X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Funistr%2Fu8-strmbtouc.c;h=e15a7a15bfae69c6d8014b1ddc72d72c8fb55725;hb=ddf6704b29173e809f3b0150c015ca282e06388f;hp=bc2fdb0de67af9020439fe7fa596b0e400a546b1;hpb=ac5cf7982cea8a4bb17680b6b9925f301cfa4220;p=gnulib.git diff --git a/lib/unistr/u8-strmbtouc.c b/lib/unistr/u8-strmbtouc.c index bc2fdb0de..e15a7a15b 100644 --- a/lib/unistr/u8-strmbtouc.c +++ b/lib/unistr/u8-strmbtouc.c @@ -1,5 +1,6 @@ /* Look at first character in UTF-8 string. - Copyright (C) 1999-2000, 2002, 2006-2007 Free Software Foundation, Inc. + Copyright (C) 1999-2000, 2002, 2006-2007, 2009-2011 Free Software + Foundation, Inc. Written by Bruno Haible , 2002. This program is free software: you can redistribute it and/or modify it @@ -23,7 +24,7 @@ int u8_strmbtouc (ucs4_t *puc, const uint8_t *s) { - /* Keep in sync with unistr.h and utf8-ucs4.c. */ + /* Keep in sync with unistr.h and u8-mbtouc-aux.c. */ uint8_t c = *s; if (c < 0x80) @@ -34,94 +35,94 @@ u8_strmbtouc (ucs4_t *puc, const uint8_t *s) if (c >= 0xc2) { if (c < 0xe0) - { + { #if CONFIG_UNICODE_SAFETY - if ((s[1] ^ 0x80) < 0x40) + if ((s[1] ^ 0x80) < 0x40) #else - if (s[1] != 0) + if (s[1] != 0) #endif - { - *puc = ((unsigned int) (c & 0x1f) << 6) - | (unsigned int) (s[1] ^ 0x80); - return 2; - } - } + { + *puc = ((unsigned int) (c & 0x1f) << 6) + | (unsigned int) (s[1] ^ 0x80); + return 2; + } + } else if (c < 0xf0) - { + { #if CONFIG_UNICODE_SAFETY - if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 - && (c >= 0xe1 || s[1] >= 0xa0) - && (c != 0xed || s[1] < 0xa0)) + if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 + && (c >= 0xe1 || s[1] >= 0xa0) + && (c != 0xed || s[1] < 0xa0)) #else - if (s[1] != 0 && s[2] != 0) + if (s[1] != 0 && s[2] != 0) #endif - { - *puc = ((unsigned int) (c & 0x0f) << 12) - | ((unsigned int) (s[1] ^ 0x80) << 6) - | (unsigned int) (s[2] ^ 0x80); - return 3; - } - } + { + *puc = ((unsigned int) (c & 0x0f) << 12) + | ((unsigned int) (s[1] ^ 0x80) << 6) + | (unsigned int) (s[2] ^ 0x80); + return 3; + } + } else if (c < 0xf8) - { + { #if CONFIG_UNICODE_SAFETY - if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 - && (s[3] ^ 0x80) < 0x40 - && (c >= 0xf1 || s[1] >= 0x90) + if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 + && (s[3] ^ 0x80) < 0x40 + && (c >= 0xf1 || s[1] >= 0x90) #if 1 - && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)) + && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)) #endif - ) + ) #else - if (s[1] != 0 && s[2] != 0 && s[3] != 0) + if (s[1] != 0 && s[2] != 0 && s[3] != 0) #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; - } - } + { + *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; + } + } #if 0 else if (c < 0xfc) - { + { #if CONFIG_UNICODE_SAFETY - if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 - && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40 - && (c >= 0xf9 || s[1] >= 0x88)) + if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 + && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40 + && (c >= 0xf9 || s[1] >= 0x88)) #else - if (s[1] != 0 && s[2] != 0 && s[3] != 0 && s[4] != 0) + if (s[1] != 0 && s[2] != 0 && s[3] != 0 && s[4] != 0) #endif - { - *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; - } - } + { + *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; + } + } else if (c < 0xfe) - { + { #if CONFIG_UNICODE_SAFETY - 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)) + 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)) #else - if (s[1] != 0 && s[2] != 0 && s[3] != 0 && s[4] != 0 && s[5] != 0) + if (s[1] != 0 && s[2] != 0 && s[3] != 0 && s[4] != 0 && s[5] != 0) #endif - { - *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; - } - } + { + *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; + } + } #endif } /* invalid or incomplete multibyte character */