version bump 0.10.6: encoding tweaks

- updated codepage to 1.9.0
- replaced \u2603 with \s\S (fixes #687 h/t @clgnik)

README.md

@@ -1165,6 +1165,11 @@ Max Digit Width is the width of the largest digit when rendered (generally the
 "0" character is the widest).  The internal width must be an integer multiple of
 the the width divided by 256.  ECMA-376 describes a formula for converting
 between pixels and the internal width.  This represents a hybrid approach.
+
+Read functions attempt to populate all three properties.  Write functions will
+try to cycle specified values to the desired type.  In order to avoid potential
+conflicts, manipulation should delete the other properties first.  For example,
+when changing the pixel width, delete the `wch` and `width` properties.
 </details>
 
 <details>
@@ -1403,8 +1408,6 @@ The exported `read` and `readFile` functions accept an options argument:
   errors on single worksheets, allowing you to read from the worksheets that do
   parse properly. Setting `WTF:1` forces those errors to be thrown.
 
-The defaults are enumerated in bits/84\_defaults.js
-
 ### Input Type
 
 Strings can be interpreted in multiple ways.  The `type` parameter for `read`

bits/01_version.js

-XLSX.version = '0.10.5';
+XLSX.version = '0.10.6';

bits/02_codepage.js

@@ -8,10 +8,22 @@ function reset_cp() { set_cp(1200); }
 var set_cp = function(cp) { current_codepage = cp; };
 
 function char_codes(data) { var o = []; for(var i = 0, len = data.length; i < len; ++i) o[i] = data.charCodeAt(i); return o; }
+
+function utf16leread(data/*:string*/)/*:string*/ {
+	var o = [];
+	for(var i = 0; i < (data.length>>1); ++i) o[i] = String.fromCharCode(data.charCodeAt(2*i) + (data.charCodeAt(2*i+1)<<8));
+	return o.join("");
+}
+function utf16beread(data/*:string*/)/*:string*/ {
+	var o = [];
+	for(var i = 0; i < (data.length>>1); ++i) o[i] = String.fromCharCode(data.charCodeAt(2*i+1) + (data.charCodeAt(2*i)<<8));
+	return o.join("");
+}
+
 var debom = function(data/*:string*/)/*:string*/ {
 	var c1 = data.charCodeAt(0), c2 = data.charCodeAt(1);
-	if(c1 == 0xFF && c2 == 0xFE) return data.substr(2);
-	if(c1 == 0xFE && c2 == 0xFF) return data.substr(2);
+	if(c1 == 0xFF && c2 == 0xFE) return utf16leread(data.substr(2));
+	if(c1 == 0xFE && c2 == 0xFF) return utf16beread(data.substr(2));
 	if(c1 == 0xFEFF) return data.substr(1);
 	return data;
 };

bits/22_xmlutils.js

@@ -128,7 +128,7 @@ var matchtag = (function() {
 	return function matchtag(f,g/*:?string*/)/*:RegExp*/ {
 		var t = f+"|"+(g||"");
 		if(mtcache[t]) return mtcache[t];
-		return (mtcache[t] = new RegExp('<(?:\\w+:)?'+f+'(?: xml:space="preserve")?(?:[^>]*)>([^\u2603]*)</(?:\\w+:)?'+f+'>',((g||"")/*:any*/)));
+		return (mtcache[t] = new RegExp('<(?:\\w+:)?'+f+'(?: xml:space="preserve")?(?:[^>]*)>([\\s\\S]*?)</(?:\\w+:)?'+f+'>',((g||"")/*:any*/)));
 	};
 })();
 

bits/49_theme.js

@@ -61,9 +61,9 @@ function parse_fontScheme(t, themes, opts) { }
 /* 20.1.4.1.15 fmtScheme CT_StyleMatrix */
 function parse_fmtScheme(t, themes, opts) { }
 
