nate/nextgenpdf
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
main
nextgenpdf/pdf_renamer.py
T

3395 lines
149 KiB
Python
Raw Permalink Blame History

# -*- coding: utf-8 -*-
import os
import tempfile
import zipfile
import threading
import uuid
import json
from datetime import datetime
from functools import wraps
from flask import Flask, request, render_template_string, redirect, url_for, session, send_from_directory, flash, get_flashed_messages, jsonify
from werkzeug.utils import secure_filename
from werkzeug.middleware.proxy_fix import ProxyFix
from PyPDF2 import PdfReader
from authlib.integrations.flask_client import OAuth
app = Flask(__name__)
# Trust proxy headers (since we're behind Nginx)
app.wsgi_app = ProxyFix(app.wsgi_app, x_for=1, x_proto=1, x_host=1, x_prefix=1)
app.config['UPLOAD_FOLDER'] = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'processed')
app.config['ARCHIVE_FOLDER'] = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'archives')
os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
os.makedirs(app.config['ARCHIVE_FOLDER'], exist_ok=True)
app.config['MAX_CONTENT_LENGTH'] = 500 * 1024 * 1024 # 500MB limit
app.secret_key = os.getenv('SECRET_KEY', 'dev-secret-key-change-in-production')
# Secure session cookie settings
app.config['SESSION_COOKIE_SECURE'] = True # Only send cookie over HTTPS
app.config['SESSION_COOKIE_HTTPONLY'] = True # Prevent JavaScript access
app.config['SESSION_COOKIE_SAMESITE'] = 'Lax' # CSRF protection
app.config['PERMANENT_SESSION_LIFETIME'] = 3600 # 1 hour session timeout
# Entra ID Configuration
TENANT_ID = os.getenv('TENANT_ID', 'your-tenant-id')
CLIENT_ID = os.getenv('CLIENT_ID', 'your-client-id')
CLIENT_SECRET = os.getenv('CLIENT_SECRET', 'your-client-secret')
print(f"DEBUG: TENANT_ID = {TENANT_ID}")
print(f"DEBUG: CLIENT_ID = {CLIENT_ID}")
print(f"DEBUG: CLIENT_SECRET = {'*' * len(CLIENT_SECRET) if CLIENT_SECRET else 'None'}")
# Admin Configuration
ADMIN_USERNAME = os.getenv('ADMIN_USERNAME', 'trbcit')
ADMIN_PASSWORD = os.getenv('ADMIN_PASSWORD', 'atdrmbicn')
# Initialize OAuth
oauth = OAuth(app)
# Register Microsoft OAuth provider with proper configuration
try:
microsoft = oauth.register(
name='microsoft',
client_id=CLIENT_ID,
client_secret=CLIENT_SECRET,
server_metadata_url=f'https://login.microsoftonline.com/{TENANT_ID}/v2.0/.well-known/openid-configuration',
client_kwargs={
'scope': 'openid email profile',
'token_endpoint_auth_method': 'client_secret_post'
}
)
print("DEBUG: Microsoft OAuth provider registered successfully")
except Exception as e:
print(f"ERROR: Failed to register Microsoft OAuth provider: {e}")
microsoft = None
# Job persistence
JOBS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'jobs.json')
job_queue = {}
job_lock = threading.Lock()
def _save_jobs_unlocked():
"""Internal: Save jobs without acquiring lock (assumes lock is already held)"""
try:
# Convert datetime objects to strings for JSON serialization
jobs_to_save = {}
for job_id, job in job_queue.items():
jobs_to_save[job_id] = job.copy()
# Convert any datetime objects if needed
if 'created_at' in jobs_to_save[job_id]:
jobs_to_save[job_id]['created_at'] = str(jobs_to_save[job_id]['created_at'])
with open(JOBS_FILE, 'w') as f:
json.dump(jobs_to_save, f, indent=2)
except Exception as e:
print(f"ERROR: Failed to save jobs: {e}")
def save_jobs():
"""Save jobs to persistent storage"""
with job_lock:
_save_jobs_unlocked()
def load_jobs():
"""Load jobs from persistent storage"""
global job_queue
try:
if os.path.exists(JOBS_FILE):
with open(JOBS_FILE, 'r') as f:
loaded_jobs = json.load(f)
# Only load jobs where archive files still exist
valid_jobs = {}
skipped_count = 0
for job_id, job_data in loaded_jobs.items():
# Only keep completed jobs with existing archive files
if job_data.get('status') == 'completed':
zip_path = job_data.get('zip_path', '')
if zip_path and os.path.exists(zip_path):
valid_jobs[job_id] = job_data
else:
skipped_count += 1
print(f"DEBUG: Skipping job {job_id} - archive file missing: {zip_path}")
# Skip jobs that were in progress (they failed during restart)
elif job_data.get('status') in ['pending', 'processing']:
skipped_count += 1
print(f"DEBUG: Skipping incomplete job {job_id} - status: {job_data.get('status')}")
# Keep error state jobs for visibility
elif job_data.get('status') == 'error':
valid_jobs[job_id] = job_data
job_queue = valid_jobs
print(f"DEBUG: Loaded {len(job_queue)} jobs from persistent storage ({skipped_count} skipped)")
# Save the cleaned up job list back to disk
if skipped_count > 0:
save_jobs()
else:
print("DEBUG: No existing jobs file found, starting fresh")
except Exception as e:
print(f"ERROR: Failed to load jobs: {e}")
job_queue = {}
# Load jobs on startup
load_jobs()
# Job cleanup settings
JOB_RETENTION_DAYS = 7
SAVE_BATCH_SIZE = 5 # Only save after this many updates
save_counter = 0
def update_job_status(job_id, status, **kwargs):
"""Update job status and persist changes"""
with job_lock:
if job_id in job_queue:
job_queue[job_id]['status'] = status
job_queue[job_id].update(kwargs)
job_queue[job_id]['updated_at'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
# Only save for important status changes
if status in ['completed', 'error', 'processing']:
_save_jobs_unlocked() # Use unlocked version since we already hold the lock
def cleanup_old_jobs():
"""Remove jobs older than JOB_RETENTION_DAYS"""
from datetime import timedelta
cutoff = datetime.now() - timedelta(days=JOB_RETENTION_DAYS)
with job_lock:
jobs_to_remove = []
for job_id, job in list(job_queue.items()):
if job.get('status') == 'completed':
try:
created_at = datetime.strptime(job.get('created_at', ''), '%Y-%m-%d %H:%M:%S')
if created_at < cutoff:
# Clean up associated files
if job.get('zip_path') and os.path.exists(job['zip_path']):
try:
os.remove(job['zip_path'])
except Exception as e:
print(f"Error removing ZIP file: {e}")
# Clean up uploaded files
for file_info in job.get('files', []):
if 'path' in file_info and os.path.exists(file_info['path']):
try:
os.remove(file_info['path'])
except Exception as e:
print(f"Error removing file: {e}")
jobs_to_remove.append(job_id)
except (ValueError, TypeError) as e:
print(f"Error parsing date for job {job_id}: {e}")
for job_id in jobs_to_remove:
del job_queue[job_id]
print(f"Cleaned up old job: {job_id}")
if jobs_to_remove:
_save_jobs_unlocked() # Use unlocked version since we already hold the lock
print(f"Removed {len(jobs_to_remove)} old jobs")
def save_jobs_batched():
"""Save jobs to disk with batching to reduce I/O"""
global save_counter
save_counter += 1
# Save immediately for critical operations, otherwise batch
if save_counter >= SAVE_BATCH_SIZE:
save_jobs()
save_counter = 0
def analyze_failed_extractions(log_path):
"""
Analyze failed extraction log to identify new patterns.
Returns suggestions for new regex patterns.
"""
import re
from collections import defaultdict
if not os.path.exists(log_path):
return "No failed extraction log found."
patterns_found = defaultdict(int)
try:
with open(log_path, 'r', encoding='utf-8') as f:
content = f.read()
# Split into individual failed extractions
failed_entries = content.split('-' * 50)
for entry in failed_entries:
if 'Text content:' in entry:
text_part = entry.split('Text content:')[1].strip()
lines = text_part.split('\n')
# Analyze line patterns
for i, line in enumerate(lines):
line = line.strip()
if not line:
continue
# Look for potential patterns
# Gender + something
if re.match(r'^(Female|Male)', line):
patterns_found['gender_start'] += 1
# School + something
if re.search(r'(?:High|School|Academy|Middle|Elementary)', line):
patterns_found['school_in_line'] += 1
# Grade + something
if re.match(r'^\d{1,2}', line):
patterns_found['grade_start'] += 1
# Names (capitalized words)
name_words = re.findall(r'\b([A-Z][a-z]+)\b', line)
if len(name_words) >= 2:
patterns_found['multiple_names'] += 1
# Check for concatenated patterns
if re.match(r'^[A-Z][a-z]+[A-Z][a-z]+', line):
patterns_found['concatenated_names'] += 1
except Exception as e:
return f"Error analyzing log: {str(e)}"
# Generate suggestions
suggestions = []
if patterns_found.get('gender_start', 0) > 0:
suggestions.append("Found gender at start of lines - may need new gender-first patterns")
if patterns_found.get('school_in_line', 0) > 0:
suggestions.append("Found school names in lines - may need school-based patterns")
if patterns_found.get('grade_start', 0) > 0:
suggestions.append("Found grades at start of lines - may need grade-first patterns")
if patterns_found.get('multiple_names', 0) > 0:
suggestions.append("Found multiple capitalized words - may need better name parsing")
if patterns_found.get('concatenated_names', 0) > 0:
suggestions.append("Found concatenated names - may need better concatenation handling")
if not suggestions:
suggestions.append("No obvious patterns detected - may need manual inspection")
def map_pattern_1(match1, match2):
return {
'gender': match1.group(1),
'school': match1.group(2).strip(),
'last_name': match1.group(3),
'grade': match2.group(1),
'first_name': match2.group(2)
}
def map_pattern_2(match1, match2, match3):
return {
'first_name': match1.group(1),
'gender': match2.group(1),
'school': match2.group(2).strip(),
'last_name': match2.group(3),
'grade': match3.group(1)
}
def map_pattern_3(match1, match2, match3):
return {
'gender': match1.group(1),
'first_name': match1.group(2),
'school': match2.group(1).strip(),
'last_name': match2.group(2),
'grade': match3.group(1)
}
def map_pattern_4(match1, match2, match3):
return {
'school': match1.group(1).strip(),
'grade': match1.group(2),
'gender': match2.group(1),
'first_name': match2.group(2),
'last_name': match3.group(1)
}
def map_pattern_5(match1, match2, match3):
return {
'first_name': match1.group(1),
'gender': match2.group(1),
'grade': match2.group(2),
'school': match3.group(1).strip(),
'last_name': match3.group(2)
}
def map_pattern_6(match1, match2, match3):
return {
'first_name': match1.group(1),
'school': match2.group(1).strip(),
'grade': match2.group(2),
'last_name': match2.group(3),
'gender': match3.group(1)
}
def map_pattern_7(match1, match2):
return {
'gender': match1.group(1),
'first_name': match1.group(2),
'school': match2.group(1).strip(),
'grade': match2.group(2),
'last_name': match2.group(3)
}
def map_pattern_8(match1, match2, match3):
return {
'school': match1.group(1).strip(),
'first_name': match1.group(2),
'last_name': match2.group(1),
'gender': match3.group(1),
'grade': match3.group(2)
}
def map_pattern_9(match1, match2, match3, match4):
return {
'first_name': match1.group(2),
'last_name': match1.group(1),
'grade': match2.group(1),
'school': match3.group(1).strip(),
'gender': match4.group(1)
}
def map_pattern_10(match1, match2):
return {
'gender': match1.group(1),
'school': match1.group(2).strip(),
'last_name': match1.group(3),
'grade': match2.group(1),
'first_name': match2.group(2)
}
ALLOWED_EXTENSIONS = {'pdf', 'zip'}
ALLOWED_MIME_TYPES = {
'pdf': 'application/pdf',
'zip': 'application/zip'
}
def login_required(f):
@wraps(f)
def decorated_function(*args, **kwargs):
print(f"DEBUG login_required: session = {dict(session)}")
if 'user' not in session and 'admin' not in session:
print("DEBUG: No user or admin in session, redirecting to login")
return redirect(url_for('login'))
print(f"DEBUG: User authenticated: {session.get('user', session.get('admin'))}")
return f(*args, **kwargs)
return decorated_function
def allowed_file(filename, file_stream=None):
"""
Validate file based on extension and optionally MIME type.
Args:
filename: The name of the file
file_stream: Optional file stream to check MIME type
Returns:
bool: True if file is allowed, False otherwise
"""
# Check extension
if '.' not in filename:
return False
ext = filename.rsplit('.', 1)[1].lower()
if ext not in ALLOWED_EXTENSIONS:
return False
# Additional MIME type validation if file stream provided
if file_stream:
try:
import magic
file_stream.seek(0)
mime_type = magic.from_buffer(file_stream.read(2048), mime=True)
file_stream.seek(0)
expected_mime = ALLOWED_MIME_TYPES.get(ext)
if expected_mime and mime_type != expected_mime:
print(f"MIME type mismatch: expected {expected_mime}, got {mime_type}")
return False
except ImportError:
# python-magic not installed, skip MIME check
pass
except Exception as e:
print(f"Error checking MIME type: {e}")
return False
return True
def sanitize_segment(value):
"""Sanitize a path segment to avoid invalid/unsafe filesystem characters."""
