Checkpoint

Author: Steve Ramage

buildSrc/src/main/groovy/GenerateDataFromManPages.groovy

@@ -8,7 +8,9 @@ import org.w3c.dom.Document
 import org.w3c.dom.Node
 import org.w3c.dom.NodeList
 import org.w3c.dom.ls.DOMImplementationLS
+import org.w3c.dom.ls.LSParser
 import org.w3c.dom.ls.LSSerializer
+import org.xml.sax.InputSource
 
 import javax.xml.parsers.DocumentBuilder
 import javax.xml.parsers.DocumentBuilderFactory
@@ -21,6 +23,7 @@ import javax.xml.xpath.XPath
 import javax.xml.xpath.XPathConstants
 import javax.xml.xpath.XPathFactory
 import java.util.regex.Matcher
+import java.util.regex.Pattern
 
 /**
  * This task scans the systemd source code man pages to extract the set of available options as well as (eventually) documentation.
@@ -231,6 +234,7 @@ class GenerateDataFromManPages extends DefaultTask {
           '[QuickFairQueueing] Section Options': ['QuickFairQueueing'],
           '[QuickFairQueueingClass] Section Options': ['QuickFairQueueingClass'],
           '[BridgeVLAN] Section Options': ['BridgeVLAN'],
+
         ]
       ]
     ],
@@ -254,20 +258,6 @@ class GenerateDataFromManPages extends DefaultTask {
   @Internal
   final DocumentBuilderFactory dbf
 
-  public GenerateDataFromManPages() {
-    xpath = XPathFactory.newInstance().newXPath()
-
-    dbf = DocumentBuilderFactory.newInstance()
-    dbf.setXIncludeAware(true)
-    dbf.setValidating(false)
-    dbf.setExpandEntityReferences(false)
-
-    dbf.setFeature("http://apache.org/xml/features/disallow-doctype-decl", false)
-    dbf.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false)
-    dbf.setFeature("http://xml.org/sax/features/external-general-entities", false)
-    dbf.setFeature("http://xml.org/sax/features/external-parameter-entities", false)
-  }
-
 
   @TaskAction
   void start() {
@@ -418,6 +408,21 @@ class GenerateDataFromManPages extends DefaultTask {
     [name, value]
   }
 
+  public GenerateDataFromManPages() {
+    xpath = XPathFactory.newInstance().newXPath()
+
+    dbf = DocumentBuilderFactory.newInstance()
+    dbf.setXIncludeAware(true)
+    //dbf.setNamespaceAware(true)
+    dbf.setValidating(false)
+    dbf.setExpandEntityReferences(false)
+
+    dbf.setFeature("http://apache.org/xml/features/disallow-doctype-decl", false)
+    dbf.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false)
+    dbf.setFeature("http://xml.org/sax/features/external-general-entities", false)
+    dbf.setFeature("http://xml.org/sax/features/external-parameter-entities", false)
+  }
+
   /**
    * Generates individual HTML files for use as inline documentation
    *
@@ -429,14 +434,66 @@ class GenerateDataFromManPages extends DefaultTask {
   private generateDocumentationHtmlFromManPages(String fileType, File sourceFile) {
     DocumentBuilder builder = dbf.newDocumentBuilder()
 
-    Document document = builder.parse(sourceFile)
+    String xmlContent = sourceFile.text
+
+
+    // I spent an hour with ChatGPT trying to get
+    // Xincludes to work properly (without spending 6 hours to understand them).
+    // Couldn't get it to work, due to Java not liking things like includes with no href, for local references.
+    // 💣 Step 1: Replace XInclude elements using regex
+    xmlContent = processXIncludesWithRegex(xmlContent, sourceFile.parentFile)
+
+
+    File outputDir = project.layout.buildDirectory.dir("tmp/rendered-xincludes").get().asFile
+    if (!outputDir.exists()) {
+      outputDir.mkdirs()
+    }
+
+    File outputFile = new File(outputDir, sourceFile.getName())
+    outputFile.text = xmlContent  // Save to file
+
+    Document document = builder.parse(outputFile)
     Transformer transformer = getXsltTransformer()
 
     String xsltOutput = transformDocument(document, transformer)
 
     segmentParametersIntoFiles(fileType, sourceFile.getName(), xsltOutput)
   }
 
+  private String processXIncludesWithRegex(String xmlContent, File baseDir) {
+    // 🔥 Regex to match <xi:include href="some.xml" xpointer="some-id"/> (xpointer is optional)
+    def includePattern = /<xi:include\s+href="([^"]+)"(?:\s+xpointer="([^"]+)")?\s*\/>/
+
+
+    return xmlContent.replaceAll(includePattern) { match, href, xpointer ->
+      File includedFile = new File(baseDir, href)
+
+      if (!includedFile.exists()) {
+        println "⚠️ WARNING: Included file '${includedFile.absolutePath}' not found!"
+        return "<!-- Failed to include: $href -->"
+      }
+
+      String includedContent = includedFile.text
+
+      if (xpointer) {
+        // Extract only the element with the specified ID
+
+        //includedContent = extractById(includedContent, xpointer) ?: "<!-- Failed to find xpointer '$xpointer' in $href -->"
+
+        def xmlContent2 = includedContent
+        def idPattern = Pattern.compile(/<([a-zA-Z0-9:_-]+)\s+[^>]*id=["']$xpointer["'][^>]*>(.*?)<\/\1>/, Pattern.DOTALL)
+        def matcher = xmlContent2 =~ idPattern
+
+        def resContent = matcher.find() ? matcher.group(0) : null
+
+        includedContent = "<!--xi:include='$href' xpointer='$xpointer'-->" + resContent + "<!-- /xi:include='$href' xpointer='$xpointer' -->"
+      }
+
+      return includedContent
+    }
+  }
+
+
   /**
    * Transforms the supplied document with the supplied transformer
    * @param document - XML Document to transform

buildSrc/src/main/resources/resolve-xinclude.xslt

@@ -0,0 +1,19 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xsl:stylesheet version="1.0"
+                xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+                xmlns:xi="http://www.w3.org/2001/XInclude">
+
+  <!-- Identity template: Copies everything as-is -->
+  <xsl:template match="@* | node()">
+    <xsl:copy>
+      <xsl:apply-templates select="@* | node()"/>
+    </xsl:copy>
+  </xsl:template>
+
+  <!-- Process XInclude -->
+  <xsl:template match="xi:include">
+    <xsl:variable name="file" select="@href"/>
+    <xsl:apply-templates select="document($file)/*"/>
+  </xsl:template>
+
+</xsl:stylesheet>