-var clrsregex = /<a:clrScheme([^>]*)>[^\u2603]*<\/a:clrScheme>/;
-var fntsregex = /<a:fontScheme([^>]*)>[^\u2603]*<\/a:fontScheme>/;
-var fmtsregex = /<a:fmtScheme([^>]*)>[^\u2603]*<\/a:fmtScheme>/;
+var clrsregex = /<a:clrScheme([^>]*)>[\s\S]*<\/a:clrScheme>/;
+var fntsregex = /<a:fontScheme([^>]*)>[\s\S]*<\/a:fontScheme>/;
+var fmtsregex = /<a:fmtScheme([^>]*)>[\s\S]*<\/a:fmtScheme>/;
 
 /* 20.1.6.10 themeElements CT_BaseStyles */
 function parse_themeElements(data, themes, opts) {
@@ -84,7 +84,7 @@ function parse_themeElements(data, themes, opts) {
 	});
 }
 
-var themeltregex = /<a:themeElements([^>]*)>[^\u2603]*<\/a:themeElements>/;
+var themeltregex = /<a:themeElements([^>]*)>[\s\S]*<\/a:themeElements>/;
 
 /* 14.2.7 Theme Part */
 function parse_theme_xml(data/*:string*/, opts) {

bits/57_cmntxml.js

@@ -4,13 +4,13 @@ function parse_comments_xml(data/*:string*/, opts)/*:Array<Comment>*/ {
 	if(data.match(/<(?:\w+:)?comments *\/>/)) return [];
 	var authors = [];
 	var commentList = [];
-	var authtag = data.match(/<(?:\w+:)?authors>([^\u2603]*)<\/(?:\w+:)?authors>/);
+	var authtag = data.match(/<(?:\w+:)?authors>([\s\S]*)<\/(?:\w+:)?authors>/);
 	if(authtag && authtag[1]) authtag[1].split(/<\/\w*:?author>/).forEach(function(x) {
 		if(x === "" || x.trim() === "") return;
 		var a = x.match(/<(?:\w+:)?author[^>]*>(.*)/);
 		if(a) authors.push(a[1]);
 	});
-	var cmnttag = data.match(/<(?:\w+:)?commentList>([^\u2603]*)<\/(?:\w+:)?commentList>/);
+	var cmnttag = data.match(/<(?:\w+:)?commentList>([\s\S]*)<\/(?:\w+:)?commentList>/);
 	if(cmnttag && cmnttag[1]) cmnttag[1].split(/<\/\w*:?comment>/).forEach(function(x, index) {
 		if(x === "" || x.trim() === "") return;
 		var cm = x.match(/<(?:\w+:)?comment[^>]*>/);
@@ -19,7 +19,7 @@ function parse_comments_xml(data/*:string*/, opts)/*:Array<Comment>*/ {
 		var comment/*:Comment*/ = ({ author: y.authorId && authors[y.authorId] ? authors[y.authorId] : "sheetjsghost", ref: y.ref, guid: y.guid }/*:any*/);
 		var cell = decode_cell(y.ref);
 		if(opts.sheetRows && opts.sheetRows <= cell.r) return;
-		var textMatch = x.match(/<(?:\w+:)?text>([^\u2603]*)<\/(?:\w+:)?text>/);
+		var textMatch = x.match(/<(?:\w+:)?text>([\s\S]*)<\/(?:\w+:)?text>/);
 		var rt = !!textMatch && !!textMatch[1] && parse_si(textMatch[1]) || {r:"",t:"",h:""};
 		comment.r = rt.r;
 		if(rt.r == "<t></t>") rt.t = rt.h = "";

