ColdFusion的XML字符編碼部2

Question

我有代碼散落等ÃÂ&xA7;用於我已經寫下面的代碼段，以除去或與可接受的值 1.替換變音符號等 一個UTF-8 XML文件有更好的方法來做到這個？ 2.當我在一些大的XML文件（> 50MB）上運行時，可能會發生內存不足錯誤。如果沒有更好的方法，我該如何優化它，避免OOM錯誤？

<cffile 
    action="read" 
    file="#ExpandPath('./xs.xml')#" 
    variable="myfile"/> 

<cfset myfile =ReReplace(myfile,'&##xC2;&##x2013;','.','all')/> 
<cfset myfile =ReReplace(myfile,'&##xC2;&##x2019;','''','all')/> 
<cfset myfile =ReReplace(myfile,'&##xC2;&##x201D;','"','all')/> 

<cfset myfile =ReReplace(myfile,'&##xC3;&##x192;&##xC2;&##xA7;','c','all')/> 
<cfset myfile =ReReplace(myfile,'&##xC3;&##xA7;','c','all')/> 
<cfset myfile =ReReplace(myfile,'&##xC3;&##xA9;','e','all')/> 
<cfset myfile =ReReplace(myfile,'&##xC3;&##x201A;&##xC2;&##x2022;','(*)','all')/> 
<cfset myfile =ReReplace(myfile,'&##xC3;&##x192;&##xC2;&##x201A;\?','(*)','all')/> 
<cfset myfile =ReReplace(myfile,'&##xC3;&##x201A;&##xC2;&##xB7;','-','all')/> 
<cfset myfile =ReReplace(myfile,'&##xC3;&##x201A;&##xC2;&##x2018;','''','all')/> 
<cfset myfile =ReReplace(myfile,' &##xC3;&##x201A;&##xC2;&##x201C;',' "','all')/> 

<cfset myfile =ReReplace(myfile,'&##xE2;&##x20AC;&##x201C;','-','all')/> 
<cfset myfile =ReReplace(myfile,'&##xE2;&##x20AC;&##x2122;','''','all')/> 
<cfset myfile =ReReplace(myfile,' &##xE2;&##x20AC;&##x153;',' "','all')/> 
<cfset myfile =ReReplace(myfile,'&##xE2;&##x20AC;&##x153;','-','all')/> 
<cfset myfile =ReReplace(myfile,'&##xE2;&##x20AC;&##xFFFD; ','" ','all')/> 
<cfset myfile =ReReplace(myfile,'&##xE2;&##x20AC;&##xFFFD;','-','all')/> 
<cfset myfile =ReReplace(myfile,'&##xE2;&##x201E;&##xA2;','(TM)','all')/> 
<cfset myfile =ReReplace(myfile,'&##xE2;&##x20AC;&##xA2;','(*)','all')/> 

<cfset myfile =ReReplace(myfile,'&##xEF;&##x201A;&##xA7;','(*)','all')/> 

<cfset myfile =ReReplace(myfile,'(&##[^;]*;)','','all')/> 

<cffile action="write" 
    file="#ExpandPath('./xs_new.xml')#" 
    output="#myfile#"/> 

感謝

Answer 1

使用ColdFusion的文件功能，在同一時間在同一行的工作，而不是讀取整個事情到內存：

<cfscript> 
myfile = FileOpen(ExpandPath('./xs.xml'), "read"); 
myNewFile = FileOpen(ExpandPath('./xs_new.xml'), "write"); 

while(NOT FileisEOF(myfile)) { 
    line = FileReadLine(myfile); // read line 

    line = ReReplace(line,'&##xC2;&##x2013;','.','all'); 
    line = ReReplace(line,'&##xC2;&##x2019;','''','all'); 
    line = ReReplace(line,'&##xC2;&##x201D;','"','all'); 

    line = ReReplace(line,'&##xC3;&##x192;&##xC2;&##xA7;','c','all'); 
    line = ReReplace(line,'&##xC3;&##xA7;','c','all'); 
    line = ReReplace(line,'&##xC3;&##xA9;','e','all'); 
    line = ReReplace(line,'&##xC3;&##x201A;&##xC2;&##x2022;','(*)','all'); 
    line = ReReplace(line,'&##xC3;&##x192;&##xC2;&##x201A;\?','(*)','all'); 
    line = ReReplace(line,'&##xC3;&##x201A;&##xC2;&##xB7;','-','all'); 
    line = ReReplace(line,'&##xC3;&##x201A;&##xC2;&##x2018;','''','all'); 
    line = ReReplace(line,' &##xC3;&##x201A;&##xC2;&##x201C;',' "','all'); 

    line = ReReplace(line,'&##xE2;&##x20AC;&##x201C;','-','all'); 
    line = ReReplace(line,'&##xE2;&##x20AC;&##x2122;','''','all'); 
    line = ReReplace(line,' &##xE2;&##x20AC;&##x153;',' "','all'); 
    line = ReReplace(line,'&##xE2;&##x20AC;&##x153;','-','all'); 
    line = ReReplace(line,'&##xE2;&##x20AC;&##xFFFD; ','" ','all'); 
    line = ReReplace(line,'&##xE2;&##x20AC;&##xFFFD;','-','all'); 
    line = ReReplace(line,'&##xE2;&##x201E;&##xA2;','(TM)','all'); 
    line = ReReplace(line,'&##xE2;&##x20AC;&##xA2;','(*)','all'); 

    line = ReReplace(line,'&##xEF;&##x201A;&##xA7;','(*)','all'); 

    line = ReReplace(line,'(&##[^;]*;)','','all'); 

    fileWrite(line); 
} 

FileClose(myfile); 
FileClose(myNewFile); 
</cfscript>