Add Unicode 5.2 scripts

src/hb-icu.c

@@ -31,6 +31,7 @@
 
 #include "hb-unicode-private.h"
 
+#include <unicode/uversion.h>
 #include <unicode/uchar.h>
 #include <unicode/uscript.h>
 
@@ -110,9 +111,12 @@ hb_icu_get_script (hb_codepoint_t unicode)
   UScriptCode scriptCode = uscript_getScript(unicode, &status);
   switch ((int) scriptCode)
   {
+#define CHECK_ICU_VERSION(major, minor) \
+	U_ICU_VERSION_MAJOR_NUM > (major) || (U_ICU_VERSION_MAJOR_NUM == (major) && U_ICU_VERSION_MINOR_NUM >= (minor))
 #define MATCH_SCRIPT(C) case USCRIPT_##C: return HB_SCRIPT_##C
+#define MATCH_SCRIPT2(C1, C2) case USCRIPT_##C1: return HB_SCRIPT_##C2
   MATCH_SCRIPT (INVALID_CODE);
-  MATCH_SCRIPT (COMMON);   /* Zyyy */
+  MATCH_SCRIPT (COMMON);             /* Zyyy */
   MATCH_SCRIPT (INHERITED);          /* Qaai */
   MATCH_SCRIPT (ARABIC);             /* Arab */
   MATCH_SCRIPT (ARMENIAN);           /* Armn */
@@ -198,6 +202,29 @@ hb_icu_get_script (hb_codepoint_t unicode)
   MATCH_SCRIPT (CARIAN);             /* Cari */
   MATCH_SCRIPT (LYCIAN);             /* Lyci */
   MATCH_SCRIPT (LYDIAN);             /* Lydi */
+
+  /* Unicode-5.2 additions */
+  MATCH_SCRIPT (AVESTAN);                /* Avst */
+#if CHECK_ICU_VERSION (4, 4)
+  MATCH_SCRIPT (BAMUM);                  /* Bamu */
+#endif
+  MATCH_SCRIPT (EGYPTIAN_HIEROGLYPHS);   /* Egyp */
+  MATCH_SCRIPT (IMPERIAL_ARAMAIC);       /* Armi */
+  MATCH_SCRIPT (INSCRIPTIONAL_PAHLAVI);  /* Phli */
+  MATCH_SCRIPT (INSCRIPTIONAL_PARTHIAN); /* Prti */
+  MATCH_SCRIPT (JAVANESE);               /* Java */
+  MATCH_SCRIPT (KAITHI);                 /* Kthi */
+  MATCH_SCRIPT2(LANNA, TAI_THAM);        /* Lana */
+#if CHECK_ICU_VERSION (4, 4)
+  MATCH_SCRIPT (LISU);                   /* Lisu */
+#endif
+  MATCH_SCRIPT (MEITEI_MAYEK);           /* Mtei */
+#if CHECK_ICU_VERSION (4, 4)
+  MATCH_SCRIPT (OLD_SOUTH_ARABIAN);      /* Sarb */
+#endif
+  MATCH_SCRIPT2(ORKHON, OLD_TURKIC);     /* Orkh */
+  MATCH_SCRIPT (SAMARITAN);              /* Samr */
+  MATCH_SCRIPT (TAI_VIET);               /* Tavt */
   }
   return HB_SCRIPT_UNKNOWN;
 }

