version bump 0.9.9: basic TXT/CSV read

fixes #489 h/t @vijayst
fixes #617 h/t @ayush000

Makefile

@@ -179,7 +179,7 @@ readme: README.md ## Update README Table of Contents
 	markdown-toc -i README.md
 
 .PHONY: book
-book: readme ## Update summary for documentation
+book: readme graph ## Update summary for documentation
 	printf "# Summary\n\n- [xlsx](README.md#xlsx)\n" > misc/docs/SUMMARY.md
 	markdown-toc README.md | sed 's/(#/(README.md#/g'>> misc/docs/SUMMARY.md
 

README.md

@@ -887,6 +887,10 @@ Plaintext format guessing follows the priority order:
 
 | Format | Test                                                                |
 |:-------|:--------------------------------------------------------------------|
+| 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 `","`              |
 | PRN    | (default)                                                           |
 
 ## Writing Options
@@ -1167,11 +1171,11 @@ Despite the library name `xlsx`, it supports numerous spreadsheet file formats:
 | Excel 3.0 (XLS BIFF3)                                        |  :o:  |       |
 | Excel 2.0/2.1 (XLS BIFF2)                                    |  :o:  |  :o:  |
 | **Excel Supported Text Formats**                             |:-----:|:-----:|
-| Delimiter-Separated Values (CSV/TXT)                         |       |  :o:  |
+| Delimiter-Separated Values (CSV/TXT)                         |  :o:  |  :o:  |
 | Data Interchange Format (DIF)                                |  :o:  |  :o:  |
 | Symbolic Link (SYLK/SLK)                                     |  :o:  |  :o:  |
 | Lotus Formatted Text (PRN)                                   |  :o:  |  :o:  |
-| UTF-16 Unicode Text (TXT)                                    |       |  :o:  |
+| UTF-16 Unicode Text (TXT)                                    |  :o:  |  :o:  |
 | **Other Workbook/Worksheet Formats**                         |:-----:|:-----:|
 | OpenDocument Spreadsheet (ODS)                               |  :o:  |  :o:  |
 | Flat XML ODF Spreadsheet (FODS)                              |  :o:  |  :o:  |
@@ -1243,7 +1247,7 @@ lies in the names of tags and attributes.
 
 Excel CSV deviates from RFC4180 in a number of important ways.  The generated
 CSV files should generally work in Excel although they may not work in RFC4180
-compatible readers.
+compatible readers.  The parser should generally understand Excel CSV.
 
 Excel TXT uses tab as the delimiter and codepage 1200.
 

bits/01_version.js

@@ -1 +1 @@
-XLSX.version = '0.9.8';
+XLSX.version = '0.9.9';

bits/40_harb.js

@@ -369,16 +369,6 @@ var DIF = (function() {
 })();
 
 var PRN = (function() {
-	function prn_to_aoa(d/*:RawData*/, opts)/*:AOA*/ {
-		switch(opts.type) {
-			case 'base64': return prn_to_aoa_str(Base64.decode(d), opts);
-			case 'binary': return prn_to_aoa_str(d, opts);
-			case 'buffer': return prn_to_aoa_str(d.toString('binary'), opts);
-			case 'array': return prn_to_aoa_str(cc2str(d), opts);
-		}
-		throw new Error("Unrecognized type " + opts.type);
-	}
-
 	function set_text_arr(data/*:string*/, arr/*:AOA*/, R/*:number*/, C/*:number*/) {
 		if(data === 'TRUE') arr[R][C] = true;
 		else if(data === 'FALSE') arr[R][C] = false;
@@ -411,7 +401,54 @@ var PRN = (function() {
 		return arr;
 	}
 
