version bump 0.11.2: proper plaintext parsing

- dollar currencies and percentages properly detected as numbers
- parse potential CDATA segments in XLSX (fixes #775 h/t @awb99)
- IE8 issues with regex
- altjs demos

Issues:
- fixes #673 h/t @huhm
- fixes #748 h/t @sangpuion
- fixes #749 h/t @GreggOD
- fixes #772 h/t @sangpuion @jyyan

README.md

@@ -167,19 +167,25 @@ CDNjs automatically pulls the latest version and makes all versions available at
 
 The `demos` directory includes sample projects for:
 
+**Frameworks**
 - [`angular 1.x`](demos/angular/)
 - [`angular 2.x / 4.x`](demos/angular2/)
-- [`browserify`](demos/browserify/)
-- [`canvas-datagrid`](demos/datagrid/)
-- [`Adobe ExtendScript`](demos/extendscript/)
 - [`meteor`](demos/meteor/)
-- [`phantomjs`](demos/phantomjs/)
+- [`vue 2`](demos/vue/)
+
+**JS Bundlers and Tooling**
+- [`browserify`](demos/browserify/)
 - [`requirejs`](demos/requirejs/)
 - [`rollup`](demos/rollup/)
 - [`systemjs`](demos/systemjs/)
-- [`vue 2`](demos/vue/)
 - [`webpack`](demos/webpack/)
 
+**JS Platforms and Integrations**
+- [`Adobe ExtendScript`](demos/extendscript/)
+- [`phantomjs`](demos/phantomjs/)
+- [`canvas-datagrid`](demos/datagrid/)
+- [`Other JS engines`](demos/altjs/)
+
 ### Optional Modules
 
 <details>

bits/01_version.js

-XLSX.version = '0.11.1';
+XLSX.version = '0.11.2';

bits/20_jsutils.js

@@ -72,7 +72,7 @@ function parse_isodur(s) {
 var good_pd_date = new Date('2017-02-19T19:06:09.000Z');
 if(isNaN(good_pd_date.getFullYear())) good_pd_date = new Date('2/19/17');
 var good_pd = good_pd_date.getFullYear() == 2017;
-/* parses aa date as a local date */
+/* parses a date as a local date */
 function parseDate(str/*:string|Date*/, fixdate/*:?number*/)/*:Date*/ {
 	var d = new Date(str);
 	if(good_pd) {
@@ -88,7 +88,9 @@ function parseDate(str/*:string|Date*/, fixdate/*:?number*/)/*:Date*/ {
 		d.setFullYear(d.getFullYear() + 100); return d;
 	}
 	var n = str.match(/\d+/g)||["2017","2","19","0","0","0"];
-	return new Date(+n[0], +n[1] - 1, +n[2], (+n[3]||0), (+n[4]||0), (+n[5]||0));
+	var out = new Date(+n[0], +n[1] - 1, +n[2], (+n[3]||0), (+n[4]||0), (+n[5]||0));
+	if(str.indexOf("Z") > -1) out = new Date(out.getTime() - out.getTimezoneOffset() * 60 * 1000);
+	return out;
 }
 
 function cc2str(arr/*:Array<number>*/)/*:string*/ {
@@ -117,8 +119,11 @@ function fill(c/*:string*/,l/*:number*/)/*:string*/ { var o = ""; while(o.length
 function fuzzynum(s/*:string*/)/*:number*/ {
 	var v/*:number*/ = Number(s);
 	if(!isNaN(v)) return v;
-	var ss = s.replace(/([\d]),([\d])/g,"$1$2").replace(/[$]/g,"");
-	if(!isNaN(v = Number(ss))) return v;
+	var wt = 1;
+	var ss = s.replace(/([\d]),([\d])/g,"$1$2").replace(/[$]/g,"").replace(/[%]/g, function() { wt *= 100; return "";});
+	if(!isNaN(v = Number(ss))) return v / wt;
+	ss = ss.replace(/[(](.*)[)]/,function($$, $1) { wt = -wt; return $1;});
+	if(!isNaN(v = Number(ss))) return v / wt;
 	return v;
 }
 function fuzzydate(s/*:string*/)/*:Date*/ {
@@ -128,7 +133,14 @@ function fuzzydate(s/*:string*/)/*:Date*/ {
 	if(y < 0 || y > 8099) return n;
 	if((m > 0 || d > 1) && y != 101) return o;
 	if(s.toLowerCase().match(/jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec/)) return o;
-	if(!s.match(/[a-zA-Z]/)) return o;
+	if(s.match(/[^-0-9:,\/\\]/)) return o;
 	return n;
 }
 
