word中复制到编辑器时，替换冗余HTML代码，清理HTML格式，这是最常见的问题，其中方法之一。

js函数如下：

function cWord(html)   
 {   
  html = REReplaceNocase(html,’<o:p>\s*<\/o:p>’,’’,’all’);   
  html = REReplaceNocase(html,’<o:p>.*?<\/o:p>’,’&nbsp;’,’all’);   
  html = REReplaceNocase(html,’\s*mso-[^:]+:[^;"]+;?’,’’,’all’);   
  html = REReplaceNocase(html,’\s*MARGIN: 0cm 0cm 0pt\s*;’,’’,’all’);   
  html = REReplaceNocase(html,’\s*MARGIN: 0cm 0cm 0pt\s*"’,’\"’,’all’);   
  html = REReplaceNocase(html,’\s*TEXT-INDENT: 0cm\s*;’,’’,’all’);   
  html = REReplaceNocase(html,’\s*TEXT-INDENT: 0cm\s*"’,’\"’,’all’);   
  html = REReplaceNocase(html,’\s*TEXT-ALIGN: [^\s;]+;?"’,’\"’,’all’);   
  html = REReplaceNocase(html,’\s*PAGE-BREAK-BEFORE: [^\s;]+;?"’,’\"’,’all’);   
  html = REReplaceNocase(html,’\s*FONT-VARIANT: [^\s;]+;?"’,’\"’,’all’);   
  html = REReplaceNocase(html,’\s*tab-stops:[^;"]*;?’,’’,’all’);   
  html = REReplaceNocase(html,’\s*tab-stops:[^"]*’,’’,’all’);   
  html = REReplaceNocase(html,’\s*face="[^"]*"’,’’,’all’);   
  html = REReplaceNocase(html,’\s*face=[^ >]*’,’’,’all’);   
  html = REReplaceNocase(html,’\s*FONT-FAMILY:[^;"]*;?’,’’,’all’);   
  html = REReplaceNocase(html,’<(\w[^>]*) class=([^ |>]*)([^>]*)’,’<\1’,’all’);   
  html = REReplaceNocase(html,’<(\w[^>]*) style="([^\"]*)"([^>]*)’,’<\1’,’all’);   
  html = REReplaceNocase(html,’\s*style="\s*"’,’’,’all’);   
  html = REReplaceNocase(html,’<SPAN\s*[^>]*>\s*&nbsp;\s*<\/SPAN>’,’&nbsp;’,’all’);   
  html = REReplaceNocase(html,’<SPAN\s*[^>]*><\/SPAN>’,’’,’all’);   
  html = REReplaceNocase(html,’<(\w[^>]*) lang=([^ |>]*)([^>]*)’,’<\1’,’all’);   
  html = REReplaceNocase(html,’<SPAN\s*>(.*?)<\/SPAN>’,’\1’,’all’);   
  html = REReplaceNocase(html,’<FONT\s*>(.*?)<\/FONT>’,’\1’,’all’);   
  html = REReplaceNocase(html,’<\\?\?xml[^>]*>’,’’,’all’);   
  html = REReplaceNocase(html,’<\/?\w+:[^>]*>’,’’,’all’);   
  html = REReplaceNocase(html,’<H\d>\s*<\/H\d>’,’’,’all’);  
  html = REReplaceNocase(html,’<H1([^>]*)>’,’<div\1><b><font size="6">’,’all’);   
  html = REReplaceNocase(html,’<H2([^>]*)>’,’<div\1><b><font size="5">’,’all’);   
  html = REReplaceNocase(html,’<H3([^>]*)>’,’<div\1><b><font size="4">’,’all’);   
  html = REReplaceNocase(html,’<H4([^>]*)>’,’<div\1><b><font size="3">’,’all’);   
  html = REReplaceNocase(html,’<H5([^>]*)>’,’<div\1><b><font size="2">’,’all’);   
  html = REReplaceNocase(html,’<H6([^>]*)>’,’<div\1><b><font size="1">’,’all’);  
  html = REReplaceNocase(html,’<\/H\d>’,’</font></b>’,’all’);   
  html = REReplaceNocase(html,’<(U|I|STRIKE)>&nbsp;<\/\1>’,’&nbsp;’,’all’);   
  html = REReplaceNocase(html,’<([^\s>]+)[^>]*>\s*<\/\1>’,’’,’all’);   
  html = REReplaceNocase(html,’<([^\s>]+)[^>]*>\s*<\/\1>’,’’,’all’);   
  html = REReplaceNocase(html,’<([^\s>]+)[^>]*>\s*<\/\1>’,’’,’all’);   
  html = REReplaceNocase(html,’(<P)([^>]*>.*?)(<\/P>)’,’<div\2’,’all’);   
  return html;   
 } 

word中复制到编辑器时,替换冗余HTML代码,清理HTML格式