Remove unused var buffer_sent

Under some circumstances, the COPY TO streamming can be CPU-bound,
particularly when PG holds the resultset in memory buffers and the size
of the rows << chunk (64 KB in my linux box).

This commits improves the situation by creating a buffer of `chunk`
size and fitting in as many rows as it can before pushing them. This
results in more balanced read and writes (in terms of size and in bigger
chunks) as well as more frequent calls to the callback, thus freeing the
main loop for other events to be processed, and therefore avoiding
starvation.

README.md

@@ -42,10 +42,15 @@ pg.connect(function(err, client, done) {
   var stream = client.query(copyFrom('COPY my_table FROM STDIN'));
   var fileStream = fs.createReadStream('some_file.tsv')
   fileStream.on('error', done);
-  fileStream.pipe(stream).on('finish', done).on('error', done);
+  stream.on('error', done);
+  stream.on('end', done);
+  fileStream.pipe(stream);
 });
 ```
 
+*Important*: Even if `pg-copy-streams.from` is used as a Writable (via `pipe`), you should not listen for the 'finish' event and expect that the COPY command has already been correctly acknowledged by the database. Internally, a duplex stream is used to pipe the data into the database connection and the COPY command should be considered complete only when the 'end' event is triggered.
+
+
 ## install
 
 ```sh
@@ -56,7 +61,10 @@ $ npm install pg-copy-streams
 
 This module __only__ works with the pure JavaScript bindings.  If you're using `require('pg').native` please make sure to use normal `require('pg')` or `require('pg.js')` when you're using copy streams.
 
-Before you set out on this magical piping journey, you _really_ should read this: http://www.postgresql.org/docs/9.3/static/sql-copy.html, and you might want to take a look at the [tests](https://github.com/brianc/node-pg-copy-streams/tree/master/test) to get an idea of how things work.
+Before you set out on this magical piping journey, you _really_ should read this: http://www.postgresql.org/docs/current/static/sql-copy.html, and you might want to take a look at the [tests](https://github.com/brianc/node-pg-copy-streams/tree/master/test) to get an idea of how things work.
+
+Take note of the following warning in the PostgreSQL documentation:
+> COPY stops operation at the first error. This should not lead to problems in the event of a COPY TO, but the target table will already have received earlier rows in a COPY FROM. These rows will not be visible or accessible, but they still occupy disk space. This might amount to a considerable amount of wasted disk space if the failure happened well into a large copy operation. You might wish to invoke VACUUM to recover the wasted space.
 
 ## contributing
 

copy-to.js

@@ -4,11 +4,12 @@ module.exports = function(txt, options) {
 
 var Transform = require('stream').Transform
 var util = require('util')
+var code = require('./message-formats')
 
 var CopyStreamQuery = function(text, options) {
   Transform.call(this, options)
   this.text = text
-  this._copyOutResponse = null
+  this._gotCopyOutResponse = false
   this.rowCount = 0
 }
 
@@ -23,63 +24,89 @@ CopyStreamQuery.prototype.submit = function(connection) {
   connection.stream.pipe(this)
 }
 
-var code = {
-  E: 69, //Error
-  H: 72, //CopyOutResponse
-  d: 0x64, //CopyData
-  c: 0x63 //CopyDone
-}
-
 CopyStreamQuery.prototype._detach = function() {
   this.connection.stream.unpipe(this)
   // Unpipe can drop us out of flowing mode
   this.connection.stream.resume()
 }
 
