plugins/org.eclipse.app4mc.help.modifier/src/org/eclipse/app4mc/help/modifier/APP4MC_Help_Step_1_UpdateTOC.java

/**
 ********************************************************************************
 * Copyright (c) 2018-2022 Robert Bosch GmbH and others.
 *
 * This program and the accompanying materials are made
 * available under the terms of the Eclipse Public License 2.0
 * which is available at https://www.eclipse.org/legal/epl-2.0/
 *
 * SPDX-License-Identifier: EPL-2.0
 *
 * Contributors:
 *     Robert Bosch GmbH - initial API and implementation
 ********************************************************************************
 */

package org.eclipse.app4mc.help.modifier;

import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.PrintStream;
import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
import java.util.List;
import java.util.Scanner;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.eclipse.app4mc.help.modifier.util.Heading;
import org.eclipse.app4mc.help.modifier.util.HeadingIterator;

public class APP4MC_Help_Step_1_UpdateTOC {

	public static void main(final String[] args) {

		String inputFilePath = "";

		try (Scanner scanner = new Scanner(System.in)) {
			System.out.println("Provide the location of input HTML file :");
			inputFilePath = scanner.nextLine(); // ".../help/advanced/printc223.html";
		}

		execute(inputFilePath);

	}


	public static File execute(final String inputFilePath) {
		final File inputFile = new File(inputFilePath);

		if (inputFile.exists() == false) {
			System.err.println("provide a valid input HTML location");
			System.exit(-1);
		}
		
		System.out.println("Reading input file : " + inputFilePath);
		

		final List<Heading> toc = new ArrayList<Heading>();
		final StringBuffer sb = new StringBuffer();
		
		try (BufferedReader br = new BufferedReader(
				new InputStreamReader(new FileInputStream(inputFile), StandardCharsets.UTF_8))) {
			
			boolean isInToc = false;
			boolean isAfterToc = false;
			int tocLevel = 0;
			
			final HeadingIterator headings = new HeadingIterator(toc);

			while (br.ready()) {

				final String readLine = br.readLine();

				/*-
				 * =======================================================================
				 * 				STEP 1 : Copy lines before table of contents
				 * ======================================================================
				 */
				
				if (readLine.trim().startsWith("<div id=\"toc_content\">")) {
					isInToc = true;
					
					appendln(sb, readLine);
					continue;
				}
				
				if (!(isInToc || isAfterToc)) {
					appendln(sb, readLine);
					continue;
				}
				
				/*-
				 * =======================================================================
				 * 				STEP 2 : Extract table of contents
				 * ======================================================================
				 */
				
				if (isInToc) {
					
					if (readLine.startsWith("<div class=\"toc_")) { // entry or sub_entry
						tocLevel++;

					}
					else if (readLine.contains("<a href=\"#")) {
						final Heading entry = new Heading();
						entry.level = tocLevel;
						entry.number = readLine.substring(0, readLine.indexOf(". "));
						entry.text = readLine.substring(readLine.indexOf("\">")+2, readLine.indexOf("</a>"));
						toc.add(entry);

					}
					else if (readLine.startsWith("</div>")) {
						tocLevel--;
						if(tocLevel < 0) {
							isInToc = false;
							isAfterToc = true;
						}
					}
					
					appendln(sb, readLine);
					continue;
				}
				
				/*-
				 * =======================================================================
				 * 				STEP 3 : Modify headings
				 * ======================================================================
				 */
				
				if (isAfterToc) {
					
					if (readLine.matches(".*<h\\d.*")) {
						// heading line found
						while (!readLine.replaceAll("\\W", "")
								.contains(headings.current().text.replaceAll("\\W", ""))) {
							// *** insert missing heading
							
							// System.out.println("found: >" + readLine + "<");
							// System.out.println("inserted: >" + headings.current() + "<");
							appendlnHeading(sb, headings.current());
							headings.next();
						}
						// *** modify existing heading
						
						// include user defined id but ignore generic ones
						String hID = extractHeadingId(readLine);
						if (! hID.contains("-")) hID = null;
						
						appendlnHeading(sb, headings.current(), hID);							
						headings.next();
						
						// debug info: original line
						// appendln(sb, "<!-- " + readLine.trim() + " -->");
					}
					else {
						// other lines
						appendln(sb, readLine);
					}
					continue;
				}

			}

		}
		catch (final Exception e) {

			e.printStackTrace();
			System.err.println("Error reading HTML file : " + inputFilePath);
		}



		/*-
		 * =======================================================================
		 * 						STEP 3 : generating output HTML file
		 * ======================================================================
		 */

		final File htmlFile = new File(inputFile.getParentFile(), "app4mc-help_1_updated_headings.html");

		try (BufferedWriter bw = new BufferedWriter(
				new OutputStreamWriter(new FileOutputStream(htmlFile), StandardCharsets.UTF_8))) {
			bw.write(sb.toString());
			bw.close();

