/BibTeX.js

Large files files are truncated, but you can click here to view the full file

{
	"translatorID": "9cb70025-a888-4a29-a210-93ec52da40d4",
	"label": "BibTeX",
	"creator": "Simon Kornblith, Richard Karnesky and Emiliano heyns",
	"target": "bib",
	"minVersion": "2.1.9",
	"maxVersion": "",
	"priority": 200,
	"configOptions": {
		"getCollections": true
	},
	"displayOptions": {
		"exportCharset": "UTF-8",
		"exportNotes": true,
		"exportFileData": false,
		"useJournalAbbreviation": false
	},
	"inRepository": true,
	"translatorType": 3,
	"browserSupport": "gcsv",
	"lastUpdated": "2014-06-23 03:37:22"
}

function detectImport() {
	var maxChars = 1048576; // 1MB
	
	var inComment = false;
	var block = "";
	var buffer = "";
	var chr = "";
	var charsRead = 0;
	
	var re = /^\s*@[a-zA-Z]+[\(\{]/;
	while((buffer = Zotero.read(4096)) && charsRead < maxChars) {
		Zotero.debug("Scanning " + buffer.length + " characters for BibTeX");
		charsRead += buffer.length;
		for (var i=0; i<buffer.length; i++) {
			chr = buffer[i];
			
			if (inComment && chr != "\r" && chr != "\n") {
				continue;
			}
			inComment = false;
			
			if(chr == "%") {
				// read until next newline
				block = "";
				inComment = true;
			} else if((chr == "\n" || chr == "\r"
				// allow one-line entries
						|| i == (buffer.length - 1))
						&& block) {
				// check if this is a BibTeX entry
				if(re.test(block)) {
					return true;
				}
				
				block = "";
			} else if(" \n\r\t".indexOf(chr) == -1) {
				block += chr;
			}
		}
	}
}

//%a = first listed creator surname
//%y = year
//%t = first word of title
var citeKeyFormat = "%a_%t_%y";

var fieldMap = {
	address:"place",
	chapter:"section",
	edition:"edition",
	type:"type",
	series:"series",
	title:"title",
	volume:"volume",
	copyright:"rights",
	isbn:"ISBN",
	issn:"ISSN",
	shorttitle:"shortTitle",
	url:"url",
	doi:"DOI",
	abstract:"abstractNote",
  	nationality: "country",
  	language:"language",
  	assignee:"assignee"
};

// Import/export in BibTeX
var extraIdentifiers = {
	lccn: 'LCCN',
	mrnumber: 'MR',
	zmnumber: 'Zbl',
	pmid: 'PMID',
	pmcid: 'PMCID'
	
	//Mostly from Wikipedia citation templates
	//asin - Amazon ID
	//bibcode/refcode - used in astronomy, but haven't seen any Bib(La)TeX examples
	//jfm - Jahrbuch ID, but it seems to be part of Zentralblatt MATH, so Zbl
	//oclc
	//ol - openlibrary.org ID
	//osti
	//rfc
	//ssrn? http://cyber.law.harvard.edu/cybersecurity/Guidelines_for_adding_Bibliography_entries
};

// Make a reverse map for convenience
var revExtraIds = {};
for(var field in extraIdentifiers) {
	revExtraIds[extraIdentifiers[field]] = field;
}

// Import only. Exported by BibLaTeX
var eprintIds = {
	// eprinttype: Zotero label
	
	// From BibLaTeX manual
	'arxiv': 'arXiv', // Sorry, but no support for eprintclass yet
	'jstor': 'JSTOR',
	'pubmed': 'PMID',
	'hdl': 'HDL',
	'googlebooks': 'GoogleBooksID'
};

function parseExtraFields(extra) {
	var lines = extra.split(/[\r\n]+/);
	var fields = [];
	for(var i=0; i<lines.length; i++) {
		var rec = { raw: lines[i] };
		var line = lines[i].trim();
		var splitAt = line.indexOf(':');
		if(splitAt > 1) {
			rec.field = line.substr(0,splitAt).trim();
			rec.value = line.substr(splitAt + 1).trim();
		}
		fields.push(rec);
	}
	return fields;
}

function extraFieldsToString(extra) {
	var str = '';
	for(var i=0; i<extra.length; i++) {
		if(!extra[i].raw) {
			str += '\n' + extra[i].field + ': ' + extra[i].value;
		} else {
			str += '\n' + extra[i].raw;
		}
	}
	
	return str.substr(1);
}

var inputFieldMap = {
	booktitle :"publicationTitle",
	school:"publisher",
	institution:"publisher",
	publisher:"publisher",
	issue:"issue",
	location:"place"
};

var zotero2bibtexTypeMap = {
	"book":"book",
	"bookSection":"incollection",
	"journalArticle":"article",
	"magazineArticle":"article",
	"newspaperArticle":"article",
	"thesis":"phdthesis",
	"letter":"misc",
	"manuscript":"unpublished",
	"patent" :"patent",
	"interview":"misc",
	"film":"misc",
	"artwork":"misc",
	"webpage":"misc",
	"conferencePaper":"inproceedings",
	"report":"techreport"
};

var bibtex2zoteroTypeMap = {
	"book":"book", // or booklet, proceedings
	"inbook":"bookSection",
	"incollection":"bookSection",
	"article":"journalArticle", // or magazineArticle or newspaperArticle
	"patent" :"patent",
	"phdthesis":"thesis",
	"unpublished":"manuscript",
	"inproceedings":"conferencePaper", // check for conference also
	"conference":"conferencePaper",
	"techreport":"report",
	"booklet":"book",
	"manual":"book",
	"mastersthesis":"thesis",
	"misc":"book",
	"proceedings":"book",
	"online":"webpage"
};

/*
 * three-letter month abbreviations. i assume these are the same ones that the
 * docs say are defined in some appendix of the LaTeX book. (i don't have the
 * LaTeX book.)
 */
var months = ["jan", "feb", "mar", "apr", "may", "jun",
			  "jul", "aug", "sep", "oct", "nov", "dec"];

var jabref = {
	format: null,
	root: {}
};

var alwaysMap = {
	"|":"{\\textbar}",
	"<":"{\\textless}",
	">":"{\\textgreater}",
	"~":"{\\textasciitilde}",
	"^":"{\\textasciicircum}",
	"\\":"{\\textbackslash}",
	"{" : "\\{",
	"}" : "\\}"
};


var strings = {};
var keyRe = /[a-zA-Z0-9\-]/;
var keywordSplitOnSpace = true;
var keywordDelimRe = '\\s*[,;]\\s*';
var keywordDelimReFlags = '';

function setKeywordSplitOnSpace( val ) {
	keywordSplitOnSpace = val;
}

function setKeywordDelimRe( val, flags ) {
	//expect string, but it could be RegExp
	if(typeof(val) != 'string') {
		keywordDelimRe = val.toString().slice(1, val.toString().lastIndexOf('/'));
		keywordDelimReFlags = val.toString().slice(val.toString().lastIndexOf('/')+1);
	} else {
		keywordDelimRe = val;
		keywordDelimReFlags = flags;
	}
}

function processField(item, field, value, rawValue) {
	if(Zotero.Utilities.trim(value) == '') return null;
	if(fieldMap[field]) {
		item[fieldMap[field]] = value;
	} else if(inputFieldMap[field]) {
		item[inputFieldMap[field]] = value;
	} else if(field == "journal") {
		if(item.publicationTitle) {
			item.journalAbbreviation = value;
		} else {
			item.publicationTitle = value;
		}
	} else if(field == "fjournal") {
		if(item.publicationTitle) {
			// move publicationTitle to abbreviation, since itprobably came from 'journal'
			item.journalAbbreviation = item.publicationTitle;
		}
		item.publicationTitle = value;
	} else if(field == "author" || field == "editor" || field == "translator") {
		// parse authors/editors/translators
		var names = splitUnprotected(rawValue.trim(), /\sand\s/gi);
		for(var i in names) {
			var name = names[i];
			// skip empty names
			if (!name) continue;
			
