Update libunibreak to fix word wrap mode issue.

Update libunibreak to fix word wrap mode issue.

Change-Id: I669168209fa4c588b07991273b7f36a3b92faca7

diff --git a/third-party/file.list b/third-party/file.list
old mode 100644 (file)
new mode 100755 (executable)
index e7fc013..856a26d
--- a/third-party/file.list
+++ b/third-party/file.list
@@ -10,7 +10,9 @@ static_libraries_libunibreak_src_files = \
   ${adaptor_thirdparty_dir}/libunibreak/linebreak.c \
   ${adaptor_thirdparty_dir}/libunibreak/linebreakdata.c \
   ${adaptor_thirdparty_dir}/libunibreak/linebreakdef.c \
-  ${adaptor_thirdparty_dir}/libunibreak/wordbreak.c
+  ${adaptor_thirdparty_dir}/libunibreak/wordbreak.c \
+  ${adaptor_thirdparty_dir}/libunibreak/unibreakbase.c \
+  ${adaptor_thirdparty_dir}/libunibreak/unibreakdef.c
 
 adaptor_resampler_src_files=\
     ${adaptor_thirdparty_dir}/resampler/resampler.cpp
\ No newline at end of file

diff --git a/third-party/libunibreak/LICENCE b/third-party/libunibreak/LICENCE
index ceec155..3eda8d5 100644 (file)
--- a/third-party/libunibreak/LICENCE
+++ b/third-party/libunibreak/LICENCE
@@ -1,5 +1,6 @@
-Copyright (C) 2008-2012 Wu Yongwei <wuyongwei at gmail dot com>
-Copyright (C) 2012 Tom Hacohen <tom dot hacohen at samsung dot com>
+Copyright (C) 2008-2015 Wu Yongwei <wuyongwei at gmail dot com>
+Copyright (C) 2012-2015 Tom Hacohen <tom at stosb dot com>
+Copyright (C) 2013 Petr Filipsky <philodej at gmail dot com>
 
 This software is provided 'as-is', without any express or implied
 warranty.  In no event will the author be held liable for any damages

diff --git a/third-party/libunibreak/linebreak.c b/third-party/libunibreak/linebreak.c
index 62a8104..2b28f05 100644 (file)
--- a/third-party/libunibreak/linebreak.c
+++ b/third-party/libunibreak/linebreak.c
@@ -4,7 +4,7 @@
  * Line breaking in a Unicode sequence.  Designed to be used in a
  * generic text renderer.
  *
- * Copyright (C) 2008-2013 Wu Yongwei <wuyongwei at gmail dot com>
+ * Copyright (C) 2008-2015 Wu Yongwei <wuyongwei at gmail dot com>
  * Copyright (C) 2013 Petr Filipsky <philodej at gmail dot com>
  *
  * This software is provided 'as-is', without any express or implied
@@ -31,9 +31,9 @@
  * Unicode 5.0.0:
  *      <URL:http://www.unicode.org/reports/tr14/tr14-19.html>
  *
- * This library has been updated according to Revision 30, for
- * Unicode 6.2.0:
- *      <URL:http://www.unicode.org/reports/tr14/tr14-30.html>
+ * This library has been updated according to Revision 33, for
+ * Unicode 7.0.0:
+ *      <URL:http://www.unicode.org/reports/tr14/tr14-33.html>
  *
  * The Unicode Terms of Use are available at
  *      <URL:http://www.unicode.org/copyright.html>
@@ -45,7 +45,7 @@
  * Implementation of the line breaking algorithm as described in Unicode
  * Standard Annex 14.
  *
- * @version 2.5, 2013/11/14
+ * @version 2.7, 2015/04/18
  * @author  Wu Yongwei
  * @author  Petr Filipsky
  */
@@ -67,11 +67,6 @@
 #define LINEBREAK_INDEX_SIZE 40
 
 /**
- * Version number of the library.
- */
-const int linebreak_version = LINEBREAK_VERSION;
-
-/**
  * Enumeration of break actions.  They are used in the break action
  * pair table below.
  */
@@ -451,7 +446,7 @@ static enum LineBreakClass resolve_lb_class(
  * @post                  \a lbpCtx->lbcCur has the updated line break class
  */
 static void treat_first_char(
-        struct LineBreakContext* lbpCtx)
+        struct LineBreakContext *lbpCtx)
 {
     switch (lbpCtx->lbcCur)
     {
@@ -465,6 +460,8 @@ static void treat_first_char(
     case LBP_SP:
         lbpCtx->lbcCur = LBP_WJ;        /* Leading space treated as WJ */
         break;
+    case LBP_HL:
+        lbpCtx->fLb21aHebrew = 1;       /* Rule LB21a */
     default:
         break;
     }
@@ -485,7 +482,7 @@ static void treat_first_char(
  *                        table lookup is needed
  */
 static int get_lb_result_simple(
-        struct LineBreakContext* lbpCtx)
+        struct LineBreakContext *lbpCtx)
 {
     if (lbpCtx->lbcCur == LBP_BK
         || (lbpCtx->lbcCur == LBP_CR && lbpCtx->lbcNew != LBP_LF))
@@ -528,14 +525,46 @@ static int get_lb_result_simple(
  *                        #LINEBREAK_ALLOWBREAK, and #LINEBREAK_NOBREAK
  */
 static int get_lb_result_lookup(
-        struct LineBreakContext* lbpCtx)
+        struct LineBreakContext *lbpCtx)
 {
-    /* TODO: Rule LB21a, as introduced by Revision 28 of UAX#14, is not
-     * yet implemented below. */
     int brk = LINEBREAK_UNDEFINED;
+
     assert((lbpCtx->lbcCur > 0) && (lbpCtx->lbcCur <= LBP_RI));
     assert((lbpCtx->lbcNew > 0) && (lbpCtx->lbcNew <= LBP_RI));
-    switch (baTable[lbpCtx->lbcCur - 1][lbpCtx->lbcNew - 1])
+
+    /* Fix for Hangul word wrap */
+    enum LineBreakClass lbcCur, lbcNew;
+
+    switch (lbpCtx->lbcCur)
+    {
+    case LBP_H2:        /**< Hangul LV */
+    case LBP_H3:        /**< Hangul LVT */
+    case LBP_JL:        /**< Hangul L Jamo */
+    case LBP_JV:        /**< Hangul V Jamo */
+    case LBP_JT:        /**< Hangul T Jamo */
+        lbcCur = LBP_AL;
+        break;
+    default:
+        lbcCur = lbpCtx->lbcCur;
+        break;
+    }
+
+    switch (lbpCtx->lbcNew)
+    {
+    case LBP_H2:        /**< Hangul LV */
+    case LBP_H3:        /**< Hangul LVT */
+    case LBP_JL:        /**< Hangul L Jamo */
+    case LBP_JV:        /**< Hangul V Jamo */
+    case LBP_JT:        /**< Hangul T Jamo */
+        lbcNew = LBP_AL;
+        break;
+    default:
+        lbcNew = lbpCtx->lbcNew;
+        break;
+    }
+
+    switch (baTable[lbcCur - 1][lbcNew - 1])
+    /* END */
     {
     case DIR_BRK:
         brk = LINEBREAK_ALLOWBREAK;
@@ -555,6 +584,19 @@ static int get_lb_result_lookup(
         brk = LINEBREAK_NOBREAK;
         break;
     }
+
+    /* Special processing due to rule LB21a */
+    if (lbpCtx->fLb21aHebrew &&
+        (lbpCtx->lbcCur == LBP_HY || lbpCtx->lbcCur == LBP_BA))
+    {
+        brk = LINEBREAK_NOBREAK;
+        lbpCtx->fLb21aHebrew = 0;
+    }
+    else if (!(lbpCtx->lbcNew == LBP_HY || lbpCtx->lbcNew == LBP_BA))
+    {
+        lbpCtx->fLb21aHebrew = (lbpCtx->lbcNew == LBP_HL);
+    }
+
     lbpCtx->lbcCur = lbpCtx->lbcNew;
     return brk;
 }
@@ -568,9 +610,9 @@ static int get_lb_result_lookup(
  * @post                  the line breaking context is initialized
  */
 void lb_init_break_context(
-        struct LineBreakContext* lbpCtx,
+        struct LineBreakContext *lbpCtx,
         utf32_t ch,
-        const char* lang)
+        const char *lang)
 {
     lbpCtx->lang = lang;
     lbpCtx->lbpLang = get_lb_prop_lang(lang);
@@ -579,6 +621,7 @@ void lb_init_break_context(
     lbpCtx->lbcCur = resolve_lb_class(
                         get_char_lb_class_lang(ch, lbpCtx->lbpLang),
                         lbpCtx->lang);
+    lbpCtx->fLb21aHebrew = 0;
     treat_first_char(lbpCtx);
 }
 
@@ -593,7 +636,7 @@ void lb_init_break_context(
  * @post                  the line breaking context is updated
  */
 int lb_process_next_char(
-        struct LineBreakContext* lbpCtx,
+        struct LineBreakContext *lbpCtx,
         utf32_t ch )
 {
     int brk;
@@ -618,127 +661,6 @@ int lb_process_next_char(
 }
 
