version bump 0.6.1: dist cleanup

- XLSX format strings properly handles literal UTF8 chars (test apachepoi_49273)
- codepage updated to 1.0.0
- jszip updated to 2.2.0 (node-only)
- dist now contains jszip and codepage dependencies
- updated test_files

Makefile

@@ -2,6 +2,8 @@ LIB=xlsx
 DEPS=$(wildcard bits/*.js)
 TARGET=$(LIB).js
 FMT=xlsx xlsm xlsb misc
+REQS=jszip.js
+ADDONS=dist/cpexcel.js
 
 $(TARGET): $(DEPS)
 	cat $^ > $@
@@ -51,7 +53,14 @@ coveralls-spin:
 	make coveralls & bash misc/spin.sh $$!
 
 .PHONY: dist
-dist: $(TARGET)
+dist: dist-deps $(TARGET)
 	cp $(TARGET) dist/
 	cp LICENSE dist/
 	uglifyjs $(TARGET) -o dist/$(LIB).min.js --source-map dist/$(LIB).min.map --preamble "$$(head -n 1 bits/00_header.js)"
+	uglifyjs $(REQS) $(TARGET) -o dist/$(LIB).core.min.js --source-map dist/$(LIB).core.min.map --preamble "$$(head -n 1 bits/00_header.js)"
+	uglifyjs $(REQS) $(ADDONS) $(TARGET) -o dist/$(LIB).full.min.js --source-map dist/$(LIB).full.min.map --preamble "$$(head -n 1 bits/00_header.js)"
+
+.PHONY: dist-deps
+dist-deps:
+	cp node_modules/codepage/dist/cpexcel.full.js dist/cpexcel.js
+	cp jszip.js dist/jszip.js

README.md

@@ -11,21 +11,45 @@ In node:
 
 In the browser:
 
+    <!-- This is the only file you need (includes xlsx.js and jszip) -->
+    <script lang="javascript" src="dist/xlsx.core.min.js"></script>
+
+In [bower](http://bower.io/):
+
+    bower install js-xlsx
+
+CDNjs automatically pulls the latest version and makes all versions available at
+<http://cdnjs.com/libraries/xlsx>
+
+Older versions of this README recommended a more explicit approach:
+
     <!-- JSZip must be included before xlsx.js -->
     <script lang="javascript" src="/path/to/jszip.js"></script>
     <script lang="javascript" src="/path/to/xlsx.js"></script>
 
+## Optional Modules
+
+The node version automatically requires modules for additional features.  Some of these modules are rather large in size and are only needed in special circumstances, so they do not ship with the core.  For browser use, they must be included directly:
+
+    <!-- international support from https://github.com/sheetjs/js-codepage -->
+    <script src="dist/cpexcel.js"></script>
+
+An appropriate version for each dependency is included in the dist/ directory.
+
+The complete single-file version is generated at `dist/xlsx.full.min.js`
+
 ## Usage
 
 Simple usage (walks through every cell of every sheet and dumps the values):
 
-    var XLSX = require('xlsx')
-    var xlsx = XLSX.readFile('test.xlsx');
+    var XLSX = require('xlsx');
+    var workbook = XLSX.readFile('test.xlsx');
     var sheet_name_list = xlsx.SheetNames;
-    xlsx.SheetNames.forEach(function(y) {
-      for (z in xlsx.Sheets[y]) {
+    sheet_name_list.forEach(function(y) {
+      var worksheet = workbook.Sheets[y];
+      for (z in worksheet) {
         if(z[0] === '!') continue;
-        console.log(y + "!" + z + "=" + JSON.stringify(xlsx.Sheets[y][z].v));
+        console.log(y + "!" + z + "=" + JSON.stringify(worksheet[z].v));
       }
     });
 

bits/01_version.js

@@ -1 +1 @@
-XLSX.version = '0.6.0';
+XLSX.version = '0.6.1';

