我已经研究在我的 iOS 应用程序中使用 PDF 一段时间了。我已经解决了一些难题，例如扫描操作员并在 UIWebView 中显示 PDF。然而，我真正需要做的是确定可编辑字段在 PDF 文档中。
理想情况下，我希望能够直接与这些领域进行交互，但这听起来非常困难，而且不是明显的第一步。我已经在与一个 Windows 服务进行交互，该服务可以通过这种方式操作 PDF，并且可以确定可编辑字段，在表单视图中从用户收集字段数据，并将该数据发布回服务器。问题是我看不到如何识别字段。我正在与政府颁发的 PDF（例如 I-9 和 W-4）进行交互，因此我无法控制 PDF 的创建或字段的命名。这就是为什么我需要动态提取它们。任何帮助和/或参考将不胜感激。
我正在使用 Apple 的 Quatrz 2D 编程指南中的[此参考](https://developer.apple.com/library/mac/#documentation/graphicsimaging/conceptual/drawingwithquartz2d/dq_pdf_scan/dq_pdf_scan.html"PDF Document Parsing")扫描 PDF 时触发操作员回调，但这并不能帮助我找到可编辑字段。
我还只是加载带有 PDF 数据的 UIWebView 以向用户显示。
[_webView loadData:decodedData MIMEType:@"application/pdf" textEncodingName:@"utf-8" baseURL:nil];
UPDATE:
我构建了一个 PDF Helper 类（如下所示）来遍历目录中所有可能的对象类型。最初我没有处理数组中的嵌套字典，所以我没有看到表单字段。一旦我修复了这个问题，我就意识到我必须考虑父引用，以避免循环递归调用，从而启动无限循环。下面的代码显示了文档目录中的大量信息。现在我只需要解析它以隔离我需要的表单字段。
PDFHelper.h
#import <Foundation/Foundation.h>
id selfClass;
@interface PDFHelper : NSObject
@property (nonatomic, strong) NSData *pdfData;
@property (nonatomic, strong) NSMutableDictionary *pdfDict;
@property (nonatomic) int catalogLevel;
-(NSArray *) copyPDFArray:(CGPDFArrayRef)arr referencingDictionary:(CGPDFDictionaryRef)dict referencingKey:(const char *)key;
-(NSArray *) getFormFields;
-(CGPDFDictionaryRef) getDocumentCatalog;
@end
PDF助手.m
#import "PDFHelper.h"
#import "FileHelpers.h"
#import "Log.h"
@implementation PDFHelper
@synthesize pdfData = _pdfData;
@synthesize pdfDict = _pdfDict;
@synthesize catalogLevel = _catalogLevel;
-(id)init
{
self = [super init];
if(self)
{
selfClass = self;
_pdfDict = [[NSMutableDictionary alloc] init];
_catalogLevel = 1;
}
return self;
}
-(NSArray *) getFormFields
{
CGPDFDictionaryRef acroForm = NULL;
if (CGPDFDictionaryGetDictionary([self getPdfDocDictionary], "AcroForm", &acroForm))
CGPDFDictionaryApplyFunction(acroForm, getDictionaryObjects, acroForm);
return [_pdfDict objectForKey:@"XFA"];
}
-(CGPDFDictionaryRef) getDocumentCatalog
{
CGPDFDictionaryRef docCatalog = [self getPdfDocDictionary];
CGPDFDictionaryApplyFunction(docCatalog, getDictionaryObjects, docCatalog);
return docCatalog;
}
-(CGPDFDictionaryRef) getPdfDocDictionary
{
NSURL *pdf = [[NSURL alloc] initFileURLWithPath:[FileHelpers pathInLibraryDirectory:@"file.pdf"]];
[_pdfData writeToFile:[pdf path] atomically:YES];
CGPDFDocumentRef pdfDocument = CGPDFDocumentCreateWithURL((__bridge CFURLRef)pdf);
CGPDFDictionaryRef returnDict = CGPDFDocumentGetCatalog(pdfDocument);
return returnDict;
}
void getDictionaryObjects (const char *key, CGPDFObjectRef object, void *info) {
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"key: %s", key]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
CGPDFDictionaryRef contentDict = (CGPDFDictionaryRef)info;
CGPDFObjectType type = CGPDFObjectGetType(object);
switch (type) {
case kCGPDFObjectTypeNull: {
[Log LogDebug:[NSString stringWithFormat:@"*****pdf null value"]];
break;
}
case kCGPDFObjectTypeBoolean: {
CGPDFBoolean objectBoolean;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeBoolean, &objectBoolean)) {
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf boolean value: %@", [NSNumber numberWithBool:objectBoolean]]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
[[selfClass pdfDict] setObject:[NSNumber numberWithBool:objectBoolean]
forKey:[NSString stringWithCString:key encoding:NSUTF8StringEncoding]];
}
break;
}
case kCGPDFObjectTypeInteger: {
CGPDFInteger objectInteger;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeInteger, &objectInteger)) {
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf integer value: %ld", (long int)objectInteger]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
[[selfClass pdfDict] setObject:[NSNumber numberWithInt:objectInteger]
forKey:[NSString stringWithCString:key encoding:NSUTF8StringEncoding]];
}
break;
}
case kCGPDFObjectTypeReal: {
CGPDFReal objectReal;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeReal, &objectReal)) {
