cd /home/daytona/workspace/attachments/7cd11e69-986a-4b28-95a0-ffeb92b21965/ && python3 -c " import pdfplumber with pdfplumber.open('shalya paper.pdf') as pdf: print(f'Total pages: {len(pdf.pages)}') for i, page in enumerate(pdf.pages): text = page.extract_text() print(f'--- PAGE {i+1} ---') print(text) print() "

cd /home/daytona/workspace/attachments/7cd11e69-986a-4b28-95a0-ffeb92b21965/ && python3 -c " import fitz # pymupdf doc = fitz.open('shalya paper.pdf') print(f'Pages: {len(doc)}') for i, page in enumerate(doc): text = page.get_text() if text.strip(): print(f'--- PAGE {i+1} ---') print(text[:500]) else: print(f'Page {i+1}: (no text layer)') "

cd /home/daytona/workspace/attachments/7cd11e69-986a-4b28-95a0-ffeb92b21965/ && python3 -c " from pypdf import PdfReader reader = PdfReader('shalya paper.pdf') print(f'Pages: {len(reader.pages)}') # Check if pages have images page = reader.pages[0] print('Resources:', page.get('/Resources')) print('Images:', list(page.images) if hasattr(page, 'images') else 'N/A') "

which tesseract && tesseract --version 2>&1 | head -3

cd /home/daytona/workspace/attachments/7cd11e69-986a-4b28-95a0-ffeb92b21965/ && mkdir -p /home/daytona/workspace/shalya-ocr && python3 -c " from pypdf import PdfReader import io, os reader = PdfReader('shalya paper.pdf') print(f'Total pages: {len(reader.pages)}') # Extract all unique images all_images = {} for i, page in enumerate(reader.pages): for img in page.images: key = img.name if key not in all_images: all_images[key] = (i, img.data) print('Unique images found:', list(all_images.keys())) for name, (pg, data) in all_images.items(): fpath = f'/home/daytona/workspace/shalya-ocr/{name}' with open(fpath, 'wb') as f: f.write(data) print(f'Saved {name} ({len(data)} bytes) from page {pg+1}') "

which pdftoppm && pdftoppm --version 2>&1 | head -2

cd /home/daytona/workspace/attachments/7cd11e69-986a-4b28-95a0-ffeb92b21965/ && pdftoppm -r 200 -png "shalya paper.pdf" /home/daytona/workspace/shalya-ocr/page && ls /home/daytona/workspace/shalya-ocr/ | head -5

cd /home/daytona/workspace/shalya-ocr && for f in page-*.png; do tesseract "$f" "${f%.png}_ocr" -l eng 2>/dev/null; done && echo "OCR done" && ls *.txt | wc -l

cd /home/daytona/workspace/shalya-ocr && cat page-01_ocr.txt && echo "===" && cat page-02_ocr.txt && echo "===" && cat page-03_ocr.txt

cd /home/daytona/workspace/shalya-ocr && cat page-*_ocr.txt > /home/daytona/workspace/shalya-ocr/all_text.txt && wc -l /home/daytona/workspace/shalya-ocr/all_text.txt

python3 << 'EOF' import re from collections import defaultdict, Counter with open('/home/daytona/workspace/shalya-ocr/all_text.txt', 'r') as f: full_text = f.read() # Split into papers by detecting exam headers papers = re.split(r'GUJARAT AYURVED UNIVERSITY', full_text) print(f"Number of paper sections found: {len(papers)-1}") # Print header of each section to understand years for i, p in enumerate(papers[1:], 1): lines = p.strip().split('\n') header = ' '.join(lines[:5]) print(f"\n=== Section {i} ===") print(header[:200]) EOF

