HTML Write support

- 'html' bookType write format
- basic HTML entity encoding (fixes SheetJS#629 h/t @xkr47)
- HTML string and table merge cell fixes
- doc notes on nodejs streaming

README.md

@@ -29,8 +29,10 @@ with a unified JS representation, and ES3/ES5 browser compatibility back to IE6.
   * [Optional Modules](#optional-modules)
   * [ECMAScript 5 Compatibility](#ecmascript-5-compatibility)
 - [Parsing Workbooks](#parsing-workbooks)
+  * [Note on Streaming Read](#note-on-streaming-read)
 - [Working with the Workbook](#working-with-the-workbook)
 - [Writing Workbooks](#writing-workbooks)
+  * [Streaming Write](#streaming-write)
 - [Interface](#interface)
   * [Parsing functions](#parsing-functions)
   * [Writing functions](#writing-functions)
@@ -298,6 +300,39 @@ function handleFile(e) {
 input_dom_element.addEventListener('change', handleFile, false);
 ```
 
+**Complete examples:**
+
+- <http://oss.sheetjs.com/js-xlsx/> HTML5 File API / Base64 Text / Web Workers
+
+Note that older versions of IE do not support HTML5 File API, so the base64 mode
+is used for testing.  On OSX you can get the base64 encoding with:
+
+```bash
+$ <target_file base64 | pbcopy
+```
+
+On Windows XP and up you can get the base64 encoding using `certutil`:
+
+```cmd
+> certutil -encode target_file target_file.b64
+```
+
+(note: You have to open the file and remove the header and footer lines)
+
+- <http://oss.sheetjs.com/js-xlsx/ajax.html> XMLHttpRequest
+
+### Note on Streaming Read
+
+The most common and interesting formats (XLS, XLSX/M, XLSB, ODS) are ultimately
+ZIP or CFB containers of files.  Neither format puts the directory structure at
+the beginning of the file: ZIP files place the Central Directory records at the
+end of the logical file, while CFB files can place the FAT structure anywhere in
+the file! As a result, to properly handle these formats, a streaming function
+would have to buffer the entire file before commencing.  That belies the
+expectations of streaming, so we do not provide any streaming read API.  If you
+really want to stream, there are node modules like `concat-stream` that will do
+the buffering for you.
+
 ## Working with the Workbook
 
 The full object format is described later in this README.
@@ -320,25 +355,6 @@ var desired_value = (desired_cell ? desired_cell.v : undefined);
 
 **Complete examples:**
 
-- <http://oss.sheetjs.com/js-xlsx/> HTML5 File API / Base64 Text / Web Workers
-
-Note that older versions of IE do not support HTML5 File API, so the base64 mode
-is used for testing.  On OSX you can get the base64 encoding with:
-
-```bash
-$ <target_file base64 | pbcopy
-```
-
-On Windows XP and up you can get the base64 encoding using `certutil`:
-
-```cmd
-> certutil -encode target_file target_file.b64
-```
-
-(note: You have to open the file and remove the header and footer lines)
-
-- <http://oss.sheetjs.com/js-xlsx/ajax.html> XMLHttpRequest
-
 - <https://github.com/SheetJS/js-xlsx/blob/master/bin/xlsx.njs> node
 
 The node version installs a command line tool `xlsx` which can read spreadsheet
@@ -392,6 +408,12 @@ saveAs(new Blob([s2ab(wbout)],{type:"application/octet-stream"}), "test.xlsx");
 - <http://git.io/WEK88Q> writing an array of arrays in nodejs
 - <http://sheetjs.com/demos/table.html> exporting an HTML table
 
+### Streaming Write
+
+`XLSX.stream.to_csv` is the streaming version of `XLSX.utils.sheet_to_csv`.  It
+takes the same arguments but returns a readable stream.
+
+<https://github.com/sheetjs/sheetaki> pipes CSV write stream to nodejs response.
