我有一个适用于 iOS 和 macOS 的解决方案，无需使用 dd 和 xxd 等外部助手。刚刚找到，所以就照原样报告，打算后期改进。目前，它同时依赖于 Objective-C 和 Swift 代码。首先，在 Objective-C 中创建这个帮助类：
AWS3MD5Hash.h
#import <Foundation/Foundation.h>
NS_ASSUME_NONNULL_BEGIN
@interface AWS3MD5Hash : NSObject
- (NSData *)dataFromFile:(FILE *)theFile startingOnByte:(UInt64)startByte length:(UInt64)length filePath:(NSString *)path singlePartSize:(NSUInteger)partSizeInMb;
- (NSData *)dataFromBigData:(NSData *)theData startingOnByte:(UInt64)startByte length:(UInt64)length;
- (NSData *)dataFromHexString:(NSString *)sourceString;
@end
NS_ASSUME_NONNULL_END
AWS3MD5Hash.m
#import "AWS3MD5Hash.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define SIZE 256
@implementation AWS3MD5Hash
- (NSData *)dataFromFile:(FILE *)theFile startingOnByte:(UInt64)startByte length:(UInt64)length filePath:(NSString *)path singlePartSize:(NSUInteger)partSizeInMb {
char *buffer = malloc(length);
NSURL *fileURL = [NSURL fileURLWithPath:path];
NSNumber *fileSizeValue = nil;
NSError *fileSizeError = nil;
[fileURL getResourceValue:&fileSizeValue
forKey:NSURLFileSizeKey
error:&fileSizeError];
NSInteger __unused result = fseek(theFile,startByte,SEEK_SET);
if (result != 0) {
free(buffer);
return nil;
}
NSInteger result2 = fread(buffer, length, 1, theFile);
NSUInteger difference = fileSizeValue.integerValue - startByte;
NSData *toReturn;
if (result2 == 0) {
toReturn = [NSData dataWithBytes:buffer length:difference];
} else {
toReturn = [NSData dataWithBytes:buffer length:result2 * length];
}
free(buffer);
return toReturn;
}
- (NSData *)dataFromBigData:(NSData *)theData startingOnByte: (UInt64)startByte length:(UInt64)length {
NSUInteger fileSizeValue = theData.length;
NSData *subData;
if (startByte + length > fileSizeValue) {
subData = [theData subdataWithRange:NSMakeRange(startByte, fileSizeValue - startByte)];
} else {
subData = [theData subdataWithRange:NSMakeRange(startByte, length)];
}
return subData;
}
- (NSData *)dataFromHexString:(NSString *)string {
string = [string lowercaseString];
NSMutableData *data= [NSMutableData new];
unsigned char whole_byte;
char byte_chars[3] = {'\0','\0','\0'};
NSInteger i = 0;
NSInteger length = string.length;
while (i < length-1) {
char c = [string characterAtIndex:i++];
if (c < '0' || (c > '9' && c < 'a') || c > 'f')
continue;
byte_chars[0] = c;
byte_chars[1] = [string characterAtIndex:i++];
whole_byte = strtol(byte_chars, NULL, 16);
[data appendBytes:&whole_byte length:1];
}
return data;
}
@end
现在创建一个普通的 swift 文件：
AWS Extensions.swift
import UIKit
import CommonCrypto
extension URL {
func calculateAWSS3MD5Hash(_ numberOfParts: UInt64) -> String? {
do {
var fileSize: UInt64!
var calculatedPartSize: UInt64!
let attr:NSDictionary? = try FileManager.default.attributesOfItem(atPath: self.path) as NSDictionary
if let _attr = attr {
fileSize = _attr.fileSize();
if numberOfParts != 0 {
let partSize = Double(fileSize / numberOfParts)
var partSizeInMegabytes = Double(partSize / (1024.0 * 1024.0))
partSizeInMegabytes = ceil(partSizeInMegabytes)
calculatedPartSize = UInt64(partSizeInMegabytes)
if calculatedPartSize % 2 != 0 {
calculatedPartSize += 1
}
if numberOfParts == 2 || numberOfParts == 3 { // Very important when there are 2 or 3 parts, in the majority of times
// the calculatedPartSize is already 8. In the remaining cases we force it.
calculatedPartSize = 8
}
if mainLogToggling {
print("The calculated part size is \(calculatedPartSize!) Megabytes")
}
}
}
if numberOfParts == 0 {
let string = self.memoryFriendlyMd5Hash()
return string
}
let hasher = AWS3MD5Hash.init()
let file = fopen(self.path, "r")
defer { let result = fclose(file)}
var index: UInt64 = 0
var bigString: String! = ""
var data: Data!
while autoreleasepool(invoking: {
if index == (numberOfParts-1) {
if mainLogToggling {
//print("Siamo all'ultima linea.")