python3 << 'PYEOF' import re from collections import defaultdict, Counter with open('/home/daytona/workspace/shalya-ocr/all_text.txt', 'r') as f: full_text = f.read() # Extract all questions - look for lines starting with (A), (B), (C), (D), (E), (F) # Also numbered questions 1-8 all_questions = [] # Split by paper papers = re.split(r'GUJARAT AYURVED UNIVERSITY', full_text) for paper in papers[1:]: lines = paper.strip().split('\n') for line in lines: line = line.strip() # Match question lines (A) (B) (C) (D) (E) (F) patterns if re.match(r'^\([A-F]\)', line) or re.match(r'^\([A-F]\)\s', line): # Clean up the line q = re.sub(r'^\([A-F]\)\s*', '', line).strip() q = re.sub(r'\s+', ' ', q) if len(q) > 15: # filter out very short/noise lines all_questions.append(q) print(f"Total question entries extracted: {len(all_questions)}") print("\nSample questions:") for q in all_questions[:20]: print(f" - {q}") PYEOF

python3 << 'PYEOF' import re from collections import defaultdict, Counter with open('/home/daytona/workspace/shalya-ocr/all_text.txt', 'r') as f: full_text = f.read() # Also get SECTION main questions (Q1, Q5) papers_raw = re.split(r'GUJARAT AYURVED UNIVERSITY', full_text) # Collect all lines with questions - broader approach # Look for lines starting with (A), (B), (C), (D), (E), (F) as sub-questions # Also look for numbered questions like "1. Describe..." # and "5. Write..." all_q_lines = [] for paper_idx, paper in enumerate(papers_raw[1:], 1): lines = paper.strip().split('\n') i = 0 while i < len(lines): line = lines[i].strip() # Sub-question lines if re.match(r'^\([A-F]\)', line): q = re.sub(r'^\([A-F]\)\s*', '', line).strip() # sometimes question continues on next line if i+1 < len(lines) and not re.match(r'^\([A-F]\)', lines[i+1].strip()) and not re.match(r'^\d+\.', lines[i+1].strip()): next_line = lines[i+1].strip() if len(next_line) > 5 and not next_line.startswith('CE') and not next_line.startswith('CG'): q = q + ' ' + next_line if len(q) > 10: all_q_lines.append(('sub', q.strip(), paper_idx)) # Main numbered questions elif re.match(r'^[1-8]\.\s+[A-Z]', line) or re.match(r'^[1-8]\.\s+[Ww]rite', line) or re.match(r'^[1-8]\.\s+[Dd]escribe', line) or re.match(r'^[1-8]\.\s+[Ee]xplain', line): q = re.sub(r'^\d+\.\s*', '', line).strip() if len(q) > 10: all_q_lines.append(('main', q.strip(), paper_idx)) i += 1 print(f"Main questions: {sum(1 for t,_,_ in all_q_lines if t=='main')}") print(f"Sub questions: {sum(1 for t,_,_ in all_q_lines if t=='sub')}") print(f"Total: {len(all_q_lines)}") # Now normalize and count frequencies def normalize_q(q): q = q.lower() q = re.sub(r'[^\w\s]', ' ', q) q = re.sub(r'\s+', ' ', q).strip() return q # Build keyword-based topic clusters topics = { # Shalya Tantra I topics "Ksharakarma / Kshar Sutra": ["ksharakarma", "kshara karma", "ksharsutra", "kshara sutra", "kshar sutra"], "Bandha vidhi / Bandages": ["bandha", "bandage", "pattabandha", "pattbandhana", "bandhana"], "Pranashta Shalya": ["pranashta shalya", "pranashta"], "Agnikarma": ["agnikarma", "agni karma"], "Shastrakarma / Shastra types": ["shastrakarma", "shastra karma", "ashtavidha shastra", "asthavidha shastra", "ashta vidha shastra", "eight shastra"], "Trividha Karma": ["trividha karma", "trividhkarma", "trividh karma"], "Anaesthesia (General/Regional/Nerve block)": ["anaesthesia", "anesthesia", "nerve block", "pudendal", "spinal anaesthesia", "general anaesthesia", "regional