version bump 0.9.2: more bugfixes

- decode sheet name for XLSX and XLML (fixes #203 h/t @rocketmonkeys) - XFExt (fixes #298 h/t @aetna-softwares @aimcom @baharudinafif) - handle truly empty `<is>` elements (fixes #506 h/t @asksahil) - pin version numbers for dependencies (fixes #469 h/t @nhtera) - sed usage fix (see #572 h/t @Liryna) - fix hex2RGB substr indices (fixes #294 h/t @kamorahul) - removed stale typescript files (see #442) - reworked shift formula regex (fixed #551 h/t @SheetJSDev) - README note on webpack codepage suppression (fixes #438 h/t @rusty1s) - README note on WTF (fixes #487 h/t @livesoftware)
SheetJS · Mar 13, 2017 · 456ab63 · 456ab63
1 parent 8cd9e81
commit 456ab63
Show file tree

Hide file tree

Showing 29 changed files with 422 additions and 531 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,4 +1,5 @@
 node_modules
+*.tgz
 misc/coverage.html
 misc/prof.js
 v8.log

diff --git a/.npmignore b/.npmignore
@@ -4,6 +4,7 @@ demos/
 index.html
 misc/
 node_modules
+*.tgz
 tmp
 *.txt
 *.[cC][sS][vV]
@@ -20,6 +21,7 @@ tmp
 *.htm
 *.html
 *.sheetjs
+*.exe
 .gitignore
 .jshintrc
 CONTRIBUTING.md

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -5,6 +5,18 @@ but not limited to API changes and file location changes.  Minor behavioral
 changes may not be included if they are not expected to break existing code.
 
 
+## 0.9.2 (2017-03-13)
+
+* Removed stale TypeScript definition files.  Flowtype comments are used in the
+  `xlsx.flow.js` source and stripped to produce `xlsx.js`.
+* sed usage reworked to support GNU sed in-place form.  BSD sed seems to work,
+  but the build script has not been tested on other sed variants:
+
+```bash
+$ sed -i.ext  [...] # GNU
+$ sed -i .ext [...] # bsd
+```
+
 ## 0.9.0 (2017-03-09)
 
 * Removed ods.js source.  The xlsx.js source absorbed the ODS logic and exposes

diff --git a/README.md b/README.md
@@ -5,36 +5,68 @@ implementation from official specifications, related documents, and test files.
 Emphasis on parsing and writing robustness, cross-format feature compatibility
 with a unified JS representation, and ES3/ES5 browser compatibility back to IE6.
 
-File format support for known spreadsheet data formats:
+[**In-Browser Demo**](http://oss.sheetjs.com/js-xlsx)
 
-| Format                                                       | Read  | Write |
-|:-------------------------------------------------------------|:-----:|:-----:|
-| **Excel Worksheet/Workbook Formats**                         |:-----:|:-----:|
-| Excel 2007+ XML Formats (XLSX/XLSM)                          |  :o:  |  :o:  |
-| Excel 2007+ Binary Format (XLSB BIFF12)                      |  :o:  |  :o:  |
-| Excel 2003-2004 XML Format (XML "SpreadsheetML")             |  :o:  |       |
-| Excel 97-2004 (XLS BIFF8)                                    |  :o:  |       |
-| Excel 5.0/95 (XLS BIFF5)                                     |  :o:  |       |
-| Excel 4.0 (XLS/XLW BIFF4)                                    |  :o:  |       |
-| Excel 3.0 (XLS BIFF3)                                        |  :o:  |       |
-| Excel 2.0/2.1 (XLS BIFF2)                                    |  :o:  |  :o:  |
-| **Excel Supported Text Formats**                             |:-----:|:-----:|
-| Delimiter-Separated Values (CSV/TSV/DSV)                     |       |  :o:  |
-| **Other Workbook/Worksheet Formats**                         |:-----:|:-----:|
-| OpenDocument Spreadsheet (ODS)                               |  :o:  |  :o:  |
-| Flat XML ODF Spreadsheet (FODS)                              |  :o:  |  :o:  |
-| Uniform Office Format Spreadsheet (标文通 UOS1/UOS2)         |  :o:  |       |
-| **Other Common Spreadsheet Output Formats**                  |:-----:|:-----:|
-| HTML Tables                                                  |  :o:  |       |
+[**Source Code**](http://git.io/xlsx)
 