+var safe_split_regex = "abacaba".split(/(:?b)/i).length == 5;
+function split_regex(str/*:string*/, re, def/*:string*/)/*:Array<string>*/ {
+	if(safe_split_regex || typeof re == "string") return str.split(re);
+	var p = str.split(re), o = [p[0]];
+	for(var i = 1; i < p.length; ++i) { o.push(def); o.push(p[i]); }
+	return o;
+}

bits/22_xmlutils.js

@@ -44,8 +44,10 @@ var unescapexml/*:StringConv*/ = (function() {
 	/* 22.4.2.4 bstr (Basic String) */
 	var encregex = /&(?:quot|apos|gt|lt|amp|#x?([\da-fA-F]+));/g, coderegex = /_x([\da-fA-F]{4})_/g;
 	return function unescapexml(text/*:string*/)/*:string*/ {
-		var s = text + '';
-		return s.replace(encregex, function($$, $1) { return encodings[$$]||String.fromCharCode(parseInt($1,$$.indexOf("x")>-1?16:10))||$$; }).replace(coderegex,function(m,c) {return String.fromCharCode(parseInt(c,16));});
+		var s = text + '', i = s.indexOf("<![CDATA[");
+		if(i == -1) return s.replace(encregex, function($$, $1) { return encodings[$$]||String.fromCharCode(parseInt($1,$$.indexOf("x")>-1?16:10))||$$; }).replace(coderegex,function(m,c) {return String.fromCharCode(parseInt(c,16));});
+		var j = s.indexOf("]]>");
+		return unescapexml(s.slice(0, i)) + s.slice(i+9,j) + unescapexml(s.slice(j+3));
 	};
 })();
 

bits/79_html.js

@@ -8,7 +8,7 @@ var HTML_ = (function() {
 		if(!mtch) throw new Error("Invalid HTML: could not find <table>");
 		var mtch2/*:any*/ = str.match(/<\/table/i);
 		var i/*:number*/ = mtch.index, j/*:number*/ = mtch2 && mtch2.index || str.length;
-		var rows = str.slice(i, j).split(/(:?<tr[^>]*>)/i);
+		var rows = split_regex(str.slice(i, j), /(:?<tr[^>]*>)/i, "<tr>");
 		var R = -1, C = 0, RS = 0, CS = 0;
 		var range = {s:{r:10000000, c:10000000},e:{r:0,c:0}};
 		var merges = [], midx = 0;

demos/altjs/.gitignore

+jvm-npm.js
+sheetjs.*

demos/altjs/Makefile

+.PHONY: all
+all: duktape nashorn
+
+.PHONY: base
+base:
+	if [ ! -e sheetjs.xlsx ]; then node ../../tests/write.js; fi
+
+.PHONY: duktape
+duktape: base ## duktape / skookum demo
+	sjs skookum.js
+
+.PHONY: nashorn
+nashorn: base ## nashorn demo
+	if [ ! -e jvm-npm.js ]; then curl -O https://rawgit.com/nodyn/jvm-npm/master/src/main/javascript/jvm-npm.js; fi
+	jjs nashorn.js

