X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Funistr%2Fu8-mbtouc-aux.c;h=02cdacd9d85d49a9e29af5840196822d9aaf481d;hb=1276a2c5f24c0c932426aca9c899fa524d2443f2;hp=53d02bf0dfee790fe8747c6a907308919d81b2f5;hpb=1a75491a06af7e04ea1170d2d32dbd1c76d9c096;p=gnulib.git diff --git a/lib/unistr/u8-mbtouc-aux.c b/lib/unistr/u8-mbtouc-aux.c index 53d02bf0d..02cdacd9d 100644 --- a/lib/unistr/u8-mbtouc-aux.c +++ b/lib/unistr/u8-mbtouc-aux.c @@ -1,5 +1,5 @@ /* Conversion UTF-8 to UCS-4. - Copyright (C) 2001-2002, 2006-2007, 2009 Free Software Foundation, Inc. + Copyright (C) 2001-2002, 2006-2007, 2009-2014 Free Software Foundation, Inc. Written by Bruno Haible , 2001. This program is free software: you can redistribute it and/or modify it @@ -30,124 +30,206 @@ u8_mbtouc_aux (ucs4_t *puc, const uint8_t *s, size_t n) if (c >= 0xc2) { if (c < 0xe0) - { - if (n >= 2) - { - if ((s[1] ^ 0x80) < 0x40) - { - *puc = ((unsigned int) (c & 0x1f) << 6) - | (unsigned int) (s[1] ^ 0x80); - return 2; - } - /* invalid multibyte character */ - } - else - { - /* incomplete multibyte character */ - *puc = 0xfffd; - return n; - } - } + { + if (n >= 2) + { + if ((s[1] ^ 0x80) < 0x40) + { + *puc = ((unsigned int) (c & 0x1f) << 6) + | (unsigned int) (s[1] ^ 0x80); + return 2; + } + /* invalid multibyte character */ + } + else + { + /* incomplete multibyte character */ + *puc = 0xfffd; + return 1; + } + } else if (c < 0xf0) - { - if (n >= 3) - { - if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 - && (c >= 0xe1 || s[1] >= 0xa0) - && (c != 0xed || s[1] < 0xa0)) - { - *puc = ((unsigned int) (c & 0x0f) << 12) - | ((unsigned int) (s[1] ^ 0x80) << 6) - | (unsigned int) (s[2] ^ 0x80); - return 3; - } - /* invalid multibyte character */ - } - else - { - /* incomplete multibyte character */ - *puc = 0xfffd; - return n; - } - } + { + if (n >= 3) + { + if ((s[1] ^ 0x80) < 0x40) + { + if ((s[2] ^ 0x80) < 0x40) + { + if ((c >= 0xe1 || s[1] >= 0xa0) + && (c != 0xed || s[1] < 0xa0)) + { + *puc = ((unsigned int) (c & 0x0f) << 12) + | ((unsigned int) (s[1] ^ 0x80) << 6) + | (unsigned int) (s[2] ^ 0x80); + return 3; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 2; + } + /* invalid multibyte character */ + } + else + { + /* incomplete multibyte character */ + *puc = 0xfffd; + if (n == 1 || (s[1] ^ 0x80) >= 0x40) + return 1; + else + return 2; + } + } else if (c < 0xf8) - { - if (n >= 4) - { - if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 - && (s[3] ^ 0x80) < 0x40 - && (c >= 0xf1 || s[1] >= 0x90) + { + if (n >= 4) + { + if ((s[1] ^ 0x80) < 0x40) + { + if ((s[2] ^ 0x80) < 0x40) + { + if ((s[3] ^ 0x80) < 0x40) + { + if ((c >= 0xf1 || s[1] >= 0x90) #if 1 - && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)) + && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)) #endif - ) - { - *puc = ((unsigned int) (c & 0x07) << 18) - | ((unsigned int) (s[1] ^ 0x80) << 12) - | ((unsigned int) (s[2] ^ 0x80) << 6) - | (unsigned int) (s[3] ^ 0x80); - return 4; - } - /* invalid multibyte character */ - } - else - { - /* incomplete multibyte character */ - *puc = 0xfffd; - return n; - } - } + ) + { + *puc = ((unsigned int) (c & 0x07) << 18) + | ((unsigned int) (s[1] ^ 