QCharAttributes: add wordStart/wordEnd flags

A simple heuristic is used to detect the word beginning and ending by
looking at the word break property value of surrounding characters.
This behaves better than the white-spaces based implementation used before
and makes it possible to tailor the default algorithm for complex scripts.

BIG FAT WARNING: The QCharAttributes buffer now has to have a length
                 of string length + 1 for the flags at end of text.

Task-Id: QTBUG-6498

Change-Id: I5589b191ffde6a50d2af0c14a00430d3852c67b4
Reviewed-by: Konstantin Ritt <ritt.ks@gmail.com>

2 files changed, 12 insertions, 2 deletions

diff --git a/src/3rdparty/harfbuzz/src/harfbuzz-shaper.h b/src/3rdparty/harfbuzz/src/harfbuzz-shaper.h
index 2ff52eaf30..5a3329dd4b 100644
--- a/src/3rdparty/harfbuzz/src/harfbuzz-shaper.h
+++ b/src/3rdparty/harfbuzz/src/harfbuzz-shaper.h
@@ -133,7 +133,9 @@ typedef struct {
     hb_bitfield sentenceBoundary : 1;
     hb_bitfield lineBreak        : 1;
     hb_bitfield whiteSpace       : 1;     /* A unicode whitespace character */
-    hb_bitfield unused           : 3;
+    hb_bitfield wordStart        : 1;
+    hb_bitfield wordEnd          : 1;
+    hb_bitfield unused           : 1;
 } HB_CharAttributes;
 
 void HB_GetTailoredCharAttributes(const HB_UChar16 *string, hb_uint32 stringLength,
diff --git a/src/3rdparty/harfbuzz/src/harfbuzz-thai.c b/src/3rdparty/harfbuzz/src/harfbuzz-thai.c
index 70c1d57ff1..f62a1b7159 100644
--- a/src/3rdparty/harfbuzz/src/harfbuzz-thai.c
+++ b/src/3rdparty/harfbuzz/src/harfbuzz-thai.c
@@ -395,8 +395,10 @@ static void HB_ThaiAssignAttributes(const HB_UChar16 *string, hb_uint32 len, HB_
     to_tis620(string, len, cstr);
 
     for (i = 0; i < len; ++i) {
-        attributes[i].lineBreak = FALSE;
         attributes[i].wordBreak = FALSE;
+        attributes[i].wordStart = FALSE;
+        attributes[i].wordEnd = FALSE;
+        attributes[i].lineBreak = FALSE;
     }
 
     if (len > 128) {
@@ -411,11 +413,17 @@ static void HB_ThaiAssignAttributes(const HB_UChar16 *string, hb_uint32 len, HB_
 
     if (break_positions) {
         attributes[0].wordBreak = TRUE;
+        attributes[0].wordStart = TRUE;
+        attributes[0].wordEnd = FALSE;
         numbreaks = th_brk((const unsigned char *)cstr, break_positions, brp_size);
         for (i = 0; i < numbreaks; ++i) {
             attributes[break_positions[i]].wordBreak = TRUE;
+            attributes[break_positions[i]].wordStart = TRUE;
+            attributes[break_positions[i]].wordEnd = TRUE;
             attributes[break_positions[i]].lineBreak = TRUE;
         }
+        if (numbreaks > 0)
+            attributes[break_positions[numbreaks - 1]].wordStart = FALSE;
 
         if (break_positions != brp)
             free(break_positions);