bits/67_wsxml.js

@@ -3,11 +3,11 @@ function parse_ws_xml_dim(ws, s) {
 	if(d.s.r<=d.e.r && d.s.c<=d.e.c && d.s.r>=0 && d.s.c>=0) ws["!ref"] = encode_range(d);
 }
 var mergecregex = /<(?:\w:)?mergeCell ref="[A-Z0-9:]+"\s*[\/]?>/g;
-var sheetdataregex = /<(?:\w+:)?sheetData>([^\u2603]*)<\/(?:\w+:)?sheetData>/;
+var sheetdataregex = /<(?:\w+:)?sheetData>([\s\S]*)<\/(?:\w+:)?sheetData>/;
 var hlinkregex = /<(?:\w:)?hyperlink [^>]*>/mg;
 var dimregex = /"(\w*:\w*)"/;
 var colregex = /<(?:\w:)?col[^>]*[\/]?>/g;
-var afregex = /<(?:\w:)?autoFilter[^>]*([\/]|>([^\u2603]*)<\/(?:\w:)?autoFilter)>/g;
+var afregex = /<(?:\w:)?autoFilter[^>]*([\/]|>([\s\S]*)<\/(?:\w:)?autoFilter)>/g;
 var marginregex= /<(?:\w:)?pageMargins[^>]*\/>/g;
 /* 18.3 Worksheets */
 function parse_ws_xml(data/*:?string*/, opts, rels, wb, themes, styles)/*:Worksheet*/ {

bits/75_xlml.js

@@ -170,7 +170,8 @@ function xlml_normalize(d)/*:string*/ {
 /* UOS uses CJK in tags */
 var xlmlregex = /<(\/?)([^\s?>!\/:]*:|)([^\s?>]*[^\s?>\/])[^>]*>/mg;
 //var xlmlregex = /<(\/?)([a-z0-9]*:|)(\w+)[^>]*>/mg;
-function parse_xlml_xml(d, opts)/*:Workbook*/ {
+function parse_xlml_xml(d, _opts)/*:Workbook*/ {
+	var opts = _opts || {};
 	make_ssf(SSF);
 	var str = debom(xlml_normalize(d));
 	if(opts && opts.type == 'binary' && typeof cptable !== 'undefined') str = cptable.utils.decode(65001, char_codes(str));
@@ -193,7 +194,7 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ {
 	var rowinfo = [], rowobj = {};
 	var Workbook/*:WBWBProps*/ = ({ Sheets:[], WBProps:{date1904:false} }/*:any*/), wsprops = {};
 	xlmlregex.lastIndex = 0;
-	str = str.replace(/<!--([^\u2603]*?)-->/mg,"");
+	str = str.replace(/<!--([\s\S]*?)-->/mg,"");
 	while((Rn = xlmlregex.exec(str))) switch(Rn[3]) {
 		case 'Data':
 			if(state[state.length-1][1]) break;

bits/80_parseods.js

@@ -40,7 +40,7 @@ var parse_content_xml = (function() {
 		var rept = 1, isstub = false;
 		var i = 0;
 		xlmlregex.lastIndex = 0;
-		str = str.replace(/<!--([^\u2603]*?)-->/mg,"").replace(/<!DOCTYPE[^\[]*\[[^\]]*\]>/gm,"");
+		str = str.replace(/<!--([\s\S]*?)-->/mg,"").replace(/<!DOCTYPE[^\[]*\[[^\]]*\]>/gm,"");
 		while((Rn = xlmlregex.exec(str))) switch((Rn[3]=Rn[3].replace(/_.*$/,""))) {
 
 			case 'table': case '工作表': // 9.1.2 <table:table>

docbits/10_install.md

@@ -25,7 +25,8 @@ CDNjs automatically pulls the latest version and makes all versions available at
 
 The `demos` directory includes sample projects for:
 
-- [`angular`](demos/angular/)
+- [`angular 1.x`](demos/angular/)
+- [`angular 2.x / 4.x`](demos/angular2/)
 - [`browserify`](demos/browserify/)
 - [`Adobe ExtendScript`](demos/extendscript/)
 - [`meteor`](demos/meteor/)

docbits/62_colrow.md

@@ -38,6 +38,11 @@ Max Digit Width is the width of the largest digit when rendered (generally the
 "0" character is the widest).  The internal width must be an integer multiple of
 the the width divided by 256.  ECMA-376 describes a formula for converting
 between pixels and the internal width.  This represents a hybrid approach.
+
+Read functions attempt to populate all three properties.  Write functions will
+try to cycle specified values to the desired type.  In order to avoid potential
+conflicts, manipulation should delete the other properties first.  For example,
+when changing the pixel width, delete the `wch` and `width` properties.
 </details>
 
 <details>

docbits/80_parseopts.md

@@ -39,8 +39,6 @@ The exported `read` and `readFile` functions accept an options argument:
   errors on single worksheets, allowing you to read from the worksheets that do
   parse properly. Setting `WTF:1` forces those errors to be thrown.
 
