☰

MRLookup

Extract BibTeX data automatically and modify BibTeX Key to AUTHOR_YEAR_TITLE.

当前为 2018-05-28 提交的版本，查看 最新版本。

  1. // ==UserScript==
  2. // @namespace         vanabeljs
  3. // @name              MRLookup
  4. // @description       Extract BibTeX data automatically and modify BibTeX Key to AUTHOR_YEAR_TITLE.
  5. // @description:ZH-CN 自动提取BibTeX数据并修改BibTeX关键字为AUTHOR_YEAR_TITLE的形式.
  6. // @copyright         2017, Van Abel (https://home.vanabel.cn)
  7. // @license           OSI-SPDX-Short-Identifier
  8. // @version           1.5.2
  9. // @include           https://www.ams.org/mrlookup
  10. // @include           https://mathscinet.ams.org/mrlookup
  11. // @include           http://mathscinet.ams.org/mrlookup
  12. // @include           http://www.ams.org/mathscinet/search/publications.html?fmt=bibtex*
  13. // @include           http://mathscinet.ams.org/mathscinet/search/publications.html?fmt=bibtex*
  14. // @include           https://mathscinet.ams.org/mathscinet/search/publications.html?fmt=bibtex*
  15. // @include           http://ams2.math.uni-bielefeld.de/mathscinet/search/publications.html?fmt=bibtex*
  16. // @include           http://mathscinet.ams.org/mathscinet/clipboard.html
  17. // @grant             GM_setClipboard
  18. // ==/UserScript==
  19.  
  20. // ==OpenUserJS==
  21. // @author Van Abel
  22. // ==/OpenUserJS==
  23.  
  24. /**
  25.   *
  26.   * Please begin typing or paste your Userscript now.
  27.   *
  28.   */
  29.  
  30. /*The first word to ignore in title*/
  31. var IgnoreStringInTitle = [
  32.   'a',
  33.   'an',
  34.   'on',
  35.   'the',
  36.   'another'
  37. ];
  38. function IgnoreStringToRegExp(arr) {
  39.   var regexp = '^(';
  40.   var arrlen = arr.length;
  41.   for (var i = 0; i < arrlen; i++) {
  42.     if (i == arrlen - 1) {
  43.       regexp += '(' + arr[i] + ')';
  44.     } else {
  45.       regexp += '(' + arr[i] + ')|';
  46.     }
  47.   }
  48.   regexp += ')\\s+';
  49.   return regexp;
  50. }//console.log(IgnoreStringToRegExp(IgnoreStringInTitle));
  51. /*split bibdata*/
  52.  
  53. function parseBibTexLine(text) {
  54.   var m = text.match(/^\s*(\S+)\s*=\s*/);
  55.   if (!m) {
  56.     console.log('line: "' + text + '"');
  57.     throw new Error('Unrecogonised line format');
  58.   }
  59.   var name = m[1];
  60.   var search = text.slice(m[0].length);
  61.   var re = /[\n\r,{}]/g;
  62.   var braceCount = 0;
  63.   var length = m[0].length;
  64.   do {
  65.     m = re.exec(search);
  66.     if (m[0] === '{') {
  67.       braceCount++;
  68.     } else if (m[0] === '}') {
  69.       if (braceCount === 0) {
  70.         throw new Error('Unexpected closing brace: "}"');
  71.       }
  72.       braceCount--;
  73.     }
  74.   } while (braceCount > 0);
  75.   return {
  76.     field: name,
  77.     value: search.slice(0, re.lastIndex),
  78.     length: length + re.lastIndex + m[0].length
  79.   };
  80. }
  81. function parseBibTex(text) {
  82.   var m = text.match(/^\s*@([^{]+){([^,\n]+)[,\n]/);
  83.   if (!m) {
  84.     throw new Error('Unrecogonised header format');
  85.   }
  86.   var result = {
  87.     typeName: m[1].trim(),
  88.     citationKey: m[2].trim()
  89.   };
  90.   text = text.slice(m[0].length).trim();
  91.   while (text[0] !== '}') {
  92.     var pair = parseBibTexLine(text);
  93.     result[pair.field] = pair.value;
  94.     text = text.slice(pair.length).trim();
  95.   }
  96.   return result;
  97. }
  98. var els = document.getElementsByTagName('pre');
  99. for (var i = 0, l = els.length; i < l; i++) {
  100.   var el = els[i];
  101.   var bibdata = parseBibTex(el.innerHTML);
  102.   /*Extract author*/
  103.   //var aureg = new RegExp('(?:(\\w+),(?:[^,}](?!and))+)+', 'g');
  104.   //console.log(audata.match(aureg));
  105.   var audata = bibdata.AUTHOR;
  106.   //clean author include \v+space and $\cmd$
  107.   audata = audata.replace(/\\[a-z]\s|(\$.*?\$)|(\\")/gi, '');
  108.   //console.log(audata);
  109.   //remove doublw , in one name
  110.   audata = audata.replace(/(?:(?:and)?(\w+,\s*\w+\.)(,.*?)?)+/g, '$1');
  111.   //console.log(audata);
  112.   //extract first name
  113.   audata = audata.replace(/(?:(\w+),(?:[^,}](?!and))+)+/g, '$1');
  114.   //console.log(audata);
  115.   var cleanreg = new RegExp('\\s*and\\s*|[{}\\\\\'\\\\\\"]', 'g');
  116.   //console.log(cleanreg);
  117.   var au = audata.replace(cleanreg, '');
  118.   //console.log(au);
  119.   /*Extract Year*/
  120.   var year = bibdata.YEAR.replace(cleanreg, '');
  121.   //console.log(year);
  122.   /*Extract Title*/
  123.   var title = bibdata.TITLE;
  124.   //clean \cmd+space
  125.   title = title.replace(/\\\w+\s*/g, '');
  126.   var titleclean = new RegExp(IgnoreStringToRegExp(IgnoreStringInTitle), 'gi');
  127.   //we don't need to clean and, but we need to clean -,{,},: and ,
  128.   //var cleanreg = new RegExp('[{}:-]|,|(\\r\\s*)|(\\n\\s*)', 'g');
  129.   title = title.replace(/[\\\'\"{}:-]|,|(\r\s*)|(\n\s*)/g, '');
  130.   //var cleandollar = new RegExp('\\$.*?\\$', 'g');
  131.   title = title.replace(/\$.*?\$/g, '');
  132.   var titlefinal = title.replace(titleclean, '');
  133.   while (title != titlefinal) {
  134.     //recursively remove the ignore word
  135.     title = titlefinal;
  136.     titlefinal = title.replace(titleclean, '');
  137.   } //var titlereg = new RegExp('(\\w+)(\\s*\\w+)*', 'gi');
  138.  
  139.   title = title.replace(/(\w+).*$/gi, '$1').replace(/\s*/g, '');
  140.   var bibkey = au + year + title;
  141.   //console.log(bibkey);
  142.   var bibkeyreg = new RegExp('MR\\d+', 'gi');
  143.   el.innerHTML = el.innerHTML.replace(bibkeyreg, bibkey);
  144.   /*click to copy to clipboard*/
  145.   el.addEventListener('click', function () {
  146.     //Actual new line break
  147.     //var linebreakreg = new RegExp('\\r|\\n', 'g');
  148.     var bibdata_lb = this.innerHTML.replace(/\r|\n/g, '\r\n').replace(/^\r\n/g, '').replace(/\s*$/g, '\r\n').replace(/\r\n\r\n/g, '\r\n');
  149.     GM_setClipboard(bibdata_lb);
  150.   });
  151. }