			// Names in BibTeX can have three commas
			pieces = splitUnprotected(name, /\s*,\s*/g);
			var creator = {};
			if (pieces.length > 1) {
				creator.firstName = pieces.pop();
				creator.lastName = unescapeBibTeX(pieces.shift());
				if(pieces.length) {
					// If anything is left, it should only be the 'Jr' part
					creator.firstName += ', ' + pieces.join(', ');
				}
				creator.firstName = unescapeBibTeX(creator.firstName);
				creator.creatorType = field;
			} else if(splitUnprotected(name, / +/g).length > 1){
				creator = Zotero.Utilities.cleanAuthor(unescapeBibTeX(name), field, false);
			} else {
				creator = {
					lastName: unescapeBibTeX(name),
					creatorType: field,
					fieldMode: 1
				}
			}
			item.creators.push(creator);
		}
	} else if(field == "institution" || field == "organization") {
		item.backupPublisher = value;
	} else if(field == "number"){ // fix for techreport
		if (item.itemType == "report") {
			item.reportNumber = value;
		} else if (item.itemType == "book" || item.itemType == "bookSection") {
			item.seriesNumber = value;
		} else if (item.itemType == "patent"){
			item.patentNumber = value;
		} else {
			item.issue = value;
		}
	} else if(field == "month") {
		var monthIndex = months.indexOf(value.toLowerCase());
		if(monthIndex != -1) {
			value = Zotero.Utilities.formatDate({month:monthIndex});
		} else {
			value += " ";
		}
		
		if(item.date) {
			if(value.indexOf(item.date) != -1) {
				// value contains year and more
				item.date = value;
			} else {
				item.date = value+item.date;
			}
		} else {
			item.date = value;
		}
	} else if(field == "year") {
		if(item.date) {
			if(item.date.indexOf(value) == -1) {
				// date does not already contain year
				item.date += value;
			}
		} else {
			item.date = value;
		}
	} else if(field == "date") {
	//We're going to assume that "date" and the date parts don't occur together. If they do, we pick date, which should hold all.
		item.date = value;
	} else if(field == "pages") {
		if (item.itemType == "book" || item.itemType == "thesis" || item.itemType == "manuscript") {
			item.numPages = value;
		}
		else {
			item.pages = value.replace(/--/g, "-");
		}
	} else if(field == "note") {
		item._extraFields.push({raw: value.trim()});
	} else if(field == "howpublished") {
		if(value.length >= 7) {
			var str = value.substr(0, 7);
			if(str == "http://" || str == "https:/" || str == "mailto:") {
				item.url = value;
			} else {
				item._extraFields.push({field: 'Published', value: value});
			}
		}
	
	} 
	//accept lastchecked or urldate for access date. These should never both occur. 
	//If they do we don't know which is better so we might as well just take the second one
	else if (field == "lastchecked"|| field == "urldate"){
		item.accessDate = value;
	} else if(field == "keywords" || field == "keyword") {
		var re = new RegExp(keywordDelimRe, keywordDelimReFlags);
		if(!value.match(re) && keywordSplitOnSpace) {
			// keywords/tags
			item.tags = value.split(/\s+/);
		} else {
			item.tags = value.split(re);
		}
	} else if (field == "comment" || field == "annote" || field == "review" || field == "notes") {
		item.notes.push({note:Zotero.Utilities.text2html(value)});
	} else if (field == "pdf" || field == "path" /*Papers2 compatibility*/) {
		item.attachments.push({path:value, mimeType:"application/pdf"});
	} else if (field == "sentelink") { // the reference manager 'Sente' has a unique file scheme in exported BibTeX; it can occur multiple times
		item.attachments.push({path:value.split(",")[0], mimeType:"application/pdf"});
	} else if (field == "file") {
		var start = 0, attachment;
		rawValue = rawValue.replace(/\$\\backslash\$/g, '\\') // Mendeley invention?
			.replace(/([^\\](?:\\\\)*)\\(.){}/g, '$1$2'); // part of Mendeley's escaping (e.g. \~{} = ~)
		for(var i=0; i<rawValue.length; i++) {
			if(rawValue[i] == '\\') {
				i++; //skip next char
				continue;
			}
			if(rawValue[i] == ';') {
				attachment = parseFilePathRecord(rawValue.slice(start, i));
				if(attachment) item.attachments.push(attachment);
				start = i+1;
			}
		}
		
		attachment = parseFilePathRecord(rawValue.slice(start));
		if(attachment) item.attachments.push(attachment);
	} else if (field == "eprint" || field == "eprinttype") {
		// Support for IDs exported by BibLaTeX
		if(field == 'eprint') item._eprint = value;
		else item._eprinttype = value;
		
		var eprint = item._eprint;
		var eprinttype = item._eprinttype;
		// If we don't have both yet, continue
		if(!eprint || !eprinttype) return;
		
		var label = eprintIds[eprinttype.trim().toLowerCase()];
		if(!label) return;
		
		item._extraFields.push({field: label, value: eprint.trim()});
		
		delete item._eprinttype;
		delete item._eprint;
	} else if (extraIdentifiers[field]) {
		var label = extraIdentifiers[field];
		item._extraFields.push({field: label, value: value.trim()});
	}
}

/**
 * Split a string on a provided delimiter, but not if delimiter appears inside { }
 * @param {String} str String to split
 * @param {RegExp} delim RegExp object for the split delimiter. Use g flag to split on each
 * @return {String[]} Array of strings without delimiters
 */
function splitUnprotected(str, delim) {
	delim.lastIndex = 0; // In case we're reusing a regexp
	var nextPossibleSplit = delim.exec(str);
	if(!nextPossibleSplit) return [str];
	
	var parts = [], open = 0, nextPartStart = 0;
	for(var i=0; i<str.length; i++) {
		if(i>nextPossibleSplit.index) {
			// Must have been inside braces
			nextPossibleSplit = delim.exec(str);
			if(!nextPossibleSplit) {
				parts.push(str.substr(nextPartStart));
				return parts;
			}
		}
		
		if(str[i] == '\\') {
			// Skip next character
			i++;
			continue;
		}
		
		if(str[i] == '{') {
			open++;
			continue;
		}
		
		if(str[i] == '}') {
			open--;
			if(open < 0) open = 0; // Shouldn't happen, but...
			continue;
		}
		
		if(open) continue;
		
		if(i == nextPossibleSplit.index) {
			parts.push(str.substring(nextPartStart, i));
			i += nextPossibleSplit[0].length - 1; // We can jump past the split delim
			nextPartStart = i + 1;
			nextPossibleSplit = delim.exec(str);
			if(!nextPossibleSplit) {
				parts.push(str.substr(nextPartStart));
				return parts;
			}
		}
	}
	
