forked from sheetjs/sheetjs
269 lines
11 KiB
JavaScript
269 lines
11 KiB
JavaScript
var XML_HEADER = '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>\r\n';
|
|
var attregexg=/([^"\s?>\/]+)\s*=\s*((?:")([^"]*)(?:")|(?:')([^']*)(?:')|([^'">\s]+))/g;
|
|
var tagregex=/<[\/\?]?[a-zA-Z0-9:_-]+(?:\s+[^"\s?>\/]+\s*=\s*(?:"[^"]*"|'[^']*'|[^'">\s=]+))*\s?[\/\?]?>/mg;
|
|
|
|
if(!(XML_HEADER.match(tagregex))) tagregex = /<[^>]*>/g;
|
|
var nsregex=/<\w*:/, nsregex2 = /<(\/?)\w+:/;
|
|
function parsexmltag(tag/*:string*/, skip_root/*:?boolean*/, skip_LC/*:?boolean*/)/*:any*/ {
|
|
var z = ({}/*:any*/);
|
|
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.slice(0, eq);
|
|
if(eq === tag.length) return z;
|
|
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.slice(0,c).trim();
|
|
while(cc.charCodeAt(c+1) == 32) ++c;
|
|
quot = ((eq=cc.charCodeAt(c+1)) == 34 || eq == 39) ? 1 : 0;
|
|
v = cc.slice(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.slice(0, q.indexOf("_")); // from ods
|
|
z[q] = v;
|
|
if(!skip_LC) z[q.toLowerCase()] = v;
|
|
}
|
|
else {
|
|
var k = (j===5 && q.slice(0,5)==="xmlns"?"xmlns":"")+q.slice(j+1);
|
|
if(z[k] && q.slice(j-3,j) == "ext") continue; // from ods
|
|
z[k] = v;
|
|
if(!skip_LC) z[k.toLowerCase()] = v;
|
|
}
|
|
}
|
|
return z;
|
|
}
|
|
function strip_ns(x/*:string*/)/*:string*/ { 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 unescapexml/*:StringConv*/ = (function() {
|
|
/* 22.4.2.4 bstr (Basic String) */
|
|
var encregex = /&(?:quot|apos|gt|lt|amp|#x?([\da-fA-F]+));/ig, coderegex = /_x([\da-fA-F]{4})_/ig;
|
|
return function unescapexml(text/*:string*/)/*:string*/ {
|
|
var s = text + '', i = s.indexOf("<![CDATA[");
|
|
if(i == -1) return s.replace(encregex, function($$, $1) { return encodings[$$]||String.fromCharCode(parseInt($1,$$.indexOf("x")>-1?16:10))||$$; }).replace(coderegex,function(m,c) {return String.fromCharCode(parseInt(c,16));});
|
|
var j = s.indexOf("]]>");
|
|
return unescapexml(s.slice(0, i)) + s.slice(i+9,j) + unescapexml(s.slice(j+3));
|
|
};
|
|
})();
|
|
|
|
var decregex=/[&<>'"]/g, charegex = /[\u0000-\u0008\u000b-\u001f]/g;
|
|
function escapexml(text/*:string*/)/*:string*/{
|
|
var s = text + '';
|
|
return s.replace(decregex, function(y) { return rencoding[y]; }).replace(charegex,function(s) { return "_x" + ("000"+s.charCodeAt(0).toString(16)).slice(-4) + "_";});
|
|
}
|
|
function escapexmltag(text/*:string*/)/*:string*/{ return escapexml(text).replace(/ /g,"_x0020_"); }
|
|
|
|
var htmlcharegex = /[\u0000-\u001f]/g;
|
|
function escapehtml(text/*:string*/)/*:string*/{
|
|
var s = text + '';
|
|
return s.replace(decregex, function(y) { return rencoding[y]; }).replace(/\n/g, "<br/>").replace(htmlcharegex,function(s) { return "&#x" + ("000"+s.charCodeAt(0).toString(16)).slice(-4) + ";"; });
|
|
}
|
|
|
|
function escapexlml(text/*:string*/)/*:string*/{
|
|
var s = text + '';
|
|
return s.replace(decregex, function(y) { return rencoding[y]; }).replace(htmlcharegex,function(s) { return "&#x" + (s.charCodeAt(0).toString(16)).toUpperCase() + ";"; });
|
|
}
|
|
|
|
