Add pdf version option (from pdfua)

Author: LonelyMidoriya

java/opendataloader-pdf-core/src/main/java/org/opendataloader/pdf/api/AutoTagger.java

@@ -59,9 +59,9 @@ private AutoTagger() {
      * @return result containing the tagged PDDocument and timing metadata
      * @throws IOException if unable to read or process the PDF
      */
-    public static TaggingResult tag(String inputPdf, Config config) throws IOException {
+    public static TaggingResult tag(String inputPdf, Config config, Float pdfVersion) throws IOException {
         ExtractionResult extraction = DocumentProcessor.extractContents(inputPdf, config);
-        return tag(inputPdf, extraction);
+        return tag(extraction, pdfVersion);
     }
 
     /**
@@ -70,15 +70,14 @@ public static TaggingResult tag(String inputPdf, Config config) throws IOExcepti
      * same extraction — call {@link DocumentProcessor#extractContents} once,
      * then pass the result here and to other output generators.
      *
-     * @param inputPdf   path to the input PDF file (used for metadata)
      * @param extraction pre-computed extraction result
      * @return result containing the tagged PDDocument and timing metadata
      * @throws IOException if unable to tag the document
      */
-    public static TaggingResult tag(String inputPdf, ExtractionResult extraction) throws IOException {
+    public static TaggingResult tag(ExtractionResult extraction, Float pdfVersion) throws IOException {
         long t0 = System.nanoTime();
         PDDocument document = StaticResources.getDocument();
-        AutoTaggingProcessor.tagDocument(new File(inputPdf), document, extraction.getContents());
+        AutoTaggingProcessor.tagDocument(document, extraction.getContents(), pdfVersion);
         long taggingNs = System.nanoTime() - t0;
 
         return new TaggingResult(document, extraction.getExtractionNs(), taggingNs,

java/opendataloader-pdf-core/src/main/java/org/opendataloader/pdf/api/OutputWriter.java

@@ -25,7 +25,7 @@
  * tagged PDF) from a pre-computed {@link ExtractionResult}.
  *
  * <p>Use this when you have already run extraction once (e.g. via
- * {@link AutoTagger#tag(String, ExtractionResult)}) and want to emit file
+ * {@link AutoTagger#tag(ExtractionResult, Float)}) and want to emit file
  * outputs from that same result without re-extracting.
  *
  * <p>Typical two-phase usage:

java/opendataloader-pdf-core/src/main/java/org/opendataloader/pdf/processors/AutoTaggingProcessor.java

@@ -59,11 +59,10 @@ public class AutoTaggingProcessor {
      * Tag a PDF document in-memory without saving to disk.
      * Adds structure tree, marked content references, and parent tree to the document.
      *
-     * @param inputPDF  the original PDF file (used for metadata only)
      * @param document  the PDDocument to tag (modified in place)
      * @param contents  extracted content by page
      */
-    public static synchronized void tagDocument(File inputPDF, PDDocument document, List<List<IObject>> contents) throws IOException {
+    public static synchronized void tagDocument(PDDocument document, List<List<IObject>> contents, Float pdfVersion) throws IOException {
         operatorIndexesToStreamInfosMap.clear();
         structParents.clear();
         structParentsIntegers.clear();
@@ -73,7 +72,7 @@ public static synchronized void tagDocument(File inputPDF, PDDocument document,
         annotationBBoxesMap.clear();
         currentStructParent = 0;
         imageChunkFigureCounter = 0;
-        isPDF2_0 = document.getVersion() == 2.0F;
+        isPDF2_0 = pdfVersion != null ? pdfVersion == 2.0F : document.getVersion() == 2.0F;
         COSDocument cosDocument = document.getDocument();
         PDCatalog catalog = document.getCatalog();
         COSObject structTreeRoot = createStructTreeRoot(catalog, cosDocument, document);
@@ -90,7 +89,7 @@ public static synchronized void tagDocument(File inputPDF, PDDocument document,
      * Tag a PDF document and save to disk. Existing behavior preserved.
      */
     public static synchronized void createTaggedPDF(File inputPDF, String outputFolder, PDDocument document, List<List<IObject>> contents) throws IOException {
-        tagDocument(inputPDF, document, contents);
+        tagDocument(document, contents, null);
         String outputFileName = outputFolder + File.separator +
             inputPDF.getName().substring(0, inputPDF.getName().length() - 4) + "_tagged.pdf";
         document.saveAs(outputFileName);

java/opendataloader-pdf-core/src/test/java/org/opendataloader/pdf/api/AutoTaggerTest.java

@@ -17,7 +17,7 @@ class AutoTaggerTest {
     void tagReturnsDocumentWithStructTree() throws Exception {
         Config config = new Config();
 
-        try (TaggingResult result = AutoTagger.tag(TEST_PDF, config)) {
+        try (TaggingResult result = AutoTagger.tag(TEST_PDF, config, null)) {
             PDDocument doc = result.getDocument();
             assertThat(doc).isNotNull();
             assertThat(doc.getCatalog().getKey(org.verapdf.as.ASAtom.STRUCT_TREE_ROOT).empty())
@@ -30,7 +30,7 @@ void tagReturnsDocumentWithStructTree() throws Exception {
     void tagTimingsArePositive() throws Exception {
         Config config = new Config();
 
-        try (TaggingResult result = AutoTagger.tag(TEST_PDF, config)) {
+        try (TaggingResult result = AutoTagger.tag(TEST_PDF, config, null)) {
             assertThat(result.getExtractionNs()).isGreaterThan(0);
             assertThat(result.getTaggingNs()).isGreaterThan(0);
         }
@@ -41,7 +41,7 @@ void saveToWritesFile(@TempDir Path tempDir) throws Exception {
         Config config = new Config();
         String outputPath = tempDir.resolve("output_tagged.pdf").toString();
 
-        try (TaggingResult result = AutoTagger.tag(TEST_PDF, config)) {
+        try (TaggingResult result = AutoTagger.tag(TEST_PDF, config, null)) {
             result.saveTo(outputPath);
         }
 
@@ -55,7 +55,7 @@ void tagIgnoresOutputFormatFlags() throws Exception {
         config.setGenerateJSON(true);
         config.setGenerateMarkdown(true);
 
-        try (TaggingResult result = AutoTagger.tag(TEST_PDF, config)) {
+        try (TaggingResult result = AutoTagger.tag(TEST_PDF, config, null)) {
             assertThat(result.getDocument()).isNotNull();
         }
     }