-	function prn_to_sheet(str/*:string*/, opts)/*:Worksheet*/ { return aoa_to_sheet(prn_to_aoa(str, opts), opts); }
+	function dsv_to_sheet_str(str/*:string*/, opts)/*:Worksheet*/ {
+		var sep = "";
+		var ws/*:Worksheet*/ = ({}/*:any*/);
+		var range/*:Range*/ = ({s: {c:0, r:0}, e: {c:0, r:0}}/*:any*/);
+
+		/* known sep */
+		if(str.substr(0,4) == "sep=" && str.charCodeAt(5) == 10) { sep = str.charAt(4); str = str.substr(6); }
+		/* TODO: actually determine the separator */
+		if(str.substr(0,1024).indexOf("\t") == -1) sep = ","; else sep = "\t";
+		var R = 0, C = 0, v = 0;
+		var start = 0, end = 0, sepcc = sep.charCodeAt(0), instr = false, cc=0;
+		for(;end < str.length;++end) switch((cc=str.charCodeAt(end))) {
+			case 0x22: instr = !instr; break;
+			case sepcc: case 0x0a: if(instr) break;
+			var s = str.slice(start, end);
+			var cell = ({}/*:any*/)
+			if(s.charCodeAt(0) == 0x3D) { cell.t = 'n'; cell.f = s.substr(1); }
+			else if(s == "TRUE") { cell.t = 'b'; cell.v = true; }
+			else if(s == "FALSE") { cell.t = 'b'; cell.v = false; }
+			else if(!isNaN(v = parseFloat(s))) { cell.t = 'n'; cell.w = s; cell.v = v; }
+			else { cell.t = 's'; cell.v = s.replace(/^"/,"").replace(/"$/,"").replace(/""/g,'"'); }
+			ws[encode_cell({c:C,r:R})] = cell;
+			start = end+1;
+			if(range.e.c < C) range.e.c = C;
+			if(range.e.r < R) range.e.r = R;
+			if(cc == sepcc) ++C; else { C = 0; ++R; }; break;
+			default: break;
+		}
+
+		ws['!ref'] = encode_range(range);
+		return ws;
+	}
+
+	function prn_to_sheet_str(str/*:string*/, opts)/*:Worksheet*/ {
+		if(str.substr(0,4) == "sep=") return dsv_to_sheet_str(str, opts);
+		if(str.indexOf("\t") >= 0 || str.indexOf(",") >= 0) return dsv_to_sheet_str(str, opts);
+		return aoa_to_sheet(prn_to_aoa_str(str, opts), opts);
+	}
+
+	function prn_to_sheet(d/*:RawData*/, opts)/*:Worksheet*/ {
+		switch(opts.type) {
+			case 'base64': return prn_to_sheet_str(Base64.decode(d), opts);
+			case 'binary': return prn_to_sheet_str(d, opts);
+			case 'buffer': return prn_to_sheet_str(d.toString('binary'), opts);
+			case 'array': return prn_to_sheet_str(cc2str(d), opts);
+		}
+		throw new Error("Unrecognized type " + opts.type);
+	}
 
 	function prn_to_workbook(str/*:string*/, opts)/*:Workbook*/ { return sheet_to_workbook(prn_to_sheet(str, opts), opts); }
 

bits/87_read.js

@@ -24,6 +24,15 @@ function read_zip(data/*:RawData*/, opts/*:?ParseOpts*/)/*:Workbook*/ {
 	return parse_zip(zip, o);
 }
 
+function read_utf16(data/*:RawData*/, o/*:ParseOpts*/)/*:Workbook*/ {
+	var d = data;
+	if(o.type == 'base64') d = Base64.decode(d);
+	d = cptable.utils.decode(1200, d.slice(2));
+	o.type = "binary";
+	if(d.charCodeAt(0) == 0x3C) return parse_xlml(d,o);
+	return PRN.to_workbook(d, o);
+}
+
 function readSync(data/*:RawData*/, opts/*:?ParseOpts*/)/*:Workbook*/ {
 	var zip, d = data, n=[0];
 	var o = opts||{};
@@ -37,11 +46,11 @@ function readSync(data/*:RawData*/, opts/*:?ParseOpts*/)/*:Workbook*/ {
 		case 0x54: if(n[1] == 0x41 && n[2] == 0x42 && n[3] == 0x4C) return DIF.to_workbook(d, o); break;
 		case 0x50: if(n[1] == 0x4B && n[2] < 0x20 && n[3] < 0x20) return read_zip(d, o); break;
 		case 0xEF: return parse_xlml(d, o);
+		case 0xFF: if(n[1] == 0xFE){ return read_utf16(d, o); } break;
 		case 0x03: case 0x83: case 0x8B: return DBF.to_workbook(d, o);
 	}
 	if(n[2] <= 12 && n[3] <= 31) return DBF.to_workbook(d, o);
 	if(0x20>n[0]||n[0]>0x7F) throw new Error("Unsupported file " + n.join("|"));
-	/* TODO: CSV / TXT */
 	return PRN.to_workbook(d, o);
 }
 

