如何从NSFileHandle逐行读取数据？
我有一个文本文件有数据给出
例如
PUFGUjVRallYZDNaazFtVjVObU1zWm5ZcUJUYU5ORk4zbGthNHNDVUdSMlFVQmpSVEoxUUNSallYaFhkanBITXBGR1NTQnpZRTltZE1OalVzSkdXQ0Z6WXR0V2RpTmpTdXgwTWs5V1lZSkZiWjFXT29OV2JSVlhaSTUwYUpwR040UUZXTzVHVXFoWFVRcFdWNHdVTUJ0Q1VHSmxXVlJVTlJCMVE1VTFWV PUFGUjVRallYZDNaazFtVjVObU1zWm5ZcUJUYU5ORk4zbGthNHNDVUdSMlFVQmpSVEoxUUNSallYaFhkanBITXBGR1NTQnpZRTltZE1OalVzSkdXQ0Z6WXR0V2RpTmpTdXgwTWs5V1lZSkZiWjFXT29OV2JSVlhaSTUwYUpwR040UUZXTzVHVXFoWFVRcFdWNHdVTUJ0Q1VHSmxXVlJVTlJCMVE1VTFWV 现在我想逐行读取数据。 这意味着首先我想读
PUFGUjVRallYZDNaazFtVjVObU1zWm5ZcUJUYU5ORk4zbGthNHNDVUdSMlFVQmpSVEoxUUNSallYaFhkanBITXBGR1NTQnpZRTltZE1OalVzSkdXQ0Z6WXR0V2RpTmpTdXgwTWs5V1lZSkZiWjFXT29OV2JSVlhaSTUwYUpwR040UUZXTzVHVXFoWFVRcFdWNHdVTUJ0Q1VHSmxXVlJVTlJCMVE1VTFWV
然后剩下的。 任何人有任何想法？
如果你的文件很小，那么@ mipadi的方法可能会很好。 但是，如果文件很大（> 1MB，也许？），那么您可能需要考虑逐行读取文件。 我曾经写过一堂课，我将在这里贴上：
//DDFileReader.h @interface DDFileReader : NSObject { NSString * filePath; NSFileHandle * fileHandle; unsigned long long currentOffset; unsigned long long totalFileLength; NSString * lineDelimiter; NSUInteger chunkSize; } @property (nonatomic, copy) NSString * lineDelimiter; @property (nonatomic) NSUInteger chunkSize; - (id) initWithFilePath:(NSString *)aPath; - (NSString *) readLine; - (NSString *) readTrimmedLine; #if NS_BLOCKS_AVAILABLE - (void) enumerateLinesUsingBlock:(void(^)(NSString*, BOOL *))block; #endif @end //DDFileReader.m #import "DDFileReader.h" @interface NSData (DDAdditions) - (NSRange) rangeOfData_dd:(NSData *)dataToFind; @end @implementation NSData (DDAdditions) - (NSRange) rangeOfData_dd:(NSData *)dataToFind { const void * bytes = [self bytes]; NSUInteger length = [self length]; const void * searchBytes = [dataToFind bytes]; NSUInteger searchLength = [dataToFind length]; NSUInteger searchIndex = 0; NSRange foundRange = {NSNotFound, searchLength}; for (NSUInteger index = 0; index < length; index++) { if (((char *)bytes)[index] == ((char *)searchBytes)[searchIndex]) { //the current character matches if (foundRange.location == NSNotFound) { foundRange.location = index; } searchIndex++; if (searchIndex >= searchLength) { return foundRange; } } else { searchIndex = 0; foundRange.location = NSNotFound; } } return foundRange; } @end @implementation DDFileReader @synthesize lineDelimiter, chunkSize; - (id) initWithFilePath:(NSString *)aPath { if (self = [super init]) { fileHandle = [NSFileHandle fileHandleForReadingAtPath:aPath]; if (fileHandle == nil) { [self release]; return nil; } lineDelimiter = [[NSString alloc] initWithString:@"\n"]; [fileHandle retain]; filePath = [aPath retain]; currentOffset = 0ULL; chunkSize = 10; [fileHandle seekToEndOfFile]; totalFileLength = [fileHandle offsetInFile]; //we don't need to seek back, since readLine will do that. } return self; } - (void) dealloc { [fileHandle closeFile]; [fileHandle release], fileHandle = nil; [filePath release], filePath = nil; [lineDelimiter release], lineDelimiter = nil; currentOffset = 0ULL; [super dealloc]; } - (NSString *) readLine { if (currentOffset >= totalFileLength) { return nil; } NSData * newLineData = [lineDelimiter dataUsingEncoding:NSUTF8StringEncoding]; [fileHandle seekToFileOffset:currentOffset]; NSMutableData * currentData = [[NSMutableData alloc] init]; BOOL shouldReadMore = YES; NSAutoreleasePool * readPool = [[NSAutoreleasePool alloc] init]; while (shouldReadMore) { if (currentOffset >= totalFileLength) { break; } NSData * chunk = [fileHandle readDataOfLength:chunkSize]; NSRange