 /**
- * Gets the next Unicode character in a UTF-8 sequence.  The index will
- * be advanced to the next complete character, unless the end of string
- * is reached in the middle of a UTF-8 sequence.
- *
- * @param[in]     s    input UTF-8 string
- * @param[in]     len  length of the string in bytes
- * @param[in,out] ip   pointer to the index
- * @return             the Unicode character beginning at the index; or
- *                     #EOS if end of input is encountered
- */
-utf32_t lb_get_next_char_utf8(
-        const utf8_t *s,
-        size_t len,
-        size_t *ip)
-{
-    utf8_t ch;
-    utf32_t res;
-
-    assert(*ip <= len);
-    if (*ip == len)
-        return EOS;
-    ch = s[*ip];
-
-    if (ch < 0xC2 || ch > 0xF4)
-    {   /* One-byte sequence, tail (should not occur), or invalid */
-        *ip += 1;
-        return ch;
-    }
-    else if (ch < 0xE0)
-    {   /* Two-byte sequence */
-        if (*ip + 2 > len)
-            return EOS;
-        res = ((ch & 0x1F) << 6) + (s[*ip + 1] & 0x3F);
-        *ip += 2;
-        return res;
-    }
-    else if (ch < 0xF0)
-    {   /* Three-byte sequence */
-        if (*ip + 3 > len)
-            return EOS;
-        res = ((ch & 0x0F) << 12) +
-              ((s[*ip + 1] & 0x3F) << 6) +
-              ((s[*ip + 2] & 0x3F));
-        *ip += 3;
-        return res;
-    }
-    else
-    {   /* Four-byte sequence */
-        if (*ip + 4 > len)
-            return EOS;
-        res = ((ch & 0x07) << 18) +
-              ((s[*ip + 1] & 0x3F) << 12) +
-              ((s[*ip + 2] & 0x3F) << 6) +
-              ((s[*ip + 3] & 0x3F));
-        *ip += 4;
-        return res;
-    }
-}
-
-/**
- * Gets the next Unicode character in a UTF-16 sequence.  The index will
- * be advanced to the next complete character, unless the end of string
- * is reached in the middle of a UTF-16 surrogate pair.
- *
- * @param[in]     s    input UTF-16 string
- * @param[in]     len  length of the string in words
- * @param[in,out] ip   pointer to the index
- * @return             the Unicode character beginning at the index; or
- *                     #EOS if end of input is encountered
- */
-utf32_t lb_get_next_char_utf16(
-        const utf16_t *s,
-        size_t len,
-        size_t *ip)
-{
-    utf16_t ch;
-
-    assert(*ip <= len);
-    if (*ip == len)
-        return EOS;
-    ch = s[(*ip)++];
-
-    if (ch < 0xD800 || ch > 0xDBFF)
-    {   /* If the character is not a high surrogate */
-        return ch;
-    }
-    if (*ip == len)
-    {   /* If the input ends here (an error) */
-        --(*ip);
-        return EOS;
-    }
-    if (s[*ip] < 0xDC00 || s[*ip] > 0xDFFF)
-    {   /* If the next character is not the low surrogate (an error) */
-        return ch;
-    }
-    /* Return the constructed character and advance the index again */
-    return (((utf32_t)ch & 0x3FF) << 10) + (s[(*ip)++] & 0x3FF) + 0x10000;
-}
-
-/**
- * Gets the next Unicode character in a UTF-32 sequence.  The index will
- * be advanced to the next character.
- *
- * @param[in]     s    input UTF-32 string
- * @param[in]     len  length of the string in dwords
- * @param[in,out] ip   pointer to the index
- * @return             the Unicode character beginning at the index; or
- *                     #EOS if end of input is encountered
- */
-utf32_t lb_get_next_char_utf32(
-        const utf32_t *s,
-        size_t len,
-        size_t *ip)
-{
-    assert(*ip <= len);
-    if (*ip == len)
-        return EOS;
-    return s[(*ip)++];
-}
-
-/**
  * Sets the line breaking information for a generic input string.
  *
  * @param[in]  s             input string
@@ -809,7 +731,7 @@ void set_linebreaks_utf8(
         char *brks)
 {
     set_linebreaks(s, len, lang, brks,
-                   (get_next_char_t)lb_get_next_char_utf8);
+                   (get_next_char_t)ub_get_next_char_utf8);
 }
 
 /**
@@ -829,7 +751,7 @@ void set_linebreaks_utf16(
         char *brks)
 {
     set_linebreaks(s, len, lang, brks,
-                   (get_next_char_t)lb_get_next_char_utf16);
+                   (get_next_char_t)ub_get_next_char_utf16);
 }
 
 /**
@@ -849,7 +771,7 @@ void set_linebreaks_utf32(
         char *brks)
 {
     set_linebreaks(s, len, lang, brks,
-                   (get_next_char_t)lb_get_next_char_utf32);
+                   (get_next_char_t)ub_get_next_char_utf32);
 }
 
 /**
@@ -868,7 +790,7 @@ void set_linebreaks_utf32(
 int is_line_breakable(
         utf32_t char1,
         utf32_t char2,
-        const char* lang)
+        const char *lang)
 {
     utf32_t s[2];
     char brks[2];

diff --git a/third-party/libunibreak/linebreak.h b/third-party/libunibreak/linebreak.h
index 94fbca0..68c8e41 100644 (file)
--- a/third-party/libunibreak/linebreak.h
+++ b/third-party/libunibreak/linebreak.h
@@ -4,7 +4,7 @@
  * Line breaking in a Unicode sequence.  Designed to be used in a
  * generic text renderer.
  *
- * Copyright (C) 2008-2012 Wu Yongwei <wuyongwei at gmail dot com>
+ * Copyright (C) 2008-2015 Wu Yongwei <wuyongwei at gmail dot com>
  *
  * This software is provided 'as-is', without any express or implied
  * warranty.  In no event will the author be held liable for any damages
@@ -30,9 +30,9 @@
  * Unicode 5.0.0:
  *      <URL:http://www.unicode.org/reports/tr14/tr14-19.html>
  *
- * This library has been updated according to Revision 30, for
- * Unicode 6.2.0:
- *      <URL:http://www.unicode.org/reports/tr14/tr14-30.html>
+ * This library has been updated according to Revision 33, for
+ * Unicode 7.0.0:
+ *      <URL:http://www.unicode.org/reports/tr14/tr14-33.html>
  *
  * The Unicode Terms of Use are available at
  *      <URL:http://www.unicode.org/copyright.html>
@@ -43,7 +43,7 @@
  *
  * Header file for the line breaking algorithm.
  *
- * @version 2.2, 2012/10/06
+ * @version 2.4, 2015/04/18
  * @author  Wu Yongwei
  */
 
@@ -51,21 +51,12 @@
 #define LINEBREAK_H
 
 #include <stddef.h>
+#include "unibreakbase.h"
 
 #ifdef __cplusplus
 extern "C" {
 #endif
 
-#define LINEBREAK_VERSION   0x0202  /**< Version of the library linebreak */
-extern const int linebreak_version;
-
-#ifndef LINEBREAK_UTF_TYPES_DEFINED
-#define LINEBREAK_UTF_TYPES_DEFINED
-typedef unsigned char   utf8_t;     /**< Type for UTF-8 data points */
-typedef unsigned short  utf16_t;    /**< Type for UTF-16 data points */
-typedef unsigned int    utf32_t;    /**< Type for UTF-32 data points */
-#endif
-
 #define LINEBREAK_MUSTBREAK     0   /**< Break is mandatory */
 #define LINEBREAK_ALLOWBREAK    1   /**< Break is allowed */
 #define LINEBREAK_NOBREAK       2   /**< No break is possible */
@@ -73,12 +64,12 @@ typedef unsigned int    utf32_t;    /**< Type for UTF-32 data points */
 
 void init_linebreak(void);
 void set_linebreaks_utf8(
-        const utf8_t *s, size_t len, const char* lang, char *brks);
+        const utf8_t *s, size_t len, const char *lang, char *brks);
 void set_linebreaks_utf16(
-        const utf16_t *s, size_t len, const char* lang, char *brks);
+        const utf16_t *s, size_t len, const char *lang, char *brks);
 void set_linebreaks_utf32(
-        const utf32_t *s, size_t len, const char* lang, char *brks);
-int is_line_breakable(utf32_t char1, utf32_t char2, const char* lang);
+        const utf32_t *s, size_t len, const char *lang, char *brks);
+int is_line_breakable(utf32_t char1, utf32_t char2, const char *lang);
 
 #ifdef __cplusplus
 }

diff --git a/third-party/libunibreak/linebreakdata.c b/third-party/libunibreak/linebreakdata.c
index 1038a14..d4bc8d8 100644 (file)
--- a/third-party/libunibreak/linebreakdata.c
+++ b/third-party/libunibreak/linebreakdata.c
@@ -3,7 +3,6 @@
 # Date: 2014-02-28, 23:15:00 GMT [KW, LI]
 */
 
-#include "linebreak.h"
 #include "linebreakdef.h"
 