 ## Interface
 
 `XLSX` is the exposed variable in the browser and the exported node variable
@@ -769,7 +791,7 @@ worksheet['C1'] = { t:'n', f: "SUM(A1:A3*B1:B3)", F:"C1:C1" };
 ```
 
 For a multi-cell array formula, every cell has the same array range but only the
-first cell has content.  Consider `D1:D3=A1:A3*B1:B3`:
+first cell specifies the formula.  Consider `D1:D3=A1:A3*B1:B3`:
 
 ```js
 worksheet['D1'] = { t:'n', F:"D1:D3", f:"A1:A3*B1:B3" };
@@ -977,7 +999,8 @@ Plaintext format guessing follows the priority order:
 
 | Format | Test                                                                |
 |:-------|:--------------------------------------------------------------------|
-| XML    | starts with <                                                       |
+| HTML   | starts with \<html                                                  |
+| XML    | starts with \<                                                      |
 | DSV    | starts with `/sep=.$/`, separator is the specified character        |
 | TSV    | one of the first 1024 characters is a tab char `"\t"`               |
 | CSV    | one of the first 1024 characters is a comma char `","`              |
@@ -1024,6 +1047,7 @@ output formats.  The specific file type is controlled with `bookType` option:
 | `csv`    | `.csv`   |   none    | single | Comma Separated Values            |
 | `txt`    | `.txt`   |   none    | single | UTF-16 Unicode Text (TXT)         |
 | `sylk`   | `.sylk`  |   none    | single | Symbolic Link (SYLK)              |
+| `html`   | `.html`  |   none    | single | HTML Document                     |
 | `dif`    | `.dif`   |   none    | single | Data Interchange Format (DIF)     |
 | `prn`    | `.prn`   |   none    | single | Lotus Formatted Text              |
 
@@ -1277,7 +1301,7 @@ Despite the library name `xlsx`, it supports numerous spreadsheet file formats:
 | Lotus 1-2-3 (WKS/WK1/WK2/WK3/WK4/123)                        |  :o:  |       |
 | Quattro Pro Spreadsheet (WQ1/WQ2/WB1/WB2/WB3/QPW)            |  :o:  |       |
 | **Other Common Spreadsheet Output Formats**                  |:-----:|:-----:|
-| HTML Tables                                                  |  :o:  |       |
+| HTML Tables                                                  |  :o:  |  :o:  |
 
 ### Excel 2007+ XML (XLSX/XLSM)
 

bin/xlsx.njs

@@ -27,6 +27,7 @@ program
 	.option('-j, --json', 'emit formatted JSON (all fields text)')
 	.option('-J, --raw-js', 'emit raw JS object (raw numbers)')
 	.option('-A, --arrays', 'emit rows as JS objects (raw numbers)')
+	.option('-H, --html', 'emit HTML')
 	.option('-D, --dif', 'emit data interchange format (dif)')
 	.option('-K, --sylk', 'emit symbolic link (sylk)')
 	.option('-P, --prn', 'emit formatted text (prn)')
@@ -160,6 +161,7 @@ if(program.readOnly) process.exit(0);
 [
 	['biff2', '.xls'],
 	['sylk', '.slk'],
+	['html', '.html'],
 	['prn', '.prn'],
 	['txt', '.txt'],
 	['dif', '.dif']

bits/22_xmlutils.js

@@ -1,4 +1,4 @@
-var attregexg=/([^\s?>\/]+)=((?:")([^"]*)(?:")|(?:')([^']*)(?:'))/g;
+var attregexg=/([^"\s?>\/]+)=((?:")([^"]*)(?:")|(?:')([^']*)(?:')|([^'">\s]+))/g;
 var tagregex=/<[^>]*>/g;
 var nsregex=/<\w*:/, nsregex2 = /<(\/?)\w+:/;
 function parsexmltag(tag/*:string*/, skip_root/*:?boolean*/)/*:any*/ {
@@ -7,11 +7,13 @@ function parsexmltag(tag/*:string*/, skip_root/*:?boolean*/)/*:any*/ {