newLineRange = [chunk rangeOfData_dd:newLineData]; if (newLineRange.location != NSNotFound) { //include the length so we can include the delimiter in the string chunk = [chunk subdataWithRange:NSMakeRange(0, newLineRange.location+[newLineData length])]; shouldReadMore = NO; } [currentData appendData:chunk]; currentOffset += [chunk length]; } [readPool release]; NSString * line = [[NSString alloc] initWithData:currentData encoding:NSUTF8StringEncoding]; [currentData release]; return [line autorelease]; } - (NSString *) readTrimmedLine { return [[self readLine] stringByTrimmingCharactersInSet:[NSCharacterSet whitespaceAndNewlineCharacterSet]]; } #if NS_BLOCKS_AVAILABLE - (void) enumerateLinesUsingBlock:(void(^)(NSString*, BOOL*))block { NSString * line = nil; BOOL stop = NO; while (stop == NO && (line = [self readLine])) { block(line, &stop); } } #endif @end
然后使用这个，你会这样做：
DDFileReader * reader = [[DDFileReader alloc] initWithFilePath:pathToMyFile]; NSString * line = nil; while ((line = [reader readLine])) { NSLog(@"read line: %@", line); } [reader release];
或者（对于10.6+和iOS 4+）：
DDFileReader * reader = [[DDFileReader alloc] initWithFilePath:pathToMyFile]; [reader enumerateLinesUsingBlock:^(NSString * line, BOOL * stop) { NSLog(@"read line: %@", line); }]; [reader release];
圣诞节快乐。 🙂
我重写了这是ARC兼容：
// // DDFileReader.m // PBX2OPML // // Created by michael isbell on 11/6/11. // Copyright (c) 2011 BlueSwitch. All rights reserved. // //DDFileReader.m #import "DDFileReader.h" @interface NSData (DDAdditions) - (NSRange) rangeOfData_dd:(NSData *)dataToFind; @end @implementation NSData (DDAdditions) - (NSRange) rangeOfData_dd:(NSData *)dataToFind { const void * bytes = [self bytes]; NSUInteger length = [self length]; const void * searchBytes = [dataToFind bytes]; NSUInteger searchLength = [dataToFind length]; NSUInteger searchIndex = 0; NSRange foundRange = {NSNotFound, searchLength}; for (NSUInteger index = 0; index < length; index++) { if (((char *)bytes)[index] == ((char *)searchBytes)[searchIndex]) { //the current character matches if (foundRange.location == NSNotFound) { foundRange.location = index; } searchIndex++; if (searchIndex >= searchLength) { return foundRange; } } else { searchIndex = 0; foundRange.location = NSNotFound; } } return foundRange; } @end @implementation DDFileReader @synthesize lineDelimiter, chunkSize; - (id) initWithFilePath:(NSString *)aPath { if (self = [super init]) { fileHandle = [NSFileHandle fileHandleForReadingAtPath:aPath]; if (fileHandle == nil) { return nil; } lineDelimiter = @"\n"; currentOffset = 0ULL; // ??? chunkSize = 10; [fileHandle seekToEndOfFile]; totalFileLength = [fileHandle offsetInFile]; //we don't need to seek back, since readLine will do that. } return self; } - (void) dealloc { [fileHandle closeFile]; currentOffset = 0ULL; } - (NSString *) readLine { if (currentOffset >= totalFileLength) { return nil; } NSData * newLineData = [lineDelimiter dataUsingEncoding:NSUTF8StringEncoding]; [fileHandle seekToFileOffset:currentOffset]; NSMutableData * currentData = [[NSMutableData alloc] init]; BOOL shouldReadMore = YES; @autoreleasepool { while (shouldReadMore) { if (currentOffset >= totalFileLength) { break; } NSData * chunk = [fileHandle readDataOfLength:chunkSize]; NSRange newLineRange = [chunk rangeOfData_dd:newLineData]; if (newLineRange.location != NSNotFound) { //include the length so we can include the delimiter in the string chunk = [chunk