,7 @@ static void set_wordbreaks(
                        }
                        break;
 
-           case WBP_Katakana:
+               case WBP_Katakana:
                        if ((wbcSeqStart == WBP_Katakana) || /* WB13 */
                                        (wbcSeqStart == WBP_ExtendNumLet)) /* 
WB13b */
                        {
@@ -252,7 +252,7 @@ static void set_wordbreaks(
                        posLast = posCur;
                        break;
 
-           case WBP_ALetter:
+               case WBP_ALetter:
                        if ((wbcSeqStart == WBP_ALetter) || /* WB5,6,7 */
                                        (wbcLast == WBP_Numeric) || /* WB10 */
                                        (wbcSeqStart == WBP_ExtendNumLet)) /* 
WB13b */
@@ -270,7 +270,7 @@ static void set_wordbreaks(
                        posLast = posCur;
                        break;
 
-           case WBP_MidNumLet:
+               case WBP_MidNumLet:
                        if ((wbcLast == WBP_ALetter) || /* WB6,7 */
                                        (wbcLast == WBP_Numeric)) /* WB11,12 */
                        {
@@ -285,7 +285,7 @@ static void set_wordbreaks(
                        }
                        break;
 
-           case WBP_MidLetter:
+               case WBP_MidLetter:
                        if (wbcLast == WBP_ALetter) /* WB6,7 */
                        {
                                /* Go on */
@@ -299,7 +299,7 @@ static void set_wordbreaks(
                        }
                        break;
 
-           case WBP_MidNum:
+               case WBP_MidNum:
                        if (wbcLast == WBP_Numeric) /* WB11,12 */
                        {
                                /* Go on */
@@ -313,7 +313,7 @@ static void set_wordbreaks(
                        }
                        break;
 
-           case WBP_Numeric:
+               case WBP_Numeric:
                        if ((wbcSeqStart == WBP_Numeric) || /* WB8,11,12 */
                                        (wbcLast == WBP_ALetter) || /* WB9 */
                                        (wbcSeqStart == WBP_ExtendNumLet)) /* 
WB13b */
@@ -331,7 +331,7 @@ static void set_wordbreaks(
                        posLast = posCur;
                        break;
 
-           case WBP_ExtendNumLet:
+               case WBP_ExtendNumLet:
                        /* WB13a,13b */
                        if ((wbcSeqStart == wbcLast) &&
                                ((wbcLast == WBP_ALetter) ||
@@ -352,7 +352,18 @@ static void set_wordbreaks(
                        posLast = posCur;
                        break;
 
-                case WBP_Any:
+               case WBP_Regional:
+                       /* WB13c */
+                       if (wbcSeqStart == WBP_Regional)
+                       {
+                               set_brks_to(s, brks, posLast, posCur, len,
+                                                       WORDBREAK_NOBREAK, 
get_next_char);
+                       }
+                       wbcSeqStart = wbcCur;
+                       posLast = posCur;
+                       break;
+
+               case WBP_Any:
                        /* Allow breaks and reset */
                        set_brks_to(s, brks, posLast, posCur, len,
                                                WORDBREAK_BREAK, get_next_char);
diff --git a/src/static_libs/libunibreak/wordbreakdata.c 
b/src/static_libs/libunibreak/wordbreakdata.c
index c42c51b..fe5afe3 100644
--- a/src/static_libs/libunibreak/wordbreakdata.c
+++ b/src/static_libs/libunibreak/wordbreakdata.c
@@ -1,6 +1,6 @@
 /* The content of this file is generated from:
-# WordBreakProperty-6.0.0.txt
-# Date: 2010-08-19, 00:48:48 GMT [MD]
+# WordBreakProperty-6.2.0.txt
+# Date: 2012-08-13, 19:12:09 GMT [MD]
 */
 