import re
if value is None:
return ''
cleaned = str(value)
# Remove path separators and other unsafe characters
cleaned = cleaned.replace(os.sep, ' ')
if os.altsep:
cleaned = cleaned.replace(os.altsep, ' ')
cleaned = re.sub(r'[<>:"/\\|?*\x00-\x1F]', ' ', cleaned)
cleaned = re.sub(r'\s+', ' ', cleaned).strip()
return cleaned
def extract_names_from_pdf(pdf_path):
reader = None
try:
reader = PdfReader(pdf_path)
# All PDFs are flattened, so only try text extraction from first page
if len(reader.pages) > 0:
first_page_text = reader.pages[0].extract_text()
extracted_data = extract_student_info_from_text(first_page_text)
if extracted_data and all(extracted_data.values()):
school_val = extracted_data.get('school', '').strip()
if school_val.isdigit() or school_val.lower().startswith('docusign envelope id'):
extracted_data['school'] = ''
return {
'filename': f"{extracted_data['last_name']}_{extracted_data['first_name']}_{extracted_data['grade']}.pdf",
'last_name': extracted_data['last_name'],
'first_name': extracted_data['first_name'],
'grade': extracted_data['grade'],
'school': extracted_data['school'],
'gender': extracted_data['gender']
}
# If extraction failed, include raw text for logging
return {
'error': 'Could not extract student information from PDF. Text extraction failed.',
'raw_text': first_page_text or ''
}
# If we get here, we couldn't extract the data or text
return {'error': 'Could not extract student information from PDF. No text found.'}
except Exception as e:
return {'error': f'PDF read error: {str(e)}'}
finally:
# Properly close PDF to prevent resource leaks
if reader is not None:
try:
reader.stream.close()
except:
pass
def extract_student_info_from_text(text):
import re
extracted = {
'first_name': '',
'last_name': '',
'grade': '',
'school': '',
'gender': ''
}
required_fields = ['first_name', 'last_name', 'grade', 'school', 'gender']
lines = [l.strip() for l in text.split('\n')]
name_re = r"[A-Z][a-zA-Z]+(?:[-'][A-Za-zA-Z]+)*"
def norm_name(value):
return value.strip().replace('"', '').title()
school_suffix_words = ['High', 'School', 'Academy', 'Middle', 'Elementary', 'Christian', 'Catholic', 'Public', 'Private']
school_suffix_re = r'(?:' + '|'.join(school_suffix_words) + r')'
skip_headers = [
'student first name:', 'student last name:', 'student grade:',
'student school:', 'details', 'gender:', 'docusign envelope id:',
'docusign envelope id', 'episode registration', 'form', 'page', 'date',
'signature', 'parent', 'guardian'
]
def is_school_only(line):
if not line:
return False
if line.strip().lower() == 'other (not listed)':
return True
words = re.sub(r'[^A-Za-z ]', '', line).split()
return len(words) >= 2 and words[-1] in school_suffix_words
def split_school_first(line):
m = re.match(rf'^(.*\b{school_suffix_re})([A-Z][a-zA-Z]+)$', line)
if m:
return m.group(1).strip(), m.group(2)
return None
# Pre-clean lines: remove headers, normalize lowercase names, split gender/school concatenations
preprocessed_lines = []
for line in lines:
orig_line = line.strip()
if not orig_line:
continue
lower_line = orig_line.lower()
if any(h in lower_line for h in skip_headers):
continue
if orig_line.islower() and orig_line.isalpha():
orig_line = orig_line.title()
m_gender = re.match(r'^(Female|Male)(.+)', orig_line)
if m_gender:
rest = m_gender.group(2).strip()
rest_is_title_words = re.match(r'^[A-Z][a-zA-Z]+(?:\s+[A-Z][a-zA-Z]+)+$', rest)
rest_is_other = rest.lower().startswith('other (not listed)')
# Keep combined gender+school/grade lines for existing patterns
if re.search(rf'\b{school_suffix_re}\b', rest) or re.search(r'\d', rest) or rest_is_title_words or rest_is_other:
orig_line = m_gender.group(1) + rest
else:
preprocessed_lines.append(m_gender.group(1))
orig_line = rest
split_school = split_school_first(orig_line)
if split_school:
preprocessed_lines.append(split_school[0])
preprocessed_lines.append(split_school[1])
continue
preprocessed_lines.append(orig_line)
lines = preprocessed_lines
# --- Custom patterns for failed extractions ---
# Pattern: Uppercase LASTNAME, School, Uppercase FIRSTNAME, GenderGrade (after preprocessing)
for i in range(len(lines) - 3):
m1 = re.match(r'^([A-Z][A-Z]+)$', lines[i])
m2 = re.match(rf'^(.*\b{school_suffix_re})$', lines[i+1])
m3 = re.match(r'^([A-Z][A-Z]+)$', lines[i+2])
m4 = re.match(r'^(Female|Male)(\d{1,2}|K)$', lines[i+3])
if m1 and m2 and m3 and m4:
extracted['last_name'] = norm_name(m1.group(1))
extracted['school'] = m2.group(1).strip()
extracted['first_name'] = norm_name(m3.group(1))
extracted['gender'] = m4.group(1)
extracted['grade'] = m4.group(2)
return extracted
# Pattern: School, Last, GenderGradeFirst (after preprocessing splits SchoolLast)
for i in range(len(lines) - 2):
m1 = re.match(rf'^(.*\b{school_suffix_re})$', lines[i])
m2 = re.match(r'^([A-Z][a-zA-Z]+)$', lines[i+1])
m3 = re.match(r'^(Female|Male)(\d{1,2}|K)([A-Z][a-zA-Z]+)$', lines[i+2])
if m1 and m2 and m3 and not is_school_only(lines[i+1]):
extracted['school'] = m1.group(1).strip()
extracted['last_name'] = norm_name(m2.group(1))
extracted['gender'] = m3.group(1)
extracted['grade'] = m3.group(2)
extracted['first_name'] = m3.group(3)
return extracted
# Pattern: School, First, GradeLast, Gender (after preprocessing splits SchoolFirst)
for i in range(len(lines) - 3):
m1 = re.match(rf'^(.*\b{school_suffix_re})$', lines[i])
m2 = re.match(r'^([A-Z][a-zA-Z]+)$', lines[i+1])
m3 = re.match(r'^(\d{1,2}|K)([A-Z][a-zA-Z]+)$', lines[i+2])
m4 = re.match(r'^(Female|Male)$', lines[i+3])
if m1 and m2 and m3 and m4 and not is_school_only(lines[i+1]):
extracted['school'] = m1.group(1).strip()
extracted['first_name'] = norm_name(m2.group(1))
extracted['grade'] = m3.group(1)
extracted['last_name'] = m3.group(2)
extracted['gender'] = m4.group(1)
return extracted
# Pattern: SchoolLast, GenderGradeFirst (e.g., Home SchoolGillum, Female11Karis)
for i in range(len(lines) - 1):
m1 = re.match(rf'^(.*\b{school_suffix_re})([A-Z][a-zA-Z]+)$', lines[i])
m2 = re.match(r'^(Female|Male)(\d{1,2}|K)([A-Z][a-zA-Z]+)$', lines[i+1])
if m1 and m2:
extracted['school'] = m1.group(1).strip()
extracted['last_name'] = norm_name(m1.group(2))
extracted['gender'] = m2.group(1)
extracted['grade'] = m2.group(2)
extracted['first_name'] = m2.group(3)
return extracted
# Pattern: SchoolFirst, GradeLast, Gender (e.g., Heritage HighKailee, 12Lawhorne, Female)
for i in range(len(lines) - 2):
m1 = re.match(rf'^(.*\b{school_suffix_re})([A-Z][a-zA-Z]+)$', lines[i])
m2 = re.match(r'^(\d{1,2}|K)([A-Z][a-zA-Z]+)$', lines[i+1])
m3 = re.match(r'^(Female|Male)$', lines[i+2])
if m1 and m2 and m3:
extracted['school'] = m1.group(1).strip()
extracted['first_name'] = norm_name(m1.group(2))
extracted['grade'] = m2.group(1)
extracted['last_name'] = m2.group(2)
extracted['gender'] = m3.group(1)
return extracted
# Pattern: Uppercase LASTNAME, SchoolFirstName, GenderGrade (e.g., NIKITINA, Linkhorne MiddleLILLIAN, Female6)
for i in range(len(lines) - 2):
m1 = re.match(r'^([A-Z][A-Z]+)$', lines[i]) # All uppercase last name
m2 = re.match(rf'^(.*\b{school_suffix_re})([A-Z][a-zA-Z]+)$', lines[i+1])
m3 = re.match(r'^(Female|Male)(\d{1,2}|K)$', lines[i+2])
if m1 and m2 and m3:
extracted['last_name'] = norm_name(m1.group(1))
extracted['school'] = m2.group(1).strip()
extracted['first_name'] = norm_name(m2.group(2))
extracted['gender'] = m3.group(1)
extracted['grade'] = m3.group(2)
return extracted
# Pattern: FirstName, GenderGradeLast, School (e.g., Noah, Male11Smith, Liberty Christian Academy)
for i in range(len(lines) - 2):
m1 = re.match(r'^([A-Z][a-zA-Z]+)$', lines[i])
m2 = re.match(r'^(Female|Male)(\d{1,2}|K)([A-Z][a-zA-Z]+)$', lines[i+1])
m3 = re.match(r'^(.+)$', lines[i+2])
if m1 and m2 and m3 and not is_school_only(lines[i]):
extracted['first_name'] = m1.group(1)
extracted['gender'] = m2.group(1)
extracted['grade'] = m2.group(2)
extracted['last_name'] = m2.group(3)
extracted['school'] = m3.group(1).strip()
return extracted
# Pattern: GenderGradeLastFirst, School (e.g., Female11SpearAva, Home School)
for i in range(len(lines) - 1):
m1 = re.match(r'^(Female|Male)(\d{1,2}|K)([A-Z][a-zA-Z]+)([A-Z][a-zA-Z]+)$', lines[i])
m2 = re.match(r'^(.+)$', lines[i+1])
if m1 and m2:
extracted['gender'] = m1.group(1)
extracted['grade'] = m1.group(2)
extracted['last_name'] = m1.group(3)
extracted['first_name'] = m1.group(4)
extracted['school'] = m2.group(1).strip()
return extracted
# Pattern: SchoolFirstName, GenderGrade (e.g., Linkhorne MiddleLILLIAN, Female6)
for i in range(len(lines) - 1):
m1 = re.match(rf'^(.*\b{school_suffix_re})([A-Z][a-zA-Z]+)$', lines[i])
m2 = re.match(r'^(Female|Male)(\d{1,2}|K)$', lines[i+1])
if m1 and m2:
extracted['school'] = m1.group(1).strip()
extracted['first_name'] = norm_name(m1.group(2))
extracted['gender'] = m2.group(1)
extracted['grade'] = m2.group(2)
# Look for last name on next line
if i + 2 < len(lines):
m3 = re.match(r'^([A-Z][a-zA-Z]+)$', lines[i+2])
if m3:
extracted['last_name'] = m3.group(1)
return extracted
# Pattern: GenderGradeFirstName, SchoolLastName (e.g., Male11Dwight, Heritage HighWilliams IV)
for i in range(len(lines) - 1):
m1 = re.match(r'^(Female|Male)(\d{1,2}|K)(' + name_re + r')$', lines[i])
m2 = re.match(rf'^(.*\b{school_suffix_re})([A-Z][a-zA-Z]+)(?:\s+(I|II|III|IV|V|VI|Jr|Sr))?$', lines[i+1])
if m1 and m2:
extracted['gender'] = m1.group(1)
extracted['grade'] = m1.group(2)
extracted['first_name'] = m1.group(3)
suffix = f" {m2.group(3)}" if m2.group(3) else ''
extracted['last_name'] = f"{m2.group(2)}{suffix}".strip()
extracted['school'] = m2.group(1).strip()
return extracted
# Pattern: GenderSchoolLastName, GradeFirstName (e.g., FemaleBrookville HighMouse, 11Mickey)
for i in range(len(lines) - 1):
m1 = re.match(r'^(Female|Male)(.+?)([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^(\d{1,2}|K)([A-Z][a-z]+)$', lines[i+1])
if m1 and m2:
extracted['gender'] = m1.group(1)
extracted['school'] = m1.group(2).strip()
extracted['last_name'] = m1.group(3)
extracted['grade'] = m2.group(1)
extracted['first_name'] = m2.group(2)
break
# Pattern: ConcatenatedNames, Grade, School, Gender (e.g., MaynardJenny, 11, Liberty Christian Academy, Female)
for i in range(len(lines) - 3):
m1 = re.match(r'^([A-Z][a-z]+)([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^(\d{1,2}|K)$', lines[i+1])
m3 = lines[i+2].strip()
m4 = re.match(r'^(Female|Male)$', lines[i+3])
if m1 and m2 and m3 and m4:
extracted['last_name'] = m1.group(1)
extracted['first_name'] = m1.group(2)
extracted['grade'] = m2.group(1)
extracted['school'] = m3
extracted['gender'] = m4.group(1)
break
# Pattern: School, GenderGradeFirstName, LastName (e.g., Liberty Christian Academy, Female11Ava, Lawrenson)
for i in range(len(lines) - 2):
if not is_school_only(lines[i]):
continue
m1 = re.match(r'^(.+)$', lines[i])
m2 = re.match(r'^(Female|Male)(\d{1,2}|K)(' + name_re + r')$', lines[i+1])
m3 = re.match(r'^(' + name_re + r')$', lines[i+2])
if m1 and m2 and m3:
extracted['school'] = m1.group(1).strip()
extracted['gender'] = m2.group(1)
extracted['grade'] = m2.group(2)
extracted['first_name'] = m2.group(3)
extracted['last_name'] = m3.group(1)
return extracted
# Pattern: SchoolFirstName, LastName, GenderGrade (e.g., Liberty Christian AcademySally, Sue, Female9)
for i in range(len(lines) - 2):
split = split_school_first(lines[i])
m1 = re.match(r'^(.+?)([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^([A-Z][a-z]+)$', lines[i+1])
m3 = re.match(r'^(Female|Male)(\d{1,2}|K)$', lines[i+2])
if m2 and m3:
if split:
school_val, first_val = split
elif m1 and not is_school_only(lines[i]) and ' ' in lines[i]:
school_val, first_val = m1.group(1).strip(), m1.group(2)
else:
continue
extracted['school'] = school_val
extracted['first_name'] = first_val
extracted['last_name'] = m2.group(1)
extracted['gender'] = m3.group(1)
extracted['grade'] = m3.group(2)
break
# Pattern: GenderGradeFirstName, SchoolLastName (e.g., Male11Dwight, Heritage HighWilliams IV)
for i in range(len(lines) - 1):