/* TODO: handle codepages */
|
|
var xlml_fixstr/*:StringConv*/ = (function() {
|
|
var entregex = /&#(\d+);/g;
|
|
function entrepl($$/*:string*/,$1/*:string*/)/*:string*/ { return String.fromCharCode(parseInt($1,10)); }
|
|
return function xlml_fixstr(str/*:string*/)/*:string*/ { return str.replace(entregex,entrepl); };
|
|
})();
|
|
var xlml_unfixstr/*:StringConv*/ = (function() {
|
|
return function xlml_unfixstr(str/*:string*/)/*:string*/ { return str.replace(/(\r\n|[\r\n])/g,"\ "); };
|
|
})();
|
|
|
|
function parsexmlbool(value/*:any*/)/*:boolean*/ {
|
|
switch(value) {
|
|
case 1: case true: case '1': case 'true': case 'TRUE': return true;
|
|
/* case '0': case 'false': case 'FALSE':*/
|
|
default: return false;
|
|
}
|
|
}
|
|
|
|
var utf8read/*:StringConv*/ = function utf8reada(orig/*:string*/)/*:string*/ {
|
|
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) { f = ((c & 31) << 6); f |= (d & 63); out += String.fromCharCode(f); 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;
|
|
};
|
|
|
|
var utf8write/*:StringConv*/ = function(orig/*:string*/)/*:string*/ {
|
|
var out/*:Array<string>*/ = [], i = 0, c = 0, d = 0;
|
|
while(i < orig.length) {
|
|
c = orig.charCodeAt(i++);
|
|
switch(true) {
|
|
case c < 128: out.push(String.fromCharCode(c)); break;
|
|
case c < 2048:
|
|
out.push(String.fromCharCode(192 + (c >> 6)));
|
|
out.push(String.fromCharCode(128 + (c & 63)));
|
|
break;
|
|
case c >= 55296 && c < 57344:
|
|
c -= 55296; d = orig.charCodeAt(i++) - 56320 + (c<<10);
|
|
out.push(String.fromCharCode(240 + ((d >>18) & 7)));
|
|
out.push(String.fromCharCode(144 + ((d >>12) & 63)));
|
|
out.push(String.fromCharCode(128 + ((d >> 6) & 63)));
|
|
out.push(String.fromCharCode(128 + (d & 63)));
|
|
break;
|
|
default:
|
|
out.push(String.fromCharCode(224 + (c >> 12)));
|
|
out.push(String.fromCharCode(128 + ((c >> 6) & 63)));
|
|
out.push(String.fromCharCode(128 + (c & 63)));
|
|
}
|
|
}
|
|
return out.join("");
|
|
};
|
|
|
|
if(has_buf) {
|
|
var utf8readb = function utf8readb(data) {
|
|
var out = Buffer.alloc(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;
|
|
}
|
|
return out.slice(0,k).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_from(data, 'binary').toString('utf8'); };
|
|
if(utf8read(corpus) == utf8readc(corpus)) utf8read = utf8readc;
|
|
|
|
utf8write = function(data) { return Buffer_from(data, 'utf8').toString("binary"); };
|
|
}
|
|
|
|
// matches <foo>...</foo> extracts content
|
|
var matchtag = (function() {
|
|
var mtcache/*:{[k:string]:RegExp}*/ = ({}/*:any*/);
|
|
return function matchtag(f/*:string*/,g/*:?string*/)/*:RegExp*/ {
|
|
var t = f+"|"+(g||"");
|
|
if(mtcache[t]) return mtcache[t];
|
|
return (mtcache[t] = new RegExp('<(?:\\w+:)?'+f+'(?: xml:space="preserve")?(?:[^>]*)>([\\s\\S]*?)</(?:\\w+:)?'+f+'>',((g||"")/*:any*/)));
|
|
};
|
|
})();
|
|
|
|
var htmldecode/*:{(s:string):string}*/ = (function() {
|
|
var entities/*:Array<[RegExp, string]>*/ = [
|
|
['nbsp', ' '], ['middot', '·'],
|
|
['quot', '"'], ['apos', "'"], ['gt', '>'], ['lt', '<'], ['amp', '&']
|
|