demos/altjs/README.md

+# Other JS Engines and Deployments
+
+There are many JS engines and deployments outside of web browsers. NodeJS is the
+most popular deployment, but there are many others for special use cases.  Some
+optimize for low overhead and others optimize for ease of embedding within other
+applications.  Since it was designed for ES3 engines, the library can be used in
+those settings!  This demo tries to demonstrate a few alternative deployments.
+
+
+## Nashorn
+
+Nashorn ships with Java 8.  It includes a command-line tool `jjs` for running JS
+scripts.  It is somewhat limited but does offer access to the full Java runtime.
+
+`jjs` does not provide a CommonJS `require` implementation.  This demo uses a
+[`shim`](https://rawgit.com/nodyn/jvm-npm/master/src/main/javascript/jvm-npm.js)
+and manually requires the library.
+
+The Java `nio` API provides the `Files.readAllBytes` method to read a file into
+a byte array.  To use in `XLSX.read`, the demo copies the bytes into a plain JS
+array and calls `XLSX.read` with type `"array"`.
+
+
+## duktape and skookum
+
+[Duktape](http://duktape.org/) is an embeddable JS engine written in C.  The
+amalgamation makes integration extremely simple!  Duktape understands the source
+code and can process binary strings out the box, but does not provide I/O or
+other standard library features.
+
+To demonstrate compatibility with duktape, this demo uses the JS runtime from
+[Skookum JS](https://github.com/saghul/sjs).  Built upon the duktape engine, it
+adds a simple I/O interface to enable reading from files.
+

demos/altjs/nashorn.js

+#!/usr/bin/env jjs
+/* read file */
+var path = java.nio.file.Paths.get('sheetjs.xlsx');
+var fileArray = java.nio.file.Files.readAllBytes(path);
+
+/* convert to plain JS array */
+function b2a(b) {
+	var out = new Array(b.length);
+	for(var i = 0; i < out.length; i++) out[i] = b[i];
+	return out;
+}
+var u8a = b2a(fileArray);
+
+/* load module */
+load('./jvm-npm.js');
+JSZip = require('../../jszip.js');
+cptable = require('../../dist/cpexcel.js');
+XLSX = require('../../xlsx.js');
+
+/* read file */
+var wb = XLSX.read(u8a, {type:"array"});
+
+/* get first worksheet */
+var ws = wb.Sheets[wb.SheetNames[0]];
+var js = XLSX.utils.sheet_to_json(ws, {header:1});
+
+/* print out every line */
+js.forEach(function(l) { java.lang.System.out.println(JSON.stringify(l)); });

demos/altjs/skookum.js

+#!/usr/bin/env sjs
+
+var XLSX = require('../../xlsx.js');
+
+var io = require('io');
+var file = io.open("sheetjs.xlsx", "rb");
+var strs = [], str = "";
+while((str = file.read()).length > 0) strs.push(str);
+var data = (Buffer.concat(strs.map(function(x) { return new Buffer(x); })));
+
+var wb = XLSX.read(data, {type:"buffer"});
+console.log(wb.Sheets[wb.SheetNames[0]]);

demos/datagrid/index.html

@@ -105,6 +105,8 @@ function process_wb(wb) {
 	var data = XLSX.utils.sheet_to_json(ws, {header:1});
 	if(!cDg) cDg = canvasDatagrid({ parentNode:document.getElementById('htmlout'), data:data });
 	else cDg.data = data;
+	var range = XLSX.utils.decode_range(ws['!ref']);
+	for(var i = range.s.c; i <= range.e.c; ++i) cDg.schema[i - range.s.c].title = XLSX.utils.encode_col(i);
 	document.getElementById('xport').disabled = false;
 	if(typeof console !== 'undefined') console.log("output", new Date());
 }

docbits/10_install.md

@@ -25,19 +25,25 @@ CDNjs automatically pulls the latest version and makes all versions available at
 
 The `demos` directory includes sample projects for:
 
+**Frameworks**
 - [`angular 1.x`](demos/angular/)
 - [`angular 2.x / 4.x`](demos/angular2/)
-- [`browserify`](demos/browserify/)
-- [`canvas-datagrid`](demos/datagrid/)
-- [`Adobe ExtendScript`](demos/extendscript/)
 - [`meteor`](demos/meteor/)
-- [`phantomjs`](demos/phantomjs/)
+- [`vue 2`](demos/vue/)
+
+**JS Bundlers and Tooling**
+- [`browserify`](demos/browserify/)
 - [`requirejs`](demos/requirejs/)
 - [`rollup`](demos/rollup/)
 - [`systemjs`](demos/systemjs/)
-- [`vue 2`](demos/vue/)
 - [`webpack`](demos/webpack/)
 