anaesthesia"], "Marma / Marmaghata": ["marma", "marmaghata"], "Sterilization / Nirjivanukarana": ["sterilization", "nirjivanukarana", "nirjivanu"], "X-Ray / Radiology in Surgery": ["x-ray", "x ray", "xray", "radiology", "radiograph"], "Rakta / Haemorrhage": ["rakta", "haemorrhage", "hemorrhage", "rakta mahatva", "rakta stambhak"], "Yantra / Surgical instruments": ["yantra", "probe", "trocar", "canula", "nadiyantra", "instrument"], "Shatkriyakala": ["shatkriyakala", "shatvidha kriyakala", "shadkriyakala", "shat kriya"], "Parenteral nutrition / Metabolic Acidosis": ["parenteral nutrition", "metabolic acidosis"], "Antibiotics in surgery": ["antibiotic"], "Inflammation": ["inflammation", "shotha"], # Vrana / Wound topics "Vrana / Wound management": ["vrana", "wound", "vranashopha", "vranaropana", "vrana vastu", "vranitagara"], "Nadivrana (Sinus / Fistula)": ["nadivrana", "nadi vrana", "sinus", "fistula in ano"], "Vidradhi (Abscess)": ["vidradhi", "abscess", "asthi vidradhi", "osteomyelitis"], # Paper II - Surgery topics "Bhagandara (Fistula in Ano)": ["bhagandara", "fistula in ano"], "Arsha (Haemorrhoids/Piles)": ["arsha", "haemorrhoid", "hemorrhoid", "piles", "parikartika", "fissure in ano"], "Aantravriddhi / Hernia": ["aantravriddhi", "hernia", "inguinal hernia", "hiatus hernia"], "Arbuda (Tumour/Cancer)": ["arbuda", "tumour", "tumor", "cancer", "neoplasm", "cyst", "ganglion"], "Galganda (Goitre/Thyroid)": ["galganda", "galgand", "goitre", "goiter", "thyroid", "toxic goitre"], "Peptic Ulcer / Intestinal Perforation": ["peptic ulcer", "chhidrodara", "intestinal perforation", "peptic"], "Appendicitis": ["appendicitis", "appendix"], "Abdominal Injuries / Peritonitis": ["abdominal injur", "peritonitis", "abdominal trauma"], "Cholecystitis / Gallbladder": ["cholecystitis", "pittashaya", "gallbladder", "gallstone", "cholelithiasis"], "Hydronephrosis / BPH / Urinary": ["hydronephrosis", "bph", "benign prostatic", "hematuria", "haematuria", "urinary bladder", "niruddhaprakasha"], "Fractures (Colles/Bhagna)": ["fracture", "colles", "bhagna", "kanda bhagna"], "DVT / Varicose veins": ["dvt", "deep vein thrombosis", "varicose", "trendlenburg", "trendenburg"], "Shock (Hypovolemic etc.)": ["shock", "hypovolemic"], "Atherosclerosis / Peripheral Vascular": ["atherosclerosis", "raynaud", "peripheral vascular", "buerger"], "Splenic Injury": ["splenic", "spleen"], "Rectal Prolapse / Anal conditions": ["rectal prolapse", "parikartika", "sannirugdhaguda", "anal stricture", "parivartika", "paraphimosis"], "Kshudra Roga": ["kshudra roga", "kshrudra roga", "paronychia", "kunakha", "pashangardabha", "kadar"], "Liver Abscess": ["liver abscess", "amoebic liver", "hepatic abscess", "pyogenic abscess"], "Nija Vrana / Agantu Vrana": ["nija vrana", "agantu vrana"], "Haemangioma / Vascular tumours": ["haemangioma", "hemangioma"], } topic_counts = defaultdict(list) for qtype, q, paper_idx in all_q_lines: q_norm = normalize_q(q) for topic, keywords in topics.items(): for kw in keywords: if kw.lower() in q_norm: topic_counts[topic].append(q[:100]) break print("\n\n=== TOPIC FREQUENCY ANALYSIS ===") sorted_topics = sorted(topic_counts.items(), key=lambda x: len(x[1]), reverse=True) for topic, questions in sorted_topics: print(f"\n{topic}: {len(questions)} times") # Show unique question variants seen = set() for q in questions: k = q[:60] if k not in seen: seen.add(k) print(f" - {q[:100]}") PYEOF