0x80) << 12) + | ((unsigned int) (s[2] ^ 0x80) << 6) + | (unsigned int) (s[3] ^ 0x80); + return 4; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 4; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 2; + } + /* invalid multibyte character */ + } + else + { + /* incomplete multibyte character */ + *puc = 0xfffd; + if (n == 1 || (s[1] ^ 0x80) >= 0x40) + return 1; + else if (n == 2 || (s[2] ^ 0x80) >= 0x40) + return 2; + else + return 3; + } + } #if 0 else if (c < 0xfc) - { - if (n >= 5) - { - if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 - && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40 - && (c >= 0xf9 || s[1] >= 0x88)) - { - *puc = ((unsigned int) (c & 0x03) << 24) - | ((unsigned int) (s[1] ^ 0x80) << 18) - | ((unsigned int) (s[2] ^ 0x80) << 12) - | ((unsigned int) (s[3] ^ 0x80) << 6) - | (unsigned int) (s[4] ^ 0x80); - return 5; - } - /* invalid multibyte character */ - } - else - { - /* incomplete multibyte character */ - *puc = 0xfffd; - return n; - } - } + { + if (n >= 5) + { + if ((s[1] ^ 0x80) < 0x40) + { + if ((s[2] ^ 0x80) < 0x40) + { + if ((s[3] ^ 0x80) < 0x40) + { + if ((s[4] ^ 0x80) < 0x40) + { + if (c >= 0xf9 || s[1] >= 0x88) + { + *puc = ((unsigned int) (c & 0x03) << 24) + | ((unsigned int) (s[1] ^ 0x80) << 18) + | ((unsigned int) (s[2] ^ 0x80) << 12) + | ((unsigned int) (s[3] ^ 0x80) << 6) + | (unsigned int) (s[4] ^ 0x80); + return 5; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 5; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 4; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + return 2; + } + /* invalid multibyte character */ + } + else + { + /* incomplete multibyte character */ + *puc = 0xfffd; + return n; + } + } else if (c < 0xfe) - { - if (n >= 6) - { - if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 - && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40 - && (s[5] ^ 0x80) < 0x40 - && (c >= 0xfd || s[1] >= 0x84)) - { - *puc = ((unsigned int) (c & 0x01) << 30) - | ((unsigned int) (s[1] ^ 0x80) << 24) - | ((unsigned int) (s[2] ^ 0x80) << 18) - | ((unsigned int) (s[3] ^ 0x80) << 12) - | ((unsigned int) (s[4] ^ 0x80) << 6) - | (unsigned int) (s[5] ^ 0x80); - return 6; - } - /* invalid multibyte character */ - } - else - { - /* incomplete multibyte character */ - *puc = 0xfffd; - return n; - } - } + { + if (n >= 6) + { + if ((s[1] ^ 0x80) < 0x40) + { + if ((s[2] ^ 0x80) < 0x40) + { + if ((s[3] ^ 0x80) < 0x40) + { + if ((s[4] ^ 0x80) < 0x40) + { + if ((s[5] ^ 0x80) < 0x40) + { + if (c >= 0xfd || s[1] >= 0x84) + { + *puc = ((unsigned int) (c & 0x01) << 30) + | ((unsigned int) (s[1] ^ 0x80) << 24) + | ((unsigned int) (s[2] ^ 0x80) << 18) + | ((unsigned int) (s[3] ^ 0x80) << 12) + | ((unsigned int) (s[4] ^ 0x80) << 6) + | (unsigned int) (s[5] ^ 0x80); + return 6; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 6; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 5; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 4; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + return 2; + } + /* invalid multibyte character */ + } + else + { + /* incomplete multibyte character */ + *puc = 0xfffd; + return n; + } + } #endif } /* invalid multibyte character */