-The defaults are enumerated in bits/84\_defaults.js
-
 ### Input Type
 
 Strings can be interpreted in multiple ways.  The `type` parameter for `read`

package.json

 {
 	"name": "xlsx",
-	"version": "0.10.5",
+	"version": "0.10.6",
 	"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" ],
@@ -19,7 +19,7 @@
 	"dependencies": {
 		"exit-on-epipe":"~1.0.0",
 		"ssf":"~0.9.4",
-		"codepage":"~1.8.0",
+		"codepage":"~1.9.0",
 		"cfb":"~0.11.1",
 		"crc-32":"~1.0.2",
 		"adler-32":"~1.0.0",

types/tslint.json

@@ -5,6 +5,7 @@
 		"no-sparse-arrays": false,
 		"only-arrow-functions": false,
 		"no-consecutive-blank-lines": false,
+		"prefer-conditional-expression": false,
 		"one-variable-per-declaration": false
 	}
 }

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 = '0.10.5';
+XLSX.version = '0.10.6';
 var current_codepage = 1200;
 /*:: declare var cptable:any; */
 /*global cptable:true */
@@ -17,10 +17,22 @@ function reset_cp() { set_cp(1200); }
 var set_cp = function(cp) { current_codepage = cp; };
 
 function char_codes(data) { var o = []; for(var i = 0, len = data.length; i < len; ++i) o[i] = data.charCodeAt(i); return o; }
+
+function utf16leread(data/*:string*/)/*:string*/ {
+	var o = [];
+	for(var i = 0; i < (data.length>>1); ++i) o[i] = String.fromCharCode(data.charCodeAt(2*i) + (data.charCodeAt(2*i+1)<<8));
+	return o.join("");
+}
+function utf16beread(data/*:string*/)/*:string*/ {
+	var o = [];
+	for(var i = 0; i < (data.length>>1); ++i) o[i] = String.fromCharCode(data.charCodeAt(2*i+1) + (data.charCodeAt(2*i)<<8));
+	return o.join("");
+}
+
 var debom = function(data/*:string*/)/*:string*/ {
 	var c1 = data.charCodeAt(0), c2 = data.charCodeAt(1);
-	if(c1 == 0xFF && c2 == 0xFE) return data.substr(2);
-	if(c1 == 0xFE && c2 == 0xFF) return data.substr(2);
+	if(c1 == 0xFF && c2 == 0xFE) return utf16leread(data.substr(2));
+	if(c1 == 0xFE && c2 == 0xFF) return utf16beread(data.substr(2));
 	if(c1 == 0xFEFF) return data.substr(1);
 	return data;
 };
@@ -1763,7 +1775,7 @@ var matchtag = (function() {
 	return function matchtag(f,g/*:?string*/)/*:RegExp*/ {
 		var t = f+"|"+(g||"");
 		if(mtcache[t]) return mtcache[t];
-		return (mtcache[t] = new RegExp('<(?:\\w+:)?'+f+'(?: xml:space="preserve")?(?:[^>]*)>([^\u2603]*)</(?:\\w+:)?'+f+'>',((g||"")/*:any*/)));
+		return (mtcache[t] = new RegExp('<(?:\\w+:)?'+f+'(?: xml:space="preserve")?(?:[^>]*)>([\\s\\S]*?)</(?:\\w+:)?'+f+'>',((g||"")/*:any*/)));
 	};
 })();
 
