Read a file/URL line-by-line in Swift

问题:

I am trying to read a file given in an NSURL and load it into an array, with items separated by a newline character \\n.

Here is the way I\'ve done it so far:

var possList: NSString? = NSString.stringWithContentsOfURL(filePath.URL) as? NSString
if var list = possList {
    list = list.componentsSeparatedByString(\"\\n\") as NSString[]
    return list
}
else {
    //return empty list
}

I\'m not very happy with this for a couple of reasons. One, I\'m working with files that range from a few kilobytes to hundreds of MB in size. As you can imagine, working with strings this large is slow and unwieldy. Secondly, this freezes up the UI when it\'s executing--again, not good.

I\'ve looked into running this code in a separate thread, but I\'ve been having trouble with that, and besides, it still doesn\'t solve the problem of dealing with huge strings.

What I\'d like to do is something along the lines of the following pseudocode:

var aStreamReader = new StreamReader(from_file_or_url)
while aStreamReader.hasNextLine == true {
    currentline = aStreamReader.nextLine()
    list.addItem(currentline)
}

How would I accomplish this in Swift?

A few notes about the files I\'m reading from: All files consist of short (<255 chars) strings separated by either \\n or \\r\\n. The length of the files range from ~100 lines to over 50 million lines. They may contain European characters, and/or characters with accents.

回答1:

(The code is for Swift 2.2/Xcode 7.3 now. Older versions can be found in the edit history if somebody needs it. An updated version for Swift 3 is provided at the end.)

The following Swift code is heavily inspired by the various answers to How to read data from NSFileHandle line by line?. It reads from the file in chunks, and converts complete lines to strings.

The default line delimiter (\\n), string encoding (UTF-8) and chunk size (4096) can be set with optional parameters.

class StreamReader  {

    let encoding : UInt
    let chunkSize : Int

    var fileHandle : NSFileHandle!
    let buffer : NSMutableData!
    let delimData : NSData!
    var atEof : Bool = false

    init?(path: String, delimiter: String = \"\\n\", encoding : UInt = NSUTF8StringEncoding, chunkSize : Int = 4096) {
        self.chunkSize = chunkSize
        self.encoding = encoding

        if let fileHandle = NSFileHandle(forReadingAtPath: path),
            delimData = delimiter.dataUsingEncoding(encoding),
            buffer = NSMutableData(capacity: chunkSize)
        {
            self.fileHandle = fileHandle
            self.delimData = delimData
            self.buffer = buffer
        } else {
            self.fileHandle = nil
            self.delimData = nil
            self.buffer = nil
            return nil
        }
    }

    deinit {
        self.close()
    }

    /// Return next line, or nil on EOF.
    func nextLine() -> String? {
        precondition(fileHandle != nil, \"Attempt to read from closed file\")

        if atEof {
            return nil
        }

        // Read data chunks from file until a line delimiter is found:
        var range = buffer.rangeOfData(delimData, options: [], range: NSMakeRange(0, buffer.length))
        while range.location == NSNotFound {
            let tmpData = fileHandle.readDataOfLength(chunkSize)
            if tmpData.length == 0 {
                // EOF or read error.
                atEof = true
                if buffer.length > 0 {
                    // Buffer contains last line in file (not terminated by delimiter).
                    let line = NSString(data: buffer, encoding: encoding)

                    buffer.length = 0
                    return line as String?
                }
                // No more lines.
                return nil
            }
            buffer.appendData(tmpData)
            range = buffer.rangeOfData(delimData, options: [], range: NSMakeRange(0, buffer.length))
        }

        // Convert complete line (excluding the delimiter) to a string:
        let line = NSString(data: buffer.subdataWithRange(NSMakeRange(0, range.location)),
            encoding: encoding)
        // Remove line (and the delimiter) from the buffer:
        buffer.replaceBytesInRange(NSMakeRange(0, range.location + range.length), withBytes: nil, length: 0)

        return line as String?
    }

    /// Start reading from the beginning of file.
    func rewind() -> Void {
        fileHandle.seekToFileOffset(0)
        buffer.length = 0
        atEof = false
    }

