ref: 330a39596c51d8412a5a344054df24f00318f68f
parent: e2411375082668960210e013350f5c08e8805f67
author: Anthony J. Bentley <[email protected]>
date: Thu Jan 28 18:16:42 EST 2016
Instead of blindly trusting the first byte, decode UTF-8 safely.
--- a/LICENSE
+++ b/LICENSE
@@ -18,6 +18,10 @@
rgbfix was rewritten from scratch by Anthony J. Bentley, and is released
under the ISC license; see the source file for the text of the license.
+The UTF-8 decoder in src/asm/charmap.c was written by Björn Höhrmann and is
+released under the MIT license. The remainder of charmap.c was written by
+stag019, and is released under the ISC license.
+
extern/err.c is derived from the Musl C library, http://www.musl-libc.org,
and is released under the MIT license.
--- a/src/asm/charmap.c
+++ b/src/asm/charmap.c
@@ -1,4 +1,58 @@
/*
+ * UTF-8 decoder copyright © 2008–2009 Björn Höhrmann <[email protected]>
+ * http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <stdint.h>
+
+static const uint8_t utf8d[] = {+ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 00..1f
+ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 20..3f
+ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 40..5f
+ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 60..7f
+ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, // 80..9f
+ 7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7, // a0..bf
+ 8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, // c0..df
+ 0xa,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x4,0x3,0x3, // e0..ef
+ 0xb,0x6,0x6,0x6,0x5,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8, // f0..ff
+ 0x0,0x1,0x2,0x3,0x5,0x8,0x7,0x1,0x1,0x1,0x4,0x6,0x1,0x1,0x1,0x1, // s0..s0
+ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,0,1,1,1,1,1,0,1,0,1,1,1,1,1,1, // s1..s2
+ 1,2,1,1,1,1,1,2,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1, // s3..s4
+ 1,2,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,3,1,3,1,1,1,1,1,1, // s5..s6
+ 1,3,1,1,1,1,1,3,1,3,1,1,1,1,1,1,1,3,1,1,1,1,1,1,1,1,1,1,1,1,1,1, // s7..s8
+};
+
+uint32_t
+decode(uint32_t* state, uint32_t* codep, uint32_t byte) {+ uint32_t type = utf8d[byte];
+
+ *codep = (*state != 0) ?
+ (byte & 0x3fu) | (*codep << 6) :
+ (0xff >> type) & (byte);
+
+ *state = utf8d[256 + *state*16 + type];
+ return *state;
+}
+
+/*
* Copyright © 2013 stag019 <[email protected]>
*
* Permission to use, copy, modify, and distribute this software for any
@@ -28,30 +82,26 @@
extern struct Section *pCurrentSection;
int
-readUTF8Char(char *destination, char *source)
+readUTF8Char(char *dest, char *src)
{- int size;
- UBYTE first;
- first = source[0];
+ uint32_t state;
+ uint32_t codep;
+ int i;
- if (first >= 0xFC) {- size = 6;
- } else if (first >= 0xF8) {- size = 5;
- } else if (first >= 0xF0) {- size = 4;
- } else if (first >= 0xE0) {- size = 3;
- } else if (first >= 0xC0) {- size = 2;
- } else if (first != '\0') {- size = 1;
- } else {- size = 0;
+ for (i = 0, state = 0;; i++) {+ if (decode(&state, &codep, (uint8_t)src[i]) == 1) {+ fatalerror("invalid UTF-8 character");+ }
+
+ dest[i] = src[i];
+
+ i++;
+ if (state == 0) {+ dest[i] = '\0';
+ return i;
+ }
+ dest[i] = src[i];
}
- strncpy(destination, source, size);
- destination[size] = 0;
- return size;
}
int