-![circo graph of format support](formats.png)
+[**Commercial Support**](http://sheetjs.com/reinforcements)
 
-Demo: <http://oss.sheetjs.com/js-xlsx>
+[**File format support for known spreadsheet data formats:**](#file-formats)
+
+![circo graph of format support](formats.png)
 
-Source: <http://git.io/xlsx>
 
-Paid support available through the [reinforcements program](http://sheetjs.com/reinforcements)
 
+## Table of Contents
+
+<!-- toc -->
+
+- [Installation](#installation)
+  * [JS Ecosystem Demos](#js-ecosystem-demos)
+  * [Optional Modules](#optional-modules)
+  * [ECMAScript 5 Compatibility](#ecmascript-5-compatibility)
+- [Parsing Workbooks](#parsing-workbooks)
+- [Working with the Workbook](#working-with-the-workbook)
+- [Writing Workbooks](#writing-workbooks)
+- [Interface](#interface)
+  * [Parsing functions](#parsing-functions)
+  * [Writing functions](#writing-functions)
+  * [Utilities](#utilities)
+- [Workbook / Worksheet / Cell Object Description](#workbook--worksheet--cell-object-description)
+  * [General Structures](#general-structures)
+  * [Cell Object](#cell-object)
+  * [Data Types](#data-types)
+  * [Formulae](#formulae)
+  * [Worksheet Object](#worksheet-object)
+  * [Workbook Object](#workbook-object)
+- [Parsing Options](#parsing-options)
+  * [Input Type](#input-type)
+  * [Guessing File Type](#guessing-file-type)
+- [Writing Options](#writing-options)
+  * [Supported Output Formats](#supported-output-formats)
+  * [Output Type](#output-type)
+- [Utility Functions](#utility-functions)
+  * [Formulae Output](#formulae-output)
+  * [CSV and general DSV Output](#csv-and-general-dsv-output)
+  * [JSON](#json)
+- [File Formats](#file-formats)
+  * [Excel 2007+ XML (XLSX/XLSM)](#excel-2007-xml-xlsxxlsm)
+  * [Excel 2.0-95 (BIFF2/BIFF3/BIFF4/BIFF5)](#excel-20-95-biff2biff3biff4biff5)
+  * [Excel 97-2004 Binary (BIFF8)](#excel-97-2004-binary-biff8)
+  * [Excel 2003-2004 (SpreadsheetML)](#excel-2003-2004-spreadsheetml)
+  * [Excel 2007+ Binary (XLSB, BIFF12)](#excel-2007-binary-xlsb-biff12)
+  * [OpenDocument Spreadsheet (ODS/FODS) and Uniform Office Spreadsheet (UOS1/2)](#opendocument-spreadsheet-odsfods-and-uniform-office-spreadsheet-uos12)
+  * [Comma-Separated Values](#comma-separated-values)
+  * [HTML](#html)
+- [Testing](#testing)
+  * [Tested Environments](#tested-environments)
+  * [Test Files](#test-files)
+- [Contributing](#contributing)
+- [License](#license)
+- [References](#references)
+- [Badges](#badges)
+
+<!-- tocstop -->
 
 ## Installation
 
@@ -83,6 +115,17 @@ 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`
 
+Webpack and browserify builds include optional modules by default.  Webpack can
+be configured to remove support with `resolve.alias`:
+
+```js
+  /* uncomment the lines below to remove support */
+  resolve: {
+    alias: { "./dist/cpexcel.js": "" } // <-- omit international support
+  }
+```
+
+
 ### ECMAScript 5 Compatibility
 
