BStream *BStream_new(void)
{
BStream *self = (BStream *)calloc(1, sizeof(BStream));
self->ba = ByteArray_new();
self->ownsByteArray = 1;
self->tmp = ByteArray_new();
self->errorBa = ByteArray_new();
self->index = 0;
self->typeBuf = (unsigned char *)malloc(512);
return self;
}
//Method exposed to ActionScript
//Takes a String and echos it
static AS3_Val echo(void* self, AS3_Val args)
{
AS3_Val byteArray;
AS3_ArrayValue( args, "AS3ValType", &byteArray);
AS3_Val length = AS3_GetS(byteArray, "length");
sztrace("length getted!");
int len = AS3_IntValue(length);
//if(len>0) return length;
char *data=NULL;
data=malloc(len);
memset(data,0,len);
int fileLen = AS3_ByteArray_readBytes(data,byteArray, len);
char *out= NULL;
out = malloc(fileLen);
memset(out,0,fileLen);
ByteArray * bytearray = ByteArray_new(fileLen);
bytearray->data = data;
PdfFile_free(PdfFile_parse(bytearray,out));
ByteArray_free(bytearray);
return AS3_String(out);
}
int main(int argc,char**argv)
{
char * filename;
if(argc>1)
{
filename = argv[argc-1];
}else{
filename = "FFMPEG.pdf";
}
FILE * _file = fopen(filename,"rb");
int fileLen = fseek(_file,0,SEEK_END);
fileLen = ftell(_file);
rewind(_file);
printf("%s,%d\n",filename,fileLen);
ByteArray * bytearray = ByteArray_new(fileLen);
fread(bytearray->data,1,fileLen,_file);
fclose(_file);
char * out = malloc(fileLen);
memset(out,0,fileLen);
PdfFile_free(PdfFile_parse(bytearray,out));
printf("%s\n",out);
return 0;
}
int main(int argc,char **argv)
{
char * filename;
if(argc>1)
{
filename = argv[argc-1];
}else{
filename = "RAR.docx";
}
FILE * _file = fopen(filename,"rb");
int fileLen = fseek(_file,0,SEEK_END);
fileLen = ftell(_file);
rewind(_file);
printf("%s,%d\n",filename,fileLen);
ByteArray * bytearray = ByteArray_new(fileLen);
fread(bytearray->data,1,fileLen,_file);
fclose(_file);
char * out = malloc(fileLen*10);
memset(out,0,fileLen*10);
int outlen=0;
//ZipFile_free(ZipFile_parser(bytearray,"",out,&outlen));
ZipFile * zipfile = ZipFile_parser(bytearray,"word/document.xml",out,&outlen);
//printf("\n%s",out);
/*
//<w:p 分段
char **matched_arr=(char**)malloc(strlen(out));
memset(matched_arr,0,strlen(out));
//<w:t>文本</w:t>
int len = regex_search_all(out,"/<w:t>([^<>]*)<\\/w:t>/",matched_arr);
printf("%d\n",len);
char * connected = string_concat(matched_arr,len,"");
printf("%s",regex_replace_all(connected,"/<[\\/]*w:t>/",""));
fflush(stdout);
regex_matchedarrClear(matched_arr,len);
*/
xmlDocPtr doc = xmlParseMemory(out, strlen(out));
//for(i=0;i<MAXNS;i++) xmlXPathRegisterNs(context,NSNAME[i],NS[i]);// //默认ns : @"//*[local-name()='price'] "
/*检查解析文档是否成功，如果不成功，libxml将指一个注册的错误并停止。一个常见错误是不适当的编码。XML标准文档除了用UTF-8或UTF-16外还可用其它编码保存。如果文档是这样，libxml将自动地为你转换到UTF-8。更多关于XML编码信息包含在XML标准中。*/
if (doc == NULL )
{
fprintf(stderr,"Document not parsed successfully. \n");
return -1;
}
xmlChar *xpath = (xmlChar*)"//w:p";
xmlXPathObjectPtr app_result = get_nodeset(doc,xpath);
if (app_result == NULL)
{
printf("app_result is NULL\n");
return -4;
}
int i = 0;
if(app_result)
{
xmlNodeSetPtr nodeset = app_result->nodesetval;
for (i=0; i < nodeset->nodeNr; i++)
{
xmlNodePtr cur = nodeset->nodeTab[i];
xmlChar *value = xmlNodeGetContent(cur);
printf("%s", (char *)value);
xmlFree(value);
//printf("name: %s\n", (char *)cur->name);
/*
xmlNodePtr son = cur->xmlChildrenNode;
while(son)
{
value = xmlNodeGetContent(son);
if (value != NULL)
{
printf("%s", (char *)value);
xmlFree(value);
}
son = son->next;
}
*/
printf("\r\n");
}
//printf("\r\n");
xmlXPathFreeObject (app_result);
}
xmlFreeDoc(doc);
ZipFile_free(zipfile);
return 0;
}
int main(int argc,char **argv)
{
char * filename;
if(argc>1)
{
filename = argv[argc-1];
}else{
filename = "xls.xlsx";
}
FILE * _file = fopen(filename,"rb");
int fileLen = fseek(_file,0,SEEK_END);
