version bump 0.6.8: first options

- preparing for options (paralleling js-xlsx)
- cellNF option
- all relevant cell types emit formats (dead code to be removed later)
- test structure converging to js-xlsx
- miscellaneous cleanup

.gitignore

@@ -1 +1,2 @@
 node_modules
+misc/coverage.html

README.md

@@ -26,7 +26,7 @@ See <http://oss.sheetjs.com/js-xls/> for a browser example.
 
 Some helper functions in `XLS.utils` generate different views of the sheets:
 
-- `XLS.utils.sheet_to_csv` generates CSV 
+- `XLS.utils.sheet_to_csv` generates CSV
 - `XLS.utils.sheet_to_row_object_array` interprets sheets as tables with a header column and generates an array of objects
 - `XLS.utils.get_formulae` generates a list of formulae
 
@@ -36,21 +36,33 @@ For more details:
 - `index.html` is the live demo
 - `bits/80_xls.js` contains the logic for generating CSV and JSON from sheets
 
-## Cell Object Description 
+## Cell Object Description
 
 `.SheetNames` is an ordered list of the sheets in the workbook
-
-`.Sheets[sheetname]` returns a data structure representing the sheet
+
+`.Sheets[sheetname]` returns a data structure representing the sheet.  Each key
+that does not start with `!` corresponds to a cell (using `A-1` notation).
 
 `.Sheets[sheetname][address]` returns the specified cell:
 
 - `.v` : the raw value of the cell
 - `.w` : the formatted text of the cell (if applicable)
 - `.t` : the type of the cell (constrained to the enumeration `ST_CellType` as documented in page 4215 of ISO/IEC 29500-1:2012(E) )
 - `.f` : the formula of the cell (if applicable)
+- `.z` : the number format string associated with the cell (if requested)
 
 For dates, `.v` holds the raw date code from the sheet and `.w` holds the text
 
+## Options
+
+The exported `read` and `readFile` functions accept an options argument:
+
+| Option Name | Default | Description |
+| :---------- | ------: | :---------- |
+| cellNF      | false   | Save number format string to the .z field |
+
+- Even if `cellNF` is false, formatted text (.w) will be generated
+
 ## Other Notes
 
 `CFB` refers to the Microsoft Compound File Binary Format, a container format for XLS as well as DOC and other pre-OOXML data formats.
@@ -67,15 +79,15 @@ Tests utilize the mocha testing framework.  Travis-CI and Sauce Labs links:
 
  - <https://travis-ci.org/SheetJS/js-xls> for XLS module in node
  - <https://travis-ci.org/SheetJS/SheetJS.github.io> for XLS* modules
- - <https://saucelabs.com/u/sheetjs> for XLS* modules using Sauce Labs 
+ - <https://saucelabs.com/u/sheetjs> for XLS* modules using Sauce Labs
 
 ## Contributing
 
-Due to the precarious nature of the Open Specifications Promise, it is very important to ensure code is cleanroom.  Consult CONTRIBUTING.md 
+Due to the precarious nature of the Open Specifications Promise, it is very important to ensure code is cleanroom.  Consult CONTRIBUTING.md
 
 ## XLSX/XLSM/XLSB Support
 
-XLSX/XLSM/XLSB support is available in [js-xlsx](https://github.com/SheetJS/js-xlsx).
+XLSX/XLSM/XLSB is available in [js-xlsx](https://github.com/SheetJS/js-xlsx).
 
