From 9dc602275b7e8424f16e0ac3a076b1ce2c69cde8 Mon Sep 17 00:00:00 2001
From: David Mesquita-Morris <mesmo@steelbreeze.net>
Date: Mon, 22 Nov 2021 06:32:58 +0000
Subject: [PATCH] Simplify the split on newline regex

---
 lib/node/index.js        |  2 +-
 lib/node/test/index.d.ts |  1 +
 lib/node/test/index.js   | 24 ++++++++++++++++++++++++
 package.json             |  2 +-
 src/index.ts             |  3 +--
 src/test/index.ts        |  5 +++++
 6 files changed, 33 insertions(+), 4 deletions(-)
 create mode 100644 lib/node/test/index.d.ts
 create mode 100644 lib/node/test/index.js
 create mode 100644 src/test/index.ts

diff --git a/lib/node/index.js b/lib/node/index.js
index d0c808f..1ce3ba7 100644
--- a/lib/node/index.js
+++ b/lib/node/index.js
@@ -9,7 +9,7 @@ exports.parse = void 0;
 function parse(text) {
     // convert the csv formatted test into a table of tokens
     const tokens = text.replace(/^\uFEFF|\r\n$|\n$|\r$/g, '') // trim byte order mark from beginning and trailing EOL if needed
-        .split(/\r\n(?=(?:(?:[^"]*"){2})*[^"]*$)|\n(?=(?:(?:[^"]*"){2})*[^"]*$)|\r(?=(?:(?:[^"]*"){2})*[^"]*$)/).map(row => // split text into rows at EOL
+        .split(/\r?\n(?=(?:(?:[^"]*"){2})*[^"]*$)|\r(?=(?:(?:[^"]*"){2})*[^"]*$)/).map(row => // split text into rows at EOL
      row.split(/,(?=(?:(?:[^"]*"){2})*[^"]*$)/) // split row into tokens based on comma delimiter (unless in quotes); see answer here: https://stackoverflow.com/questions/23582276/split-string-by-comma-but-ignore-commas-inside-quotes/23582323#23582323
         .map(token => token.replace(/(^"|"$)/g, '') // dequote tokens if needed 
         .replace(/\"\"/g, '"'))); // replace double double quotes with double quotes
diff --git a/lib/node/test/index.d.ts b/lib/node/test/index.d.ts
new file mode 100644
index 0000000..cb0ff5c
--- /dev/null
+++ b/lib/node/test/index.d.ts
@@ -0,0 +1 @@
+export {};
diff --git a/lib/node/test/index.js b/lib/node/test/index.js
new file mode 100644
index 0000000..8c44e6f
--- /dev/null
+++ b/lib/node/test/index.js
@@ -0,0 +1,24 @@
+"use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    Object.defineProperty(o, k2, { enumerable: true, get: function() { return m[k]; } });
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || function (mod) {
+    if (mod && mod.__esModule) return mod;
+    var result = {};
+    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
+    __setModuleDefault(result, mod);
+    return result;
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+const csv = __importStar(require(".."));
+const data = '\uFEFFa,b,c\r"1",2,3\n4,"5",6\r\n7,"The number eight: ""8""",9\r"a\r\na",b,"c, d"\n12';
+console.log(csv.parse(data));
diff --git a/package.json b/package.json
index a44d6ff..0f81d76 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@steelbreeze/csv",
-  "version": "1.0.0-alpha.1",
+  "version": "1.0.0-alpha.2",
   "description": "Tools for reading and writnig files formatted as CSV",
   "main": "lib/node/index.js",
   "module": "lib/node/index.js",
diff --git a/src/index.ts b/src/index.ts
index bf65478..07c60ab 100644
--- a/src/index.ts
+++ b/src/index.ts
@@ -1,4 +1,3 @@
-
 /**
  * Parses a string encoded as a comma seperated values
  * @param text The source csv text.
@@ -7,7 +6,7 @@
 export function parse(text: string): Array<any> {
 	// convert the csv formatted test into a table of tokens
 	const tokens = text.replace(/^\uFEFF|\r\n$|\n$|\r$/g, '')	// trim byte order mark from beginning and trailing EOL if needed
-		.split(/\r\n(?=(?:(?:[^"]*"){2})*[^"]*$)|\n(?=(?:(?:[^"]*"){2})*[^"]*$)|\r(?=(?:(?:[^"]*"){2})*[^"]*$)/).map(row =>							// split text into rows at EOL
+		.split(/\r?\n(?=(?:(?:[^"]*"){2})*[^"]*$)|\r(?=(?:(?:[^"]*"){2})*[^"]*$)/).map(row =>							// split text into rows at EOL
 			row.split(/,(?=(?:(?:[^"]*"){2})*[^"]*$)/)			// split row into tokens based on comma delimiter (unless in quotes); see answer here: https://stackoverflow.com/questions/23582276/split-string-by-comma-but-ignore-commas-inside-quotes/23582323#23582323
 				.map(token => token.replace(/(^"|"$)/g, '')		// dequote tokens if needed 
 					.replace(/\"\"/g, '"')));					// replace double double quotes with double quotes
diff --git a/src/test/index.ts b/src/test/index.ts
new file mode 100644
index 0000000..28c9e7c
--- /dev/null
+++ b/src/test/index.ts
@@ -0,0 +1,5 @@
+import * as csv from '..';
+
+const data = '\uFEFFa,b,c\r"1",2,3\n4,"5",6\r\n7,"The number eight: ""8""",9\r"a\r\na",b,"c, d"\n12';
+
+console.log(csv.parse(data));