/*********************************************************************************************************
 * 프로그램명 : TagFilter.java 프로그램설명 : 프로젝트와 관련된 정보를 얻을수 있는 class 작성자 : 강원중 작성일 : 2004.01.06 변경일 : 2003.11.30
 **********************************************************************************************************/

package kr.co.kihyun.text.html;

import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.io.StringReader;
import java.io.StringWriter;
import java.util.Arrays;
import java.util.HashSet;
import java.util.List;
import java.util.Set;

import net.htmlparser.jericho.Attribute;
import net.htmlparser.jericho.CharacterReference;
import net.htmlparser.jericho.Element;
import net.htmlparser.jericho.EndTagType;
import net.htmlparser.jericho.HTMLElementName;
import net.htmlparser.jericho.HTMLElements;
import net.htmlparser.jericho.OutputDocument;
import net.htmlparser.jericho.Segment;
import net.htmlparser.jericho.StartTag;
import net.htmlparser.jericho.StartTagType;
import net.htmlparser.jericho.Tag;

import org.w3c.dom.Document;
import org.w3c.tidy.Tidy;

public class Html extends Tidy {
	/**
	 * 
	 */
	private static final long serialVersionUID = 1L;

	public static final String width = "hh";
	public static final String height = "height";
	public static final String tdWidth = "";
	public static final String tdHeight = "25";

        //50.public static을 통한 선언 오류(CWE-500) : Delete by YOUNGJUN,CHO
	//public static String tdOption = " ";
        //------------------------------------------------
        
	// public static String titleBGColor = "#E0E0E0";
	public static final String titleBGColor = "#f3f6fc";
	public static final String inputBGColor = "#FFFFFF";

	public static final String titleFontColor = "#404040";
	public static final String strFontColor = "#4F484F";
	public static final String intFontColor = "#4F484F";
	public static final String dynaTotLineFontColor = "red"; // 동적표의 마지막 한 라인 집계

	// list of HTML elements that will be retained in the final output:
	private static final Set<String> VALID_ELEMENT_NAMES = new HashSet<String>(Arrays.asList(new String[] {
			HTMLElementName.A, HTMLElementName.ABBR, HTMLElementName.ACRONYM, HTMLElementName.ADDRESS,
			HTMLElementName.APPLET, HTMLElementName.AREA, HTMLElementName.B, HTMLElementName.BASE,
			HTMLElementName.BASEFONT, HTMLElementName.BDO, HTMLElementName.BIG, HTMLElementName.BLOCKQUOTE,
			HTMLElementName.BODY, HTMLElementName.BR, HTMLElementName.BUTTON, HTMLElementName.CAPTION,
			HTMLElementName.CENTER, HTMLElementName.CITE, HTMLElementName.CODE, HTMLElementName.COL,
			HTMLElementName.COLGROUP, HTMLElementName.DD, HTMLElementName.DEL, HTMLElementName.DFN,
			HTMLElementName.DIR, HTMLElementName.DIV, HTMLElementName.DL, HTMLElementName.DT, HTMLElementName.EM,
			HTMLElementName.FIELDSET, HTMLElementName.FONT, HTMLElementName.FORM, HTMLElementName.FRAME,
			HTMLElementName.FRAMESET, HTMLElementName.H1, HTMLElementName.H2, HTMLElementName.H3, HTMLElementName.H4,
			HTMLElementName.H5, HTMLElementName.H6, HTMLElementName.HEAD, HTMLElementName.HR, HTMLElementName.HTML,
			HTMLElementName.I, HTMLElementName.IFRAME, HTMLElementName.IMG, HTMLElementName.INPUT, HTMLElementName.INS,
			HTMLElementName.ISINDEX, HTMLElementName.KBD, HTMLElementName.LABEL, HTMLElementName.LEGEND,
			HTMLElementName.LI, HTMLElementName.LINK, HTMLElementName.MAP, HTMLElementName.MENU, HTMLElementName.META,
			HTMLElementName.NOFRAMES, HTMLElementName.NOSCRIPT, HTMLElementName.OBJECT, HTMLElementName.OL,
			HTMLElementName.OPTGROUP, HTMLElementName.OPTION, HTMLElementName.P, HTMLElementName.PARAM,
			HTMLElementName.PRE, HTMLElementName.Q, HTMLElementName.S, HTMLElementName.SAMP, HTMLElementName.SCRIPT,
			HTMLElementName.SELECT, HTMLElementName.SMALL, HTMLElementName.SPAN, HTMLElementName.STRIKE,
			HTMLElementName.STRONG, HTMLElementName.STYLE, HTMLElementName.SUB, HTMLElementName.SUP,
			HTMLElementName.TABLE, HTMLElementName.TBODY, HTMLElementName.TD, HTMLElementName.TEXTAREA,
			HTMLElementName.TFOOT, HTMLElementName.TH, HTMLElementName.THEAD, HTMLElementName.TITLE,
			HTMLElementName.TR, HTMLElementName.TT, HTMLElementName.U, HTMLElementName.UL, HTMLElementName.VAR }));