 ## License
 
@@ -95,7 +107,8 @@ OSP-covered specifications:
  - [MS-OLEDS]: Object Linking and Embedding (OLE) Data Structures
  - [MS-OLEPS]: Object Linking and Embedding (OLE) Property Set Data Structures
  - [MS-OSHARED]: Office Common Data Types and Objects Structures
- - [MS-OVBA]: Office VBA File Format Structure 
+ - [MS-OVBA]: Office VBA File Format Structure
+ - [MS-OE376]: Office Implementation Information for ECMA-376 Standards Support
  - [XLS]: Microsoft Office Excel 97-2007 Binary File Format Specification
 
 Certain features are shared with the Office Open XML File Formats, covered in:

bin/xls2csv.njs

@@ -44,12 +44,16 @@ if(!fs.existsSync(filename)) {
 	process.exit(2);
 }
 
-if(program.dev) X.verbose = 2;
+var opts = {}, wb;
+if(program.listSheets) opts.bookSheets = true;
 
-var wb;
-if(program.dev) wb = X.readFile(filename);
+if(program.dev) {
+	X.verbose = 2;
+	opts.WTF = true;
+	wb = X.readFile(filename, opts);
+}
 else try {
-	wb = X.readFile(filename);
+	wb = X.readFile(filename, opts);
 } catch(e) {
 	var msg = (program.quiet) ? "" : n + "2csv: error parsing ";
 	msg += filename + ": " + e;

bits/01_version.js

@@ -1 +1 @@
-XLS.version = '0.6.7';
+XLS.version = '0.6.8';

bits/08_blob.js

@@ -1,5 +1,5 @@
 function readIEEE754(buf, idx, isLE, nl, ml) {
-	if(isLE === undefined) isLE = true;
+	if(typeof isLE === 'undefined') isLE = true;
 	if(!nl) nl = 8;
 	if(!ml && nl === 8) ml = 52;
 	var e, m, el = nl * 8 - ml - 1, eMax = (1 << el) - 1, eBias = eMax >> 1;
@@ -179,13 +179,6 @@ function CheckField(hexstr, fld) {
 	this.l += hexstr.length/2;
 }
 
-function WarnField(hexstr, fld) {
-	var b = this.slice(this.l, this.l+hexstr.length/2);
-	var m = b.hexlify ? b.hexlify() : __hexlify(b);
-	if(m !== hexstr) console.error((fld||"") + 'Expected ' + hexstr +' saw ' + m);
-	this.l += hexstr.length/2;
-}
-
 function prep_blob(blob, pos) {
 	blob.read_shift = ReadShift.bind(blob);
 	blob.chk = CheckField;

bits/18_cfb.js

@@ -26,7 +26,6 @@ var fat_addrs = []; // locations of FAT sectors
 var blob = file.slice(0,512);
 prep_blob(blob);
 var read = ReadShift.bind(blob), chk = CheckField.bind(blob);
-//var wrn = WarnField.bind(blob);
 var j = 0, q;
 
 // header signature 8
@@ -36,7 +35,6 @@ chk(HEADER_SIGNATURE, 'Header Signature: ');
 chk(HEADER_CLSID, 'CLSID: ');
 
 // minor version 2
-//wrn(HEADER_MINOR_VERSION, 'Minor Version: ');
 read(2);
 
 // major version 3

bits/80_xls.js

@@ -26,7 +26,7 @@ function parse_compobj(obj) {
 }
 
 
-function parse_xlscfb(cfb) {
+function parse_xlscfb(cfb, options) {
 reset_cp();
 var CompObj = cfb.find('!CompObj');
 var Summary = cfb.find('!SummaryInformation');
@@ -56,7 +56,7 @@ function slurp(R, blob, length, opts) {
 }
 
