我有一个文本文件，其中包含数据
e.g。
PUFGUjVRallYZDNaazFtVjVObU1zWm5ZcUJUYU5ORk4zbGthNHNDVUdSMlFVQmpSVEoxUUNSallYaFhkanBITXBGR1NTQnpZRTltZE1OalVzSkdXQ0Z6WXR0V2RpTmpTdXgwTWs5V1lZSkZiWjFXT29OV2JSVlhaSTUwYUpwR040UUZXTzVHVXFoWFVRcFdWNHdVTUJ0Q1VHSmxXVlJVTlJCMVE1VTFWV
PUFGUjVRallYZDNaazFtVjVObU1zWm5ZcUJUYU5ORk4zbGthNHNDVUdSMlFVQmpSVEoxUUNSallYaFhkanBITXBGR1NTQnpZRTltZE1OalVzSkdXQ0Z6WXR0V2RpTmpTdXgwTWs5V1lZSkZiWjFXT29OV2JSVlhaSTUwYUpwR040UUZXTzVHVXFoWFVRcFdWNHdVTUJ0Q1VHSmxXVlJVTlJCMVE1VTFWV
现在我想逐行读取数据。这意味着首先我要阅读
PUFGUjVRallYZDNaazFtVjVObU1zWm5ZcUJUYU5ORk4zbGthNHNDVUdSMlFVQmpSVEoxUUNSallYaFhkanBITXBGR1NTQnpZRTltZE1OalVzSkdXQ0Z6WXR0V2RpTmpTdXgwTWs5V1lZSkZiWjFXT29OV2JSVlhaSTUwYUpwR040UUZXTzVHVXFoWFVRcFdWNHdVTUJ0Q1VHSmxXVlJVTlJCMVE1VTFWV
然后下一个剩下的。 任何人都有任何想法??
答案 0 :(得分：147)
如果您的文件很小，那么@ mipadi的方法可能会很好。但是，如果您的文件很大（可能是> 1MB？），那么您可能需要考虑逐行读取文件。我曾写过一次课程，我将在此处粘贴：
//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
然后使用它，你会做：
DDFileReader * reader = [[DDFileReader alloc] initWithFilePath:pathToMyFile];
NSString * line = nil;
while ((line = [reader readLine])) {
NSLog(@"read line: %@", line);
}
[reader release];
或（适用于10.6+和iOS 4 +）：
DDFileReader * reader = [[DDFileReader alloc] initWithFilePath:pathToMyFile];
[reader enumerateLinesUsingBlock:^(NSString * line, BOOL * stop) {
NSLog(@"read line: %@", line);
}];
[reader release];
答案 1 :(得分：21)
我将此重写为符合ARC标准：
//
// 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
答案 2 :(得分：17)
我根据GitHub project的源代码开始Dave DeLong。欢迎您改进代码。到现在为止，我可以向前和向后阅读文件。
答案 3 :(得分：12)
NSString *fh = [NSString stringWithContentsOfFile:filePath encoding:fileEncoding error:NULL];
for (NSString *line in [fh componentsSeparatedByString:@"\n"]) {
// Do something with the line
}
在Cocoa或内置语言结构中没有用于逐行读取文件的API。
答案 4 :(得分：4)
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不会保留换行符。另外，我们+1为str的长度，因为我们想为NULL终止腾出空间。
答案 5 :(得分：3)
这是一个用于从NSInputStream中读取单个行的方法。请注意，它针对可读性而非速度进行了优化。 ; - ）
- (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];
答案 6 :(得分：2)
我发现GitX也使用了线路阅读器 结帐brotherbard's repository on GitHub或website of the Michael Stapelberg。
@Joe Yang
太好了！接下来的几天我会仔细看看
如果您想 fork my repository on GitHub并向我发送拉取请求，我会很高兴。
答案 7 :(得分：1)
我已将FileReader修改为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
答案 8 :(得分：1)
您还可以在https://github.com/xcvista/ohttpd2/tree/master/CGIStream查看我为HTTP服务器项目创建的CGIStream库。此代码不是文件描述符，而是在NSInputStream上运行。它本质上是来自Microsoft的.net框架的System.IO.StreamReader和System.IO.StreamWriter的Objective-C克隆。
它不仅适用于文件，还适用于网络套接字。我用它来处理HTTP协议，这是CGI前缀的同名。
答案 9 :(得分：1)
我遇到了与其他情况类似的情况，这是我在Swift 3中的解决方案。假设文本文件为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
}
}
}
以下是用法：
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
答案 10 :(得分：0)
这在Swift 5上对我有用。
https://gist.github.com/sooop/a2b110f8eebdf904d0664ed171bcd7a2