 #include "linebreak.h"
@@ -69,7 +69,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x05F0, 0x05F2, WBP_ALetter},
        {0x05F3, 0x05F3, WBP_ALetter},
        {0x05F4, 0x05F4, WBP_MidLetter},
-       {0x0600, 0x0603, WBP_Format},
+       {0x0600, 0x0604, WBP_Format},
        {0x060C, 0x060D, WBP_MidNum},
        {0x0610, 0x061A, WBP_Extend},
        {0x0620, 0x063F, WBP_ALetter},
@@ -117,6 +117,9 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x0829, 0x082D, WBP_Extend},
        {0x0840, 0x0858, WBP_ALetter},
        {0x0859, 0x085B, WBP_Extend},
+       {0x08A0, 0x08A0, WBP_ALetter},
+       {0x08A2, 0x08AC, WBP_ALetter},
+       {0x08E4, 0x08FE, WBP_Extend},
        {0x0900, 0x0902, WBP_Extend},
        {0x0903, 0x0903, WBP_Extend},
        {0x0904, 0x0939, WBP_ALetter},
@@ -360,9 +363,11 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x109A, 0x109C, WBP_Extend},
        {0x109D, 0x109D, WBP_Extend},
        {0x10A0, 0x10C5, WBP_ALetter},
+       {0x10C7, 0x10C7, WBP_ALetter},
+       {0x10CD, 0x10CD, WBP_ALetter},
        {0x10D0, 0x10FA, WBP_ALetter},
        {0x10FC, 0x10FC, WBP_ALetter},
-       {0x1100, 0x1248, WBP_ALetter},
+       {0x10FD, 0x1248, WBP_ALetter},
        {0x124A, 0x124D, WBP_ALetter},
        {0x1250, 0x1256, WBP_ALetter},
        {0x1258, 0x1258, WBP_ALetter},
@@ -396,7 +401,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x1760, 0x176C, WBP_ALetter},
        {0x176E, 0x1770, WBP_ALetter},
        {0x1772, 0x1773, WBP_Extend},
-       {0x17B4, 0x17B5, WBP_Format},
+       {0x17B4, 0x17B5, WBP_Extend},
        {0x17B6, 0x17B6, WBP_Extend},
        {0x17B7, 0x17BD, WBP_Extend},
        {0x17BE, 0x17C5, WBP_Extend},
@@ -466,9 +471,11 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x1BA6, 0x1BA7, WBP_Extend},
        {0x1BA8, 0x1BA9, WBP_Extend},
        {0x1BAA, 0x1BAA, WBP_Extend},
+       {0x1BAB, 0x1BAB, WBP_Extend},
+       {0x1BAC, 0x1BAD, WBP_Extend},
        {0x1BAE, 0x1BAF, WBP_ALetter},
        {0x1BB0, 0x1BB9, WBP_Numeric},
-       {0x1BC0, 0x1BE5, WBP_ALetter},
+       {0x1BBA, 0x1BE5, WBP_ALetter},
        {0x1BE6, 0x1BE6, WBP_Extend},
        {0x1BE7, 0x1BE7, WBP_Extend},
        {0x1BE8, 0x1BE9, WBP_Extend},
@@ -494,10 +501,12 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x1CE9, 0x1CEC, WBP_ALetter},
        {0x1CED, 0x1CED, WBP_Extend},
        {0x1CEE, 0x1CF1, WBP_ALetter},
-       {0x1CF2, 0x1CF2, WBP_Extend},
+       {0x1CF2, 0x1CF3, WBP_Extend},
+       {0x1CF4, 0x1CF4, WBP_Extend},
+       {0x1CF5, 0x1CF6, WBP_ALetter},
        {0x1D00, 0x1D2B, WBP_ALetter},
-       {0x1D2C, 0x1D61, WBP_ALetter},
-       {0x1D62, 0x1D77, WBP_ALetter},
+       {0x1D2C, 0x1D6A, WBP_ALetter},
+       {0x1D6B, 0x1D77, WBP_ALetter},
        {0x1D78, 0x1D78, WBP_ALetter},
        {0x1D79, 0x1D9A, WBP_ALetter},
        {0x1D9B, 0x1DBF, WBP_ALetter},
@@ -565,13 +574,16 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x24B6, 0x24E9, WBP_ALetter},
        {0x2C00, 0x2C2E, WBP_ALetter},
        {0x2C30, 0x2C5E, WBP_ALetter},
-       {0x2C60, 0x2C7C, WBP_ALetter},
-       {0x2C7D, 0x2C7D, WBP_ALetter},
+       {0x2C60, 0x2C7B, WBP_ALetter},
+       {0x2C7C, 0x2C7D, WBP_ALetter},
        {0x2C7E, 0x2CE4, WBP_ALetter},
        {0x2CEB, 0x2CEE, WBP_ALetter},
        {0x2CEF, 0x2CF1, WBP_Extend},