].map(function(x/*:[string, string]*/) { return [new RegExp('&' + x[0] + ';', "ig"), x[1]]; });
|
|
return function htmldecode(str/*:string*/)/*:string*/ {
|
|
var o = str
|
|
// Remove new lines and spaces from start of content
|
|
.replace(/^[\t\n\r ]+/, "")
|
|
// Remove new lines and spaces from end of content
|
|
.replace(/[\t\n\r ]+$/,"")
|
|
// Added line which removes any white space characters after and before html tags
|
|
.replace(/>\s+/g,">").replace(/\s+</g,"<")
|
|
// Replace remaining new lines and spaces with space
|
|
.replace(/[\t\n\r ]+/g, " ")
|
|
// Replace <br> tags with new lines
|
|
.replace(/<\s*[bB][rR]\s*\/?>/g,"\n")
|
|
// Strip HTML elements
|
|
.replace(/<[^>]*>/g,"");
|
|
for(var i = 0; i < entities.length; ++i) o = o.replace(entities[i][0], entities[i][1]);
|
|
return o;
|
|
};
|
|
})();
|
|
|
|
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 + ">([\\s\\S]*?)</(?:vt:)?" + bt + ">", 'g') );
|
|
};})();
|
|
var vtvregex = /<\/?(?:vt:)?variant>/g, vtmregex = /<(?:vt:)([^>]*)>([\s\S]*)</;
|
|
function parseVector(data/*:string*/, opts)/*:Array<{v:string,t:string}>*/ {
|
|
var h = parsexmltag(data);
|
|
|
|
var matches/*:Array<string>*/ = data.match(vtregex(h.baseType))||[];
|
|
var res/*:Array<any>*/ = [];
|
|
if(matches.length != h.size) {
|
|
if(opts.WTF) throw new Error("unexpected vector length " + matches.length + " != " + h.size);
|
|
return res;
|
|
}
|
|
matches.forEach(function(x/*:string*/) {
|
|
var v = x.replace(vtvregex,"").match(vtmregex);
|
|
if(v) res.push({v:utf8read(v[2]), t:v[1]});
|
|
});
|
|
return res;
|
|
}
|
|
|
|
var wtregex = /(^\s|\s$|\n)/;
|
|
function writetag(f/*:string*/,g/*:string*/)/*:string*/ { return '<' + f + (g.match(wtregex)?' xml:space="preserve"' : "") + '>' + g + '</' + f + '>'; }
|
|
|
|
function wxt_helper(h)/*:string*/ { return keys(h).map(function(k) { return " " + k + '="' + h[k] + '"';}).join(""); }
|
|
function writextag(f/*:string*/,g/*:?string*/,h) { return '<' + f + ((h != null) ? wxt_helper(h) : "") + ((g != null) ? (g.match(wtregex)?' xml:space="preserve"' : "") + '>' + g + '</' + f : "/") + '>';}
|
|
|
|
function write_w3cdtf(d/*:Date*/, t/*:?boolean*/)/*:string*/ { try { return d.toISOString().replace(/\.\d*/,""); } catch(e) { if(t) throw e; } return ""; }
|
|
|
|
function write_vt(s, xlsx/*:?boolean*/)/*:string*/ {
|
|
switch(typeof s) {
|
|
case 'string':
|
|
var o = writextag('vt:lpwstr', escapexml(s));
|
|
if(xlsx) o = o.replace(/"/g, "_x0022_");
|
|
return o;
|
|
case 'number': return writextag((s|0)==s?'vt:i4':'vt:r8', escapexml(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 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'
|
|
}/*:any*/);
|
|
|
|
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'
|
|
];
|
|
|
|
var XLMLNS = ({
|
|
'o': 'urn:schemas-microsoft-com:office:office',
|
|
'x': 'urn:schemas-microsoft-com:office:excel',
|
|
'ss': 'urn:schemas-microsoft-com:office:spreadsheet',
|
|
'dt': 'uuid:C2F41010-65B3-11d1-A29F-00AA00C14882',
|
|
'mv': 'http://macVmlSchemaUri',
|
|
'v': 'urn:schemas-microsoft-com:vml',
|
|
'html': 'http://www.w3.org/TR/REC-html40'
|
|
}/*:any*/);
|