docbits/80_parseopts.md

@@ -76,5 +76,9 @@ Plaintext format guessing follows the priority order:
 
 | Format | Test                                                                |
 |:-------|:--------------------------------------------------------------------|
+| 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 `","`              |
 | PRN    | (default)                                                           |
 

docbits/85_filetype.md

@@ -14,11 +14,11 @@ Despite the library name `xlsx`, it supports numerous spreadsheet file formats:
 | Excel 3.0 (XLS BIFF3)                                        |  :o:  |       |
 | Excel 2.0/2.1 (XLS BIFF2)                                    |  :o:  |  :o:  |
 | **Excel Supported Text Formats**                             |:-----:|:-----:|
-| Delimiter-Separated Values (CSV/TXT)                         |       |  :o:  |
+| Delimiter-Separated Values (CSV/TXT)                         |  :o:  |  :o:  |
 | Data Interchange Format (DIF)                                |  :o:  |  :o:  |
 | Symbolic Link (SYLK/SLK)                                     |  :o:  |  :o:  |
 | Lotus Formatted Text (PRN)                                   |  :o:  |  :o:  |
-| UTF-16 Unicode Text (TXT)                                    |       |  :o:  |
+| UTF-16 Unicode Text (TXT)                                    |  :o:  |  :o:  |
 | **Other Workbook/Worksheet Formats**                         |:-----:|:-----:|
 | OpenDocument Spreadsheet (ODS)                               |  :o:  |  :o:  |
 | Flat XML ODF Spreadsheet (FODS)                              |  :o:  |  :o:  |
@@ -90,7 +90,7 @@ lies in the names of tags and attributes.
 
 Excel CSV deviates from RFC4180 in a number of important ways.  The generated
 CSV files should generally work in Excel although they may not work in RFC4180
-compatible readers.
+compatible readers.  The parser should generally understand Excel CSV.
 
 Excel TXT uses tab as the delimiter and codepage 1200.
 

formats.dot

@@ -13,15 +13,11 @@ digraph G {
 		xls8  [label="XLS\nBIFF8"];
 	}
 
-	subgraph OD {
-		node  [style=filled,color=yellow];
+	subgraph OLD {
+		node  [style=filled,color=cyan];
 		ods   [label="ODS"];
 		fods  [label="FODS"];
 		uos   [label="UOS"];
-	}
-
-	subgraph OLD {
-		node  [style=filled,color=cyan];
 		html  [label="HTML\nTable"];
 		csv   [label="CSV"];
 		txt   [label="TXT\nUTF-16"];
@@ -59,7 +55,9 @@ digraph G {
 		dif -> csf
 		prn -> csf
 		csf -> prn
+		csv -> csf
 		csf -> csv
+		txt -> csf
 		csf -> txt
 		dbf -> csf
 		html -> csf

misc/legend.dot

@@ -7,16 +7,16 @@ digraph G {
 		label="Supported Format Types"
 		color="white"
 		XL[label="Excel",style=filled,color=green];
-		OD[label="ODF",style=filled,color=yellow];
+		CSF[label="JS",shape=doublecircle];
 		OLD[label="Other",style=filled,color=cyan];
-		{ edge[style=invis] XL -> OD -> OLD[constraint=false]}
+		{ edge[style=invis] XL -> CSF -> OLD[constraint=false]}
 	}
 
 	subgraph cluster_1 {
 		label="Workbook Format Conversions (blue arrow)"
 		color="white"
 		x1i[label="XLSX"]
-		c1[shape=doublecircle,label="CSF"];
+		c1[shape=doublecircle,label="JS"];
 		x1o[label="XLSB"]
 		{ edge[color=blue]
 			x1i->c1[constraint=false,label="read"]
@@ -28,7 +28,7 @@ digraph G {
 		label="Single-Worksheet Format Conversions (green arrow)"
 		color="white"
 		x2i[label="SYLK"]
-		c2[shape=doublecircle,label="CSF"];
+		c2[shape=doublecircle,label="JS"];
 		x2o[label="CSV"]
 		{ edge[color=aquamarine4]
 			x2i->c2[constraint=false,label="read"]
@@ -37,6 +37,6 @@ digraph G {
 	}
 