subdataWithRange:NSMakeRange(0, newLineRange.location+[newLineData length])]; shouldReadMore = NO; } [currentData appendData:chunk]; currentOffset += [chunk length]; } } NSString * line = [[NSString alloc] initWithData:currentData encoding:NSUTF8StringEncoding]; return line; } - (NSString *) readTrimmedLine { return [[self readLine] stringByTrimmingCharactersInSet:[NSCharacterSet whitespaceAndNewlineCharacterSet]]; } #if NS_BLOCKS_AVAILABLE - (void) enumerateLinesUsingBlock:(void(^)(NSString*, BOOL*))block { NSString * line = nil; BOOL stop = NO; while (stop == NO && (line = [self readLine])) { block(line, &stop); } } #endif @end
我开始了一个基于Dave DeLong源代码的GitHub项目 。 欢迎您改进代码。 现在我可以阅读文件向前和向后。
NSString *fh = [NSString stringWithContentsOfFile:filePath encoding:fileEncoding error:NULL]; for (NSString *line in [fh componentsSeparatedByString:@"\n"]) { // Do something with the line }
Cocoa中没有API或内置的语言结构，用于逐行读取文件。
这里是我用来从NSInputStream中读取单独一行的方法。 请注意，它为可读性而不是速度进行了优化。 😉
- (NSString*) readLine: (NSInputStream*) inputStream { NSMutableData* data = [NSMutableData data]; uint8_t oneByte; do { int actuallyRead = [inputStream read: &oneByte maxLength: 1]; if (actuallyRead == 1) { [data appendBytes: &oneByte length: 1]; } } while (oneByte != '\n'); return [[NSString alloc] initWithData: data encoding: NSUTF8StringEncoding];
我发现GitX也使用线阅读器。
在GitHub或者Michael Stapelberg的网站 上检查brotherbard的存储库 。
@杨乔
太好了！ 接下来的几天我会仔细看看。
我会很高兴，如果你想在GitHub上分发我的存储库，并发送一个拉请求 。
LARGE文本文件的这个问题的答案不需要自定义函数。 Objective-C是c的超集，因此有c方法可以做到这一点。
FILE* file = fopen("path to my file", "r"); size_t length; char *cLine = fgetln(file,&length); while (length>0) { char str[length+1]; strncpy(str, cLine, length); str[length] = '\0'; NSString *line = [NSString stringWithFormat:@"%s",str]; % Do what you want here. cLine = fgetln(file,&length); }
请注意，fgetln不会保留你的换行符。 此外，我们+1的长度，因为我们想为NULL终止空间。
我已经修改FileReader到一个NSFileHandle类别，希望它可以帮助其他人
@interface NSFileHandle (Readline) - (NSString*)readLine; - (NSString*)readLineBackwards; @end #import "NSFileHandle+Readline.h" #import "NSDataExtensions.h" @implementation NSFileHandle (Readline) - (NSString*)readLine { NSString * _lineDelimiter = @"\n"; NSData* newLineData = [_lineDelimiter dataUsingEncoding:NSUTF8StringEncoding]; NSMutableData* currentData = [[NSMutableData alloc] init]; BOOL shouldReadMore = YES; NSUInteger _chunkSize = 10; while (shouldReadMore) { NSData* chunk = [self readDataOfLength:_chunkSize]; // always length = 10 if ([chunk length] == 0) { break; } // Find the location and length of the next line delimiter. NSRange newLineRange = [chunk rangeOfData:newLineData]; if (newLineRange.location != NSNotFound) { // Include the length so we can include the delimiter in the string. NSRange subDataRange = NSMakeRange(0, newLineRange.location + [newLineData length]); unsigned long long newOffset = [self offsetInFile] - [chunk length] + newLineRange.location + [newLineData length]; [self seekToFileOffset:newOffset]; chunk = [chunk subdataWithRange:subDataRange]; shouldReadMore = NO; } [currentData appendData:chunk]; } NSString* line = [currentData stringValueWithEncoding:NSASCIIStringEncoding]; return line; } - (NSString*)readLineBackwards { NSString * _lineDelimiter = @"\n"; NSData* newLineData = [_lineDelimiter dataUsingEncoding:NSUTF8StringEncoding]; NSUInteger _chunkSize = 10; NSMutableData* currentData = [[NSMutableData alloc] init]; BOOL shouldReadMore = YES; while (shouldReadMore) { unsigned long long offset; NSUInteger