m1 = re.match(r'^(Female|Male)(\d{1,2}|K)(' + name_re + r')$', lines[i])
m2 = re.match(r'^(.+)$', lines[i+1])
if m1 and m2:
m_school = re.match(rf'^(.*\b{school_suffix_re})([A-Z][a-zA-Z]+)(?:\s+(I|II|III|IV|V|VI|Jr|Sr))?$', m2.group(1).strip())
if m_school:
extracted['gender'] = m1.group(1)
extracted['grade'] = m1.group(2)
extracted['first_name'] = m1.group(3)
suffix = f" {m_school.group(3)}" if m_school.group(3) else ''
extracted['last_name'] = f"{m_school.group(2)}{suffix}".strip()
extracted['school'] = m_school.group(1).strip()
break
# Pattern: SchoolFirstName, GenderGradeLastName (e.g., Forest MiddleCheyanne, Female8Henderson)
for i in range(len(lines) - 1):
split = split_school_first(lines[i])
m1 = re.match(r'^(.+?)([A-Z][a-zA-Z]+)$', lines[i])
m2 = re.match(r'^(Female|Male)(\d{1,2}|K)(' + name_re + r')$', lines[i+1])
if m2:
if split:
school_val, first_val = split
elif m1 and not is_school_only(lines[i]) and ' ' in lines[i]:
school_val, first_val = m1.group(1).strip(), m1.group(2)
else:
continue
extracted['school'] = school_val
extracted['first_name'] = first_val
extracted['gender'] = m2.group(1)
extracted['grade'] = m2.group(2)
extracted['last_name'] = m2.group(3)
break
# Pattern: FirstName, GenderGradeLastName, School (e.g., Myla, Female8Littlejohn, Home School)
for i in range(len(lines) - 2):
m1 = re.match(r'^(' + name_re + r')$', lines[i])
m2 = re.match(r'^(Female|Male)(\d{1,2}|K)(' + name_re + r')$', lines[i+1])
m3 = re.match(r'^(.+)$', lines[i+2])
if m1 and m2 and m3:
extracted['first_name'] = m1.group(1)
extracted['gender'] = m2.group(1)
extracted['grade'] = m2.group(2)
extracted['last_name'] = m2.group(3)
extracted['school'] = m3.group(1).strip()
break
# Pattern: LastName, SchoolFirstName, GenderGrade (e.g., NIKITINA, Linkhorne MiddleLILLIAN, Female6)
for i in range(len(lines) - 2):
m1 = re.match(r'^([A-Z]{2,})$', lines[i])
split = split_school_first(lines[i+1])
m2 = re.match(r'^(.+?)([A-Z][a-zA-Z]+)$', lines[i+1])
m3 = re.match(r'^(Female|Male)(\d{1,2}|K)$', lines[i+2])
if m1 and m3:
if split:
school_val, first_val = split
elif m2:
school_val, first_val = m2.group(1).strip(), m2.group(2)
else:
continue
extracted['last_name'] = norm_name(m1.group(1))
extracted['school'] = school_val
extracted['first_name'] = norm_name(first_val)
extracted['gender'] = m3.group(1)
extracted['grade'] = m3.group(2)
break
# Pattern: FirstName, SchoolGradeLastName, Gender (e.g., Michael, Home School7Shuck, Male)
for i in range(len(lines) - 2):
m1 = re.match(r'^([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^(.+?)(\d{1,2}|K)([A-Z][a-z]+)$', lines[i+1])
m3 = re.match(r'^(Female|Male)$', lines[i+2])
if m1 and m2 and m3:
extracted['first_name'] = m1.group(1)
extracted['school'] = m2.group(1).strip()
extracted['grade'] = m2.group(2)
extracted['last_name'] = m2.group(3)
extracted['gender'] = m3.group(1)
break
# Pattern: GradeFirstName, SchoolLastName, Gender (e.g., 9Joshua, Liberty Christian AcademyMcCain, Male)
for i in range(len(lines) - 2):
m1 = re.match(r'^(\d{1,2}|K)([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^(.+?)([A-Z][a-z]+)$', lines[i+1])
m3 = re.match(r'^(Female|Male)$', lines[i+2])
if m1 and m2 and m3:
extracted['grade'] = m1.group(1)
extracted['first_name'] = m1.group(2)
extracted['school'] = m2.group(1).strip()
extracted['last_name'] = m2.group(2)
extracted['gender'] = m3.group(1)
break
# Pattern: School, GenderFirstName, GradeLastName (e.g., Other (Not Listed), FemaleSophia, 11Porter)
for i in range(len(lines) - 2):
m1 = re.match(r'^(.+)$', lines[i])
m2 = re.match(r'^(Female|Male)([A-Z][a-z]+)$', lines[i+1])
m3 = re.match(r'^(\d{1,2}|K)([A-Z][a-z]+)$', lines[i+2])
if m1 and m2 and m3:
extracted['school'] = m1.group(1).strip()
extracted['gender'] = m2.group(1)
extracted['first_name'] = m2.group(2)
extracted['grade'] = m3.group(1)
extracted['last_name'] = m3.group(2)
return extracted
# Pattern: GenderGradeLastNameFirstName, School (e.g., Female11SpearAva, Home School)
for i in range(len(lines) - 1):
m1 = re.match(r'^(Female|Male)(\d{1,2}|K)([A-Z][a-z]+)([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^(.+)$', lines[i+1])
if m1 and m2:
extracted['gender'] = m1.group(1)
extracted['grade'] = m1.group(2)
extracted['last_name'] = m1.group(3)
extracted['first_name'] = m1.group(4)
extracted['school'] = m2.group(1).strip()
break
# Pattern: GenderGradeLastName, SchoolFirstName (e.g., Male11Seckman, New CovenantMicharl)
for i in range(len(lines) - 1):
m1 = re.match(r'^(Female|Male)(\d{1,2}|K)([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^(.+?)([A-Z][a-z]+)$', lines[i+1])
if m1 and m2:
split = split_school_first(lines[i+1])
if split:
school_val, first_val = split
elif is_school_only(lines[i+1]):
continue
else:
school_val, first_val = m2.group(1).strip(), m2.group(2)
extracted['gender'] = m1.group(1)
extracted['grade'] = m1.group(2)
extracted['last_name'] = m1.group(3)
extracted['school'] = school_val
extracted['first_name'] = first_val
break
# Pattern: GenderLastName, GradeFirstName, School (e.g., MaleKirk, 10Jaihden "JJ", Home School)
for i in range(len(lines) - 2):
m1 = re.match(r'^(Female|Male)([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^(\d{1,2}|K)([A-Z][a-z]+)', lines[i+1])
m3 = re.match(r'^(.+)$', lines[i+2])
if m1 and m2 and m3:
extracted['gender'] = m1.group(1)
extracted['last_name'] = m1.group(2)
extracted['grade'] = m2.group(1)
extracted['first_name'] = m2.group(2)
extracted['school'] = m3.group(1).strip()
break
# Pattern: FirstName, Grade, SchoolLastName, Gender (e.g., Tracey, 12, Other (Not Listed)Lindsay, Female)
for i in range(len(lines) - 3):
m1 = re.match(r'^([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^(\d{1,2}|K)$', lines[i+1])
m3 = re.match(r'^(.+?)([A-Z][a-z]+)$', lines[i+2])
m4 = re.match(r'^(Female|Male)$', lines[i+3])
if m1 and m2 and m3 and m4:
extracted['first_name'] = m1.group(1)
extracted['grade'] = m2.group(1)
extracted['school'] = m3.group(1).strip()
extracted['last_name'] = m3.group(2)
extracted['gender'] = m4.group(1)
break
# Pattern: GenderGrade, SchoolLastNameFirstName (e.g., Female7, Brookville MiddleBrownMicah)
for i in range(len(lines) - 1):
m1 = re.match(r'^(Female|Male)(\d{1,2}|K)$', lines[i])
m2 = re.match(r'^(.+?)([A-Z][a-z]+)([A-Z][a-z]+)$', lines[i+1])
if m1 and m2:
extracted['gender'] = m1.group(1)
extracted['grade'] = m1.group(2)
extracted['school'] = m2.group(1).strip()
extracted['last_name'] = m2.group(2)
extracted['first_name'] = m2.group(3)
break
# Pattern: GenderSchoolGradeFirstName, LastName (e.g., FemaleRustburg High9Lexi, Wilson)
for i in range(len(lines) - 1):
m1 = re.match(r'^(Female|Male)(.+?)(\d{1,2}|K)(' + name_re + r')$', lines[i])
m2 = re.match(r'^(' + name_re + r')$', lines[i+1])
if m1 and m2:
extracted['gender'] = m1.group(1)
extracted['school'] = m1.group(2).strip()
extracted['grade'] = m1.group(3)
extracted['first_name'] = m1.group(4)
extracted['last_name'] = m2.group(1)
break
# Pattern: GenderSchoolGradeLastNameFirstName (e.g., MaleLiberty Christian Academy11SnakenbergBryson)
for i in range(len(lines) - 0):
m1 = re.match(r'^(Female|Male)(.+?)(\d{1,2}|K)([A-Z][a-z]+)([A-Z][a-z]+)$', lines[i])
if m1:
extracted['gender'] = m1.group(1)
extracted['school'] = m1.group(2).strip()
extracted['grade'] = m1.group(3)
extracted['last_name'] = m1.group(4)
extracted['first_name'] = m1.group(5)
break
# Pattern: SchoolLastNameFirstName, Grade, Gender (e.g., Monelison MiddleCarmodyLandon, 7, Male)
for i in range(len(lines) - 2):
m1 = re.match(r'^(.+?)([A-Z][a-z]+)([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^(\d{1,2}|K)$', lines[i+1])
m3 = re.match(r'^(Female|Male)$', lines[i+2])
if m1 and m2 and m3:
extracted['school'] = m1.group(1).strip()
extracted['last_name'] = m1.group(2)
extracted['first_name'] = m1.group(3)
extracted['grade'] = m2.group(1)
extracted['gender'] = m3.group(1)
break
# Pattern: FirstName, GradeLastName, School, Gender (e.g., Jesse, 6McGinniss, Timberlake Christian, Male)
for i in range(len(lines) - 3):
m1 = re.match(r'^([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^(\d{1,2}|K)(' + name_re + r')$', lines[i+1])
m3 = re.match(r'^(.+)$', lines[i+2])
m4 = re.match(r'^(Female|Male)$', lines[i+3])
if m1 and m2 and m3 and m4:
extracted['first_name'] = m1.group(1)
extracted['grade'] = m2.group(1)
extracted['last_name'] = m2.group(2)
extracted['school'] = m3.group(1).strip()
extracted['gender'] = m4.group(1)
break
# Pattern: GenderFirstName, LastName, Grade, School (e.g., MaleBenjamin, Byrne-Cox, 12, Home School)
for i in range(len(lines) - 3):
m1 = re.match(r'^(Female|Male)([A-Z][a-z]+)$', lines[i])
m2 = re.match(r'^(' + name_re + r')$', lines[i+1])
m3 = re.match(r'^(\d{1,2}|K)$', lines[i+2])
m4 = re.match(r'^(.+)$', lines[i+3])
if m1 and m2 and m3 and m4:
extracted['gender'] = m1.group(1)
extracted['first_name'] = m1.group(2)
extracted['last_name'] = m2.group(1)
extracted['grade'] = m3.group(1)
extracted['school'] = m4.group(1).strip()
break
# Pattern: FirstName, LastName, Grade, GenderSchool (e.g., Andrew, Servin-Hernandez, 8, MaleSandusky Middle)
for i in range(len(lines) - 3):
m1 = re.match(r'^(' + name_re + r')$', lines[i])
m2 = re.match(r'^(' + name_re + r')$', lines[i+1])
m3 = re.match(r'^(\d{1,2}|K)$', lines[i+2])
m4 = re.match(r'^(Female|Male)(.+)$', lines[i+3])
if m1 and m2 and m3 and m4:
extracted['first_name'] = m1.group(1)
extracted['last_name'] = m2.group(1)
extracted['grade'] = m3.group(1)
extracted['gender'] = m4.group(1)
extracted['school'] = m4.group(2).strip()
break
# Pattern: SchoolGradeFirstName, GenderLastName (e.g., Temple Christian6Morgan, MaleChristian)
for i in range(len(lines) - 1):
m1 = re.match(r'^(.+?)(\d{1,2}|K)(' + name_re + r')$', lines[i])
m2 = re.match(r'^(Female|Male)(' + name_re + r')$', lines[i+1])
if m1 and m2:
extracted['school'] = m1.group(1).strip()
extracted['grade'] = m1.group(2)
extracted['first_name'] = m1.group(3)
extracted['gender'] = m2.group(1)
extracted['last_name'] = m2.group(2)
break
# Pattern: GenderGradeLastName, SchoolFirstName (e.g., Male9Bieri, Liberty Christian AcademySJ)
for i in range(len(lines) - 1):
m1 = re.match(r'^(Female|Male)(\d{1,2}|K)(' + name_re + r')$', lines[i])
m2 = re.match(r'^(.+?)(' + name_re + r')$', lines[i+1])
if m1 and m2:
split = split_school_first(lines[i+1])
if split:
school_val, first_val = split
elif is_school_only(lines[i+1]):
continue
else:
school_val, first_val = m2.group(1).strip(), m2.group(2)
extracted['gender'] = m1.group(1)
extracted['grade'] = m1.group(2)
extracted['last_name'] = m1.group(3)
extracted['school'] = school_val
extracted['first_name'] = first_val
break
# Pattern: SchoolLastNameFirstName, GenderGrade (e.g., Home SchoolBethelAbigail, Female7)
for i in range(len(lines) - 1):
m1 = re.match(r'^(.+?)(' + name_re + r')(' + name_re + r')$', lines[i])
m2 = re.match(r'^(Female|Male)(\d{1,2}|K)$', lines[i+1])
if m1 and m2:
extracted['school'] = m1.group(1).strip()
extracted['last_name'] = m1.group(2)
extracted['first_name'] = m1.group(3)
extracted['gender'] = m2.group(1)
extracted['grade'] = m2.group(2)
break
# Pattern: SchoolLastName, GradeFirstName, Gender (e.g., Other (Not Listed)Caballero, 7Mason, Male)
for i in range(len(lines) - 2):
m1 = re.match(r'^(.+?)(' + name_re + r')$', lines[i])
m2 = re.match(r'^(\d{1,2}|K)(' + name_re + r')$', lines[i+1])
m3 = re.match(r'^(Female|Male)$', lines[i+2])
if m1 and m2 and m3:
extracted['school'] = m1.group(1).strip()
extracted['last_name'] = m1.group(2)
extracted['grade'] = m2.group(1)
extracted['first_name'] = m2.group(2)
extracted['gender'] = m3.group(1)
break
# Pattern: GradeLastName, School, GenderFirstName (e.g., 6Petty, Other (Not Listed), FemaleAnia)
for i in range(len(lines) - 2):
m1 = re.match(r'^(\d{1,2}|K)(' + name_re + r')$', lines[i])
m2 = re.match(r'^(.+)$', lines[i+1])
m3 = re.match(r'^(Female|Male)(' + name_re + r')$', lines[i+2])
if m1 and m2 and m3:
extracted['grade'] = m1.group(1)
extracted['last_name'] = m1.group(2)
extracted['school'] = m2.group(1).strip()
extracted['gender'] = m3.group(1)
extracted['first_name'] = m3.group(2)
break
# Pattern: Grade, SchoolLastNameFirstName, Gender (e.g., 9, Home SchoolSpearCharlotte, Female)
for i in range(len(lines) - 2):
m1 = re.match(r'^(\d{1,2}|K)$', lines[i])
m2 = re.match(r'^(.+?)(' + name_re + r')(' + name_re + r')$', lines[i+1])
m3 = re.match(r'^(Female|Male)$', lines[i+2])
if m1 and m2 and m3:
extracted['grade'] = m1.group(1)
extracted['school'] = m2.group(1).strip()
extracted['last_name'] = m2.group(2)
extracted['first_name'] = m2.group(3)
extracted['gender'] = m3.group(1)
break
# Pattern: Grade, GenderSchoolLastNameFirstName (e.g., 9, FemaleHome SchoolHeagyPaige)
for i in range(len(lines) - 1):
m1 = re.match(r'^(\d{1,2}|K)$', lines[i])
m2 = re.match(r'^(Female|Male)(.+?)(' + name_re + r')(' + name_re + r')$', lines[i+1])
if m1 and m2:
extracted['grade'] = m1.group(1)
extracted['gender'] = m2.group(1)
extracted['school'] = m2.group(2).strip()
extracted['last_name'] = m2.group(3)
extracted['first_name'] = m2.group(4)
break
# Pattern: GenderGradeLastName FirstName, School (e.g., Male7Trochesset Oliver, Liberty Christian Academy)
for i in range(len(lines) - 1):
m1 = re.match(r'^(Female|Male)(\d{1,2}|K)(' + name_re + r')\s+(' + name_re + r')$', lines[i])
m2 = re.match(r'^(.+)$', lines[i+1])
if m1 and m2:
extracted['gender'] = m1.group(1)
extracted['grade'] = m1.group(2)
extracted['last_name'] = m1.group(3)
extracted['first_name'] = m1.group(4)
extracted['school'] = m2.group(1).strip()
break
# Pattern: FirstName, SchoolLastName, Grade, Gender (e.g., Neale, Other (Not Listed)Hans, 9, Male)
for i in range(len(lines) - 3):
m1 = re.match(r'^(' + name_re + r')$', lines[i])
m2 = re.match(r'^(.+?)(' + name_re + r')$', lines[i+1])
m3 = re.match(r'^(\d{1,2}|K)$', lines[i+2])
m4 = re.match(r'^(Female|Male)$', lines[i+3])
if m1 and m2 and m3 and m4:
extracted['first_name'] = m1.group(1)
extracted['school'] = m2.group(1).strip()
extracted['last_name'] = m2.group(2)
extracted['grade'] = m3.group(1)
extracted['gender'] = m4.group(1)
break
# Pattern: GradeLastNameFirstName, GenderSchool (e.g., 11DorsettJaxon, MaleLiberty Christian Academy)
for i in range(len(lines) - 1):
m1 = re.match(r'^(\d{1,2}|K)(' + name_re + r')(' + name_re + r')$', lines[i])
m2 = re.match(r'^(Female|Male)(.+)$', lines[i+1])
if m1 and m2:
extracted['grade'] = m1.group(1)
extracted['last_name'] = m1.group(2)
extracted['first_name'] = m1.group(3)
extracted['gender'] = m2.group(1)
extracted['school'] = m2.group(2).strip()
break
# Pattern: FirstName, Grade, GenderSchoolLastName (e.g., Neale, 6, MaleOther (Not Listed)Sebastian)
for i in range(len(lines) - 2):
m1 = re.match(r'^(' + name_re + r')$', lines[i])
m2 = re.match(r'^(\d{1,2}|K)$', lines[i+1])
m3 = re.match(r'^(Female|Male)(.+?)(' + name_re + r')$', lines[i+2])
if m1 and m2 and m3:
extracted['first_name'] = m1.group(1)
extracted['grade'] = m2.group(1)
extracted['gender'] = m3.group(1)
extracted['school'] = m3.group(2).strip()
extracted['last_name'] = m3.group(3)
break
# Pattern: Name, Grade, GenderSchool (missing first or last name)
for i in range(len(lines) - 2):
m1 = re.match(r'^([A-Za-z]+)$', lines[i])
m2 = re.match(r'^(\d{1,2}|K)$', lines[i+1])
m3 = re.match(r'^(Female|Male)(.+)$', lines[i+2])
if m1 and m2 and m3:
extracted['last_name'] = norm_name(m1.group(1))
extracted['first_name'] = 'Unknown'
extracted['grade'] = m2.group(1)
extracted['gender'] = m3.group(1)
extracted['school'] = m3.group(2).strip()
return extracted
# Pattern: GradeLastNameFirstName, School, Gender (e.g., 12ClarkAva, Jefferson Forest High, Female)
for i in range(len(lines) - 2):
m1 = re.match(r'^(\d{1,2}|K)(' + name_re + r')(' + name_re + r')$', lines[i])
m2 = re.match(r'^(.+)$', lines[i+1])
m3 = re.match(r'^(Female|Male)$', lines[i+2])
if m1 and m2 and m3:
extracted['grade'] = m1.group(1)
extracted['last_name'] = m1.group(2)
extracted['first_name'] = m1.group(3)
extracted['school'] = m2.group(1).strip()
extracted['gender'] = m3.group(1)
break
# Pattern: LastName, Grade, GenderFirstName, School (e.g., Johnke, 6, FemaleKyla, Other (Not Listed))
for i in range(len(lines) - 3):
m1 = re.match(r'^(' + name_re + r')$', lines[i])
m2 = re.match(r'^(\d{1,2}|K)$', lines[i+1])
m3 = re.match(r'^(Female|Male)(' + name_re + r')$', lines[i+2])
m4 = re.match(r'^(.+)$', lines[i+3])
if m1 and m2 and m3 and m4:
extracted['last_name'] = m1.group(1)
extracted['grade'] = m2.group(1)
extracted['gender'] = m3.group(1)
extracted['first_name'] = m3.group(2)
extracted['school'] = m4.group(1).strip()
break
# Pattern: SchoolFirstName (case-insensitive), GenderGradeLastName (case-insensitive)
for i in range(len(lines) - 1):
if is_school_only(lines[i]) or (' ' not in lines[i] and not split_school_first(lines[i])):
continue
m1 = re.match(r'^(.+?)([A-Za-z]+)$', lines[i], re.IGNORECASE)
m2 = re.match(r'^(Female|Male)(\d{1,2}|K)([A-Za-z]+)$', lines[i+1], re.IGNORECASE)
if m1 and m2:
extracted['school'] = m1.group(1).strip()
extracted['first_name'] = norm_name(m1.group(2))
extracted['gender'] = m2.group(1).capitalize()
extracted['grade'] = m2.group(2)
extracted['last_name'] = norm_name(m2.group(3))
break
# Pattern: LastName, GenderSchoolGradeFirstName (e.g., Porter, MaleLiberty Christian Academy8Samuel)
for i in range(len(lines) - 1):
m1 = re.match(r'^(' + name_re + r')$', lines[i])
m2 = re.match(r'^(Female|Male)(.+?)(\d{1,2}|K)(' + name_re + r')$', lines[i+1])
if m1 and m2:
extracted['last_name'] = m1.group(1)
extracted['gender'] = m2.group(1)
extracted['school'] = m2.group(2).strip()
extracted['grade'] = m2.group(3)
extracted['first_name'] = m2.group(4)
break
# Pattern: LastName, GenderFirstName, Grade, School (e.g., Brainard, FemaleEmily, 10, Other (Not Listed))
for i in range(len(lines) - 3):
m1 = re.match(r'^(' + name_re + r')$', lines[i])
m2 = re.match(r'^(Female|Male)(' + name_re + r')$', lines[i+1])
m3 = re.match(r'^(\d{1,2}|K)$', lines[i+2])
m4 = re.match(r'^(.+)$', lines[i+3])
if m1 and m2 and m3 and m4:
extracted['last_name'] = m1.group(1)
extracted['gender'] = m2.group(1)
extracted['first_name'] = m2.group(2)
extracted['grade'] = m3.group(1)
extracted['school'] = m4.group(1).strip()
break
# Pattern: LastName, GenderSchoolGradeFirstName (e.g., Mays, FemaleAmherst High9Kara)
for i in range(len(lines) - 1):
m1 = re.match(r'^(' + name_re + r')$', lines[i])
m2 = re.match(r'^(Female|Male)(.+?)(\d{1,2}|K)(' + name_re + r')$', lines[i+1])
if m1 and m2:
extracted['last_name'] = m1.group(1)
extracted['gender'] = m2.group(1)
extracted['school'] = m2.group(2).strip()
extracted['grade'] = m2.group(3)
extracted['first_name'] = m2.group(4)
break
# Pattern: GradeLastName, GenderSchoolFirstName (e.g., 10Davis, FemaleE.C. Glass HighTa'Mya)
for i in range(len(lines) - 1):
m1 = re.match(r'^(\d{1,2}|K)(' + name_re + r')$', lines[i])
m2 = re.match(r'^(Female|Male)(.+?)(' + name_re + r')$', lines[i+1])
if m1 and m2:
extracted['grade'] = m1.group(1)
extracted['last_name'] = m1.group(2)
extracted['gender'] = m2.group(1)
extracted['school'] = m2.group(2).strip()
extracted['first_name'] = m2.group(3)
break
# Pattern: School, GenderLastName, GradeFirstName (e.g., Liberty Christian Academy, MaleHagner, 9Jarad Jr.)
for i in range(len(lines) - 2):
m1 = re.match(r'^(.+)$', lines[i])
m2 = re.match(r'^(Female|Male)(' + name_re + r')$', lines[i+1])
m3 = re.match(r'^(\d{1,2}|K)(' + name_re + r')', lines[i+2])
if m1 and m2 and m3:
extracted['school'] = m1.group(1).strip()
extracted['gender'] = m2.group(1)
extracted['last_name'] = m2.group(2)
extracted['grade'] = m3.group(1)
extracted['first_name'] = m3.group(2)
break
# Pattern: GenderLastName, SchoolGradeFirstName (e.g., MaleMartin, Monelison Middle7Levi)
for i in range(len(lines) - 1):
m1 = re.match(r'^(Female|Male)(' + name_re + r')$', lines[i])
m2 = re.match(r'^(.+?)(\d{1,2}|K)(' + name_re + r')$', lines[i+1])
if m1 and m2:
extracted['gender'] = m1.group(1)
extracted['last_name'] = m1.group(2)
extracted['school'] = m2.group(1).strip()
extracted['grade'] = m2.group(2)
extracted['first_name'] = m2.group(3)
break
# Pattern: FirstName, School, GenderGradeLastName (e.g., Lillian, Other (Not Listed), Female6Buchanan)
for i in range(len(lines) - 2):
m1 = re.match(r'^(' + name_re + r')$', lines[i])
m2 = re.match(r'^(.+)$', lines[i+1])
m3 = re.match(r'^(Female|Male)(\d{1,2}|K)(' + name_re + r')$', lines[i+2])
if m1 and m2 and m3:
extracted['first_name'] = m1.group(1)
extracted['school'] = m2.group(1).strip()
extracted['gender'] = m3.group(1)
extracted['grade'] = m3.group(2)
extracted['last_name'] = m3.group(3)
break
# Pattern: FirstName, School, GenderLastName, Grade (e.g., Luke, Other (Not Listed), MaleHottle, 11)
for i in range(len(lines) - 3):
m1 = re.match(r'^(' + name_re + r')$', lines[i])
m2 = re.match(r'^(.+)$', lines[i+1])
m3 = re.match(r'^(Female|Male)(' + name_re + r')$', lines[i+2])
m4 = re.match(r'^(\d{1,2}|K)$', lines[i+3])
if m1 and m2 and m3 and m4:
extracted['first_name'] = m1.group(1)
extracted['school'] = m2.group(1).strip()
extracted['gender'] = m3.group(1)
extracted['last_name'] = m3.group(2)
extracted['grade'] = m4.group(1)
break
# Pattern: SchoolGradeFirstName, LastName, Gender (e.g., Monelison Middle8Laila, Mays, Female)
for i in range(len(lines) - 2):
m1 = re.match(r'^(.+?)(\d{1,2}|K)(' + name_re + r')$', lines[i])
m2 = re.match(r'^(' + name_re + r')$', lines[i+1])
m3 = re.match(r'^(Female|Male)$', lines[i+2])
if m1 and m2 and m3:
extracted['school'] = m1.group(1).strip()
extracted['grade'] = m1.group(2)
extracted['first_name'] = m1.group(3)
extracted['last_name'] = m2.group(1)
extracted['gender'] = m3.group(1)
break
# Pattern: GradeLastNameFirstName (multi-word first), GenderSchool (e.g., 6HoskinsMary Emma, FemaleNew Covenant)
for i in range(len(lines) - 1):
m1 = re.match(r'^(\d{1,2}|K)(' + name_re + r')(.+)$', lines[i])
m2 = re.match(r'^(Female|Male)(.+)$', lines[i+1])
if m1 and m2:
extracted['grade'] = m1.group(1)
extracted['last_name'] = m1.group(2)
extracted['first_name'] = m1.group(3).strip()
extracted['gender'] = m2.group(1)
extracted['school'] = m2.group(2).strip()
break
# Pattern: SchoolGradeLastNameFirstName, Gender (e.g., Brookville Middle6DraganEmily, Female)
for i in range(len(lines) - 1):
m1 = re.match(r'^(.+?)(\d{1,2}|K)(' + name_re + r')(' + name_re + r')$', lines[i])
m2 = re.match(r'^(Female|Male)$', lines[i+1])
if m1 and m2:
extracted['school'] = m1.group(1).strip()
extracted['grade'] = m1.group(2)
extracted['last_name'] = m1.group(3)
extracted['first_name'] = m1.group(4)
extracted['gender'] = m2.group(1)
break
if all(extracted.get(field) for field in required_fields):
return extracted
# Enhanced preprocessing: aggressively split lines with multiple fields stuck together
processed_lines = []
valid_schools = [
'Amherst', 'Appomattox', 'Brookville', 'Dunbar', 'E.C. Glass', 'Forest', 'Heritage', 'Home School',
'Jefferson Forest', 'Liberty Christian Academy', 'Linkhorne', 'Monelison', 'Rustburg', 'Sandusky',
'Temple Christian', 'Timberlake Christian'
]
school_suffixes = [' High', ' Middle', ' Academy', ' Elementary', ' School', ' Christian']
all_school_names = sorted([base + suffix for base in valid_schools for suffix in [''] + school_suffixes], key=len, reverse=True)
for line in lines:
orig_line = line.strip()
# Ignore header/title/label lines
if not orig_line or any(h in orig_line.lower() for h in skip_headers):
continue
# Normalize single-word lowercase names
if orig_line.islower() and orig_line.isalpha():
orig_line = orig_line.title()
# Split school+name concatenations (e.g., "Liberty Christian AcademyWhorley")
split_school = split_school_first(orig_line)
if split_school:
processed_lines.append(split_school[0])
processed_lines.append(split_school[1])
continue
# Aggressive split: if line starts with a valid school name (with suffix) and is immediately followed by a capitalized name or digit, split
split_done = False
