mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
6270ad5b7f
from rb_econv_stateless_encoding to apply stateless ASCII incompatible encodings such as UTF-16BE. * io.c (make_writeconv): use rb_econv_asciicompat_encoding. * transcode_data.h (rb_transcoder_asciicompat_type_t): renamed from rb_transcoder_stateful_type_t. (rb_transcoder): use rb_transcoder_asciicompat_type_t. * transcode.c: follow the type change. (asciicompat_encoding_i): renamed from stateless_encoding_i. (rb_econv_asciicompat_encoding): renamed from rb_econv_stateless_encoding. (econv_s_asciicompat_encoding): method renamed. * tool/transcode-tblgen.rb: follow the type change. * enc/trans/utf_16_32.trans: follow the type change. rb_from_UTF_16BE to UTF-8 is asciicompat_decoder. rb_from_UTF_16LE to UTF-8 is asciicompat_decoder. rb_from_UTF_32BE to UTF-8 is asciicompat_decoder. rb_from_UTF_32LE to UTF-8 is asciicompat_decoder. UTF-8 to rb_to_UTF_16BE is asciicompat_encoder. UTF-8 to rb_to_UTF_16LE is asciicompat_encoder. UTF-8 to rb_to_UTF_32BE is asciicompat_encoder. UTF-8 to rb_to_UTF_32LE is asciicompat_encoder. * enc/trans/newline.trans: follow the type change. universal newline decoder is asciicompat_converter. * enc/trans/escape.trans: follow the type change. * enc/trans/iso2022.trans: ditto. * enc/trans/japanese.trans: ditto. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@19249 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
97 lines
4.1 KiB
C
97 lines
4.1 KiB
C
/**********************************************************************
|
|
|
|
transcode_data.h -
|
|
|
|
$Author$
|
|
created at: Mon 10 Dec 2007 14:01:47 JST 2007
|
|
|
|
Copyright (C) 2007 Martin Duerst
|
|
|
|
**********************************************************************/
|
|
|
|
#include "ruby/ruby.h"
|
|
|
|
#ifndef RUBY_TRANSCODE_DATA_H
|
|
#define RUBY_TRANSCODE_DATA_H 1
|
|
|
|
#define WORDINDEX_SHIFT_BITS 2
|
|
#define WORDINDEX2INFO(widx) ((widx) << WORDINDEX_SHIFT_BITS)
|
|
#define INFO2WORDINDEX(info) ((info) >> WORDINDEX_SHIFT_BITS)
|
|
#define BYTE_LOOKUP_BASE(bl) ((bl)[0])
|
|
#define BYTE_LOOKUP_INFO(bl) ((bl)[1])
|
|
|
|
#define PType (unsigned int)
|
|
|
|
#define NOMAP (PType 0x01) /* single byte direct map */
|
|
#define ONEbt (0x02) /* one byte payload */
|
|
#define TWObt (0x03) /* two bytes payload */
|
|
#define THREEbt (0x05) /* three bytes payload */
|
|
#define FOURbt (0x06) /* four bytes payload, UTF-8 only, macros start at getBT0 */
|
|
#define INVALID (PType 0x07) /* invalid byte sequence */
|
|
#define UNDEF (PType 0x09) /* legal but undefined */
|
|
#define ZERObt (PType 0x0A) /* zero bytes of payload, i.e. remove */
|
|
#define FUNii (PType 0x0B) /* function from info to info */
|
|
#define FUNsi (PType 0x0D) /* function from start to info */
|
|
#define FUNio (PType 0x0E) /* function from info to output */
|
|
#define FUNso (PType 0x0F) /* function from start to output */
|
|
#define STR1 (PType 0x11) /* string up to 255 bytes: 1byte length + content */
|
|
|
|
#define STR1_BYTEINDEX(w) ((w) >> 6)
|
|
#define makeSTR1(bi) (((bi) << 6) | STR1)
|
|
|
|
#define o1(b1) (PType((((unsigned char)(b1))<<8)|ONEbt))
|
|
#define o2(b1,b2) (PType((((unsigned char)(b1))<<8)|(((unsigned char)(b2))<<16)|TWObt))
|
|
#define o3(b1,b2,b3) (PType(((((unsigned char)(b1))<<8)|(((unsigned char)(b2))<<16)|(((unsigned char)(b3))<<24)|THREEbt)&0xffffffffU))
|
|
#define o4(b0,b1,b2,b3) (PType(((((unsigned char)(b1))<< 8)|(((unsigned char)(b2))<<16)|(((unsigned char)(b3))<<24)|((((unsigned char)(b0))&0x07)<<5)|FOURbt)&0xffffffffU))
|
|
|
|
#define getBT1(a) (((a)>> 8)&0xFF)
|
|
#define getBT2(a) (((a)>>16)&0xFF)
|
|
#define getBT3(a) (((a)>>24)&0xFF)
|
|
#define getBT0(a) ((((a)>> 5)&0x07)|0xF0) /* for UTF-8 only!!! */
|
|
|
|
#define o2FUNii(b1,b2) (PType((((unsigned char)(b1))<<8)|(((unsigned char)(b2))<<16)|FUNii))
|
|
|
|
/* do we need these??? maybe not, can be done with simple tables */
|
|
#define ONETRAIL /* legal but undefined if one more trailing UTF-8 */
|
|
#define TWOTRAIL /* legal but undefined if two more trailing UTF-8 */
|
|
#define THREETRAIL /* legal but undefined if three more trailing UTF-8 */
|
|
|
|
typedef enum {
|
|
asciicompat_converter, /* ASCII-compatible -> ASCII-compatible */
|
|
asciicompat_decoder, /* ASCII-incompatible -> ASCII-compatible */
|
|
asciicompat_encoder /* ASCII-compatible -> ASCII-incompatible */
|
|
/* ASCII-incompatible -> ASCII-incompatible is intentionally ommitted. */
|
|
} rb_transcoder_asciicompat_type_t;
|
|
|
|
typedef struct rb_transcoder rb_transcoder;
|
|
|
|
/* static structure, one per supported encoding pair */
|
|
struct rb_transcoder {
|
|
const char *src_encoding;
|
|
const char *dst_encoding;
|
|
unsigned int conv_tree_start;
|
|
const unsigned char *byte_array;
|
|
unsigned int byte_array_length;
|
|
const unsigned int *word_array;
|
|
unsigned int word_array_length;
|
|
int word_size;
|
|
int input_unit_length;
|
|
int max_input;
|
|
int max_output;
|
|
rb_transcoder_asciicompat_type_t asciicompat_type;
|
|
size_t state_size;
|
|
int (*state_init_func)(void*); /* ret==0:success ret!=0:failure(errno) */
|
|
int (*state_fini_func)(void*); /* ret==0:success ret!=0:failure(errno) */
|
|
VALUE (*func_ii)(void*, VALUE); /* info -> info */
|
|
VALUE (*func_si)(void*, const unsigned char*, size_t); /* start -> info */
|
|
int (*func_io)(void*, VALUE, const unsigned char*); /* info -> output */
|
|
int (*func_so)(void*, const unsigned char*, size_t, unsigned char*); /* start -> output */
|
|
int (*finish_func)(void*, unsigned char*); /* -> output */
|
|
int (*resetsize_func)(void*); /* -> len */
|
|
int (*resetstate_func)(void*, unsigned char*); /* -> output */
|
|
};
|
|
|
|
void rb_declare_transcoder(const char *enc1, const char *enc2, const char *lib);
|
|
void rb_register_transcoder(const rb_transcoder *);
|
|
|
|
#endif /* RUBY_TRANSCODE_DATA_H */
|