 Since xlsx.js uses ES5 functions like `Array#forEach`, older browsers require
@@ -143,10 +186,10 @@ oReq.send();
 ```js
 /* processing array buffers, only required for readAsArrayBuffer */
 function fixdata(data) {
-	var o = "", l = 0, w = 10240;
-	for(; l<data.byteLength/w; ++l) o+=String.fromCharCode.apply(null,new Uint8Array(data.slice(l*w,l*w+w)));
-	o+=String.fromCharCode.apply(null, new Uint8Array(data.slice(l*w)));
-	return o;
+  var o = "", l = 0, w = 10240;
+  for(; l<data.byteLength/w; ++l) o+=String.fromCharCode.apply(null,new Uint8Array(data.slice(l*w,l*w+w)));
+  o+=String.fromCharCode.apply(null, new Uint8Array(data.slice(l*w)));
+  return o;
 }
 
 var rABS = true; // true: readAsBinaryString ; false: readAsArrayBuffer
@@ -528,6 +571,7 @@ The exported `read` and `readFile` functions accept an options argument:
 | bookSheets  | false   | If true, only parse enough to get the sheet names    |
 | bookVBA     | false   | If true, expose vbaProject.bin to `vbaraw` field **  |
 | password    | ""      | If defined and file is encrypted, use password **    |
+| WTF         | false   | If true, throw errors on unexpected file features ** |
 
 - `cellFormula` option only applies to formats that require extra processing to
   parse formulae (XLS/XLSB).
@@ -545,6 +589,9 @@ The exported `read` and `readFile` functions accept an options argument:
 - `cellDates` currently does not convert numerical dates to JS dates.
 - Currently only XOR encryption is supported.  Unsupported error will be thrown
   for files employing other encryption methods.
+- WTF is mainly for development.  By default, the parser will suppress read
+  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
 
@@ -754,8 +801,37 @@ Example showing the effect of `raw`:
 
 ## File Formats
 
-Despite the fact that the name of the library is `xlsx`, it supports numerous
-non-XLSX file formats:
+Despite the library name `xlsx`, it supports numerous spreadsheet file formats:
+
+| Format                                                       | Read  | Write |
+|:-------------------------------------------------------------|:-----:|:-----:|
+| **Excel Worksheet/Workbook Formats**                         |:-----:|:-----:|
+| Excel 2007+ XML Formats (XLSX/XLSM)                          |  :o:  |  :o:  |
+| Excel 2007+ Binary Format (XLSB BIFF12)                      |  :o:  |  :o:  |
+| Excel 2003-2004 XML Format (XML "SpreadsheetML")             |  :o:  |       |
+| Excel 97-2004 (XLS BIFF8)                                    |  :o:  |       |
+| Excel 5.0/95 (XLS BIFF5)                                     |  :o:  |       |
+| Excel 4.0 (XLS/XLW BIFF4)                                    |  :o:  |       |
+| Excel 3.0 (XLS BIFF3)                                        |  :o:  |       |
+| Excel 2.0/2.1 (XLS BIFF2)                                    |  :o:  |  :o:  |
+| **Excel Supported Text Formats**                             |:-----:|:-----:|
+| Delimiter-Separated Values (CSV/TSV/DSV)                     |       |  :o:  |
+| **Other Workbook/Worksheet Formats**                         |:-----:|:-----:|
+| OpenDocument Spreadsheet (ODS)                               |  :o:  |  :o:  |
+| Flat XML ODF Spreadsheet (FODS)                              |  :o:  |  :o:  |
+| Uniform Office Format Spreadsheet (标文通 UOS1/UOS2)         |  :o:  |       |
+| **Other Common Spreadsheet Output Formats**                  |:-----:|:-----:|
+| HTML Tables                                                  |  :o:  |       |
+
+### Excel 2007+ XML (XLSX/XLSM)
+
+XLSX and XLSM files are ZIP containers containing a series of XML files in
+accordance with the Open Packaging Conventions (OPC).  The XLSM filetype, almost
+identical to XLSX, is used for files containing macros.
+
+The format is standardized in ECMA-376 and later in ISO/IEC 29500.  Excel does
+not follow the specification, and there are additional documents discussing how
+Excel deviates from the specification.
 
 ### Excel 2.0-95 (BIFF2/BIFF3/BIFF4/BIFF5)
 
@@ -816,26 +892,6 @@ Excel HTML worksheets include special metadata encoded in styles.  For example,
 `mso-number-format` is a localized string containing the number format.  Despite
 the metadata the output is valid HTML, although it does accept bare `&` symbols.
 
-## Tested Environments
-
- - NodeJS 0.8, 0.9, 0.10, 0.11, 0.12, 4.x, 5.x, 6.x, 7.x
- - IE 6/7/8/9/10/11 (IE6-9 browsers require shims for interacting with client)
- - Chrome 24+
- - Safari 6+
- - FF 18+
-
-Tests utilize the mocha testing framework.  Travis-CI and Sauce Labs links:
-
- - <https://travis-ci.org/SheetJS/js-xlsx> for XLSX module in nodejs
- - <https://travis-ci.org/SheetJS/SheetJS.github.io> for XLS\* modules
- - <https://saucelabs.com/u/sheetjs> for XLS\* modules using Sauce Labs
-
-## Test Files
-
-Test files are housed in [another repo](https://github.com/SheetJS/test_files).
-
-Running `make init` will refresh the `test_files` submodule and get the files.
-
 ## Testing
 
 `make test` will run the node-based tests.  By default it runs tests on files in
@@ -865,16 +921,36 @@ $ make lint        # JSHint and JSCS checks
 $ make flow        # make lint + Flow checking
 ```
 