	// I don't think we should ever get here*, but just to be safe
	// *we should always be returning from the for loop
	var last = str.substr(nextPartStart).trim();
	if(last) parts.push(last);
	
	return parts;
}

function parseFilePathRecord(record) {
	var start = 0, fields = [];
	for(var i=0; i<record.length; i++) {
		if(record[i] == '\\') {
			i++;
			continue;
		}
		if(record[i] == ':') {
			fields.push(decodeFilePathComponent(record.slice(start, i)));
			start = i+1;
		}
	}
	
	fields.push(decodeFilePathComponent(record.slice(start)));
	
	if(fields.length != 3 && fields.length != 1) {
		Zotero.debug("Unknown file path record format: " + record);
		return;
	}
	
	var attachment = {};
	if(fields.length == 3) {
		attachment.title = fields[0].trim() || 'Attachment';
		attachment.path = fields[1];
		attachment.mimeType = fields[2];
		if(attachment.mimeType.search(/pdf/i) != -1) {
			attachment.mimeType = 'application/pdf';
		}
	} else {
		attachment.title = 'Attachment';
		attachment.path = fields[0];
	}
	
	attachment.path = attachment.path.trim();
	if(!attachment.path) return;
	
	return attachment;
}

function getFieldValue(read) {
	var value = "";
	// now, we have the first character of the field
	if(read == "{") {
		// character is a brace
		var openBraces = 1, nextAsLiteral = false;
		while(read = Zotero.read(1)) {
			if(nextAsLiteral) { // Previous character was a backslash
				value += read;
				nextAsLiteral = false;
				continue;
			}
			
			if(read == "\\") {
				value += read;
				nextAsLiteral = true;
				continue;
			}
			
			if(read == "{") {
				openBraces++;
				value += "{";
			} else if(read == "}") {
				openBraces--;
				if(openBraces == 0) {
					break;
				} else {
					value += "}";
				}
			} else {
				value += read;
			}
		}
		
	} else if(read == '"') {
		var openBraces = 0;
		while(read = Zotero.read(1)) {
			if(read == "{" && value[value.length-1] != "\\") {
				openBraces++;
				value += "{";
			} else if(read == "}" && value[value.length-1] != "\\") {
				openBraces--;
				value += "}";
			} else if(read == '"' && openBraces == 0) {
				break;
			} else {
				value += read;
			}
		}
	}

	return value;
}

function unescapeBibTeX(value) {
	if(value.length < 2) return value;
	
	// replace accented characters (yucky slow)
	value = value.replace(/{?(\\[`"'^~=]){?\\?([A-Za-z])}/g, "{$1$2}");
	//for special characters rendered by \[a-z] we need a space
	value = value.replace(/{?(\\[a-z]){?\\?([A-Za-z])}/g, "{$1 $2}");
	//convert tex markup into permitted HTML
	value = mapTeXmarkup(value);
	for (var mapped in reversemappingTable) { // really really slow!
		var unicode = reversemappingTable[mapped];
		while(value.indexOf(mapped) !== -1) {
			Zotero.debug("Replace " + mapped + " in " + value + " with " + unicode);
			value = value.replace(mapped, unicode);
		}
		mapped = mapped.replace(/[{}]/g, "");
		while(value.indexOf(mapped) !== -1) {
			//Z.debug(value)
			Zotero.debug("Replace(2) " + mapped + " in " + value + " with " + unicode);
			value = value.replace(mapped, unicode);
		}
	}
	
	// kill braces
	value = value.replace(/([^\\])[{}]+/g, "$1");
	if(value[0] == "{") {
		value = value.substr(1);
	}
	
	// chop off backslashes
	value = value.replace(/([^\\])\\([#$%&~_^\\{}])/g, "$1$2");
	value = value.replace(/([^\\])\\([#$%&~_^\\{}])/g, "$1$2");
	if(value[0] == "\\" && "#$%&~_^\\{}".indexOf(value[1]) != -1) {
		value = value.substr(1);
	}
	if(value[value.length-1] == "\\" && "#$%&~_^\\{}".indexOf(value[value.length-2]) != -1) {
		value = value.substr(0, value.length-1);
	}
	value = value.replace(/\\\\/g, "\\");
	value = value.replace(/\s+/g, " ");
	
	return value;
}

function jabrefSplit(str, sep) {
	var quoted = false;
	var result = [];

	str = str.split('');
	while (str.length > 0) {
		if (result.length == 0) { result = ['']; }

		if (str[0] == sep) {
			str.shift();
			result.push('');
		} else {
			if (str[0] == '\\') { str.shift(); }
			result[result.length - 1] += str.shift();
		}
	}
	return result;
}

function jabrefCollect(arr, func) {
	if (arr == null) { return []; }

	var result = [];

	for (var i = 0; i < arr.length; i++) {
		if (func(arr[i])) {
			result.push(arr[i]);
		}
	}
	return result;
}

function processComment() {
	var comment = "";
	var read;
	var collectionPath = [];
	var parentCollection, collection;

	while(read = Zotero.read(1)) {
		if (read == "}") { break; } // JabRef ought to escape '}' but doesn't; embedded '}' chars will break the import just as it will on JabRef itself
		comment += read;
	}

	if (comment == 'jabref-meta: groupsversion:3;') {
		jabref.format = 3;
		return;
	}

	if (comment.indexOf('jabref-meta: groupstree:') == 0) {
		if (jabref.format != 3) {
			Zotero.debug("jabref: fatal: unsupported group format: " + jabref.format);
			return;
		}
		comment = comment.replace(/^jabref-meta: groupstree:/, '').replace(/[\r\n]/gm, '')

		var records = jabrefSplit(comment, ';');
		while (records.length > 0) {
			var record = records.shift();
			var keys = jabrefSplit(record, ';');
			if (keys.length < 2) { continue; }

			var record = {id: keys.shift()};
			record.data = record.id.match(/^([0-9]) ([^:]*):(.*)/);
			if (record.data == null) {
				Zotero.debug("jabref: fatal: unexpected non-match for group " + record.id);
				return;
			}
			record.level = parseInt(record.data[1]);
			record.type = record.data[2]
			record.name = record.data[3]
			record.intersection = keys.shift(); // 0 = independent, 1 = intersection, 2 = union

			if (isNaN(record.level)) {
				Zotero.debug("jabref: fatal: unexpected record level in " + record.id);
				return;
			}

			if (record.level == 0) { continue; }
			if (record.type != 'ExplicitGroup') {
				Zotero.debug("jabref: fatal: group type " + record.type + " is not supported");
				return;
			}

			collectionPath = collectionPath.slice(0, record.level - 1).concat([record.name]);
			Zotero.debug("jabref: locating level " + record.level + ": " + collectionPath.join('/'));

			if (jabref.root.hasOwnProperty(collectionPath[0])) {
				collection = jabref.root[collectionPath[0]];
				Zotero.debug("jabref: root " + collection.name + " found");
			} else {
				collection = new Zotero.Collection();
				collection.name = collectionPath[0];
				collection.type = 'collection';
				collection.children = [];
				jabref.root[collectionPath[0]] = collection;
				Zotero.debug("jabref: root " + collection.name + " created");
			}
			parentCollection = null;

			for (var i = 1; i < collectionPath.length; i++) {
				var path = collectionPath[i];
				Zotero.debug("jabref: looking for child " + path + " under " + collection.name);

				var child = jabrefCollect(collection.children, function(n) { return (n.name == path)})
				if (child.length != 0) {
					child = child[0]
					Zotero.debug("jabref: child " + child.name + " found under " + collection.name);
				} else {
					child = new Zotero.Collection();
					child.name = path;
					child.type = 'collection';
					child.children = [];

					collection.children.push(child);
					Zotero.debug("jabref: child " + child.name + " created under " + collection.name);
				}

				parentCollection = collection;
				collection = child;
			}

			if (parentCollection) {
				parentCollection = jabrefCollect(parentCollection.children, function(n) { return (n.type == 'item') });
			}

			if (record.intersection == '2' && parentCollection) { // union with parent
				collection.children = parentCollection;
			}

			while(keys.length > 0) {
				key = keys.shift();
				if (key != '') {
					Zotero.debug('jabref: adding ' + key + ' to ' + collection.name);
					collection.children.push({type: 'item', id: key});
				}
			}

			if (parentCollection && record.intersection == '1') { // intersection with parent
				collection.children = jabrefMap(collection.children, function(n) { parentCollection.indexOf(n) !== -1; });
			}
		}
	}
}

function beginRecord(type, closeChar) {
	type = Zotero.Utilities.trimInternal(type.toLowerCase());
	if(type != "string") {
		var zoteroType = bibtex2zoteroTypeMap[type];
		if (!zoteroType) {
			Zotero.debug("discarded item from BibTeX; type was "+type);
			return;
		}
		var item = new Zotero.Item(zoteroType);
		item._extraFields = [];
	}
	
	var field = "";
	