-
 CopyStreamQuery.prototype._transform = function(chunk, enc, cb) {
   var offset = 0
+  var Byte1Len = 1;
+  var Int32Len = 4;
   if(this._remainder && chunk) {
     chunk = Buffer.concat([this._remainder, chunk])
   }
-  if(!this._copyOutResponse) {
-    this._copyOutResponse = true
-    if(chunk[0] == code.E) {
-      this._detach()
-      this.push(null)
-      return cb();
+
+  var length;
+  var messageCode;
+  var needPush = false;
+
+  var buffer = Buffer.alloc(chunk.length);
+  var buffer_offset = 0;
+
+  this.pushBufferIfneeded = function() {
+    if (needPush && buffer_offset > 0) {
+      this.push(buffer.slice(0, buffer_offset))
+      buffer_offset = 0;
     }
-    if(chunk[0] != code.H) {
-      this.emit('error', new Error('Expected copy out response'))
-    }
-    var length = chunk.readUInt32BE(1)
-    offset = 1
-    offset += length
   }
-  while((chunk.length - offset) > 5) {
+
+  while((chunk.length - offset) >= (Byte1Len + Int32Len)) {
     var messageCode = chunk[offset]
-    //complete or error
-    if(messageCode == code.c || messageCode == code.E) {
-      this._detach()
-      this.push(null)
-      return cb();
+
+    //console.log('PostgreSQL message ' + String.fromCharCode(messageCode))
+    switch(messageCode) {
+
+      // detect COPY start
+      case code.CopyOutResponse:
+        if (!this._gotCopyOutResponse) {
+          this._gotCopyOutResponse = true
+        } else {
+          this.emit('error', new Error('Unexpected CopyOutResponse message (H)'))
+        }
+        break;
+
+      // meaningful row
+      case code.CopyData:
+        needPush = true;
+        break;
+
+      // standard interspersed messages. discard
+      case code.ParameterStatus:
+      case code.NoticeResponse:
+      case code.NotificationResponse:
+        break;
+  
+      case code.ErrorResponse:
+      case code.CopyDone:
+        this.pushBufferIfneeded();
+        this._detach()
+        this.push(null)
+        return cb();
+        break;
+      default:
+        this.emit('error', new Error('Unexpected PostgreSQL message ' + String.fromCharCode(messageCode)))
     }
-    //something bad happened
-    if(messageCode != code.d) {
-      return this.emit('error', new Error('expected "d" (copydata message)'))
-    }
-    var length = chunk.readUInt32BE(offset + 1) - 4 //subtract length of UInt32
-    //can we read the next row?
-    if(chunk.length > (offset + length + 5)) {
-      offset += 5
-      var slice = chunk.slice(offset, offset + length)
-      offset += length
-      this.push(slice)
-      this.rowCount++
+
+    length = chunk.readUInt32BE(offset+Byte1Len)
+    if(chunk.length >= (offset + Byte1Len + length)) {
+      offset += Byte1Len + Int32Len
+      if (needPush) {
+        var row = chunk.slice(offset, offset + length - Int32Len)
+        this.rowCount++
+        row.copy(buffer, buffer_offset);
+        buffer_offset += row.length;
+      }
+      offset += (length - Int32Len)
     } else {
+      // we need more chunks for a complete message
       break;
     }
   }
+
+  this.pushBufferIfneeded();
+
   if(chunk.length - offset) {
     var slice = chunk.slice(offset)
     this._remainder = slice

index.js

@@ -10,6 +10,7 @@ module.exports = {
 
 var Transform = require('stream').Transform
 var util = require('util')
+var code = require('./message-formats')
 
 var CopyStreamQuery = function(text, options) {
   Transform.call(this, options)
@@ -26,28 +27,23 @@ CopyStreamQuery.prototype.submit = function(connection) {
   connection.query(this.text)
 }
 
-var code = {
-  H: 72, //CopyOutResponse
-  d: 0x64, //CopyData
-  c: 0x63 //CopyDone
-}
 
-var copyDataBuffer = Buffer([code.d])
+var copyDataBuffer = Buffer([code.CopyData])
 CopyStreamQuery.prototype._transform = function(chunk, enc, cb) {
+  var Int32Len = 4;
   this.push(copyDataBuffer)
-  var lenBuffer = Buffer(4)
-  lenBuffer.writeUInt32BE(chunk.length + 4, 0)
+  var lenBuffer = Buffer(Int32Len)
+  lenBuffer.writeUInt32BE(chunk.length + Int32Len, 0)
   this.push(lenBuffer)
   this.push(chunk)
-  this.rowCount++
   cb()
 }
 
 CopyStreamQuery.prototype._flush = function(cb) {
-  var finBuffer = Buffer([code.c, 0, 0, 0, 4])
+  var Int32Len = 4;
+  var finBuffer = Buffer([code.CopyDone, 0, 0, 0, Int32Len])
   this.push(finBuffer)
-  //never call this callback, do not close underlying stream
-  //cb()
+  this.cb_flush = cb
 }
 
 CopyStreamQuery.prototype.handleError = function(e) {
@@ -55,12 +51,24 @@ CopyStreamQuery.prototype.handleError = function(e) {
 }
 
 CopyStreamQuery.prototype.handleCopyInResponse = function(connection) {
-  this.pipe(connection.stream)
+  this.pipe(connection.stream, { end: false })
 }
 
-CopyStreamQuery.prototype.handleCommandComplete = function() {
-  this.unpipe()
-  this.emit('end')
+CopyStreamQuery.prototype.handleCommandComplete = function(msg) {
+  // Parse affected row count as in
+  // https://github.com/brianc/node-postgres/blob/35e5567f86774f808c2a8518dd312b8aa3586693/lib/result.js#L37
+  var match = /COPY (\d+)/.exec((msg || {}).text)
+  if (match) {
+    this.rowCount = parseInt(match[1], 10)
+  }
+
+  // we delay the _flush cb so that the 'end' event is
+  // triggered after CommandComplete
+  this.cb_flush()
+
+  // unpipe from connection
+  this.unpipe(this.connection)
+  this.connection = null
 }
 