+**JS Platforms and Integrations**
+- [`Adobe ExtendScript`](demos/extendscript/)
+- [`phantomjs`](demos/phantomjs/)
+- [`canvas-datagrid`](demos/datagrid/)
+- [`Other JS engines`](demos/altjs/)
+
 ### Optional Modules
 
 <details>

misc/docs/README.md

@@ -161,19 +161,25 @@ CDNjs automatically pulls the latest version and makes all versions available at
 
 The `demos` directory includes sample projects for:
 
+**Frameworks**
 - [`angular 1.x`](demos/angular/)
 - [`angular 2.x / 4.x`](demos/angular2/)
-- [`browserify`](demos/browserify/)
-- [`canvas-datagrid`](demos/datagrid/)
-- [`Adobe ExtendScript`](demos/extendscript/)
 - [`meteor`](demos/meteor/)
-- [`phantomjs`](demos/phantomjs/)
+- [`vue 2`](demos/vue/)
+
+**JS Bundlers and Tooling**
+- [`browserify`](demos/browserify/)
 - [`requirejs`](demos/requirejs/)
 - [`rollup`](demos/rollup/)
 - [`systemjs`](demos/systemjs/)
-- [`vue 2`](demos/vue/)
 - [`webpack`](demos/webpack/)
 
+**JS Platforms and Integrations**
+- [`Adobe ExtendScript`](demos/extendscript/)
+- [`phantomjs`](demos/phantomjs/)
+- [`canvas-datagrid`](demos/datagrid/)
+- [`Other JS engines`](demos/altjs/)
+
 ### Optional Modules
 
 

package.json

 {
 	"name": "xlsx",
-	"version": "0.11.1",
+	"version": "0.11.2",
 	"author": "sheetjs",
 	"description": "Excel (XLSB/XLSX/XLS/XML) ODS and other spreadsheet format (CSV/DIF/DBF/SYLK) parser and writer",
 	"keywords": [ "excel", "xls", "xlsx", "xlsb", "xlsm", "ods", "csv", "dbf", "dif", "sylk", "office", "spreadsheet" ],

test.js

@@ -568,14 +568,14 @@ describe('input formats', function() {
 		X.read(fs.readFileSync(paths.cstxlsb, 'base64'), {type: 'base64'});
 	});
 	var k = browser ? 'array' : 'buffer';
-	(typeof UInt8Array !== 'undefined' ? it : it.skip)('should read ' + k + 's', function() {
-		X.read(fs.readFileSync(paths.cstxls, 'buffer'), {type: k});
-		X.read(fs.readFileSync(paths.cstxml, 'buffer'), {type: k});
-		X.read(fs.readFileSync(paths.cstods, 'buffer'), {type: k});
-		X.read(fs.readFileSync(paths.cstxlsx, 'buffer'), {type: k});
-		X.read(fs.readFileSync(paths.cstxlsb, 'buffer'), {type: k});
-	});
-	(typeof UInt8Array !== 'undefined' ? it : it.skip)('should read array', function() {
+	(typeof Uint8Array !== 'undefined' ? it : it.skip)('should read ' + k + 's', function() {
+		X.read(fs.readFileSync(paths.cstxls, browser ? 'buffer' : null), {type: k});
+		X.read(fs.readFileSync(paths.cstxml, browser ? 'buffer' : null), {type: k});
+		X.read(fs.readFileSync(paths.cstods, browser ? 'buffer' : null), {type: k});
+		X.read(fs.readFileSync(paths.cstxlsx, browser ? 'buffer' : null), {type: k});
+		X.read(fs.readFileSync(paths.cstxlsb, browser ? 'buffer' : null), {type: k});
+	});
+	(typeof Uint8Array !== 'undefined' ? it : it.skip)('should read array', function() {
 		X.read(fs.readFileSync(paths.cstxls, 'binary').split("").map(function(x) { return x.charCodeAt(0); }), {type:'array'});
 		X.read(fs.readFileSync(paths.cstxml, 'binary').split("").map(function(x) { return x.charCodeAt(0); }), {type:'array'});
 		X.read(fs.readFileSync(paths.cstxlsx, 'binary').split("").map(function(x) { return x.charCodeAt(0); }), {type:'array'});
@@ -1847,26 +1847,34 @@ describe('csv', function() {
 