 // 2.3.2
-function parse_workbook(blob) {
+function parse_workbook(blob, options) {
 	var wb = {opts:{}};
 	var Sheets = {};
 	var out = [];
@@ -265,40 +265,63 @@ function parse_workbook(blob) {
 					temp_val = {ixfe: val.ixfe, XF: XFs[val.ixfe], v:val.val, t:'n'};
 					if(temp_val.XF) try {
 						temp_val.w=SSF.format(temp_val.XF.ifmt||0, temp_val.v);
-					} catch(e) { }
+						if(opts.cellNF) temp_val.z = SSF._table[temp_val.XF.ifmt||0];
+					} catch(e) { if(opts.WTF) throw e; }
 					addline({c:val.c, r:val.r}, temp_val);
 				} break;
 				case 'BoolErr': {
 					temp_val = {ixfe: val.ixfe, XF: XFs[val.ixfe], v:val.val, t:val.t};
 					if(temp_val.XF) try {
 						temp_val.w=SSF.format(temp_val.XF.ifmt||0, temp_val.v);
-					} catch(e) { }
+						if(opts.cellNF) temp_val.z = SSF._table[temp_val.XF.ifmt||0];
+					} catch(e) { if(opts.WTF) throw e; }
 					addline({c:val.c, r:val.r}, temp_val);
 				} break;
 				case 'RK': {
 					temp_val = {ixfe: val.ixfe, XF: XFs[val.ixfe], v:val.rknum, t:'n'};
 					if(temp_val.XF) try {
 						temp_val.w=SSF.format(temp_val.XF.ifmt||0, temp_val.v);
-					} catch(e) { }
+						if(opts.cellNF) temp_val.z = SSF._table[temp_val.XF.ifmt||0];
+					} catch(e) { if(opts.WTF) throw e; }
 					addline({c:val.c, r:val.r}, temp_val);
 				} break;
 				case 'MulRk': {
 					for(var j = val.c; j <= val.C; ++j) {
 						var ixfe = val.rkrec[j-val.c][0];
-						addline({c:j, r:val.r}, {ixfe: ixfe, XF: XFs[ixfe], v:val.rkrec[j-val.c][1], t:'n'});
+						temp_val= {ixfe:ixfe, XF:XFs[ixfe], v:val.rkrec[j-val.c][1], t:'n'};
+						if(temp_val.XF) try {
+							temp_val.w=SSF.format(temp_val.XF.ifmt||0, temp_val.v);
+							if(opts.cellNF) temp_val.z = SSF._table[temp_val.XF.ifmt||0];
+						} catch(e) { if(opts.WTF) throw e; }
+						addline({c:j, r:val.r}, temp_val);
 					}
 				} break;
 				case 'Formula': {
 					switch(val.val) {
 						case 'String': last_formula = val; break;
 						case 'Array Formula': throw "Array Formula unsupported";
-						default: addline(val.cell, {v:val.val, f:stringify_formula(val.formula, range, val.cell, supbooks), ixfe: val.cell.ixfe, XF:XFs[val.cell.ixfe], t:'n'}); // TODO: infer type from formula
+						default: // TODO: infer type from formula
+							temp_val = {v:val.val, ixfe:val.cell.ixfe, t:'n'};
+							temp_val.XF = XFs[temp_val.ixfe];
+							temp_val.f = stringify_formula(val.formula,range,val.cell,supbooks);
+							if(temp_val.XF) try {
+								temp_val.w=SSF.format(temp_val.XF.ifmt||0, temp_val.v);
+								if(opts.cellNF) temp_val.z = SSF._table[temp_val.XF.ifmt||0];
+							} catch(e) { if(opts.WTF) throw e; }
+							addline(val.cell, temp_val);
 					}
 				} break;
 				case 'String': {
 					if(last_formula) {
 						last_formula.val = val;
-						addline(last_formula.cell, {v:last_formula.val, f:stringify_formula(last_formula.formula, range, last_formula.cell, supbooks), ixfe: last_formula.cell.ixfe, t:'s'});
+						temp_val = {v:last_formula.val, ixfe:last_formula.cell.ixfe, t:'s'};
+						temp_val.XF = XFs[temp_val.ixfe];
+						temp_val.f = stringify_formula(last_formula.formula, range, last_formula.cell, supbooks);
+						if(temp_val.XF) try {
+							temp_val.w=SSF.format(temp_val.XF.ifmt||0, temp_val.v);
+							if(opts.cellNF) temp_val.z = SSF._table[temp_val.XF.ifmt||0];
+						} catch(e) { if(opts.WTF) throw e; }
+						addline(last_formula.cell, temp_val);
 						last_formula = null;
 					}
 				} break;
@@ -310,11 +333,22 @@ function parse_workbook(blob) {
 					shared_formulae[last_cell] = val[0];
 				} break;
 				case 'LabelSst': {
-					addline({c:val.c, r:val.r}, {v:sst[val.isst].t, ixfe:val.ixfe, t:'s'});
+					temp_val={v:sst[val.isst].t, ixfe:val.ixfe, t:'s'};
+					temp_val.XF = XFs[temp_val.ixfe];
+					if(temp_val.XF) try {
+						temp_val.w=SSF.format(temp_val.XF.ifmt||0, temp_val.v);
+						if(opts.cellNF) temp_val.z = SSF._table[temp_val.XF.ifmt||0];
+					} catch(e) { if(opts.WTF) throw e; }
+					addline({c:val.c, r:val.r}, temp_val);
 				} break;
 				case 'Label': {
 					/* Some writers erroneously write Label */
-					addline({c:val.c, r:val.r}, {v:val.val, ixfe:val.ixfe, t:'s'});
+					temp_val = {v:val.val, ixfe:val.ixfe, XF:XFs[val.ixfe], t:'s'};
+					if(temp_val.XF) try {
+						temp_val.w=SSF.format(temp_val.XF.ifmt||0, temp_val.v);
+						if(opts.cellNF) temp_val.z = SSF._table[temp_val.XF.ifmt||0];
+					} catch(e) { if(opts.WTF) throw e; }
+					addline({c:val.c, r:val.r}, temp_val);
 				} break;
 				case 'Dimensions': {
 					range = val;
@@ -480,7 +514,7 @@ function parse_workbook(blob) {
 	if(opts.enc) wb.Encryption = opts.enc;
 	return wb;
 }
-if(Workbook) WorkbookP = parse_workbook(Workbook.content);
+if(Workbook) WorkbookP = parse_workbook(Workbook.content, options);
 else throw new Error("Cannot find Workbook stream");
 if(CompObj) CompObjP = parse_compobj(CompObj);
 