    /// Close the underlying file. No reading must be done after calling this method.
    func close() -> Void {
        fileHandle?.closeFile()
        fileHandle = nil
    }
}

Usage:

if let aStreamReader = StreamReader(path: \"/path/to/file\") {
    defer {
        aStreamReader.close()
    }
    while let line = aStreamReader.nextLine() {
        print(line)
    }
}

You can even use the reader with a for-in loop

for line in aStreamReader {
    print(line)
}

by implementing the SequenceType protocol (compare http://robots.thoughtbot.com/swift-sequences):

extension StreamReader : SequenceType {
    func generate() -> AnyGenerator<String> {
        return AnyGenerator {
            return self.nextLine()
        }
    }
}

---

Update for Swift 3/Xcode 8 beta 6: Also \"modernized\" to use guard and the new Data value type:

class StreamReader  {

    let encoding : String.Encoding
    let chunkSize : Int
    var fileHandle : FileHandle!
    let delimData : Data
    var buffer : Data
    var atEof : Bool

    init?(path: String, delimiter: String = \"\\n\", encoding: String.Encoding = .utf8,
          chunkSize: Int = 4096) {

        guard let fileHandle = FileHandle(forReadingAtPath: path),
            let delimData = delimiter.data(using: encoding) else {
                return nil
        }
        self.encoding = encoding
        self.chunkSize = chunkSize
        self.fileHandle = fileHandle
        self.delimData = delimData
        self.buffer = Data(capacity: chunkSize)
        self.atEof = false
    }

    deinit {
        self.close()
    }

    /// Return next line, or nil on EOF.
    func nextLine() -> String? {
        precondition(fileHandle != nil, \"Attempt to read from closed file\")

        // Read data chunks from file until a line delimiter is found:
        while !atEof {
            if let range = buffer.range(of: delimData) {
                // Convert complete line (excluding the delimiter) to a string:
                let line = String(data: buffer.subdata(in: 0..<range.lowerBound), encoding: encoding)
                // Remove line (and the delimiter) from the buffer:
                buffer.removeSubrange(0..<range.upperBound)
                return line
            }
            let tmpData = fileHandle.readData(ofLength: chunkSize)
            if tmpData.count > 0 {
                buffer.append(tmpData)
            } else {
                // EOF or read error.
                atEof = true
                if buffer.count > 0 {
                    // Buffer contains last line in file (not terminated by delimiter).
                    let line = String(data: buffer as Data, encoding: encoding)
                    buffer.count = 0
                    return line
                }
            }
        }
        return nil
    }

    /// Start reading from the beginning of file.
    func rewind() -> Void {
        fileHandle.seek(toFileOffset: 0)
        buffer.count = 0
        atEof = false
    }

    /// Close the underlying file. No reading must be done after calling this method.
    func close() -> Void {
        fileHandle?.closeFile()
        fileHandle = nil
    }
}

extension StreamReader : Sequence {
    func makeIterator() -> AnyIterator<String> {
        return AnyIterator {
            return self.nextLine()
        }
    }
}

回答2:

I\'ve wrapped code from algal\'s answer into convenient class (Swift 4.0)

UPD: This code is platform independent (macOS, iOS, ubuntu)

import Foundation

/// Read text file line by line
public class LineReader {
    public let path: String

    fileprivate let file: UnsafeMutablePointer<FILE>!

    init?(path: String) {
        self.path = path
        file = fopen(path, \"r\")
        guard file != nil else { return nil }
    }

    public var nextLine: String? {
        var line:UnsafeMutablePointer<CChar>? = nil
        var linecap:Int = 0
        defer { free(line) }
        return getline(&line, &linecap, file) > 0 ? String(cString: line!) : nil
    }

    deinit {
        fclose(file)
    }
}

extension LineReader: Sequence {
    public func  makeIterator() -> AnyIterator<String> {
        return AnyIterator<String> {
            return self.nextLine
        }
    }
}

Usage:

guard let reader = LineReader(path: \"/Path/to/file.txt\") else {
    return; // cannot open file
}

for line in reader {
    print(\">\" + line.trimmingCharacters(in: .whitespacesAndNewlines))      
}

Repository on github

回答3:

I\'m late to the game, but here\'s small class I wrote for that purpose. After some different attempts (try to subclass NSInputStream) I found this to be a reasonable and simple approach.