 describe('HTML', function() {
 	describe('input', function(){
-		var b = "<table><tr><td>1</td><td>4,001</td></tr><tr><td>$41.08</td></tr></table>";
+		var b = "<table><tr><td>-0.08</td><td>4,001</td><td>\u00e3\u0081\u0082 1</td></tr><tr><td>$41.08</td><td>11%</td></tr></table>";
 		it('should generate numbers by default', function() {
-			var sheet = X.read(b, {type:"binary"}).Sheets.Sheet1
+			var sheet = X.read(b, {type:"binary"}).Sheets.Sheet1;
 			var cell = get_cell(sheet, "A1");
-			assert.equal(cell.v, 1);
+			assert.equal(cell.v, -0.08);
 			assert.equal(cell.t, 'n');
 			cell = get_cell(sheet, "B1");
 			assert.equal(cell.v, 4001);
+			cell = get_cell(sheet, "C1");
+			assert.equal(cell.v, "あ 1");
 			cell = get_cell(sheet, "A2");
 			assert.equal(cell.v, 41.08);
+			cell = get_cell(sheet, "B2");
+			assert.equal(cell.v, .11);
 		});
 		it('should generate strings if raw option is passed', function() {
-			var sheet = X.read(b, {type:"binary", raw:true}).Sheets.Sheet1
+			var sheet = X.read(b, {type:"binary", raw:true}).Sheets.Sheet1;
 			var cell = get_cell(sheet, "A1");
-			assert.equal(cell.v, "1");
+			assert.equal(cell.v, "-0.08");
 			assert.equal(cell.t, 's');
 			cell = get_cell(sheet, "B1");
 			assert.equal(cell.v, "4,001");
+			cell = get_cell(sheet, "C1");
+			assert.equal(cell.v, "あ 1");
 			cell = get_cell(sheet, "A2");
 			assert.equal(cell.v, "$41.08");
+			cell = get_cell(sheet, "B2");
+			assert.equal(cell.v, "11%");
 		});
 	});
 });

types/.npmignore

 Makefile
 *xlsx*.ts
+doc.ts
 write.ts
 tslint.json

xlsx.flow.js

@@ -6,7 +6,7 @@
 /*global global, exports, module, require:false, process:false, Buffer:false */
 var XLSX = {};
 (function make_xlsx(XLSX){
-XLSX.version = '0.11.1';
+XLSX.version = '0.11.2';
 var current_codepage = 1200;
 /*:: declare var cptable:any; */
 /*global cptable:true */
@@ -1539,7 +1539,7 @@ function parse_isodur(s) {
 var good_pd_date = new Date('2017-02-19T19:06:09.000Z');
 if(isNaN(good_pd_date.getFullYear())) good_pd_date = new Date('2/19/17');
 var good_pd = good_pd_date.getFullYear() == 2017;
-/* parses aa date as a local date */
+/* parses a date as a local date */
 function parseDate(str/*:string|Date*/, fixdate/*:?number*/)/*:Date*/ {
 	var d = new Date(str);
 	if(good_pd) {
@@ -1555,7 +1555,9 @@ function parseDate(str/*:string|Date*/, fixdate/*:?number*/)/*:Date*/ {
 		d.setFullYear(d.getFullYear() + 100); return d;
 	}
 	var n = str.match(/\d+/g)||["2017","2","19","0","0","0"];
-	return new Date(+n[0], +n[1] - 1, +n[2], (+n[3]||0), (+n[4]||0), (+n[5]||0));
+	var out = new Date(+n[0], +n[1] - 1, +n[2], (+n[3]||0), (+n[4]||0), (+n[5]||0));
+	if(str.indexOf("Z") > -1) out = new Date(out.getTime() - out.getTimezoneOffset() * 60 * 1000);
+	return out;
 }
 