@@ -7669,9 +7681,9 @@ function parse_fontScheme(t, themes, opts) { }
 /* 20.1.4.1.15 fmtScheme CT_StyleMatrix */
 function parse_fmtScheme(t, themes, opts) { }
 
-var clrsregex = /<a:clrScheme([^>]*)>[^\u2603]*<\/a:clrScheme>/;
-var fntsregex = /<a:fontScheme([^>]*)>[^\u2603]*<\/a:fontScheme>/;
-var fmtsregex = /<a:fmtScheme([^>]*)>[^\u2603]*<\/a:fmtScheme>/;
+var clrsregex = /<a:clrScheme([^>]*)>[\s\S]*<\/a:clrScheme>/;
+var fntsregex = /<a:fontScheme([^>]*)>[\s\S]*<\/a:fontScheme>/;
+var fmtsregex = /<a:fmtScheme([^>]*)>[\s\S]*<\/a:fmtScheme>/;
 
 /* 20.1.6.10 themeElements CT_BaseStyles */
 function parse_themeElements(data, themes, opts) {
@@ -7692,7 +7704,7 @@ function parse_themeElements(data, themes, opts) {
 	});
 }
 
-var themeltregex = /<a:themeElements([^>]*)>[^\u2603]*<\/a:themeElements>/;
+var themeltregex = /<a:themeElements([^>]*)>[\s\S]*<\/a:themeElements>/;
 
