Handle parsing utf-8 bom encoded files (mholt#961)

Co-authored-by: peteruithoven <peter@metabolic.nl>
btakita · Nov 25, 2022 · aa00468 · aa00468
1 parent c1cbe16
commit aa00468
Show file tree

Hide file tree

Showing 3 changed files with 22 additions and 0 deletions.
diff --git a/papaparse.js b/papaparse.js
@@ -235,6 +235,7 @@ License: MIT
 		}
 		else if (typeof _input === 'string')
 		{
+			_input = stripBom(_input);
 			if (_config.download)
 				streamer = new NetworkStreamer(_config);
 			else
@@ -248,6 +249,14 @@ License: MIT
 			streamer = new FileStreamer(_config);
 
 		return streamer.stream(_input);
+
+		// Strip character from UTF-8 BOM encoded files that cause issue parsing the file
+		function stripBom(string) {
+			if (string.charCodeAt(0) === 0xfeff) {
+				return string.slice(1);
+			}
+			return string;
+		}
 	}
 
 

diff --git a/tests/node-tests.js b/tests/node-tests.js
@@ -5,6 +5,7 @@ var Papa = require("../papaparse.js");
 var fs = require('fs');
 var assert = require('assert');
 var longSampleRawCsv = fs.readFileSync(__dirname + '/long-sample.csv', 'utf8');
+var utf8BomSampleRawCsv = fs.readFileSync(__dirname + '/utf-8-bom-sample.csv', 'utf8');
 
 function assertLongSampleParsedCorrectly(parsedCsv) {
 	assert.equal(8, parsedCsv.data.length);
@@ -287,4 +288,14 @@ describe('PapaParse', function() {
 			}
 		});
 	});
+
+	it('handles utf-8 BOM encoded files', function(done) {
+		Papa.parse(utf8BomSampleRawCsv, {
+			header: true,
+			complete: function(parsedCsv) {
+				assert.deepEqual(parsedCsv.data[0], { A: 'X', B: 'Y', C: 'Z' });
+				done();
+			}
+		});
+	});
 });
diff --git a/tests/utf-8-bom-sample.csv b/tests/utf-8-bom-sample.csv
@@ -0,0 +1,2 @@
+A,B,C
+X,Y,Z