for school_name in all_school_names:
if orig_line.startswith(school_name):
rest = orig_line[len(school_name):]
if rest and (re.match(r'^[A-Z]', rest) or re.match(r'^\d', rest)):
processed_lines.append(school_name)
processed_lines.append(rest)
split_done = True
break
if split_done:
continue
# --- Always split off leading gender ---
m_gender = re.match(r'^(Female|Male)(.+)', orig_line)
if m_gender:
processed_lines.append(m_gender.group(1))
orig_line = m_gender.group(2).strip()
# --- Split at last school suffix if followed by capitalized name or number ---
last_pos = -1
last_suffix = ''
for suffix in school_suffixes:
idx = orig_line.rfind(suffix)
if idx != -1 and idx + len(suffix) > last_pos:
last_pos = idx + len(suffix)
last_suffix = suffix
if last_pos != -1 and last_pos < len(orig_line):
# Always split at the last suffix: everything after is not part of the school name
processed_lines.append(orig_line[:last_pos].strip())
trailing = orig_line[last_pos:].strip()
if trailing:
# Split all words (including lowercase, apostrophes, spaces, etc.) as separate lines
for part in re.findall(r"[\w'\-]+", trailing):
processed_lines.append(part)
continue
# Pattern: Gender + School + LastName (e.g., 'FemaleBrookville HighMouse')
m = re.match(r'^(Female|Male)([A-Z][a-z]+(?: [A-Z][a-z]+)*)([A-Z][a-z]+)$', orig_line)
if m:
processed_lines.append(m.group(1))
processed_lines.append(m.group(2).strip())
processed_lines.append(m.group(3))
continue
# Pattern: Grade + FirstName (e.g., '11Mickey')
m2 = re.match(r'^(\d{1,2}|K)([A-Z][a-z]+)$', orig_line)
if m2:
processed_lines.append(m2.group(1))
processed_lines.append(m2.group(2))
continue
# Pattern: Two concatenated names (e.g., 'MaynardJenny')
m3 = re.match(r'^([A-Z][a-z]+)([A-Z][a-z]+)$', orig_line)
if m3 and orig_line not in processed_lines:
processed_lines.append(m3.group(1))
processed_lines.append(m3.group(2))
continue
# Pattern: Gender + FirstName (e.g., 'MaleJoshua')
m7 = re.match(r'^(Female|Male)([A-Z][a-z]+)$', orig_line)
if m7:
processed_lines.append(m7.group(1))
processed_lines.append(m7.group(2))
continue
# Pattern: Gender + School + FirstName + LastName + Grade (all concatenated)
m4 = re.match(r'^(Female|Male)([A-Z][a-z]+(?: [A-Z][a-z]+)*)([A-Z][a-z]+)([A-Z][a-z]+)(\d{1,2}|K)$', orig_line)
if m4:
processed_lines.append(m4.group(1))
processed_lines.append(m4.group(2).strip())
processed_lines.append(m4.group(3))
processed_lines.append(m4.group(4))
processed_lines.append(m4.group(5))
continue
# Pattern: Gender + School + FirstName + LastName (no grade)
m5 = re.match(r'^(Female|Male)([A-Z][a-z]+(?: [A-Z][a-z]+)*)([A-Z][a-z]+)([A-Z][a-z]+)$', orig_line)
if m5:
processed_lines.append(m5.group(1))
processed_lines.append(m5.group(2).strip())
processed_lines.append(m5.group(3))
processed_lines.append(m5.group(4))
continue
# Pattern: Grade + Gender + School + FirstName + LastName (e.g., '10FemaleHomeSchoolAbigailDober')
m6 = re.match(r'^(\d{1,2}|K)(Female|Male)([A-Z][a-z]+(?: [A-Z][a-z]+)*)([A-Z][a-z]+)([A-Z][a-z]+)$', orig_line)
if m6:
processed_lines.append(m6.group(1))
processed_lines.append(m6.group(2))
processed_lines.append(m6.group(3).strip())
processed_lines.append(m6.group(4))
processed_lines.append(m6.group(5))
continue
# Otherwise, keep line as is
processed_lines.append(orig_line)
# Remove empty lines
lines = [l for l in processed_lines if l.strip()]
# First pass: Look for individual fields that appear on separate lines
for line in lines:
line = line.strip()
if not line:
continue
# Look for grade (numbers, including K-12)
grade_match = re.match(r'^(?:Grade\s*)?(\d{1,2}|K|k|\d+(?:st|nd|rd|th))$', line)
if grade_match:
grade = grade_match.group(1).upper()
if grade in ['K', '1', '2', '3', '4', '5', '6', '7', '8', '9', '10', '11', '12']:
extracted['grade'] = grade
# Look for gender (case insensitive, handle common variations)
if re.match(r'^(Male|Female|M|F|Boy|Girl)$', line, re.IGNORECASE):
gender = line.capitalize()
if gender in ['Male', 'Female']:
extracted['gender'] = gender
# Look for school names (more flexible pattern)
school_match = re.match(r'^(.+?)(?:\s+(?:High|School|Academy|Middle|Elementary|Christian|Catholic|Public|Private))$', line, re.IGNORECASE)
if school_match and len(school_match.group(1)) > 3: # Avoid false positives
extracted['school'] = line
# If line is all uppercase and not a known field, treat as possible school
if line.isupper() and len(line) > 5 and not any(x in line for x in ['STUDENT', 'NAME', 'GRADE', 'GENDER', 'DETAILS', 'DOCUSIGN', 'ENVELOPE', 'ID']):
extracted['school'] = line.title()
# Second pass: Try various concatenation patterns
patterns = [
# Pattern 1: Gender + School + LastName, Grade + FirstName
{
'regex1': r'^(Female|Male)(.+?)([A-Z][a-z]+)$',
'regex2': r'^(\d{1,2}|K)([A-Z][a-z]+)$',
'map': lambda m1, m2: {
'gender': m1.group(1),
'school': m1.group(2).strip(),
'last_name': m1.group(3),
'grade': m2.group(1),
'first_name': m2.group(2)
}
},
# Pattern 2: FirstName, Gender + School + LastName, Grade
{
'regex1': r'^([A-Z][a-z]+)$',
'regex2': r'^(Female|Male)(.+?)([A-Z][a-z]+)$',
'regex3': r'^(\d{1,2}|K)$',
'map': lambda m1, m2, m3: {
'first_name': m1.group(1),
'gender': m2.group(1),
'school': m2.group(2).strip(),
'last_name': m2.group(3),
'grade': m3.group(1)
}
},
# Pattern 3: Gender + FirstName, School + LastName, Grade
{
'regex1': r'^(Female|Male)([A-Z][a-z]+)$',
'regex2': r'^(.+?)([A-Z][a-z]+)$',
'regex3': r'^(\d{1,2}|K)$',
'map': lambda m1, m2, m3: {
'gender': m1.group(1),
'first_name': m1.group(2),
'school': m2.group(1).strip(),
'last_name': m2.group(2),
'grade': m3.group(1)
}
},
# Pattern 4: School + Grade, Gender + FirstName, LastName
{
'regex1': r'^(.+?)(\d{1,2}|K)$',
'regex2': r'^(Female|Male)([A-Z][a-z]+)$',
'regex3': r'^([A-Z][a-z]+)$',
'map': lambda m1, m2, m3: {
'school': m1.group(1).strip(),
'grade': m1.group(2),
'gender': m2.group(1),
'first_name': m2.group(2),
'last_name': m3.group(1)
}
},
# Pattern 5: FirstName, Gender + Grade, School + LastName
{
'regex1': r'^([A-Z][a-z]+)$',
'regex2': r'^(Female|Male)(\d{1,2}|K)$',
'regex3': r'^(.+?)([A-Z][a-z]+)$',
'map': lambda m1, m2, m3: {
'first_name': m1.group(1),
'gender': m2.group(1),
'grade': m2.group(2),
'school': m3.group(1).strip(),
'last_name': m3.group(2)
}
},
# Pattern 6: FirstName, School + Grade + LastName, Gender
{
'regex1': r'^([A-Z][a-z]+)$',
'regex2': r'^(.+?)(\d{1,2}|K)([A-Z][a-z]+)$',
'regex3': r'^(Female|Male)$',
'map': lambda m1, m2, m3: {
'first_name': m1.group(1),
'school': m2.group(1).strip(),
'grade': m2.group(2),
'last_name': m2.group(3),
'gender': m3.group(1)
}
},
# Pattern 7: Gender + FirstName, School + Grade + LastName
{
'regex1': r'^(Female|Male)([A-Z][a-z]+)$',
'regex2': r'^(.+?)(\d{1,2}|K)([A-Z][a-z]+)$',
'map': lambda m1, m2: {
'gender': m1.group(1),
'first_name': m1.group(2),
'school': m2.group(1).strip(),
'grade': m2.group(2),
'last_name': m2.group(3)
}
},
]
for pattern in patterns:
if 'regex3' in pattern:
for i in range(len(lines) - 2):
m1 = re.match(pattern['regex1'], lines[i])
m2 = re.match(pattern['regex2'], lines[i+1])
m3 = re.match(pattern['regex3'], lines[i+2])
if m1 and m2 and m3:
mapped = pattern['map'](m1, m2, m3)
extracted.update(mapped)
break
else:
for i in range(len(lines) - 1):
m1 = re.match(pattern['regex1'], lines[i])
m2 = re.match(pattern['regex2'], lines[i+1])
if m1 and m2:
mapped = pattern['map'](m1, m2)
extracted.update(mapped)
break
if all(extracted.get(field) for field in ['first_name', 'last_name', 'grade', 'school', 'gender']):
break
# Post-processing and validation
required_fields = ['first_name', 'last_name', 'grade', 'school', 'gender']
if all(extracted.get(field) for field in required_fields):
# Clean up school name: remove trailing student name or stray numbers, but keep valid suffixes
school_clean = extracted['school'].strip()
suffix_keep = {'School', 'Academy', 'Middle', 'High', 'Elementary', 'Christian', 'Catholic', 'Public', 'Private'}
parts = school_clean.split()
if parts:
last_part = parts[-1]
first_name = extracted['first_name'] or ''
last_name = extracted['last_name'] or ''
if last_part.isdigit():
parts = parts[:-1]
elif last_part in {first_name, last_name}:
parts = parts[:-1]
elif last_part not in suffix_keep and last_part in {first_name.title(), last_name.title()}:
parts = parts[:-1]
school_clean = ' '.join(parts).strip()
# Remove any names from school if they match first/last name
for n in [extracted['first_name'], extracted['last_name']]:
if n:
school_clean = re.sub(rf'\b{re.escape(n)}\b', '', school_clean).strip()
extracted['school'] = school_clean
# Final check: discard invalid schools (pure grade, header text, or same as student name)
school_clean = extracted['school'].strip()
if any(x in school_clean.lower() for x in ['docusign envelope id', 'episode registration']):
extracted['school'] = ''
return extracted
if re.fullmatch(r'(\d{1,2}|K)', school_clean):
extracted['school'] = ''
else:
first_lower = extracted['first_name'].lower() if extracted['first_name'] else ''
last_lower = extracted['last_name'].lower() if extracted['last_name'] else ''
if school_clean.lower() in {first_lower, last_lower}:
extracted['school'] = ''
else:
extracted['school'] = school_clean
return extracted
# Fallback: Try to extract fields from any order in the lines (for highly concatenated or out-of-order data)
forbidden_names = set(['School', 'Home', 'High', 'Middle', 'Academy', 'Christian', 'Temple', 'Rustburg', 'Liberty', 'Forest', 'Heritage', 'Amherst', 'Appomattox', 'Dunbar', 'Glass', 'Jefferson', 'Linkhorne', 'Monelison', 'Sandusky', 'Timberlake'])
gender_words = set(['Male', 'Female'])
grade_words = set([str(i) for i in range(1,13)] + ['K'])
school_name = extracted['school'].lower()
names = []
for line in lines:
for word in line.split():
w_lower = word.lower()
# Exclude if word matches or contains any part of the school name
if (re.match(r'^[A-Z][a-z]+$', word)
and word not in forbidden_names
and word not in gender_words
and word not in grade_words
and school_name not in w_lower
and w_lower not in school_name):
names.append(word)
# Require two distinct names
if len(names) >= 2 and names[0] != names[1]:
if not extracted['first_name']:
extracted['first_name'] = names[0]
if not extracted['last_name']:
extracted['last_name'] = names[1]
else:
return None
# Look for grade
for line in lines:
m = re.search(r'(\d{1,2}|K)', line)
if m and not extracted['grade']:
extracted['grade'] = m.group(1)
# Look for gender
for line in lines:
if 'female' in line.lower() and not extracted['gender']:
extracted['gender'] = 'Female'
elif 'male' in line.lower() and not extracted['gender']:
extracted['gender'] = 'Male'
# Look for school (any line with 'school', 'academy', 'high', etc.)
for line in lines:
if any(x in line.lower() for x in ['school', 'academy', 'high', 'middle', 'elementary', 'christian', 'catholic', 'public', 'private']):
extracted['school'] = line.strip()
break
if all(extracted.get(field) for field in required_fields):
extracted['school'] = re.sub(r'\s+', ' ', extracted['school']).strip()
return extracted
return None
def process_job(job_id, files):
temp_extract_dirs = []
job_failed = False
try:
print("=== DEBUG: process_job STARTED ===")
with job_lock:
job_queue[job_id]['status'] = 'processing'
job_queue[job_id]['progress'] = 'Starting job processing...'
save_jobs() # Persist initial progress
# Create base Episode directory for this job
episode_dir = os.path.join(app.config['UPLOAD_FOLDER'], f'Episode_{job_id}')
os.makedirs(episode_dir, exist_ok=True)
processed_files = []
skipped_dir = os.path.join(episode_dir, 'Skipped')
os.makedirs(skipped_dir, exist_ok=True)
skipped_log_path = os.path.join(skipped_dir, 'skipped_files.log')
job_queue[job_id]['progress'] = 'Created output directory structure'
# Analyze ZIP contents before processing
zip_contents = {}
job_queue[job_id]['progress'] = 'Analyzing uploaded files...'
