myocr-lib 0.1.3__py3-none-any.whl → 0.1.4__py3-none-any.whl

{myocr_lib-0.1.3.dist-info → myocr_lib-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: myocr_lib
-Version: 0.1.3
+Version: 0.1.4
 Summary: To be available soon
 Keywords: utility,library,functions,ocr,image-processing
 Classifier: Development Status :: 3 - Alpha
@@ -16,4 +16,3 @@ Requires-Dist: ocrmypdf>=16.12.0
 Requires-Dist: Pillow>=9.0.0
 Requires-Dist: opencv-python>=4.12.0
 Requires-Dist: PyMuPDF>=1.26.7
-

myocr_lib-0.1.4.dist-info/RECORD

@@ -0,0 +1,8 @@
+ocr_img/__init__.py,sha256=A0HMZNNgwObl6qZHeGKXQSf-VhPlkQt3YKEcA_VXHLw,80
+ocr_img/main_code.py,sha256=738bf1zZTr1FRncvPfUik4SSS2nSMkPqrCFRtnQeGmM,1300
+ocr_pdf/__init__.py,sha256=t4SYasAJ1pjnd7sZBnPe1PqMbR18-4onsHXu93zw1LE,96
+ocr_pdf/main_code.py,sha256=7wYi6HPUoKyvqOk02qiPC2RR39CSKCRb9Eki8vhOes0,9368
+myocr_lib-0.1.4.dist-info/METADATA,sha256=7IopmcXCQifPCF8B_8AJRCVQIP8rQofXsLEA2sU1u5g,675
+myocr_lib-0.1.4.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+myocr_lib-0.1.4.dist-info/top_level.txt,sha256=m22oM9I_3SovUyKNzGQIpqgCp7GTXua0G7cEYqMx654,16
+myocr_lib-0.1.4.dist-info/RECORD,,

{myocr_lib-0.1.3.dist-info → myocr_lib-0.1.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.3.2)
+Generator: setuptools (80.10.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

ocr_pdf/main_code.py

@@ -13,6 +13,50 @@ class OCRDataExtractor:
         self.pages_to_ocr = [] # holds the pages needing ocr 
 
 
+    def _raise_for_ocr_results(self, result):
+        """This function raises the corresponding and matching exceptions based on the value of thre result code."""
+        # key for the exceptions code
+        exceptions_codes = {exc:"" for exc in [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 130]}
+
+        return_code = result.returncode
+
+        match return_code:
+            case 1:
+                raise Exception("Invalid arguments were provided.")
+
+            case 2:
+                raise Exception("The input file is not a valid PDF.")
+
+            case 3:
+                raise Exception("An external program (like Tesseract or Ghostscript) required by OCRmyPDF is missing.")
+            
+            case 4: 
+                raise Exception("An output file was created, but it is invalid (the file will still be produced).")
+
+            case 5: 
+                raise Exception("Insufficient permissions to read the input or write the output file.")
+            
+            case 6:
+                raise Exception("The file already contains text, and the command was not configured to force re-processing.")
+            
+            case 7: 
+                raise Exception("An error occurred in an external program (e.g., Ghostscript).")
+            
+            case 8:
+                raise Exception("The input PDF is encrypted and cannot be processed.")
+            
+            case 9:
+                raise Exception("Tesseract rejected a custom configuration file.")
+            
+            case 10: 
+                raise Exception("A valid PDF was created, but conversion to PDF/A failed.")
+
+            case 15:
+                raise Exception("An unexpected or other error occurred.")
+
+            case 130:
+                raise Exception("The program was interrupted by the user (Ctrl+C). ")
+
 
     def _apply_whole_pdf_ocr(self):
         # Define the Commands
@@ -27,14 +71,65 @@ class OCRDataExtractor:
         # run the command
         result = subprocess.run(command, capture_output=True, text=True)
         
