Automatic Feed Translation

From AwasuWiki
Revision as of 04:18, 18 January 2010 by Kevotheclone (talk | contribs)
Jump to: navigation, search

Automatic Feed Translation

Using the XSLT file listed below you can automatically translate a foreign language feed into your language, utilizing Google's Translation API, whenever Awasu updates the associated Channel. Here is the list of supported languages.

Customising the XSLT file

Your language

There is a constant in the XSLT file called "yourLanguage" which you can change to a specific two-character language code of your language. If your language is English, the XSLT file below should work well without any modification.

Feed language

There is a constant in the XSLT file called "feedLanguage" which you can change to a specific two-character language code if you know the language of the feed; this will improve Google's language translation accuracy. Leaving the "feedLanguage" constant blank (empty quotation marks: "") should still work as Google will attempt to guess the feed's langauge.

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
                              xmlns:msxsl="urn:schemas-microsoft-com:xslt"
                              xmlns:ktc="http://www.awasu.com/forums/profile.php?mode=viewprofile&u=24618"
                              xmlns:atom="http://www.w3.org/2005/Atom"
                              xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <xsl:output method="xml" version="1.0" encoding="UTF-8" indent="yes"/>
  <msxsl:script language="JScript" implements-prefix="ktc"><![CDATA[
  /*
  Name: AutoTranslate.xsl

  Description: Automatically translates Atom and RSS feed items received in Awasu to your language using Google's translation service.

  Author: kevotheclone (http://www.awasu.com/forums/profile.php?mode=viewprofile&u=24618)

  For additional documentation: http://www.awasu.com/wiki/Automatic_Feed_Translation
  */

  // Constants...

  // Don't edit these two constants until Google says otherwise.
  var baseURL = "http://ajax.googleapis.com/ajax/services/language/translate";
  var version = "v=1.0";

  /*
  Change this constant (feedLanguage) to the two-character language code of the feed (if known).
  This will improve Google language translation accuracy.
  
  Leave is blank (empty quotation marks: "") if the feed language is unknown or 
  the feed contains multiple languages. Google will attempt to guess the langauge
  each time the translateLang() function is called.
  
  Supported language codes are listed here:
  http://code.google.com/apis/ajaxlanguage/documentation/reference.html#LangNameArray
  */
  var feedLanguage = "";
  
  /*
  Change this constant (yourLanguage) to your desired two-character language code.
  Supported language codes are listed here:
  http://code.google.com/apis/ajaxlanguage/documentation/reference.html#LangNameArray
  */
  var yourLanguage = "en";

  var xmlhttp = new ActiveXObject("Msxml2.XMLHTTP.4.0");
  var cache = {}; // Case-sensitive results cache.
  var chunks;     // Array of Strings, for breaking up large text into multiple HTTP calls. 

  var WshShell = new ActiveXObject("WScript.Shell"); // For logging error messages.

  function translateText(textToTranslate) 
  {
    var translatedText = "";
    try
    {
      textToTranslate = textToTranslate.replace(/^\s+|\s+$/g,"");             // Remove leading and trailing whitespace.
      textToTranslate = textToTranslate.replace(/^\s*|\s(?=\s)|\s*$/g," "); // Replace repeated spaces, newlines and tabs with a single space.

      if (cache[textToTranslate])         // It's it in the cache,
        return cache[textToTranslate]; // return it.

      if (textToTranslate)
      {

        chunks = textToTranslate.match(/.{2000,4000}\b|.+$/g);

        for (var i=0; i<chunks.length; i++)
        {
          xmlhttp.open("POST", baseURL, false);
          xmlhttp.setRequestHeader("Referer", "http://www.awasu.com/forums/profile.php?mode=viewprofile&u=24618");
          xmlhttp.setRequestHeader("Content-Type", "application/x-www-form-urlencoded");
          xmlhttp.send("v=1.0&q=" + encodeURIComponent(chunks[i]) + "&langpair=" + feedLanguage + "|" + yourLanguage);
          eval("var response = " + xmlhttp.responseText);
          /*
          If successful, concatenate the translated chunk of text to our output buffer,
          else, if any chunk fails return the original untranslated text.
          */
          if (xmlhttp.status == 200)
          {
            if (response.responseStatus == 200) // check responseStatus, 200=success, 400=error
              translatedText += encodeURI(response.responseData.translatedText);
            else
            {
              WshShell.LogEvent(1, "Error from Google's Translate service.\r\n\r\nStatus code and description:\r\n" + 
                                   response.responseStatus + " - " + response.responseDetails + "\r\n\r\nText to translate:\r\n" + textToTranslate);
              return textToTranslate;
            }
          }
          else
          {
            WshShell.LogEvent(1, "Error connecting to Google's translate service.\r\n\r\nHTTP Status code and description:\r\n" + 
                                 xmlhttp.status + " - " + xmlhttp.statusText);
            return textToTranslate;
          }
        }
        cache[textToTranslate] = decodeURI(translatedText); // Add the results to the cache.
        return decodeURI(translatedText);
      }
      else // The element's value is a null string.
      {
        cache[textToTranslate] = "";
        return "";
      }
    }
    catch(e)
    {
      cache[textToTranslate] = e;
      return e;
    }
  }

  function itsBetterWithBacon(textToTranslate)
  {
    return "bacon: " + textToTranslate + " :bacon";
  }

]]></msxsl:script>
  <xsl:template match="node()|@*">
    <xsl:copy>
      <xsl:apply-templates select="@*"/>
      <xsl:apply-templates/>
    </xsl:copy>
  </xsl:template>
  
  <!-- Atom-based template match patterns -->
  <xsl:template match="/atom:feed/atom:title | /atom:feed/atom:subtitle | /atom:feed/atom:entry/atom:title | /atom:feed/atom:entry/atom:content | /atom:feed/atom:entry/atom:category/@term">
    <xsl:call-template name="translateText"/>
  </xsl:template>

  <!-- RSS-based template match patterns -->
  <xsl:template match="/rss/channel/title | /rss/channel/description | /rss/channel/item/title | /rss/channel/item/description | /rss/channel/item/content:encoded | /rss/channel/item/category">
    <xsl:call-template name="translateText"/>
  </xsl:template>

<!-- Named template that calls the embedded JavaScript function that translates the text -->
  <xsl:template name="translateText">
    <xsl:variable name="elementName" select="name()"/>
    <xsl:element name="{name(.)}">
      <xsl:value-of select="ktc:translateText(normalize-space(.))"/>
    </xsl:element>
  </xsl:template>
</xsl:stylesheet>