 /* 14.2.7 Theme Part */
 function parse_theme_xml(data/*:string*/, opts) {
@@ -8135,13 +8147,13 @@ function parse_comments_xml(data/*:string*/, opts)/*:Array<Comment>*/ {
 	if(data.match(/<(?:\w+:)?comments *\/>/)) return [];
 	var authors = [];
 	var commentList = [];
-	var authtag = data.match(/<(?:\w+:)?authors>([^\u2603]*)<\/(?:\w+:)?authors>/);
+	var authtag = data.match(/<(?:\w+:)?authors>([\s\S]*)<\/(?:\w+:)?authors>/);
 	if(authtag && authtag[1]) authtag[1].split(/<\/\w*:?author>/).forEach(function(x) {
 		if(x === "" || x.trim() === "") return;
 		var a = x.match(/<(?:\w+:)?author[^>]*>(.*)/);
 		if(a) authors.push(a[1]);
 	});
-	var cmnttag = data.match(/<(?:\w+:)?commentList>([^\u2603]*)<\/(?:\w+:)?commentList>/);
+	var cmnttag = data.match(/<(?:\w+:)?commentList>([\s\S]*)<\/(?:\w+:)?commentList>/);
 	if(cmnttag && cmnttag[1]) cmnttag[1].split(/<\/\w*:?comment>/).forEach(function(x, index) {
 		if(x === "" || x.trim() === "") return;
 		var cm = x.match(/<(?:\w+:)?comment[^>]*>/);
@@ -8150,7 +8162,7 @@ function parse_comments_xml(data/*:string*/, opts)/*:Array<Comment>*/ {
 		var comment/*:Comment*/ = ({ author: y.authorId && authors[y.authorId] ? authors[y.authorId] : "sheetjsghost", ref: y.ref, guid: y.guid }/*:any*/);
 		var cell = decode_cell(y.ref);
 		if(opts.sheetRows && opts.sheetRows <= cell.r) return;
-		var textMatch = x.match(/<(?:\w+:)?text>([^\u2603]*)<\/(?:\w+:)?text>/);
+		var textMatch = x.match(/<(?:\w+:)?text>([\s\S]*)<\/(?:\w+:)?text>/);
 		var rt = !!textMatch && !!textMatch[1] && parse_si(textMatch[1]) || {r:"",t:"",h:""};
 		comment.r = rt.r;
 		if(rt.r == "<t></t>") rt.t = rt.h = "";
@@ -10711,11 +10723,11 @@ function parse_ws_xml_dim(ws, s) {
 	if(d.s.r<=d.e.r && d.s.c<=d.e.c && d.s.r>=0 && d.s.c>=0) ws["!ref"] = encode_range(d);
 }
 var mergecregex = /<(?:\w:)?mergeCell ref="[A-Z0-9:]+"\s*[\/]?>/g;
-var sheetdataregex = /<(?:\w+:)?sheetData>([^\u2603]*)<\/(?:\w+:)?sheetData>/;
+var sheetdataregex = /<(?:\w+:)?sheetData>([\s\S]*)<\/(?:\w+:)?sheetData>/;
 var hlinkregex = /<(?:\w:)?hyperlink [^>]*>/mg;
 var dimregex = /"(\w*:\w*)"/;
 var colregex = /<(?:\w:)?col[^>]*[\/]?>/g;
-var afregex = /<(?:\w:)?autoFilter[^>]*([\/]|>([^\u2603]*)<\/(?:\w:)?autoFilter)>/g;
+var afregex = /<(?:\w:)?autoFilter[^>]*([\/]|>([\s\S]*)<\/(?:\w:)?autoFilter)>/g;
 var marginregex= /<(?:\w:)?pageMargins[^>]*\/>/g;
 /* 18.3 Worksheets */
 function parse_ws_xml(data/*:?string*/, opts, rels, wb, themes, styles)/*:Worksheet*/ {
@@ -10816,7 +10828,7 @@ function write_ws_xml_protection(sp)/*:string*/ {
 function parse_ws_xml_hlinks(s, data/*:Array<string>*/, rels) {
 	var dense = Array.isArray(s);
 	for(var i = 0; i != data.length; ++i) {
-		var val = parsexmltag(data[i], true);
+		var val = parsexmltag(utf8read(data[i]), true);
 		if(!val.ref) return;
 		var rel = rels ? rels['!id'][val.id] : null;
 		if(rel) {
@@ -13058,7 +13070,8 @@ function xlml_normalize(d)/*:string*/ {
 /* UOS uses CJK in tags */
 var xlmlregex = /<(\/?)([^\s?>!\/:]*:|)([^\s?>]*[^\s?>\/])[^>]*>/mg;
 //var xlmlregex = /<(\/?)([a-z0-9]*:|)(\w+)[^>]*>/mg;
-function parse_xlml_xml(d, opts)/*:Workbook*/ {
+function parse_xlml_xml(d, _opts)/*:Workbook*/ {
+	var opts = _opts || {};
 	make_ssf(SSF);
 	var str = debom(xlml_normalize(d));
 	if(opts && opts.type == 'binary' && typeof cptable !== 'undefined') str = cptable.utils.decode(65001, char_codes(str));
@@ -13081,7 +13094,7 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ {
 	var rowinfo = [], rowobj = {};
 	var Workbook/*:WBWBProps*/ = ({ Sheets:[], WBProps:{date1904:false} }/*:any*/), wsprops = {};
 	xlmlregex.lastIndex = 0;
-	str = str.replace(/<!--([^\u2603]*?)-->/mg,"");
+	str = str.replace(/<!--([\s\S]*?)-->/mg,"");
 	while((Rn = xlmlregex.exec(str))) switch(Rn[3]) {
 		case 'Data':
 			if(state[state.length-1][1]) break;
@@ -16363,7 +16376,7 @@ var parse_content_xml = (function() {
 		var rept = 1, isstub = false;
 		var i = 0;
 		xlmlregex.lastIndex = 0;
-		str = str.replace(/<!--([^\u2603]*?)-->/mg,"").replace(/<!DOCTYPE[^\[]*\[[^\]]*\]>/gm,"");
+		str = str.replace(/<!--([\s\S]*?)-->/mg,"").replace(/<!DOCTYPE[^\[]*\[[^\]]*\]>/gm,"");
 		while((Rn = xlmlregex.exec(str))) switch((Rn[3]=Rn[3].replace(/_.*$/,""))) {
 
 			case 'table': case '工作表': // 9.1.2 <table:table>