bits/10_ssf.js

@@ -105,7 +105,7 @@ var general_fmt = function(v) {
 		}
 		else {
 			o = v.toFixed(11).replace(/(\.[0-9]*[1-9])0*$/,"$1");
-				if(o.length > 11 + (v<0?1:0)) o = v.toPrecision(6);
+			if(o.length > 11 + (v<0?1:0)) o = v.toPrecision(6);
 		}
 		o = o.replace(/(\.[0-9]*[1-9])0+e/,"$1e").replace(/\.0*e/,"e");
 		return o.replace("e","E").replace(/\.0*$/,"").replace(/\.([0-9]*[^0])0*$/,".$1").replace(/(E[+-])([0-9])$/,"$1"+"0"+"$2");
@@ -217,7 +217,7 @@ var write_num = function(type, fmt, val) {
 	if(fmt.indexOf("E") > -1) {
 		var idx = fmt.indexOf("E") - fmt.indexOf(".") - 1;
 		if(fmt.match(/^#+0.0E\+0$/)) {
-		var period = fmt.indexOf("."); if(period === -1) period=fmt.indexOf('E');
+			var period = fmt.indexOf("."); if(period === -1) period=fmt.indexOf('E');
 			var ee = (Number(val.toExponential(0).substr(2+(val<0))))%period;
 			if(ee < 0) ee += period;
 			o = (val/Math.pow(10,ee)).toPrecision(idx+1+(period+ee)%period);

bits/52_sstxml.js

@@ -1,9 +1,33 @@
+/* 18.4.1 charset to codepage mapping */
+var CS2CP = {
+	0:    1252, /* ANSI */
+	1:   65001, /* DEFAULT */
+	2:   65001, /* SYMBOL */
+	77:  10000, /* MAC */
+	128:   932, /* SHIFTJIS */
+	129:   949, /* HANGUL */
+	130:  1361, /* JOHAB */
+	134:   936, /* GB2312 */
+	136:   950, /* CHINESEBIG5 */
+	161:  1253, /* GREEK */
+	162:  1254, /* TURKISH */
+	163:  1258, /* VIETNAMESE */
+	177:  1255, /* HEBREW */
+	178:  1256, /* ARABIC */
+	186:  1257, /* BALTIC */
+	204:  1251, /* RUSSIAN */
+	222:   874, /* THAI */
+	238:  1250, /* EASTEUROPE */
+	255:  1252, /* OEM */
+    69:   6969  /* MISC */
+};
+
 /* Parse a list of <r> tags */
 var parse_rs = (function() {
 	var tregex = matchtag("t"), rpregex = matchtag("rPr");
 	/* 18.4.7 rPr CT_RPrElt */
 	var parse_rpr = function(rpr, intro, outro) {
-		var font = {};
+		var font = {}, cp = 65001;
 		(rpr.match(/<[^>]*>/g)||[]).forEach(function(x) {
 			var y = parsexmltag(x);
 			switch(y[0]) {
@@ -20,7 +44,10 @@ var parse_rs = (function() {
 				case '<shadow/>': break;
 
 				/* 18.4.1 charset CT_IntProperty TODO */
-				case '<charset': break;
+				case '<charset':
+					if(y.val == '1') break;
+					cp = CS2CP[parseInt(y.val, 10)];
+					break;
 
 				/* 18.4.2 outline CT_BooleanProperty TODO */
 				case '<outline':
@@ -85,18 +112,20 @@ var parse_rs = (function() {
 		if(font.i) style.push("font-style: italic;");
 		intro.push('<span style="' + style.join("") + '">');
 		outro.push("</span>");
+		return cp;
 	};
 
