Add OCRModule::PageNeedsOCR sample usage (Python, Ruby, PHP, Go)

Samples/OCRTest/GO/OCR_test.go

@@ -233,6 +233,42 @@ func TestOCR(t *testing.T) {
 		doc.Save(outputPath+"physics.pdf", uint(0))
 		fmt.Println("Example 6: extracting and applying OCR XML from physics.tif")
 
+		// Example 7) Check whether a page needs OCR before running it, to avoid unnecessary OCR
+		// processing on pages that already contain extractable text
+		// --------------------------------------------------------------------------------
+
+		// A) Open the .pdf document
+
+		doc = NewPDFDoc(inputPath + "german_kids_song.pdf")
+
+		// B) Grab the page to be checked
+
+		page := doc.GetPage(1)
+
+		// C) Ask OCRModule whether the page needs OCR. Passing process_invisible_text as false
+		// means invisible text (e.g. from a prior OCR pass) is ignored and only visible content
+		// is considered, while true would treat an existing invisible text layer as sufficient
+		// to consider the page as not needing OCR.
+
+		needsOCR := OCRModulePageNeedsOCR(doc, page, false)
+		if needsOCR {
+			fmt.Println("Example 7: page 1 of german_kids_song.pdf needs OCR")
+		} else {
+			fmt.Println("Example 7: page 1 of german_kids_song.pdf does not need OCR")
+		}
+
+		// D) Only run OCR if it is actually needed
+
+		if needsOCR {
+			opts = NewOCROptions()
+			if use_iris {
+				opts.SetOCREngine("iris")
+			}
+			opts.AddLang("deu")
+			OCRModuleProcessPDF(doc, opts)
+			doc.Save(outputPath+"german_kids_song_conditional.pdf", uint(0))
+		}
+
 		PDFNetTerminate()
 	}
 }

Samples/OCRTest/PHP/OCRTest.php

@@ -224,6 +224,37 @@
 
 		echo "Example 6: extracting and applying OCR XML from physics.tif \n";
 
+		//--------------------------------------------------------------------------------
+		// Example 7) Check whether a page needs OCR before running it, to avoid unnecessary OCR processing on pages that already contain extractable text
+
+		// A) Open the .pdf document
+
+		$doc = new PDFDoc($input_path."german_kids_song.pdf");
+
+		// B) Grab the page to be checked
+
+		$page = $doc->GetPage(1);
+
+		// C) Ask OCRModule whether the page needs OCR. Passing process_invisible_text as false
+		// means invisible text (e.g. from a prior OCR pass) is ignored and only visible content
+		// is considered, while true would treat an existing invisible text layer as sufficient
+		// to consider the page as not needing OCR.
+
+		$needs_ocr = OCRModule::PageNeedsOCR($doc, $page, false);
+		echo "Example 7: page 1 of german_kids_song.pdf ".($needs_ocr ? "needs" : "does not need")." OCR \n";
+
+		// D) Only run OCR if it is actually needed
+
+		if ($needs_ocr) {
+			$opts = new OCROptions();
+			if ($use_iris) {
+				$opts->SetOCREngine("iris");
+			}
+			$opts->AddLang("deu");
+			OCRModule::ProcessPDF($doc, $opts);
+			$doc->Save($output_path."german_kids_song_conditional.pdf", 0);
+		}
+
 		echo "Done. \n";
 
 	}

Samples/OCRTest/PYTHON/OCRTest.py

@@ -222,6 +222,36 @@ def main():
         doc.Save(output_path + "physics.pdf", 0)
         print("Example 6: extracting and applying OCR XML from physics.tif")
 
+        # Example 7) Check whether a page needs OCR before running it, to avoid unnecessary OCR
+        # processing on pages that already contain extractable text
+        # --------------------------------------------------------------------------------
+
+        # A) Open the .pdf document
+
+        doc = PDFDoc(input_path + "german_kids_song.pdf")
+
+        # B) Grab the page to be checked
+
+        page = doc.GetPage(1)
+
+        # C) Ask OCRModule whether the page needs OCR. Passing process_invisible_text as False
+        # means invisible text (e.g. from a prior OCR pass) is ignored and only visible content
+        # is considered, while True would treat an existing invisible text layer as sufficient
+        # to consider the page as not needing OCR.
+
+        needs_ocr = OCRModule.PageNeedsOCR(doc, page, False)
+        print("Example 7: page 1 of german_kids_song.pdf " + ("needs" if needs_ocr else "does not need") + " OCR")
+
+        # D) Only run OCR if it is actually needed
+
+        if needs_ocr:
+            opts = OCROptions()
+            if use_iris:
+                opts.SetOCREngine("iris")
+            opts.AddLang("deu")
+            OCRModule.ProcessPDF(doc, opts)
+            doc.Save(output_path + "german_kids_song_conditional.pdf", 0)
+
         PDFNet.Terminate()
 
 

Samples/OCRTest/RUBY/OCRTest.rb

@@ -249,6 +249,36 @@
 
       doc.Close
 
+      # Example 7) Check whether a page needs OCR before running it, to avoid unnecessary OCR
+      # processing on pages that already contain extractable text
+      # --------------------------------------------------------------------------------
+
+      # A) Open the .pdf document
+      doc = PDFDoc.new(input_path + "german_kids_song.pdf")
+
+      # B) Grab the page to be checked
+      page = doc.GetPage(1)
+
+      # C) Ask OCRModule whether the page needs OCR. Passing process_invisible_text as false
+      # means invisible text (e.g. from a prior OCR pass) is ignored and only visible content
+      # is considered, while true would treat an existing invisible text layer as sufficient
+      # to consider the page as not needing OCR.
+      needs_ocr = OCRModule.PageNeedsOCR(doc, page, false)
+      puts "Example 7: page 1 of german_kids_song.pdf #{needs_ocr ? 'needs' : 'does not need'} OCR"
+
+      # D) Only run OCR if it is actually needed
+      if needs_ocr
+         opts = OCROptions.new
+         if use_iris
+            opts.SetOCREngine("iris")
+         end
+         opts.AddLang("deu")
+         OCRModule.ProcessPDF(doc, opts)
+         doc.Save(output_path + "german_kids_song_conditional.pdf", 0)
+      end
+
+      doc.Close
+
    end
    rescue Exception=>e
       puts e