Jump to content

Wikipedia:AutoEd/htmltowikitext.js

From Wikipedia, the free encyclopedia
//Convert HTML to wikitext
function autoEdHTMLtoWikitext(str) {
  // <b> and <i> tags
  str = str.replace(/<B[ ]*>((?:[^<>]|<[a-z][^<>]*\/>|<([a-z]+)(?:| [^<>]*)>[^<>]*<\/\3>)*?)<\/\1[ ]*>/gi,  "'''$1'''");
  str = str.replace(/<I[ ]*>((?:[^<>]|<[a-z][^<>]*\/>|<([a-z]+)(?:| [^<>]*)>[^<>]*<\/\3>)*?)<\/\1[ ]*>/gi,  "''$1''");
  // </br>, <\br>, <br\>, <BR />, ...
  str = str.replace(/<[\\\/]+BR[\\\/\s]*>/gim, '<br />');
  str = str.replace(/<[\\\/\s]*BR[\s]*[\\\/]+[\s]*>/gim, '<br />');
  // <.br>, <br.>, <Br>, ...
  str = str.replace(/<[\s\.]*BR[\s\.]*>/gim, '<br>');
  // <br>>, <<br />, <<br >> ...
  str = str.replace(/<[\s]*(<br[\s\/]*>)/gim, '$1');
  str = str.replace(/(<br[\s\/]*>)[\s]*>/gim, '$1');
  // <hr>
  str = str.replace(/([\r\n])[\t ]*<[\\\/\. ]*HR[\\\/\. ]*>/gi, '$1----');
  // str = str.replace(/(.)<[\\\/\. ]*HR[\\\/\. ]*>/gi, '$1\n----'); // Breaks wikitables
  // Not really an HTML-to-wikitext fix, but close enough
  str = str.replace(/([^>\s]\s*)<[\\\/\s]*REFERENCES[\\\/\s]*>/gim, '$1<references />');
  // Repeated references tag
  str = str.replace(/(<references \/>)[\s]*\1/gim, '$1');
  // Make sure <H1>, ..., <H6> is after a newline
  str = str.replace(/([^\r\n ])[\t ]*(<H[1-6][^<>]*>)/gim, '$1\n$2');
  // Make sure </H1>, ..., </H6> is before a newline
  str = str.replace(/(<\/H[1-6][^<>]*>)[\t ]*([^\r\n ])/gim, '$1\n$2');
  // Remove newlines from inside <H1>, ..., <H6>
  var loopcount = 0;
  while( str.search( /<H([1-6])[^<>]*>(?:[^<>]|<\/?[^\/h\r\n][^<>]*>)*?<\/H\1[^<>]*>/gim ) >= 0 && loopcount <= 10 ) {
    str = str.replace(/(<H)([1-6])([^<>]*>(?:[^<>]|<\/?[^\/h\r\n][^<>]*>)*?)[\r\n]((?:[^<>]|<\/?[^\/h\r\n][^<>]*>)*?<\/H)\2([^<>]*>)/gim, '$1$2$3 $4$2$5');
    loopcount++;
  }
  // Replace <H1>, ..., <H6> with wikified section headings
  str = str.replace(/(^|[\r\n])[\t ]*<H1[^<>]*>([^\r\n]*?)<\/H1[\r\n\t ]*>[\t ]*([\r\n]|$)/gim, '$1=$2=$3');
  str = str.replace(/(^|[\r\n])[\t ]*<H2[^<>]*>([^\r\n]*?)<\/H2[\r\n\t ]*>[\t ]*([\r\n]|$)/gim, '$1==$2==$3');
  str = str.replace(/(^|[\r\n])[\t ]*<H3[^<>]*>([^\r\n]*?)<\/H3[\r\n\t ]*>[\t ]*([\r\n]|$)/gim, '$1===$2===$3');
  str = str.replace(/(^|[\r\n])[\t ]*<H4[^<>]*>([^\r\n]*?)<\/H4[\r\n\t ]*>[\t ]*([\r\n]|$)/gim, '$1====$2====$3');
  str = str.replace(/(^|[\r\n])[\t ]*<H5[^<>]*>([^\r\n]*?)<\/H5[\r\n\t ]*>[\t ]*([\r\n]|$)/gim, '$1=====$2=====$3');
  str = str.replace(/(^|[\r\n])[\t ]*<H6[^<>]*>([^\r\n]*?)<\/H6[\r\n\t ]*>[\t ]*([\r\n]|$)/gim, '$1======$2======$3');

  return str;
}