version bump 0.10.7: autocorrections for bad files

- recalculate SSF for malformed files (fixes SheetJS#506 h/t @asksahil)
- malformed shared string (fixes SheetJS#445 h/t @ramzec)
- SSF added to TS def (fixes SheetJS#711 h/t @duckywang1)
- Norsk property names
- resolved gitbook processing issues

.travis.yml

@@ -13,19 +13,19 @@ node_js:
 matrix:
   include:
     - node_js: "6"
-      env: TZ="America/New_York"
+      env: TZ="America/New_York" FMTS=misc
     - node_js: "8"
       env: TZ="America/Los_Angeles"
     - node_js: "6"
-      env: TZ="Europe/London"
+      env: TZ="Europe/London" FMTS=misc
     - node_js: "8"
       env: TZ="Europe/Berlin"
     - node_js: "6"
-      env: TZ="Asia/Kolkata"
+      env: TZ="Asia/Kolkata" FMTS=misc
     - node_js: "7"
       env: TZ="Asia/Shanghai"
     - node_js: "8"
-      env: TZ="Asia/Seoul"
+      env: TZ="Asia/Seoul" FMTS=misc
 before_install:
   - "npm install -g [email protected]"
   - "npm install -g [email protected] voc"

Makefile

@@ -205,8 +205,9 @@ readme: README.md ## Update README Table of Contents
 
 .PHONY: book
 book: readme graph ## Update summary for documentation
-	printf "# Summary\n\n- [xlsx](README.md#xlsx)\n" > misc/docs/SUMMARY.md
+	printf "# Summary\n\n- [xlsx](README.md#sheetjs-js-xlsx)\n" > misc/docs/SUMMARY.md
 	markdown-toc README.md | sed 's/(#/(README.md#/g'>> misc/docs/SUMMARY.md
+	<README.md grep -vE "(details|summary)>" > misc/docs/README.md
 
 .PHONY: help
 help:

README.md

@@ -59,12 +59,12 @@ enhancements, additional features by request, and dedicated support.
   * [ECMAScript 5 Compatibility](#ecmascript-5-compatibility)
 - [Philosophy](#philosophy)
 - [Parsing Workbooks](#parsing-workbooks)
-  * [Complete Examples](#complete-examples)
+  * [Parsing Examples](#parsing-examples)
   * [Streaming Read](#streaming-read)
 - [Working with the Workbook](#working-with-the-workbook)
-  * [Complete Examples](#complete-examples-1)
+  * [Parsing and Writing Examples](#parsing-and-writing-examples)
 - [Writing Workbooks](#writing-workbooks)
-  * [Complete Examples](#complete-examples-2)
+  * [Writing Examples](#writing-examples)
   * [Streaming Write](#streaming-write)
 - [Interface](#interface)
   * [Parsing functions](#parsing-functions)
@@ -403,7 +403,7 @@ input_dom_element.addEventListener('change', handleFile, false);
 </details>
 
 
-### Complete Examples
+### Parsing Examples
 
 - <http://oss.sheetjs.com/js-xlsx/> HTML5 File API / Base64 Text / Web Workers
 
@@ -550,7 +550,9 @@ wb.Sheets[ws_name] = ws;
 </details>
 
 
-### Complete Examples
+### Parsing and Writing Examples
+
+- <http://sheetjs.com/demos/modify.html> read + modify + write files
 