Remember to #import <stdio.h> in your bridging header.

// Use is like this:
let readLine = ReadLine(somePath)
while let line = readLine.readLine() {
    // do something...
}

class ReadLine {

    private var buf = UnsafeMutablePointer<Int8>.alloc(1024)
    private var n: Int = 1024

    let path: String
    let mode: String = \"r\"

    private lazy var filepointer: UnsafeMutablePointer<FILE> = {
        let csmode = self.mode.withCString { cs in return cs }
        let cspath = self.path.withCString { cs in return cs }

        return fopen(cspath, csmode)
    }()

    init(path: String) {
        self.path = path
    }

    func readline() -> String? {
        // unsafe for unknown input
        if getline(&buf, &n, filepointer) > 0 {
            return String.fromCString(UnsafePointer<CChar>(buf))
        }

        return nil
    }

    deinit {
        buf.dealloc(n)
        fclose(filepointer)
    }
}

回答4:

It turns out good old-fasioned C API is pretty comfortable in Swift once you grok UnsafePointer. Here is a simple cat that reads from stdin and prints to stdout line-by-line. You don\'t even need Foundation. Darwin suffices:

import Darwin
let bufsize = 4096
// let stdin = fdopen(STDIN_FILENO, \"r\") it is now predefined in Darwin
var buf = UnsafePointer<Int8>.alloc(bufsize)
while fgets(buf, Int32(bufsize-1), stdin) {
    print(String.fromCString(CString(buf)))
}
buf.destroy()

回答5:

This function takes a file stream and returns an AnyGenerator that returns every line of the file:

func lineGenerator(file:UnsafeMutablePointer<FILE>) -> AnyGenerator<String>
{
  return AnyGenerator { () -> String? in
    var line:UnsafeMutablePointer<CChar> = nil
    var linecap:Int = 0
    defer { free(line) }
    return getline(&line, &linecap, file) > 0 ? String.fromCString(line) : nil
  }
}

So for instance, here\'s how you would use it to print every line of a file named \"foo\" in your app bundle:

let path = NSBundle.mainBundle().pathForResource(\"foo\", ofType: nil)!
let file = fopen(path,\"r\") // open the file stream
for line in lineGenerator(file) {
  // suppress print\'s automatically inserted line ending, since
  // lineGenerator captures each line\'s own new line character.
  print(line, separator: \"\", terminator: \"\")
}
fclose(file) // cleanup the file stream

I developed this answer by modifying Alex Brown\'s answer to remove a memory leak mentioned by Martin R\'s comment, and by updating it to work with Swift 2.2 (Xcode 7.3).

回答6:

Try this answer, or read the Mac OS Stream Programming Guide.

You may find that performance will actually be better using the stringWithContentsOfURL, though, as it will be quicker to work with memory-based (or memory-mapped) data than disc-based data.

Executing it on another thread is well documented, also, for example here.

Update

If you don\'t want to read it all at once, and you don\'t want to use NSStreams, then you\'ll probably have to use C-level file I/O. There are many reasons not to do this - blocking, character encoding, handling I/O errors, speed to name but a few - this is what the Foundation libraries are for. I\'ve sketched a simple answer below that just deals with ACSII data:

class StreamReader {

    var eofReached = false
    let fileHandle: UnsafePointer<FILE>

    init (path: String) {
        self.fileHandle = fopen(path.bridgeToObjectiveC().UTF8String, \"rb\".bridgeToObjectiveC().UTF8String)
    }

    deinit {
        fclose(self.fileHandle)
    }

    func nextLine() -> String {
        var nextChar: UInt8 = 0
        var stringSoFar = \"\"
        var eolReached = false
        while (self.eofReached == false) && (eolReached == false) {
            if fread(&nextChar, 1, 1, self.fileHandle) == 1 {
                switch nextChar & 0xFF {
                case 13, 10 : // CR, LF
                    eolReached = true
                case 0...127 : // Keep it in ASCII
                    stringSoFar += NSString(bytes:&nextChar, length:1, encoding: NSASCIIStringEncoding)
                default :
                    stringSoFar += \"<\\(nextChar)>\"
                }
            } else { // EOF or error
                self.eofReached = true
            }
        }
        return stringSoFar
    }
}

