encoding.h revision d46ee884c41b808b239563b1978468aae12e33a2
/*
* Summary: interface for the encoding conversion functions
* Description: interface for the encoding conversion functions needed for
* XML basic encoding and iconv() support.
*
* Related specs are
* rfc2044 (UTF-8 and UTF-16) F. Yergeau Alis Technologies
* [ISO-10646] UTF-8 and UTF-16 in Annexes
* [ISO-8859-1] ISO Latin-1 characters codes.
* [UNICODE] The Unicode Consortium, "The Unicode Standard --
* Worldwide Character Encoding -- Version 1.0", Addison-
* Wesley, Volume 1, 1991, Volume 2, 1992. UTF-8 is
* described in Unicode Technical Report #4.
* [US-ASCII] Coded Character Set--7-bit American Standard Code for
* Information Interchange, ANSI X3.4-1986.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_CHAR_ENCODING_H__
#define __XML_CHAR_ENCODING_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_ICONV_ENABLED
#include <iconv.h>
#endif
#ifdef __cplusplus
extern "C" {
#endif
/*
* xmlCharEncoding:
*
* Predefined values for some standard encodings.
* Libxml does not do beforehand translation on UTF8 and ISOLatinX.
* It also supports ASCII, ISO-8859-1, and UTF16 (LE and BE) by default.
*
* Anything else would have to be translated to UTF8 before being
* given to the parser itself. The BOM for UTF16 and the encoding
* declaration are looked at and a converter is looked for at that
* point. If not found the parser stops here as asked by the XML REC. A
* converter can be registered by the user using xmlRegisterCharEncodingHandler
* but the current form doesn't allow stateful transcoding (a serious
* problem agreed !). If iconv has been found it will be used
* automatically and allow stateful transcoding, the simplest is then
* to be sure to enable iconv and to provide iconv libs for the encoding
* support needed.
*
* Note that the generic "UTF-16" is not a predefined value. Instead, only
* the specific UTF-16LE and UTF-16BE are present.
*/
typedef enum {
XML_CHAR_ENCODING_NONE= 0, /* No char encoding detected */
/**
* xmlCharEncodingInputFunc:
* @out: a pointer to an array of bytes to store the UTF-8 result
* @outlen: the length of @out
* @in: a pointer to an array of chars in the original encoding
* @inlen: the length of @in
*
* Take a block of chars in the original encoding and try to convert
* it to an UTF-8 block of chars out.
*
* Returns the number of bytes written, -1 if lack of space, or -2
* if the transcoding failed.
* The value of @inlen after return is the number of octets consumed
* if the return value is positive, else unpredictiable.
* The value of @outlen after return is the number of octets consumed.
*/
/**
* xmlCharEncodingOutputFunc:
* @out: a pointer to an array of bytes to store the result
* @outlen: the length of @out
* @in: a pointer to an array of UTF-8 chars
* @inlen: the length of @in
*
* Take a block of UTF-8 chars in and try to convert it to another
* encoding.
* Note: a first call designed to produce heading info is called with
* in = NULL. If stateful this should also initialize the encoder state.
*
* Returns the number of bytes written, -1 if lack of space, or -2
* if the transcoding failed.
* The value of @inlen after return is the number of octets consumed
* if the return value is positive, else unpredictiable.
* The value of @outlen after return is the number of octets produced.
*/
/*
* Block defining the handlers for non UTF-8 encodings.
* If iconv is supported, there are two extra fields.
*/
typedef struct _xmlCharEncodingHandler xmlCharEncodingHandler;
struct _xmlCharEncodingHandler {
char *name;
#ifdef LIBXML_ICONV_ENABLED
#endif /* LIBXML_ICONV_ENABLED */
};
#ifdef __cplusplus
}
#endif
#ifdef __cplusplus
extern "C" {
#endif
/*
* Interfaces for encoding handlers.
*/
xmlInitCharEncodingHandlers (void);
xmlCleanupCharEncodingHandlers (void);
xmlFindCharEncodingHandler (const char *name);
xmlNewCharEncodingHandler (const char *name,
/*
* Interfaces for encoding names and aliases.
*/
xmlAddEncodingAlias (const char *name,
const char *alias);
xmlDelEncodingAlias (const char *alias);
xmlGetEncodingAlias (const char *alias);
xmlCleanupEncodingAliases (void);
xmlParseCharEncoding (const char *name);
/*
* Interfaces directly used by the parsers.
*/
xmlDetectCharEncoding (const unsigned char *in,
int len);
/*
* Export a few useful functions
*/
#ifdef LIBXML_OUTPUT_ENABLED
UTF8Toisolat1 (unsigned char *out,
int *outlen,
const unsigned char *in,
int *inlen);
#endif /* LIBXML_OUTPUT_ENABLED */
isolat1ToUTF8 (unsigned char *out,
int *outlen,
const unsigned char *in,
int *inlen);
#ifdef __cplusplus
}
#endif
#endif /* __XML_CHAR_ENCODING_H__ */