 	/* 18.4.4 r CT_RElt */
 	function parse_r(r) {
 		var terms = [[],"",[]];
 		/* 18.4.12 t ST_Xstring */
-		var t = r.match(tregex);
+		var t = r.match(tregex), cp = 65001;
 		if(!isval(t)) return "";
 		terms[1] = t[1];
 
 		var rpr = r.match(rpregex);
-		if(isval(rpr)) parse_rpr(rpr[1], terms[0], terms[2]);
+		if(isval(rpr)) cp = parse_rpr(rpr[1], terms[0], terms[2]);
+
 		return terms[0].join("") + terms[1].replace(/\r\n/g,'<br/>') + terms[2].join("");
 	}
 	return function(rs) {

bits/57_styxml.js

@@ -7,7 +7,7 @@ function parseNumFmts(t, opts) {
 		switch(y[0]) {
 			case '<numFmts': case '</numFmts>': case '<numFmts/>': break;
 			case '<numFmt': {
-				var f=unescapexml(y.formatCode), i=parseInt(y.numFmtId,10);
+				var f=utf8read(unescapexml(y.formatCode)), i=parseInt(y.numFmtId,10);
 				styles.NumberFmt[i] = f; if(i>0) SSF.load(f,i);
 			} break;
 			default: if(opts.WTF) throw 'unrecognized ' + y[0] + ' in numFmts';

dist/xlsx.js

@@ -3,7 +3,7 @@
 /*jshint eqnull:true */
 var XLSX = {};
 (function(XLSX){
-XLSX.version = '0.6.0';
+XLSX.version = '0.6.1';
 /* ssf.js (C) 2013-2014 SheetJS -- http://sheetjs.com */
 var SSF = {};
 var make_ssf = function(SSF){
@@ -111,7 +111,7 @@ var general_fmt = function(v) {
 		}
 		else {
 			o = v.toFixed(11).replace(/(\.[0-9]*[1-9])0*$/,"$1");
-				if(o.length > 11 + (v<0?1:0)) o = v.toPrecision(6);
+			if(o.length > 11 + (v<0?1:0)) o = v.toPrecision(6);
 		}
 		o = o.replace(/(\.[0-9]*[1-9])0+e/,"$1e").replace(/\.0*e/,"e");
 		return o.replace("e","E").replace(/\.0*$/,"").replace(/\.([0-9]*[^0])0*$/,".$1").replace(/(E[+-])([0-9])$/,"$1"+"0"+"$2");
@@ -223,7 +223,7 @@ var write_num = function(type, fmt, val) {
 	if(fmt.indexOf("E") > -1) {
 		var idx = fmt.indexOf("E") - fmt.indexOf(".") - 1;
 		if(fmt.match(/^#+0.0E\+0$/)) {
-		var period = fmt.indexOf("."); if(period === -1) period=fmt.indexOf('E');
+			var period = fmt.indexOf("."); if(period === -1) period=fmt.indexOf('E');
 			var ee = (Number(val.toExponential(0).substr(2+(val<0))))%period;
 			if(ee < 0) ee += period;
 			o = (val/Math.pow(10,ee)).toPrecision(idx+1+(period+ee)%period);
@@ -841,12 +841,36 @@ function parse_FontFlags(data, length) {
 	};
 	return out;
 }
+/* 18.4.1 charset to codepage mapping */
+var CS2CP = {
+	0:    1252, /* ANSI */
+	1:   65001, /* DEFAULT */
+	2:   65001, /* SYMBOL */
+	77:  10000, /* MAC */
+	128:   932, /* SHIFTJIS */
+	129:   949, /* HANGUL */
+	130:  1361, /* JOHAB */
+	134:   936, /* GB2312 */
+	136:   950, /* CHINESEBIG5 */
+	161:  1253, /* GREEK */
+	162:  1254, /* TURKISH */
+	163:  1258, /* VIETNAMESE */
+	177:  1255, /* HEBREW */
+	178:  1256, /* ARABIC */
+	186:  1257, /* BALTIC */
+	204:  1251, /* RUSSIAN */
+	222:   874, /* THAI */
+	238:  1250, /* EASTEUROPE */
+	255:  1252, /* OEM */
+    69:   6969  /* MISC */
+};
+
 /* Parse a list of <r> tags */
 var parse_rs = (function() {
 	var tregex = matchtag("t"), rpregex = matchtag("rPr");
 	/* 18.4.7 rPr CT_RPrElt */
 	var parse_rpr = function(rpr, intro, outro) {
-		var font = {};
+		var font = {}, cp = 65001;
 		(rpr.match(/<[^>]*>/g)||[]).forEach(function(x) {
 			var y = parsexmltag(x);
 			switch(y[0]) {
@@ -863,7 +887,10 @@ var parse_rs = (function() {
 				case '<shadow/>': break;
 
