Merge pull request #4 from bigman73/master

Added support for skipHeader option

Author: danielgindi

README.md

@@ -9,6 +9,7 @@ A CSV stream reader, with many many features, and ability to work with the large
 * Support for excel-style multiline cells wrapped in quotes
 * Choosing a different delimiter instead of the comma
 * Automatic skipping empty lines
+* Automatic skipping of the first header row
 * Automatic parsing of numbers and booleans
 * Automatic trimming
 * Being a stream transformer, you can `.pause()` if you need some time to process the row and `.resume()` when you are ready to receive and process more rows.
@@ -29,6 +30,7 @@ Name | Type | Default | Explanation
   `multiline` | `Boolean` | `true` | Allow multiline cells, when the cell is wrapped with quotes ("...\n...") 
   `allowQuotes` | `Boolean` | `true` | Should quotes be treated as a special character that wraps cells etc.
   `skipEmptyLines` | `Boolean` | `false` | Should empty lines be automatically skipped?
+  `skipHeader` | `Boolean` | `false` | Should the first header row be skipped?
   `parseNumbers` | `Boolean` | `false` | Should numbers be automatically parsed? This will parse any format supported by `parseFloat` including scientific notation, `Infinity` and `NaN`.
   `parseBooleans` | `Boolean` | `false` | Automatically parse booleans (strictly lowercase `true` and `false`)
   `ltrim` | `Boolean` | `false` | Automatically left-trims columns

index.js

@@ -20,6 +20,7 @@ var Transform = stream.Transform;
  * @param {Boolean=false} options.ltrim - Automatically left-trims columns
  * @param {Boolean=false} options.rtrim - Automatically right-trims columns
  * @param {Boolean=false} options.trim - If true, then both 'ltrim' and 'rtrim' are set to true
+ * @param {Boolean=false} options.skipheader - If true, then skip the first header row
  * @returns {CsvReadableStream}
  * @constructor
  */
@@ -42,6 +43,7 @@ var CsvReadableStream = function (options) {
         , lastLineEndCR = false
         , lookForBOM = true
         , isQuoted = false
+        , rowCount = 0
 
         , multiline = !!options.multiline || typeof options.multiline === 'undefined'
         , delimiter = options.delimiter != null ? options.delimiter.toString() || ',' : ','
@@ -52,6 +54,7 @@ var CsvReadableStream = function (options) {
         , ltrim = !!options.ltrim || !!options.trim
         , rtrim = !!options.rtrim || !!options.trim
         , trim = options.ltrim && options.rtrim
+        , skipHeader = options.skipHeader
 
         , postProcessingEnabled = parseNumbers || parseBooleans || ltrim || rtrim;
 
@@ -119,6 +122,7 @@ var CsvReadableStream = function (options) {
                     lastLineEndCR = c === '\r';
                     dataIndex++;
                     isFinishedLine = true;
+                    rowCount++;
 
                     if (!multiline) {
                         isQuoted = false;
@@ -172,7 +176,14 @@ var CsvReadableStream = function (options) {
             data = null;
         }
 
-        if (isFinishedLine || (data === null && this._isStreamDone)) {
+        if (isFinishedLine && skipHeader && rowCount === 1) {
+            column = '';
+            columns = [];
+             // Look to see if there are more rows in available data
+            this._processChunk();
+            return;
+        }
+        else if (isFinishedLine || (data === null && this._isStreamDone)) {
 
             if (columns.length || column || data || !this._isStreamDone) {
 

package.json

@@ -4,7 +4,7 @@
   "description": "A CSV stream reader, with many many features, and ability to work with the largest datasets",
   "main": "index.js",
   "scripts": {
-    "test": "echo \"Error: no test specified\" && exit 1"
+    "test": "node test/test.js"
   },
   "repository": {
     "type": "git",

test/test-header.csv

@@ -0,0 +1,3 @@
+NAME,AGE
+John Smith,50
+Jane Doe,25

test/test.js

@@ -0,0 +1,17 @@
+var fs = require('fs');
+var CsvReadableStream = require('../index.js');
+
+var inputStream = fs.createReadStream('test/test-header.csv', 'utf8');
+
+inputStream
+	.pipe(CsvReadableStream({ 
+        parseNumbers: true, 
+        parseBooleans: true, 
+        trim: true,
+        skipHeader: true }))
+	.on('data', function (row) {
+	    console.log('A row arrived: ', row);
+	})
+	.on('end', function (data) {
+	    console.log('No more rows!');
+	});