+       {0x2CF2, 0x2CF3, WBP_ALetter},
        {0x2D00, 0x2D25, WBP_ALetter},
-       {0x2D30, 0x2D65, WBP_ALetter},
+       {0x2D27, 0x2D27, WBP_ALetter},
+       {0x2D2D, 0x2D2D, WBP_ALetter},
+       {0x2D30, 0x2D67, WBP_ALetter},
        {0x2D6F, 0x2D6F, WBP_ALetter},
        {0x2D7F, 0x2D7F, WBP_Extend},
        {0x2D80, 0x2D96, WBP_ALetter},
@@ -586,7 +598,8 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x2DE0, 0x2DFF, WBP_Extend},
        {0x2E2F, 0x2E2F, WBP_ALetter},
        {0x3005, 0x3005, WBP_ALetter},
-       {0x302A, 0x302F, WBP_Extend},
+       {0x302A, 0x302D, WBP_Extend},
+       {0x302E, 0x302F, WBP_Extend},
        {0x3031, 0x3035, WBP_Katakana},
        {0x303B, 0x303B, WBP_ALetter},
        {0x303C, 0x303C, WBP_ALetter},
@@ -616,9 +629,10 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0xA66E, 0xA66E, WBP_ALetter},
        {0xA66F, 0xA66F, WBP_Extend},
        {0xA670, 0xA672, WBP_Extend},
-       {0xA67C, 0xA67D, WBP_Extend},
+       {0xA674, 0xA67D, WBP_Extend},
        {0xA67F, 0xA67F, WBP_ALetter},
        {0xA680, 0xA697, WBP_ALetter},
+       {0xA69F, 0xA69F, WBP_Extend},
        {0xA6A0, 0xA6E5, WBP_ALetter},
        {0xA6E6, 0xA6EF, WBP_ALetter},
        {0xA6F0, 0xA6F1, WBP_Extend},
@@ -628,8 +642,9 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0xA771, 0xA787, WBP_ALetter},
        {0xA788, 0xA788, WBP_ALetter},
        {0xA78B, 0xA78E, WBP_ALetter},
-       {0xA790, 0xA791, WBP_ALetter},
-       {0xA7A0, 0xA7A9, WBP_ALetter},
+       {0xA790, 0xA793, WBP_ALetter},
+       {0xA7A0, 0xA7AA, WBP_ALetter},
+       {0xA7F8, 0xA7F9, WBP_ALetter},
        {0xA7FA, 0xA7FA, WBP_ALetter},
        {0xA7FB, 0xA801, WBP_ALetter},
        {0xA802, 0xA802, WBP_Extend},
@@ -686,6 +701,14 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0xAAB7, 0xAAB8, WBP_Extend},
        {0xAABE, 0xAABF, WBP_Extend},
        {0xAAC1, 0xAAC1, WBP_Extend},
+       {0xAAE0, 0xAAEA, WBP_ALetter},
+       {0xAAEB, 0xAAEB, WBP_Extend},
+       {0xAAEC, 0xAAED, WBP_Extend},
+       {0xAAEE, 0xAAEF, WBP_Extend},
+       {0xAAF2, 0xAAF2, WBP_ALetter},
+       {0xAAF3, 0xAAF4, WBP_ALetter},
+       {0xAAF5, 0xAAF5, WBP_Extend},
+       {0xAAF6, 0xAAF6, WBP_Extend},
        {0xAB01, 0xAB06, WBP_ALetter},
        {0xAB09, 0xAB0E, WBP_ALetter},
        {0xAB11, 0xAB16, WBP_ALetter},
@@ -781,6 +804,8 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x1083F, 0x10855, WBP_ALetter},
        {0x10900, 0x10915, WBP_ALetter},
        {0x10920, 0x10939, WBP_ALetter},
+       {0x10980, 0x109B7, WBP_ALetter},
+       {0x109BE, 0x109BF, WBP_ALetter},
        {0x10A00, 0x10A00, WBP_ALetter},
        {0x10A01, 0x10A03, WBP_Extend},
        {0x10A05, 0x10A06, WBP_Extend},
@@ -809,10 +834,40 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x110B7, 0x110B8, WBP_Extend},
        {0x110B9, 0x110BA, WBP_Extend},
        {0x110BD, 0x110BD, WBP_Format},
+       {0x110D0, 0x110E8, WBP_ALetter},
+       {0x110F0, 0x110F9, WBP_Numeric},
+       {0x11100, 0x11102, WBP_Extend},
+       {0x11103, 0x11126, WBP_ALetter},
+       {0x11127, 0x1112B, WBP_Extend},
+       {0x1112C, 0x1112C, WBP_Extend},
+       {0x1112D, 0x11134, WBP_Extend},
+       {0x11136, 0x1113F, WBP_Numeric},
+       {0x11180, 0x11181, WBP_Extend},
+       {0x11182, 0x11182, WBP_Extend},