currentChunkSize = _chunkSize; if ([self offsetInFile] <= _chunkSize) { offset = 0; currentChunkSize = [self offsetInFile]; shouldReadMore = NO; } else { offset = [self offsetInFile] - _chunkSize; } NSLog(@"seek to offset %qu, offset in file is %qu", offset, [self offsetInFile]); [self seekToFileOffset:offset]; NSData* chunk = [self readDataOfLength:currentChunkSize]; NSRange newLineRange = [chunk rangeOfDataBackwardsSearch:newLineData]; if (newLineRange.location == NSNotFound) { [self seekToFileOffset:offset]; } if (newLineRange.location != NSNotFound) { NSUInteger subDataLoc = newLineRange.location; NSUInteger subDataLen = currentChunkSize - subDataLoc; chunk = [chunk subdataWithRange:NSMakeRange(subDataLoc, subDataLen)]; NSLog(@"got chunk data %@", [chunk stringValueWithEncoding:NSASCIIStringEncoding]); shouldReadMore = NO; [self seekToFileOffset:offset + newLineRange.location]; } [currentData prepend:chunk]; } NSString* line = [[NSString alloc] initWithData:currentData encoding:NSASCIIStringEncoding]; return [line autorelease]; } @end // // NSDataExtensions.m // LineReader // // Created by Tobias Preuss on 08.10.10. // Copyright 2010 Tobias Preuss. All rights reserved. // #import "NSDataExtensions.h" // ----------------------------------------------------------------------------- // NSData additions. // ----------------------------------------------------------------------------- /** Extension of the NSData class. Data can be found forwards or backwards. Further the extension supplies a function to convert the contents to string for debugging purposes. @param Additions Category labeled Additions. @returns An initialized NSData object or nil if the object could not be created. */ @implementation NSData (Additions) /** Returns a range of data. @param dataToFind Data object specifying the delimiter and encoding. @returns A range. */ - (NSRange)rangeOfData:(NSData*)dataToFind { const void* bytes = [self bytes]; NSUInteger length = [self length]; const void* searchBytes = [dataToFind bytes]; NSUInteger searchLength = [dataToFind length]; NSUInteger searchIndex = 0; NSRange foundRange = {NSNotFound, searchLength}; for (NSUInteger index = 0; index < length; index++) { // The current character matches. if (((char*)bytes)[index] == ((char*)searchBytes)[searchIndex]) { // Store found location if not done earlier. if (foundRange.location == NSNotFound) { foundRange.location = index; } // Increment search character index to check for match. searchIndex++; // All search character match. // Break search routine and return found position. if (searchIndex >= searchLength) { return foundRange; } } // Match does not continue. // Return to the first search character. // Discard former found location. else { searchIndex = 0; foundRange.location = NSNotFound; } } return foundRange; } - (NSRange)rangeOfDataBackwardsSearch:(NSData*)dataToFind { const void* bytes = [self bytes]; NSUInteger length = [self length]; const void* searchBytes = [dataToFind bytes]; NSUInteger searchLength = [dataToFind length]; NSUInteger searchIndex = 0; NSRange foundRange = {NSNotFound, searchLength}; if (length < searchLength) { return foundRange; } for (NSUInteger index = length - searchLength; index >= 0;) { // NSLog(@"%c == %c", ((char*)bytes)[index], ((char*)searchBytes)[searchIndex]); /* DEBUG LOG */ if (((char*)bytes)[index] == ((char*)searchBytes)[searchIndex]) { // The current character matches. if (foundRange.location == NSNotFound) { foundRange.location = index; } index++; searchIndex++; if (searchIndex >= searchLength) { return foundRange; } } else { // Decrement to search backwards. if (foundRange.location == NSNotFound) { // Skip if first byte has been reached. if (index == 0) { foundRange.location = NSNotFound; return foundRange; } index--; } // Jump over the former found location // to avoid endless loop. else { index = index - 2; } searchIndex = 0; foundRange.location = NSNotFound; } } return foundRange; } - (NSString*)stringValueWithEncoding:(NSStringEncoding)encoding { return [[NSString alloc] initWithData:self encoding:encoding]; } @end // ----------------------------------------------------------------------------- // NSMutableData additions. // ----------------------------------------------------------------------------- /** Extension of the NSMutableData class. Data can be prepended in addition to the append function of the framework. @param Additions Category labeled Additions. @returns An initialized NSMutableData object or nil if the object could not be created. */ @implementation NSMutableData (Additions) /** Inserts the data before the data of the object. @param data Data to be prepended. */ - (void)prepend:(NSData*)data { NSMutableData* concat = [NSMutableData dataWithData:data]; [concat appendData:self]; [self setData:concat]; } @end
您也可以通过https://github.com/xcvista/ohttpd2/tree/master/CGIStream查看我为我的HTTP服务器项目创build的CGIStream库。; 这个代码不是文件描述符，而是在NSInputStream上运行。 它本质上是一个来自微软.NET框架的System.IO.StreamReader和System.IO.StreamWriter的Objective-C克隆。
它不仅能处理文件，还能处理networking套接字。 我用它来处理HTTP协议，这是CGI前缀的同名。
我碰到类似的情况，还有其他一些情况，这里是我在Swift 3中的解决scheme。假设文本文件是utf8。
extension FileHandle { func enumerateLines(_ block: @escaping (String, UnsafeMutablePointer<Bool>) -> Void) { // find the end of file var offset = self.offsetInFile let eof = self.seekToEndOfFile() self.seek(toFileOffset: offset) let blockSize = 1024 var buffer = Data() // process to the end of file while offset + UInt64(buffer.count) < eof { var found = false // make sure buffer contains at least one CR, LF or null while !found && offset + UInt64(buffer.count) < eof { let block = self.readData(ofLength: blockSize) buffer.append(block) for byte in block { if [0x0d, 0x0a, 0x00].contains(byte) { found = true ; break } } } // retrieve lines within the buffer var index = 0 var head = 0 // head of line var done = false buffer.enumerateBytes({ (pointer, count, stop) in while index < count { // find a line terminator if [0x0d, 0x0a, 0x00].contains(pointer[index]) { let lineData = Data(pointer[head ..< index]) if let line = String(bytes: lineData, encoding: .utf8) { block(line, &stop) // stop requested if pointer[index] == 0x0d && index+1 < count && pointer[index+1] == 0x0a { index += 2 ; head = index } else { index += 1 ; head = index } if stop { done = true ; return } // end of enumerateLines } else { return } // end of enumerateLines } else { index += 1 } } }) offset += UInt64(head) buffer.replaceSubrange(0 ..< head, with: Data()) if done { // stop requested self.seek(toFileOffset: offset) return } } }
这是用法：
let fileURL = Bundle.main.url(forResource: "huge_file", withExtension: "txt")! let fileHandle = try! FileHandle(forReadingFrom: fileURL) fileHandle.enumerateLines { (line, stop) in if someCondition { stop.pointee = true } print(line) } /* let remaining = fileHandle.readDataToEndOfFile() */
https://gist.github.com/codelynx/c1de603a85e7503fe9597d027e93f4de