 - <https://github.com/SheetJS/js-xlsx/blob/master/bin/xlsx.njs> node
 
@@ -607,7 +609,7 @@ saveAs(new Blob([s2ab(wbout)],{type:"application/octet-stream"}), "test.xlsx");
 ```
 </details>
 
-### Complete Examples
+### Writing Examples
 
 - <http://sheetjs.com/demos/table.html> exporting an HTML table
 - <http://sheetjs.com/demos/writexlsx.html> generates a simple file

bits/01_version.js

@@ -1 +1 @@
-XLSX.version = '0.10.6';
+XLSX.version = '0.10.7';

bits/22_xmlutils.js

@@ -135,9 +135,9 @@ var matchtag = (function() {
 var vtregex = (function(){ var vt_cache = {};
 	return function vt_regex(bt) {
 		if(vt_cache[bt] !== undefined) return vt_cache[bt];
-		return (vt_cache[bt] = new RegExp("<(?:vt:)?" + bt + ">(.*?)</(?:vt:)?" + bt + ">", 'g') );
+		return (vt_cache[bt] = new RegExp("<(?:vt:)?" + bt + ">([\\s\\S]*?)</(?:vt:)?" + bt + ">", 'g') );
 };})();
-var vtvregex = /<\/?(?:vt:)?variant>/g, vtmregex = /<(?:vt:)([^>]*)>(.*)</;
+var vtvregex = /<\/?(?:vt:)?variant>/g, vtmregex = /<(?:vt:)([^>]*)>([\s\S]*)</;
 function parseVector(data) {
 	var h = parsexmltag(data);
 

bits/28_binstructs.js

@@ -5,7 +5,7 @@ function write_UInt32LE(x/*:number*/, o) {
 }
 
 /* [MS-XLSB] 2.5.168 */
-function parse_XLWideString(data)/*:string*/ {
+function parse_XLWideString(data/*::, length*/)/*:string*/ {
 	var cchCharacters = data.read_shift(4);
 	return cchCharacters === 0 ? "" : data.read_shift(cchCharacters, 'dbcs');
 }
@@ -88,7 +88,7 @@ var parse_XLSBCodeName = parse_XLWideString;
 var write_XLSBCodeName = write_XLWideString;
 
 /* [MS-XLSB] 2.5.166 */
-function parse_XLNullableWideString(data)/*:string*/ {
+function parse_XLNullableWideString(data/*::, length*/)/*:string*/ {
 	var cchCharacters = data.read_shift(4);
 	return cchCharacters === 0 || cchCharacters === 0xFFFFFFFF ? "" : data.read_shift(cchCharacters, 'dbcs');
 }
@@ -129,7 +129,7 @@ function write_RkNumber(data/*:number*/, o) {
 
 
 /* [MS-XLSB] 2.5.117 RfX */
-function parse_RfX(data)/*:Range*/ {
+function parse_RfX(data /*::, length*/)/*:Range*/ {
 	var cell/*:Range*/ = ({s: {}, e: {}}/*:any*/);
 	cell.s.r = data.read_shift(4);
 	cell.e.r = data.read_shift(4);

bits/33_coreprops.js

@@ -26,7 +26,7 @@ var CORE_PROPS_REGEX/*:Array<RegExp>*/ = (function() {
 	for(var i = 0; i < CORE_PROPS.length; ++i) {
 		var f = CORE_PROPS[i];
 		var g = "(?:"+ f[0].substr(0,f[0].indexOf(":")) +":)"+ f[0].substr(f[0].indexOf(":")+1);
-		r[i] = new RegExp("<" + g + "[^>]*>(.*)<\/" + g + ">");
+		r[i] = new RegExp("<" + g + "[^>]*>([\\s\\S]*?)<\/" + g + ">");
 	}
 	return r;
 })();

bits/34_extprops.js

@@ -25,7 +25,7 @@ function parse_ext_props(data, p) {
 			case "string": p[f[1]] = (data.match(matchtag(f[0]))||[])[1]; break;
 			case "bool": p[f[1]] = (data.match(matchtag(f[0]))||[])[1] === "true"; break;
 			case "raw":
-				var cur = data.match(new RegExp("<" + f[0] + "[^>]*>(.*)<\/" + f[0] + ">"));
+				var cur = data.match(new RegExp("<" + f[0] + "[^>]*>([\\s\\S]*?)<\/" + f[0] + ">"));
 				if(cur && cur.length > 0) q[f[1]] = cur[1];
 				break;
 		}
@@ -49,13 +49,15 @@ function parse_ext_props(data, p) {
 				case "Fogli di lavoro":
 				case "Folhas de cálculo":
 				case "Planilhas":
+				case "Regneark":
 				case "Werkbladen":
 					p.Worksheets = len;
 					p.SheetNames = parts.slice(idx, idx + len);