	// by setting dontRead to true, we can skip a read on the next iteration
	// of this loop. this is useful after we read past the end of a string.
	var dontRead = false;
	
	var value, rawValue;
	while(dontRead || (read = Zotero.read(1))) {
		dontRead = false;
		
		if(read == "=") {								// equals begin a field
		// read whitespace
			var read = Zotero.read(1);
			while(" \n\r\t".indexOf(read) != -1) {
				read = Zotero.read(1);
			}
			
			if(keyRe.test(read)) {
				// read numeric data here, since we might get an end bracket
				// that we should care about
				value = "";
				value += read;
				
				// character is a number
				while((read = Zotero.read(1)) && keyRe.test(read)) {
					value += read;
				}
				
				// don't read the next char; instead, process the character
				// we already read past the end of the string
				dontRead = true;
				
				// see if there's a defined string
				if(strings[value]) value = strings[value];
			} else {
				rawValue = getFieldValue(read);
				value = unescapeBibTeX(rawValue);
			}
			
			if(item) {
				processField(item, field.toLowerCase(), value, rawValue);
			} else if(type == "string") {
				strings[field] = value;
			}
			field = "";
		} else if(read == ",") {						// commas reset
			if (item.itemID == null) {
				item.itemID = field; // itemID = citekey
			}
			field = "";
		} else if(read == closeChar) {
			if(item) {
				item.extra = extraFieldsToString(item._extraFields);
				delete item._extraFields;
				
				if (!item.publisher && item.backupPublisher){
					item.publisher=item.backupPublisher;
					delete item.backupPublisher;
				}
				item.complete();
			}
			return;
		} else if(" \n\r\t".indexOf(read) == -1) {		// skip whitespace
			field += read;
		}
	}
}

function doImport() {
	var read = "", text = "", recordCloseElement = false;
	var type = false;
	
	while(read = Zotero.read(1)) {
		if(read == "@") {
			type = "";
		} else if(type !== false) {
			if(type == "comment") {
				processComment();
				type = false;
			} else if(read == "{") {		// possible open character
				beginRecord(type, "}");
				type = false;
			} else if(read == "(") {		// possible open character
				beginRecord(type, ")");
				type = false;
			} else if(/[a-zA-Z0-9-_]/.test(read)) {
				type += read;
			}
		}
	}
	for (var key in jabref.root) {
		if (jabref.root.hasOwnProperty(key)) { jabref.root[key].complete(); }
	}
}

// some fields are, in fact, macros.  If that is the case then we should not put the
// data in the braces as it will cause the macros to not expand properly
function writeField(field, value, isMacro) {
	if (!value && typeof value != "number") return;
	value = value + ""; // convert integers to strings
	Zotero.write(",\n\t" + field + " = ");
	if (!isMacro) Zotero.write("{");
	// url field is preserved, for use with \href and \url
	// Other fields (DOI?) may need similar treatment
	if (!isMacro && !(field == "url" || field == "doi" || field == "file" || field == "lccn" )) {
		// I hope these are all the escape characters!
		value = value.replace(/[|\<\>\~\^\\\{\}]/g, mapEscape).replace(/([\#\$\%\&\_])/g, "\\$1");

		//disable 
		/** if (field == "title" || field == "type" || field == "shorttitle" || field == "booktitle" || field == "series") {
			if (!isTitleCase(value)) {
				//protect caps for everything but the first letter
				value = value.replace(/(.)([A-Z]+)/g, "$1{$2}");
			} else {	//protect all-caps vords and initials
				value = value.replace(/([\s.-])([A-Z]+)(?=\.)/g, "$1{$2}");	//protect initials
				if(value.toUpperCase() != value) value = value.replace(/(\s)([A-Z]{2,})(?=[\.,\s]|$)/g, "$1{$2}");
			}
		} 
		**/

		// Case of words with uppercase characters in non-initial positions is preserved with braces.
		// we're looking at all unicode letters
		var protectCaps = new ZU.XRegExp("\\b\\p{Letter}+\\p{Uppercase_Letter}\\p{Letter}*", 'g')
		if (field != "pages") {
			value = ZU.XRegExp.replace(value, protectCaps, "{$0}");
		}
	}
	if (Zotero.getOption("exportCharset") != "UTF-8") {
		value = value.replace(/[\u0080-\uFFFF]/g, mapAccent);
	}
	//convert the HTML markup allowed in Zotero for rich text to TeX; excluding doi/url/file shouldn't be necessary, but better to be safe;
	if (!((field == "url") || (field == "doi") || (field == "file"))) value = mapHTMLmarkup(value);
	Zotero.write(value);
	if (!isMacro) Zotero.write("}");
}

function mapHTMLmarkup(characters){
	//converts the HTML markup allowed in Zotero for rich text to TeX
	//since  < and > have already been escaped, we need this rather hideous code - I couldn't see a way around it though.
	//italics and bold
	characters = characters.replace(/\{\\textless\}i\{\\textgreater\}(.+?)\{\\textless\}\/i{\\textgreater\}/g, "\\textit{$1}")
		.replace(/\{\\textless\}b\{\\textgreater\}(.+?)\{\\textless\}\/b{\\textgreater\}/g, "\\textbf{$1}");
	//sub and superscript
	characters = characters.replace(/\{\\textless\}sup\{\\textgreater\}(.+?)\{\\textless\}\/sup{\\textgreater\}/g, "\$^{\\textrm{$1}}\$")
		.replace(/\{\\textless\}sub\{\\textgreater\}(.+?)\{\\textless\}\/sub\{\\textgreater\}/g, "\$_{\\textrm{$1}}\$");
	//two variants of small caps
	characters = characters.replace(/\{\\textless\}span\sstyle=\"small\-caps\"\{\\textgreater\}(.+?)\{\\textless\}\/span{\\textgreater\}/g, "\\textsc{$1}")
		.replace(/\{\\textless\}sc\{\\textgreater\}(.+?)\{\\textless\}\/sc\{\\textgreater\}/g, "\\textsc{$1}");
	return characters;
}


function mapTeXmarkup(tex){
	//reverse of the above - converts tex mark-up into html mark-up permitted by Zotero
	//italics and bold
	tex = tex.replace(/\\textit\{([^\}]+\})/g, "<i>$1</i>").replace(/\\textbf\{([^\}]+\})/g, "<b>$1</b>");
	//two versions of subscript the .* after $ is necessary because people m
	tex = tex.replace(/\$[^\{\$]*_\{([^\}]+\})\$/g, "<sub>$1</sub>").replace(/\$[^\{]*_\{\\textrm\{([^\}]+\}\})/g, "<sub>$1</sub>");	
	//two version of superscript
	tex = tex.replace(/\$[^\{]*\^\{([^\}]+\}\$)/g, "<sup>$1</sup>").replace(/\$[^\{]*\^\{\\textrm\{([^\}]+\}\})/g, "<sup>$1</sup>");	
	//small caps
	tex = tex.replace(/\\textsc\{([^\}]+)/g, "<span style=\"small-caps\">$1</span>");
	return tex;
}
//Disable the isTitleCase function until we decide what to do with it.
/* const skipWords = ["but", "or", "yet", "so", "for", "and", "nor",
	"a", "an", "the", "at", "by", "from", "in", "into", "of", "on",
	"to", "with", "up", "down", "as", "while", "aboard", "about",
	"above", "across", "after", "against", "along", "amid", "among",
	"anti", "around", "as", "before", "behind", "below", "beneath",
	"beside", "besides", "between", "beyond", "but", "despite",
	"down", "during", "except", "for", "inside", "like", "near",
	"off", "onto", "over", "past", "per", "plus", "round", "save",
	"since", "than", "through", "toward", "towards", "under",
	"underneath", "unlike", "until", "upon", "versus", "via",
	"within", "without"];

