From 785e95ef0a95ca8fb39ef57678cd4876ee657c43 Mon Sep 17 00:00:00 2001 From: John Tapsell Date: Wed, 8 Feb 2012 10:12:13 +0000 Subject: Harfbuzz-thai: Hide ZWJ and ZWNJ characters and show Inherited characters Thai is not supposed to have ZWJ and ZWNJ characters or any other of the Inherited Unicode Scripts (http://www.verisigninc.com/assets/idn-inherited-unicode-script.pdf) - they don't have a mapping to the thai encoding tis620 which libthai requires. However it is an unfortunate fact that there are many websites etc that liberally place these ZWJ and ZWNJ characters throughout thai text to force word boundaries, so we must also deal with them. We deal with all Inherited characters by mapping them to the invalid code ~0 in tis620 encoding, following what libthai does internally in its own tis620 encoding functions, and then replacing this character with the original unicode and setting dontPrint to true to hide the ZWJ and ZWNJ characters. Includes a unit test to check the behaviour. Change-Id: I1ee8388b650cb5fc61bcb265efb9843c73f327ac Reviewed-by: Adrian Yanes Reviewed-by: Lars Knoll Reviewed-by: Eskil Abrahamsen Blomfeldt --- src/3rdparty/harfbuzz/src/harfbuzz-thai.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'src/3rdparty/harfbuzz/src') diff --git a/src/3rdparty/harfbuzz/src/harfbuzz-thai.c b/src/3rdparty/harfbuzz/src/harfbuzz-thai.c index 386fd5c252..bf6c35b19c 100644 --- a/src/3rdparty/harfbuzz/src/harfbuzz-thai.c +++ b/src/3rdparty/harfbuzz/src/harfbuzz-thai.c @@ -77,7 +77,7 @@ static void to_tis620(const HB_UChar16 *string, hb_uint32 len, const char *cstr) else if (string[i] >= 0xe01 && string[i] <= 0xe5b) result[i] = (unsigned char)(string[i] - 0xe00 + 0xa0); else - result[i] = '?'; + result[i] = (unsigned char)~0; // Same encoding as libthai uses for invalid chars } result[len] = 0; @@ -259,8 +259,13 @@ static HB_Bool HB_ThaiConvertStringToGlyphIndices (HB_ShaperItem *item) for (int lgi = 0; lgi < lgn; lgi++) { if ( rglyphs[lgi] == 0xdd/*TH_BLANK_BASE_GLYPH*/ ) { glyphString[slen++] = C_DOTTED_CIRCLE; - } - else { + } else if (cstr[i] == (signed char)~0) { + // The only glyphs that should be passed to this function that cannot be mapped to + // tis620 are the ones of type Inherited class. Pass these glyphs untouched. + glyphString[slen++] = string[i]; + if (string[i] == 0x200D || string[i] == 0x200C) + item->attributes[slen-1].dontPrint = true; // Hide ZWJ and ZWNJ characters + } else { glyphString[slen++] = (HB_UChar16) thai_get_glyph_index (font_type, rglyphs[lgi]); } } -- cgit v1.2.3