fileLen = ftell(_file);
rewind(_file);
printf("%s,%d\n",filename,fileLen);
ByteArray * bytearray = ByteArray_new(fileLen);
fread(bytearray->data,1,fileLen,_file);
fclose(_file);
char * out = malloc(fileLen*10);
memset(out,0,fileLen*10);
int outlen=0;
//ZipFile_free(ZipFile_parser(bytearray,"",out,&outlen));
ZipFile * zipfile = ZipFile_parser(bytearray,"xl/sharedStrings.xml",out,&outlen);
//printf("\n%s",out);
ZipFile_free(zipfile);
/*
char **matched_arr=(char**)malloc(strlen(out));
memset(matched_arr,0,strlen(out));
//<w:t></w:t>
int len = regex_search_all(out,"/<t>([^<>]*)<\\/t>/",matched_arr);
printf("%d\n",len);
char * connected = string_concat(matched_arr,len,"");
printf("%s",regex_replace_all(connected,"/<[\\/]*w:t>/",""));
fflush(stdout);
*/
xmlDocPtr string_doc = xmlParseMemory(out, strlen(out));
if (string_doc== NULL )
{
fprintf(stderr,"Document not parsed successfully. \n");
return -1;
}
xmlChar *xpath1 = (xmlChar*)("//ns:t");
xmlXPathObjectPtr _result = get_nodeset(string_doc,xpath1);
if (_result == NULL)
{
printf("_result is NULL\n");
return -4;
}
int i;
i = 0;
xmlChar ** str_arr=NULL;
if(_result)
{
xmlNodeSetPtr nodeset = _result->nodesetval;
str_arr = malloc(sizeof(char**)*nodeset->nodeNr);
memset(str_arr,0,sizeof(char**)*nodeset->nodeNr);
for (i=0; i < nodeset->nodeNr; i++)
{
xmlNodePtr cur; //定义结点指针(你需要它为了在各个结点间移动)
cur = nodeset->nodeTab[i];
//printf("name: %s\n", (char *)cur->name);
cur = cur->xmlChildrenNode;
while(cur!=NULL)
{
xmlChar *value;
value = xmlNodeGetContent(cur);
str_arr[i]=value;
if (value != NULL)
{
//printf("%s\t", (char *)value);
//xmlFree(value);
}
cur = cur->next;
}
//printf("\r\n");
}
xmlXPathFreeObject (_result);
}
xmlFreeDoc(string_doc);
int sheetIndex = 0;
while(1){
sheetIndex++;
memset(out,0,fileLen*10);
// xl/worksheets/sheet1.xml
char sheetName[64];
memset(sheetName,0,64);
sprintf(sheetName,"xl/worksheets/sheet%d.xml",sheetIndex);
bytearray->position=0;
ZipFile_free(ZipFile_parser(bytearray,sheetName,out,&outlen));
//printf("\n%s\n",out);
if(out==NULL || strlen(out)==0)
break;
xmlDocPtr doc = xmlParseMemory(out, strlen(out));
if (doc == NULL )
{
fprintf(stderr,"Document not parsed successfully. \n");
return -1;
}
xmlChar *xpath = (xmlChar*)("//ns:row");
xmlXPathObjectPtr app_result = get_nodeset(doc,xpath);
if (app_result == NULL)
{
printf("app_result is NULL\n");
return -4;
}
if(app_result)
{
xmlNodeSetPtr nodeset = app_result->nodesetval;
xmlNodePtr cur = nodeset->nodeTab[0];
while(cur)
{
//printf("name: %s\n", (char *)cur->name);
xmlNodePtr son = cur->xmlChildrenNode;
while(son)
{
xmlChar *value;
xmlChar* prop = xmlGetProp(son, (const xmlChar*)"t");
//if(prop) printf("prop:%s",prop);
value = xmlNodeGetContent(son);
if (value != NULL)
{
if(prop && strcmp("s",(char*)prop)==0)
{
//printf("====%s\t", (char *)value);
printf("%s\t", (char *)str_arr[atoi((char*)value)]);
}else{
printf("%s\t", (char *)value);
}
xmlFree(value);
}
son = son->next;
xmlFree(prop);
}
printf("\r\n");
cur = cur->next;
}
printf("\r\n");
xmlXPathFreeObject (app_result);
}
xmlFreeDoc(doc);
}
/*
xmlNodePtr cur; //定义结点指针(你需要它为了在各个结点间移动)
cur = xmlDocGetRootElement(doc); //确定文档根元素
if (cur == NULL)
{
fprintf(stderr,"empty document\n");
xmlFreeDoc(doc);
return -2;
}
if (xmlStrcmp(cur->name, (const xmlChar *) "worksheet"))
{
xmlFreeDoc(doc);
return -3;
}
cur = cur->xmlChildrenNode;
while(cur!=NULL)
{
xmlNodePtr son = cur->children;
while(son){
//xmlChar* prop = xmlGetProp(son, "spans");
//printf("\n%s,%s",son->name,prop);
xmlChar *key;
if ((!xmlStrcmp(son->name, (const xmlChar *)"sheetData")))
{
key = xmlNodeListGetString(doc, son->xmlChildrenNode, 1);
printf("keyword: %s\n", key);
xmlFree(key);
}
son = son->next;
}
cur = cur->next;
}
*/
return 0;
//regex_matchedarrClear(matched_arr,len);
}