|
|
Please, use the following patch
Index: LineBreaking.cpp
--- LineBreaking.cpp (revision 15297)
+++ LineBreaking.cpp (working copy)
@@ -113,6 +113,14 @@
{ DI_BRK, PR_BRK, PR_BRK, IN_BRK, IN_BRK, DI_BRK, PR_BRK, PR_BRK, PR_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, PR_BRK, CI_BRK, PR_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, DI_BRK, IN_BRK, DI_BRK } // CB
};
+// https://www.unicode.org/reports/tr14/#Examples
+// Depending on the nature of the document, Korean either uses implicit breaking around characters
+// (type 2 as defined in Section 3, Introduction) or uses spaces (type 1). Space-based layout is
+// common in magazines and other informal documents with ragged margins, while books, with both
+// margins justified, use the other type, as it affords more line break opportunities and therefore
+// leads to better justification.
+#define HANGUL_TEXT_WRAPPING_PER_WORD 1
+
////////////////////////////////////////////////////////////////////////////////////////////////////
static uint8_t GetType(uint32_t ch)
{
@@ -126,14 +134,26 @@
{
case LBT_AI:
return LBT_AL;
+
case LBT_CJ:
// "Strict" line breaking
// http://www.unicode.org/reports/tr14/#CJ
return LBT_NS;
+
case LBT_SA:
case LBT_SG:
case LBT_XX:
return LBT_AL;
+
- #if HANGUL_TEXT_WRAPPING_PER_WORD
- case LBT_H2:
- case LBT_H3:
- case LBT_JL:
- case LBT_JV:
- case LBT_JT:
- return LBT_AL;
- #endif
-
default:
return type;
}
|
