小编典典

在Swift中逐行读取文件/ URL

swift

我正在尝试读取中给定的文件NSURL并将其加载到数组中,其中各项之间用换行符分隔\n

到目前为止,这是我做的方法:

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
}

我对此不太满意,原因有两个。第一,我正在处理大小从几千字节到数百MB不等的文件。可以想象,使用如此大的字符串是缓慢且笨拙的。其次,这会在执行时冻结UI,这同样是不好的。

我已经考虑过在单独的线程中运行此代码,但是我一直在遇到麻烦,此外,它仍然不能解决处理巨大字符串的问题。

我想做的事情与以下伪代码类似:

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

我将如何在Swift中完成此任务?

关于我正在读取的文件的一些注意事项:
所有文件都由短字符串(<255个字符)组成,用\n或分隔\r\n。文件的长度从大约100行到超过5000万行。它们可能包含欧洲字符和/或带有重音符号的字符。


阅读 650

收藏
2020-07-07

共1个答案

小编典典

(该代码现在适用于Swift 2.2 / Xcode 7.3。如果有人需要,可以在编辑历史记录中找到旧版本。最后提供了Swift 3的更新版本。)

以下Swift代码从如何逐行从NSFileHandle中读取数据的各种答案中获得了很大的启发
。它从块中读取文件,并将完整的行转换为字符串。

\n可以使用可选参数设置默认的行定界符(),字符串编码(UTF-8)和块大小(4096)。

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
    }
}

用法:

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

您甚至可以将阅读器与for-in循环一起使用

for line in aStreamReader {
    print(line)
}

通过实施SequenceType协议(比较http://robots.thoughtbot.com/swift-
sequences):

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

Swift 3 / Xcode 8 beta 6更新: 还要“现代化”使用guard和新 Data值类型:

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()
        }
    }
}
2020-07-07