confluence to asciidoc

convert.groovy

/*
 * JBoss, Home of Professional Open Source
 * Copyright 2017, Red Hat, Inc., and individual contributors as indicated
 * by the @authors tag.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 * http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

@Grab('net.sourceforge.htmlcleaner:htmlcleaner:2.21')
import org.htmlcleaner.*

import java.nio.charset.StandardCharsets
import java.nio.file.Files
import java.nio.file.Paths

def src = new File('html').toPath()
def dst = new File('asciidoc').toPath()

HtmlCleaner cleaner = new HtmlCleaner()
def props = cleaner.properties
props.translateSpecialEntities = false
props.setAdvancedXmlEscape(true)
props.setPruneTags("script")
TagTransformation divTransformer = new TagTransformation("div")
CleanerTransformations transformations = new CleanerTransformations();
//transformations.addTransformation(divTransformer)
transformations.addTransformation(new TagTransformation("thead"))
transformations.addTransformation(new TagTransformation("tbody"))
transformations.addTransformation(new TagTransformation("tfoot"))
transformations.addTransformation(new TagTransformation("header"))
transformations.addTransformation(new TagTransformation("span"))
transformations.addTransformation(new TagTransformation("code"))
/*transformations.addTransformation(new TagTransformation("h5", "h6",))
transformations.addTransformation(new TagTransformation("h4", "h5",))
transformations.addTransformation(new TagTransformation("h3", "h4",))
transformations.addTransformation(new TagTransformation("h2", "h3",))
transformations.addTransformation(new TagTransformation("h1", "h2",))*/
props.setCleanerTransformations(transformations)

def serializer = new PrettyHtmlSerializer(props);

static String guessLanguage(TagNode sourceTag) {
  String source = sourceTag.getText()
  if (source.contains("xmlns")
          || source.contains("<")
          &&  (
                !source.contains("void")
                &&!source.contains("static ")
                &&!source.contains(".class")
                &&!source.contains("new ")
                &&!source.contains("final ")
              )
        ) {
    return "xml"
  } else if (source.contains("import")
            || source.contains(".java")
            || source.contains("java.")
            || source.contains("assert")
            || source.contains("Assert.")
            || source.contains("new ")
            || source.contains("class")
            || source.contains("interface")
            || source.contains("package")
            || source.contains("private ")
            || source.contains("public ")
            || source.contains("static ")
            || source.contains("String ")
            || source.contains("Boolean ")
            || source.contains("boolean ")
            || source.contains("ModelNode ")
            || source.contains("newInstance")
            || source.contains("try")
            || source.contains("void ")
            || source.contains("catch")
            || source.contains("@Test")
            || source.contains("System.out")
            || source.contains("new ModelNode(")
            || source.contains("throw")
            || source.contains(".close();")
            || source.contains(".log")
            || source.contains("@EJB")
            || source.contains("@Stateless")
            || source.contains("log.")
            || source.contains("bsh ")
            || source.contains(".resolveModelAttribute")
            || source.contains(".parseAndSetParameter")
            || source.contains("KernelServices ")
            || source.contains(".registerOperationHandler")
            || source.contains(".registerSubsystemModel")
            || source.contains(".addChildResource")
            || source.contains("AttributeConverter ")
            || source.contains(".addOperationTransformationOverride")
            || source.contains("attributeBuilder")
            || source.contains("RejectAttributeChecker")
            || source.contains("PathAddress ")
            || source.contains("@Arquillian")
            || source.contains("DiscardAttributeChecker")
            || source.contains("PathElement")
            || source.contains("Transformation")


    ) {

      return "java"
    }else if (source.contains("outcome")
          || source.contains(":write-attribute")
          || source.contains(":add")
          || source.contains(":undefine")
          || source.contains(":read-")
          || source.contains("standalone@")
          || source.contains("domain@")
          || source.contains('"operation"')
          || source.contains('"children" =')
          || source.contains('"address"')
          || source.contains('model-description')
          || source.contains('reload')
          || source.contains('request-properties')
          || source.contains('reply-properties')
          || source.contains('value-type')
          || source.contains('value-type')
          || source.contains('"attributes" =')
          || source.contains('/subsystem=')
          || source.contains('/deployment=')
          || source.contains('"result" =')
          || source.contains('deploy ')
          || source.contains('"rollout-plan" =')
          || source.contains('"description" =')
          || source.contains('deployment-overlay ')
  ) {
    return "ruby";

  }  else if (source.contains(".sh")
          || source.contains(".bat")
          || source.contains("cd ")
          || source.contains("mvn ")
          || source.contains("keytool")
          || source.contains("@Test")
          || source.contains("grep")
          || source.contains("cat")
          || source.contains("##")
          || source.contains(" matches")
          || source.contains("cp ")
          || source.contains("ls ")
          || source.contains("-D")
          || source.contains("curl ")
          || source.contains("sudo ")
          || source.contains("vi ")
          || source.contains("yum ")
          || source.contains("git ")
          || source.contains("rm ")
  ) {

    return "bash"
  }else if (source.matches("\\\\w+=[^\\\\s]+")){
    println(" found props")
    return ""
  }else if (
    source.contains("MSC service thread")
    || source.contains("[stdout] ")
    || source.contains("; legacy version: ")
    || source.contains("(DeploymentScanner-threads: ")
    || source.contains("DeploymentScanner-threads ")
    || source.contains("http://")
    || source.contains(".jar")
    || source.contains(".war")
  ){
    return ""
  }else if (source.contains("CREATE TABLE")){
    return "sql"
  }
  //println "we have to guess: " + source
  return ""
  //return "java"
}
static String getAdmotionMapping(String confluenceType){
     /*
     note
     tip
     info
     warning

