fix(magic_pdf): correct color channel conversion for OCR in PDF extract

magic_pdf/model/pdf_extract_kit.py

@@ -215,7 +215,8 @@ class CustomPEKModel:
                         })
 
                 # OCR识别
-                ocr_res = self.ocr_model.ocr(np.array(new_image), mfd_res=adjusted_mfdetrec_res)[0]
+                new_image = cv2.cvtColor(np.asarray(new_image), cv2.COLOR_RGB2BGR)
+                ocr_res = self.ocr_model.ocr(new_image, mfd_res=adjusted_mfdetrec_res)[0]
 
                 # 整合结果
                 if ocr_res:

magic_pdf/model/pek_sub_modules/self_modify.py

@@ -301,60 +301,4 @@ class ModifiedPaddleOCR(PaddleOCR):
                 filter_rec_res.append(rec_result)
         end = time.time()
         time_dict['all'] = end - start
-        return filter_boxes, filter_rec_res, time_dict
-
-
-if __name__ == '__main__':
-    def merge_intervals(intervals):
-        # Sort the intervals based on the start value
-        intervals.sort(key=lambda x: x[0])
-
-        merged = []
-        for interval in intervals:
-            # If the list of merged intervals is empty or if the current
-            # interval does not overlap with the previous, simply append it.
-            if not merged or merged[-1][1] < interval[0]:
-                merged.append(interval)
-            else:
-                # Otherwise, there is overlap, so we merge the current and previous intervals.
-                merged[-1][1] = max(merged[-1][1], interval[1])
-
-        return merged
-
-
-    def remove_intervals(original, masks):
-        # Merge all mask intervals
-        merged_masks = merge_intervals(masks)
-
-        result = []
-        original_start, original_end = original
-
-        for mask in merged_masks:
-            mask_start, mask_end = mask
-
-            # If the mask starts after the original range, ignore it
-            if mask_start > original_end:
-                continue
-
-            # If the mask ends before the original range starts, ignore it
-            if mask_end < original_start:
-                continue
-
-            # Remove the masked part from the original range
-            if original_start < mask_start:
-                result.append([original_start, mask_start - 1])
-
-            original_start = max(mask_end + 1, original_start)
-
-        # Add the remaining part of the original range, if any
-        if original_start <= original_end:
-            result.append([original_start, original_end])
-
-        return result
-
-
-    # Test the function
-    original_range = [1, 100]
-    masks = [[0, 15], [25, 40], [55, 80]]
-    result = remove_intervals(original_range, masks)
-    print(result)  # Expected output: [[1, 4], [21, 59], [81, 100]]
+        return filter_boxes, filter_rec_res, time_dict
\ No newline at end of file