 	{ edge[style=invis] XL -> x1i -> x2i; }
-	{ edge[style=invis] OD -> c1 -> c2; }
+	{ edge[style=invis] CSF -> c1 -> c2; }
 	{ edge[style=invis] OLD -> x1o -> x2o; }
 }

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "xlsx",
-	"version": "0.9.8",
+	"version": "0.9.9",
 	"author": "sheetjs",
 	"description": "Excel (XLSB/XLSX/XLSM/XLS/XML) and ODS (ODS/FODS/UOS) spreadsheet parser and writer",
 	"keywords": [ "excel", "xls", "xlsx", "xlsb", "xlsm", "ods", "office", "spreadsheet" ],

xlsx.flow.js

@@ -5,7 +5,7 @@
 /*exported XLSX */
 var XLSX = {};
 (function make_xlsx(XLSX){
-XLSX.version = '0.9.8';
+XLSX.version = '0.9.9';
 var current_codepage = 1200, current_cptable;
 /*:: declare var cptable:any; */
 if(typeof module !== "undefined" && typeof require !== 'undefined') {
@@ -5129,16 +5129,6 @@ var DIF = (function() {
 })();
 
 var PRN = (function() {
-	function prn_to_aoa(d/*:RawData*/, opts)/*:AOA*/ {
-		switch(opts.type) {
-			case 'base64': return prn_to_aoa_str(Base64.decode(d), opts);
-			case 'binary': return prn_to_aoa_str(d, opts);
-			case 'buffer': return prn_to_aoa_str(d.toString('binary'), opts);
-			case 'array': return prn_to_aoa_str(cc2str(d), opts);
-		}
-		throw new Error("Unrecognized type " + opts.type);
-	}
-
 	function set_text_arr(data/*:string*/, arr/*:AOA*/, R/*:number*/, C/*:number*/) {
 		if(data === 'TRUE') arr[R][C] = true;
 		else if(data === 'FALSE') arr[R][C] = false;
@@ -5171,7 +5161,54 @@ var PRN = (function() {
 		return arr;
 	}
 
-	function prn_to_sheet(str/*:string*/, opts)/*:Worksheet*/ { return aoa_to_sheet(prn_to_aoa(str, opts), opts); }
+	function dsv_to_sheet_str(str/*:string*/, opts)/*:Worksheet*/ {
+		var sep = "";
+		var ws/*:Worksheet*/ = ({}/*:any*/);
+		var range/*:Range*/ = ({s: {c:0, r:0}, e: {c:0, r:0}}/*:any*/);
+
+		/* known sep */
+		if(str.substr(0,4) == "sep=" && str.charCodeAt(5) == 10) { sep = str.charAt(4); str = str.substr(6); }
+		/* TODO: actually determine the separator */
+		if(str.substr(0,1024).indexOf("\t") == -1) sep = ","; else sep = "\t";
+		var R = 0, C = 0, v = 0;
+		var start = 0, end = 0, sepcc = sep.charCodeAt(0), instr = false, cc=0;
+		for(;end < str.length;++end) switch((cc=str.charCodeAt(end))) {
+			case 0x22: instr = !instr; break;
+			case sepcc: case 0x0a: if(instr) break;
+			var s = str.slice(start, end);
+			var cell = ({}/*:any*/)
+			if(s.charCodeAt(0) == 0x3D) { cell.t = 'n'; cell.f = s.substr(1); }
+			else if(s == "TRUE") { cell.t = 'b'; cell.v = true; }
+			else if(s == "FALSE") { cell.t = 'b'; cell.v = false; }
+			else if(!isNaN(v = parseFloat(s))) { cell.t = 'n'; cell.w = s; cell.v = v; }
+			else { cell.t = 's'; cell.v = s.replace(/^"/,"").replace(/"$/,"").replace(/""/g,'"'); }
+			ws[encode_cell({c:C,r:R})] = cell;
+			start = end+1;
+			if(range.e.c < C) range.e.c = C;
+			if(range.e.r < R) range.e.r = R;
+			if(cc == sepcc) ++C; else { C = 0; ++R; }; break;
+			default: break;
+		}
+
+		ws['!ref'] = encode_range(range);
+		return ws;
+	}
+
+	function prn_to_sheet_str(str/*:string*/, opts)/*:Worksheet*/ {
+		if(str.substr(0,4) == "sep=") return dsv_to_sheet_str(str, opts);
+		if(str.indexOf("\t") >= 0 || str.indexOf(",") >= 0) return dsv_to_sheet_str(str, opts);
+		return aoa_to_sheet(prn_to_aoa_str(str, opts), opts);
+	}
+
+	function prn_to_sheet(d/*:RawData*/, opts)/*:Worksheet*/ {
+		switch(opts.type) {
+			case 'base64': return prn_to_sheet_str(Base64.decode(d), opts);
+			case 'binary': return prn_to_sheet_str(d, opts);
+			case 'buffer': return prn_to_sheet_str(d.toString('binary'), opts);
+			case 'array': return prn_to_sheet_str(cc2str(d), opts);
+		}
+		throw new Error("Unrecognized type " + opts.type);
+	}
 