function isTitleCase(string) {
	const wordRE = /[\s[(]([^\s,\.:?!\])]+)/g;

	var word;
	while (word = wordRE.exec(string)) {
		word = word[1];
		if(word.search(/\d/) != -1	//ignore words with numbers (including just numbers)
			|| skipWords.indexOf(word.toLowerCase()) != -1) {
			continue;
		}

		if(word.toLowerCase() == word) return false;
	}
	return true;
}
*/

function mapEscape(character) {
	return alwaysMap[character];
}

function mapAccent(character) {
	return (mappingTable[character] ? mappingTable[character] : "?");
}

var filePathSpecialChars = '\\\\:;{}$'; // $ for Mendeley
var encodeFilePathRE = new RegExp('[' + filePathSpecialChars + ']', 'g');

function encodeFilePathComponent(value) {
	return value.replace(encodeFilePathRE, "\\$&");
}

function decodeFilePathComponent(value) {
	return value.replace(/\\([^A-Za-z0-9.])/g, "$1");
}

// a little substitution function for BibTeX keys, where we don't want LaTeX 
// escaping, but we do want to preserve the base characters

function tidyAccents(s) {
	var r=s.toLowerCase();

	// XXX Remove conditional when we drop Zotero 2.1.x support
	// This is supported in Zotero 3.0 and higher
	if (ZU.removeDiacritics !== undefined)
		r = ZU.removeDiacritics(r, true);
	else {
	// We fall back on the replacement list we used previously
		r = r.replace(new RegExp("[ä]", 'g'),"ae");
		r = r.replace(new RegExp("[ö]", 'g'),"oe");
		r = r.replace(new RegExp("[ü]", 'g'),"ue");
		r = r.replace(new RegExp("[àáâãå]", 'g'),"a");
		r = r.replace(new RegExp("æ", 'g'),"ae");
		r = r.replace(new RegExp("ç", 'g'),"c");
		r = r.replace(new RegExp("[èéêë]", 'g'),"e");
		r = r.replace(new RegExp("[ìíîï]", 'g'),"i");
		r = r.replace(new RegExp("ñ", 'g'),"n");                            
		r = r.replace(new RegExp("[òóôõ]", 'g'),"o");
		r = r.replace(new RegExp("œ", 'g'),"oe");
		r = r.replace(new RegExp("[ùúû]", 'g'),"u");
		r = r.replace(new RegExp("[ýÿ]", 'g'),"y");
	}

	return r;
};

var numberRe = /^[0-9]+/;
// Below is a list of words that should not appear as part of the citation key
// in includes the indefinite articles of English, German, French and Spanish, as well as a small set of English prepositions whose 
// force is more grammatical than lexical, i.e. which are likely to strike many as 'insignificant'.
// The assumption is that most who want a title word in their key would prefer the first word of significance.
var citeKeyTitleBannedRe = /\b(a|an|the|some|from|on|in|to|of|do|with|der|die|das|ein|eine|einer|eines|einem|einen|un|une|la|le|l\'|el|las|los|al|uno|una|unos|unas|de|des|del|d\')(\s+|\b)/g;
var citeKeyConversionsRe = /%([a-zA-Z])/;
var citeKeyCleanRe = /[^a-z0-9\!\$\&\*\+\-\.\/\:\;\<\>\?\[\]\^\_\`\|]+/g;

var citeKeyConversions = {
	"a":function (flags, item) {
		if(item.creators && item.creators[0] && item.creators[0].lastName) {
			return item.creators[0].lastName.toLowerCase().replace(/ /g,"_").replace(/,/g,"");
		}
		return "";
	},
	"t":function (flags, item) {
		if (item["title"]) {
			return item["title"].toLowerCase().replace(citeKeyTitleBannedRe, "").split(/\s+/g)[0];
		}
		return "";
	},
	"y":function (flags, item) {
		if(item.date) {
			var date = Zotero.Utilities.strToDate(item.date);
			if(date.year && numberRe.test(date.year)) {
				return date.year;
			}
		}
		return "????";
	}
}


function buildCiteKey (item,citekeys) {
	var basekey = "";
	var counter = 0;
	citeKeyFormatRemaining = citeKeyFormat;
	while (citeKeyConversionsRe.test(citeKeyFormatRemaining)) {
		if (counter > 100) {
			Zotero.debug("Pathological BibTeX format: " + citeKeyFormat);
			break;
		}
		var m = citeKeyFormatRemaining.match(citeKeyConversionsRe);
		if (m.index > 0) {
			//add data before the conversion match to basekey
			basekey = basekey + citeKeyFormatRemaining.substr(0, m.index);
		}
		var flags = ""; // for now
		var f = citeKeyConversions[m[1]];
		if (typeof(f) == "function") {
			var value = f(flags, item);
			Zotero.debug("Got value " + value + " for %" + m[1]);
			//add conversion to basekey
			basekey = basekey + value;
		}
		citeKeyFormatRemaining = citeKeyFormatRemaining.substr(m.index + m.length);
		counter++;
	}
	if (citeKeyFormatRemaining.length > 0) {
		basekey = basekey + citeKeyFormatRemaining;
	}

	// for now, remove any characters not explicitly known to be allowed;
	// we might want to allow UTF-8 citation keys in the future, depending
	// on implementation support.
	//
	// no matter what, we want to make sure we exclude
	// " # % ' ( ) , = { } ~ and backslash
	// however, we want to keep the base characters 

	basekey = tidyAccents(basekey);
	basekey = basekey.replace(citeKeyCleanRe, "");
	var citekey = basekey;
	var i = 0;
	while(citekeys[citekey]) {
		i++;
		citekey = basekey + "-" + i;
	}
	citekeys[citekey] = true;
	return citekey;
}

function doExport() {
	//Zotero.write("% BibTeX export generated by Zotero "+Zotero.Utilities.getVersion());
	// to make sure the BOM gets ignored
	Zotero.write("\n");
	
	var first = true;
	var citekeys = new Object();
	var item;
	while(item = Zotero.nextItem()) {
		//don't export standalone notes and attachments
		if(item.itemType == "note" || item.itemType == "attachment") continue;

		// determine type
		var type = zotero2bibtexTypeMap[item.itemType];
		if (typeof(type) == "function") { type = type(item); }
		if(!type) type = "misc";
		
		// create a unique citation key
		var citekey = buildCiteKey(item, citekeys);
		
		// write citation key
		Zotero.write((first ? "" : "\n\n") + "@"+type+"{"+citekey);
		first = false;
		
		for(var field in fieldMap) {
			if(item[fieldMap[field]]) {
				writeField(field, item[fieldMap[field]]);
			}
		}

		if(item.reportNumber || item.issue || item.seriesNumber || item.patentNumber) {
			writeField("number", item.reportNumber || item.issue || item.seriesNumber|| item.patentNumber);
		}
		
		if (item.accessDate){
			var accessYMD = item.accessDate.replace(/\s*\d+:\d+:\d+/, "");
			writeField("urldate", accessYMD);
		}
		
		if(item.publicationTitle) {
			if(item.itemType == "bookSection" || item.itemType == "conferencePaper") {
				writeField("booktitle", item.publicationTitle);
			} else if(Zotero.getOption("useJournalAbbreviation") && item.journalAbbreviation){
				writeField("journal", item.journalAbbreviation);
			} else {
				writeField("journal", item.publicationTitle);
			}
		}
		
		if(item.publisher) {
			if(item.itemType == "thesis") {
				writeField("school", item.publisher);
			} else if(item.itemType =="report") {
				writeField("institution", item.publisher);
			} else {
				writeField("publisher", item.publisher);
			}
		}
		