 /** Default line breaking properties as from the Unicode Web site. */

diff --git a/third-party/libunibreak/linebreakdef.c b/third-party/libunibreak/linebreakdef.c
index 3455afd..41a7296 100644 (file)
--- a/third-party/libunibreak/linebreakdef.c
+++ b/third-party/libunibreak/linebreakdef.c
@@ -4,7 +4,7 @@
  * Line breaking in a Unicode sequence.  Designed to be used in a
  * generic text renderer.
  *
- * Copyright (C) 2008-2012 Wu Yongwei <wuyongwei at gmail dot com>
+ * Copyright (C) 2008-2015 Wu Yongwei <wuyongwei at gmail dot com>
  *
  * This software is provided 'as-is', without any express or implied
  * warranty.  In no event will the author be held liable for any damages
@@ -30,9 +30,9 @@
  * Unicode 5.0.0:
  *      <URL:http://www.unicode.org/reports/tr14/tr14-19.html>
  *
- * This library has been updated according to Revision 30, for
- * Unicode 6.2.0:
- *      <URL:http://www.unicode.org/reports/tr14/tr14-30.html>
+ * This library has been updated according to Revision 33, for
+ * Unicode 7.0.0:
+ *      <URL:http://www.unicode.org/reports/tr14/tr14-33.html>
  *
  * The Unicode Terms of Use are available at
  *      <URL:http://www.unicode.org/copyright.html>

diff --git a/third-party/libunibreak/linebreakdef.h b/third-party/libunibreak/linebreakdef.h
index d557aba..7600d0a 100644 (file)
--- a/third-party/libunibreak/linebreakdef.h
+++ b/third-party/libunibreak/linebreakdef.h
@@ -4,7 +4,7 @@
  * Line breaking in a Unicode sequence.  Designed to be used in a
  * generic text renderer.
  *
- * Copyright (C) 2008-2013 Wu Yongwei <wuyongwei at gmail dot com>
+ * Copyright (C) 2008-2015 Wu Yongwei <wuyongwei at gmail dot com>
  * Copyright (C) 2013 Petr Filipsky <philodej at gmail dot com>
  *
  * This software is provided 'as-is', without any express or implied
@@ -31,9 +31,9 @@
  * Unicode 5.0.0:
  *      <URL:http://www.unicode.org/reports/tr14/tr14-19.html>
  *
- * This library has been updated according to Revision 30, for
- * Unicode 6.2.0:
- *      <URL:http://www.unicode.org/reports/tr14/tr14-30.html>
+ * This library has been updated according to Revision 33, for
+ * Unicode 7.0.0:
+ *      <URL:http://www.unicode.org/reports/tr14/tr14-33.html>
  *
  * The Unicode Terms of Use are available at
  *      <URL:http://www.unicode.org/copyright.html>
@@ -45,16 +45,12 @@
  * Definitions of internal data structures, declarations of global
  * variables, and function prototypes for the line breaking algorithm.
  *
- * @version 2.4, 2013/11/10
+ * @version 2.6, 2015/04/18
  * @author  Wu Yongwei
  * @author  Petr Filipsky
  */
 
-/**
- * Constant value to mark the end of string.  It is not a valid Unicode
- * character.
- */
-#define EOS 0xFFFFFFFF
+#include "unibreakdef.h"
 
 /**
  * Line break classes.  This is a direct mapping of Table 1 of Unicode
@@ -143,28 +139,20 @@ struct LineBreakContext
     enum LineBreakClass lbcCur;     /**< Breaking class of current codepoint */
     enum LineBreakClass lbcNew;     /**< Breaking class of next codepoint */
     enum LineBreakClass lbcLast;    /**< Breaking class of last codepoint */
+    int fLb21aHebrew;               /**< Flag for Hebrew letters (LB21a) */
 };
 
-/**
- * Abstract function interface for #lb_get_next_char_utf8,
- * #lb_get_next_char_utf16, and #lb_get_next_char_utf32.
- */
-typedef utf32_t (*get_next_char_t)(const void *, size_t, size_t *);
-
 /* Declarations */
 extern struct LineBreakProperties lb_prop_default[];
 extern struct LineBreakPropertiesLang lb_prop_lang_map[];
 
 /* Function Prototype */
-utf32_t lb_get_next_char_utf8(const utf8_t *s, size_t len, size_t *ip);
-utf32_t lb_get_next_char_utf16(const utf16_t *s, size_t len, size_t *ip);
-utf32_t lb_get_next_char_utf32(const utf32_t *s, size_t len, size_t *ip);
 void lb_init_break_context(
-        struct LineBreakContext* lbpCtx,
+        struct LineBreakContext *lbpCtx,
         utf32_t ch,
-        const char* lang);
+        const char *lang);
 int lb_process_next_char(
-        struct LineBreakContext* lbpCtx,
+        struct LineBreakContext *lbpCtx,
         utf32_t ch);
 void set_linebreaks(
         const void *s,

diff --git a/third-party/libunibreak/unibreakbase.c b/third-party/libunibreak/unibreakbase.c
new file mode 100755 (executable)
index 0000000..dbe3a38
--- /dev/null
+++ b/third-party/libunibreak/unibreakbase.c
@@ -0,0 +1,41 @@
+/* vim: set expandtab tabstop=4 softtabstop=4 shiftwidth=4: */
+
+/*
+ * Break processing in a Unicode sequence.  Designed to be used in a
+ * generic text renderer.
+ *
+ * Copyright (C) 2015 Wu Yongwei <wuyongwei at gmail dot com>
+ *
+ * This software is provided 'as-is', without any express or implied
+ * warranty.  In no event will the author be held liable for any damages
+ * arising from the use of this software.
+ *
+ * Permission is granted to anyone to use this software for any purpose,
+ * including commercial applications, and to alter it and redistribute
+ * it freely, subject to the following restrictions:
+ *
+ * 1. The origin of this software must not be misrepresented; you must
+ *    not claim that you wrote the original software.  If you use this
+ *    software in a product, an acknowledgement in the product
+ *    documentation would be appreciated but is not required.
+ * 2. Altered source versions must be plainly marked as such, and must
+ *    not be misrepresented as being the original software.
+ * 3. This notice may not be removed or altered from any source
+ *    distribution.
+ */
+
+/**
+ * @file    unibreakbase.c
+ *
+ * Definition of basic libunibreak information.
+ *
+ * @version 1.0, 2015/04/18
+ * @author  Wu Yongwei
+ */
+
+#include "unibreakbase.h"
+
+/**
+ * Version number of the library.
+ */
+const int unibreak_version = UNIBREAK_VERSION;

diff --git a/third-party/libunibreak/unibreakbase.h b/third-party/libunibreak/unibreakbase.h
new file mode 100755 (executable)
index 0000000..76b35e6
--- /dev/null
+++ b/third-party/libunibreak/unibreakbase.h
@@ -0,0 +1,73 @@
+/* vim: set expandtab tabstop=4 softtabstop=4 shiftwidth=4: */
+
+/*
+ * Break processing in a Unicode sequence.  Designed to be used in a
+ * generic text renderer.
+ *
+ * Copyright (C) 2015 Wu Yongwei <wuyongwei at gmail dot com>
+ *
+ * This software is provided 'as-is', without any express or implied
+ * warranty.  In no event will the author be held liable for any damages
+ * arising from the use of this software.
+ *
+ * Permission is granted to anyone to use this software for any purpose,
+ * including commercial applications, and to alter it and redistribute
+ * it freely, subject to the following restrictions:
+ *
+ * 1. The origin of this software must not be misrepresented; you must
+ *    not claim that you wrote the original software.  If you use this
+ *    software in a product, an acknowledgement in the product
+ *    documentation would be appreciated but is not required.
+ * 2. Altered source versions must be plainly marked as such, and must
+ *    not be misrepresented as being the original software.
+ * 3. This notice may not be removed or altered from any source
+ *    distribution.
+ *
+ * The main reference is Unicode Standard Annex 14 (UAX #14):
+ *      <URL:http://www.unicode.org/reports/tr14/>
+ *
+ * When this library was designed, this annex was at Revision 19, for
+ * Unicode 5.0.0:
+ *      <URL:http://www.unicode.org/reports/tr14/tr14-19.html>
+ *
+ * This library has been updated according to Revision 33, for
+ * Unicode 7.0.0:
+ *      <URL:http://www.unicode.org/reports/tr14/tr14-33.html>
+ *
+ * The Unicode Terms of Use are available at
+ *      <URL:http://www.unicode.org/copyright.html>
+ */
+
+/**
+ * @file    unibreakbase.h
+ *
+ * Header file for common definitions in the libunibreak library.
+ *
+ * @version 1.0, 2015/04/18
+ * @author  Wu Yongwei
+ */
+
+#ifndef UNIBREAKBASE_H
+#define UNIBREAKBASE_H
+
+#include <stddef.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#define UNIBREAK_VERSION   0x0300      /**< Version of the library linebreak */
+extern const int unibreak_version;
+
+#ifndef UNIBREAK_UTF_TYPES_DEFINED
+#define UNIBREAK_UTF_TYPES_DEFINED
+typedef unsigned char   utf8_t;     /**< Type for UTF-8 data points */
+typedef unsigned short  utf16_t;    /**< Type for UTF-16 data points */
+typedef unsigned int    utf32_t;    /**< Type for UTF-32 data points */
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* UNIBREAKBASE_H */