python3 << 'PYEOF' # Extract specific most-repeated individual questions for the top categories import re from collections import Counter with open('/home/daytona/workspace/shalya-ocr/all_text.txt', 'r') as f: full_text = f.read() papers_raw = re.split(r'GUJARAT AYURVED UNIVERSITY', full_text) # Collect specific question counts for most repeated individual questions specific_q_patterns = { # Paper I "Vrana / Wound (Sadyovrana, Dagdha, Nadivrana, Vranashotha)": [ "sadyovrana", "dagdha vrana", "vranashotha", "wound healing", "vrana shotha", "burns" ], "Marma importance in surgery": ["importance of marma in surgery", "importance of marma", "surgical importance of marma"], "Pranashta Shalya (def + removal)": ["pranashta shalya"], "Anaesthesia (Spinal/General/Regional)": ["spinal anaesthesia", "regional anaesthesia", "general anaesthesia", "anaesthesia"], "Ksharakarma / Kshar Sutra": ["ksharakarma", "kshara sutra", "ksharsutra", "kshara karma"], "Agnikarma (types, indications)": ["agnikarma", "agni karma"], "Sterilization / Autoclave": ["sterilization", "autoclave", "nirjivanukarana", "nirjantukarana"], "Bandha / Bandages (types)": ["bandha", "bandage", "pattabandha", "pattabandhana"], "Rakta / Haemorrhage / Raktamokshana": ["raktamokshana", "haemorrhage", "hemorrhage", "rakta stambhak", "rakta mahatva"], "Trividha Karma": ["trividha karma", "trividhkarma"], "Ashtavidha Shastrakarma": ["ashtavidha shastra", "ashta vidha shastra", "asthavidha shastra"], "Shatkriyakala": ["shatkriyakala", "shatvidha kriyakala", "shat kriya"], "Yantra (types, Nadiyantra)": ["yantra", "nadiyantra"], # Paper II "Hernia (Inguinal/Femoral/Incisional)": ["hernia", "aantravriddhi"], "BPH / Hydronephrosis": ["bph", "benign prostatic", "hydronephrosis", "hematuria"], "Vidradhi / Abscess (Breast/Liver/Osteo)": ["vidradhi", "abscess", "osteomyelitis"], "Bhagandara / Fistula in Ano": ["bhagandara", "fistula in ano"], "Arsha / Haemorrhoids / Parikartika": ["arsha", "haemorrhoid", "parikartika", "fissure in ano"], "Galganda / Goitre / Thyroid": ["galganda", "galgand", "goitre", "goiter", "thyroid"], "Fractures (Bhagna/Colles/Femur)": ["bhagna", "fracture", "colles"], "Arbuda / Tumour / Cancer / Cyst": ["arbuda", "tumour", "tumor", "cyst", "ganglion"], "DVT / Varicose Veins": ["dvt", "varicose", "deep vein thrombosis"], "Cholecystitis / Gallstones": ["cholecystitis", "cholelithiasis", "pittashaya"], "Shock / Marmaghata": ["shock", "marmaghata"], "Peptic Ulcer / Chhidrodara": ["peptic ulcer", "chhidrodara", "intestinal perforation"], "Atherosclerosis / Raynaud / PVD": ["atherosclerosis", "raynaud", "buerger"], "Kshudra Roga (Chippa/Kunakha/Kadar)": ["chippa", "kunakha", "kadar", "paronychia", "pashangardabha"], "Appendicitis": ["appendicitis"], "Peritonitis / Abdominal injury": ["peritonitis", "abdominal injur"], } all_lines = full_text.lower() print("SPECIFIC QUESTION/TOPIC REPEAT COUNT:") print("="*60) for topic, keywords in specific_q_patterns.items(): count = 0 for kw in keywords: count += all_lines.count(kw) print(f"{topic}: ~{count} mentions") PYEOF