	// list of HTML attributes that will be retained in the final output:
	private static final Set<String> VALID_ATTRIBUTE_NAMES = new HashSet<String>(Arrays.asList(new String[] { "id",
			"class", "hreflang", "title", "name", "rel", "rev", "type", "defer", "language", "xml:space", "style",
			"dir", "lang", "xml:lang", "xmlns", "ismap", "charset", "coords", "target", "href", "nohref", "size",
			"color", "face", "cite", "link", "alink", "vlink", "media", "shape", "height", "width", "align", "valign",
			"alt", "start", "label", "multiple", "archive", "code", "codebase", "codetype", "classid", "data",
			"declare", "standby", "hspace", "object", "vspace", "background", "bgcolor", "text", "disabled", "value",
			"valuetype", "char", "charoff", "span", "datetime", "compact", "profile", "noshade", "action", "accept",
			"accept-charset", "enctype", "method", "border", "ismap", "usemap", "frameborder", "longdesc",
			"marginheight", "marginwidth", "scrolling", "src", "checked", "maxlength", "readonly", "prompt", "for",
			"content", "http-equiv", "scheme", "cellpadding", "cellspacing", "frame", "summary", "abbr", "axis",
			"colspan", "headers", "nowrap", "rowspan", "scope", "cols", "rows", "accesskey", "tabindex", "onload",
			"onunload", "onblur", "onchange", "onfocus", "onreset", "onselect", "onsubmit", "onabort", "onkeydown",
			"onkeypress", "onkeyup", "onclick", "ondbclick", "onmousedown", "onmousemove", "onmouseout", "onmouseover",
			"onmouseup" }));

	// list of HTML properties that will be retained in the final output:
	private static final Set<String> VALID_PROPERTY_NAMES = new HashSet<String>(Arrays.asList(new String[] {
			"font-family", "font-family", "font-variant", "font-weight", "font-size", "font", "color",
			"background-color", "background-image", "background-repeat", "background-attachment",
			"background-position", "background", "word-spacing", "letter-spacing", "text-decoration", "vertical-align",
			"text-transform", "text-align", "text-indent", "line-height", "margin-top", "margin-right",
			"margin-bottom", "margin-left", "margin", "padding-top", "padding-right", "padding-bottom", "padding-left",
			"padding", "border-top-width", "border-right-width", "border-bottom-width", "border-left-width",
			"border-width", "border-color", "border-style", "border-top", "border-right", "border-bottom",
			"border-left", "border", "width", "height", "float", "float", "display", "white-space", "list-style-type",
			"list-style-image", "list-style-position", "list-style" }));

	private static final Object VALID_MARKER = new Object();

	// public static final String DOC_TYPE = "\"-//W3C//DTD XHTML 1.0 Transitional//EN\" \""+Moumi.getDtdUri()+"\"";
	public static final String DOC_TYPE = "\"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://localhost:7001/dtd/loose.dtd\"";
	private net.htmlparser.jericho.Source source = null;
	private OutputDocument outputDocument = null;

	public Html(InputStream in) {
		this(new InputStreamReader(in));
	}

	public Html(String in) {
		this(new StringReader(in));
	}

	public Html(Reader reader) {
		super();
		try {
			setTidyMark(false);
			setDocType(DOC_TYPE);
			setDropEmptyParas(true);
			setDropProprietaryAttributes(true);
			setHideComments(true);
			source = new net.htmlparser.jericho.Source(reader);
			source.fullSequentialParse();
			outputDocument = new OutputDocument(source);
			sanitise(false, true);
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}

	/*
	 * override setDocType, dtd까지 auto로 가능하도록.
	 */

	public Document parseDOM() {
		StringWriter out = new StringWriter();
		Document doc = parseDOM(new StringReader(outputDocument.toString()), out);
		out.getBuffer().toString();
		return doc;
	}

	public void encodeInvalidMarkup() {
		encodeInvalidMarkup(false);
	}

	public void encodeInvalidMarkup(boolean formatWhiteSpace) {
		sanitise(formatWhiteSpace, false);
	}

	public void stripInvalidMarkup() {
		stripInvalidMarkup(false);
	}

	public void stripInvalidMarkup(boolean formatWhiteSpace) {
		sanitise(formatWhiteSpace, true);
	}