		if(item.creators && item.creators.length) {
			// split creators into subcategories
			var author = "";
			var editor = "";
			var translator = "";
			var collaborator = "";
			var primaryCreatorType = Zotero.Utilities.getCreatorsForType(item.itemType)[0];
			for(var i in item.creators) {
				var creator = item.creators[i];
				var creatorString;

				if (creator.firstName) {
					var fname = creator.firstName.split(/\s*,!?\s*/);
					fname.push(fname.shift()); // If we have a Jr. part(s), it should precede first name
					creatorString = creator.lastName + ", " + fname.join(', ');
				} else {
					creatorString = creator.lastName;
				}
				
				creatorString = creatorString.replace(/[|\<\>\~\^\\\{\}]/g, mapEscape)
					.replace(/([\#\$\%\&\_])/g, "\\$1");
																			
				if (creator.fieldMode == true) { // fieldMode true, assume corporate author
					creatorString = "{" + creatorString + "}";
				} else {
					creatorString = creatorString.replace(/ (and) /gi, ' {$1} ');
				}

				if (creator.creatorType == "editor" || creator.creatorType == "seriesEditor") {
					editor += " and "+creatorString;
				} else if (creator.creatorType == "translator") {
					translator += " and "+creatorString;
				} else if (creator.creatorType == primaryCreatorType) {
					author += " and "+creatorString;
				} else {
					collaborator += " and "+creatorString;
				}
			}
			
			if(author) {
				writeField("author", "{" + author.substr(5) + "}", true);
			}
			if(editor) {
				writeField("editor", "{" + editor.substr(5) + "}", true);
			}
			if(translator) {
				writeField("translator",  "{" + translator.substr(5) + "}", true);
			}
			if(collaborator) {
				writeField("collaborator",  "{" + collaborator.substr(5) + "}", true);
			}
		}
		
		if(item.date) {
			var date = Zotero.Utilities.strToDate(item.date);
			// need to use non-localized abbreviation
			if(typeof date.month == "number") {
				writeField("month", months[date.month], true);
			}
			if(date.year) {
				writeField("year", date.year);
			}
		}
		
		if(item.extra) {
			// Export identifiers
			var extraFields = parseExtraFields(item.extra);
			for(var i=0; i<extraFields.length; i++) {
				var rec = extraFields[i];
				if(!rec.field || !revExtraIds[rec.field]) continue;
				var value = rec.value.trim();
				if(value) {
					writeField(revExtraIds[rec.field], '{'+value+'}', true);
					extraFields.splice(i, 1);
					i--;
				}
			}
			var extra = extraFieldsToString(extraFields); // Make sure we join exactly with what we split
			if(extra) writeField("note", extra);
		}
		
		if(item.tags && item.tags.length) {
			var tagString = "";
			for(var i in item.tags) {
				var tag = item.tags[i];
				tagString += ", "+tag.tag;
			}
			writeField("keywords", tagString.substr(2));
		}
		
		if(item.pages) {
			writeField("pages", item.pages.replace("-","--"));
		}
		
		// Commented out, because we don't want a books number of pages in the BibTeX "pages" field for books.
		//if(item.numPages) {
		//	writeField("pages", item.numPages);
		//}
		
		/* We'll prefer url over howpublished see 
		https://forums.zotero.org/discussion/24554/bibtex-doubled-url/#Comment_157802
		
		if(item.itemType == "webpage") {
			writeField("howpublished", item.url);
		}*/
		if (item.notes && Zotero.getOption("exportNotes")) {
			for(var i in item.notes) {
				var note = item.notes[i];
				writeField("annote", Zotero.Utilities.unescapeHTML(note["note"]));
			}
		}		
		
		if(item.attachments) {
			var attachmentString = "";
			
			for(var i in item.attachments) {
				var attachment = item.attachments[i];
				if(Zotero.getOption("exportFileData") && attachment.saveFile) {
					attachment.saveFile(attachment.defaultPath, true);
					attachmentString += ";" + encodeFilePathComponent(attachment.title)
						+ ":" + encodeFilePathComponent(attachment.defaultPath)
						+ ":" + encodeFilePathComponent(attachment.mimeType);
				} else if(attachment.localPath) {
					attachmentString += ";" + encodeFilePathComponent(attachment.title)
						+ ":" + encodeFilePathComponent(attachment.localPath)
						+ ":" + encodeFilePathComponent(attachment.mimeType);
				}
			}
			
			if(attachmentString) {
				writeField("file", attachmentString.substr(1));
			}
		}
		
		Zotero.write("\n}");
	}
}

var exports = {
	"doExport": doExport,
	"doImport": doImport,
	"setKeywordDelimRe": setKeywordDelimRe,
	"setKeywordSplitOnSpace": setKeywordSplitOnSpace
}

/*
 * new mapping table based on that from Matthias Steffens,
 * then enhanced with some fields generated from the unicode table.
 */

