2
我一直試圖解析一段文本的pdf頁面到NSString一段時間,而我唯一能找到的就是搜索特定字符串值的方法。在iPhone上將整個pdf頁面解析爲NSString
我希望做的是解析PDF的一個頁面,而無需使用任何外部庫,如PDFKitten,PDFKit等
我想有一個NSArray,的NSString或NSDictionary中,如果數據可能。
感謝:D!
到目前爲止我嘗試過的一塊。
CGPDFDocumentRef MyGetPDFDocumentRef (const char *filename) {
CFStringRef path;
CFURLRef url;
CGPDFDocumentRef document;
path = CFStringCreateWithCString (NULL, filename,kCFStringEncodingUTF8);
url = CFURLCreateWithFileSystemPath (NULL, path, kCFURLPOSIXPathStyle, 0);
CFRelease (path);
document = CGPDFDocumentCreateWithURL (url);// 2
CFRelease(url);
int count = CGPDFDocumentGetNumberOfPages (document);// 3
if (count == 0) {
printf("`%s' needs at least one page!", filename);
return NULL;
}
return document;
}
// table methods to parse pdf
static void op_MP (CGPDFScannerRef s, void *info) {
const char *name;
if (!CGPDFScannerPopName(s, &name))
return;
printf("MP /%s\n", name);
}
static void op_DP (CGPDFScannerRef s, void *info) {
const char *name;
if (!CGPDFScannerPopName(s, &name))
return;
printf("DP /%s\n", name);
}
static void op_BMC (CGPDFScannerRef s, void *info) {
const char *name;
if (!CGPDFScannerPopName(s, &name))
return;
printf("BMC /%s\n", name);
}
static void op_BDC (CGPDFScannerRef s, void *info) {
const char *name;
if (!CGPDFScannerPopName(s, &name))
return;
printf("BDC /%s\n", name);
}
static void op_EMC (CGPDFScannerRef s, void *info) {
const char *name;
if (!CGPDFScannerPopName(s, &name))
return;
printf("EMC /%s\n", name);
}
void MyDisplayPDFPage (CGContextRef myContext,size_t pageNumber,const char *filename) {
CGPDFDocumentRef document;
CGPDFPageRef page;
document = MyGetPDFDocumentRef (filename);// 1
totalPages=CGPDFDocumentGetNumberOfPages(document);
page = CGPDFDocumentGetPage (document, 1);// 2
CGPDFDictionaryRef d;
d = CGPDFPageGetDictionary(page);
CGPDFScannerRef myScanner;
CGPDFOperatorTableRef myTable;
myTable = CGPDFOperatorTableCreate();
CGPDFOperatorTableSetCallback (myTable, "MP", &op_MP);
CGPDFOperatorTableSetCallback (myTable, "DP", &op_DP);
CGPDFOperatorTableSetCallback (myTable, "BMC", &op_BMC);
CGPDFOperatorTableSetCallback (myTable, "BDC", &op_BDC);
CGPDFOperatorTableSetCallback (myTable, "EMC", &op_EMC);
CGPDFContentStreamRef myContentStream = CGPDFContentStreamCreateWithPage (page);// 3
myScanner = CGPDFScannerCreate (myContentStream, myTable, NULL);// 4
CGPDFScannerScan (myScanner);// 5
CGPDFStringRef str;
d = CGPDFPageGetDictionary(page);
if (CGPDFDictionaryGetString(d, "Lorem", &str)){
CFStringRef s;
s = CGPDFStringCopyTextString(str);
if (s != NULL) {
NSLog(@"%@ testing it", s);
}
CFRelease(s);
}
}
- (void)viewDidLoad {
[super viewDidLoad];
MyDisplayPDFPage(UIGraphicsGetCurrentContext(), 1, [[[NSBundle mainBundle] pathForResource:@"TestPage" ofType:@"pdf"] UTF8String]);
}