 CopyStreamQuery.prototype.handleReadyForQuery = function() {

message-formats.js

@@ -0,0 +1,25 @@
+/**
+ * The COPY feature uses the following protocol codes.
+ * The codes for the most recent protocol version are documented on
+ * https://www.postgresql.org/docs/current/static/protocol-message-formats.html
+ * 
+ * The protocol flow itself is described on
+ * https://www.postgresql.org/docs/current/static/protocol-flow.html
+ */
+module.exports = {
+  ErrorResponse:        0x45, // E
+  CopyInResponse:       0x47, // G
+  CopyOutResponse:      0x48, // H
+  CopyBothResponse:     0x57, // W
+  CopyDone:             0x63, // c
+  CopyData:             0x64, // d
+  CopyFail:             0x66, // f
+
+  // It is possible for NoticeResponse and ParameterStatus messages to be interspersed between CopyData messages;
+  // frontends must handle these cases, and should be prepared for other asynchronous message types as well
+  // (see Section 50.2.6).
+  // Otherwise, any message type other than CopyData or CopyDone may be treated as terminating copy-out mode.
+  NotificationResponse: 0x41, // A
+  NoticeResponse:       0x4E, // N
+  ParameterStatus:      0x53  // S
+} 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "pg-copy-streams",
-  "version": "1.0.0",
+  "version": "1.2.0",
   "description": "Low-Level COPY TO and COPY FROM streams for PostgreSQL in JavaScript using",
   "main": "index.js",
   "scripts": {

test/copy-from.js

@@ -30,10 +30,6 @@ var testRange = function(top) {
 
   var txt = 'COPY numbers FROM STDIN'
   var stream = fromClient.query(copy(txt))
-  var rowEmitCount = 0
-  stream.on('row', function() {
-    rowEmitCount++
-  })
   for(var i = 0; i < top; i++) {
     stream.write(Buffer('' + i + '\t' + i*10 + '\n'))
   }
@@ -43,6 +39,7 @@ var testRange = function(top) {
     fromClient.query('SELECT COUNT(*) FROM numbers', function(err, res) {
       assert.ifError(err)
       assert.equal(res.rows[0].count, top, 'expected ' + top + ' rows but got ' + res.rows[0].count)
+      assert.equal(stream.rowCount, top, 'expected ' + top + ' rows but db count is ' + stream.rowCount)
       //console.log('found ', res.rows.length, 'rows')
       countDone()
       var firstRowDone = gonna('have correct result')
@@ -58,3 +55,19 @@ var testRange = function(top) {
 }
 
 testRange(1000)
+
+var testSingleEnd = function() {
+  var fromClient = client()
+  fromClient.query('CREATE TEMP TABLE numbers(num int)')
+  var txt = 'COPY numbers FROM STDIN';
+  var stream = fromClient.query(copy(txt))
+  var count = 0;
+  stream.on('end', function() {
+    count++;
+    assert(count==1, '`end` Event was triggered ' + count + ' times');
+    if (count == 1) fromClient.end();
+  })
+  stream.end(Buffer('1\n'))
+    
+}
+testSingleEnd()

test/copy-to.js

@@ -7,6 +7,7 @@ var concat = require('concat-stream')
 var pg = require('pg')
 
 var copy = require('../').to
+var code = require('../message-formats')
 
 var client = function() {
   var client = new pg.Client()
@@ -22,6 +23,18 @@ var testConstruction = function() {
 
 testConstruction()
 
+var testComparators = function() {
+  var copy1 = copy();
+  copy1.pipe(concat(function(buf) {
+    assert(copy1._gotCopyOutResponse, 'should have received CopyOutResponse')
+    assert(!copy1._remainder, 'Message with no additional data (len=Int4Len+0) should not leave a remainder')
+  }))
+  copy1.end(new Buffer([code.CopyOutResponse, 0x00, 0x00, 0x00, 0x04])); 
+
+
+}
+testComparators();
+
 var testRange = function(top) {
   var fromClient = client()
   var txt = 'COPY (SELECT * from generate_series(0, ' + (top - 1) + ')) TO STDOUT'
@@ -73,5 +86,37 @@ var testInternalPostgresError = function() {
     queryClient.end()
   })
 }
-
 testInternalPostgresError()
+
+var testNoticeResponse = function() {
+  // we use a special trick to generate a warning
+  // on the copy stream.
+  var queryClient = client()
+  var set = '';
+  set += 'SET SESSION client_min_messages = WARNING;'
+  set += 'SET SESSION standard_conforming_strings = off;'
+  set += 'SET SESSION escape_string_warning = on;'
+  queryClient.query(set, function(err, res) {
+    assert.equal(err, null, 'testNoticeResponse - could not SET parameters')
+    var runStream = function(callback) {
+      var txt = "COPY (SELECT '\\\n') TO STDOUT"
+      var stream = queryClient.query(copy(txt))
+      stream.on('data', function(data) {
+      })
+      stream.on('error', callback)
+     
+      // make sure stream is pulled from 
+      stream.pipe(concat(callback.bind(null,null)))
+    }
+
+    runStream(function(err) {
+      assert.equal(err, null, err)
+      queryClient.end()
+    })
+
+  })
+}
+
+testNoticeResponse();
+
+