+       {0x11183, 0x111B2, WBP_ALetter},
+       {0x111B3, 0x111B5, WBP_Extend},
+       {0x111B6, 0x111BE, WBP_Extend},
+       {0x111BF, 0x111C0, WBP_Extend},
+       {0x111C1, 0x111C4, WBP_ALetter},
+       {0x111D0, 0x111D9, WBP_Numeric},
+       {0x11680, 0x116AA, WBP_ALetter},
+       {0x116AB, 0x116AB, WBP_Extend},
+       {0x116AC, 0x116AC, WBP_Extend},
+       {0x116AD, 0x116AD, WBP_Extend},
+       {0x116AE, 0x116AF, WBP_Extend},
+       {0x116B0, 0x116B5, WBP_Extend},
+       {0x116B6, 0x116B6, WBP_Extend},
+       {0x116B7, 0x116B7, WBP_Extend},
+       {0x116C0, 0x116C9, WBP_Numeric},
        {0x12000, 0x1236E, WBP_ALetter},
        {0x12400, 0x12462, WBP_ALetter},
        {0x13000, 0x1342E, WBP_ALetter},
        {0x16800, 0x16A38, WBP_ALetter},
+       {0x16F00, 0x16F44, WBP_ALetter},
+       {0x16F50, 0x16F50, WBP_ALetter},
+       {0x16F51, 0x16F7E, WBP_Extend},
+       {0x16F8F, 0x16F92, WBP_Extend},
+       {0x16F93, 0x16F9F, WBP_ALetter},
        {0x1B000, 0x1B000, WBP_Katakana},
        {0x1D165, 0x1D166, WBP_Extend},
        {0x1D167, 0x1D169, WBP_Extend},
@@ -853,6 +908,40 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x1D7AA, 0x1D7C2, WBP_ALetter},
        {0x1D7C4, 0x1D7CB, WBP_ALetter},
        {0x1D7CE, 0x1D7FF, WBP_Numeric},
+       {0x1EE00, 0x1EE03, WBP_ALetter},
+       {0x1EE05, 0x1EE1F, WBP_ALetter},
+       {0x1EE21, 0x1EE22, WBP_ALetter},
+       {0x1EE24, 0x1EE24, WBP_ALetter},
+       {0x1EE27, 0x1EE27, WBP_ALetter},
+       {0x1EE29, 0x1EE32, WBP_ALetter},
+       {0x1EE34, 0x1EE37, WBP_ALetter},
+       {0x1EE39, 0x1EE39, WBP_ALetter},
+       {0x1EE3B, 0x1EE3B, WBP_ALetter},
+       {0x1EE42, 0x1EE42, WBP_ALetter},
+       {0x1EE47, 0x1EE47, WBP_ALetter},
+       {0x1EE49, 0x1EE49, WBP_ALetter},
+       {0x1EE4B, 0x1EE4B, WBP_ALetter},
+       {0x1EE4D, 0x1EE4F, WBP_ALetter},
+       {0x1EE51, 0x1EE52, WBP_ALetter},
+       {0x1EE54, 0x1EE54, WBP_ALetter},
+       {0x1EE57, 0x1EE57, WBP_ALetter},
+       {0x1EE59, 0x1EE59, WBP_ALetter},
+       {0x1EE5B, 0x1EE5B, WBP_ALetter},
+       {0x1EE5D, 0x1EE5D, WBP_ALetter},
+       {0x1EE5F, 0x1EE5F, WBP_ALetter},
+       {0x1EE61, 0x1EE62, WBP_ALetter},
+       {0x1EE64, 0x1EE64, WBP_ALetter},
+       {0x1EE67, 0x1EE6A, WBP_ALetter},
+       {0x1EE6C, 0x1EE72, WBP_ALetter},
+       {0x1EE74, 0x1EE77, WBP_ALetter},
+       {0x1EE79, 0x1EE7C, WBP_ALetter},
+       {0x1EE7E, 0x1EE7E, WBP_ALetter},
+       {0x1EE80, 0x1EE89, WBP_ALetter},
+       {0x1EE8B, 0x1EE9B, WBP_ALetter},
+       {0x1EEA1, 0x1EEA3, WBP_ALetter},
+       {0x1EEA5, 0x1EEA9, WBP_ALetter},
+       {0x1EEAB, 0x1EEBB, WBP_ALetter},
+       {0x1F1E6, 0x1F1FF, WBP_Regional},
        {0xE0001, 0xE0001, WBP_Format},
        {0xE0020, 0xE007F, WBP_Format},
        {0xE0100, 0xE01EF, WBP_Extend},
diff --git a/src/static_libs/libunibreak/wordbreakdef.h 
b/src/static_libs/libunibreak/wordbreakdef.h
index 0b4b165..ca8b1b6 100644
--- a/src/static_libs/libunibreak/wordbreakdef.h
+++ b/src/static_libs/libunibreak/wordbreakdef.h
@@ -40,7 +40,7 @@
  * Definitions of internal data structures, declarations of global
  * variables, and function prototypes for the word breaking algorithm.
  *
- * @version    2.1, 2012/01/18
+ * @version    2.2, 2013/05/14
  * @author     Tom Hacohen
  */
 