 	for(; eq !== tag.length; ++eq) if((c = tag.charCodeAt(eq)) === 32 || c === 10 || c === 13) break;
 	if(!skip_root) z[0] = tag.substr(0, eq);
 	if(eq === tag.length) return z;
-	var m = tag.match(attregexg), j=0, v="", i=0, q="", cc="";
+	var m = tag.match(attregexg), j=0, v="", i=0, q="", cc="", quot = 1;
 	if(m) for(i = 0; i != m.length; ++i) {
 		cc = m[i];
 		for(c=0; c != cc.length; ++c) if(cc.charCodeAt(c) === 61) break;
-		q = cc.substr(0,c); v = cc.substring(c+2, cc.length-1);
+		q = cc.substr(0,c);
+		quot = ((eq=cc.charCodeAt(c+1)) == 34 || eq == 39) ? 1 : 0;
+		v = cc.substring(c+1+quot, cc.length-quot);
 		for(j=0;j!=q.length;++j) if(q.charCodeAt(j) === 58) break;
 		if(j===q.length) {
 			if(q.indexOf("_") > 0) q = q.substr(0, q.indexOf("_")); // from ods
@@ -54,9 +56,10 @@ function escapexml(text/*:string*/, xml/*:?boolean*/)/*:string*/{
 }
 function escapexmltag(text/*:string*/)/*:string*/{ return escapexml(text).replace(/ /g,"_x0020_"); }
 
+var htmlcharegex = /[\u0000-\u001f]/g;
 function escapehtml(text){
 	var s = text + '';
-	return s.replace(decregex, function(y) { return rencoding[y]; });
+	return s.replace(decregex, function(y) { return rencoding[y]; }).replace(htmlcharegex,function(s) { return "&#x" + ("000"+s.charCodeAt(0).toString(16)).slice(-4) + ";"; });
 }
 
 /* TODO: handle codepages */

bits/41_lotus.js

@@ -28,7 +28,7 @@ var WK_ = (function() {
 		if(!d) return d;
 		var o = opts || {};
 		if(DENSE != null && o.dense == null) o.dense = DENSE;
-		var s = (o.dense ? [] : {}), n = "Sheet1", sidx = 0;
+		var s/*:Worksheet*/ = ((o.dense ? [] : {})/*:any*/), n = "Sheet1", sidx = 0;
 		var sheets = {}, snames = [n];
 
 		var refguess = {s: {r:0, c:0}, e: {r:0, c:0} };

bits/43_sstbin.js

@@ -22,8 +22,8 @@ function parse_sst_bin(data, opts)/*:SST*/ {
 				pass = false; break;
 
 			default:
-				if(R_n.indexOf("Begin") > 0) state.push(R_n);
-				else if(R_n.indexOf("End") > 0) state.pop();
+				if(R_n.indexOf("Begin") > 0){}
+				else if(R_n.indexOf("End") > 0){}
 				if(!pass || opts.WTF) throw new Error("Unexpected record " + RT + " " + R_n);
 		}
 	});

bits/61_fcommon.js

@@ -1,7 +1,7 @@
 /* TODO: it will be useful to parse the function str */
 var rc_to_a1 = (function(){
 	var rcregex = /(^|[^A-Za-z])R(\[?)(-?\d+|)\]?C(\[?)(-?\d+|)\]?/g;
-	var rcbase;
+	var rcbase/*:Cell*/ = ({r:0,c:0}/*:any*/);
 	function rcfunc($$,$1,$2,$3,$4,$5) {
 		var R = $3.length>0?parseInt($3,10)|0:0, C = $5.length>0?parseInt($5,10)|0:0;
 		if(C<0 && $4.length === 0) C=0;
@@ -10,7 +10,7 @@ var rc_to_a1 = (function(){
 		if($2.length > 0 || $3.length == 0) rRel = true; if(rRel) R += rcbase.r; else --R;
 		return $1 + (cRel ? "" : "$") + encode_col(C) + (rRel ? "" : "$") + encode_row(R);
 	}
-	return function rc_to_a1(fstr, base) {
+	return function rc_to_a1(fstr/*:string*/, base/*:Cell*/)/*:string*/ {
 		rcbase = base;
 		return fstr.replace(rcregex, rcfunc);
 	};

bits/72_wbxml.js

@@ -160,6 +160,8 @@ function write_wb_xml(wb/*:Workbook*/, opts/*:?WriteOpts*/)/*:string*/ {
 	var o = [XML_HEADER];
 	o[o.length] = WB_XML_ROOT;
 
+	var write_names = (wb.Workbook && (wb.Workbook.Names||[]).length > 0);
+
 	/* fileVersion */
 	/* fileSharing */
 
@@ -185,9 +187,9 @@ function write_wb_xml(wb/*:Workbook*/, opts/*:?WriteOpts*/)/*:string*/ {
 	/* functionGroups */
 	/* externalReferences */
 
-	if(wb.Workbook && (wb.Workbook.Names||[]).length > 0) {
+	if(write_names) {