 				/* 18.4.1 charset CT_IntProperty TODO */
-				case '<charset': break;
+				case '<charset':
+					if(y.val == '1') break;
+					cp = CS2CP[parseInt(y.val, 10)];
+					break;
 
 				/* 18.4.2 outline CT_BooleanProperty TODO */
 				case '<outline':
@@ -928,18 +955,20 @@ var parse_rs = (function() {
 		if(font.i) style.push("font-style: italic;");
 		intro.push('<span style="' + style.join("") + '">');
 		outro.push("</span>");
+		return cp;
 	};
 
 	/* 18.4.4 r CT_RElt */
 	function parse_r(r) {
 		var terms = [[],"",[]];
 		/* 18.4.12 t ST_Xstring */
-		var t = r.match(tregex);
+		var t = r.match(tregex), cp = 65001;
 		if(!isval(t)) return "";
 		terms[1] = t[1];
 
 		var rpr = r.match(rpregex);
-		if(isval(rpr)) parse_rpr(rpr[1], terms[0], terms[2]);
+		if(isval(rpr)) cp = parse_rpr(rpr[1], terms[0], terms[2]);
+
 		return terms[0].join("") + terms[1].replace(/\r\n/g,'<br/>') + terms[2].join("");
 	}
 	return function(rs) {
@@ -1016,7 +1045,7 @@ function parseNumFmts(t, opts) {
 		switch(y[0]) {
 			case '<numFmts': case '</numFmts>': case '<numFmts/>': break;
 			case '<numFmt': {
-				var f=unescapexml(y.formatCode), i=parseInt(y.numFmtId,10);
+				var f=utf8read(unescapexml(y.formatCode)), i=parseInt(y.numFmtId,10);
 				styles.NumberFmt[i] = f; if(i>0) SSF.load(f,i);
 			} break;
 			default: if(opts.WTF) throw 'unrecognized ' + y[0] + ' in numFmts';

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "xlsx",
-	"version": "0.6.0",
+	"version": "0.6.1",
 	"author": "sheetjs",
 	"description": "XLSB / XLSX / XLSM (Excel 2007+ Spreadsheet) parser",
 	"keywords": [ "xlsx", "xlsb", "xlsm", "office", "excel", "spreadsheet" ],
@@ -10,9 +10,9 @@
 	"main": "./xlsx",
 	"dependencies": {
 		"ssf":"~0.6.4",
-		"codepage":"",
+		"codepage":"1.x",
 		"cfb":"",
-		"jszip":"~2.1.0",
+		"jszip":"~2.2.0",
 		"commander":""
 	},
 	"devDependencies": {
@@ -23,7 +23,7 @@
 	"repository": { "type":"git", "url":"git://github.com/SheetJS/js-xlsx.git" },
 	"scripts": {
 		"pretest": "git submodule init && git submodule update",
-		"test": "make mocha",
+		"test": "make test",
 		"test-jasmine": "jasmine-node --verbose tests/"
 	},
 	"config": {

test.js

@@ -298,7 +298,7 @@ describe('features', function() {
 		[wb1,wb2].map(function(wb) { return wb.Sheets[sheet]; }).forEach(function(ws, i) {
 			assert.equal(ws.B1.c.length, 1,"must have 1 comment");
 			assert.equal(ws.B1.c[0].a, "Yegor Kozlov","must have the same author");
-			assert.equal(ws.B1.c[0].t.replace(/\r\n/g,"\n"), "Yegor Kozlov:\nfirst cell", "must have the concatenated texts");
+			assert.equal(ws.B1.c[0].t.replace(/\r\n/g,"\n").replace(/\r/g,"\n"), "Yegor Kozlov:\nfirst cell", "must have the concatenated texts");
 			if(i > 0) return;
 			assert.equal(ws.B1.c[0].r, '<r><rPr><b/><sz val="8"/><color indexed="81"/><rFont val="Tahoma"/></rPr><t>Yegor Kozlov:</t></r><r><rPr><sz val="8"/><color indexed="81"/><rFont val="Tahoma"/></rPr><t xml:space="preserve">\r\nfirst cell</t></r>', "must have the rich text representation");
 			assert.equal(ws.B1.c[0].h, '<span style="font-weight: bold;">Yegor Kozlov:</span><span style=""><br/>first cell</span>', "must have the html representation");