 	function prn_to_workbook(str/*:string*/, opts)/*:Workbook*/ { return sheet_to_workbook(prn_to_sheet(str, opts), opts); }
 
@@ -15064,6 +15101,15 @@ function read_zip(data/*:RawData*/, opts/*:?ParseOpts*/)/*:Workbook*/ {
 	return parse_zip(zip, o);
 }
 
+function read_utf16(data/*:RawData*/, o/*:ParseOpts*/)/*:Workbook*/ {
+	var d = data;
+	if(o.type == 'base64') d = Base64.decode(d);
+	d = cptable.utils.decode(1200, d.slice(2));
+	o.type = "binary";
+	if(d.charCodeAt(0) == 0x3C) return parse_xlml(d,o);
+	return PRN.to_workbook(d, o);
+}
+
 function readSync(data/*:RawData*/, opts/*:?ParseOpts*/)/*:Workbook*/ {
 	var zip, d = data, n=[0];
 	var o = opts||{};
@@ -15077,11 +15123,11 @@ function readSync(data/*:RawData*/, opts/*:?ParseOpts*/)/*:Workbook*/ {
 		case 0x54: if(n[1] == 0x41 && n[2] == 0x42 && n[3] == 0x4C) return DIF.to_workbook(d, o); break;
 		case 0x50: if(n[1] == 0x4B && n[2] < 0x20 && n[3] < 0x20) return read_zip(d, o); break;
 		case 0xEF: return parse_xlml(d, o);
+		case 0xFF: if(n[1] == 0xFE){ return read_utf16(d, o); } break;
 		case 0x03: case 0x83: case 0x8B: return DBF.to_workbook(d, o);
 	}
 	if(n[2] <= 12 && n[3] <= 31) return DBF.to_workbook(d, o);
 	if(0x20>n[0]||n[0]>0x7F) throw new Error("Unsupported file " + n.join("|"));
-	/* TODO: CSV / TXT */
 	return PRN.to_workbook(d, o);
 }
 

xlsx.js

@@ -5,7 +5,7 @@
 /*exported XLSX */
 var XLSX = {};
 (function make_xlsx(XLSX){
-XLSX.version = '0.9.8';
+XLSX.version = '0.9.9';
 var current_codepage = 1200, current_cptable;
 if(typeof module !== "undefined" && typeof require !== 'undefined') {
 	if(typeof cptable === 'undefined') cptable = require('./dist/cpexcel.js');
@@ -5073,16 +5073,6 @@ var DIF = (function() {
 })();
 
 var PRN = (function() {
-	function prn_to_aoa(d, opts) {
-		switch(opts.type) {
-			case 'base64': return prn_to_aoa_str(Base64.decode(d), opts);
-			case 'binary': return prn_to_aoa_str(d, opts);
-			case 'buffer': return prn_to_aoa_str(d.toString('binary'), opts);
-			case 'array': return prn_to_aoa_str(cc2str(d), opts);
-		}
-		throw new Error("Unrecognized type " + opts.type);
-	}
-
 	function set_text_arr(data, arr, R, C) {
 		if(data === 'TRUE') arr[R][C] = true;
 		else if(data === 'FALSE') arr[R][C] = false;
@@ -5115,7 +5105,54 @@ var PRN = (function() {
 		return arr;
 	}
 