@@ -563,6 +597,7 @@ function get_formulae(ws) {
 		var x = ws[y];
 		var val = "";
 		if(x.f) val = x.f;
+		else if(typeof x.w !== 'undefined') val = "'" + x.w;
 		else if(typeof x.v === 'number') val = x.v;
 		else val = x.v;
 		cmds.push(y + "=" + val);
@@ -588,6 +623,6 @@ var utils = {
 };
 
 function xlsread(f, options) {
-	return parse_xlscfb(CFB.read(f, options));
+	return parse_xlscfb(CFB.read(f, options), options);
 }
-var readFile = function(f) { return parse_xlscfb(CFB.read(f, {type:'file'})); };
+var readFile = function(f,o){return parse_xlscfb(CFB.read(f,{type:'file'}),o);};

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "xlsjs",
-	"version": "0.6.7",
+	"version": "0.6.8",
 	"author": "sheetjs",
 	"description": "(one day) a full-featured XLS parser and writer.  For now, primitive parser",
 	"keywords": [ "xls", "office", "excel", "spreadsheet" ],

test.js

@@ -3,6 +3,9 @@ var XLS;
 var fs = require('fs'), assert = require('assert');
 describe('source',function(){ it('should load', function(){ XLS = require('./'); });});
 
+var opts = {};
+if(process.env.WTF) opts.WTF = true;
+
 var files = (fs.existsSync('tests.lst') ? fs.readFileSync('tests.lst', 'utf-8').split("\n") : fs.readdirSync('test_files')).filter(function(x){return x.substr(-4)==".xls" || x.substr(-8)==".xls.b64";});
 