// OP\'s original request follows:
var aStreamReader = StreamReader(path: \"~/Desktop/Test.text\".stringByStandardizingPath)

while aStreamReader.eofReached == false { // Changed property name for more accurate meaning
    let currentline = aStreamReader.nextLine()
    //list.addItem(currentline)
    println(currentline)
}

回答7:

(Note: I\'m using Swift 3.0.1 on Xcode 8.2.1 with macOS Sierra 10.12.3)

All of the answers I\'ve seen here missed that he could be looking for LF or CRLF. If everything goes well, s/he could just match on LF and check the returned string for an extra CR at the end. But the general query involves multiple search strings. In other words, the delimiter needs to be a Set<String>, where the set is neither empty nor contains the empty string, instead of a single string.

On my first try at this last year, I tried to do the \"right thing\" and search for a general set of strings. It was too hard; you need a full blown parser and state machines and such. I gave up on it and the project it was part of.

Now I\'m doing the project again, and facing the same challenge again. Now I\'m going to hard-code searching on CR and LF. I don\'t think anyone would need to search on two semi-independent and semi-dependent characters like this outside of CR/LF parsing.

I\'m using the search methods provided by Data, so I\'m not doing string encodings and stuff here. Just raw binary processing. Just assume I got an ASCII superset, like ISO Latin-1 or UTF-8, here. You can handle string encoding at the next-higher layer, and you punt on whether a CR/LF with secondary code-points attached still counts as a CR or LF.

The algorithm: just keep searching for the next CR and the next LF from your current byte offset.

• If neither is found, then consider the next data string to be from the current offset to the end-of-data. Note that the terminator length is 0. Mark this as the end of your reading loop.
• If a LF is found first, or only a LF is found, consider the next data string to be from the current offset to the LF. Note that the terminator length is 1. Move the offset to after the LF.
• If only a CR is found, do like the LF case (just with a different byte value).
• Otherwise, we got a CR followed by a LF.
  • If the two are adjacent, then handle like the LF case, except the terminator length will be 2.
  • If there is one byte between them, and said byte is also CR, then we got the \"Windows developer wrote a binary \\r\\n while in text mode, giving a \\r\\r\\n\" problem. Also handle it like the LF case, except the terminator length will be 3.
  • Otherwise the CR and LF aren\'t connected, and handle like the just-CR case.

Here\'s some code for that:

struct DataInternetLineIterator: IteratorProtocol {

    /// Descriptor of the location of a line
    typealias LineLocation = (offset: Int, length: Int, terminatorLength: Int)

    /// Carriage return.
    static let cr: UInt8 = 13
    /// Carriage return as data.
    static let crData = Data(repeating: cr, count: 1)
    /// Line feed.
    static let lf: UInt8 = 10
    /// Line feed as data.
    static let lfData = Data(repeating: lf, count: 1)

    /// The data to traverse.
    let data: Data
    /// The byte offset to search from for the next line.
    private var lineStartOffset: Int = 0

    /// Initialize with the data to read over.
    init(data: Data) {
        self.data = data
    }

    mutating func next() -> LineLocation? {
        guard self.data.count - self.lineStartOffset > 0 else { return nil }

        let nextCR = self.data.range(of: DataInternetLineIterator.crData, options: [], in: lineStartOffset..<self.data.count)?.lowerBound
        let nextLF = self.data.range(of: DataInternetLineIterator.lfData, options: [], in: lineStartOffset..<self.data.count)?.lowerBound
        var location: LineLocation = (self.lineStartOffset, -self.lineStartOffset, 0)
        let lineEndOffset: Int
        switch (nextCR, nextLF) {
        case (nil, nil):
            lineEndOffset = self.data.count
        case (nil, let offsetLf):
            lineEndOffset = offsetLf!
            location.terminatorLength = 1
        case (let offsetCr, nil):
            lineEndOffset = offsetCr!
            location.terminatorLength = 1
        default:
            lineEndOffset = min(nextLF!, nextCR!)
            if nextLF! < nextCR! {
                location.terminatorLength = 1
            } else {
                switch nextLF! - nextCR! {
                case 2 where self.data[nextCR! + 1] == DataInternetLineIterator.cr:
                    location.terminatorLength += 1  // CR-CRLF
                    fallthrough
                case 1:
                    location.terminatorLength += 1  // CRLF
                    fallthrough
                default:
                    location.terminatorLength += 1  // CR-only
                }
            }
        }
        self.lineStartOffset = lineEndOffset + location.terminatorLength
        location.length += self.lineStartOffset
        return location
    }