diff --git a/third-party/libunibreak/unibreakdef.c b/third-party/libunibreak/unibreakdef.c
new file mode 100755 (executable)
index 0000000..2647b61
--- /dev/null
+++ b/third-party/libunibreak/unibreakdef.c
@@ -0,0 +1,159 @@
+/* vim: set expandtab tabstop=4 softtabstop=4 shiftwidth=4: */
+
+/*
+ * Break processing in a Unicode sequence.  Designed to be used in a
+ * generic text renderer.
+ *
+ * Copyright (C) 2015 Wu Yongwei <wuyongwei at gmail dot com>
+ *
+ * This software is provided 'as-is', without any express or implied
+ * warranty.  In no event will the author be held liable for any damages
+ * arising from the use of this software.
+ *
+ * Permission is granted to anyone to use this software for any purpose,
+ * including commercial applications, and to alter it and redistribute
+ * it freely, subject to the following restrictions:
+ *
+ * 1. The origin of this software must not be misrepresented; you must
+ *    not claim that you wrote the original software.  If you use this
+ *    software in a product, an acknowledgement in the product
+ *    documentation would be appreciated but is not required.
+ * 2. Altered source versions must be plainly marked as such, and must
+ *    not be misrepresented as being the original software.
+ * 3. This notice may not be removed or altered from any source
+ *    distribution.
+ */
+
+/**
+ * @file    unibreakdef.c
+ *
+ * Definition of utility functions used by the libunibreak library.
+ *
+ * @version 1.0, 2015/04/18
+ * @author  Wu Yongwei
+ */
+
+#include <assert.h>
+#include <stddef.h>
+#include "unibreakdef.h"
+
+/**
+ * Gets the next Unicode character in a UTF-8 sequence.  The index will
+ * be advanced to the next complete character, unless the end of string
+ * is reached in the middle of a UTF-8 sequence.
+ *
+ * @param[in]     s    input UTF-8 string
+ * @param[in]     len  length of the string in bytes
+ * @param[in,out] ip   pointer to the index
+ * @return             the Unicode character beginning at the index; or
+ *                     #EOS if end of input is encountered
+ */
+utf32_t ub_get_next_char_utf8(
+        const utf8_t *s,
+        size_t len,
+        size_t *ip)
+{
+    utf8_t ch;
+    utf32_t res;
+
+    assert(*ip <= len);
+    if (*ip == len)
+        return EOS;
+    ch = s[*ip];
+
+    if (ch < 0xC2 || ch > 0xF4)
+    {   /* One-byte sequence, tail (should not occur), or invalid */
+        *ip += 1;
+        return ch;
+    }
+    else if (ch < 0xE0)
+    {   /* Two-byte sequence */
+        if (*ip + 2 > len)
+            return EOS;
+        res = ((ch & 0x1F) << 6) + (s[*ip + 1] & 0x3F);
+        *ip += 2;
+        return res;
+    }
+    else if (ch < 0xF0)
+    {   /* Three-byte sequence */
+        if (*ip + 3 > len)
+            return EOS;
+        res = ((ch & 0x0F) << 12) +
+              ((s[*ip + 1] & 0x3F) << 6) +
+              ((s[*ip + 2] & 0x3F));
+        *ip += 3;
+        return res;
+    }
+    else
+    {   /* Four-byte sequence */
+        if (*ip + 4 > len)
+            return EOS;
+        res = ((ch & 0x07) << 18) +
+              ((s[*ip + 1] & 0x3F) << 12) +
+              ((s[*ip + 2] & 0x3F) << 6) +
+              ((s[*ip + 3] & 0x3F));
+        *ip += 4;
+        return res;
+    }
+}
+
+/**
+ * Gets the next Unicode character in a UTF-16 sequence.  The index will
+ * be advanced to the next complete character, unless the end of string
+ * is reached in the middle of a UTF-16 surrogate pair.
+ *
+ * @param[in]     s    input UTF-16 string
+ * @param[in]     len  length of the string in words
+ * @param[in,out] ip   pointer to the index
+ * @return             the Unicode character beginning at the index; or
+ *                     #EOS if end of input is encountered
+ */
+utf32_t ub_get_next_char_utf16(
+        const utf16_t *s,
+        size_t len,
+        size_t *ip)
+{
+    utf16_t ch;
+
+    assert(*ip <= len);
+    if (*ip == len)
+        return EOS;
+    ch = s[(*ip)++];
+
+    if (ch < 0xD800 || ch > 0xDBFF)
+    {   /* If the character is not a high surrogate */
+        return ch;
+    }
+    if (*ip == len)
+    {   /* If the input ends here (an error) */
+        --(*ip);
+        return EOS;
+    }
+    if (s[*ip] < 0xDC00 || s[*ip] > 0xDFFF)
+    {   /* If the next character is not the low surrogate (an error) */
+        return ch;
+    }
+    /* Return the constructed character and advance the index again */
+    return (((utf32_t)ch & 0x3FF) << 10) + (s[(*ip)++] & 0x3FF) + 0x10000;
+}
+
+/**
+ * Gets the next Unicode character in a UTF-32 sequence.  The index will
+ * be advanced to the next character.
+ *
+ * @param[in]     s    input UTF-32 string
+ * @param[in]     len  length of the string in dwords
+ * @param[in,out] ip   pointer to the index
+ * @return             the Unicode character beginning at the index; or
+ *                     #EOS if end of input is encountered
+ */
+utf32_t ub_get_next_char_utf32(
+        const utf32_t *s,
+        size_t len,
+        size_t *ip)
+{
+    assert(*ip <= len);
+    if (*ip == len)
+        return EOS;
+    return s[(*ip)++];
+}

diff --git a/third-party/libunibreak/unibreakdef.h b/third-party/libunibreak/unibreakdef.h
new file mode 100755 (executable)
index 0000000..b823e50
--- /dev/null
+++ b/third-party/libunibreak/unibreakdef.h
@@ -0,0 +1,80 @@
+/* vim: set expandtab tabstop=4 softtabstop=4 shiftwidth=4: */
+
+/*
+ * Break processing in a Unicode sequence.  Designed to be used in a
+ * generic text renderer.
+ *
+ * Copyright (C) 2015 Wu Yongwei <wuyongwei at gmail dot com>
+ *
+ * This software is provided 'as-is', without any express or implied
+ * warranty.  In no event will the author be held liable for any damages
+ * arising from the use of this software.
+ *
+ * Permission is granted to anyone to use this software for any purpose,
+ * including commercial applications, and to alter it and redistribute
+ * it freely, subject to the following restrictions:
+ *
+ * 1. The origin of this software must not be misrepresented; you must
+ *    not claim that you wrote the original software.  If you use this
+ *    software in a product, an acknowledgement in the product
+ *    documentation would be appreciated but is not required.
+ * 2. Altered source versions must be plainly marked as such, and must
+ *    not be misrepresented as being the original software.
+ * 3. This notice may not be removed or altered from any source
+ *    distribution.
+ *
+ * The main reference is Unicode Standard Annex 14 (UAX #14):
+ *      <URL:http://www.unicode.org/reports/tr14/>
+ *
+ * When this library was designed, this annex was at Revision 19, for
+ * Unicode 5.0.0:
+ *      <URL:http://www.unicode.org/reports/tr14/tr14-19.html>
+ *
+ * This library has been updated according to Revision 33, for
+ * Unicode 7.0.0:
+ *      <URL:http://www.unicode.org/reports/tr14/tr14-33.html>
+ *
+ * The Unicode Terms of Use are available at
+ *      <URL:http://www.unicode.org/copyright.html>
+ */
+
+/**
+ * @file    unibreakdef.h
+ *
+ * Header file for private definitions in the libunibreak library.
+ *
+ * @version 1.1, 2015/04/19
+ * @author  Wu Yongwei
+ */
+
+#ifndef UNIBREAKDEF_H
+#define UNIBREAKDEF_H
+
+#include "unibreakbase.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * Constant value to mark the end of string.  It is not a valid Unicode
+ * character.
+ */
+#define EOS 0xFFFFFFFF
+
+/**
+ * Abstract function interface for #ub_get_next_char_utf8,
+ * #ub_get_next_char_utf16, and #ub_get_next_char_utf32.
+ */
+typedef utf32_t (*get_next_char_t)(const void *, size_t, size_t *);
+
+/* Function Prototype */
+utf32_t ub_get_next_char_utf8(const utf8_t *s, size_t len, size_t *ip);
+utf32_t ub_get_next_char_utf16(const utf16_t *s, size_t len, size_t *ip);
+utf32_t ub_get_next_char_utf32(const utf32_t *s, size_t len, size_t *ip);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* UNIBREAKDEF_H */

diff --git a/third-party/libunibreak/wordbreak.c b/third-party/libunibreak/wordbreak.c
index e67a1f8..d7d5a42 100644 (file)
--- a/third-party/libunibreak/wordbreak.c
+++ b/third-party/libunibreak/wordbreak.c
@@ -4,7 +4,7 @@
  * Word breaking in a Unicode sequence.  Designed to be used in a
  * generic text renderer.
  *
- * Copyright (C) 2013 Tom Hacohen <tom at stosb dot com>
+ * Copyright (C) 2013-2015 Tom Hacohen <tom at stosb dot com>
  *
  * This software is provided 'as-is', without any express or implied
  * warranty.  In no event will the author be held liable for any damages
@@ -30,9 +30,9 @@
  * Unicode 6.0.0:
  *      <URL:http://www.unicode.org/reports/tr29/tr29-17.html>
  *
- * This library has been updated according to Revision 21, for
- * Unicode 6.2.0:
- *      <URL:http://www.unicode.org/reports/tr29/tr29-21.html>
+ * This library has been updated according to Revision 25, for
+ * Unicode 7.0.0:
+ *      <URL:http://www.unicode.org/reports/tr29/tr29-25.html>
  *
  * The Unicode Terms of Use are available at
  *      <URL:http://www.unicode.org/copyright.html>
@@ -44,16 +44,14 @@
  * Implementation of the word breaking algorithm as described in Unicode
  * Standard Annex 29.
  *
- * @version 2.4, 2013/09/28
+ * @version 2.6, 2015/04/18
  * @author  Tom Hacohen
  */
 