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf real value: %ld", (long int)objectReal]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
[[selfClass pdfDict] setObject:[NSNumber numberWithInt:objectReal]
forKey:[NSString stringWithCString:key encoding:NSUTF8StringEncoding]];
}
break;
}
case kCGPDFObjectTypeName: {
const char *name;
if (CGPDFDictionaryGetName(contentDict, key, &name))
{
NSString *dictName = [[NSString alloc] initWithCString:name encoding:NSUTF8StringEncoding];
if (dictName)
{
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf name value: %@", dictName]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
[[selfClass pdfDict] setObject:dictName
forKey:[NSString stringWithCString:key encoding:NSUTF8StringEncoding]];
}
}
break;
}
case kCGPDFObjectTypeString: {
CGPDFStringRef objectString;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeString, &objectString)) {
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf string value: %@", (__bridge NSString *)CGPDFStringCopyTextString(objectString)]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
[[selfClass pdfDict] setObject:(__bridge NSString *)CGPDFStringCopyTextString(objectString)
forKey:[NSString stringWithCString:key encoding:NSUTF8StringEncoding]];
}
break;
}
case kCGPDFObjectTypeArray: {
CGPDFArrayRef objectArray;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeArray, &objectArray)) {
NSArray *myArray=[selfClass copyPDFArray:objectArray referencingDictionary:contentDict referencingKey:key];
[[selfClass pdfDict] setObject:myArray
forKey:[NSString stringWithCString:key encoding:NSUTF8StringEncoding]];
}
break;
}
case kCGPDFObjectTypeDictionary: {
CGPDFDictionaryRef objectDictionary;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeDictionary, &objectDictionary)) {
NSString *logString = @"Found dictionary";
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
//[Log LogDebug:logString];
NSString *keyCheck = [[NSString alloc] initWithUTF8String:key];
if (![keyCheck isEqualToString:@"Parent"] && ![keyCheck isEqualToString:@"P"])
{
[selfClass setCatalogLevel:[selfClass catalogLevel] + 1];
CGPDFDictionaryApplyFunction(objectDictionary, getDictionaryObjects, objectDictionary);
[selfClass setCatalogLevel:[selfClass catalogLevel] - 1];
}
}
break;
}
case kCGPDFObjectTypeStream: {
CGPDFStreamRef objectStream;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeStream, &objectStream)) {
CGPDFDictionaryRef dict = CGPDFStreamGetDictionary( objectStream );
CGPDFDataFormat fmt = CGPDFDataFormatRaw;
CFDataRef streamData = CGPDFStreamCopyData(objectStream, &fmt);
NSData *data = [[NSData alloc] initWithData:(__bridge NSData *)(streamData)];
[data writeToFile:[FileHelpers pathInDocumentDirectory:@"data.dat"] atomically:YES];
NSString *dataString = [[NSString alloc] initWithData:data encoding:NSUTF8StringEncoding];
//if (!dataString) {
// dataString = [[NSString alloc] initWithData:(__bridge NSData *)(streamData) encoding:NSUTF16StringEncoding];
// }
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf stream length: %ld - %@", (long int)CFDataGetLength( streamData ), dataString]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
NSString *keyCheck = [[NSString alloc] initWithUTF8String:key];
if( dict && ![keyCheck isEqualToString:@"Parent"] && ![keyCheck isEqualToString:@"P"])
{
[selfClass setCatalogLevel:[selfClass catalogLevel] + 1];
CGPDFDictionaryApplyFunction(dict, getDictionaryObjects, dict);
[selfClass setCatalogLevel:[selfClass catalogLevel] - 1];
}
}
}
}
}
- (NSArray *)copyPDFArray:(CGPDFArrayRef)arr referencingDictionary:(CGPDFDictionaryRef)dict referencingKey:(const char *)key
{
int i = 0;
NSMutableArray *temp = [[NSMutableArray alloc] init];
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf array count: %zu", CGPDFArrayGetCount(arr)]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
for(i=0; i<CGPDFArrayGetCount(arr); i++){
CGPDFObjectRef object;
CGPDFArrayGetObject(arr, i, &object);
CGPDFObjectType type = CGPDFObjectGetType(object);
switch(type){
case kCGPDFObjectTypeNull: {