src/hb-ot-tag.c

@@ -120,7 +120,24 @@ static const hb_tag_t ot_scripts[][3] = {
   {HB_TAG('v','a','i',' ')},	/* HB_SCRIPT_VAI */
   {HB_TAG('c','a','r','i')},	/* HB_SCRIPT_CARIAN */
   {HB_TAG('l','y','c','i')},	/* HB_SCRIPT_LYCIAN */
-  {HB_TAG('l','y','d','i')} 	/* HB_SCRIPT_LYDIAN */
+  {HB_TAG('l','y','d','i')},	/* HB_SCRIPT_LYDIAN */
+
+  /* Unicode-5.2 additions */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_AVESTAN */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_BAMUM */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_EGYPTIAN_HIEROGLYPHS */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_IMPERIAL_ARAMAIC */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_INSCRIPTIONAL_PAHLAVI */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_INSCRIPTIONAL_PARTHIAN */
+  {HB_TAG('j','a','v','a')},	/* HB_SCRIPT_JAVANESE */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_KAITHI */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_LISU */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_MEITEI_MAYEK */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_OLD_SOUTH_ARABIAN */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_OLD_TURKIC */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_SAMARITAN */
+  {HB_TAG('D','F','L','T')},	/* HB_SCRIPT_TAI_THAM */
+  {HB_TAG('D','F','L','T')} 	/* HB_SCRIPT_TAI_VIET */
 };
 
 const hb_tag_t *
@@ -140,7 +157,7 @@ hb_ot_tag_to_script (hb_tag_t tag)
   int i;
 
   for (i = 0; i < ARRAY_LENGTH (ot_scripts); i++) {
-    hb_tag_t *p = ot_scripts[i];
+    const hb_tag_t *p = ot_scripts[i];
     while (*p)
       if (tag == *p)
         return i;

src/hb-unicode.c

@@ -286,7 +286,24 @@ const hb_direction_t horiz_dir[] =
   LTR,	/* Vaii */
   LTR,	/* Cari */
   LTR,	/* Lyci */
-  LTR	/* Lydi */
+  LTR,	/* Lydi */
+
+  /* Unicode-5.2 additions */
+  RTL,	/* Avst */
+  LTR,	/* Bamu */
+  LTR,	/* Egyp */
+  RTL,	/* Armi */
+  RTL,	/* Phli */
+  RTL,	/* Prti */
+  LTR,	/* Java */
+  LTR,	/* Kthi */
+  LTR,	/* Lisu */
+  LTR,	/* Mtei */
+  RTL,	/* Sarb */
+  RTL,	/* Orkh */
+  RTL,	/* Samr */
+  LTR,	/* Lana */
+  LTR 	/* Tavt */
 };
 #undef LTR
 #undef RTL

src/hb-unicode.h

@@ -155,7 +155,24 @@ typedef enum
   HB_SCRIPT_VAI,                /* Vaii */
   HB_SCRIPT_CARIAN,             /* Cari */
   HB_SCRIPT_LYCIAN,             /* Lyci */
-  HB_SCRIPT_LYDIAN              /* Lydi */
+  HB_SCRIPT_LYDIAN,             /* Lydi */
+
+  /* Unicode-5.2 additions */
+  HB_SCRIPT_AVESTAN,                /* Avst */
+  HB_SCRIPT_BAMUM,                  /* Bamu */
+  HB_SCRIPT_EGYPTIAN_HIEROGLYPHS,   /* Egyp */
+  HB_SCRIPT_IMPERIAL_ARAMAIC,       /* Armi */
+  HB_SCRIPT_INSCRIPTIONAL_PAHLAVI,  /* Phli */
+  HB_SCRIPT_INSCRIPTIONAL_PARTHIAN, /* Prti */
+  HB_SCRIPT_JAVANESE,               /* Java */
+  HB_SCRIPT_KAITHI,                 /* Kthi */
+  HB_SCRIPT_LISU,                   /* Lisu */
+  HB_SCRIPT_MEITEI_MAYEK,           /* Mtei */
+  HB_SCRIPT_OLD_SOUTH_ARABIAN,      /* Sarb */
+  HB_SCRIPT_OLD_TURKIC,             /* Orkh */
+  HB_SCRIPT_SAMARITAN,              /* Samr */
+  HB_SCRIPT_TAI_THAM,               /* Lana */
+  HB_SCRIPT_TAI_VIET                /* Tavt */
 } hb_script_t;