-To run the in-browser tests, clone
-[The oss.sheetjs.com repo](https://github.com/SheetJS/SheetJS.github.io) and
-replace the xlsx.js file (then fire up the browser and go to `stress.html`):
+To run the in-browser tests, clone the repo for
+[oss.sheetjs.com](https://github.com/SheetJS/SheetJS.github.io) and replace
+the xlsx.js file (then fire up the browser and go to `stress.html`):
 
 ```bash
 $ cp xlsx.js ../SheetJS.github.io
 $ cd ../SheetJS.github.io
 $ simplehttpserver # or "python -mSimpleHTTPServer" or "serve"
 $ open -a Chromium.app http://localhost:8000/stress.html
 ```
+### Tested Environments
+
+ - NodeJS 0.8, 0.9, 0.10, 0.11, 0.12, 4.x, 5.x, 6.x, 7.x
+ - IE 6/7/8/9/10/11 (IE6-9 browsers require shims for interacting with client)
+ - Chrome 24+
+ - Safari 6+
+ - FF 18+
+
+Tests utilize the mocha testing framework.  Travis-CI and Sauce Labs links:
+
+ - <https://travis-ci.org/SheetJS/js-xlsx> for XLSX module in nodejs
+ - <https://travis-ci.org/SheetJS/SheetJS.github.io> for XLS\* modules
+ - <https://saucelabs.com/u/sheetjs> for XLS\* modules using Sauce Labs
+
+### Test Files
+
+Test files are housed in [another repo](https://github.com/SheetJS/test_files).
+
+Running `make init` will refresh the `test_files` submodule and get the files.
+
 
