Edinburgh Speech Tools  2.1-release
charset.c File Reference
#include <stdio.h>
#include <stdlib.h>
#include "system.h"
#include "charset.h"
#include "string16.h"
Include dependency graph for charset.c:

Go to the source code of this file.

Functions

void init_charset (void)
 
int EncodingIsAsciiSuperset (CharacterEncoding enc)
 
int EncodingsCompatible (CharacterEncoding enc1, CharacterEncoding enc2, CharacterEncoding *enc3)
 
CharacterEncoding FindEncoding (char8 *name)
 

Variables

int iso_to_unicode [8][256]
 
int iso_max_val [8]
 
char8unicode_to_iso [8]
 
const char8CharacterEncodingName [CE_enum_count]
 
const char8CharacterEncodingNameAndByteOrder [CE_enum_count]
 
struct character_encoding_alias CharacterEncodingAlias []
 
const int CE_alias_count
 
CharacterEncoding InternalCharacterEncoding
 

Function Documentation

void init_charset ( void  )

Definition at line 233 of file charset.c.

int EncodingIsAsciiSuperset ( CharacterEncoding  enc)

Definition at line 286 of file charset.c.

int EncodingsCompatible ( CharacterEncoding  enc1,
CharacterEncoding  enc2,
CharacterEncoding enc3 
)

Definition at line 297 of file charset.c.

CharacterEncoding FindEncoding ( char8 name)

Definition at line 335 of file charset.c.

Variable Documentation

int iso_to_unicode[8][256]

Definition at line 33 of file charset.c.

int iso_max_val[8]

Definition at line 34 of file charset.c.

char8* unicode_to_iso[8]

Definition at line 35 of file charset.c.

const char8* CharacterEncodingName[CE_enum_count]
Initial value:
= {
"unknown",
"unspecified-ascii-superset",
"UTF-8",
"ISO-646",
"ISO-8859-1",
"ISO-8859-2",
"ISO-8859-3",
"ISO-8859-4",
"ISO-8859-5",
"ISO-8859-6",
"ISO-8859-7",
"ISO-8859-8",
"ISO-8859-9",
"UTF-16",
"UTF-16",
"ISO-10646-UCS-2",
"ISO-10646-UCS-2",
}

Definition at line 170 of file charset.c.

const char8* CharacterEncodingNameAndByteOrder[CE_enum_count]
Initial value:
= {
"unknown",
"unspecified_ascii_superset",
"UTF-8",
"ISO-646",
"ISO-8859-1",
"ISO-8859-2",
"ISO-8859-3",
"ISO-8859-4",
"ISO-8859-5",
"ISO-8859-6",
"ISO-8859-7",
"ISO-8859-8",
"ISO-8859-9",
"UTF-16-B",
"UTF-16-L",
"ISO-10646-UCS-2-B",
"ISO-10646-UCS-2-L",
}

Definition at line 193 of file charset.c.

struct character_encoding_alias CharacterEncodingAlias[]
Initial value:
= {
{"ASCII", CE_ISO_646},
{"ISO-Latin-1", CE_ISO_8859_1},
{"ISO-Latin-2", CE_ISO_8859_2},
{"ISO-Latin-3", CE_ISO_8859_3},
{"ISO-Latin-4", CE_ISO_8859_4},
{"ISO-Latin-5", CE_ISO_8859_5},
{"ISO-Latin-6", CE_ISO_8859_6},
{"ISO-Latin-7", CE_ISO_8859_7},
{"ISO-Latin-8", CE_ISO_8859_8},
{"UCS-2", CE_ISO_10646_UCS_2B},
}

Definition at line 216 of file charset.c.

const int CE_alias_count
Initial value:
=
struct character_encoding_alias CharacterEncodingAlias[]
Definition: charset.c:216

Definition at line 228 of file charset.c.

CharacterEncoding InternalCharacterEncoding

Definition at line 231 of file charset.c.