compromise/src/term/render/renderHtml.js

natural language processing in the browser

'use strict';
//turn xml special characters into apersand-encoding.
//i'm not sure this is perfectly safe.
const escapeHtml = (s) => {
  const HTML_CHAR_MAP = {
    '<': '&lt;',
    '>': '&gt;',
    '&': '&amp;',
    '"': '&quot;',
    '\'': '&#39;',
    ' ': '&nbsp;'
  };
  return s.replace(/[<>&"' ]/g, function(ch) {
    return HTML_CHAR_MAP[ch];
  });
};

//remove html elements already in the text
//not tested!
//http://stackoverflow.com/questions/295566/sanitize-rewrite-html-on-the-client-side
const sanitize = (html) => {
  const tagBody = '(?:[^"\'>]|"[^"]*"|\'[^\']*\')*';
  const tagOrComment = new RegExp(
    '<(?:'
    // Comment body.
    + '!--(?:(?:-*[^->])*--+|-?)'
    // Special "raw text" elements whose content should be elided.
    + '|script\\b' + tagBody + '>[\\s\\S]*?</script\\s*'
    + '|style\\b' + tagBody + '>[\\s\\S]*?</style\\s*'
    // Regular name
    + '|/?[a-z]'
    + tagBody
    + ')>',
    'gi');
  let oldHtml;
  do {
    oldHtml = html;
    html = html.replace(tagOrComment, '');
  } while (html !== oldHtml);
  return html.replace(/</g, '&lt;');
}

//turn the term into ~properly~ formatted html
const renderHtml = function(t) {
  let classes = Object.keys(t.tag).filter((tag) => tag !== 'Term');
  classes = classes.map(c => 'nlp' + c);
  classes = classes.join(' ');
  let text = sanitize(t.text)
  text = escapeHtml(text);
  let el = '<span class="' + classes + '">' + text + '</span>';
  return escapeHtml(t.whitespace.before) + el + escapeHtml(t.whitespace.after)
};

module.exports = renderHtml;