 
 ## Contributing

diff --git a/bits/01_version.js b/bits/01_version.js
@@ -1 +1 @@
-XLSX.version = '0.9.1';
+XLSX.version = '0.9.2';
diff --git a/bits/30_ctype.js b/bits/30_ctype.js
@@ -193,7 +193,6 @@ function parse_ct(data/*:?string*/, opts) {
 			case '<Default': ctext[y.Extension] = y.ContentType; break;
 			case '<Override':
 				if(ct[ct2type[y.ContentType]] !== undefined) ct[ct2type[y.ContentType]].push(y.PartName);
-				else if(opts.WTF) console.error(y);
 				break;
 		}
 	});

diff --git a/bits/34_extprops.js b/bits/34_extprops.js
@@ -70,7 +70,7 @@ function write_ext_props(cp, opts)/*:string*/ {
 
 	/* TODO: HeadingPairs, TitlesOfParts */
 	o[o.length] = (W('HeadingPairs', W('vt:vector', W('vt:variant', '<vt:lpstr>Worksheets</vt:lpstr>')+W('vt:variant', W('vt:i4', String(cp.Worksheets))), {size:2, baseType:"variant"})));
-	o[o.length] = (W('TitlesOfParts', W('vt:vector', cp.SheetNames.map(function(s) { return "<vt:lpstr>" + s + "</vt:lpstr>"; }).join(""), {size: cp.Worksheets, baseType:"lpstr"})));
+	o[o.length] = (W('TitlesOfParts', W('vt:vector', cp.SheetNames.map(function(s) { return "<vt:lpstr>" + escapexml(s) + "</vt:lpstr>"; }).join(""), {size: cp.Worksheets, baseType:"lpstr"})));
 	if(o.length>2){ o[o.length] = ('</Properties>'); o[1]=o[1].replace("/>",">"); }
 	return o.join("");
 }
diff --git a/bits/39_xlsbiff.js b/bits/39_xlsbiff.js
@@ -34,7 +34,6 @@ function parse_XTI(blob, length) {
 function parse_RkRec(blob, length) {
 	var ixfe = blob.read_shift(2);
 	var RK = parse_RkNumber(blob);
-	//console.log("::", ixfe, RK,";;");
 	return [ixfe, RK];
 }
 

diff --git a/bits/45_styutils.js b/bits/45_styutils.js
@@ -1,6 +1,6 @@
 function hex2RGB(h) {
 	var o = h.substr(h[0]==="#"?1:0,6);
-	return [parseInt(o.substr(0,2),16),parseInt(o.substr(0,2),16),parseInt(o.substr(0,2),16)];
+	return [parseInt(o.substr(0,2),16),parseInt(o.substr(2,2),16),parseInt(o.substr(4,2),16)];
 }
 function rgb2Hex(rgb) {
 	for(var i=0,o=1; i!=3; ++i) o = o*256 + (rgb[i]>255?255:rgb[i]<0?0:rgb[i]);

diff --git a/bits/50_styxls.js b/bits/50_styxls.js
@@ -68,10 +68,15 @@ function update_xfext(xf, xfext) {
 		switch(xfe[0]) { /* 2.5.108 extPropData */
 			case 0x04: break; /* foreground color */
 			case 0x05: break; /* background color */
-			case 0x07: case 0x08: case 0x09: case 0x0a: break;
+			case 0x06: break; /* gradient fill */
+			case 0x07: break; /* top cell border color */
+			case 0x08: break; /* bottom cell border color */
+			case 0x09: break; /* left cell border color */
+			case 0x0a: break; /* right cell border color */
+			case 0x0b: break; /* diagonal cell border color */
 			case 0x0d: break; /* text color */
 			case 0x0e: break; /* font scheme */
-			default: throw "bafuq" + xfe[0].toString(16);
+			case 0x0f: break; /* indentation level */
 		}
 	});
 }

diff --git a/bits/61_fcommon.js b/bits/61_fcommon.js
@@ -16,9 +16,10 @@ var rc_to_a1 = (function(){
 	};
 })();
 