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf array null(%d)", i]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
break;
}
case kCGPDFObjectTypeBoolean: {
CGPDFBoolean objectBool;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeBoolean, &objectBool)) {
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf array boolean value(%d): %@", i, [NSNumber numberWithBool:objectBool]]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
[temp addObject:[NSNumber numberWithBool:objectBool]];
}
break;
}
case kCGPDFObjectTypeInteger: {
CGPDFInteger objectInteger;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeInteger, &objectInteger)) {
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf array integer value(%d): %ld", i, (long int)objectInteger]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
[temp addObject:[NSNumber numberWithInt:objectInteger]];
}
break;
}
case kCGPDFObjectTypeReal:
{
CGPDFReal objectReal;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeReal, &objectReal))
{
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf array real(%d): %ld", i, (long int)objectReal]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
[temp addObject:[NSNumber numberWithInt:objectReal]];
}
break;
}
case kCGPDFObjectTypeName:
{
const char *name;
if (CGPDFDictionaryGetName(dict, key, &name))
{
NSString *dictName = [[NSString alloc] initWithCString:name encoding:NSUTF8StringEncoding];
if (dictName)
{
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf array name value(%d): %@", i, dictName]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
[[selfClass pdfDict] setObject:dictName
forKey:[NSString stringWithCString:key encoding:NSUTF8StringEncoding]];
}
}
break;
}
case kCGPDFObjectTypeString:
{
CGPDFStringRef objectString;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeString, &objectString))
{
NSString *tempStr = (__bridge NSString *)CGPDFStringCopyTextString(objectString);
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf array string(%d): %@", i, tempStr]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
[temp addObject:tempStr];
}
break;
}
case kCGPDFObjectTypeArray :
{
CGPDFArrayRef objectArray;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeArray, &objectArray))
{
NSArray *tempArr = [selfClass copyPDFArray:objectArray referencingDictionary:dict referencingKey:key];
[temp addObject:tempArr];
}
break;
}
case kCGPDFObjectTypeDictionary :
{
CGPDFDictionaryRef objectDict;
NSString *keyCheck = [[NSString alloc] initWithUTF8String:key];
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeDictionary, &objectDict) && ![keyCheck isEqualToString:@"Parent"] && ![keyCheck isEqualToString:@"P"])
{
[selfClass setCatalogLevel:[selfClass catalogLevel] + 1];
CGPDFDictionaryApplyFunction( objectDict, getDictionaryObjects, objectDict);
[selfClass setCatalogLevel:[selfClass catalogLevel] - 1];
}
break;
}
case kCGPDFObjectTypeStream :
{
CGPDFStreamRef objectStream;
if (CGPDFObjectGetValue(object, kCGPDFObjectTypeStream, &objectStream))
{
CGPDFDictionaryRef streamDict = CGPDFStreamGetDictionary( objectStream );
CGPDFDataFormat fmt = CGPDFDataFormatRaw;
CFDataRef streamData = CGPDFStreamCopyData(objectStream, &fmt);
NSString *dataString = [[NSString alloc] initWithData:(__bridge NSData *)(streamData) encoding:NSUTF8StringEncoding];
NSString *logString = [[NSString alloc] initWithString:[NSString stringWithFormat:@"pdf array stream length: (%d): %ld - %@", i, (long int)CFDataGetLength( streamData ), dataString]];
for (int i = 0; i < [selfClass catalogLevel]; i++)
logString = [NSString stringWithFormat:@"-%@", logString];
[Log LogDebug:logString];
NSString *keyCheck = [[NSString alloc] initWithUTF8String:key];
if( streamDict && ![keyCheck isEqualToString:@"Parent"] && ![keyCheck isEqualToString:@"P"])
{
[selfClass setCatalogLevel:[selfClass catalogLevel] + 1];
CGPDFDictionaryApplyFunction( streamDict, getDictionaryObjects, streamDict );
[selfClass setCatalogLevel:[selfClass catalogLevel] - 1];
}
}
}
}
}
return temp;
}
@end