for file_info in files:
if file_info['name'].lower().endswith('.zip'):
try:
with zipfile.ZipFile(file_info['path'], 'r') as zip_ref:
pdf_files = [f for f in zip_ref.namelist() if f.lower().endswith('.pdf')]
zip_contents[file_info['name']] = pdf_files
except Exception as e:
zip_contents[file_info['name']] = [f"Error reading ZIP: {str(e)}"]
job_queue[job_id]['zip_contents'] = zip_contents
total_files = sum(1 for file_info in files if file_info['name'].lower().endswith('.pdf')) + \
sum(len(zip_contents.get(file_info['name'], []))
for file_info in files if file_info['name'].lower().endswith('.zip'))
job_queue[job_id]['progress'] = f'Found {total_files} files to process'
save_jobs() # Persist file count
processed_count = 0
for file_info in files:
filepath = file_info['path']
filename = file_info['name']
if filename.lower().endswith('.zip'):
try:
job_queue[job_id]['progress'] = f'Extracting ZIP archive: {filename}'
print(f"DEBUG: Starting ZIP extraction for {filename}")
# Extract ZIP
extract_dir = os.path.join(app.config['UPLOAD_FOLDER'], f'extract_{job_id}_{os.path.splitext(filename)[0]}')
os.makedirs(extract_dir, exist_ok=True)
temp_extract_dirs.append(extract_dir)
print(f"DEBUG: Created extract directory: {extract_dir}")
with zipfile.ZipFile(filepath, 'r') as zip_ref:
file_count = len(zip_ref.namelist())
print(f"DEBUG: ZIP contains {file_count} files: {zip_ref.namelist()}")
zip_ref.extractall(extract_dir)
job_queue[job_id]['progress'] = f'Extracted {file_count} files from {filename}'
save_jobs() # Persist ZIP extraction progress
print(f"DEBUG: ZIP extraction completed, progress updated: {job_queue[job_id]['progress']}")
# Process PDFs in extract_dir
pdf_files_found = []
for root, dirs, files_in_zip in os.walk(extract_dir):
for f in files_in_zip:
if f.lower().endswith('.pdf'):
pdf_files_found.append(f)
pdf_path = os.path.join(root, f)
job_queue[job_id]['progress'] = f'Processing PDF: {f}'
save_jobs() # Persist current file progress
print(f"DEBUG: Processing PDF: {f} at {pdf_path}")
print(f"DEBUG: File exists: {os.path.exists(pdf_path)}")
# Skip MacOS resource fork files (._*)
if f.startswith('._'):
print(f"DEBUG: Skipping MacOS resource fork file: {f}")
continue
pdf_info = extract_names_from_pdf(pdf_path)
print(f"DEBUG: PDF extraction result: {pdf_info}")
if 'error' in pdf_info:
# Move skipped file to Skipped/
skipped_pdf_path = os.path.join(skipped_dir, f)
try:
os.rename(pdf_path, skipped_pdf_path)
except Exception as move_err:
print(f"WARNING: Could not move skipped PDF {f}: {move_err}")
# Log skip reason and raw text if available
with open(skipped_log_path, 'a', encoding='utf-8') as slog:
slog.write(f"File: {f}\nReason: {pdf_info['error']}\n")
if 'raw_text' in pdf_info:
slog.write(f"Raw Text:\n{pdf_info['raw_text']}\n")
slog.write("-"*50 + "\n")
# Store reason and raw_text for web GUI
processed_files.append(('skipped', f, pdf_info['error'], pdf_info.get('raw_text', '')))
job_queue[job_id]['progress'] = f'Skipped {f} - {pdf_info["error"]}'
print(f"DEBUG: Skipped PDF {f}: {pdf_info['error']}")
else:
job_queue[job_id]['progress'] = f'Extracted data for {pdf_info["first_name"]} {pdf_info["last_name"]}'
print(f"DEBUG: Successfully extracted data for {pdf_info['first_name']} {pdf_info['last_name']}")
# Create folder structure: Episode/School/Grade/Gender/
school_dir = os.path.join(episode_dir, sanitize_segment(pdf_info['school']) or 'Unknown_School')
grade_dir = os.path.join(school_dir, sanitize_segment(pdf_info['grade']) or 'Unknown_Grade')
gender_dir = os.path.join(grade_dir, sanitize_segment(pdf_info['gender']) or 'Unknown_Gender')
print(f"DEBUG: Creating directories: {school_dir} -> {grade_dir} -> {gender_dir}")
os.makedirs(gender_dir, exist_ok=True)
print(f"DEBUG: Directories created successfully")
# Move file to appropriate folder with new name
safe_filename = secure_filename(pdf_info['filename']) or pdf_info['filename']
new_path = os.path.join(gender_dir, safe_filename)
print(f"DEBUG: Attempting to move {pdf_path} to {new_path}")
counter = 1
while os.path.exists(new_path):
base, ext = os.path.splitext(pdf_info['filename'])
new_path = os.path.join(gender_dir, f"{base}_{counter}{ext}")
counter += 1
print(f"DEBUG: File exists, trying {new_path}")
print(f"DEBUG: Moving file to {new_path}")
os.rename(pdf_path, new_path)
processed_files.append(('success', os.path.relpath(new_path, episode_dir), new_path))
processed_count += 1
job_queue[job_id]['progress'] = f'Organized {processed_count}/{total_files} files'
# Batch saves - only every 5 files
if processed_count % 5 == 0:
save_jobs()
print(f"DEBUG: Organized file {processed_count}/{total_files}")
print(f"DEBUG: Found {len(pdf_files_found)} PDF files in ZIP: {pdf_files_found}")
except Exception as e:
processed_files.append(('skipped', filename, f'ZIP processing error: {str(e)}'))
job_queue[job_id]['progress'] = f'Failed to process ZIP {filename}: {str(e)}'
print(f"ZIP processing error for {filename}: {str(e)}")
continue
else:
# Single PDF
try:
job_queue[job_id]['progress'] = f'Processing PDF: {filename}'
save_jobs() # Persist current file progress
# Skip MacOS resource fork files (._*)
if filename.startswith('._'):
print(f"DEBUG: Skipping MacOS resource fork file: {filename}")
continue
pdf_info = extract_names_from_pdf(filepath)
if 'error' in pdf_info:
# Move skipped file to Skipped/
skipped_pdf_path = os.path.join(skipped_dir, filename)
try:
os.rename(filepath, skipped_pdf_path)
except Exception as move_err:
print(f"WARNING: Could not move skipped PDF {filename}: {move_err}")
# Log skip reason and raw text if available
with open(skipped_log_path, 'a', encoding='utf-8') as slog:
slog.write(f"File: {filename}\nReason: {pdf_info['error']}\n")
if 'raw_text' in pdf_info:
slog.write(f"Raw Text:\n{pdf_info['raw_text']}\n")
slog.write("-"*50 + "\n")
processed_files.append(('skipped', filename, pdf_info['error'], pdf_info.get('raw_text', '')))
job_queue[job_id]['progress'] = f'Skipped {filename} - {pdf_info["error"]}'
else:
job_queue[job_id]['progress'] = f'Extracted data for {pdf_info["first_name"]} {pdf_info["last_name"]}'
# Create folder structure: Episode/School/Grade/Gender/
school_dir = os.path.join(episode_dir, sanitize_segment(pdf_info['school']) or 'Unknown_School')
grade_dir = os.path.join(school_dir, sanitize_segment(pdf_info['grade']) or 'Unknown_Grade')
gender_dir = os.path.join(grade_dir, sanitize_segment(pdf_info['gender']) or 'Unknown_Gender')
os.makedirs(gender_dir, exist_ok=True)
# Move file to appropriate folder with new name
safe_filename = secure_filename(pdf_info['filename']) or pdf_info['filename']
new_filepath = os.path.join(gender_dir, safe_filename)
counter = 1
while os.path.exists(new_filepath):
base, ext = os.path.splitext(pdf_info['filename'])
new_filepath = os.path.join(gender_dir, f"{base}_{counter}{ext}")
counter += 1
os.rename(filepath, new_filepath)
processed_files.append(('success', os.path.relpath(new_filepath, episode_dir), new_filepath))
processed_count += 1
job_queue[job_id]['progress'] = f'Organized {processed_count}/{total_files} files'
# Batch saves - only every 5 files
if processed_count % 5 == 0:
save_jobs()
except Exception as e:
processed_files.append(('skipped', filename, f'PDF processing error: {str(e)}'))
job_queue[job_id]['progress'] = f'Failed to process PDF {filename}: {str(e)}'
print(f"PDF processing error for {filename}: {str(e)}")
continue
job_queue[job_id]['progress'] = 'Creating ZIP archive...'
# Create ZIP of the entire Episode directory structure
# Always create ZIP, including Skipped/ folder if present
try:
zip_output = os.path.join(app.config['ARCHIVE_FOLDER'], f'renamed_{job_id}.zip')
print(f"DEBUG: Creating ZIP at {zip_output}")
with zipfile.ZipFile(zip_output, 'w', zipfile.ZIP_DEFLATED) as zip_out:
for root, dirs, files_in_dir in os.walk(episode_dir):
for file in files_in_dir:
if file.startswith('.') or file.startswith('._'):
continue # Ignore dotfiles and MacOS resource forks
file_path = os.path.join(root, file)
arcname = os.path.relpath(file_path, episode_dir)
print(f"DEBUG: Adding to ZIP: {file_path} as {arcname}")
zip_out.write(file_path, arcname)
job_queue[job_id]['zip_path'] = zip_output
job_queue[job_id]['zip_name'] = f'renamed_{job_id}.zip'
success_count = len([p for p in processed_files if p[0] == 'success'])
skipped_count = len([p for p in processed_files if p[0] == 'skipped'])
job_queue[job_id]['progress'] = (
f"Created ZIP archive with {success_count} organized files and {skipped_count} skipped files"
)
save_jobs() # Persist completion progress
print(f"DEBUG: ZIP creation completed successfully")
# Clean up Episode directory after successful ZIP creation
try:
import shutil
shutil.rmtree(episode_dir)
print(f"DEBUG: Cleaned up Episode directory: {episode_dir}")
except Exception as cleanup_error:
print(f"WARNING: Failed to clean up Episode directory: {cleanup_error}")
# Clean up original uploaded files
for file_info in files:
try:
if os.path.exists(file_info['path']):
os.remove(file_info['path'])
print(f"DEBUG: Removed uploaded file: {file_info['path']}")
except Exception as file_cleanup_error:
print(f"WARNING: Failed to remove uploaded file: {file_cleanup_error}")
except Exception as e:
job_queue[job_id]['progress'] = f'Error creating ZIP: {str(e)}'
job_queue[job_id]['status'] = 'error'
job_failed = True
save_jobs() # Persist error status
print(f"DEBUG: ZIP creation failed: {str(e)}")
with job_lock:
if not job_failed:
job_queue[job_id]['status'] = 'completed'
job_queue[job_id]['processed_files'] = processed_files
# Store skipped as (filename, reason, raw_text)
job_queue[job_id]['skipped'] = [(p[1], p[2], p[3]) for p in processed_files if p[0] == 'skipped']
save_jobs() # Persist completed job
print(f"DEBUG: Job {job_id} completed successfully. Processed: {len(processed_files)}, Skipped: {len(job_queue[job_id]['skipped'])}")
except Exception as e:
with job_lock:
job_queue[job_id]['status'] = 'error'
job_queue[job_id]['progress'] = f'Job failed with error: {str(e)}'
save_jobs() # Persist error status
print(f"Job {job_id} failed: {str(e)}") # Debug logging
finally:
# Clean up temporary directories
for temp_dir in temp_extract_dirs:
if os.path.exists(temp_dir):
try:
import shutil
shutil.rmtree(temp_dir)
print(f"DEBUG: Cleaned up temporary directory: {temp_dir}")
except Exception as cleanup_error:
print(f"ERROR: Failed to clean up {temp_dir}: {cleanup_error}")
@app.route('/login')
def login():
return render_template_string('''
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>NextGenPDF - Login</title>
<style>
* { margin: 0; padding: 0; box-sizing: border-box; }
body {
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
min-height: 100vh;
display: flex;
justify-content: center;
align-items: center;
padding: 20px;
}
.login-wrapper {
background: white;
border-radius: 15px;
box-shadow: 0 20px 60px rgba(0, 0, 0, 0.3);
overflow: hidden;
max-width: 900px;
width: 100%;
display: grid;
grid-template-columns: 1fr 1fr;
}
.login-left {
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
padding: 60px 40px;
display: flex;
flex-direction: column;
justify-content: center;
align-items: center;
color: white;
text-align: center;
}
.login-left img { width: 180px; margin-bottom: 30px; filter: brightness(0) invert(1); }
.login-left h1 { font-size: 32px; margin-bottom: 15px; font-weight: 600; }
.login-left p { font-size: 16px; line-height: 1.6; opacity: 0.9; }
.login-right {
padding: 60px 40px;
display: flex;
flex-direction: column;
justify-content: center;
}
.login-right h2 {
font-size: 24px;
color: #333;
margin-bottom: 40px;
text-align: center;
font-weight: 600;
}
.login-options { display: flex; flex-direction: column; gap: 20px; }
.login-option { }
.login-option h3 {
font-size: 14px;
color: #666;
text-transform: uppercase;
letter-spacing: 1px;
margin-bottom: 15px;
font-weight: 600;
}
.login-btn {
width: 100%;
padding: 14px 24px;
font-size: 16px;
border: none;
border-radius: 8px;
cursor: pointer;
font-weight: 600;
transition: all 0.3s ease;
text-decoration: none;
display: block;
text-align: center;
}
.btn-microsoft {
background: #0078d4;
color: white;
}
.btn-microsoft:hover {
background: #106ebe;
transform: translateY(-2px);
box-shadow: 0 10px 25px rgba(0, 120, 212, 0.3);
}
form { width: 100%; }
.form-group { margin-bottom: 15px; }
.form-group input {
width: 100%;
padding: 12px 16px;
border: 1px solid #ddd;
border-radius: 8px;
font-size: 15px;
transition: all 0.3s ease;
font-family: inherit;
}
.form-group input:focus {
outline: none;
border-color: #667eea;
box-shadow: 0 0 0 3px rgba(102, 126, 234, 0.1);
}
.btn-admin {
width: 100%;
padding: 12px 24px;
background: #28a745;
color: white;
border: none;
border-radius: 8px;
font-size: 16px;
font-weight: 600;
cursor: pointer;
transition: all 0.3s ease;
}
.btn-admin:hover {
background: #218838;
transform: translateY(-2px);
box-shadow: 0 10px 25px rgba(40, 167, 69, 0.3);
}
.divider {
text-align: center;
margin: 25px 0;
position: relative;
color: #999;
}
.divider::before {
content: '';
position: absolute;
top: 50%;
left: 0;
right: 0;
height: 1px;
background: #ddd;
}
.divider span {
background: white;
padding: 0 10px;
position: relative;
font-size: 13px;
}
@media (max-width: 768px) {
.login-wrapper { grid-template-columns: 1fr; }
.login-left { padding: 40px 30px; }
.login-right { padding: 40px 30px; }
.login-left h1 { font-size: 24px; }
}
</style>
</head>
<body>
<div class="login-wrapper">
<div class="login-left">
<img src="/static/trbc-logo-full.png" alt="Logo">
<h1>NextGenPDF</h1>
<p>Automated PDF Organization & Renaming System</p>
</div>
<div class="login-right">
<h2>Welcome Back</h2>
<div class="login-options">
<div class="login-option">
<h3>Microsoft Entra ID</h3>
<a href="/entra-login" class="login-btn btn-microsoft">Sign in with Microsoft</a>
</div>
<div class="divider"><span>or</span></div>
<div class="login-option">
<h3>Administrator Login</h3>
<form method="post" action="/admin-login">
<div class="form-group">
<input type="text" name="username" placeholder="Username" required>
</div>
<div class="form-group">
<input type="password" name="password" placeholder="Password" required>
</div>
<button type="submit" class="btn-admin">Sign In</button>
