forked from sheetjs/sheetjs
		
	- browser shim updated (h/t @wintersm for discovering this) - smart tag ignores (h/t @lostinplace) - sheet_to_row_object_array bugfix (fixes #80, h/t @ChrisBurkeBSD) - README improved - baltic and vietnamese codepages: updated codepage to 1.3.4 - iOS Numbers can handle inline strings -> disabling SST by default - avoid Buffer accessors (see https://github.com/joyent/node/issues/7809) - caching certain hot regexes
		
			
				
	
	
		
			161 lines
		
	
	
		
			6.1 KiB
		
	
	
	
		
			JavaScript
		
	
	
	
	
	
			
		
		
	
	
			161 lines
		
	
	
		
			6.1 KiB
		
	
	
	
		
			JavaScript
		
	
	
	
	
	
| var attregexg=/\b[\w:]+=["'][^"]*['"]/g;
 | |
| var tagregex=/<[^>]*>/g;
 | |
| var nsregex=/<\w*:/, nsregex2 = /<(\/?)\w+:/;
 | |
| function parsexmltag(tag, skip_root) {
 | |
| 	var z = [];
 | |
| 	var eq = 0, c = 0;
 | |
| 	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, w="", v="", i=0, q="", cc="";
 | |
| 	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);
 | |
| 		for(j=0;j!=q.length;++j) if(q.charCodeAt(j) === 58) break;
 | |
| 		if(j===q.length) z[q] = v;
 | |
| 		else z[(j===5 && q.substr(0,5)==="xmlns"?"xmlns":"")+q.substr(j+1)] = v;
 | |
| 	}
 | |
| 	return z;
 | |
| }
 | |
| function strip_ns(x) { return x.replace(nsregex2, "<$1"); }
 | |
| 
 | |
| var encodings = {
 | |
| 	'"': '"',
 | |
| 	''': "'",
 | |
| 	'>': '>',
 | |
| 	'<': '<',
 | |
| 	'&': '&'
 | |
| };
 | |
| var rencoding = evert(encodings);
 | |
| var rencstr = "&<>'\"".split("");
 | |
| 
 | |
| // TODO: CP remap (need to read file version to determine OS)
 | |
| var encregex = /&[a-z]*;/g, coderegex = /_x([\da-fA-F]+)_/g;
 | |
| function unescapexml(text){
 | |
| 	var s = text + '';
 | |
| 	return s.replace(encregex, function($$) { return encodings[$$]; }).replace(coderegex,function(m,c) {return String.fromCharCode(parseInt(c,16));});
 | |
| }
 | |
| var decregex=/[&<>'"]/g, charegex = /[\u0000-\u0008\u000b-\u001f]/g;
 | |
| function escapexml(text){
 | |
| 	var s = text + '';
 | |
| 	return s.replace(decregex, function(y) { return rencoding[y]; }).replace(charegex,function(s) { return "_x" + ("000"+s.charCodeAt(0).toString(16)).substr(-4) + "_";});
 | |
| }
 | |
| 
 | |
| function parsexmlbool(value, tag) {
 | |
| 	switch(value) {
 | |
| 		case '1': case 'true': case 'TRUE': return true;
 | |
| 		/* case '0': case 'false': case 'FALSE':*/
 | |
| 		default: return false;
 | |
| 	}
 | |
| }
 | |
| 
 | |
| var utf8read = function utf8reada(orig) {
 | |
| 	var out = "", i = 0, c = 0, d = 0, e = 0, f = 0, w = 0;
 | |
| 	while (i < orig.length) {
 | |
| 		c = orig.charCodeAt(i++);
 | |
| 		if (c < 128) { out += String.fromCharCode(c); continue; }
 | |
| 		d = orig.charCodeAt(i++);
 | |
| 		if (c>191 && c<224) { out += String.fromCharCode(((c & 31) << 6) | (d & 63)); continue; }
 | |
| 		e = orig.charCodeAt(i++);
 | |
| 		if (c < 240) { out += String.fromCharCode(((c & 15) << 12) | ((d & 63) << 6) | (e & 63)); continue; }
 | |
| 		f = orig.charCodeAt(i++);
 | |
| 		w = (((c & 7) << 18) | ((d & 63) << 12) | ((e & 63) << 6) | (f & 63))-65536;
 | |
| 		out += String.fromCharCode(0xD800 + ((w>>>10)&1023));
 | |
| 		out += String.fromCharCode(0xDC00 + (w&1023));
 | |
| 	}
 | |
| 	return out;
 | |
| };
 | |
| 
 | |
| 
 | |
| if(has_buf) {
 | |
| 	var utf8readb = function utf8readb(data) {
 | |
| 		var out = new Buffer(2*data.length), w, i, j = 1, k = 0, ww=0, c;
 | |
| 		for(i = 0; i < data.length; i+=j) {
 | |
| 			j = 1;
 | |
| 			if((c=data.charCodeAt(i)) < 128) w = c;
 | |
| 			else if(c < 224) { w = (c&31)*64+(data.charCodeAt(i+1)&63); j=2; }
 | |
| 			else if(c < 240) { w=(c&15)*4096+(data.charCodeAt(i+1)&63)*64+(data.charCodeAt(i+2)&63); j=3; }
 | |
| 			else { j = 4;
 | |