 					break;
 
 				case "Named Ranges":
 				case "Benannte Bereiche":
+				case "Navngivne områder":
 					p.NamedRanges = len;
 					p.DefinedNames = parts.slice(idx, idx + len);
 					break;

bits/38_xlstypes.js

@@ -108,7 +108,7 @@ function parse_VtVector(blob, cb) {
 }
 
 /* [MS-OLEPS] 2.15 TypedPropertyValue */
-function parse_TypedPropertyValue(blob, type, _opts) {
+function parse_TypedPropertyValue(blob, type/*:number*/, _opts) {
 	var t = blob.read_shift(2), ret, opts = _opts||{};
 	blob.l += 2;
 	if(type !== VT_VARIANT)
@@ -124,7 +124,7 @@ function parse_TypedPropertyValue(blob, type, _opts) {
 		case 0x41 /*VT_BLOB*/: return parse_BLOB(blob);
 		case 0x47 /*VT_CF*/: return parse_ClipboardData(blob);
 		case 0x50 /*VT_STRING*/: return parse_VtString(blob, t, !opts.raw && 4).replace(chr0,'');
-		case 0x51 /*VT_USTR*/: return parse_VtUnalignedString(blob, t, 4).replace(chr0,'');
+		case 0x51 /*VT_USTR*/: return parse_VtUnalignedString(blob, t/*, 4*/).replace(chr0,'');
 		case 0x100C /*VT_VECTOR|VT_VARIANT*/: return parse_VtVecHeadingPair(blob);
 		case 0x101E /*VT_LPSTR*/: return parse_VtVecUnalignedLpstr(blob);
 		default: throw new Error("TypedPropertyValue unrecognized type " + type + " " + t);
@@ -277,16 +277,16 @@ function parslurp(blob, length, cb) {
 
 function parsebool(blob, length) { return blob.read_shift(length) === 0x1; }
 
-function parseuint16(blob) { return blob.read_shift(2, 'u'); }
-function parseuint16a(blob, length) { return parslurp(blob,length,parseuint16);}
+function parseuint16(blob/*::, length:?number, opts:?any*/) { return blob.read_shift(2, 'u'); }
+function parseuint16a(blob, length/*:: :?number, opts:?any*/) { return parslurp(blob,length,parseuint16);}
 
 /* --- 2.5 Structures --- */
 
 /* [MS-XLS] 2.5.14 Boolean */
 var parse_Boolean = parsebool;
 
 /* [MS-XLS] 2.5.10 Bes (boolean or error) */
-function parse_Bes(blob) {
+function parse_Bes(blob/*::, length*/) {
 	var v = blob.read_shift(1), t = blob.read_shift(1);
 	return t === 0x01 ? v : v === 0x01;
 }
@@ -360,7 +360,7 @@ function parse_XLUnicodeString2(blob, length, opts) {
 var parse_ControlInfo = parsenoop;
 
 /* [MS-OSHARED] 2.3.7.6 URLMoniker TODO: flags */
-var parse_URLMoniker = function(blob/*, length, opts*/) {
+var parse_URLMoniker = function(blob/*::, length, opts*/) {
 	var len = blob.read_shift(4), start = blob.l;
 	var extra = false;
 	if(len > 24) {

bits/40_harb.js

@@ -292,15 +292,15 @@ var SYLK = (function() {
 		return [arr, sht];
 	}
 
-	function sylk_to_sheet(str/*:string*/, opts)/*:Worksheet*/ {
-		var aoasht = sylk_to_aoa(str, opts);
+	function sylk_to_sheet(d/*:RawData*/, opts)/*:Worksheet*/ {
+		var aoasht = sylk_to_aoa(d, opts);
 		var aoa = aoasht[0], ws = aoasht[1];
 		var o = aoa_to_sheet(aoa, opts);
 		keys(ws).forEach(function(k) { o[k] = ws[k]; });
 		return o;
 	}
 
-	function sylk_to_workbook(str/*:string*/, opts)/*:Workbook*/ { return sheet_to_workbook(sylk_to_sheet(str, opts), opts); }
+	function sylk_to_workbook(d/*:RawData*/, opts)/*:Workbook*/ { return sheet_to_workbook(sylk_to_sheet(d, opts), opts); }
 
 	function write_ws_cell_sylk(cell/*:Cell*/, ws/*:Worksheet*/, R/*:number*/, C/*:number*/, opts)/*:string*/ {
 		var o = "C;Y" + (R+1) + ";X" + (C+1) + ";K";
@@ -580,7 +580,7 @@ var PRN = (function() {
 		return prn_to_sheet_str(str, opts);