-	function prn_to_sheet(str, opts) { return aoa_to_sheet(prn_to_aoa(str, opts), opts); }
+	function dsv_to_sheet_str(str, opts) {
+		var sep = "";
+		var ws = ({});
+		var range = ({s: {c:0, r:0}, e: {c:0, r:0}});
+
+		/* known sep */
+		if(str.substr(0,4) == "sep=" && str.charCodeAt(5) == 10) { sep = str.charAt(4); str = str.substr(6); }
+		/* TODO: actually determine the separator */
+		if(str.substr(0,1024).indexOf("\t") == -1) sep = ","; else sep = "\t";
+		var R = 0, C = 0, v = 0;
+		var start = 0, end = 0, sepcc = sep.charCodeAt(0), instr = false, cc=0;
+		for(;end < str.length;++end) switch((cc=str.charCodeAt(end))) {
+			case 0x22: instr = !instr; break;
+			case sepcc: case 0x0a: if(instr) break;
+			var s = str.slice(start, end);
+			var cell = ({})
+			if(s.charCodeAt(0) == 0x3D) { cell.t = 'n'; cell.f = s.substr(1); }
+			else if(s == "TRUE") { cell.t = 'b'; cell.v = true; }
+			else if(s == "FALSE") { cell.t = 'b'; cell.v = false; }
+			else if(!isNaN(v = parseFloat(s))) { cell.t = 'n'; cell.w = s; cell.v = v; }
+			else { cell.t = 's'; cell.v = s.replace(/^"/,"").replace(/"$/,"").replace(/""/g,'"'); }
+			ws[encode_cell({c:C,r:R})] = cell;
+			start = end+1;
+			if(range.e.c < C) range.e.c = C;
+			if(range.e.r < R) range.e.r = R;
+			if(cc == sepcc) ++C; else { C = 0; ++R; }; break;
+			default: break;
+		}
+
+		ws['!ref'] = encode_range(range);
+		return ws;
+	}
+
+	function prn_to_sheet_str(str, opts) {
+		if(str.substr(0,4) == "sep=") return dsv_to_sheet_str(str, opts);
+		if(str.indexOf("\t") >= 0 || str.indexOf(",") >= 0) return dsv_to_sheet_str(str, opts);
+		return aoa_to_sheet(prn_to_aoa_str(str, opts), opts);
+	}
+
+	function prn_to_sheet(d, opts) {
+		switch(opts.type) {
+			case 'base64': return prn_to_sheet_str(Base64.decode(d), opts);
+			case 'binary': return prn_to_sheet_str(d, opts);
+			case 'buffer': return prn_to_sheet_str(d.toString('binary'), opts);
+			case 'array': return prn_to_sheet_str(cc2str(d), opts);
+		}
+		throw new Error("Unrecognized type " + opts.type);
+	}
 
 	function prn_to_workbook(str, opts) { return sheet_to_workbook(prn_to_sheet(str, opts), opts); }
 
@@ -14999,6 +15036,15 @@ var zip, d = data;
 	return parse_zip(zip, o);
 }
 
+function read_utf16(data, o) {
+	var d = data;
+	if(o.type == 'base64') d = Base64.decode(d);
+	d = cptable.utils.decode(1200, d.slice(2));
+	o.type = "binary";
+	if(d.charCodeAt(0) == 0x3C) return parse_xlml(d,o);
+	return PRN.to_workbook(d, o);
+}
+
 function readSync(data, opts) {
 	var zip, d = data, n=[0];
 	var o = opts||{};
@@ -15012,11 +15058,11 @@ function readSync(data, opts) {
 		case 0x54: if(n[1] == 0x41 && n[2] == 0x42 && n[3] == 0x4C) return DIF.to_workbook(d, o); break;
 		case 0x50: if(n[1] == 0x4B && n[2] < 0x20 && n[3] < 0x20) return read_zip(d, o); break;
 		case 0xEF: return parse_xlml(d, o);
+		case 0xFF: if(n[1] == 0xFE){ return read_utf16(d, o); } break;
 		case 0x03: case 0x83: case 0x8B: return DBF.to_workbook(d, o);
 	}
 	if(n[2] <= 12 && n[3] <= 31) return DBF.to_workbook(d, o);
 	if(0x20>n[0]||n[0]>0x7F) throw new Error("Unsupported file " + n.join("|"));
-	/* TODO: CSV / TXT */
 	return PRN.to_workbook(d, o);
 }