| 				w = (c & 7)*262144+(data.charCodeAt(i+1)&63)*4096+(data.charCodeAt(i+2)&63)*64+(data.charCodeAt(i+3)&63);
 | |
| 				w -= 65536; ww = 0xD800 + ((w>>>10)&1023); w = 0xDC00 + (w&1023);
 | |
| 			}
 | |
| 			if(ww !== 0) { out[k++] = ww&255; out[k++] = ww>>>8; ww = 0; }
 | |
| 			out[k++] = w%256; out[k++] = w>>>8;
 | |
| 		}
 | |
| 		out.length = k;
 | |
| 		return out.toString('ucs2');
 | |
| 	};
 | |
| 	var corpus = "foo bar baz\u00e2\u0098\u0083\u00f0\u009f\u008d\u00a3";
 | |
| 	if(utf8read(corpus) == utf8readb(corpus)) utf8read = utf8readb;
 | |
| 	var utf8readc = function utf8readc(data) { return Buffer(data, 'binary').toString('utf8'); };
 | |
| 	if(utf8read(corpus) == utf8readc(corpus)) utf8read = utf8readc;
 | |
| }
 | |
| 
 | |
| // matches <foo>...</foo> extracts content
 | |
| var matchtag = (function() {
 | |
| 	var mtcache = {};
 | |
| 	return function matchtag(f,g) {
 | |
| 		var t = f+"|"+g;
 | |
| 		if(mtcache[t] !== undefined) return mtcache[t];
 | |
| 		return (mtcache[t] = new RegExp('<(?:\\w+:)?'+f+'(?: xml:space="preserve")?(?:[^>]*)>([^\u2603]*)</(?:\\w+:)?'+f+'>',(g||"")));
 | |
| 	};
 | |
| })();
 | |
| 
 | |
| 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') );
 | |
| };})();
 | |
| var vtvregex = /<\/?vt:variant>/g, vtmregex = /<vt:([^>]*)>(.*)</;
 | |
| function parseVector(data) {
 | |
| 	var h = parsexmltag(data);
 | |
| 
 | |
| 	var matches = data.match(vtregex(h.baseType))||[];
 | |
| 	if(matches.length != h.size) throw "unexpected vector length " + matches.length + " != " + h.size;
 | |
| 	var res = [];
 | |
| 	matches.forEach(function(x) {
 | |
| 		var v = x.replace(vtvregex,"").match(vtmregex);
 | |
| 		res.push({v:v[2], t:v[1]});
 | |
| 	});
 | |
| 	return res;
 | |
| }
 | |
| 
 | |
| var wtregex = /(^\s|\s$|\n)/;
 | |
| function writetag(f,g) {return '<' + f + (g.match(wtregex)?' xml:space="preserve"' : "") + '>' + g + '</' + f + '>';}
 | |
| 
 | |
| function wxt_helper(h) { return keys(h).map(function(k) { return " " + k + '="' + h[k] + '"';}).join(""); }
 | |
| function writextag(f,g,h) { return '<' + f + (isval(h) ? wxt_helper(h) : "") + (isval(g) ? (g.match(wtregex)?' xml:space="preserve"' : "") + '>' + g + '</' + f : "/") + '>';}
 | |
| 
 | |
| function write_w3cdtf(d, t) { try { return d.toISOString().replace(/\.\d*/,""); } catch(e) { if(t) throw e; } }
 | |
| 
 | |
| function write_vt(s) {
 | |
| 	switch(typeof s) {
 | |
| 		case 'string': return writextag('vt:lpwstr', s);
 | |
| 		case 'number': return writextag((s|0)==s?'vt:i4':'vt:r8', String(s));
 | |
| 		case 'boolean': return writextag('vt:bool',s?'true':'false');
 | |
| 	}
 | |
| 	if(s instanceof Date) return writextag('vt:filetime', write_w3cdtf(s));
 | |
| 	throw new Error("Unable to serialize " + s);
 | |
| }
 | |
| 
 | |
| var XML_HEADER = '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>\r\n';
 | |
| var XMLNS = {
 | |
| 	'dc': 'http://purl.org/dc/elements/1.1/',
 | |
| 	'dcterms': 'http://purl.org/dc/terms/',
 | |
| 	'dcmitype': 'http://purl.org/dc/dcmitype/',
 | |
| 	'mx': 'http://schemas.microsoft.com/office/mac/excel/2008/main',
 | |
| 	'r': 'http://schemas.openxmlformats.org/officeDocument/2006/relationships',
 | |
| 	'sjs': 'http://schemas.openxmlformats.org/package/2006/sheetjs/core-properties',
 | |
| 	'vt': 'http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes',
 | |
| 	'xsi': 'http://www.w3.org/2001/XMLSchema-instance',
 | |
| 	'xsd': 'http://www.w3.org/2001/XMLSchema'
 | |
| };
 | |
| 
 | |
| XMLNS.main = [
 | |
| 	'http://schemas.openxmlformats.org/spreadsheetml/2006/main',
 | |
| 	'http://purl.oclc.org/ooxml/spreadsheetml/main',
 | |
| 	'http://schemas.microsoft.com/office/excel/2006/main',
 | |
| 	'http://schemas.microsoft.com/office/excel/2006/2'
 | |
| ];
 |