 		o[o.length] = "<definedNames>";
-		wb.Workbook.Names.forEach(function(n) {
+		if(wb.Workbook && wb.Workbook.Names) wb.Workbook.Names.forEach(function(n) {
 			var d = {name:n.Name};
 			if(n.Comment) d.comment = n.Comment;
 			if(n.Sheet != null) d.localSheetId = ""+n.Sheet;

bits/75_xlml.js

@@ -171,7 +171,7 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ {
 	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));
-	if(str.substr(0,1000).indexOf("<html") >= 0) return parse_html(str, opts);
+	if(str.substr(0,1000).indexOf("<html") >= 0) return HTML_.to_workbook(str, opts);
 	var Rn;
 	var state = [], tmp;
 	if(DENSE != null && opts.dense == null) opts.dense = DENSE;

bits/79_html.js

@@ -1,46 +1,93 @@
 /* TODO: in browser attach to DOM; in node use an html parser */
-function parse_html(str/*:string*/, _opts)/*:Workbook*/ {
-	var opts = _opts || {};
-	if(DENSE != null && opts.dense == null) opts.dense = DENSE;
-	var ws/*:Worksheet*/ = opts.dense ? ([]/*:any*/) : ({}/*:any*/);
-	var o/*:Workbook*/ = { SheetNames: ["Sheet1"], Sheets: {Sheet1:ws} };
-	var i = str.indexOf("<table"), j = str.indexOf("</table");
-	if(i == -1 || j == -1) throw new Error("Invalid HTML: missing <table> / </table> pair");
-	var rows = str.slice(i, j).split(/<tr[^>]*>/);
-	var R = 0, C = 0;
-	var range = {s:{r:10000000, c:10000000},e:{r:0,c:0}};
-	for(i = 0; i < rows.length; ++i) {
-		if(rows[i].substr(0,3) != "<td") continue;
-		var cells = rows[i].split("</td>");
-		for(j = 0; j < cells.length; ++j) {
-			if(cells[j].substr(0,3) != "<td") continue;
-			++C;
-			var m = cells[j], cc = 0;
-			/* TODO: parse styles etc */
-			while(m.charAt(0) == "<" && (cc = m.indexOf(">")) > -1) m = m.slice(cc+1);
-			while(m.indexOf(">") > -1) m = m.slice(0, m.lastIndexOf("<"));
-			/* TODO: generate stub cells */
-			if(!m.length) continue;
-			if(range.s.r > R) range.s.r = R;
-			if(range.e.r < R) range.e.r = R;
-			if(range.s.c > C) range.s.c = C;
-			if(range.e.c < C) range.e.c = C;
-			if(opts.dense) {
-				if(!ws[R]) ws[R] = [];
-				if(Number(m) == Number(m)) ws[R][C] = {t:'n', v:+m};
-				else ws[R][C] = {t:'s', v:m};
-			} else {
-				var coord/*:string*/ = encode_cell({r:R, c:C});
-				/* TODO: value parsing */
-				if(Number(m) == Number(m)) ws[coord] = {t:'n', v:+m};
-				else ws[coord] = {t:'s', v:m};
+var HTML_ = (function() {
+	function html_to_sheet(str/*:string*/, _opts)/*:Workbook*/ {
+		var opts = _opts || {};
+		if(DENSE != null && opts.dense == null) opts.dense = DENSE;
+		var ws/*:Worksheet*/ = opts.dense ? ([]/*:any*/) : ({}/*:any*/);
+		var i = str.indexOf("<table"), j = str.indexOf("</table");
+		if(i == -1 || j == -1) throw new Error("Invalid HTML: missing <table> / </table> pair");
+		var rows = str.slice(i, j).split(/(:?<tr[^>]*>)/);
+		var R = -1, C = 0, RS = 0, CS = 0;
+		var range = {s:{r:10000000, c:10000000},e:{r:0,c:0}};
+		var merges = [], midx = 0;
+		for(i = 0; i < rows.length; ++i) {
+			var row = rows[i].trim();
+			if(row.substr(0,3) == "<tr") { ++R; C = 0; continue; }
+			if(row.substr(0,3) != "<td") continue;
+			var cells = row.split("</td>");
+			for(j = 0; j < cells.length; ++j) {
+				var cell = cells[j].trim();
+				if(cell.substr(0,3) != "<td") continue;
+				var m = cell, cc = 0;
+				/* TODO: parse styles etc */
+				while(m.charAt(0) == "<" && (cc = m.indexOf(">")) > -1) m = m.slice(cc+1);