}
}
data = hasher.data(from: file!, startingOnByte: index * calculatedPartSize * 1024 * 1024, length: calculatedPartSize * 1024 * 1024, filePath: self.path, singlePartSize: UInt(calculatedPartSize))
bigString = bigString + MD5.get(data: data) + "\n"
index += 1
if index == numberOfParts {
return false
}
return true
}) {}
let final = MD5.get(data :hasher.data(fromHexString: bigString)) + "-\(numberOfParts)"
return final
} catch {
}
return nil
}
func memoryFriendlyMd5Hash() -> String? {
let bufferSize = 1024 * 1024
do {
// Open file for reading:
let file = try FileHandle(forReadingFrom: self)
defer {
file.closeFile()
}
// Create and initialize MD5 context:
var context = CC_MD5_CTX()
CC_MD5_Init(&context)
// Read up to `bufferSize` bytes, until EOF is reached, and update MD5 context:
while autoreleasepool(invoking: {
let data = file.readData(ofLength: bufferSize)
if data.count > 0 {
data.withUnsafeBytes {
_ = CC_MD5_Update(&context, $0, numericCast(data.count))
}
return true // Continue
} else {
return false // End of file
}
}) { }
// Compute the MD5 digest:
var digest = Data(count: Int(CC_MD5_DIGEST_LENGTH))
digest.withUnsafeMutableBytes {
_ = CC_MD5_Final($0, &context)
}
let hexDigest = digest.map { String(format: "%02hhx", $0) }.joined()
return hexDigest
} catch {
print("Cannot open file:", error.localizedDescription)
return nil
}
}
struct MD5 {
static func get(data: Data) -> String {
var digest = [UInt8](repeating: 0, count: Int(CC_MD5_DIGEST_LENGTH))
let _ = data.withUnsafeBytes { bytes in
CC_MD5(bytes, CC_LONG(data.count), &digest)
}
var digestHex = ""
for index in 0..<Int(CC_MD5_DIGEST_LENGTH) {
digestHex += String(format: "%02x", digest[index])
}
return digestHex
}
// The following is a memory friendly version
static func get2(data: Data) -> String {
var currentIndex = 0
let bufferSize = 1024 * 1024
//var digest = [UInt8](repeating: 0, count: Int(CC_MD5_DIGEST_LENGTH))
// Create and initialize MD5 context:
var context = CC_MD5_CTX()
CC_MD5_Init(&context)
while autoreleasepool(invoking: {
var subData: Data!
if (currentIndex + bufferSize) < data.count {
subData = data.subdata(in: Range.init(NSMakeRange(currentIndex, bufferSize))!)
currentIndex = currentIndex + bufferSize
} else {
subData = data.subdata(in: Range.init(NSMakeRange(currentIndex, data.count - currentIndex))!)
currentIndex = currentIndex + (data.count - currentIndex)
}
if subData.count > 0 {
subData.withUnsafeBytes {
_ = CC_MD5_Update(&context, $0, numericCast(subData.count))
}
return true
} else {
return false
}
}) { }
// Compute the MD5 digest:
var digest = Data(count: Int(CC_MD5_DIGEST_LENGTH))
digest.withUnsafeMutableBytes {
_ = CC_MD5_Final($0, &context)
}
var digestHex = ""
for index in 0..<Int(CC_MD5_DIGEST_LENGTH) {
digestHex += String(format: "%02x", digest[index])
}
return digestHex
}
}
现在添加：
#import "AWS3MD5Hash.h"
到您的 Objective-C 桥接头。你应该可以接受这个设置。
使用示例
要测试此设置，您可以在负责处理 AWS 连接的对象内调用以下方法：
func getMd5HashForFile() {
let credentialProvider = AWSCognitoCredentialsProvider(regionType: AWSRegionType.USEast2, identityPoolId: "<INSERT_POOL_ID>")
let configuration = AWSServiceConfiguration(region: AWSRegionType.APSoutheast2, credentialsProvider: credentialProvider)
configuration?.timeoutIntervalForRequest = 3.0
configuration?.timeoutIntervalForResource = 3.0
AWSServiceManager.default().defaultServiceConfiguration = configuration
AWSS3.register(with: configuration!, forKey: "defaultKey")
let s3 = AWSS3.s3(forKey: "defaultKey")
let headObjectRequest = AWSS3HeadObjectRequest()!
headObjectRequest.bucket = "<NAME_OF_YOUR_BUCKET>"
headObjectRequest.key = self.latestMapOnServer.key
let _: AWSTask? = s3.headObject(headObjectRequest).continueOnSuccessWith { (awstask) -> Any? in
let headObjectOutput: AWSS3HeadObjectOutput? = awstask.result
var ETag = headObjectOutput?.eTag!
// Here you should parse the returned Etag and extract the number of parts to provide to the helper function. Etags end with a "-" followed by the number of parts. If you don't see this format, then pass 0 as the number of parts.
ETag = ETag!.replacingOccurrences(of: "\"", with: "")
print("headObjectOutput.ETag \(ETag!)")
let mapOnDiskUrl = self.getMapsDirectory().appendingPathComponent(self.latestMapOnDisk!)
let hash = mapOnDiskUrl.calculateAWSS3MD5Hash(<Take the number of parts from the ETag returned by the server>)
if hash == ETag {
print("They are the same.")
}
print ("\(hash!)")
return nil
}
}
如果服务器返回的ETag没有以ETag结尾的“-”，就传0来计算AWSS3MD5Hash。如果您遇到任何问题，请发表评论。我正在研究一个快速的解决方案，我会在完成后立即更新这个答案。谢谢