var mappingTable = {
	"\u00A0":"~", // NO-BREAK SPACE
	"\u00A1":"{\\textexclamdown}", // INVERTED EXCLAMATION MARK
	"\u00A2":"{\\textcent}", // CENT SIGN
	"\u00A3":"{\\textsterling}", // POUND SIGN
	"\u00A5":"{\\textyen}", // YEN SIGN
	"\u00A6":"{\\textbrokenbar}", // BROKEN BAR
	"\u00A7":"{\\textsection}", // SECTION SIGN
	"\u00A8":"{\\textasciidieresis}", // DIAERESIS
	"\u00A9":"{\\textcopyright}", // COPYRIGHT SIGN
	"\u00AA":"{\\textordfeminine}", // FEMININE ORDINAL INDICATOR
	"\u00AB":"{\\guillemotleft}", // LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
	"\u00AC":"{\\textlnot}", // NOT SIGN
	"\u00AD":"-", // SOFT HYPHEN
	"\u00AE":"{\\textregistered}", // REGISTERED SIGN
	"\u00AF":"{\\textasciimacron}", // MACRON
	"\u00B0":"{\\textdegree}", // DEGREE SIGN
	"\u00B1":"{\\textpm}", // PLUS-MINUS SIGN
	"\u00B2":"{\\texttwosuperior}", // SUPERSCRIPT TWO
	"\u00B3":"{\\textthreesuperior}", // SUPERSCRIPT THREE
	"\u00B4":"{\\textasciiacute}", // ACUTE ACCENT
	"\u00B5":"{\\textmu}", // MICRO SIGN
	"\u00B6":"{\\textparagraph}", // PILCROW SIGN
	"\u00B7":"{\\textperiodcentered}", // MIDDLE DOT
	"\u00B8":"{\\c\\ }", // CEDILLA
	"\u00B9":"{\\textonesuperior}", // SUPERSCRIPT ONE
	"\u00BA":"{\\textordmasculine}", // MASCULINE ORDINAL INDICATOR
	"\u00BB":"{\\guillemotright}", // RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
	"\u00BC":"{\\textonequarter}", // VULGAR FRACTION ONE QUARTER
	"\u00BD":"{\\textonehalf}", // VULGAR FRACTION ONE HALF
	"\u00BE":"{\\textthreequarters}", // VULGAR FRACTION THREE QUARTERS
	"\u00BF":"{\\textquestiondown}", // INVERTED QUESTION MARK
	"\u00C6":"{\\AE}", // LATIN CAPITAL LETTER AE
	"\u00D0":"{\\DH}", // LATIN CAPITAL LETTER ETH
	"\u00D7":"{\\texttimes}", // MULTIPLICATION SIGN
	"\u00D8":"{\\O}", // LATIN CAPITAL LETTER O WITH STROKE
	"\u00DE":"{\\TH}", // LATIN CAPITAL LETTER THORN
	"\u00DF":"{\\ss}", // LATIN SMALL LETTER SHARP S
	"\u00E6":"{\\ae}", // LATIN SMALL LETTER AE
	"\u00F0":"{\\dh}", // LATIN SMALL LETTER ETH
	"\u00F7":"{\\textdiv}", // DIVISION SIGN
	"\u00F8":"{\\o}", // LATIN SMALL LETTER O WITH STROKE
	"\u00FE":"{\\th}", // LATIN SMALL LETTER THORN
	"\u0131":"{\\i}", // LATIN SMALL LETTER DOTLESS I
	"\u0132":"IJ", // LATIN CAPITAL LIGATURE IJ
	"\u0133":"ij", // LATIN SMALL LIGATURE IJ
	"\u0138":"k", // LATIN SMALL LETTER KRA
	"\u0149":"'n", // LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
	"\u014A":"{\\NG}", // LATIN CAPITAL LETTER ENG
	"\u014B":"{\\ng}", // LATIN SMALL LETTER ENG
	"\u0152":"{\\OE}", // LATIN CAPITAL LIGATURE OE
	"\u0153":"{\\oe}", // LATIN SMALL LIGATURE OE
	"\u017F":"s", // LATIN SMALL LETTER LONG S
	"\u02B9":"'", // MODIFIER LETTER PRIME
	"\u02BB":"'", // MODIFIER LETTER TURNED COMMA
	"\u02BC":"'", // MODIFIER LETTER APOSTROPHE
	"\u02BD":"'", // MODIFIER LETTER REVERSED COMMA
	"\u02C6":"{\\textasciicircum}", // MODIFIER LETTER CIRCUMFLEX ACCENT
	"\u02C8":"'", // MODIFIER LETTER VERTICAL LINE
	"\u02C9":"-", // MODIFIER LETTER MACRON
	"\u02CC":",", // MODIFIER LETTER LOW VERTICAL LINE
	"\u02D0":":", // MODIFIER LETTER TRIANGULAR COLON
	"\u02DA":"o", // RING ABOVE
	"\u02DC":"\\~{}", // SMALL TILDE
	"\u02DD":"{\\textacutedbl}", // DOUBLE ACUTE ACCENT
	"\u0374":"'", // GREEK NUMERAL SIGN
	"\u0375":",", // GREEK LOWER NUMERAL SIGN
	"\u037E":";", // GREEK QUESTION MARK
	//Greek letters courtesy of spartanroc
	"\u0393":"$\\Gamma$", // GREEK Gamma
	"\u0394":"$\\Delta$", // GREEK Delta
	"\u0398":"$\\Theta$", // GREEK Theta
	"\u039B":"$\\Lambda$", // GREEK Lambda
	"\u039E":"$\\Xi$", // GREEK Xi
	"\u03A0":"$\\Pi$", // GREEK Pi
	"\u03A3":"$\\Sigma$", // GREEK Sigma
	"\u03A6":"$\\Phi$", // GREEK Phi
	"\u03A8":"$\\Psi$", // GREEK Psi
	"\u03A9":"$\\Omega$", // GREEK Omega
	"\u03B1":"$\\alpha$", // GREEK alpha
	"\u03B2":"$\\beta$", // GREEK beta
	"\u03B3":"$\\gamma$", // GREEK gamma
	"\u03B4":"$\\delta$", // GREEK delta
	"\u03B5":"$\\varepsilon$", // GREEK var-epsilon
	"\u03B6":"$\\zeta$", // GREEK zeta
	"\u03B7":"$\\eta$", // GREEK eta
	"\u03B8":"$\\theta$", // GREEK theta
	"\u03B9":"$\\iota$", // GREEK iota
	"\u03BA":"$\\kappa$", // GREEK kappa
	"\u03BB":"$\\lambda$", // GREEK lambda
	"\u03BC":"$\\mu$", // GREEK mu
	"\u03BD":"$\\nu$", // GREEK nu
	"\u03BE":"$\\xi$", // GREEK xi
	"\u03C0":"$\\pi$", // GREEK pi
	"\u03C1":"$\\rho$", // GREEK rho
	"\u03C2":"$\\varsigma$", // GREEK var-sigma
	"\u03C3":"$\\sigma$", // GREEK sigma
	"\u03C4":"$\\tau$", // GREEK tau
	"\u03C5":"$\\upsilon$", // GREEK upsilon
	"\u03C6":"$\\varphi$", // GREEK var-phi
	"\u03C7":"$\\chi$", // GREEK chi
	"\u03C8":"$\\psi$", // GREEK psi
	"\u03C9":"$\\omega$", // GREEK omega
	"\u03D1":"$\\vartheta$", // GREEK var-theta
	"\u03D2":"$\\Upsilon$", // GREEK Upsilon
	"\u03D5":"$\\phi$", // GREEK phi
	"\u03D6":"$\\varpi$", // GREEK var-pi
	"\u03F1":"$\\varrho$", // GREEK var-rho
	"\u03F5":"$\\epsilon$", // GREEK epsilon
	//Greek letters end
	"\u2000":" ", // EN QUAD
	"\u2001":"  ", // EM QUAD
	"\u2002":" ", // EN SPACE
	"\u2003":"  ", // EM SPACE
	"\u2004":" ", // THREE-PER-EM SPACE
	"\u2005":" ", // FOUR-PER-EM SPACE
	"\u2006":" ", // SIX-PER-EM SPACE
	"\u2007":" ", // FIGURE SPACE
	"\u2008":" ", // PUNCTUATION SPACE
	"\u2009":" ", // THIN SPACE
	"\u2010":"-", // HYPHEN
	"\u2011":"-", // NON-BREAKING HYPHEN
	"\u2012":"-", // FIGURE DASH
	"\u2013":"{\\textendash}", // EN DASH
	"\u2014":"{\\textemdash}", // EM DASH
	"\u2015":"{\\textemdash}", // HORIZONTAL BAR or QUOTATION DASH (not in LaTeX -- use EM DASH)
	"\u2016":"{\\textbardbl}", // DOUBLE VERTICAL LINE
	"\u2017":"{\\textunderscore}", // DOUBLE LOW LINE