	// TODO: implement
	/*
	 * public void toPDF(OutputStream out) { toPDF(out, defaultStyleSheet); }
	 * 
	 * public void toPDF(OutputStream out, File styleSheet) { out = new BufferedOutputStream(out); try { Fop fop =
	 * fopFactory.newFop(MimeConstants.MIME_PDF, foUserAgent, out); TransformerFactory factory =
	 * TransformerFactory.newInstance(); Transformer transformer = factory.newTransformer(new StreamSource(styleSheet));
	 * transformer.setParameter("versionParam", "2.0"); LOG.debug("EXPORTING FROM:\n{}", domBuf); Source src = new
	 * StreamSource(new StringReader(domBuf)); // Result res = new SAXResult(fop.getDefaultHandler()); Result res = new
	 * StreamResult(out); transformer.transform(src, res); out.close(); } catch (FOPException e) { e.printStackTrace();
	 * } catch (TransformerConfigurationException e) { e.printStackTrace(); } catch (TransformerException e) {
	 * e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } }
	 */

	private void sanitise(boolean formatWhiteSpace, boolean stripInvalidElements) {
		List<Tag> tags = source.getAllTags();
		int pos = 0;
		for (Tag tag : tags) {
			if (processTag(tag, outputDocument)) {
				tag.setUserData(VALID_MARKER);
			} else {
				if (!stripInvalidElements)
					continue; // element will be encoded along with surrounding text
				outputDocument.remove(tag);
			}
			reencodeTextSegment(source, outputDocument, pos, tag.getBegin(), formatWhiteSpace);
			pos = tag.getEnd();
		}
		reencodeTextSegment(source, outputDocument, pos, source.getEnd(), formatWhiteSpace);
	}

	private static boolean processTag(Tag tag, OutputDocument outputDocument) {
		String elementName = tag.getName();
		if (!VALID_ELEMENT_NAMES.contains(elementName))
			return false;
		if (tag.getTagType() == StartTagType.NORMAL) {
			Element element = tag.getElement();
			if (HTMLElements.getEndTagRequiredElementNames().contains(elementName)) {
				if (element.getEndTag() == null)
					return false; // refect start tag if its required end tag is missing
			} else if (HTMLElements.getEndTagOptionalElementNames().contains(elementName)) {
				if (elementName == HTMLElementName.LI && !isValidLITag(tag))
					return false; // reject invalid LI tags
				if (element.getEndTag() == null)
					outputDocument.insert(element.getEnd(), getEndTagHTML(elementName)); // insert optional end tag if
																							// it is missing
			}
			outputDocument.replace(tag, getStartTagHTML(element.getStartTag()));
		} else if (tag.getTagType() == EndTagType.NORMAL) {
			if (tag.getElement() == null)
				return false; // reject end tags that aren't associated with a start tag
			if (elementName == HTMLElementName.LI && !isValidLITag(tag))
				return false; // reject invalid LI tags
			outputDocument.replace(tag, getEndTagHTML(elementName));
		} else {
			return false; // reject abnormal tags
		}
		return true;
	}

	private static boolean isValidLITag(Tag tag) {
		Element parentElement = tag.getElement().getParentElement();
		if (parentElement == null)
			return false; // ignore LI elements without a parent
		if (parentElement.getStartTag().getUserData() != VALID_MARKER)
			return false; // ignore LI elements who's parent is not valid
		return parentElement.getName() == HTMLElementName.UL || parentElement.getName() == HTMLElementName.OL; // only
																												// accept
																												// LI
																												// tags
																												// who's
																												// immediate
																												// parent
																												// is UL
																												// or
																												// OL.
	}

	private static void reencodeTextSegment(net.htmlparser.jericho.Source source, OutputDocument outputDocument,
			int begin, int end, boolean formatWhiteSpace) {
		if (begin >= end)
			return;
		Segment textSegment = new Segment(source, begin, end);
		String decodedText = CharacterReference.decode(textSegment);
		String encodedText = formatWhiteSpace ? CharacterReference.encodeWithWhiteSpaceFormatting(decodedText)
				: CharacterReference.encode(decodedText);
		outputDocument.replace(textSegment, encodedText);
	}

	private static CharSequence getStartTagHTML(StartTag startTag) {
		// tidies and filters out non-approved attributes
		StringBuilder sb = new StringBuilder();
		sb.append('<').append(startTag.getName());
		for (Attribute attribute : startTag.getAttributes()) {
			if (VALID_ATTRIBUTE_NAMES.contains(attribute.getKey())) {
				sb.append(' ').append(attribute.getName());
				if (attribute.getValue() != null) {
					sb.append("=\"");
					if ("style".equals(attribute.getKey())) {
						String[] properties = attribute.getValue().split(";");
						for (String property : properties) {
							String name = property.split(":")[0].trim();
							if (VALID_PROPERTY_NAMES.contains(name)) {
								sb.append(CharacterReference.encode(property));
								sb.append("; ");
							}
						}
					} else {
						sb.append(CharacterReference.encode(attribute.getValue()));
					}
					sb.append('"');
				}
			}
		}
		if (startTag.getElement().getEndTag() == null
				&& !HTMLElements.getEndTagOptionalElementNames().contains(startTag.getName()))
			sb.append(" /");
		sb.append('>');
		return sb;
	}

	private static String getEndTagHTML(String tagName) {
		return "</" + tagName + '>';
	}

}