 #include <assert.h>
 #include <stddef.h>
 #include <string.h>
-#include "linebreak.h"
-#include "linebreakdef.h"
-
+#include "unibreakdef.h"
 #include "wordbreak.h"
 #include "wordbreakdata.c"
 
@@ -256,8 +254,24 @@ static void set_wordbreaks(
             posLast = posCur;
             break;
 
+        case WBP_Hebrew_Letter:
         case WBP_ALetter:
-            if ((wbcSeqStart == WBP_ALetter) || /* WB5,6,7 */
+            if ((wbcSeqStart == WBP_Hebrew_Letter) &&
+                    (wbcLast == WBP_Double_Quote)) /* WB7b,c */
+            {
+               if (wbcCur == WBP_Hebrew_Letter)
+                 {
+                     set_brks_to(s, brks, posLast, posCur, len,
+                             WORDBREAK_NOBREAK, get_next_char);
+                 }
+               else
+                 {
+                     set_brks_to(s, brks, posLast, posCur, len,
+                             WORDBREAK_BREAK, get_next_char);
+                 }
+            }
+            else if (((wbcSeqStart == WBP_ALetter) ||
+                        (wbcSeqStart == WBP_Hebrew_Letter)) || /* WB5,6,7 */
                     (wbcLast == WBP_Numeric) || /* WB10 */
                     (wbcSeqStart == WBP_ExtendNumLet)) /* WB13b */
             {
@@ -274,8 +288,18 @@ static void set_wordbreaks(
             posLast = posCur;
             break;
 
+        case WBP_Single_Quote:
+            if (wbcLast == WBP_Hebrew_Letter) /* WB7a */
+            {
+                set_brks_to(s, brks, posLast, posCur, len,
+                            WORDBREAK_NOBREAK, get_next_char);
+                wbcSeqStart = wbcCur;
+                posLast = posCur;
+            }
+            /* No break on purpose */
         case WBP_MidNumLet:
-            if ((wbcLast == WBP_ALetter) || /* WB6,7 */
+            if (((wbcLast == WBP_ALetter) ||
+                        (wbcLast == WBP_Hebrew_Letter)) || /* WB6,7 */
                     (wbcLast == WBP_Numeric)) /* WB11,12 */
             {
                 /* Go on */
@@ -290,7 +314,8 @@ static void set_wordbreaks(
             break;
 
         case WBP_MidLetter:
-            if (wbcLast == WBP_ALetter) /* WB6,7 */
+            if ((wbcLast == WBP_ALetter) ||
+                    (wbcLast == WBP_Hebrew_Letter)) /* WB6,7 */
             {
                 /* Go on */
             }
@@ -319,7 +344,8 @@ static void set_wordbreaks(
 
         case WBP_Numeric:
             if ((wbcSeqStart == WBP_Numeric) || /* WB8,11,12 */
-                    (wbcLast == WBP_ALetter) || /* WB9 */
+                    ((wbcLast == WBP_ALetter) ||
+                     (wbcLast == WBP_Hebrew_Letter)) || /* WB9 */
                     (wbcSeqStart == WBP_ExtendNumLet)) /* WB13b */
             {
                 set_brks_to(s, brks, posLast, posCur, len,
@@ -339,6 +365,7 @@ static void set_wordbreaks(
             /* WB13a,13b */
             if ((wbcSeqStart == wbcLast) &&
                 ((wbcLast == WBP_ALetter) ||
+                 (wbcLast == WBP_Hebrew_Letter) ||
                  (wbcLast == WBP_Numeric) ||
                  (wbcLast == WBP_Katakana) ||
                  (wbcLast == WBP_ExtendNumLet)))
@@ -356,9 +383,9 @@ static void set_wordbreaks(
             posLast = posCur;
             break;
 
-        case WBP_Regional:
+        case WBP_Regional_Indicator:
             /* WB13c */
-            if (wbcSeqStart == WBP_Regional)
+            if (wbcSeqStart == WBP_Regional_Indicator)
             {
                 set_brks_to(s, brks, posLast, posCur, len,
                             WORDBREAK_NOBREAK, get_next_char);
@@ -367,6 +394,20 @@ static void set_wordbreaks(
             posLast = posCur;
             break;
 
+        case WBP_Double_Quote:
+            if (wbcLast == WBP_Hebrew_Letter) /* WB7b,c */
+            {
+               /* Go on */
+            }
+            else
+            {
+                set_brks_to(s, brks, posLast, posCur, len,
+                            WORDBREAK_BREAK, get_next_char);
+                wbcSeqStart = wbcCur;
+                posLast = posCur;
+            }
+            break;
+
         case WBP_Any:
             /* Allow breaks and reset */
             set_brks_to(s, brks, posLast, posCur, len,
@@ -408,7 +449,7 @@ void set_wordbreaks_utf8(
         char *brks)
 {
     set_wordbreaks(s, len, lang, brks,
-                   (get_next_char_t)lb_get_next_char_utf8);
+                   (get_next_char_t)ub_get_next_char_utf8);
 }
 
 /**
@@ -428,7 +469,7 @@ void set_wordbreaks_utf16(
         char *brks)
 {
     set_wordbreaks(s, len, lang, brks,
-                   (get_next_char_t)lb_get_next_char_utf16);
+                   (get_next_char_t)ub_get_next_char_utf16);
 }
 
 /**
@@ -448,5 +489,5 @@ void set_wordbreaks_utf32(
         char *brks)
 {
     set_wordbreaks(s, len, lang, brks,
-                   (get_next_char_t)lb_get_next_char_utf32);
+                   (get_next_char_t)ub_get_next_char_utf32);
 }

diff --git a/third-party/libunibreak/wordbreak.h b/third-party/libunibreak/wordbreak.h
index cd2bf2c..360953f 100644 (file)
--- a/third-party/libunibreak/wordbreak.h
+++ b/third-party/libunibreak/wordbreak.h
@@ -4,7 +4,7 @@
  * Word breaking in a Unicode sequence.  Designed to be used in a
  * generic text renderer.
  *
- * Copyright (C) 2013 Tom Hacohen <tom at stosb dot com>
+ * Copyright (C) 2013-2015 Tom Hacohen <tom at stosb dot com>
  *
  * This software is provided 'as-is', without any express or implied
  * warranty.  In no event will the author be held liable for any damages
@@ -30,9 +30,9 @@
  * Unicode 6.0.0:
  *      <URL:http://www.unicode.org/reports/tr29/tr29-17.html>
  *
- * This library has been updated according to Revision 21, for
- * Unicode 6.2.0:
- *      <URL:http://www.unicode.org/reports/tr29/tr29-21.html>
+ * This library has been updated according to Revision 25, for
+ * Unicode 7.0.0:
+ *      <URL:http://www.unicode.org/reports/tr29/tr29-25.html>
  *
  * The Unicode Terms of Use are available at
  *      <URL:http://www.unicode.org/copyright.html>
@@ -43,7 +43,7 @@
  *
  * Header file for the word breaking (segmentation) algorithm.
  *
- * @version 2.3, 2013/09/28
+ * @version 2.5, 2015/04/18
  * @author  Tom Hacohen
  */
 
@@ -51,7 +51,7 @@
 #define WORDBREAK_H
 
 #include <stddef.h>
-#include "linebreak.h"
+#include "unibreakbase.h"
 
 #ifdef __cplusplus
 extern "C" {

diff --git a/third-party/libunibreak/wordbreakdata.c b/third-party/libunibreak/wordbreakdata.c
index fe5afe3..c6d5694 100644 (file)
--- a/third-party/libunibreak/wordbreakdata.c
+++ b/third-party/libunibreak/wordbreakdata.c
@@ -1,16 +1,16 @@
 /* The content of this file is generated from:
-# WordBreakProperty-6.2.0.txt
-# Date: 2012-08-13, 19:12:09 GMT [MD]
+# WordBreakProperty-7.0.0.txt
+# Date: 2014-02-19, 15:51:39 GMT [MD]
 */
 
-#include "linebreak.h"
 #include "wordbreakdef.h"
 
