com.sta.cts.HTML2XML Maven / Gradle / Ivy

Go to download

package com.sta.cts;

import java.util.Enumeration;
import java.util.Hashtable;

import java.io.IOException;

import com.sta.mlogger.MLogger;

/**
 * Name: HTML2XML
 * Description: Hilfsklasse, um HTML nach XML (nicht XHTML!) zu konvertieren.
 * 
 * Comment: ...
 * 
 * Copyright: Copyright (c) 2016, 2018, 2019
 * Company: >StA-Soft<
 * @author StA
 * @version 1.0
 */

public class HTML2XML
{

  /**
   * Tags, die als leere Tags vorkommen (k?nnen).
   */

  private static Hashtable statEmptyTags = new Hashtable();

  static
  {
    statEmptyTags.put("meta", 1);
    statEmptyTags.put("link", 1);
    statEmptyTags.put("br", 1);
    statEmptyTags.put("img", 1);
    statEmptyTags.put("col", 1);
    statEmptyTags.put("hr", 1);
  }

  /**
   * Entities.
   */

  private static Hashtable statEntities = new Hashtable();

  /**
   * Entities vorbereiten.
   */

  static
  {
    // https://wiki.selfhtml.org/wiki/Referenz:HTML/Zeichenreferenz
    String[] entities = {
      "nbsp",
      "iexcl",
      "cent",
      "pound",
      "curren",
      "yen",
      "brvbar",
      "sect",
      "uml",
      "copy",
      "ordf",
      "laquo",
      "not",
      "shy",
      "reg",
      "macr",

      "deg",
      "plusmn",
      "sup2",
      "sup3",
      "acute",
      "micro",
      "para",
      "middot",
      "cedil",
      "sup1",
      "ordm",
      "raquo",
      "frac14",
      "frac12",
      "frac34",
      "iquest",

      "Agrave",
      "Aacute",
      "Acirc",
      "Atilde",
      "Auml",
      "Aring",
      "AElig",
      "Ccedil",
      "Egrave",
      "Eacute",
      "Ecirc",
      "Euml",
      "Igrave",
      "Iacute",
      "Icirc",
      "Iuml",

      "ETH",
      "Ntilde",
      "Ograve",
      "Oacute",
      "Ocirc",
      "Otilde",
      "Ouml",
      "times",
      "Oslash",
      "Ugrave",
      "Uacute",
      "Ucirc",
      "Uuml",
      "Yacute",
      "THORN",
      "szlig",

      "agrave",
      "aacute",
      "acirc",
      "atilde",
      "auml",
      "aring",
      "aelig",
      "ccedil",
      "egrave",
      "eacute",
      "ecirc",
      "euml",
      "igrave",
      "iacute",
      "icirc",
      "iuml",

      "eth",
      "ntilde",
      "ograve",
      "oacute",
      "ocirc",
      "otilde",
      "ouml",
      "divide",
      "oslash",
      "ugrave",
      "uacute",
      "ucirc",
      "uuml",
      "yacute",
      "thorn",
      "yuml"
    };
    for (int i = 0; i < entities.length; i++)
    {
      statEntities.put(entities[i], 0xa0 + i);
    }
    statEntities.put("mdash", 0x2014);
  }

  /**
   * Entities ermitteln.
   * @return Entities
   */

  public static Hashtable getEntities()
  {
    return statEntities;
  }

  /**
   * HTML nach XML konvertieren.
   * @param xg XML-Generator (Ziel)
   * @param xs XML-Scanner (Quelle)
   * @throws IOException im Fehlerfall
   */

  public static void runConvHTML2XML(XMLGenerator xg, XMLScanner xs) throws IOException
  {
    while (true)
    {
      // Token holen
      Object obj = xs.getToken();
      // Falls es sich um Inhalt (Strings) handelt: einfach kopieren
      while ((obj != null) && (obj instanceof String))
      {
        xg.putContent((String) obj);
        obj = xs.getToken();
      }
      // Falls Dateiende oder kein XMLTag: Ende
      if ((obj == null) || (!(obj instanceof XMLTag)))
      {
        return;
      }
      // Token ist ein XMLTag
      XMLTag tag = (XMLTag) obj;
      if (!tag.isOpen())
      {
        xs.ungetToken(tag);
        break;
      }
      // Falls ?ffnendes Tag: Tag auch in der Zieldatei ?ffnen
      String tagname = tag.getName();
      xg.openTag(tagname);
      // Alle Attribute kopieren
      Enumeration e = tag.getAttrNames();
      while ((e != null) && e.hasMoreElements())
      {
        String attrname  = (String) e.nextElement();
        String attrvalue = tag.getAttr(attrname);
        xg.putAttr(attrname, attrvalue);
      }
      // Falls auch schlie?endes Tag: Token zur?cklegen
      if (tag.isClose())
      {
        tag.resOpen();
        xs.ungetToken(tag);
      }
      else if (statEmptyTags.containsKey(tagname))
      {
        tag.resOpen();
        tag.setClose();
        xs.ungetToken(tag);
      }
      else
      {
        // Inhalt konvertieren, falls vorhanden
        runConvHTML2XML(xg, xs);
      }
      // Jetzt mu? ein schlie?endes Tag mit gleichem Namen kommen
      xg.closeTag(tagname);
      String msg = " expected.";
      obj = xs.getToken();
      if (obj == null)
      {
        MLogger.wrn(msg + " Unexpected end of file.");
        continue;
      }
      if (!(obj instanceof XMLTag))
      {
        xs.ungetToken(obj);
        MLogger.wrn(msg + " Unexpected: " + obj.toString());
        continue;
      }
      tag = (XMLTag) obj;
      if (tag.isOpen() || !tag.isClose() || !tag.getName().equals(tagname))
      {
        xs.ungetToken(obj);
        MLogger.wrn(msg + " Found: <" + tag.getName() + "...>.");
        continue;
      }
    }
  }

  /**
   * HTML nach XML konvertieren.
   * @param pDstFileName HTML-Dateiname
   * @param pSrcFileName XML-Dateiname
   * @throws IOException im Fehlerfall
   */

  public static void runConvHTML2XML(String pDstFileName, String pSrcFileName) throws IOException
  {
    XMLScanner xs = new XMLScanner();
    xs.setEntities(statEntities);
    xs.init(pSrcFileName);
    try
    {
      XMLGenerator xg = new XMLGenerator();
      xg.createXML(pDstFileName);
      try
      {
        // xg.directWriteLn("");
        // xg.directWriteLn("]>");
        runConvHTML2XML(xg, xs);
      }
      finally
      {
        xg.closeXML();
      }
    }
    finally
    {
      xs.done();
    }
  }

  //===========================================================================

  /**
   * Dummy-Constructor.
   */

  protected HTML2XML()
  {
  }

}