</form>
</div>
</div>
</div>
</div>
</body>
</html>
''')
@app.route('/entra-login')
def entra_login():
# Check if Microsoft OAuth provider is available
if microsoft is None:
flash('Microsoft Entra ID authentication is not configured.', 'error')
return redirect(url_for('login'))
# Check if Microsoft Entra ID is configured
if TENANT_ID in ['your-tenant-id', 'YOUR_MICROSOFT_ENTRA_TENANT_ID'] or \
CLIENT_ID in ['your-client-id', 'YOUR_MICROSOFT_ENTRA_CLIENT_ID'] or \
CLIENT_SECRET in ['your-client-secret', 'YOUR_MICROSOFT_ENTRA_CLIENT_SECRET']:
flash('Microsoft Entra ID is not properly configured. Please check your environment variables.', 'error')
return redirect(url_for('login'))
try:
redirect_uri = url_for('auth', _external=True)
print(f"DEBUG: Initiating OAuth with redirect_uri: {redirect_uri}")
return microsoft.authorize_redirect(redirect_uri)
except Exception as e:
print(f"ERROR: Failed to initiate OAuth: {e}")
import traceback
print(f"Traceback: {traceback.format_exc()}")
flash('Failed to initiate Microsoft authentication. Please try again or use admin login.', 'error')
return redirect(url_for('login'))
@app.route('/admin-login', methods=['POST'])
def admin_login():
username = request.form.get('username')
password = request.form.get('password')
if username == ADMIN_USERNAME and password == ADMIN_PASSWORD:
session['admin'] = True
return redirect(url_for('upload_files'))
else:
return render_template_string('''
<!DOCTYPE html>
<html>
<head>
<title>Login Failed</title>
<style>
body { font-family: Arial, sans-serif; background-color: #f4f4f4; text-align: center; padding: 50px; }
.error { color: #dc3545; background-color: #f8d7da; padding: 20px; border-radius: 5px; border: 1px solid #f5c6cb; }
a { color: #007bff; text-decoration: none; }
</style>
</head>
<body>
<div class="error">
<h1>Login Failed</h1>
<p>Invalid username or password.</p>
<a href="/login">Try Again</a>
</div>
</body>
</html>
''')
@app.route('/auth')
def auth():
try:
print("DEBUG: Starting OAuth callback processing")
token = microsoft.authorize_access_token()
print(f"DEBUG: Got token: {token}")
# Get user info from the token's userinfo (already parsed by Authlib)
user_info = token.get('userinfo')
if not user_info:
print("ERROR: No userinfo in token")
flash('Failed to get user information from Microsoft.', 'error')
return redirect(url_for('login'))
print(f"DEBUG: Parsed user info: {user_info}")
# Store user information in session
session['user'] = {
'name': user_info.get('name', 'Unknown'),
'email': user_info.get('email') or user_info.get('preferred_username', 'unknown@example.com'),
'oid': user_info.get('oid'),
}
session.permanent = True
print(f"DEBUG: User logged in successfully: {session['user']}")
return redirect(url_for('upload_files'))
except Exception as e:
print(f"OAuth error: {e}") # Log the error for debugging
import traceback
print(f"Full traceback: {traceback.format_exc()}")
flash('Authentication failed. Please try again.', 'error')
return redirect(url_for('login'))
@app.route('/logout')
@login_required
def logout():
session.pop('user', None)
session.pop('admin', None)
return redirect(url_for('login'))
@app.route('/', methods=['GET', 'POST'])
@login_required
def upload_files():
if request.method == 'POST':
files = request.files.getlist('files')
if not files or all(not f.filename for f in files):
flash('No files selected.', 'error')
return redirect(url_for('upload_files'))
# Create job ID using timestamp format: YYYY-MM-DD_HH-MM-SS
job_id = datetime.now().strftime('%Y-%m-%d_%H-%M-%S')
job_queue[job_id] = {
'status': 'queued',
'files': [],
'zip_path': None,
'zip_name': None,
'processed_files': [],
'skipped': [],
'created_at': datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
'job_id': job_id # Store the job ID for reference
}
file_list = []
for file in files:
if file and not file.filename.startswith('.') and allowed_file(file.filename):
filename = secure_filename(file.filename)
filepath = os.path.join(app.config['UPLOAD_FOLDER'], f"{job_id}_{filename}")
file.save(filepath)
file_list.append({'name': filename, 'path': filepath})
print(f"Uploaded file: {filename} -> {filepath}") # Debug logging
if not file_list:
flash('No valid files uploaded. Only PDF and ZIP files are allowed.', 'error')
job_queue.pop(job_id, None) # Remove empty job
return redirect(url_for('upload_files'))
job_queue[job_id]['files'] = file_list
print(f"Created job {job_id} with {len(file_list)} files") # Debug logging
# Save job to persistent storage
save_jobs()
# Start processing in background
def process_with_context():
with app.app_context():
process_job(job_id, file_list)
thread = threading.Thread(target=process_with_context)
thread.daemon = True
thread.start()
flash(f'Job created successfully. Processing {len(file_list)} files...', 'success')
return redirect(url_for('jobs'))
return render_template_string('''
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>NextGenPDF - Upload Files</title>
<style>
* { margin: 0; padding: 0; box-sizing: border-box; }
body {
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
background: linear-gradient(135deg, #f5f7fa 0%, #c3cfe2 100%);
min-height: 100vh;
padding: 30px 20px;
}
.container { max-width: 1200px; margin: 0 auto; }
.header {
display: flex;
justify-content: space-between;
align-items: center;
margin-bottom: 40px;
}
.header-info { display: flex; align-items: center; gap: 20px; }
.logo img { height: 50px; }
.header-text h1 {
font-size: 28px;
color: #333;
margin: 0;
font-weight: 600;
}
.header-text p {
font-size: 14px;
color: #666;
margin: 5px 0 0 0;
}
.header-actions { display: flex; gap: 10px; }
.nav-link {
display: inline-flex;
align-items: center;
gap: 8px;
padding: 12px 20px;
background: white;
color: #667eea;
text-decoration: none;
border-radius: 8px;
font-weight: 600;
transition: all 0.3s ease;
box-shadow: 0 2px 8px rgba(0, 0, 0, 0.1);
}
.nav-link:hover {
transform: translateY(-2px);
box-shadow: 0 5px 15px rgba(0, 0, 0, 0.15);
}
.logout-btn {
background: linear-gradient(135deg, #f093fb 0%, #f5576c 100%);
color: white !important;
}
.main-content { display: grid; grid-template-columns: 1fr 1fr; gap: 30px; }
.upload-section {
background: white;
padding: 40px;
border-radius: 15px;
box-shadow: 0 10px 30px rgba(0, 0, 0, 0.1);
}
.upload-section h2 {
font-size: 22px;
color: #333;
margin-bottom: 30px;
font-weight: 600;
}
.upload-area {
border: 2px dashed #667eea;
border-radius: 12px;
padding: 60px 20px;
text-align: center;
background: #f8f9ff;
cursor: pointer;
transition: all 0.3s ease;
position: relative;
}
.upload-area:hover {
border-color: #764ba2;
background: #f3f4ff;
}
.upload-area.active {
border-color: #28a745;
background: #f0f9f4;
}
.upload-icon {
font-size: 48px;
margin-bottom: 15px;
color: #667eea;
}
.upload-area.active .upload-icon { color: #28a745; }
.upload-text {
color: #333;
font-size: 16px;
font-weight: 500;
}
.upload-text p {
margin: 5px 0;
color: #666;
font-size: 14px;
}
.upload-input {
position: absolute;
top: 0;
left: 0;
width: 100%;
height: 100%;
opacity: 0;
cursor: pointer;
}
.submit-btn {
width: 100%;
padding: 14px 24px;
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
color: white;
border: none;
border-radius: 8px;
font-size: 16px;
font-weight: 600;
cursor: pointer;
margin-top: 20px;
transition: all 0.3s ease;
}
.submit-btn:hover {
transform: translateY(-2px);
box-shadow: 0 10px 25px rgba(102, 126, 234, 0.3);
}
.submit-btn:disabled {
opacity: 0.5;
cursor: not-allowed;
transform: none;
}
.file-list {
margin-top: 20px;
max-height: 300px;
overflow-y: auto;
}
.file-item {
background: #f8f9fa;
padding: 10px 15px;
border-radius: 6px;
margin: 8px 0;
display: flex;
justify-content: space-between;
align-items: center;
font-size: 14px;
}
.file-item .remove-btn {
background: #dc3545;
color: white;
border: none;
border-radius: 4px;
padding: 4px 8px;
cursor: pointer;
font-size: 12px;
}
.info-section {
background: white;
padding: 40px;
border-radius: 15px;
box-shadow: 0 10px 30px rgba(0, 0, 0, 0.1);
}
.info-section h2 {
font-size: 22px;
color: #333;
margin-bottom: 20px;
font-weight: 600;
}
.info-box {
background: linear-gradient(135deg, #667eea15 0%, #764ba215 100%);
border-left: 4px solid #667eea;
padding: 20px;
border-radius: 8px;
margin-bottom: 20px;
}
.info-box h3 {
color: #667eea;
font-size: 16px;
margin-bottom: 12px;
font-weight: 600;
}
.info-box p, .info-box ul {
color: #555;
font-size: 14px;
line-height: 1.6;
margin: 0;
}
.info-box ul {
padding-left: 20px;
margin: 10px 0;
}
.info-box li {
margin: 8px 0;
color: #555;
}
.feature-item {
display: flex;
align-items: flex-start;
gap: 12px;
margin-bottom: 12px;
}
.feature-icon {
color: #28a745;
font-weight: bold;
font-size: 18px;
flex-shrink: 0;
}
.feature-text {
color: #555;
font-size: 14px;
}
.quick-links {
display: flex;
gap: 10px;
margin-top: 20px;
}
.quick-link {
flex: 1;
padding: 15px;
background: #f8f9fa;
border-radius: 8px;
text-align: center;
text-decoration: none;
color: #667eea;
font-weight: 600;
transition: all 0.3s ease;
border: 1px solid #e9ecef;
}
.quick-link:hover {
background: #667eea;
color: white;
}
.alert {
padding: 15px 20px;
border-radius: 8px;
margin-bottom: 20px;
font-size: 14px;
}
.alert.success {
background: #d4edda;
color: #155724;
border: 1px solid #c3e6cb;
}
.alert.error {
background: #f8d7da;
color: #721c24;
border: 1px solid #f5c6cb;
}
@media (max-width: 768px) {
.main-content { grid-template-columns: 1fr; }
.header { flex-direction: column; text-align: center; gap: 20px; }
.header-actions { justify-content: center; flex-wrap: wrap; }
}
</style>
</head>
<body>
<div class="container">
<div class="header">
<div class="header-info">
<div class="logo"><img src="/static/trbc-logo-full.png" alt="Logo"></div>
<div class="header-text">
<h1>NextGenPDF</h1>
<p>Automated PDF Organization & Renaming</p>
</div>
</div>
<div class="header-actions">
<a href="/jobs" class="nav-link">View Jobs</a>
<a href="/logout" class="nav-link logout-btn">Logout</a>
</div>
</div>
{% with messages = get_flashed_messages(with_categories=true) %}
{% if messages %}
{% for category, message in messages %}
<div class="alert {{ category }}">{{ message }}</div>
{% endfor %}
{% endif %}
{% endwith %}
<div class="main-content">
<div class="upload-section">
<h2>Upload Files</h2>
<form method="post" enctype="multipart/form-data" id="upload-form">
<div class="upload-area" id="upload-area">
<div class="upload-icon">Upload</div>
<div class="upload-text">
<p style="font-weight: 600;">Drag & drop your files here</p>
<p>or click to select PDF and ZIP files</p>
</div>
<input type="file" id="file-input" name="files" multiple accept=".pdf,.zip" class="upload-input">
</div>
<div class="file-list" id="file-list"></div>
<button type="submit" class="submit-btn" id="submit-btn">Upload & Process Files</button>
</form>
</div>
<div class="info-section">
<h2>How It Works</h2>
<div class="info-box">
<h3>What is NextGenPDF?</h3>
<p>NextGenPDF automatically extracts student information from PDF registration forms and organizes them into a structured folder system.</p>
</div>
<div class="info-box">
<h3>Processing Steps</h3>
<div class="feature-item">
<div class="feature-icon">1</div>
<div class="feature-text">Upload individual PDFs or ZIP files</div>
</div>
<div class="feature-item">
<div class="feature-icon">2</div>
<div class="feature-text">System extracts name, school, grade, and gender</div>
</div>
<div class="feature-item">
<div class="feature-icon">3</div>
<div class="feature-text">Files renamed to: <strong>LastName_FirstName_Grade.pdf</strong></div>
</div>
<div class="feature-item">
<div class="feature-icon">4</div>
<div class="feature-text">Organized into: <strong>Episode/School/Grade/Gender/</strong></div>
</div>
<div class="feature-item">
<div class="feature-icon">5</div>
<div class="feature-text">Download organized ZIP archive</div>
</div>
</div>
<div class="quick-links">
<a href="/jobs" class="quick-link">View Jobs ></a>
</div>
</div>
</div>
</div>
<script>
const uploadArea = document.getElementById('upload-area');
const fileInput = document.getElementById('file-input');
const fileList = document.getElementById('file-list');
const uploadForm = document.getElementById('upload-form');
let selectedFiles = [];
// Drag and drop handlers
uploadArea.addEventListener('dragover', (e) => {
e.preventDefault();
uploadArea.classList.add('active');
});
uploadArea.addEventListener('dragleave', () => {
uploadArea.classList.remove('active');
});
uploadArea.addEventListener('drop', (e) => {
e.preventDefault();
uploadArea.classList.remove('active');
const files = e.dataTransfer.files;
fileInput.files = files;
updateFileList(files);
});
uploadArea.addEventListener('click', () => fileInput.click());
fileInput.addEventListener('change', (e) => {
updateFileList(e.target.files);
});
function updateFileList(files) {
selectedFiles = Array.from(files);
fileList.innerHTML = '';
if (selectedFiles.length === 0) {
document.getElementById('submit-btn').disabled = true;
return;
}
selectedFiles.forEach((file, index) => {
const item = document.createElement('div');
item.className = 'file-item';
const size = (file.size / 1024 / 1024).toFixed(2);
item.innerHTML = `
<span>File: ${file.name} (${size} MB)</span>
<button type="button" class="remove-btn" onclick="removeFile(${index})">Remove</button>
`;
fileList.appendChild(item);
});
document.getElementById('submit-btn').disabled = false;
}
function removeFile(index) {
selectedFiles.splice(index, 1);
const dt = new DataTransfer();
selectedFiles.forEach(file => dt.items.add(file));
fileInput.files = dt.files;
updateFileList(dt.files);
}
uploadForm.addEventListener('submit', (e) => {
if (selectedFiles.length === 0) {
e.preventDefault();
alert('Please select files to upload');
}
});
</script>
</body>
</html>
''')
@app.route('/jobs')
@login_required
def jobs():
return render_template_string('''
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>NextGenPDF - Jobs Dashboard</title>
<style>
* { margin: 0; padding: 0; box-sizing: border-box; }
body {
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
background: linear-gradient(135deg, #f5f7fa 0%, #c3cfe2 100%);
min-height: 100vh;
padding: 30px 20px;
}
.container { max-width: 1200px; margin: 0 auto; }