      */
  if (confluenceType.equals("note")){
    return "NOTE"
  }
  if (confluenceType.equals("tip")){
    return "TIP";
  }
  if (confluenceType.equals("info")){
    return "IMPORTANT"
  }
  if (confluenceType.equals("warning")){
    return "WARNING"
  }

  throw new RuntimeException("Could not map '"+confluenceType+"'")
}

src.toFile().eachFileRecurse { f ->
  def relative = src.relativize(f.toPath())
  def target = dst.resolve(relative)
  if (f.isDirectory()) {
    if (Files.notExists(target)) {
      Files.createDirectory(target)
    };
  } else if (f.name.endsWith('.html')) {
    def tmpHtml = Paths.get('clean', relative.toString()) //File.createTempFile('clean', 'html')
    println "Converting $relative"
    String html = new String(Files.readAllBytes(f.toPath()),StandardCharsets.UTF_8);
    html = html
            .replaceAll("<code class=\\\"value\\\">(.*?)<\\/code>","\$1")
            .replaceAll("<code class=\\\"plain\\\">(.*?)<\\/code>","\$1")
            .replaceAll("<code class=\\\"comments\\\">(.*?)<\\/code>","\$1")
            .replaceAll("<code class=\\\"keyword\\\">(.*?)<\\/code>","\$1")
            .replaceAll("<code class=\\\"string\\\">(.*?)<\\/code>","\$1")
            .replaceAll("<code class=\\\"color1\\\">(.*?)<\\/code>","\$1")
            .replaceAll("<code class=\\\"preprocessor\\\">(.*?)<\\/code>","\$1")
            .replaceAll("<div class=\\\"line\\\">(.*?)<\\/div>","\$1")
            .replaceAll("<code>(.*?)<\\/code>","\$1")


    def result = cleaner.clean(html)
    TagNodeVisitor visitor = { parent, htmlNode ->

      if (htmlNode instanceof TagNode) {
        TagNode tagNode = (TagNode)htmlNode;
        tagNode?.attributes?.remove 'class'
        tagNode?.attributes?.remove 'id'
        if ('td' == tagNode?.name || 'th' == tagNode?.name) {
          tagNode.name = 'td'
          String txt = tagNode.text
          tagNode.removeAllChildren()
          tagNode.insertChild(0, new ContentNode(txt))
        }
        if ('p' == tagNode?.name && 'title' == tagNode.attributes.id) {
          tagNode.removeFromTree()
        }

        if ('ul' == tagNode?.name && 'docnav' == tagNode.getAttributeByName("class")) {
          tagNode.removeFromTree()
          print "ul processed"
        }
        if ('pre' == tagNode?.name) {
          String className = tagNode.getAttributeByName("class")
          if (className != null && className.contains("brush: java")) {
            tagNode.removeAttribute("class")
            tagNode.addAttribute("class", "java")
          }
        }
        if ('div' == tagNode?.name) {
          tagNode.removeAttribute("id")
          String className = tagNode.getAttributeByName("class")
          if (className != null) {
            if (className.contains("admonition-body")) {
              String parentClass = parent.getAttributeByName("class")
              String adMotionLevel = parentClass.substring(parentClass.lastIndexOf("-")+1)
              int idx = parent.getParent().getChildIndex(parent);
              parent.getParent().insertChild(idx, tagNode);
              List<TagNode> titleNodes =  parent.getElementListByName("p",false);

              parent.removeFromTree();
              tagNode.removeAttribute("class")
              tagNode.insertChild(0, new ContentNode("["+getAdmotionMapping(adMotionLevel)+"]"))
              if (!titleNodes.isEmpty()) {
                tagNode.insertChild(0, titleNodes.get(0))
                //parent.getParent().insertChildBefore(tagNode, titleNodes.get(0))
              }
            } else if ("panel-content".equals(className)) {
              tagNode.removeAttribute("class")
              tagNode.insertChild(0, new ContentNode("****"))
              tagNode.addChild(new ContentNode("****"))
              print("merge careful, new panel format for file: ")
            } else if (className.contains("syntaxhighlighter")) {
             if (!"confbox programlisting".equals(parent.getAttributeByName("class"))){
               println "something is really wrong"
              throw new RuntimeException("bruh");
             }
              List<BaseToken> children = tagNode.getAllChildren();
              int index = parent.getParent().getChildIndex(tagNode.getParent());
              TagNode pre = new TagNode("pre")
              pre.addChildren(children);
              parent.getParent().insertChild(index, pre)
              pre.addAttribute("class", guessLanguage(pre))
              tagNode.getParent().removeFromTree();
            }
          }
        }
    }



      true
    } as TagNodeVisitor


    result.traverse(visitor)
    //result.traverse(divCleaner)


    serializer.writeToFile(
            result, tmpHtml.absolutePath, "utf-8"
    )
  


    //println "pandoc -f html -t asciidoctorj -R -S --normalize -s $tmpHtml -o ${target}.adoc"
    //"pandoc -f html -t asciidoc -R -S --normalize -s $tmpHtml -o ${target.getFileName()}.adoc".execute().waitFor()
    def targetPath = dst.absolutePath + "\\${target.fileName.toString().substring(0, target.fileName.toString().length() - 5)}.adoc"
    println targetPath
    //println "pandoc --section-divs -f html -t asciidoc -R -S --normalize -s $tmpHtml -o ${targetPath}"
    "pandoc  -R -f html -R --atx-headers -t asciidoc -s $tmpHtml -o ${targetPath}".execute().waitFor()
    //tmpHtml.delete()
  } else {
    if (Files.notExists(f.toPath())) {
      Files.copy(f.toPath(), target)
    }
    }
}