}

Of course, if you have a Data block of a length that\'s at least a significant fraction of a gigabyte, you\'ll take a hit whenever no more CR or LF exist from the current byte offset; always fruitlessly searching until the end during every iteration. Reading the data in chunks would help:

struct DataBlockIterator: IteratorProtocol {

    /// The data to traverse.
    let data: Data
    /// The offset into the data to read the next block from.
    private(set) var blockOffset = 0
    /// The number of bytes remaining.  Kept so the last block is the right size if it\'s short.
    private(set) var bytesRemaining: Int
    /// The size of each block (except possibly the last).
    let blockSize: Int

    /// Initialize with the data to read over and the chunk size.
    init(data: Data, blockSize: Int) {
        precondition(blockSize > 0)

        self.data = data
        self.bytesRemaining = data.count
        self.blockSize = blockSize
    }

    mutating func next() -> Data? {
        guard bytesRemaining > 0 else { return nil }
        defer { blockOffset += blockSize ; bytesRemaining -= blockSize }

        return data.subdata(in: blockOffset..<(blockOffset + min(bytesRemaining, blockSize)))
    }

}

You have to mix these ideas together yourself, since I haven\'t done it yet. Consider:

• Of course, you have to consider lines completely contained in a chunk.
• But you have to handle when the ends of a line are in adjacent chunks.
• Or when the endpoints have at least one chunk between them
• The big complication is when the line ends with a multi-byte sequence, but said sequence straddles two chunks! (A line ending in just CR that\'s also the last byte in the chunk is an equivalent case, since you need to read the next chunk to see if your just-CR is actually a CRLF or CR-CRLF. There are similar shenanigans when the chunk ends with CR-CR.)
• And you need to handle when there are no more terminators from your current offset, but the end-of-data is in a later chunk.

Good luck!

回答8:

Or you could simply use a Generator:

let stdinByLine = GeneratorOf({ () -> String? in
    var input = UnsafeMutablePointer<Int8>(), lim = 0
    return getline(&input, &lim, stdin) > 0 ? String.fromCString(input) : nil
})

Let\'s try it out

for line in stdinByLine {
    println(\">>> \\(line)\")
}

It\'s simple, lazy, and easy to chain with other swift things like enumerators and functors such as map, reduce, filter; using the lazy() wrapper.

---

It generalises to all FILE as:

let byLine = { (file:UnsafeMutablePointer<FILE>) in
    GeneratorOf({ () -> String? in
        var input = UnsafeMutablePointer<Int8>(), lim = 0
        return getline(&input, &lim, file) > 0 ? String.fromCString(input) : nil
    })
}

called like

for line in byLine(stdin) { ... }

回答9:

I wanted a version that did not continually modify the buffer or duplicate code, as both are inefficient, and would allow for any size buffer (including 1 byte) and any delimiter. It has one public method: readline(). Calling this method will return the String value of the next line or nil at EOF.

import Foundation

// LineStream(): path: String, [buffSize: Int], [delim: String] -> nil | String
// ============= --------------------------------------------------------------
// path:     the path to a text file to be parsed
// buffSize: an optional buffer size, (1...); default is 4096
// delim:    an optional delimiter String; default is \"\\n\"
// ***************************************************************************
class LineStream {
    let path: String
    let handle: NSFileHandle!