-/* TODO actually parse the formula */
+/* no defined name can collide with a valid cell address A1:XFD1048576 ... except LOG10! */
+var crefregex = /(^|[^._A-Z0-9])([$]?)([A-Z]{1,2}|[A-W][A-Z]{2}|X[A-E][A-Z]|XF[A-D])([$]?)([1-9]\d{0,5}|10[0-3]\d{4}|104[0-7]\d{3}|1048[0-4]\d{2}|10485[0-6]\d|104857[0-6])(?![_.\(A-Za-z0-9])/g;
 function shift_formula_str(f/*:string*/, delta/*:Cell*/)/*:string*/ {
-	return f.replace(/(^|[^A-Z0-9])([$]?)([A-Z]+)([$]?)(\d+)/g, function($0, $1, $2, $3, $4, $5, off, str) {
+	return f.replace(crefregex, function($0, $1, $2, $3, $4, $5, off, str) {
 		return $1+($2=="$" ? $2+$3 : encode_col(decode_col($3)+delta.c))+($4=="$" ? $4+$5 : encode_row(decode_row($5) + delta.r));
 	});
 }

diff --git a/bits/67_wsxml.js b/bits/67_wsxml.js
@@ -265,7 +265,7 @@ return function parse_ws_xml_data(sdata, s, opts, guess) {
 				case 'inlineStr':
 					cref = d.match(isregex);
 					p.t = 's';
-					if(cref != null) { if((sstr = parse_si(cref[1]))) p.v = sstr.t; } else p.v = "";
+					if(cref != null && (sstr = parse_si(cref[1]))) p.v = sstr.t; else p.v = "";
 					break; // inline string
 				case 'b': p.v = parsexmlbool(p.v); break;
 				case 'd':

diff --git a/bits/72_wbxml.js b/bits/72_wbxml.js
@@ -41,7 +41,7 @@ function parse_wb_xml(data, opts)/*:WorkbookFile*/ {
 			/* 18.2.20 sheets CT_Sheets 1 */
 			case '<sheets>': case '</sheets>': break; // aggregate sheet
 			/* 18.2.19   sheet CT_Sheet + */
-			case '<sheet': delete y[0]; y.name = utf8read(y.name); wb.Sheets.push(y); break;
+			case '<sheet': delete y[0]; y.name = unescapexml(utf8read(y.name)); wb.Sheets.push(y); break;
 			case '</sheet>': break;
 
 			/* 18.2.15 functionGroups CT_FunctionGroups ? */
@@ -140,7 +140,7 @@ function write_wb_xml(wb/*:Workbook*/, opts/*:?WriteOpts*/)/*:string*/ {
 	o[o.length] = (writextag('workbookPr', null, {date1904:safe1904(wb)}));
 	o[o.length] = "<sheets>";
 	for(var i = 0; i != wb.SheetNames.length; ++i)
-		o[o.length] = (writextag('sheet',null,{name:wb.SheetNames[i].substr(0,31), sheetId:""+(i+1), "r:id":"rId"+(i+1)}));
+		o[o.length] = (writextag('sheet',null,{name:escapexml(wb.SheetNames[i].substr(0,31)), sheetId:""+(i+1), "r:id":"rId"+(i+1)}));
 	o[o.length] = "</sheets>";
 	if(o.length>2){ o[o.length] = '</workbook>'; o[1]=o[1].replace("/>",">"); }
 	return o.join("");

diff --git a/bits/75_xlml.js b/bits/75_xlml.js
@@ -237,7 +237,7 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ {
 				r = c = 0;
 				state.push([Rn[3], false]);
 				tmp = xlml_parsexmltag(Rn[0]);
-				sheetname = tmp.Name;
+				sheetname = unescapexml(tmp.Name);
 				cursheet = {};
 				mergecells = [];
 			}

diff --git a/dist/xlsx.core.min.js b/dist/xlsx.core.min.js
diff --git a/dist/xlsx.core.min.map b/dist/xlsx.core.min.map
diff --git a/dist/xlsx.full.min.js b/dist/xlsx.full.min.js
diff --git a/dist/xlsx.full.min.map b/dist/xlsx.full.min.map