Safe fs.ReadStream
and fs.WriteStream
using the same fd.
Let's say that you want to perform a parallel upload of a file to a remote
server. To do this, we want to create multiple read streams. The first thing
you might think of is to use the {start: 0, end: 0}
API offs.createReadStream
. This gives you two choices:
fs.ReadStream
objects.Neither of these are acceptable options. The first one is a severe bug,
because the API docs for fs.write
state:
Note that it is unsafe to use
fs.write
multiple times on the same file
without waiting for the callback. For this scenario,fs.createWriteStream
is strongly recommended.
fs.createWriteStream
will solve the problem if you only create one of them
for the file descriptor, but it will exhibit this unsafety if you create
multiple write streams per file descriptor.
The second option suffers from a race condition. For each additional time the
file is opened after the first, it is possible that the file is modified. So
in our parallel uploading example, we might upload a corrupt file that never
existed on the client's computer.
This module solves this problem by providing createReadStream
andcreateWriteStream
that operate on a shared file descriptor and provides
the convenient stream API while still allowing slicing and dicing.
This module also gives you some additional power that the builtinfs.createWriteStream
do not give you. These features are:
FdSlicer
instance from a Buffer
. This enables youvar fdSlicer = require('fd-slicer');
var fs = require('fs');
fs.open("file.txt", 'r', function(err, fd) {
if (err) throw err;
var slicer = fdSlicer.createFromFd(fd);
var firstPart = slicer.createReadStream({start: 0, end: 100});
var secondPart = slicer.createReadStream({start: 100});
var firstOut = fs.createWriteStream("first.txt");
var secondOut = fs.createWriteStream("second.txt");
firstPart.pipe(firstOut);
secondPart.pipe(secondOut);
});
You can also create from a buffer:
var fdSlicer = require('fd-slicer');
var slicer = FdSlicer.createFromBuffer(someBuffer);
var firstPart = slicer.createReadStream({start: 0, end: 100});
var secondPart = slicer.createReadStream({start: 100});
var firstOut = fs.createWriteStream("first.txt");
var secondOut = fs.createWriteStream("second.txt");
firstPart.pipe(firstOut);
secondPart.pipe(secondOut);
var fdSlicer = require('fd-slicer');
fs.open("file.txt", 'r', function(err, fd) {
if (err) throw err;
var slicer = fdSlicer.createFromFd(fd);
// ...
});
Make sure fd
is a properly initialized file descriptor. If you want to
use createReadStream
make sure you open it for reading and if you want
to use createWriteStream
make sure you open it for writing.
options
is an optional object which can contain:
autoClose
- if set to true
, the file descriptor will be automaticallyfalse
. ref()
and unref()
can be used to increase or decrease thevar fdSlicer = require('fd-slicer');
var slicer = fdSlicer.createFromBuffer(someBuffer);
// ...
options
is an optional object which can contain:
maxChunkSize
- A Number
of bytes. see createReadStream()
.The file descriptor passed in. undefined
if created from a buffer.
Available options
:
start
- Number. The offset into the file to start reading from. Defaultsend
- Number. Exclusive upper bound offset into the file to stop readinghighWaterMark
- Number. The maximum number of bytes to store in theencoding
- String. If specified, then buffers will be decoded to stringsnull
.The ReadableStream that this returns has these additional methods:
destroy(err)
- stop streaming. err
is optional and is the error thatnew Error("stream destroyed")
.If maxChunkSize
was specified (see createFromBuffer()
), the read stream
will provide chunks of at most that size. Normally, the read stream provides
the entire range requested in a single chunk, but this can cause performance
problems in some circumstances.
See thejoshwolfe/yauzl#87.
Available options
:
start
- Number. The offset into the file to start writing to. Defaults toend
- Number. Exclusive upper bound offset into the file. If this offseterr.code === 'ETOOBIG'
. Defaults to Infinity
.highWaterMark
- Number. Buffer level when write()
starts returningdecodeStrings
- Boolean. Whether or not to decode strings into Buffers_write()
. Defaults to true
.The WritableStream that this returns has these additional methods:
destroy()
- stop streamingAnd these additional properties:
bytesWritten
- number of bytes written to the streamAnd these additional events:
bytesWritten
changes.Equivalent to fs.read
, but with concurrency protection.callback
must be defined.
Equivalent to fs.write
, but with concurrency protection.callback
must be defined.
Increase the autoClose
reference count by 1.
Decrease the autoClose
reference count by 1.
Emitted if fs.close
returns an error when auto closing.
Emitted when fd-slicer closes the file descriptor due to autoClose
. Never
emitted if created from a buffer.