Aren
/
haiku
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Unlike what shatty wrote in his commit messages, convert_from_utf8() does return 

B_OK here when called with an empty string.
Since this is the natural thing to expect anyway, I changed our version to return
a sane value here as well - if this causes an error within our StyledEdit, as
shatty writes, we should just fix our StyledEdit.
Cleanup to match our style guides a bit better, added license.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16328 a95241bf-73f2-0310-859d-f6bbb57e9c96
This commit is contained in:
Axel Dörfler 2006-02-10 12:00:38 +00:00
parent a544829365
commit cf45491bc8
1 changed files with 93 additions and 81 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

174
src/kits/textencoding/utf8_conversions.cpp
View File

@ -1,122 +1,129 @@
#include <UTF8.h>
#include <iconv.h>
/*
* Copyright 2003-2006, Haiku, Inc. All Rights Reserved.
* Distributed under the terms of the MIT License.
*
* Authors:
* Andrew Bachmann
*/
#include <CharacterSet.h>
#include <CharacterSetRoster.h>
#include <Errors.h>
#include <UTF8.h>
#include <errno.h>
#include <iconv.h>
#include <stdio.h>
#include <Debug.h>
//#define DEBUG_CONV 1
#ifdef DEBUG_CONV
#define DEBPRINT(ARGS) printf ARGS;
# define DEBPRINT(ARGS) printf ARGS;
#else
#define DEBPRINT(ARGS) ;
# define DEBPRINT(ARGS) ;
#endif
using namespace BPrivate;
typedef char ** input_buffer_t;
int iconvctl(iconv_t icd, int request, void* argument);
int iconvctl (iconv_t icd, int request, void* argument);
status_t
convert_encoding(const char * from, const char * to,
const char * src, int32 * srcLen,
char * dst, int32 * dstLen,
int32 * state, char substitute)
convert_encoding(const char* from, const char* to, const char* src,
int32* srcLen, char* dst, int32* dstLen, int32* state,
char substitute)
{
status_t status;
if (*srcLen == 0) {
// nothing to do!
DEBPRINT(("nothing to do\n"));
*dstLen = 0;
return B_ERROR;
return B_OK;
}
iconv_t conversion = iconv_open(to,from);
iconv_t conversion = iconv_open(to, from);
if (conversion == (iconv_t)-1) {
DEBPRINT(("iconv_open failed\n"));
return B_ERROR;
}
if ((state == NULL) || (*state == 0)) {
iconv(conversion,0,0,0,0);
}
input_buffer_t inputBuffer = const_cast<input_buffer_t>(&src);
if (state == NULL || *state == 0)
iconv(conversion, 0, 0, 0, 0);
char** inputBuffer = const_cast<char**>(&src);
size_t inputLeft = *srcLen;
size_t outputLeft = *dstLen;
do {
size_t nonReversibleConversions = iconv(conversion,inputBuffer,&inputLeft,&dst,&outputLeft);
size_t nonReversibleConversions = iconv(conversion, inputBuffer,
&inputLeft, &dst, &outputLeft);
if (nonReversibleConversions == (size_t)-1) {
if (errno == E2BIG) {
// Not enough room in the output buffer for the next converted character
// This is not a "real" error, we just quit out.
break;
}
switch (errno) {
case EILSEQ: // unable to generate a corresponding character
case EILSEQ: // unable to generate a corresponding character
{
// discard the input character
const int one = 1, zero = 0;
iconvctl(conversion,ICONV_SET_DISCARD_ILSEQ,(void*)&one);
iconv(conversion,inputBuffer,&inputLeft,&dst,&outputLeft);
iconvctl(conversion,ICONV_SET_DISCARD_ILSEQ,(void*)&zero);
// prepare to convert the substitute character to target encoding
char * original = new char[1];
original[0] = substitute;
size_t len = 1;
char * copy = original;
// Perform the conversion
// We ignore any errors during this as part of robustness/best-effort
// We use ISO-8859-1 as a source because it is a single byte encoding
// It also overlaps UTF-8 for the lower 128 characters. It is also
// likely to have a mapping to almost any target encoding.
iconv_t iso8859_1to = iconv_open(to,"ISO-8859-1");
if (iso8859_1to != (iconv_t)-1) {
iconv(iso8859_1to,0,0,0,0);
iconv(iso8859_1to,const_cast<input_buffer_t>(&copy),&len,&dst,&outputLeft);