 	}
 
-	function prn_to_workbook(str/*:string*/, opts)/*:Workbook*/ { return sheet_to_workbook(prn_to_sheet(str, opts), opts); }
+	function prn_to_workbook(d/*:RawData*/, opts)/*:Workbook*/ { return sheet_to_workbook(prn_to_sheet(d, opts), opts); }
 
 	function sheet_to_prn(ws/*:Worksheet*/, opts/*:?any*/)/*:string*/ {
 		var o/*:Array<string>*/ = [];

bits/42_sstxml.js

@@ -163,7 +163,7 @@ var parse_rs = (function parse_rs_factory() {
 
 /* 18.4.8 si CT_Rst */
 var sitregex = /<(?:\w+:)?t[^>]*>([^<]*)<\/(?:\w+:)?t>/g, sirregex = /<(?:\w+:)?r>/;
-var sirphregex = /<(?:\w+:)?rPh.*?>(.*?)<\/(?:\w+:)?rPh>/g;
+var sirphregex = /<(?:\w+:)?rPh.*?>([\s\S]*?)<\/(?:\w+:)?rPh>/g;
 function parse_si(x, opts) {
 	var html = opts ? opts.cellHTML : true;
 	var z = {};

bits/47_styxml.js

@@ -17,44 +17,48 @@ function parse_borders(t, styles, themes, opts) {
 			case '</border>': break;
 
 			/* note: not in spec, appears to be CT_BorderPr */
-			case '<left': case '<left/>': break;
+			case '<left/>': break;
+			case '<left': case '<left>': break;
 			case '</left>': break;
 
 			/* note: not in spec, appears to be CT_BorderPr */
-			case '<right': case '<right/>': break;
+			case '<right/>': break;
+			case '<right': case '<right>': break;
 			case '</right>': break;
 
 			/* 18.8.43 top CT_BorderPr */
-			case '<top': case '<top/>': break;
+			case '<top/>': break;
+			case '<top': case '<top>': break;
 			case '</top>': break;
 
 			/* 18.8.6 bottom CT_BorderPr */
-			case '<bottom': case '<bottom/>': break;
+			case '<bottom/>': break;
+			case '<bottom': case '<bottom>': break;
 			case '</bottom>': break;
 
 			/* 18.8.13 diagonal CT_BorderPr */
-			case '<diagonal': case '<diagonal/>': break;
+			case '<diagonal': case '<diagonal>': case '<diagonal/>': break;
 			case '</diagonal>': break;
 
 			/* 18.8.25 horizontal CT_BorderPr */
-			case '<horizontal': case '<horizontal/>': break;
+			case '<horizontal': case '<horizontal>': case '<horizontal/>': break;
 			case '</horizontal>': break;
 
 			/* 18.8.44 vertical CT_BorderPr */
-			case '<vertical': case '<vertical/>': break;
+			case '<vertical': case '<vertical>': case '<vertical/>': break;
 			case '</vertical>': break;
 
 			/* 18.8.37 start CT_BorderPr */
-			case '<start': case '<start/>': break;
+			case '<start': case '<start>': case '<start/>': break;
 			case '</start>': break;
 
 			/* 18.8.16 end CT_BorderPr */
-			case '<end': case '<end/>': break;
+			case '<end': case '<end>': case '<end/>': break;
 			case '</end>': break;
 
 			/* 18.8.? color CT_Color */
-			case '<color': case '<color/>': break;
-			case '</color>': break;
+			case '<color': case '<color>': break;
+			case '<color/>': case '</color>': break;
 
 			default: if(opts && opts.WTF) throw new Error('unrecognized ' + y[0] + ' in borders');
 		}
@@ -71,7 +75,7 @@ function parse_fills(t, styles, themes, opts) {
 			case '<fills': case '<fills>': case '</fills>': break;
 
 			/* 18.8.20 fill CT_Fill */
-			case '<fill>': break;
+			case '<fill>': case '<fill': break;
 			case '</fill>': styles.Fills.push(fill); fill = {}; break;
 
 			/* 18.8.24 gradientFill CT_GradientFill */
@@ -204,7 +208,7 @@ function parse_fonts(t, styles, themes, opts) {
 				if(!font.color) font.color = {};
 				if(y.auto) font.color.auto = parsexmlbool(y.auto);
 
