Update annotations.py

annotations.py

@@ -13,9 +13,7 @@ def extract_pdf_text(file) -> str:
         for page in doc:
             text = page.get_text("text")
             full_text += text + "\n"
-            print(f"Extracted text from page {page.number + 1}: {len(text)} characters")
         doc.close()
-        print(f"Total extracted text length: {len(full_text)} characters")
         return full_text
     except Exception as e:
         print(f"Error extracting text from PDF: {e}")
@@ -37,7 +35,6 @@ def check_language_issues(full_text: str) -> Dict[str, Any]:
                 "offset": match.offset,
                 "length": match.errorLength
             })
-        print(f"Total language issues found: {len(issues)}")
         return {
             "total_issues": len(issues),
             "issues": issues
@@ -55,7 +52,6 @@ def highlight_issues_in_pdf(file, language_matches: List[Dict[str, Any]]) -> byt
     try:
         # Open the PDF
         doc = fitz.open(stream=file.read(), filetype="pdf") if not isinstance(file, str) else fitz.open(file)
-        print(f"Opened PDF with {len(doc)} pages.")
 
         # Extract words with positions from each page
         word_list = []  # List of tuples: (page_number, word, x0, y0, x1, y1)
@@ -65,19 +61,16 @@ def highlight_issues_in_pdf(file, language_matches: List[Dict[str, Any]]) -> byt
             for w in words:
                 word_text = w[4]
                 word_list.append((page_number, word_text, w[0], w[1], w[2], w[3]))
-            print(f"Page {page_number + 1}: Extracted {len(words)} words.")
 
         # Concatenate all words to form the full text
         concatenated_text = " ".join([w[1] for w in word_list])
-        print(f"Concatenated text length: {len(concatenated_text)} characters.")
 
         # Iterate over each language issue
-        for idx, issue in enumerate(language_matches, 1):
+        for issue in language_matches:
             offset = issue["offset"]
             length = issue["length"]
             error_text = concatenated_text[offset:offset+length]
-            print(f"\nIssue {idx}: '{error_text}' at offset {offset} with length {length}")
-            
+
             # Find the words that fall within the error span
             current_pos = 0
             target_words = []
@@ -89,10 +82,6 @@ def highlight_issues_in_pdf(file, language_matches: List[Dict[str, Any]]) -> byt
                     target_words.append(word)
                 current_pos += word_length
 
-            if not target_words:
-                print("No matching words found for this issue.")
-                continue
-
             # Add highlight annotations to the target words
             for target in target_words:
                 page_num, word_text, x0, y0, x1, y1 = target
@@ -103,14 +92,18 @@ def highlight_issues_in_pdf(file, language_matches: List[Dict[str, Any]]) -> byt
                 highlight = page.add_highlight_annot(rect)
                 highlight.set_colors(stroke=(1, 1, 0))  # Yellow color
                 highlight.update()
-                print(f"Highlighted '{word_text}' on page {page_num + 1} at position ({x0}, {y0}, {x1}, {y1})")
 
         # Save annotated PDF to bytes
         byte_stream = io.BytesIO()
         doc.save(byte_stream)
         annotated_pdf_bytes = byte_stream.getvalue()
         doc.close()
-        print("Annotated PDF successfully created.")
+
+        # Save annotated PDF locally for verification
+        with open("annotated_temp.pdf", "wb") as f:
+            f.write(annotated_pdf_bytes)
+        print("Annotated PDF saved as 'annotated_temp.pdf' for manual verification.")
+
         return annotated_pdf_bytes
     except Exception as e:
         print(f"Error in highlighting PDF: {e}")
@@ -131,5 +124,4 @@ def analyze_pdf(file) -> Tuple[Dict[str, Any], bytes]:
         annotated_pdf = highlight_issues_in_pdf(file, issues) if issues else None
         return language_issues, annotated_pdf
     except Exception as e:
-        print(f"Error in analyze_pdf: {e}")
         return {"error": str(e)}, None