libxml中文解决方案
网摘1：
使用libxml2处理xml文件时，默认加载是使用utf-8编码，所以在修改和保存为GB2312编码时，需要将数据转换为utf-8编码，然后再进行修改和保存！
转换使用iconv，以下是转换代码
char * ConvertEnc( char *encFrom, char *encTo, const char * in)
{
static char bufin[1024], bufout[1024], *sin, *sout;
int mode, lenin, lenout, ret, nline;
iconv_t c_pt;
if ((c_pt = iconv_open(encTo, encFrom)) == (iconv_t)-1)
{
printf("iconv_open false: %s ==> %s", encFrom, encTo);
return NULL;
}
iconv(c_pt, NULL, NULL, NULL, NULL);
lenin = strlen(in) + 1;
lenout = 1024;
sin = (char *)in;
sout = bufout;
ret = iconv(c_pt, &sin, (size_t *)&lenin, &sout, (size_t *)&lenout);
if (ret == -1)
{
return NULL;
}
iconv_close(c_pt);
return bufout;
}
以下是实例
test.xml
<?xml version="1.0" encoding="gb2312"?>
<parent>测试</parent>
读取代码
int main(void)
{
xmlDocPtr doc = NULL;
xmlNodePtr cur = NULL;
doc = xmlParseFile("test.xml");
cur = xmlDocGetRootElement(doc);
printf("%s", Convert("utf-8", "gb2312", (char *)xmlNodeGetContent(cur)));
}
修改、保存代码
test2.xml
<?xml version="1.0" encoding="gb2312"?>
<story>
<storyinfo>
<author>John Fleck</author>
<datewritten>June 2, 2002</datewritten>
<keyword>我来也 example keyword</keyword>
<书目> C++ </书目>
<测试> test </测试>
</storyinfo>
<body>
<headline>This is the headline</headline>
<para>This is the body text.</para>
</body>
</story>
xmlDocPtr
parseDoc(char *docname, char *uri) {
xmlDocPtr doc;
xmlNodePtr cur;
xmlNodePtr newnode;
xmlAttrPtr newattr;
doc = xmlParseFile(docname);
if (doc == NULL ) {
fprintf(stderr,"Document not parsed successfully. ");
return (NULL);
}
cur = xmlDocGetRootElement(doc);
if (cur == NULL) {
fprintf(stderr,"empty document");
xmlFreeDoc(doc);
return (NULL);
}
if (xmlStrcmp(cur->name, (const xmlChar *) "story")) {
fprintf(stderr,"document of the wrong type, root node != story");
xmlFreeDoc(doc);
return (NULL);
}
newnode = xmlNewTextChild (cur, NULL, (xmlChar *)"reference", NULL);
newattr = xmlNewProp (newnode, (xmlChar *)"uri", (xmlChar *)uri);
return(doc);
}
int main(int argc, char ** argv )
{
int options = 0;
xmlDocPtr doc = NULL;
char * output = NULL;
char * szNode = NULL;
int ret = 0;
xmlAddEncodingAlias("UTF-8", "DVEnc");
xmlKeepBlanksDefault(0);
defaultEntityLoader = xmlGetExternalEntityLoader();
xmlSetExternalEntityLoader(xmllintExternalEntityLoader);
xmlLineNumbersDefault(1);
szNode = Convert("gb2312", "utf-8", "测试" );
doc = parseDoc( argv[2], szNode);
ret = xmlSaveFormatFileEnc(output ? output : "-", doc, argv[1], 1);
if (ret < 0)
{
fprintf(stderr, "failed save to %s",
output ? output : "-");
}
return 0;
}
执行
xmlout gb2312 test2.xml
结果
<?xml version="1.0" encoding="gb2312"?>
<story>
<storyinfo>
<author>John Fleck</author>
<datewritten>June 2, 2002</datewritten>
<keyword>我来也 example keyword</keyword>
<书目> C++ </书目>
<测试> test </测试>
</storyinfo>
<body>
<headline>This is the headline</headline>
<para>This is the body text.</para>
</body>
<reference uri="测试"/>
</story>
网摘2：
LibXML2自身已经支持了中文编码.只是他的所有api处理的数据都是UTF-8类型的，所以只要在读入和写入数据时进行相应转换即可！代码1是使用 linux下C API进行编码转换；代码2因为libxml2已融合了iconv，使用了libxml2的函数来进行编码转换.
/*
compile: gcc -I/usr/include/libxml2/ -lxml2 iconv.c
input:
test.xml
<?xml version="1.0" encoding="gb2312"?>
<parent>测试</parent>
output:
测试
1) iconv
#include <libxml/xmlmemory.h>
#include <libxml/parser.h>
#include <arpa/inet.h>
#include <iconv.h>
char * Convert( char *encFrom, char *encTo, const char * in)
{
static char bufin[1024], bufout[1024], *sin, *sout;
int mode, lenin, lenout, ret, nline;
iconv_t c_pt;
if ((c_pt = iconv_open(encTo, encFrom)) == (iconv_t)-1)
{
printf("iconv_open false: %s ==> %s\n", encFrom, encTo);
return NULL;
}
iconv(c_pt, NULL, NULL, NULL, NULL);
lenin = strlen(in) + 1;
lenout = 1024;
sin = (char *)in;
sout = bufout;
ret = iconv(c_pt, &sin, (size_t *)&lenin, &sout, (size_t *)&lenout);
if (ret == -1)
{
return NULL;
}
iconv_close(c_pt);
return bufout;
}
int main(void)
{
xmlDocPtr doc = NULL;
xmlNodePtr cur = NULL;
doc = xmlParseFile("test.xml");
cur = xmlDocGetRootElement(doc);
printf("%s\n", (char *)xmlNodeGetContent(cur));
//printf("%s\n", Convert("utf-8", "gb2312", (char *)xmlNodeGetContent(cur)));
}
2) xmlFindCharEncodingHandler
使用数据类型：xmlCharEncodingHandlerPtr
/*******************************************
* compile: gcc -I/usr/include/libxml2/ -lxml2 convert.c
* usage: convert utf-8 string or null
* input: ./convert 测试
* output:
[wuqifu@localhost test]$ ./convert 测试
ISO-8859-1:虏芒脢脭
<?xml version="1.0" encoding="ISO-8859-1"?>
<root>测试</root>
*******************************************/
#include <libxml/encoding.h>
/**
* function name: ConvertInput
* input:
@in: string in a given encoding
@encoding: the encoding used
* description: Converts @in into UTF-8 for processing with libxml2 APIs
* return: returns the converted UTF-8 string, or NULL in case of error.
**/
unsigned char* ConvertInput(const char *in, const char *encoding)
{
unsigned char *out;
int ret;
int size;
int out_size;
int temp;
xmlCharEncodingHandlerPtr handler;
if (in == 0)
return 0;
handler = xmlFindCharEncodingHandler(encoding);
if (!handler) {
printf("ConvertInput: no encoding handler found for '%s'\n",
encoding ? encoding : "");
return 0;
}
size = (int) strlen(in) + 1;
out_size = size * 2 - 1;
out = (unsigned char *) xmlMalloc((size_t) out_size);
if (out != 0) {
temp = size - 1;
ret = handler->input(out, &out_size, (const unsigned char *) in, &temp);
if ((ret < 0) || (temp - size + 1)) {
if (ret < 0) {
printf("ConvertInput: conversion wasn't successful.\n");
} else {
printf
("ConvertInput: conversion wasn't successful. converted: %i octets.\n",
temp);
}
xmlFree(out);
out = 0;
} else {
out = (unsigned char *) xmlRealloc(out, out_size + 1);
out[out_size] = 0; /*null terminating out */
}
} else {
printf("ConvertInput: no mem\n");
}
return out;
}
int main(int argc, char **argv)
{
unsigned char *content, *out;
xmlDocPtr doc;
xmlNodePtr rootnode;
char *encoding = "ISO-8859-1"; //utf-8, ISO-8859-1
if (argc <= 1) {
printf("Usage: %s content\n", argv[0]);
return(0);
}
content = argv[1];
out = ConvertInput(content, encoding);
printf( "%s:%s\n", encoding, out );
doc = xmlNewDoc ("1.0");
rootnode = xmlNewDocNode(doc, NULL, (const xmlChar*)"root", out);
xmlDocSetRootElement(doc, rootnode);
xmlSaveFormatFileEnc("-", doc, encoding, 1);
return (1);
}