 /* Excel enforces 31 character sheet limit, although technical file limit is 255 */
@@ -64,17 +67,72 @@ function parsetest(x, wb) {
 describe('should parse test files', function() {
 	files.forEach(function(x) {
 		it(x, x.substr(-8) == ".pending" ? null : function() {
-			var wb = x.substr(-4) == ".b64" ? XLS.read(fs.readFileSync(dir + x, 'utf8'), {type: 'base64'}) : XLS.readFile(dir + x);
+			var wb = x.substr(-4) == ".b64" ? XLS.read(fs.readFileSync(dir + x, 'utf8'), {type: 'base64'}) : XLS.readFile(dir + x, opts);
 			if(x.substr(-4) === ".xls") parsetest(x, wb);
 		});
 	});
 });
 
-describe('other features', function() {
+describe('options', function() {
+	before(function() {
+		XLS = require('./');
+	});
+	describe('cell', function() {
+		it('should generate formulae by default', function() {
+			var wb = XLS.readFile(dir + 'formula_stress_test.xls');
+			var found = false;
+			wb.SheetNames.forEach(function(s) {
+				var ws = wb.Sheets[s];
+				Object.keys(ws).forEach(function(addr) {
+					if(addr[0] === "!" || !ws.hasOwnProperty(addr)) return;
+					if(typeof ws[addr].f !== 'undefined') return found = true;
+				});
+			});
+			assert(found);
+		});
+		it('should not generate number formats by default', function() {
+			var wb = XLS.readFile(dir+'number_format.xls');
+			wb.SheetNames.forEach(function(s) {
+				var ws = wb.Sheets[s];
+				Object.keys(ws).forEach(function(addr) {
+					if(addr[0] === "!" || !ws.hasOwnProperty(addr)) return;
+					assert(typeof ws[addr].z === 'undefined');
+				});
+			});
+		});
+		it('should generate number formats when requested', function() {
+			var wb = XLS.readFile(dir+'number_format.xls', {cellNF: true});
+			wb.SheetNames.forEach(function(s) {
+				var ws = wb.Sheets[s];
+				Object.keys(ws).forEach(function(addr) {
+					if(addr[0] === "!" || !ws.hasOwnProperty(addr)) return;
+					assert(typeof ws[addr].t!== 'n' || typeof ws[addr].z !== 'undefined');
+				});
+			});
+		});
+	});
+});
+
+describe('input formats', function() {
+	it('should read binary strings', function() {
+		XLS.read(fs.readFileSync(dir+'formula_stress_test.xls', 'binary'), {type:'binary'});
+	});
+	it('should read base64 strings', function() {
+		XLS.read(fs.readFileSync(dir+'comments_stress_test.xls', 'base64'), {type: 'base64'});
+	});
+});
+
+describe('invalid files', function() {
 	it('should fail on passwords', function() {
 		assert.throws(function() { XLS.readFile(dir + 'apachepoi_password.xls'); });
 	});
-	it('should read binary strings', function() {
-		XLS.read(fs.readFileSync(dir + 'formula_stress_test.xls', 'binary'), {type:'binary'});
+	it('should fail on XLSX files', function() {
+		assert.throws(function() { XLS.readFile(dir + 'roo_type_excelx.xls'); });
+	});
+	it('should fail on ODS files', function() {
+		assert.throws(function() { XLS.readFile(dir + 'roo_type_openoffice.xls');});
+	});
+	it('should fail on DOC files', function() {
+		assert.throws(function() { XLS.readFile(dir + 'word_doc.doc');});
 	});
 });

tests.lst

@@ -309,6 +309,7 @@ apachepoi_unicodeNameRecord.xls
 apachepoi_xor-encryption-abc.xls.pending
 apachepoi_yearfracExamples.xls
 comments_stress_test.xls
+custom_properties.xls
 formula_stress_test.xls
 jxls-core_array.xls
 jxls-core_beandata.xls
@@ -460,3 +461,4 @@ xlrd_picture_in_cell.xls
 xlrd_profiles.xls
 xlrd_ragged.xls
 xlrd_xf_class.xls
+xlsx-stream-d-date-cell.xls