mirror of
https://github.com/darlinghq/darling-libxml2.git
synced 2025-03-09 05:20:53 +00:00
Added the UTF-8, UTF-16 and ISO Lat 1 conversion routines, not yet used, Daniel.
This commit is contained in:
Daniel Veillard
parent
33942846fc
commit
891e404a09
@ -1,3 +1,9 @@
|
||||
Sun Oct 18 20:40:58 EDT 1998
|
||||
|
||||
* encoding.[ch], Makefile.am: Added the UTF-8, UTF-16 and ISO Latin 1
|
||||
conversion routines. However they are not yet used to convert the
|
||||
inputs. The core will run with UTF-8.
|
||||
|
||||
Sun Oct 18 15:08:19 EDT 1998 Daniel Veillard <Daniel.Veillard@w3.org>
|
||||
|
||||
* tree.c : make sure that the type id is properly set-up when
|
||||
|
||||
@ -11,6 +11,7 @@ lib_LTLIBRARIES = libxml.la
|
||||
libxml_la_SOURCES = \
|
||||
SAX.c \
|
||||
entities.c \
|
||||
encoding.c \
|
||||
error.c \
|
||||
error.h \
|
||||
parser.c \
|
||||
@ -20,6 +21,7 @@ libxml_la_SOURCES = \
|
||||
xmlincdir = $(includedir)/gnome-xml
|
||||
xmlinc_HEADERS = \
|
||||
entities.h \
|
||||
encoding.h \
|
||||
parser.h \
|
||||
tree.h
|
||||
|
||||
|
||||
175
encoding.c
Normal file
175
encoding.c
Normal file
@ -0,0 +1,175 @@
|
||||
/*
|
||||
* encoding.c : implements the encoding conversion functions needed for XML
|
||||
*
|
||||
* Related specs:
|
||||
* 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.
|
||||
*
|
||||
* Original code from "Martin J. Duerst" <duerst@w3.org>
|
||||
*
|
||||
* See Copyright for the status of this software.
|
||||
*
|
||||
* $Id$
|
||||
*
|
||||
* Daniel.Veillard@w3.org
|
||||
*/
|
||||
|
||||
#include "encoding.h"
|
||||
|
||||
/*
|
||||
* Take a block of ISO Latin 1 chars in and try to convert it to an UTF-8
|
||||
* block of chars out.
|
||||
*
|
||||
* Returns the number of byte written, or -1 by lack of space.
|
||||
*/
|
||||
int isolat1ToUTF8(unsigned char* out, int outlen, unsigned char* in, int inlen)
|
||||
{
|
||||
unsigned char* outstart= out;
|
||||
unsigned char* outend= out+outlen;
|
||||
unsigned char* inend= in+inlen;
|
||||
unsigned char c;
|
||||
|
||||
while (in < inend) {
|
||||
c= *in++;
|
||||
if (c < 0x80) {
|
||||
if (out >= outend) return -1;
|
||||
*out++ = c;
|
||||
}
|
||||
else {
|
||||
if (out >= outend) return -1;
|
||||
*out++ = 0xC0 | (c >> 6);
|
||||
if (out >= outend) return -1;
|
||||
*out++ = 0x80 | (0x3F & c);
|
||||
}
|
||||
}
|
||||
return out-outstart;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
* Take a block of UTF-8 chars in and try to convert it to an ISO Latin 1
|
||||
* block of chars out.
|
||||
*
|
||||
* Returns the number of byte written, or -1 by lack of space, or -2
|
||||
* if the transcoding failed.
|
||||
*
|
||||
* TODO: need a fallback mechanism ...
|
||||
*/
|
||||
int UTF8Toisolat1(unsigned char* out, int outlen, unsigned char* in, int inlen)
|
||||
{
|
||||
unsigned char* outstart= out;
|
||||
unsigned char* outend= out+outlen;
|
||||
unsigned char* inend= in+inlen;
|
||||
unsigned char c, d;
|
||||
|
||||
while (in < inend) {
|
||||
c= *in++;
|
||||
if (c < 0x80) {
|
||||
if (out >= outend) return -1;
|
||||
*out++= c;
|
||||
}
|
||||
else if (((c & 0xFE) == 0xC2) && in<inend) {
|
||||
if (out >= outend) return -1;
|
||||
*out++= ((c & 0x03) << 6) | (*in++ & 0x3F);
|
||||
}
|
||||
else return -2;
|
||||
}
|
||||
return out-outstart;
|
||||
}
|
||||
|
||||
/*
|
||||
* Take a block of UTF-16 ushorts in and try to convert it to an UTF-8
|
||||
* block of chars out.
|
||||
*
|
||||
* Returns the number of byte written, or -1 by lack of space.