tests.lst

@@ -103,6 +103,7 @@ apachepoi_56011.xlsx
 apachepoi_56017.xlsx
 apachepoi_56169.xlsx
 apachepoi_56278.xlsx
+apachepoi_56315.xlsx
 apachepoi_AverageTaxRates.xlsx
 apachepoi_Booleans.xlsx
 apachepoi_BrNotClosed.xlsx
@@ -187,6 +188,24 @@ jxls-examples_stress1.xlsx
 jxls-examples_stress2.xlsx
 jxls-reader_departmentData.xlsx
 large_strings.xlsx.pending
+libreoffice_calc_cjk-text_cell-justify-distributed-single.xlsx
+libreoffice_calc_conditional-formatting.xlsx
+libreoffice_calc_conditional-formatting_all_icon_sets.xlsx
+libreoffice_calc_drawing-object_shapes.xlsx
+libreoffice_calc_export-millon-rows.xlsx
+libreoffice_calc_external-ref_access-basic.xlsx
+libreoffice_calc_external-ref_extdata.xlsx
+libreoffice_calc_tab-color.xlsx
+libreoffice_calc_text-angled-with-border.xlsx
+libreoffice_calc_xlsx-export-single-cell-at-last-row.xlsx
+libreoffice_calc_xlsx-import_encryption_simple-encryption-2007.xlsx.pending
+libreoffice_calc_xlsx-import_encryption_simple-encryption-2010.xlsx.pending
+libreoffice_calc_xlsx-import_format-as-table.xlsx
+libreoffice_calc_xlsx-import_named-range.xlsx
+libreoffice_calc_xlsx-import_perf_300000_line_sample.xlsx.pending
+libreoffice_calc_xlsx-import_perf_8-by-300000-cells.xlsx.pending
+libreoffice_calc_xlsx-import_perf_pivot-table-with-large-unique-entries.xlsx
+libreoffice_calc_xlsx-import_shared-formula_1.xlsx
 merge_cells.xlsx
 mixed_sheets.xlsx
 named_ranges_2011.xlsx

tests/files

@@ -1 +1 @@
-Subproject commit b422ac319612c2b54c9d46eeed78acde901eda7c
+Subproject commit 42ff3701227761dc8e5dca11642a6e43dd846325

