通过 iPhone 应用程序以字符串形式读取 PDF 文件

Question

我在“阅读 PDF”的 iPhone 应用程序开发中遇到了一些问题。 我试过下面的代码。 我知道我使用了错误的解析方法 - 解析方法仅用于搜索目的。 但我想将整个 pdf 文本转换为字符串。 比如说 Apple 的 MobileHIG.pdf - 我在这段代码中使用过。

@implementation NetPDFViewController

size_t totalPages;  // a variable to store total pages

// a method to get the pdf ref
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);  
}

// a method to display pdf page.

void MyDisplayPDFPage (CGContextRef myContext,size_t pageNumber,const char *filename) {
    CGPDFDocumentRef document;
    CGPDFPageRef page;
    document = MyGetPDFDocumentRef (filename);// 1
    totalPages=CGPDFDocumentGetNumberOfPages(document);
    page = CGPDFDocumentGetPage (document, pageNumber);// 2

    CGPDFDictionaryRef d;

    d = CGPDFPageGetDictionary(page);

// ----- edit   problem here - CGPDFDictionary is completely unknown 
// ----- as we don't know keys & values of it.
    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

//  CGPDFDictionaryRef d;

    CGPDFStringRef str; // represents a sequence of bytes

    d = CGPDFPageGetDictionary(page);

    if (CGPDFDictionaryGetString(d, "Thumb", &str)){
        CFStringRef s;
        s = CGPDFStringCopyTextString(str);
        if (s != NULL) {
            //need something in here in case it cant find anything
            NSLog(@"%@ testing it", s);
        }
        CFRelease(s);       
//      CFDataRef data = CGPDFStreamCopyData (stream, CGPDFDataFormatRaw);
    }

// -----------------------------------  

    CGContextDrawPDFPage (myContext, page);// 3
    CGContextTranslateCTM(myContext, 0, 20);
    CGContextScaleCTM(myContext, 1.0, -1.0);
    CGPDFDocumentRelease (document);// 4
}

- (void)viewDidLoad {
    [super viewDidLoad];


// -------------------------------------------------------- 
// code for simple direct image from pdf docs.
    UIGraphicsBeginImageContext(CGSizeMake(320, 460));
    initialPage=28;
    MyDisplayPDFPage(UIGraphicsGetCurrentContext(), initialPage, [[[NSBundle mainBundle] pathForResource:@"MobileHIG" ofType:@"pdf"] UTF8String]);
    imgV.image=UIGraphicsGetImageFromCurrentImageContext();
    imgV.image=[imgV.image rotate:UIImageOrientationDownMirrored];  
}

- (void)touchesBegan:(NSSet *)touches withEvent:(UIEvent *)event{
    UITouch *touch = [touches anyObject];
    CGPoint LasttouchPoint =  [touch locationInView:self.view];
    int LasttouchX = LasttouchPoint.x;
    startpoint=LasttouchX;
}


- (void)touchesMoved:(NSSet *)touches withEvent:(UIEvent *)event{

}

- (void)touchesEnded:(NSSet *)touches withEvent:(UIEvent *)event{
    UITouch *touch = [touches anyObject];
    CGPoint LasttouchPoint =  [touch locationInView:self.view];
    int LasttouchX = LasttouchPoint.x;
    endpoint=LasttouchX;
    if(startpoint>(endpoint+75)){
        initialPage++;
        [self loadPage:initialPage nextOne:YES];
    } else if((startpoint+75)<endpoint){
        initialPage--;
        [self loadPage:initialPage nextOne:NO];
    }
}


-(void)loadPage:(NSUInteger)page nextOne:(BOOL)yesOrNo{
    if(page<=totalPages && page>0){
        UIGraphicsBeginImageContext(CGSizeMake(720, 720));  
        MyDisplayPDFPage(UIGraphicsGetCurrentContext(), page, [[[NSBundle mainBundle] pathForResource:@"MobileHIG" ofType:@"pdf"] UTF8String]);

        CATransition *transition = [CATransition animation];
        transition.duration = 0.75;
        transition.timingFunction = [CAMediaTimingFunction functionWithName:kCAMediaTimingFunctionEaseInEaseOut];
        transition.type=kCATransitionPush;
        if(yesOrNo){
            transition.subtype=kCATransitionFromRight;
        } else {
            transition.subtype=kCATransitionFromLeft;
        }

        transition.delegate = self;
        [imgV.layer addAnimation:transition forKey:nil];
        imgV.image=UIGraphicsGetImageFromCurrentImageContext();
        imgV.image=[imgV.image rotate:UIImageOrientationDownMirrored];
    }
}

但是我什至无法从 pdf 文档中读取一行。 还缺少什么？

Answer 1

如果您想从 pdf 文件中提取一些内容，那么您可能需要阅读以下内容：

解析 PDF 内容

来自 Quartz 2D 编程指南。

基本上，您将使用CGPDFScanner对象来解析内容，其工作原理如下。 您注册一些回调，当遇到 pdf 流中的某些 pdf 运算符时，Quartz 2D 会自动调用这些回调。 在这个初始步骤之后，您实际上开始解析 pdf 流。

简单看一下您的代码，您似乎没有按照解析通过CGPDFDocumentGetPage()获得的页面的 pdf 内容所需的步骤进行操作。 您首先需要使用CGPDFOperatorTableCreate()和CGPDFOperatorTableSetCallback()设置回调，然后获取页面，您需要使用该页面创建内容流（使用CGPDFContentStreamCreateWithPage() ），然后通过CGPDFScannerCreate()实例化CGPDFScanner并实际启动通过CGPDFScannerScan()扫描。

上述 URL 指出的文档的“解析 PDF 内容”部分为您提供了实现 pdf 解析所需的所有信息。

希望这可以帮助。

Answer 2

我有一个图书馆可以做这件事，链接在这里： https : //bitbucket.org/zachron/pdfiphone/overview

Answer 3

看看QuartzDemo示例应用程序是如何做到这一点的，特别是 QuartzImages.h 和 QuartzImages.m 文件中的 QuartzPDFView 类。 它显示了通过 Quartz 加载 PDF 的示例。