 static struct WordBreakProperties wb_prop_default[] = {
        {0x000A, 0x000A, WBP_LF},
        {0x000B, 0x000C, WBP_Newline},
        {0x000D, 0x000D, WBP_CR},
-       {0x0027, 0x0027, WBP_MidNumLet},
+       {0x0022, 0x0022, WBP_Double_Quote},
+       {0x0027, 0x0027, WBP_Single_Quote},
        {0x002C, 0x002C, WBP_MidNum},
        {0x002E, 0x002E, WBP_MidNumLet},
        {0x0030, 0x0039, WBP_Numeric},
@@ -36,6 +36,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x0295, 0x02AF, WBP_ALetter},
        {0x02B0, 0x02C1, WBP_ALetter},
        {0x02C6, 0x02D1, WBP_ALetter},
+       {0x02D7, 0x02D7, WBP_MidLetter},
        {0x02E0, 0x02E4, WBP_ALetter},
        {0x02EC, 0x02EC, WBP_ALetter},
        {0x02EE, 0x02EE, WBP_ALetter},
@@ -46,6 +47,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x037A, 0x037A, WBP_ALetter},
        {0x037B, 0x037D, WBP_ALetter},
        {0x037E, 0x037E, WBP_MidNum},
+       {0x037F, 0x037F, WBP_ALetter},
        {0x0386, 0x0386, WBP_ALetter},
        {0x0387, 0x0387, WBP_MidLetter},
        {0x0388, 0x038A, WBP_ALetter},
@@ -55,7 +57,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x03F7, 0x0481, WBP_ALetter},
        {0x0483, 0x0487, WBP_Extend},
        {0x0488, 0x0489, WBP_Extend},
-       {0x048A, 0x0527, WBP_ALetter},
+       {0x048A, 0x052F, WBP_ALetter},
        {0x0531, 0x0556, WBP_ALetter},
        {0x0559, 0x0559, WBP_ALetter},
        {0x0561, 0x0587, WBP_ALetter},
@@ -65,13 +67,14 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x05C1, 0x05C2, WBP_Extend},
        {0x05C4, 0x05C5, WBP_Extend},
        {0x05C7, 0x05C7, WBP_Extend},
-       {0x05D0, 0x05EA, WBP_ALetter},
-       {0x05F0, 0x05F2, WBP_ALetter},
+       {0x05D0, 0x05EA, WBP_Hebrew_Letter},
+       {0x05F0, 0x05F2, WBP_Hebrew_Letter},
        {0x05F3, 0x05F3, WBP_ALetter},
        {0x05F4, 0x05F4, WBP_MidLetter},
-       {0x0600, 0x0604, WBP_Format},
+       {0x0600, 0x0605, WBP_Format},
        {0x060C, 0x060D, WBP_MidNum},
        {0x0610, 0x061A, WBP_Extend},
+       {0x061C, 0x061C, WBP_Format},
        {0x0620, 0x063F, WBP_ALetter},
        {0x0640, 0x0640, WBP_ALetter},
        {0x0641, 0x064A, WBP_ALetter},
@@ -117,10 +120,8 @@ 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},
+       {0x08A0, 0x08B2, WBP_ALetter},
+       {0x08E4, 0x0902, WBP_Extend},
        {0x0903, 0x0903, WBP_Extend},
        {0x0904, 0x0939, WBP_ALetter},
        {0x093A, 0x093A, WBP_Extend},
@@ -138,8 +139,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x0962, 0x0963, WBP_Extend},
        {0x0966, 0x096F, WBP_Numeric},
        {0x0971, 0x0971, WBP_ALetter},
-       {0x0972, 0x0977, WBP_ALetter},
-       {0x0979, 0x097F, WBP_ALetter},
+       {0x0972, 0x0980, WBP_ALetter},
        {0x0981, 0x0981, WBP_Extend},
        {0x0982, 0x0983, WBP_Extend},
        {0x0985, 0x098C, WBP_ALetter},
@@ -247,12 +247,12 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x0BD0, 0x0BD0, WBP_ALetter},
        {0x0BD7, 0x0BD7, WBP_Extend},
        {0x0BE6, 0x0BEF, WBP_Numeric},
+       {0x0C00, 0x0C00, WBP_Extend},
        {0x0C01, 0x0C03, WBP_Extend},
        {0x0C05, 0x0C0C, WBP_ALetter},
        {0x0C0E, 0x0C10, WBP_ALetter},
        {0x0C12, 0x0C28, WBP_ALetter},
-       {0x0C2A, 0x0C33, WBP_ALetter},
-       {0x0C35, 0x0C39, WBP_ALetter},
+       {0x0C2A, 0x0C39, WBP_ALetter},
        {0x0C3D, 0x0C3D, WBP_ALetter},
        {0x0C3E, 0x0C40, WBP_Extend},
        {0x0C41, 0x0C44, WBP_Extend},
@@ -263,6 +263,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x0C60, 0x0C61, WBP_ALetter},
        {0x0C62, 0x0C63, WBP_Extend},
        {0x0C66, 0x0C6F, WBP_Numeric},
+       {0x0C81, 0x0C81, WBP_Extend},
        {0x0C82, 0x0C83, WBP_Extend},
        {0x0C85, 0x0C8C, WBP_ALetter},
        {0x0C8E, 0x0C90, WBP_ALetter},
@@ -284,6 +285,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x0CE2, 0x0CE3, WBP_Extend},
        {0x0CE6, 0x0CEF, WBP_Numeric},
        {0x0CF1, 0x0CF2, WBP_ALetter},
+       {0x0D01, 0x0D01, WBP_Extend},
        {0x0D02, 0x0D03, WBP_Extend},
        {0x0D05, 0x0D0C, WBP_ALetter},
        {0x0D0E, 0x0D10, WBP_ALetter},
@@ -311,6 +313,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x0DD2, 0x0DD4, WBP_Extend},
        {0x0DD6, 0x0DD6, WBP_Extend},
        {0x0DD8, 0x0DDF, WBP_Extend},
+       {0x0DE6, 0x0DEF, WBP_Numeric},
        {0x0DF2, 0x0DF3, WBP_Extend},
        {0x0E31, 0x0E31, WBP_Extend},
        {0x0E34, 0x0E3A, WBP_Extend},
@@ -391,6 +394,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x1681, 0x169A, WBP_ALetter},
        {0x16A0, 0x16EA, WBP_ALetter},
        {0x16EE, 0x16F0, WBP_ALetter},
+       {0x16F1, 0x16F8, WBP_ALetter},
        {0x1700, 0x170C, WBP_ALetter},
        {0x170E, 0x1711, WBP_ALetter},
        {0x1712, 0x1714, WBP_Extend},
@@ -411,6 +415,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x17DD, 0x17DD, WBP_Extend},
        {0x17E0, 0x17E9, WBP_Numeric},
        {0x180B, 0x180D, WBP_Extend},
+       {0x180E, 0x180E, WBP_Format},
        {0x1810, 0x1819, WBP_Numeric},
        {0x1820, 0x1842, WBP_ALetter},
        {0x1843, 0x1843, WBP_ALetter},
@@ -419,7 +424,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x18A9, 0x18A9, WBP_Extend},
        {0x18AA, 0x18AA, WBP_ALetter},
        {0x18B0, 0x18F5, WBP_ALetter},
-       {0x1900, 0x191C, WBP_ALetter},
+       {0x1900, 0x191E, WBP_ALetter},
        {0x1920, 0x1922, WBP_Extend},
        {0x1923, 0x1926, WBP_Extend},
        {0x1927, 0x1928, WBP_Extend},
@@ -434,7 +439,8 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x19D0, 0x19D9, WBP_Numeric},
        {0x1A00, 0x1A16, WBP_ALetter},
        {0x1A17, 0x1A18, WBP_Extend},
-       {0x1A19, 0x1A1B, WBP_Extend},
+       {0x1A19, 0x1A1A, WBP_Extend},
+       {0x1A1B, 0x1A1B, WBP_Extend},
        {0x1A55, 0x1A55, WBP_Extend},
        {0x1A56, 0x1A56, WBP_Extend},
        {0x1A57, 0x1A57, WBP_Extend},
@@ -449,6 +455,8 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x1A7F, 0x1A7F, WBP_Extend},
        {0x1A80, 0x1A89, WBP_Numeric},
        {0x1A90, 0x1A99, WBP_Numeric},
+       {0x1AB0, 0x1ABD, WBP_Extend},
+       {0x1ABE, 0x1ABE, WBP_Extend},
        {0x1B00, 0x1B03, WBP_Extend},
        {0x1B04, 0x1B04, WBP_Extend},
        {0x1B05, 0x1B33, WBP_ALetter},
@@ -471,8 +479,7 @@ 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},
+       {0x1BAB, 0x1BAD, WBP_Extend},
        {0x1BAE, 0x1BAF, WBP_ALetter},
        {0x1BB0, 0x1BB9, WBP_Numeric},
        {0x1BBA, 0x1BE5, WBP_ALetter},
@@ -504,13 +511,14 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x1CF2, 0x1CF3, WBP_Extend},
        {0x1CF4, 0x1CF4, WBP_Extend},
        {0x1CF5, 0x1CF6, WBP_ALetter},
+       {0x1CF8, 0x1CF9, WBP_Extend},
        {0x1D00, 0x1D2B, WBP_ALetter},
        {0x1D2C, 0x1D6A, WBP_ALetter},
        {0x1D6B, 0x1D77, WBP_ALetter},
        {0x1D78, 0x1D78, WBP_ALetter},
        {0x1D79, 0x1D9A, WBP_ALetter},
        {0x1D9B, 0x1DBF, WBP_ALetter},
-       {0x1DC0, 0x1DE6, WBP_Extend},
+       {0x1DC0, 0x1DF5, WBP_Extend},
        {0x1DFC, 0x1DFF, WBP_Extend},
        {0x1E00, 0x1F15, WBP_ALetter},
        {0x1F18, 0x1F1D, WBP_ALetter},
@@ -544,7 +552,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x2044, 0x2044, WBP_MidNum},
        {0x2054, 0x2054, WBP_ExtendNumLet},
        {0x2060, 0x2064, WBP_Format},
-       {0x206A, 0x206F, WBP_Format},
+       {0x2066, 0x206F, WBP_Format},
        {0x2071, 0x2071, WBP_ALetter},
        {0x207F, 0x207F, WBP_ALetter},
        {0x2090, 0x209C, WBP_ALetter},
@@ -631,7 +639,8 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0xA670, 0xA672, WBP_Extend},
        {0xA674, 0xA67D, WBP_Extend},
        {0xA67F, 0xA67F, WBP_ALetter},
-       {0xA680, 0xA697, WBP_ALetter},
+       {0xA680, 0xA69B, WBP_ALetter},
+       {0xA69C, 0xA69D, WBP_ALetter},
        {0xA69F, 0xA69F, WBP_Extend},
        {0xA6A0, 0xA6E5, WBP_ALetter},
        {0xA6E6, 0xA6EF, WBP_ALetter},
@@ -642,8 +651,9 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0xA771, 0xA787, WBP_ALetter},
        {0xA788, 0xA788, WBP_ALetter},
        {0xA78B, 0xA78E, WBP_ALetter},
-       {0xA790, 0xA793, WBP_ALetter},
-       {0xA7A0, 0xA7AA, WBP_ALetter},
+       {0xA790, 0xA7AD, WBP_ALetter},
+       {0xA7B0, 0xA7B1, WBP_ALetter},
+       {0xA7F7, 0xA7F7, WBP_ALetter},
        {0xA7F8, 0xA7F9, WBP_ALetter},
        {0xA7FA, 0xA7FA, WBP_ALetter},
        {0xA7FB, 0xA801, WBP_ALetter},
@@ -683,6 +693,8 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0xA9BD, 0xA9C0, WBP_Extend},
        {0xA9CF, 0xA9CF, WBP_ALetter},
        {0xA9D0, 0xA9D9, WBP_Numeric},
+       {0xA9E5, 0xA9E5, WBP_Extend},
+       {0xA9F0, 0xA9F9, WBP_Numeric},
        {0xAA00, 0xAA28, WBP_ALetter},
        {0xAA29, 0xAA2E, WBP_Extend},
        {0xAA2F, 0xAA30, WBP_Extend},
@@ -696,6 +708,8 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0xAA4D, 0xAA4D, WBP_Extend},
        {0xAA50, 0xAA59, WBP_Numeric},
        {0xAA7B, 0xAA7B, WBP_Extend},
+       {0xAA7C, 0xAA7C, WBP_Extend},
+       {0xAA7D, 0xAA7D, WBP_Extend},
        {0xAAB0, 0xAAB0, WBP_Extend},
        {0xAAB2, 0xAAB4, WBP_Extend},
        {0xAAB7, 0xAAB8, WBP_Extend},
@@ -714,6 +728,9 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0xAB11, 0xAB16, WBP_ALetter},
        {0xAB20, 0xAB26, WBP_ALetter},
        {0xAB28, 0xAB2E, WBP_ALetter},
+       {0xAB30, 0xAB5A, WBP_ALetter},
+       {0xAB5C, 0xAB5F, WBP_ALetter},
+       {0xAB64, 0xAB65, WBP_ALetter},
        {0xABC0, 0xABE2, WBP_ALetter},
        {0xABE3, 0xABE4, WBP_Extend},
        {0xABE5, 0xABE5, WBP_Extend},