xlsx.js

@@ -3,7 +3,7 @@
 /*jshint eqnull:true */
 var XLSX = {};
 (function(XLSX){
-XLSX.version = '0.6.0';
+XLSX.version = '0.6.1';
 /* ssf.js (C) 2013-2014 SheetJS -- http://sheetjs.com */
 var SSF = {};
 var make_ssf = function(SSF){
@@ -111,7 +111,7 @@ var general_fmt = function(v) {
 		}
 		else {
 			o = v.toFixed(11).replace(/(\.[0-9]*[1-9])0*$/,"$1");
-				if(o.length > 11 + (v<0?1:0)) o = v.toPrecision(6);
+			if(o.length > 11 + (v<0?1:0)) o = v.toPrecision(6);
 		}
 		o = o.replace(/(\.[0-9]*[1-9])0+e/,"$1e").replace(/\.0*e/,"e");
 		return o.replace("e","E").replace(/\.0*$/,"").replace(/\.([0-9]*[^0])0*$/,".$1").replace(/(E[+-])([0-9])$/,"$1"+"0"+"$2");
@@ -223,7 +223,7 @@ var write_num = function(type, fmt, val) {
 	if(fmt.indexOf("E") > -1) {
 		var idx = fmt.indexOf("E") - fmt.indexOf(".") - 1;
 		if(fmt.match(/^#+0.0E\+0$/)) {
-		var period = fmt.indexOf("."); if(period === -1) period=fmt.indexOf('E');
+			var period = fmt.indexOf("."); if(period === -1) period=fmt.indexOf('E');
 			var ee = (Number(val.toExponential(0).substr(2+(val<0))))%period;
 			if(ee < 0) ee += period;
 			o = (val/Math.pow(10,ee)).toPrecision(idx+1+(period+ee)%period);
@@ -841,12 +841,36 @@ function parse_FontFlags(data, length) {
 	};
 	return out;
 }
+/* 18.4.1 charset to codepage mapping */
+var CS2CP = {
+	0:    1252, /* ANSI */
+	1:   65001, /* DEFAULT */
+	2:   65001, /* SYMBOL */
+	77:  10000, /* MAC */
+	128:   932, /* SHIFTJIS */
+	129:   949, /* HANGUL */
+	130:  1361, /* JOHAB */
+	134:   936, /* GB2312 */
+	136:   950, /* CHINESEBIG5 */
+	161:  1253, /* GREEK */
+	162:  1254, /* TURKISH */
+	163:  1258, /* VIETNAMESE */
+	177:  1255, /* HEBREW */
+	178:  1256, /* ARABIC */
+	186:  1257, /* BALTIC */
+	204:  1251, /* RUSSIAN */
+	222:   874, /* THAI */
+	238:  1250, /* EASTEUROPE */
+	255:  1252, /* OEM */
+    69:   6969  /* MISC */
+};
+
 /* Parse a list of <r> tags */
 var parse_rs = (function() {
 	var tregex = matchtag("t"), rpregex = matchtag("rPr");
 	/* 18.4.7 rPr CT_RPrElt */
 	var parse_rpr = function(rpr, intro, outro) {
-		var font = {};
+		var font = {}, cp = 65001;
 		(rpr.match(/<[^>]*>/g)||[]).forEach(function(x) {
 			var y = parsexmltag(x);
 			switch(y[0]) {
@@ -863,7 +887,10 @@ var parse_rs = (function() {
 				case '<shadow/>': break;
 
 				/* 18.4.1 charset CT_IntProperty TODO */
-				case '<charset': break;
+				case '<charset':
+					if(y.val == '1') break;
+					cp = CS2CP[parseInt(y.val, 10)];
+					break;
 
 				/* 18.4.2 outline CT_BooleanProperty TODO */
 				case '<outline':
@@ -928,18 +955,20 @@ var parse_rs = (function() {
 		if(font.i) style.push("font-style: italic;");
 		intro.push('<span style="' + style.join("") + '">');
 		outro.push("</span>");
+		return cp;
 	};
 
 	/* 18.4.4 r CT_RElt */
 	function parse_r(r) {
 		var terms = [[],"",[]];
 		/* 18.4.12 t ST_Xstring */
-		var t = r.match(tregex);
+		var t = r.match(tregex), cp = 65001;
 		if(!isval(t)) return "";
 		terms[1] = t[1];
 
 		var rpr = r.match(rpregex);
-		if(isval(rpr)) parse_rpr(rpr[1], terms[0], terms[2]);
+		if(isval(rpr)) cp = parse_rpr(rpr[1], terms[0], terms[2]);
+
 		return terms[0].join("") + terms[1].replace(/\r\n/g,'<br/>') + terms[2].join("");
 	}
 	return function(rs) {
@@ -1016,7 +1045,7 @@ function parseNumFmts(t, opts) {
 		switch(y[0]) {
 			case '<numFmts': case '</numFmts>': case '<numFmts/>': break;
 			case '<numFmt': {
-				var f=unescapexml(y.formatCode), i=parseInt(y.numFmtId,10);
+				var f=utf8read(unescapexml(y.formatCode)), i=parseInt(y.numFmtId,10);
 				styles.NumberFmt[i] = f; if(i>0) SSF.load(f,i);
 			} break;
 			default: if(opts.WTF) throw 'unrecognized ' + y[0] + ' in numFmts';