    let delim: NSData!
    let encoding: NSStringEncoding

    var buffer = NSData()
    var buffSize: Int

    var buffIndex = 0
    var buffEndIndex = 0

    init?(path: String,
      buffSize: Int = 4096,
      delim: String = \"\\n\",
      encoding: NSStringEncoding = NSUTF8StringEncoding)
    {
      self.handle = NSFileHandle(forReadingAtPath: path)
      self.path = path
      self.buffSize = buffSize < 1 ? 1 : buffSize
      self.encoding = encoding
      self.delim = delim.dataUsingEncoding(encoding)
      if handle == nil || self.delim == nil {
        print(\"ERROR initializing LineStream\") /* TODO use STDERR */
        return nil
      }
    }

  // PRIVATE
  // fillBuffer(): _ -> Int [0...buffSize]
  // ============= -------- ..............
  // Fill the buffer with new data; return with the buffer size, or zero
  // upon reaching end-of-file
  // *********************************************************************
  private func fillBuffer() -> Int {
    buffer = handle.readDataOfLength(buffSize)
    buffIndex = 0
    buffEndIndex = buffer.length

    return buffEndIndex
  }

  // PRIVATE
  // delimLocation(): _ -> Int? nil | [1...buffSize]
  // ================ --------- ....................
  // Search the remaining buffer for a delimiter; return with the location
  // of a delimiter in the buffer, or nil if one is not found.
  // ***********************************************************************
  private func delimLocation() -> Int? {
    let searchRange = NSMakeRange(buffIndex, buffEndIndex - buffIndex)
    let rangeToDelim = buffer.rangeOfData(delim,
                                          options: [], range: searchRange)
    return rangeToDelim.location == NSNotFound
        ? nil
        : rangeToDelim.location
  }

  // PRIVATE
  // dataStrValue(): NSData -> String (\"\" | String)
  // =============== ---------------- .............
  // Attempt to convert data into a String value using the supplied encoding; 
  // return the String value or empty string if the conversion fails.
  // ***********************************************************************
    private func dataStrValue(data: NSData) -> String? {
      if let strVal = NSString(data: data, encoding: encoding) as? String {
          return strVal
      } else { return \"\" }
}

  // PUBLIC
  // readLine(): _ -> String? nil | String
  // =========== ____________ ............
  // Read the next line of the file, i.e., up to the next delimiter or end-of-
  // file, whichever occurs first; return the String value of the data found, 
  // or nil upon reaching end-of-file.
  // *************************************************************************
  func readLine() -> String? {
    guard let line = NSMutableData(capacity: buffSize) else {
        print(\"ERROR setting line\")
        exit(EXIT_FAILURE)
    }

    // Loop until a delimiter is found, or end-of-file is reached
    var delimFound = false
    while !delimFound {
        // buffIndex will equal buffEndIndex in three situations, resulting
        // in a (re)filling of the buffer:
        //   1. Upon the initial call;
        //   2. If a search for a delimiter has failed
        //   3. If a delimiter is found at the end of the buffer
        if buffIndex == buffEndIndex {
            if fillBuffer() == 0 {
                return nil
            }
        }

        var lengthToDelim: Int
        let startIndex = buffIndex

        // Find a length of data to place into the line buffer to be
        // returned; reset buffIndex
        if let delim = delimLocation() {
            // SOME VALUE when a delimiter is found; append that amount of
            // data onto the line buffer,and then return the line buffer
            delimFound = true
            lengthToDelim = delim - buffIndex
            buffIndex = delim + 1   // will trigger a refill if at the end
                                    // of the buffer on the next call, but
                                    // first the line will be returned
        } else {
            // NIL if no delimiter left in the buffer; append the rest of
            // the buffer onto the line buffer, refill the buffer, and
            // continue looking
            lengthToDelim = buffEndIndex - buffIndex
            buffIndex = buffEndIndex    // will trigger a refill of buffer
                                        // on the next loop
        }

        line.appendData(buffer.subdataWithRange(
            NSMakeRange(startIndex, lengthToDelim)))
    }

    return dataStrValue(line)
  }
}

It is called as follows:

guard let myStream = LineStream(path: \"/path/to/file.txt\")
else { exit(EXIT_FAILURE) }

while let s = myStream.readLine() {
  print(s)
}