@@ -728,15 +745,16 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0xD7CB, 0xD7FB, WBP_ALetter},
        {0xFB00, 0xFB06, WBP_ALetter},
        {0xFB13, 0xFB17, WBP_ALetter},
-       {0xFB1D, 0xFB1D, WBP_ALetter},
+       {0xFB1D, 0xFB1D, WBP_Hebrew_Letter},
        {0xFB1E, 0xFB1E, WBP_Extend},
-       {0xFB1F, 0xFB28, WBP_ALetter},
-       {0xFB2A, 0xFB36, WBP_ALetter},
-       {0xFB38, 0xFB3C, WBP_ALetter},
-       {0xFB3E, 0xFB3E, WBP_ALetter},
-       {0xFB40, 0xFB41, WBP_ALetter},
-       {0xFB43, 0xFB44, WBP_ALetter},
-       {0xFB46, 0xFBB1, WBP_ALetter},
+       {0xFB1F, 0xFB28, WBP_Hebrew_Letter},
+       {0xFB2A, 0xFB36, WBP_Hebrew_Letter},
+       {0xFB38, 0xFB3C, WBP_Hebrew_Letter},
+       {0xFB3E, 0xFB3E, WBP_Hebrew_Letter},
+       {0xFB40, 0xFB41, WBP_Hebrew_Letter},
+       {0xFB43, 0xFB44, WBP_Hebrew_Letter},
+       {0xFB46, 0xFB4F, WBP_Hebrew_Letter},
+       {0xFB50, 0xFBB1, WBP_ALetter},
        {0xFBD3, 0xFD3D, WBP_ALetter},
        {0xFD50, 0xFD8F, WBP_ALetter},
        {0xFD92, 0xFDC7, WBP_ALetter},
@@ -745,7 +763,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0xFE10, 0xFE10, WBP_MidNum},
        {0xFE13, 0xFE13, WBP_MidLetter},
        {0xFE14, 0xFE14, WBP_MidNum},
-       {0xFE20, 0xFE26, WBP_Extend},
+       {0xFE20, 0xFE2D, WBP_Extend},
        {0xFE33, 0xFE34, WBP_ExtendNumLet},
        {0xFE4D, 0xFE4F, WBP_ExtendNumLet},
        {0xFE50, 0xFE50, WBP_MidNum},
@@ -784,11 +802,14 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x101FD, 0x101FD, WBP_Extend},
        {0x10280, 0x1029C, WBP_ALetter},
        {0x102A0, 0x102D0, WBP_ALetter},
-       {0x10300, 0x1031E, WBP_ALetter},
+       {0x102E0, 0x102E0, WBP_Extend},
+       {0x10300, 0x1031F, WBP_ALetter},
        {0x10330, 0x10340, WBP_ALetter},
        {0x10341, 0x10341, WBP_ALetter},
        {0x10342, 0x10349, WBP_ALetter},
        {0x1034A, 0x1034A, WBP_ALetter},
+       {0x10350, 0x10375, WBP_ALetter},
+       {0x10376, 0x1037A, WBP_Extend},
        {0x10380, 0x1039D, WBP_ALetter},
        {0x103A0, 0x103C3, WBP_ALetter},
        {0x103C8, 0x103CF, WBP_ALetter},
@@ -796,12 +817,19 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x10400, 0x1044F, WBP_ALetter},
        {0x10450, 0x1049D, WBP_ALetter},
        {0x104A0, 0x104A9, WBP_Numeric},
+       {0x10500, 0x10527, WBP_ALetter},
+       {0x10530, 0x10563, WBP_ALetter},
+       {0x10600, 0x10736, WBP_ALetter},
+       {0x10740, 0x10755, WBP_ALetter},
+       {0x10760, 0x10767, WBP_ALetter},
        {0x10800, 0x10805, WBP_ALetter},
        {0x10808, 0x10808, WBP_ALetter},
        {0x1080A, 0x10835, WBP_ALetter},
        {0x10837, 0x10838, WBP_ALetter},
        {0x1083C, 0x1083C, WBP_ALetter},
        {0x1083F, 0x10855, WBP_ALetter},
+       {0x10860, 0x10876, WBP_ALetter},
+       {0x10880, 0x1089E, WBP_ALetter},
        {0x10900, 0x10915, WBP_ALetter},
        {0x10920, 0x10939, WBP_ALetter},
        {0x10980, 0x109B7, WBP_ALetter},
@@ -816,9 +844,14 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x10A38, 0x10A3A, WBP_Extend},
        {0x10A3F, 0x10A3F, WBP_Extend},
        {0x10A60, 0x10A7C, WBP_ALetter},
+       {0x10A80, 0x10A9C, WBP_ALetter},
+       {0x10AC0, 0x10AC7, WBP_ALetter},
+       {0x10AC9, 0x10AE4, WBP_ALetter},
+       {0x10AE5, 0x10AE6, WBP_Extend},
        {0x10B00, 0x10B35, WBP_ALetter},
        {0x10B40, 0x10B55, WBP_ALetter},
        {0x10B60, 0x10B72, WBP_ALetter},
+       {0x10B80, 0x10B91, WBP_ALetter},
        {0x10C00, 0x10C48, WBP_ALetter},
        {0x11000, 0x11000, WBP_Extend},
        {0x11001, 0x11001, WBP_Extend},
@@ -826,7 +859,7 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x11003, 0x11037, WBP_ALetter},
        {0x11038, 0x11046, WBP_Extend},
        {0x11066, 0x1106F, WBP_Numeric},
-       {0x11080, 0x11081, WBP_Extend},
+       {0x1107F, 0x11081, WBP_Extend},
        {0x11082, 0x11082, WBP_Extend},
        {0x11083, 0x110AF, WBP_ALetter},
        {0x110B0, 0x110B2, WBP_Extend},
@@ -842,6 +875,9 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x1112C, 0x1112C, WBP_Extend},
        {0x1112D, 0x11134, WBP_Extend},
        {0x11136, 0x1113F, WBP_Numeric},
+       {0x11150, 0x11172, WBP_ALetter},
+       {0x11173, 0x11173, WBP_Extend},
+       {0x11176, 0x11176, WBP_ALetter},
        {0x11180, 0x11181, WBP_Extend},
        {0x11182, 0x11182, WBP_Extend},
        {0x11183, 0x111B2, WBP_ALetter},
@@ -850,6 +886,68 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x111BF, 0x111C0, WBP_Extend},
        {0x111C1, 0x111C4, WBP_ALetter},
        {0x111D0, 0x111D9, WBP_Numeric},
+       {0x111DA, 0x111DA, WBP_ALetter},
+       {0x11200, 0x11211, WBP_ALetter},
+       {0x11213, 0x1122B, WBP_ALetter},
+       {0x1122C, 0x1122E, WBP_Extend},
+       {0x1122F, 0x11231, WBP_Extend},
+       {0x11232, 0x11233, WBP_Extend},
+       {0x11234, 0x11234, WBP_Extend},
+       {0x11235, 0x11235, WBP_Extend},
+       {0x11236, 0x11237, WBP_Extend},
+       {0x112B0, 0x112DE, WBP_ALetter},
+       {0x112DF, 0x112DF, WBP_Extend},
+       {0x112E0, 0x112E2, WBP_Extend},
+       {0x112E3, 0x112EA, WBP_Extend},
+       {0x112F0, 0x112F9, WBP_Numeric},
+       {0x11301, 0x11301, WBP_Extend},
+       {0x11302, 0x11303, WBP_Extend},
+       {0x11305, 0x1130C, WBP_ALetter},
+       {0x1130F, 0x11310, WBP_ALetter},
+       {0x11313, 0x11328, WBP_ALetter},
+       {0x1132A, 0x11330, WBP_ALetter},
+       {0x11332, 0x11333, WBP_ALetter},
+       {0x11335, 0x11339, WBP_ALetter},
+       {0x1133C, 0x1133C, WBP_Extend},
+       {0x1133D, 0x1133D, WBP_ALetter},
+       {0x1133E, 0x1133F, WBP_Extend},
+       {0x11340, 0x11340, WBP_Extend},
+       {0x11341, 0x11344, WBP_Extend},
+       {0x11347, 0x11348, WBP_Extend},
+       {0x1134B, 0x1134D, WBP_Extend},
+       {0x11357, 0x11357, WBP_Extend},
+       {0x1135D, 0x11361, WBP_ALetter},
+       {0x11362, 0x11363, WBP_Extend},
+       {0x11366, 0x1136C, WBP_Extend},
+       {0x11370, 0x11374, WBP_Extend},
+       {0x11480, 0x114AF, WBP_ALetter},
+       {0x114B0, 0x114B2, WBP_Extend},
+       {0x114B3, 0x114B8, WBP_Extend},
+       {0x114B9, 0x114B9, WBP_Extend},
+       {0x114BA, 0x114BA, WBP_Extend},
+       {0x114BB, 0x114BE, WBP_Extend},
+       {0x114BF, 0x114C0, WBP_Extend},
+       {0x114C1, 0x114C1, WBP_Extend},
+       {0x114C2, 0x114C3, WBP_Extend},
+       {0x114C4, 0x114C5, WBP_ALetter},
+       {0x114C7, 0x114C7, WBP_ALetter},
+       {0x114D0, 0x114D9, WBP_Numeric},
+       {0x11580, 0x115AE, WBP_ALetter},
+       {0x115AF, 0x115B1, WBP_Extend},
+       {0x115B2, 0x115B5, WBP_Extend},
+       {0x115B8, 0x115BB, WBP_Extend},
+       {0x115BC, 0x115BD, WBP_Extend},
+       {0x115BE, 0x115BE, WBP_Extend},
+       {0x115BF, 0x115C0, WBP_Extend},
+       {0x11600, 0x1162F, WBP_ALetter},
+       {0x11630, 0x11632, WBP_Extend},
+       {0x11633, 0x1163A, WBP_Extend},
+       {0x1163B, 0x1163C, WBP_Extend},
+       {0x1163D, 0x1163D, WBP_Extend},
+       {0x1163E, 0x1163E, WBP_Extend},
+       {0x1163F, 0x11640, WBP_Extend},
+       {0x11644, 0x11644, WBP_ALetter},
+       {0x11650, 0x11659, WBP_Numeric},
        {0x11680, 0x116AA, WBP_ALetter},
        {0x116AB, 0x116AB, WBP_Extend},
        {0x116AC, 0x116AC, WBP_Extend},
@@ -859,16 +957,36 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x116B6, 0x116B6, WBP_Extend},
        {0x116B7, 0x116B7, WBP_Extend},
        {0x116C0, 0x116C9, WBP_Numeric},
-       {0x12000, 0x1236E, WBP_ALetter},
-       {0x12400, 0x12462, WBP_ALetter},
+       {0x118A0, 0x118DF, WBP_ALetter},
+       {0x118E0, 0x118E9, WBP_Numeric},
+       {0x118FF, 0x118FF, WBP_ALetter},
+       {0x11AC0, 0x11AF8, WBP_ALetter},
+       {0x12000, 0x12398, WBP_ALetter},
+       {0x12400, 0x1246E, WBP_ALetter},
        {0x13000, 0x1342E, WBP_ALetter},
        {0x16800, 0x16A38, WBP_ALetter},
+       {0x16A40, 0x16A5E, WBP_ALetter},
+       {0x16A60, 0x16A69, WBP_Numeric},
+       {0x16AD0, 0x16AED, WBP_ALetter},
+       {0x16AF0, 0x16AF4, WBP_Extend},
+       {0x16B00, 0x16B2F, WBP_ALetter},
+       {0x16B30, 0x16B36, WBP_Extend},
+       {0x16B40, 0x16B43, WBP_ALetter},
+       {0x16B50, 0x16B59, WBP_Numeric},
+       {0x16B63, 0x16B77, WBP_ALetter},
+       {0x16B7D, 0x16B8F, 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},
+       {0x1BC00, 0x1BC6A, WBP_ALetter},
+       {0x1BC70, 0x1BC7C, WBP_ALetter},
+       {0x1BC80, 0x1BC88, WBP_ALetter},
+       {0x1BC90, 0x1BC99, WBP_ALetter},
+       {0x1BC9D, 0x1BC9E, WBP_Extend},
+       {0x1BCA0, 0x1BCA3, WBP_Format},
        {0x1D165, 0x1D166, WBP_Extend},
        {0x1D167, 0x1D169, WBP_Extend},
        {0x1D16D, 0x1D172, WBP_Extend},
@@ -908,6 +1026,8 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x1D7AA, 0x1D7C2, WBP_ALetter},
        {0x1D7C4, 0x1D7CB, WBP_ALetter},
        {0x1D7CE, 0x1D7FF, WBP_Numeric},
+       {0x1E800, 0x1E8C4, WBP_ALetter},
+       {0x1E8D0, 0x1E8D6, WBP_Extend},
        {0x1EE00, 0x1EE03, WBP_ALetter},
        {0x1EE05, 0x1EE1F, WBP_ALetter},
        {0x1EE21, 0x1EE22, WBP_ALetter},
@@ -941,7 +1061,10 @@ static struct WordBreakProperties wb_prop_default[] = {
        {0x1EEA1, 0x1EEA3, WBP_ALetter},
        {0x1EEA5, 0x1EEA9, WBP_ALetter},
        {0x1EEAB, 0x1EEBB, WBP_ALetter},
-       {0x1F1E6, 0x1F1FF, WBP_Regional},
+       {0x1F130, 0x1F149, WBP_ALetter},
+       {0x1F150, 0x1F169, WBP_ALetter},
+       {0x1F170, 0x1F189, WBP_ALetter},
+       {0x1F1E6, 0x1F1FF, WBP_Regional_Indicator},
        {0xE0001, 0xE0001, WBP_Format},
        {0xE0020, 0xE007F, WBP_Format},
        {0xE0100, 0xE01EF, WBP_Extend},