|
||||
*/
|
||||
int UTF16ToUTF8(unsigned char* out, int outlen, unsigned short* in, int inlen)
|
||||
{
|
||||
unsigned char* outstart= out;
|
||||
unsigned char* outend= out+outlen;
|
||||
unsigned short* inend= in+inlen;
|
||||
unsigned int c, d;
|
||||
int bits;
|
||||
|
||||
while (in < inend) {
|
||||
c= *in++;
|
||||
if ((c & 0xFC00) == 0xD800) { /* surrogates */
|
||||
if ((in<inend) && (((d=*in++) & 0xFC00) == 0xDC00)) {
|
||||
c &= 0x03FF;
|
||||
c <<= 10;
|
||||
c |= d & 0x03FF;
|
||||
c += 0x10000;
|
||||
}
|
||||
else return -1;
|
||||
}
|
||||
|
||||
/* assertion: c is a single UTF-4 value */
|
||||
|
||||
if (out >= outend) return -1;
|
||||
if (c < 0x80) { *out++= c; bits= -6; }
|
||||
else if (c < 0x800) { *out++= (c >> 6) | 0xC0; bits= 0; }
|
||||
else if (c < 0x10000) { *out++= (c >> 12) | 0xE0; bits= 6; }
|
||||
else { *out++= (c >> 18) | 0xF0; bits= 12; }
|
||||
|
||||
for ( ; bits < 0; bits-= 6) {
|
||||
if (out >= outend) return -1;
|
||||
*out++= (c >> bits) & 0x3F;
|
||||
}
|
||||
}
|
||||
return out-outstart;
|
||||
}
|
||||
|
||||
/*
|
||||
* Take a block of UTF-8 chars in and try to convert it to an UTF-16
|
||||
* block of chars out.
|
||||
*
|
||||
* Returns the number of byte written, or -1 by lack of space, or -2
|
||||
* if the transcoding failed.
|
||||
*
|
||||
* TODO: need a fallback mechanism ...
|
||||
*/
|
||||
int UTF8ToUTF16(unsigned short* out, int outlen, unsigned char* in, int inlen)
|
||||
{
|
||||
unsigned short* outstart= out;
|
||||
unsigned short* outend= out+outlen;
|
||||
unsigned char* inend= in+inlen;
|
||||
unsigned int c, d, trailing;
|
||||
|
||||
while (in < inend) {
|
||||
d= *in++;
|
||||
if (d < 0x80) { c= d; trailing= 0; }
|
||||
else if (d < 0xC0) return -2; /* trailing byte in leading position */
|
||||
else if (d < 0xE0) { c= d & 0x1F; trailing= 1; }
|
||||
else if (d < 0xF0) { c= d & 0x0F; trailing= 2; }
|
||||
else if (d < 0xF8) { c= d & 0x07; trailing= 3; }
|
||||
else return -2; /* no chance for this in UTF-16 */
|
||||
|
||||
for ( ; trailing; trailing--) {
|
||||
if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80)) return -1;
|
||||
c <<= 6;
|
||||
c |= d & 0x3F;
|
||||
}
|
||||
|
||||
/* assertion: c is a single UTF-4 value */
|
||||
if (c < 0x10000) {
|
||||
if (out >= outend) return -1;
|
||||
*out++ = c;
|
||||
}
|
||||
else if (c < 0x110000) {
|
||||
if (out+1 >= outend) return -1;
|
||||
c -= 0x10000;
|
||||
*out++ = 0xD800 | (c >> 10);
|
||||
*out++ = 0xDC00 | (c & 0x03FF);
|
||||
}
|
||||
else return -1;
|
||||
}
|
||||
return out-outstart;
|
||||
}
|
||||
|
||||
36
encoding.h
Normal file
36
encoding.h
Normal file
@ -0,0 +1,36 @@
|
||||
/*
|
||||
* encoding.h : interface for the encoding conversion functions needed for
|
||||
* XML
|
||||
*
|
||||
* Related specs:
|
||||
* 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.
|
||||
*
|
||||
* Original code from "Martin J. Duerst" <duerst@w3.org>
|
||||
*
|
||||
* See Copyright for the status of this software.
|
||||
*
|
||||
* $Id$
|
||||
*
|
||||
* Daniel.Veillard@w3.org
|
||||
*/
|
||||
|
||||
#ifndef __XML_ENCODING_H__
|
||||
#define __XML_ENCODING_H__
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* __XML_ENCODING_H__ */
|
||||
36
include/libxml/encoding.h
Normal file
36
include/libxml/encoding.h
Normal file
@ -0,0 +1,36 @@
|
||||
/*
|
||||
* encoding.h : interface for the encoding conversion functions needed for
|
||||
* XML
|
||||
*
|
||||
* Related specs:
|
||||
* 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.
|
||||
*
|
||||
* Original code from "Martin J. Duerst" <duerst@w3.org>
|
||||
*
|
||||
* See Copyright for the status of this software.
|
||||
*
|
||||
* $Id$
|
||||
*
|
||||
* Daniel.Veillard@w3.org
|
||||
*/
|
||||
|
||||
#ifndef __XML_ENCODING_H__
|
||||
#define __XML_ENCODING_H__
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* __XML_ENCODING_H__ */
|
||||
Loading…
x
Reference in New Issue
Block a user