From 554fd8c5195424bdbcabf5de30fdc183aba391bd Mon Sep 17 00:00:00 2001 From: upstream source tree Date: Sun, 15 Mar 2015 20:14:05 -0400 Subject: obtained gcc-4.6.4.tar.bz2 from upstream website; verified gcc-4.6.4.tar.bz2.sig; imported gcc-4.6.4 source tree from verified upstream tarball. downloading a git-generated archive based on the 'upstream' tag should provide you with a source tree that is binary identical to the one extracted from the above tarball. if you have obtained the source via the command 'git clone', however, do note that line-endings of files in your working directory might differ from line-endings of the respective files in the upstream repository. --- libjava/gnu/gcj/convert/natInput_EUCJIS.cc | 101 +++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) create mode 100644 libjava/gnu/gcj/convert/natInput_EUCJIS.cc (limited to 'libjava/gnu/gcj/convert/natInput_EUCJIS.cc') diff --git a/libjava/gnu/gcj/convert/natInput_EUCJIS.cc b/libjava/gnu/gcj/convert/natInput_EUCJIS.cc new file mode 100644 index 000000000..42562b9cb --- /dev/null +++ b/libjava/gnu/gcj/convert/natInput_EUCJIS.cc @@ -0,0 +1,101 @@ +/* Copyright (C) 1999 Free Software Foundation + + This file is part of libgcj. + +This software is copyrighted work licensed under the terms of the +Libgcj License. Please consult the file "LIBGCJ_LICENSE" for +details. */ + +#include +#include +#include + +#define ERROR_CHAR 0xFFFD + +extern unsigned short JIS0208_to_Unicode[84][94]; +extern unsigned short JIS0212_to_Unicode[76][94]; + +jint +gnu::gcj::convert::Input_EUCJIS::read(jcharArray outbuffer, jint outpos, + jint count) +{ + jint start_outpos = outpos; + for (;;) + { + if (outpos - start_outpos >= count) + break; + if (inpos >= inlength) + break; + int b = ((unsigned char*) elements(inbuffer))[inpos++]; + if (codeset == 0) // ASCII or JIS-Roman + { + if (b < 128) + { +#if 1 + // Technically, we should translate 0x5c to Yen symbol; + // in practice, it is not clear. + if (b == 0x5c) + b = 0x00A5; // Yen sign. +#endif + elements(outbuffer)[outpos++] = (char) b; + } + else + { + if (b == 0x8E) // SS2 + codeset = 2; + else if (b == 0x8F) // SS3 + codeset = 3; + else + { + codeset = 1; + first_byte = b; + } + } + } + else if (codeset == 1) // JIS X 0208:1997 + { + first_byte -= 0x80 + 33; + b -= 0x80 + 33; + if ((unsigned) first_byte >= 84 || (unsigned) b >= 94) + b = ERROR_CHAR; + else + { + b = JIS0208_to_Unicode[first_byte][b]; + if (b == 0) + b = ERROR_CHAR; + } + elements(outbuffer)[outpos++] = b; + codeset = 0; + } + else if (codeset == 2) // Half-width katakana + { + if (b >= 0xA1 && b <= 0xDF) + b += 0xFF61 - 0xA1; + else + b = ERROR_CHAR; + elements(outbuffer)[outpos++] = b; + codeset = 0; + } + else if (codeset == 3) // second byte of JIS X 0212-1990 + { + first_byte = b; + codeset = 4; + } + else // codeset == 4 // third byte of JIS X 0212-1990 + { + first_byte -= 0x80 + 34; + b -= 0x80 + 33; + if ((unsigned) first_byte >= 76 || (unsigned) b >= 94) + b = ERROR_CHAR; + else + { + b = JIS0208_to_Unicode[first_byte][b]; + if (b == 0) + b = ERROR_CHAR; + } + elements(outbuffer)[outpos++] = b; + codeset = 0; + } + } + return outpos - start_outpos; +} -- cgit v1.2.3