-				if(y.rgb) font.color.rgb = y.rgb;
+				if(y.rgb) font.color.rgb = y.rgb.slice(-6);
 				else if(y.indexed) {
 					font.color.index = parseInt(y.indexed, 10);
 					var icv = XLSIcv[font.color.index];
@@ -240,7 +244,14 @@ function parse_numFmts(t, styles, opts) {
 			case '<numFmts': case '</numFmts>': case '<numFmts/>': case '<numFmts>': break;
 			case '<numFmt': {
 				var f=unescapexml(utf8read(y.formatCode)), j=parseInt(y.numFmtId,10);
-				styles.NumberFmt[j] = f; if(j>0) SSF.load(f,j);
+				styles.NumberFmt[j] = f;
+				if(j>0) {
+					if(j > 0x188) {
+						for(j = 0x188; j > 0x3c; --j) if(styles.NumberFmt[j] == null) break;
+						styles.NumberFmt[j] = f;
+					}
+					SSF.load(f,j);
+				}
 			} break;
 			case '</numFmt>': break;
 			default: if(opts.WTF) throw new Error('unrecognized ' + y[0] + ' in numFmts');
@@ -271,13 +282,16 @@ function parse_cellXfs(t, styles, opts) {
 			case '<cellXfs': case '<cellXfs>': case '<cellXfs/>': case '</cellXfs>': break;
 
 			/* 18.8.45 xf CT_Xf */
-			case '<xf':
+			case '<xf': case '<xf/>':
 				xf = y;
 				delete xf[0];
 				for(i = 0; i < cellXF_uint.length; ++i) if(xf[cellXF_uint[i]])
 					xf[cellXF_uint[i]] = parseInt(xf[cellXF_uint[i]], 10);
 				for(i = 0; i < cellXF_bool.length; ++i) if(xf[cellXF_bool[i]])
 					xf[cellXF_bool[i]] = parsexmlbool(xf[cellXF_bool[i]], "");
+				if(xf.numFmtId > 0x188) {
+					for(i = 0x188; i > 0x3c; --i) if(styles.NumberFmt[xf.numFmtId] == styles.NumberFmt[i]) { xf.numFmtId = i; break; }
+				}
 				styles.CellXf.push(xf); break;
 			case '</xf>': break;
 
@@ -316,15 +330,16 @@ function write_cellXfs(cellXfs)/*:string*/ {
 
 /* 18.8 Styles CT_Stylesheet*/
 var parse_sty_xml= (function make_pstyx() {
-var numFmtRegex = /<numFmts([^>]*)>.*<\/numFmts>/;
-var cellXfRegex = /<cellXfs([^>]*)>.*<\/cellXfs>/;
-var fillsRegex = /<fills([^>]*)>.*<\/fills>/;
-var fontsRegex = /<fonts([^>]*)>.*<\/fonts>/;
-var bordersRegex = /<borders([^>]*)>.*<\/borders>/;
+var numFmtRegex = /<numFmts([^>]*)>[\S\s]*?<\/numFmts>/;
+var cellXfRegex = /<cellXfs([^>]*)>[\S\s]*?<\/cellXfs>/;
+var fillsRegex = /<fills([^>]*)>[\S\s]*?<\/fills>/;
+var fontsRegex = /<fonts([^>]*)>[\S\s]*?<\/fonts>/;
+var bordersRegex = /<borders([^>]*)>[\S\s]*?<\/borders>/;
 
 return function parse_sty_xml(data, themes, opts) {
 	var styles = {};
 	if(!data) return styles;
+	data = data.replace(/<!--([\s\S]*?)-->/mg,"").replace(/<!DOCTYPE[^\[]*\[[^\]]*\]>/gm,"");
 	/* 18.8.39 styleSheet CT_Stylesheet */
 	var t;
 

bits/48_stybin.js

@@ -259,14 +259,14 @@ function parse_sty_bin(data, themes, opts) {
 function write_FMTS_bin(ba, NF/*:?SSFTable*/) {
 	if(!NF) return;
 	var cnt = 0;
-	[[5,8],[23,26],[41,44],[/*63*/57,/*66],[164,*/392]].forEach(function(r) {
+	[[5,8],[23,26],[41,44],[/*63*/50,/*66],[164,*/392]].forEach(function(r) {
 		/*:: if(!NF) return; */
 		for(var i = r[0]; i <= r[1]; ++i) if(NF[i] != null) ++cnt;
 	});
 
 	if(cnt == 0) return;
 	write_record(ba, "BrtBeginFmts", write_UInt32LE(cnt));
-	[[5,8],[23,26],[41,44],[/*63*/57,/*66],[164,*/392]].forEach(function(r) {
+	[[5,8],[23,26],[41,44],[/*63*/50,/*66],[164,*/392]].forEach(function(r) {
 		/*:: if(!NF) return; */
 		for(var i = r[0]; i <= r[1]; ++i) if(NF[i] != null) write_record(ba, "BrtFmt", write_BrtFmt(i, NF[i]));
 	});