Update annotations.py

annotations.py

@@ -8,12 +8,15 @@ import io
 def extract_pdf_text(file) -> str:
     """Extracts full text from a PDF file using PyMuPDF."""
     try:
+        # Open the PDF file
         doc = fitz.open(stream=file.read(), filetype="pdf") if not isinstance(file, str) else fitz.open(file)
         full_text = ""
-        for page in doc:
+        for page_num, page in enumerate(doc, start=1):
             text = page.get_text("text")
             full_text += text + "\n"
+            print(f"Extracted text from page {page_num}: {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}")
@@ -28,13 +31,14 @@ def check_language_issues(full_text: str) -> Dict[str, Any]:
         for match in matches:
             issues.append({
                 "message": match.message,
-                "context": match.context,
+                "context": match.context.strip(),
                 "suggestions": match.replacements[:3] if match.replacements else [],
                 "category": match.category,
                 "rule_id": match.ruleId,
                 "offset": match.offset,
                 "length": match.errorLength
             })
+        print(f"Total language issues found: {len(issues)}")
         return {
             "total_issues": len(issues),
             "issues": issues
@@ -52,6 +56,7 @@ 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)
@@ -61,15 +66,18 @@ 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"Total words extracted: {len(word_list)}")
 
         # 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 issue in language_matches:
+        for idx, issue in enumerate(language_matches, start=1):
             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
@@ -82,6 +90,10 @@ 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
@@ -92,6 +104,7 @@ 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()
@@ -112,6 +125,8 @@ def highlight_issues_in_pdf(file, language_matches: List[Dict[str, Any]]) -> byt
 def analyze_pdf(file) -> Tuple[Dict[str, Any], bytes]:
     """Analyzes the PDF for language issues and returns results and annotated PDF."""
     try:
+        # Reset file pointer before reading
+        file.seek(0)
         full_text = extract_pdf_text(file)
         if not full_text:
             return {"error": "Failed to extract text from PDF."}, None
@@ -121,6 +136,8 @@ def analyze_pdf(file) -> Tuple[Dict[str, Any], bytes]:
             return language_issues, None
 
         issues = language_issues.get("issues", [])
+        # Reset file pointer before highlighting
+        file.seek(0)
         annotated_pdf = highlight_issues_in_pdf(file, issues) if issues else None
         return language_issues, annotated_pdf
     except Exception as e: