File: _stream_transform.js

package info (click to toggle)
nodejs 4.8.2~dfsg-1
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 62,476 kB
  • ctags: 111,183
  • sloc: cpp: 661,544; ansic: 31,406; python: 23,073; makefile: 1,418; sh: 1,384; perl: 255; lisp: 222; ruby: 76; xml: 50
file content (192 lines) | stat: -rw-r--r-- 6,348 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
// a transform stream is a readable/writable stream where you do
// something with the data.  Sometimes it's called a "filter",
// but that's not a great name for it, since that implies a thing where
// some bits pass through, and others are simply ignored.  (That would
// be a valid example of a transform, of course.)
//
// While the output is causally related to the input, it's not a
// necessarily symmetric or synchronous transformation.  For example,
// a zlib stream might take multiple plain-text writes(), and then
// emit a single compressed chunk some time in the future.
//
// Here's how this works:
//
// The Transform stream has all the aspects of the readable and writable
// stream classes.  When you write(chunk), that calls _write(chunk,cb)
// internally, and returns false if there's a lot of pending writes
// buffered up.  When you call read(), that calls _read(n) until
// there's enough pending readable data buffered up.
//
// In a transform stream, the written data is placed in a buffer.  When
// _read(n) is called, it transforms the queued up data, calling the
// buffered _write cb's as it consumes chunks.  If consuming a single
// written chunk would result in multiple output chunks, then the first
// outputted bit calls the readcb, and subsequent chunks just go into
// the read buffer, and will cause it to emit 'readable' if necessary.
//
// This way, back-pressure is actually determined by the reading side,
// since _read has to be called to start processing a new chunk.  However,
// a pathological inflate type of transform can cause excessive buffering
// here.  For example, imagine a stream where every byte of input is
// interpreted as an integer from 0-255, and then results in that many
// bytes of output.  Writing the 4 bytes {ff,ff,ff,ff} would result in
// 1kb of data being output.  In this case, you could write a very small
// amount of input, and end up with a very large amount of output.  In
// such a pathological inflating mechanism, there'd be no way to tell
// the system to stop doing the transform.  A single 4MB write could
// cause the system to run out of memory.
//
// However, even in such a pathological case, only a single written chunk
// would be consumed, and then the rest would wait (un-transformed) until
// the results of the previous transformed chunk were consumed.

'use strict';

module.exports = Transform;

const Duplex = require('_stream_duplex');
const util = require('util');
util.inherits(Transform, Duplex);


function TransformState(stream) {
  this.afterTransform = function(er, data) {
    return afterTransform(stream, er, data);
  };

  this.needTransform = false;
  this.transforming = false;
  this.writecb = null;
  this.writechunk = null;
  this.writeencoding = null;
}

function afterTransform(stream, er, data) {
  var ts = stream._transformState;
  ts.transforming = false;

  var cb = ts.writecb;

  if (!cb)
    return stream.emit('error', new Error('no writecb in Transform class'));

  ts.writechunk = null;
  ts.writecb = null;

  if (data !== null && data !== undefined)
    stream.push(data);

  cb(er);

  var rs = stream._readableState;
  rs.reading = false;
  if (rs.needReadable || rs.length < rs.highWaterMark) {
    stream._read(rs.highWaterMark);
  }
}


function Transform(options) {
  if (!(this instanceof Transform))
    return new Transform(options);

  Duplex.call(this, options);

  this._transformState = new TransformState(this);

  // when the writable side finishes, then flush out anything remaining.
  var stream = this;

  // start out asking for a readable event once data is transformed.
  this._readableState.needReadable = true;

  // we have implemented the _read method, and done the other things
  // that Readable wants before the first _read call, so unset the
  // sync guard flag.
  this._readableState.sync = false;

  if (options) {
    if (typeof options.transform === 'function')
      this._transform = options.transform;

    if (typeof options.flush === 'function')
      this._flush = options.flush;
  }

  this.once('prefinish', function() {
    if (typeof this._flush === 'function')
      this._flush(function(er) {
        done(stream, er);
      });
    else
      done(stream);
  });
}

Transform.prototype.push = function(chunk, encoding) {
  this._transformState.needTransform = false;
  return Duplex.prototype.push.call(this, chunk, encoding);
};

// This is the part where you do stuff!
// override this function in implementation classes.
// 'chunk' is an input chunk.
//
// Call `push(newChunk)` to pass along transformed output
// to the readable side.  You may call 'push' zero or more times.
//
// Call `cb(err)` when you are done with this chunk.  If you pass
// an error, then that'll put the hurt on the whole operation.  If you
// never call cb(), then you'll never get another chunk.
Transform.prototype._transform = function(chunk, encoding, cb) {
  throw new Error('not implemented');
};

Transform.prototype._write = function(chunk, encoding, cb) {
  var ts = this._transformState;
  ts.writecb = cb;
  ts.writechunk = chunk;
  ts.writeencoding = encoding;
  if (!ts.transforming) {
    var rs = this._readableState;
    if (ts.needTransform ||
        rs.needReadable ||
        rs.length < rs.highWaterMark)
      this._read(rs.highWaterMark);
  }
};

// Doesn't matter what the args are here.
// _transform does all the work.
// That we got here means that the readable side wants more data.
Transform.prototype._read = function(n) {
  var ts = this._transformState;

  if (ts.writechunk !== null && ts.writecb && !ts.transforming) {
    ts.transforming = true;
    this._transform(ts.writechunk, ts.writeencoding, ts.afterTransform);
  } else {
    // mark that we need a transform, so that any data that comes in
    // will get processed, now that we've asked for it.
    ts.needTransform = true;
  }
};


function done(stream, er) {
  if (er)
    return stream.emit('error', er);

  // if there's nothing in the write buffer, then that means
  // that nothing more will ever be provided
  var ws = stream._writableState;
  var ts = stream._transformState;

  if (ws.length)
    throw new Error('calling transform done when ws.length != 0');

  if (ts.transforming)
    throw new Error('calling transform done when still transforming');

  return stream.push(null);
}