+				while(m.indexOf(">") > -1) m = m.slice(0, m.lastIndexOf("<"));
+				var tag = parsexmltag(cell.slice(0, cell.indexOf(">")));
+				CS = tag.colspan ? +tag.colspan : 1;
+				if((RS = +tag.rowspan)>0 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
+				/* TODO: generate stub cells */
+				if(!m.length) { C += CS; continue; }
+				m = unescapexml(m).replace(/[\r\n]/g,"");
+				if(range.s.r > R) range.s.r = R;
+				if(range.e.r < R) range.e.r = R;
+				if(range.s.c > C) range.s.c = C;
+				if(range.e.c < C) range.e.c = C;
+				if(opts.dense) {
+					if(!ws[R]) ws[R] = [];
+					if(Number(m) == Number(m)) ws[R][C] = {t:'n', v:+m};
+					else ws[R][C] = {t:'s', v:m};
+				} else {
+					var coord/*:string*/ = encode_cell({r:R, c:C});
+					/* TODO: value parsing */
+					if(Number(m) == Number(m)) ws[coord] = {t:'n', v:+m};
+					else ws[coord] = {t:'s', v:m};
+				}
+				C += CS;
 			}
 		}
-		++R; C = 0;
+		ws['!ref'] = encode_range(range);
+		return ws;
 	}
-	ws['!ref'] = encode_range(range);
-	return o;
-}
+	function html_to_book(str/*:string*/, opts)/*:Workbook*/ {
+		return sheet_to_workbook(html_to_sheet(str, opts), opts);
+	}
+	function sheet_to_html(ws/*:Worksheet*/, opts)/*:string*/ {
+		var o/*:Array<string>*/ = [];
+		var r = decode_range(ws['!ref']), cell/*:Cell*/;
+		var dense = Array.isArray(ws);
+		var M = (ws['!merges'] ||[]);
+		for(var R = r.s.r; R <= r.e.r; ++R) {
+			var oo = [];
+			for(var C = r.s.c; C <= r.e.c; ++C) {
+				var RS = 0, CS = 0;
+				for(var j = 0; j < M.length; ++j) {
+					if(M[j].s.r > R || M[j].s.c > C) continue;
+					if(M[j].e.r < R || M[j].e.c < C) continue;
+					if(M[j].s.r < R || M[j].s.c < C) { RS = -1; break; }
+					RS = M[j].e.r - M[j].s.r + 1; CS = M[j].e.c - M[j].s.c + 1; break;
+				}
+				if(RS < 0) continue;
+				var coord = encode_cell({r:R,c:C});
+				cell = dense ? (ws[R]||[])[C] : ws[coord];
+				if(!cell || cell.v == null) { oo.push("<td></td>"); continue; }
+				/* TODO: html entities */
+				var w = cell.h || escapexml(cell.w || (format_cell(cell), cell.w) || "");
+				var sp = {};
+				if(RS > 1) sp.rowspan = RS;
+				if(CS > 1) sp.colspan = CS;
+				oo.push(writextag('td', w, sp));
+			}
+			o.push("<tr>" + oo.join("") + "</tr>");
+		}
+		return "<html><body><table>" + o.join("") + "</table></body></html>";
+	}
+
+	return {
+		to_workbook: html_to_book,
+		to_sheet: html_to_sheet,
+		from_sheet: sheet_to_html
+	};
+})();
 
 function parse_dom_table(table/*:HTMLElement*/, _opts/*:?any*/)/*:Worksheet*/ {
 	var opts = _opts || {};
@@ -61,7 +108,7 @@ function parse_dom_table(table/*:HTMLElement*/, _opts/*:?any*/)/*:Worksheet*/ {
 			}
 			/* TODO: figure out how to extract nonstandard mso- style */
 			CS = +elt.getAttribute("colspan") || 1;
-			if((RS = +elt.getAttribute("rowspan"))>0) merges.push({s:{r:R,c:C},e:{r:R + RS - 1, c:C + CS - 1}});
+			if((RS = +elt.getAttribute("rowspan"))>0 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
 			var o = {t:'s', v:v};
 			if(v != null && v.length && !isNaN(Number(v))) o = {t:'n', v:Number(v)};
 			if(opts.dense) { if(!ws[R]) ws[R] = []; ws[R][C] = o; }

bits/82_sheeter.js

@@ -8,6 +8,7 @@ function write_obj_str(factory/*:WriteObjStrFactory*/) {
 	};
 }
 
+var write_htm_str = write_obj_str(HTML_);
 var write_csv_str = write_obj_str({from_sheet:sheet_to_csv});
 var write_slk_str = write_obj_str(SYLK);
 var write_dif_str = write_obj_str(DIF);