+        try:
+            self._raise_for_ocr_results(result)
+
+        except Exception as e:
+            print("Error during OCR process:\n", str(e))
+
+            if result.returncode == 6: # already has text
+                print("Retrying using forcing..")
+                # use force ocr 
+                # Define the Commands
+                command = [
+                    "ocrmypdf",
+                    f"{self.input_pdf_path}",
+                    f"{self.output_file_path}",
+                    "--force-ocr",
+                    "--tesseract-timeout", "1000" # increased timeout
+                ]
+
+                # run the command
+                result = subprocess.run(command, capture_output=True, text=True)
+
+            else:
+                raise e
+
+
         if result.returncode == 0:
-            print("OCR on PDF Was successfully.")
+            print("OCR Was applied on the PDF.")
         
             return True
         
         return False
     
 
+    ########### Ratio Functions
+    def _text_coverage_ratio(self,page):
+        blocks = page.get_text("blocks")
+        page_area = page.rect.width * page.rect.height
+
+        text_area = 0
+        for block in blocks:
+            if block[6] == 0:  # text block
+                x0, y0, x1, y1 = block[:4]
+                text_area += (x1 - x0) * (y1 - y0)
+
+        return text_area / page_area if page_area else 0
+
+    def _image_coverage_ratio(self, page):
+        images = page.get_images(full=True)
+        page_area = page.rect.width * page.rect.height
+        image_area = 0
+
+        for img in images:
+            xref = img[0]
+            rects = page.get_image_rects(xref)
+            for r in rects:
+                image_area += r.width * r.height
+
+        return image_area / page_area if page_area else 0
+
     def _is_whole_pdf_ocr(self):
         # read and extract the whole text from the pdf
         THRESHOLD_VALUE = 100 # minimum text
@@ -44,14 +139,31 @@ class OCRDataExtractor:
             for page_num in range(len(doc)):
                 page = doc.load_page(page_num)
                 text = page.get_text()
-                if len(text.strip()) > THRESHOLD_VALUE:
-                    is_whole_pdf_ocr_applicable = False
-                else:
+
+                # add logic if the image and text ratio is above a certain threshold
+                image_ratio = self._image_coverage_ratio(page)
+                text_ratio = self._text_coverage_ratio(page)
+                print(f"Image :\t{image_ratio*100:.2f}")
+
+
+                # if len(text.strip()) > THRESHOLD_VALUE:
+                if image_ratio > 0.45:
+                    # print("Length of text:\n", len(text.strip()))
+                    print(f"Image :\t{image_ratio*100:.2f}")
                     # append to the page list
                     self.pages_to_ocr.append(page_num)
+
+                elif text_ratio < 0.05:
+                    print(f"Text :\t{text_ratio*100:.2f}")
+                    # append to the page list
+                    self.pages_to_ocr.append(page_num)
+
+                else:
+                    is_whole_pdf_ocr_applicable = False
             
         return is_whole_pdf_ocr_applicable
     
+    ########### Page by Page Functions
     def _is_page_by_page_ocr(self):
         return len(self.pages_to_ocr) > 0
     

myocr_lib-0.1.3.dist-info/RECORD

@@ -1,8 +0,0 @@
-ocr_img/__init__.py,sha256=A0HMZNNgwObl6qZHeGKXQSf-VhPlkQt3YKEcA_VXHLw,80
-ocr_img/main_code.py,sha256=738bf1zZTr1FRncvPfUik4SSS2nSMkPqrCFRtnQeGmM,1300
-ocr_pdf/__init__.py,sha256=t4SYasAJ1pjnd7sZBnPe1PqMbR18-4onsHXu93zw1LE,96
-ocr_pdf/main_code.py,sha256=Rz9PtpA79XPbX2VsmeNaQabnY_ZoRkYylTUeNZPc2cE,5175
-myocr_lib-0.1.3.dist-info/METADATA,sha256=s-8a8rie6ytZfIIF4vplbuot2_gHccJ8gUF9vHslcwY,677
-myocr_lib-0.1.3.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
-myocr_lib-0.1.3.dist-info/top_level.txt,sha256=m22oM9I_3SovUyKNzGQIpqgCp7GTXua0G7cEYqMx654,16
-myocr_lib-0.1.3.dist-info/RECORD,,