 function cc2str(arr/*:Array<number>*/)/*:string*/ {
@@ -1584,8 +1586,11 @@ function fill(c/*:string*/,l/*:number*/)/*:string*/ { var o = ""; while(o.length
 function fuzzynum(s/*:string*/)/*:number*/ {
 	var v/*:number*/ = Number(s);
 	if(!isNaN(v)) return v;
-	var ss = s.replace(/([\d]),([\d])/g,"$1$2").replace(/[$]/g,"");
-	if(!isNaN(v = Number(ss))) return v;
+	var wt = 1;
+	var ss = s.replace(/([\d]),([\d])/g,"$1$2").replace(/[$]/g,"").replace(/[%]/g, function() { wt *= 100; return "";});
+	if(!isNaN(v = Number(ss))) return v / wt;
+	ss = ss.replace(/[(](.*)[)]/,function($$, $1) { wt = -wt; return $1;});
+	if(!isNaN(v = Number(ss))) return v / wt;
 	return v;
 }
 function fuzzydate(s/*:string*/)/*:Date*/ {
@@ -1595,10 +1600,17 @@ function fuzzydate(s/*:string*/)/*:Date*/ {
 	if(y < 0 || y > 8099) return n;
 	if((m > 0 || d > 1) && y != 101) return o;
 	if(s.toLowerCase().match(/jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec/)) return o;
-	if(!s.match(/[a-zA-Z]/)) return o;
+	if(s.match(/[^-0-9:,\/\\]/)) return o;
 	return n;
 }
 
+var safe_split_regex = "abacaba".split(/(:?b)/i).length == 5;
+function split_regex(str/*:string*/, re, def/*:string*/)/*:Array<string>*/ {
+	if(safe_split_regex || typeof re == "string") return str.split(re);
+	var p = str.split(re), o = [p[0]];
+	for(var i = 1; i < p.length; ++i) { o.push(def); o.push(p[i]); }
+	return o;
+}
 function getdatastr(data)/*:?string*/ {
 	if(!data) return null;
 	if(data.data) return debom(data.data);
@@ -1720,8 +1732,10 @@ var unescapexml/*:StringConv*/ = (function() {
 	/* 22.4.2.4 bstr (Basic String) */
 	var encregex = /&(?:quot|apos|gt|lt|amp|#x?([\da-fA-F]+));/g, coderegex = /_x([\da-fA-F]{4})_/g;
 	return function unescapexml(text/*:string*/)/*:string*/ {
-		var s = text + '';
-		return s.replace(encregex, function($$, $1) { return encodings[$$]||String.fromCharCode(parseInt($1,$$.indexOf("x")>-1?16:10))||$$; }).replace(coderegex,function(m,c) {return String.fromCharCode(parseInt(c,16));});
+		var s = text + '', i = s.indexOf("<![CDATA[");
+		if(i == -1) return s.replace(encregex, function($$, $1) { return encodings[$$]||String.fromCharCode(parseInt($1,$$.indexOf("x")>-1?16:10))||$$; }).replace(coderegex,function(m,c) {return String.fromCharCode(parseInt(c,16));});
+		var j = s.indexOf("]]>");
+		return unescapexml(s.slice(0, i)) + s.slice(i+9,j) + unescapexml(s.slice(j+3));
 	};
 })();
 
@@ -16369,7 +16383,7 @@ var HTML_ = (function() {
 		if(!mtch) throw new Error("Invalid HTML: could not find <table>");
 		var mtch2/*:any*/ = str.match(/<\/table/i);
 		var i/*:number*/ = mtch.index, j/*:number*/ = mtch2 && mtch2.index || str.length;
-		var rows = str.slice(i, j).split(/(:?<tr[^>]*>)/i);
+		var rows = split_regex(str.slice(i, j), /(:?<tr[^>]*>)/i, "<tr>");
 		var R = -1, C = 0, RS = 0, CS = 0;
 		var range = {s:{r:10000000, c:10000000},e:{r:0,c:0}};
 		var merges = [], midx = 0;