@@ -50,20 +50,21 @@
  */
 enum WordBreakClass
 {
-   WBP_Undefined,
-   WBP_CR,
-   WBP_LF,
-   WBP_Newline,
-   WBP_Extend,
-   WBP_Format,
-   WBP_Katakana,
-   WBP_ALetter,
-   WBP_MidNumLet,
-   WBP_MidLetter,
-   WBP_MidNum,
-   WBP_Numeric,
-   WBP_ExtendNumLet,
-   WBP_Any
+       WBP_Undefined,
+       WBP_CR,
+       WBP_LF,
+       WBP_Newline,
+       WBP_Extend,
+       WBP_Format,
+       WBP_Katakana,
+       WBP_ALetter,
+       WBP_MidNumLet,
+       WBP_MidLetter,
+       WBP_MidNum,
+       WBP_Numeric,
+       WBP_ExtendNumLet,
+       WBP_Regional,
+       WBP_Any
 };
 
 /**

-- 

------------------------------------------------------------------------------
Get 100% visibility into Java/.NET code with AppDynamics Lite!
It's a free troubleshooting tool designed for production.
Get down to code-level detail for bottlenecks, with <2% overhead. 
Download for free and get started troubleshooting in minutes. 
http://pubads.g.doubleclick.net/gampad/clk?id=48897031&iu=/4140/ostg.clktrk

Reply via email to