iconv_close(iso8859_1to);
// discard the input character
const int one = 1, zero = 0;
iconvctl(conversion, ICONV_SET_DISCARD_ILSEQ, (void*)&one);
iconv(conversion, inputBuffer, &inputLeft, &dst, &outputLeft);
iconvctl(conversion, ICONV_SET_DISCARD_ILSEQ, (void*)&zero);
// prepare to convert the substitute character to target encoding
char* original = new char[1];
original[0] = substitute;
size_t len = 1;
char* copy = original;
// Perform the conversion
// We ignore any errors during this as part of robustness/best-effort
// We use ISO-8859-1 as a source because it is a single byte encoding
// It also overlaps UTF-8 for the lower 128 characters. It is also
// likely to have a mapping to almost any target encoding.
iconv_t iso8859_1to = iconv_open(to,"ISO-8859-1");
if (iso8859_1to != (iconv_t)-1) {
iconv(iso8859_1to, 0, 0, 0, 0);
iconv(iso8859_1to, const_cast<char**>(&copy), &len, &dst,
&outputLeft);
iconv_close(iso8859_1to);
}
delete original;
break;
}
delete original;
}
break;
case EINVAL: // incomplete multibyte sequence in the input
// we just eat bad bytes, as part of robustness/best-effort
inputBuffer++;
inputLeft--;
break;
default:
// unknown error, completely bail
status = errno;
iconv_close(conversion);
return status;
case EINVAL: // incomplete multibyte sequence in the input
// we just eat bad bytes, as part of robustness/best-effort
inputBuffer++;
inputLeft--;
break;
default:
// unknown error, completely bail
status_t status = errno;
iconv_close(conversion);
return status;
}
}
} while ((inputLeft > 0) && (outputLeft > 0));
} while (inputLeft > 0 && outputLeft > 0);
*srcLen -= inputLeft;
*dstLen -= outputLeft;
iconv_close(conversion);
if (*srcLen != 0) {
// able to convert at least one character
DEBPRINT(("able to convert at least one character\n"));
return B_OK;
} else {
// not able to convert at least one character
DEBPRINT(("not able to convert at least one character\n"));
return B_ERROR;
}
return B_OK;
}
status_t
convert_to_utf8(uint32 srcEncoding,
const char * src, int32 * srcLen,
char * dst, int32 * dstLen,
int32 * state, char substitute)
convert_to_utf8(uint32 srcEncoding, const char* src, int32* srcLen,
char* dst, int32* dstLen, int32* state, char substitute)
{
const BCharacterSet * charset = BCharacterSetRoster::GetCharacterSetByConversionID(srcEncoding);
if (charset == 0) {
const BCharacterSet* charset = BCharacterSetRoster::GetCharacterSetByConversionID(
srcEncoding);
if (charset == NULL)
return B_ERROR;
}
#if DEBUG_CONV
fprintf(stderr, "convert_to_utf8(%s) : \"", charset->GetName());
for (int i = 0 ; i < *srcLen ; i++) {
@ -124,19 +131,21 @@ convert_to_utf8(uint32 srcEncoding,
}
fprintf(stderr, "\"\n");
#endif
return convert_encoding(charset->GetName(),"UTF-8",src,srcLen,dst,dstLen,state,substitute);
return convert_encoding(charset->GetName(), "UTF-8", src, srcLen,
dst, dstLen, state, substitute);
}
status_t
convert_from_utf8(uint32 dstEncoding,
const char * src, int32 * srcLen,
char * dst, int32 * dstLen,
int32 * state, char substitute)
convert_from_utf8(uint32 dstEncoding, const char* src, int32* srcLen,
char* dst, int32* dstLen, int32* state, char substitute)
{
const BCharacterSet * charset = BCharacterSetRoster::GetCharacterSetByConversionID(dstEncoding);
if (charset == 0) {
const BCharacterSet* charset = BCharacterSetRoster::GetCharacterSetByConversionID(
dstEncoding);
if (charset == NULL)
return B_ERROR;
}
#if DEBUG_CONV
fprintf(stderr, "convert_from_utf8(%s) : \"", charset->GetName());
for (int i = 0 ; i < *srcLen ; i++) {
@ -144,5 +153,8 @@ convert_from_utf8(uint32 dstEncoding,
}
fprintf(stderr, "\"\n");
#endif
return convert_encoding("UTF-8",charset->GetName(),src,srcLen,dst,dstLen,state,substitute);
return convert_encoding("UTF-8", charset->GetName(), src, srcLen,
dst, dstLen, state, substitute);
}