			System.out.println("Generated modified HTML file at : " + htmlFile.getAbsolutePath());

		} catch (final IOException e) {
			e.printStackTrace();
			System.err.println("Error writing file : " + htmlFile.getAbsolutePath());
		}
		
		
		/*-
		 * =======================================================================
		 * 						STEP 4 : generating toc file
		 * ======================================================================
		 */

		HeadingIterator nodes = new HeadingIterator(toc);
		
		final File tocFile = new File(inputFile.getParentFile(), "app4mc-help_toc.html");

		try (PrintStream out = new PrintStream(new FileOutputStream(tocFile))) {
			
			out.println("<!DOCTYPE html>");
			out.println("<html lang=\"en-US\">");
			out.println("  <head>");
			out.println("    <meta charset=\"utf-8\" />");
			out.println("    <link rel=\"stylesheet\" href=\"css/toc-style.css\" type=\"text/css\">");
			out.println("  </head>");
			out.println("  <body>");
			out.println("    <h1>Contents</h1>");
			out.println("    <div class=\"toc-tree\">");
			writeNodeList(out, nodes);
			out.println("    </div>");
			out.println("  </body>");
			out.println("</html>");
			
		} catch (final IOException e) {
			e.printStackTrace();
			System.err.println("Error writing file : " + tocFile.getAbsolutePath());
		}
		
		return htmlFile;	// for further processing
	}
		

	// ========== Functions for TOC export ==========

	private static void writeNodeList(PrintStream out, HeadingIterator headings) {
		int listLevel = headings.current().level;
		
		out.println("<ul>");
		while (headings.current().level == listLevel) {
			if (hasSubElements(headings)) {
				writeExpandableNode(out, headings);
			} else {
				writeLeafNode(out, headings);
			}
		}
		out.println("</ul>");
	}
	
	private static void writeExpandableNode(PrintStream out, HeadingIterator headings) {
		final Heading h = headings.current();
		// output pattern:	<li>	<input type="checkbox" id="toc1.2.3" />
		//							<label for="toc1.2.3"><a href="#section1.2.3">Text</a></label>
		//							...
		//					</li>
		out.println("<li>" + getInput(h) + getLabel(h, getLink(h)));
		headings.next();
		writeNodeList(out, headings);
		out.println("</li>");
	}

	private static void writeLeafNode(PrintStream out, HeadingIterator headings) {
		final Heading h = headings.current();
		//output pattern: <li><label class="leaf"><a href="#section1.2.3">Text</a></label></li>
		out.println("<li><label class=\"leaf\">" + getLink(h) + "</label></li>");
		headings.next();
	}
	
	private static boolean hasSubElements(HeadingIterator headings) {
		return headings.current().level < headings.preview().level;
	}
	

	private static String getInput(Heading h) {
		// pattern: <input type="checkbox" id="toc1.2.3" />
		return "<input type=\"checkbox\" id=\"toc" + h.number + "\" />";
	}
	
	private static String getLabel(Heading h, String text) {
		// pattern: <label for="toc1.2.3">text</label>
		return "<label for=\"toc" + h.number + "\">" + text + "</label>";
	}

	private static String getLink(Heading h) {
		// pattern: <a href="#section1.2.3">Text</a>
		return "<a href=\"#section" + h.number + "\">" + h.text + "</a>";
	}

	// ========== Functions for Headings modification ==========

	private static void appendlnHeading(final StringBuffer sb, final Heading heading) {
		appendlnHeading(sb, heading, null);
	}

	private static void appendlnHeading(final StringBuffer sb, final Heading heading, final String id) {
		sb.append(System.getProperty("line.separator"));
		sb.append(System.getProperty("line.separator"));
		sb.append("<h" + heading.level);
		if (id != null && id != "") {
			sb.append(" id=\"" + id + "\"");			
		}
		sb.append(">");
		sb.append("<a id=\"section" + heading.number + "\">");
		if (heading.level <= 3) {
			sb.append(heading.number + " ");
		}
		sb.append("</a>");
		sb.append(heading.text);
		sb.append("</h" + heading.level + ">");
		sb.append(System.getProperty("line.separator"));
	}

	private static void appendln(final StringBuffer sb, final String line) {
		sb.append(line);
		sb.append(System.getProperty("line.separator"));
	}

	private static String extractHeadingId(String input) {
		String result = null;
		
		final Pattern idPattern = Pattern.compile(".*<h\\d\\s+id\\=\"(?<anchorDef>.*?)\">.*");
		final Matcher mID = idPattern.matcher(input);
		while (mID.find()) {
			result = mID.group("anchorDef");
			// System.out.println("AnchorDef : >" + result + "<");
		}
		
		return result;
	}
	
}