	"\u2018":"{\\textquoteleft}", // LEFT SINGLE QUOTATION MARK
	"\u2019":"{\\textquoteright}", // RIGHT SINGLE QUOTATION MARK
	"`" : "\u2018", // LEFT SINGLE QUOTATION MARK
	"'" : "\u2019", // RIGHT SINGLE QUOTATION MARK
	"\u201A":"{\\quotesinglbase}", // SINGLE LOW-9 QUOTATION MARK
	"\u201B":"'", // SINGLE HIGH-REVERSED-9 QUOTATION MARK
	"\u201C":"{\\textquotedblleft}", // LEFT DOUBLE QUOTATION MARK
	"\u201D":"{\\textquotedblright}", // RIGHT DOUBLE QUOTATION MARK
	"\u201E":"{\\quotedblbase}", // DOUBLE LOW-9 QUOTATION MARK
	"\u201F":"{\\quotedblbase}", // DOUBLE HIGH-REVERSED-9 QUOTATION MARK
	"\u2020":"{\\textdagger}", // DAGGER
	"\u2021":"{\\textdaggerdbl}", // DOUBLE DAGGER
	"\u2022":"{\\textbullet}", // BULLET
	"\u2023":">", // TRIANGULAR BULLET
	"\u2024":".", // ONE DOT LEADER
	"\u2025":"..", // TWO DOT LEADER
	"\u2026":"{\\textellipsis}", // HORIZONTAL ELLIPSIS
	"\u2027":"-", // HYPHENATION POINT
	"\u202F":" ", // NARROW NO-BREAK SPACE
	"\u2030":"{\\textperthousand}", // PER MILLE SIGN
	"\u2032":"'", // PRIME
	"\u2033":"'", // DOUBLE PRIME
	"\u2034":"'''", // TRIPLE PRIME
	"\u2035":"`", // REVERSED PRIME
	"\u2036":"``", // REVERSED DOUBLE PRIME
	"\u2037":"```", // REVERSED TRIPLE PRIME
	"\u2039":"{\\guilsinglleft}", // SINGLE LEFT-POINTING ANGLE QUOTATION MARK
	"\u203A":"{\\guilsinglright}", // SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
	"\u203C":"!!", // DOUBLE EXCLAMATION MARK
	"\u203E":"-", // OVERLINE
	"\u2043":"-", // HYPHEN BULLET
	"\u2044":"{\\textfractionsolidus}", // FRACTION SLASH
	"\u2048":"?!", // QUESTION EXCLAMATION MARK
	"\u2049":"!?", // EXCLAMATION QUESTION MARK
	"\u204A":"7", // TIRONIAN SIGN ET
	"\u2070":"$^{0}$", // SUPERSCRIPT ZERO
	"\u2074":"$^{4}$", // SUPERSCRIPT FOUR
	"\u2075":"$^{5}$", // SUPERSCRIPT FIVE
	"\u2076":"$^{6}$", // SUPERSCRIPT SIX
	"\u2077":"$^{7}$", // SUPERSCRIPT SEVEN
	"\u2078":"$^{8}$", // SUPERSCRIPT EIGHT
	"\u2079":"$^{9}$", // SUPERSCRIPT NINE
	"\u207A":"$^{+}$", // SUPERSCRIPT PLUS SIGN
	"\u207B":"$^{-}$", // SUPERSCRIPT MINUS
	"\u207C":"$^{=}$", // SUPERSCRIPT EQUALS SIGN
	"\u207D":"$^{(}$", // SUPERSCRIPT LEFT PARENTHESIS
	"\u207E":"$^{)}$", // SUPERSCRIPT RIGHT PARENTHESIS
	"\u207F":"$^{n}$", // SUPERSCRIPT LATIN SMALL LETTER N
	"\u2080":"$_{0}$", // SUBSCRIPT ZERO
	"\u2081":"$_{1}$", // SUBSCRIPT ONE
	"\u2082":"$_{2}$", // SUBSCRIPT TWO
	"\u2083":"$_{3}$", // SUBSCRIPT THREE
	"\u2084":"$_{4}$", // SUBSCRIPT FOUR
	"\u2085":"$_{5}$", // SUBSCRIPT FIVE
	"\u2086":"$_{6}$", // SUBSCRIPT SIX
	"\u2087":"$_{7}$", // SUBSCRIPT SEVEN
	"\u2088":"$_{8}$", // SUBSCRIPT EIGHT
	"\u2089":"$_{9}$", // SUBSCRIPT NINE
	"\u208A":"$_{+}$", // SUBSCRIPT PLUS SIGN
	"\u208B":"$_{-}$", // SUBSCRIPT MINUS
	"\u208C":"$_{=}$", // SUBSCRIPT EQUALS SIGN
	"\u208D":"$_{(}$", // SUBSCRIPT LEFT PARENTHESIS
	"\u208E":"$_{)}$", // SUBSCRIPT RIGHT PARENTHESIS
	"\u20AC":"{\\texteuro}", // EURO SIGN
	"\u2100":"a/c", // ACCOUNT OF
	"\u2101":"a/s", // ADDRESSED TO THE SUBJECT
	"\u2103":"{\\textcelsius}", // DEGREE CELSIUS
	"\u2105":"c/o", // CARE OF
	"\u2106":"c/u", // CADA UNA
	"\u2109":"F", // DEGREE FAHRENHEIT
	"\u2113":"l", // SCRIPT SMALL L
	"\u2116":"{\\textnumero}", // NUMERO SIGN
	"\u2117":"{\\textcircledP}", // SOUND RECORDING COPYRIGHT
	"\u2120":"{\\textservicemark}", // SERVICE MARK
	"\u2121":"TEL", // TELEPHONE SIGN
	"\u2122":"{\\texttrademark}", // TRADE MARK SIGN
	"\u2126":"{\\textohm}", // OHM SIGN
	"\u212A":"K", // KELVIN SIGN
	"\u212B":"A", // ANGSTROM SIGN
	"\u212E":"{\\textestimated}", // ESTIMATED SYMBOL
	"\u2153":" 1/3", // VULGAR FRACTION ONE THIRD
	"\u2154":" 2/3", // VULGAR FRACTION TWO THIRDS
	"\u2155":" 1/5", // VULGAR FRACTION ONE FIFTH
	"\u2156":" 2/5", // VULGAR FRACTION TWO FIFTHS
	"\u2157":" 3/5", // VULGAR FRACTION THREE FIFTHS
	"\u2158":" 4/5", // VULGAR FRACTION FOUR FIFTHS
	"\u2159":" 1/6", // VULGAR FRACTION ONE SIXTH
	"\u215A":" 5/6", // VULGAR FRACTION FIVE SIXTHS
	"\u215B":" 1/8", // VULGAR FRACTION ONE EIGHTH
	"\u215C":" 3/8", // VULGAR FRACTION THREE EIGHTHS
	"\u215D":" 5/8", // VULGAR FRACTION FIVE EIGHTHS
	"\u215E":" 7/8", // VULGAR FRACTION SEVEN EIGHTHS
	"\u215F":" 1/", // FRACTION NUMERATOR ONE
	"\u2160":"I", // ROMAN NUMERAL ONE
	"\u2161":"II", // ROMAN NUMERAL TWO
	"\u2162":"III", // ROMAN NUMERAL THREE
	"\u2163":"IV", // ROMAN NUMERAL FOUR
	"\u2164":"V", // ROMAN NUMERAL FIVE
	"\u2165":"VI", // ROMAN NUMERAL SIX
	"\u2166":"VII", // ROMAN NUMERAL SEVEN
	"\u2167":"VIII", // ROMAN NUMERAL EIGHT
	"\u2168":"IX", // ROMAN NUMERAL NINE
	"\u2169":"X", // ROMAN NUMERAL TEN
	"\u216A":"XI", // ROMAN NUMERAL ELEVEN
	"\u216B":"XII", // ROMAN NUMERAL TWELVE
	"\u216C":"L", // ROMAN NUMERAL FIFTY
	"\u216D":"C", // ROMAN NUMERAL ONE HUNDRED
	"\u216E":"D", // ROMAN NUMERAL FIVE HUNDRED
	"\u216F":"M", // ROMAN NUMERAL ONE THOUSAND
	"\u2170":"i", // SMALL ROMAN NUMERAL ONE
	"\u2171":"ii", // SMALL ROMAN NUMERAL TWO
	"\u2172":"iii", // SMALL ROMAN NUMERAL THREE
	"\u2173":"iv", // SMALL ROMAN NUMERAL FOUR
	"\u2174":"v", // SMALL ROMAN NUMERAL FIVE
	"\u2175":"vi", // SMALL ROMAN NUMERAL SIX
	"\u2176":"vii", // SMALL ROMAN NUMERAL SEVEN
	"\u2177":"viii", // SMALL ROMAN NUMERAL EIGHT
	"\u2178":"ix", // SMALL ROMAN NUMERAL NINE
	"\u2179":"x", // SMALL ROMAN NUMERAL TEN
	"\u217A":"xi", // SMALL ROMAN NUMERAL ELEVEN
	"\u217B":"xii", // SMALL ROMAN NUMERAL TWELVE
	"\u217C":"l", // SMALL ROMAN NUMERAL FIFTY
	"\u217D":"c", // SMALL ROMAN NUMERAL ONE HUNDRED
	"\u217E":"d", // SMALL ROMAN NUMERAL FIVE HUNDRED
	"\u217F":"m", // SMALL ROMAN NUMERAL ONE THOUSAND…