diff --git a/third-party/libunibreak/wordbreakdef.h b/third-party/libunibreak/wordbreakdef.h
index 72816f9..7130a13 100644 (file)
--- a/third-party/libunibreak/wordbreakdef.h
+++ b/third-party/libunibreak/wordbreakdef.h
@@ -4,8 +4,7 @@
  * Word breaking in a Unicode sequence.  Designed to be used in a
  * generic text renderer.
  *
- * Copyright (C) 2013 Tom Hacohen <tom at stosb dot com>
- * Copyright (C) 2013 Petr Filipsky <philodej at gmail dot com>
+ * Copyright (C) 2013-15 Tom Hacohen <tom at stosb dot com>
  *
  * This software is provided 'as-is', without any express or implied
  * warranty.  In no event will the author be held liable for any damages
@@ -31,9 +30,8 @@
  * Unicode 6.0.0:
  *      <URL:http://www.unicode.org/reports/tr29/tr29-17.html>
  *
- * This library has been updated according to Revision 21, for
- * Unicode 6.2.0:
- *      <URL:http://www.unicode.org/reports/tr29/tr29-21.html>
+ * This library has been updated according to Revision 25, for
+ * Unicode 7.0.0:
  *
  * The Unicode Terms of Use are available at
  *      <URL:http://www.unicode.org/copyright.html>
@@ -45,11 +43,12 @@
  * Definitions of internal data structures, declarations of global
  * variables, and function prototypes for the word breaking algorithm.
  *
- * @version 2.4, 2013/11/10
+ * @version 2.6, 2015/04/19
  * @author  Tom Hacohen
- * @author  Petr Filipsky
  */
 
+#include "unibreakdef.h"
+
 /**
  * Word break classes.  This is a direct mapping of Table 3 of Unicode
  * Standard Annex 29, Revision 23.
@@ -61,18 +60,18 @@ enum WordBreakClass
     WBP_LF,
     WBP_Newline,
     WBP_Extend,
+    WBP_Regional_Indicator,
     WBP_Format,
     WBP_Katakana,
+    WBP_Hebrew_Letter,
     WBP_ALetter,
+    WBP_Single_Quote,
+    WBP_Double_Quote,
     WBP_MidNumLet,
     WBP_MidLetter,
     WBP_MidNum,
     WBP_Numeric,
     WBP_ExtendNumLet,
-    WBP_Regional,
-    WBP_Hebrew,
-    WBP_Single,
-    WBP_Double,
     WBP_Any
 };