X-Git-Url: https://git.xonotic.org/?p=xonotic%2Fgmqcc.git;a=blobdiff_plain;f=utf8.c;h=06a651ac5fada4e3cbdc6e9629c2b1deade8abc5;hp=6089df19038bfa171b2b1c4352e8f1ee58eb3dff;hb=ba0ac9737272ac247c1850be891b51c446144732;hpb=3e362e872c0596ff3e058c791a416ac7f8ae4c67

diff --git a/utf8.c b/utf8.c
index 6089df1..06a651a 100644
--- a/utf8.c
+++ b/utf8.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2012, 2013
+ * Copyright (C) 2012, 2013, 2014
  *     Dale Weiler
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy of
@@ -50,42 +50,31 @@
  * In this table the transition values are pre-multiplied with 16 to
  * save a shift instruction for every byte, we throw away fillers
  * which makes the table smaller.
+ *
+ * The first section of the table handles bytes with leading C
+ * The second section of the table handles bytes with leading D
+ * The third section of the table handles bytes with leading E
+ * The last section of the table handles bytes with leading F
+ *
+ * The values themselfs in the table are arranged so that when you
+ * left shift them by 6 to shift continuation characters into place, the
+ * new top bits tell you:
+ *
+ *  1 - if you keep going
+ *  2 - the range of valid values for the next byte
  */
 static const uint32_t utf8_tab[] = {
-    0xC0000002, 0xC0000003, 0xC0000004, 0xC0000005, 0xC0000006, 0xC0000007,
-    0xC0000008, 0xC0000009, 0xC000000A, 0xC000000B, 0xC000000C, 0xC000000D,
-    0xC000000E, 0xC000000F, 0xC0000010, 0xC0000011, 0xC0000012, 0xC0000013,
-    0xC0000014, 0xC0000015, 0xC0000016, 0xC0000017, 0xC0000018, 0xC0000019,
-    0xC000001A, 0xC000001B, 0xC000001C, 0xC000001D, 0xC000001E, 0xC000001F,
-    0xB3000000, 0xC3000001, 0xC3000002, 0xC3000003, 0xC3000004, 0xC3000005,
-    0xC3000006, 0xC3000007, 0xC3000008, 0xC3000009, 0xC300000A, 0xC300000B,
-    0xC300000C, 0xD300000D, 0xC300000E, 0xC300000F, 0xBB0C0000, 0xC30C0001,
-    0xC30C0002, 0xC30C0003, 0xD30C0004, 0x58257830, 0x202C,     0x3B031B01,
-    0x30,       0x5,        0xFFFFFD1C, 0x7C,       0xFFFFFD5C, 0x4C,
-    0xFFFFFE4C, 0xA4,       0xFFFFFE8C, 0xC4,       0xFFFFFEFC, 0x10C,
-    0x14,       0x0,        0x527A01,   0x1107801,  0x8070C1B,  0x10070190,
-    0x14,       0x1C,       0xFFFFFD08, 0x2A,       0x0,        0x0,
-    0x14,       0x0,        0x527A01,   0x1107801,  0x8070C1B,  0x190,
-    0x24,       0x1C,       0xFFFFFC98, 0x40,       0x46100E00, 0xF4A180E,
-    0x8008770B, 0x3B1A3F00, 0x2224332A, 0x0,        0x1C,       0x44,
-    0xFFFFFDA0, 0x3E,       0x100E4100, 0xD430286,  0x70C7906,  0x8,
-    0x44,       0x64,       0xFFFFFDC0, 0x65,       0x100E4200, 0xE45028F,
-    0x45038E18, 0x48D200E,  0x8C280E45, 0x300E4805, 0xE480686,  0x4D078338,
-    0xE6C400E,  0x300E4138, 0x42280E41, 0xE42200E,  0x100E4218, 0x80E42,
-    0x14,       0xAC,       0xFFFFFDE8, 0x2,        0x0,        0x0,
-    0x0,        0x0,        0x4004D0,   0x0,        0x4004B0,   0x0,
-    0x0,        0x0,        0x1,        0x0,        0x1,        0x0,
-    0xC,        0x0,        0x4003A8,   0x0,        0xD,        0x0,
-    0x4005B4,   0x0,        0x19,       0x0,        0x6007E0,   0x0,
-    0x1B,       0x0,        0x8,        0x0,        0x1A,       0x0,
-    0x6007E8,   0x0,        0x1C,       0x0,        0x8,        0x0,
-    0x6FFFFEF5, 0x0,        0x400260,   0x0,        0x5,        0x0,
-    0x4002E0,   0x0,        0x6,        0x0,        0x400280,   0x0,
-    0xA,        0x0,        0x3F,       0x0,        0xB,        0x0,
-    0x18,       0x0,        0x15,       0x0,        0x0,        0x0,
-    0x3,        0x0,        0x6009D0,   0x0,        0x2,        0x0,
-    0x48,       0x0,        0x14,       0x0,        0x7,        0x0,
-    0x17,       0x0,        0x400360,   0x0,        0x7,        0x0
+    0xC0000002, 0xC0000003, 0xC0000004, 0xC0000005, 0xC0000006,
+    0xC0000007, 0xC0000008, 0xC0000009, 0xC000000A, 0xC000000B,
+    0xC000000C, 0xC000000D, 0xC000000E, 0xC000000F, 0xC0000010,
+    0xC0000011, 0xC0000012, 0xC0000013, 0xC0000014, 0xC0000015,
+    0xC0000016, 0xC0000017, 0xC0000018, 0xC0000019, 0xC000001A,
+    0xC000001B, 0xC000001C, 0xC000001D, 0xC000001E, 0xC000001F,
+    0xB3000000, 0xC3000001, 0xC3000002, 0xC3000003, 0xC3000004,
+    0xC3000005, 0xC3000006, 0xC3000007, 0xC3000008, 0xC3000009,
+    0xC300000A, 0xC300000B, 0xC300000C, 0xD300000D, 0xC300000E,
+    0xC300000F, 0xBB0C0000, 0xC30C0001, 0xC30C0002, 0xC30C0003,
+    0xD30C0004
 };
 
 int utf8_from(char *s, utf8ch_t ch) {