.header {
display: flex;
justify-content: space-between;
align-items: center;
margin-bottom: 40px;
}
.header-info { display: flex; align-items: center; gap: 20px; }
.logo img { height: 50px; }
.header-text h1 {
font-size: 28px;
color: #333;
margin: 0;
font-weight: 600;
}
.header-text p {
font-size: 14px;
color: #666;
margin: 5px 0 0 0;
}
.header-actions { display: flex; gap: 10px; }
.nav-link {
display: inline-flex;
align-items: center;
gap: 8px;
padding: 12px 20px;
background: white;
color: #667eea;
text-decoration: none;
border-radius: 8px;
font-weight: 600;
transition: all 0.3s ease;
box-shadow: 0 2px 8px rgba(0, 0, 0, 0.1);
}
.nav-link:hover {
transform: translateY(-2px);
box-shadow: 0 5px 15px rgba(0, 0, 0, 0.15);
}
.logout-btn {
background: linear-gradient(135deg, #f093fb 0%, #f5576c 100%);
color: white !important;
}
.jobs-container { }
.job-card {
background: white;
border-radius: 12px;
box-shadow: 0 5px 20px rgba(0, 0, 0, 0.1);
margin-bottom: 25px;
overflow: hidden;
transition: all 0.3s ease;
}
.job-card:hover {
box-shadow: 0 10px 35px rgba(0, 0, 0, 0.15);
transform: translateY(-2px);
}
.job-header {
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
color: white;
padding: 20px;
display: flex;
justify-content: space-between;
align-items: center;
}
.job-title { font-size: 18px; font-weight: 600; }
.job-meta { font-size: 12px; opacity: 0.9; }
.status-badge {
padding: 8px 16px;
border-radius: 20px;
font-size: 12px;
font-weight: 600;
text-transform: uppercase;
letter-spacing: 0.5px;
}
.status-queued { background: rgba(255, 193, 7, 0.2); color: #f57f17; }
.status-processing { background: rgba(0, 150, 136, 0.2); color: #00897b; }
.status-completed { background: rgba(76, 175, 80, 0.2); color: #558b2f; }
.status-error { background: rgba(244, 67, 54, 0.2); color: #c62828; }
.job-body { padding: 25px; }
.job-info { display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 20px; margin-bottom: 20px; }
.info-item { }
.info-label {
font-size: 12px;
text-transform: uppercase;
letter-spacing: 0.5px;
color: #999;
font-weight: 600;
margin-bottom: 5px;
}
.info-value {
font-size: 16px;
color: #333;
font-weight: 500;
}
.progress-bar {
width: 100%;
height: 8px;
background: #f0f0f0;
border-radius: 10px;
overflow: hidden;
margin-top: 10px;
}
.progress-fill {
height: 100%;
background: linear-gradient(90deg, #667eea 0%, #764ba2 100%);
width: 0%;
transition: width 0.5s ease;
}
.progress-text {
font-size: 12px;
color: #667eea;
font-style: italic;
margin-top: 8px;
}
.zip-contents {
background: #f8f9fa;
border-radius: 8px;
padding: 15px;
margin: 15px 0;
}
.zip-toggle {
cursor: pointer;
font-weight: 600;
color: #667eea;
display: flex;
align-items: center;
justify-content: space-between;
padding: 10px 0;
user-select: none;
}
.zip-toggle:hover { color: #764ba2; }
.zip-details {
display: none;
margin-top: 15px;
max-height: 400px;
overflow-y: auto;
}
.file-list { list-style: none; }
.file-list li {
padding: 8px 12px;
background: white;
margin: 5px 0;
border-radius: 4px;
font-size: 13px;
color: #555;
border-left: 3px solid #667eea;
}
.skipped-section {
background: #fff3cd;
border-left: 4px solid #ffc107;
border-radius: 8px;
padding: 15px;
margin: 15px 0;
}
.skipped-toggle {
cursor: pointer;
font-weight: 600;
color: #856404;
display: flex;
align-items: center;
justify-content: space-between;
user-select: none;
}
.skipped-toggle:hover { color: #533f03; }
.skipped-details { display: none; margin-top: 15px; }
.action-buttons {
display: flex;
gap: 10px;
flex-wrap: wrap;
margin-top: 20px;
}
.btn {
padding: 10px 20px;
border: none;
border-radius: 6px;
font-size: 14px;
font-weight: 600;
cursor: pointer;
transition: all 0.3s ease;
text-decoration: none;
display: inline-flex;
align-items: center;
gap: 8px;
}
.btn-download {
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
color: white;
}
.btn-download:hover {
transform: translateY(-2px);
box-shadow: 0 5px 15px rgba(102, 126, 234, 0.3);
}
.btn-delete {
background: #dc3545;
color: white;
}
.btn-delete:hover {
background: #c82333;
transform: translateY(-2px);
box-shadow: 0 5px 15px rgba(220, 53, 69, 0.3);
}
.empty-state {
text-align: center;
padding: 60px 20px;
background: white;
border-radius: 12px;
box-shadow: 0 5px 20px rgba(0, 0, 0, 0.1);
}
.empty-state-icon { font-size: 64px; margin-bottom: 20px; }
.empty-state-text {
font-size: 18px;
color: #666;
margin-bottom: 20px;
}
.empty-state-link {
display: inline-block;
padding: 12px 24px;
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
color: white;
text-decoration: none;
border-radius: 6px;
font-weight: 600;
transition: all 0.3s ease;
}
.empty-state-link:hover {
transform: translateY(-2px);
box-shadow: 0 5px 15px rgba(102, 126, 234, 0.3);
}
.alert {
padding: 15px 20px;
border-radius: 8px;
margin-bottom: 20px;
font-size: 14px;
}
.alert.success {
background: #d4edda;
color: #155724;
border: 1px solid #c3e6cb;
}
.alert.error {
background: #f8d7da;
color: #721c24;
border: 1px solid #f5c6cb;
}
@media (max-width: 768px) {
.header { flex-direction: column; gap: 20px; }
.header-actions { justify-content: center; flex-wrap: wrap; }
.job-header { flex-direction: column; align-items: flex-start; gap: 10px; }
.job-info { grid-template-columns: 1fr; }
}
</style>
</head>
<body>
<div class="container">
<div class="header">
<div class="header-info">
<div class="logo"><img src="/static/trbc-logo-full.png" alt="Logo"></div>
<div class="header-text">
<h1>Jobs Dashboard</h1>
<p>Monitor your PDF processing jobs</p>
</div>
</div>
<div class="header-actions">
<a href="/" class="nav-link">Upload Files</a>
<a href="/logout" class="nav-link logout-btn">Logout</a>
</div>
</div>
{% with messages = get_flashed_messages(with_categories=true) %}
{% if messages %}
{% for category, message in messages %}
<div class="alert {{ category }}">{{ message }}</div>
{% endfor %}
{% endif %}
{% endwith %}
<div class="jobs-container">
{% if jobs %}
{% for job_id, job in jobs.items() %}
<div class="job-card">
<div class="job-header">
<div>
<div class="job-title">Job {{ job_id[:8] }}</div>
<div class="job-meta">Created: {{ job.created_at }}</div>
</div>
<div class="status-badge status-{{ job.status }}">{{ job.status }}</div>
</div>
<div class="job-body">
<div class="job-info">
<div class="info-item">
<div class="info-label">Total Files</div>
<div class="info-value">{{ job.files|length }}</div>
</div>
<div class="info-item">
<div class="info-label">Status</div>
<div class="info-value" style="color: {% if job.status == 'completed' %}#558b2f{% elif job.status == 'processing' %}#00897b{% elif job.status == 'error' %}#c62828{% else %}#f57f17{% endif %};">
{% if job.status == 'completed' %}Completed{% elif job.status == 'processing' %}Processing{% elif job.status == 'error' %}Error{% else %}Queued{% endif %}
</div>
</div>
</div>
{% if job.status == 'processing' and job.progress %}
<div>
<div class="info-label">Progress</div>
<div class="progress-bar">
<div class="progress-fill" id="progress-{{ job_id }}"></div>
</div>
<div class="progress-text" id="progress-text-{{ job_id }}">{{ job.progress }}</div>
</div>
{% endif %}
{% if job.zip_contents %}
<div class="zip-contents">
{% for zip_name, pdf_files in job.zip_contents.items() %}
<div class="zip-toggle" onclick="toggleDetails(this)">
<span>ZIP: {{ zip_name }} ({{ pdf_files|length }} files)</span>
<span>></span>
</div>
<div class="zip-details">
<ul class="file-list">
{% for pdf_file in pdf_files %}
<li>{{ pdf_file }}</li>
{% endfor %}
</ul>
</div>
{% endfor %}
</div>
{% endif %}
{% if job.status == 'completed' %}
{% if job.skipped and job.skipped|length > 0 %}
<div class="skipped-section">
<div class="skipped-toggle" onclick="toggleSkipped(this)">
<span>Skipped Files ({{ job.skipped|length }})</span>
<span>></span>
</div>
<div class="skipped-details">
<ul class="file-list">
{% for skip_info in job.skipped %}
<li><strong>{{ skip_info[0] }}</strong>: {{ skip_info[1] }}</li>
{% endfor %}
</ul>
</div>
</div>
{% endif %}
<div class="action-buttons">
{% if job.zip_name %}
<a href="/download/{{ job.zip_name }}" class="btn btn-download">Download ZIP</a>
{% else %}
<span style="color: #999; font-size: 14px;">No files were successfully processed</span>
{% endif %}
<form method="post" action="/delete/{{ job_id }}" style="display: contents;">
<button type="submit" class="btn btn-delete" onclick="return confirm('Are you sure? This cannot be undone.')">Delete Job</button>
</form>
</div>
{% endif %}
</div>
</div>
{% endfor %}
{% else %}
<div class="empty-state">
<div class="empty-state-icon">No Jobs</div>
<div class="empty-state-text">No jobs yet</div>
<a href="/" class="empty-state-link">Upload Files to Get Started</a>
</div>
{% endif %}
</div>
</div>
<script>
let previousJobStatuses = {};
function toggleDetails(element) {
const details = element.nextElementSibling;
const arrow = element.querySelector('span:last-child');
if (details.style.display === 'block') {
details.style.display = 'none';
arrow.textContent = '>';
} else {
details.style.display = 'block';
arrow.textContent = 'v';
}
}
function toggleSkipped(element) {
const details = element.nextElementSibling;
const arrow = element.querySelector('span:last-child');
if (details.style.display === 'block') {
details.style.display = 'none';
arrow.textContent = '>';
} else {
details.style.display = 'block';
arrow.textContent = 'v';
}
}
function updateJobs() {
fetch('/api/jobs', { credentials: 'same-origin' })
.then(response => {
if (!response.ok) throw new Error(`HTTP ${response.status}`);
return response.json();
})
.then(data => {
const jobs = Object.entries(data);
// Check for job completions
let hasNewCompletion = false;
if (jobs.length > 0) {
jobs.forEach(([jobId, job]) => {
if (job.status === 'completed' && previousJobStatuses[jobId] === 'processing') {
hasNewCompletion = true;
}
previousJobStatuses[jobId] = job.status;
});
}
if (hasNewCompletion) {
setTimeout(() => { window.location.href = '/completed-jobs'; }, 500);
return;
}
// Update progress bars for processing jobs
jobs.forEach(([jobId, job]) => {
if (job.status === 'processing' && job.progress) {
const progressBar = document.getElementById(`progress-${jobId}`);
const progressText = document.getElementById(`progress-text-${jobId}`);
if (progressBar) {
const match = job.progress.match(/(\d+)\/(\d+)/);
if (match) {
const current = parseInt(match[1]);
const total = parseInt(match[2]);
const percentage = (current / total) * 100;
progressBar.style.width = percentage + '%';
}
}
if (progressText) {
progressText.textContent = job.progress;
}
}
});
})
.catch(err => console.error('Error updating jobs:', err));
}
// Update every 2 seconds
setInterval(updateJobs, 2000);
updateJobs(); // Initial update
</script>
</body>
</html>
''', jobs=job_queue)
@app.route('/api/jobs')
@login_required
def api_jobs():
return jsonify(job_queue)
@app.route('/download/<filename>')
@login_required
def download(filename):
"""Download a completed job's ZIP file with path traversal protection"""
# Prevent path traversal attacks
if '..' in filename or '/' in filename or '\\' in filename:
return "Invalid filename", 400
# Security check: only allow downloading files that belong to completed jobs
with job_lock:
for job_id, job in job_queue.items():
if job.get('status') == 'completed' and job.get('zip_name') == filename:
# Use ARCHIVE_FOLDER instead of UPLOAD_FOLDER
file_path = os.path.join(app.config['ARCHIVE_FOLDER'], filename)
# Verify the resolved path is within ARCHIVE_FOLDER
resolved_path = os.path.abspath(file_path)
archive_folder = os.path.abspath(app.config['ARCHIVE_FOLDER'])
if not resolved_path.startswith(archive_folder):
return "Access denied", 403
if os.path.exists(resolved_path):
return send_from_directory(app.config['ARCHIVE_FOLDER'], filename, as_attachment=True)
return "File not found or access denied", 404
@app.route('/delete/<job_id>', methods=['POST'])
@login_required
def delete_job(job_id):
import sys
print(f"DEBUG: delete_job called for job_id: {job_id}", file=sys.stderr, flush=True)
print(f"DEBUG: delete_job called for job_id: {job_id}", flush=True)
try:
print(f"DEBUG: Acquiring job_lock", file=sys.stderr, flush=True)
with job_lock:
print(f"DEBUG: Lock acquired, checking if job exists", file=sys.stderr, flush=True)
if job_id in job_queue:
job = job_queue[job_id]
print(f"DEBUG: Job found with status: {job.get('status')}", file=sys.stderr, flush=True)
# Only allow deletion of completed jobs
if job.get('status') == 'completed':
print(f"DEBUG: Job is completed, proceeding with deletion", file=sys.stderr, flush=True)
# Clean up the ZIP file from archives folder
if job.get('zip_name'):
print(f"DEBUG: ARCHIVE_FOLDER config: {app.config.get('ARCHIVE_FOLDER')}", file=sys.stderr, flush=True)
zip_path = os.path.join(app.config['ARCHIVE_FOLDER'], job['zip_name'])
print(f"DEBUG: Attempting to delete ZIP at: {zip_path}", file=sys.stderr, flush=True)
if os.path.exists(zip_path):
try:
os.remove(zip_path)
print(f"DEBUG: Deleted archive file: {zip_path}", file=sys.stderr, flush=True)
except Exception as e:
print(f"ERROR: Failed to delete archive: {e}", file=sys.stderr, flush=True)
import traceback
traceback.print_exc(file=sys.stderr)
else:
print(f"DEBUG: ZIP file does not exist: {zip_path}", file=sys.stderr, flush=True)
# Clean up any remaining uploaded files
print(f"DEBUG: Cleaning up {len(job.get('files', []))} uploaded files", file=sys.stderr, flush=True)
for file_info in job.get('files', []):
if 'path' in file_info and os.path.exists(file_info['path']):
try:
os.remove(file_info['path'])
print(f"DEBUG: Deleted uploaded file: {file_info['path']}", file=sys.stderr, flush=True)
except Exception as e:
print(f"ERROR: Failed to delete uploaded file: {e}", file=sys.stderr, flush=True)
# Remove the job from the queue
print(f"DEBUG: Removing job from queue", file=sys.stderr, flush=True)
del job_queue[job_id]
print(f"DEBUG: Saving jobs to disk", file=sys.stderr, flush=True)
_save_jobs_unlocked() # Use unlocked version since we already hold the lock
print(f"DEBUG: Job deletion complete", file=sys.stderr, flush=True)
else:
print(f"DEBUG: Job status is not completed: {job.get('status')}", file=sys.stderr, flush=True)
return "Only completed jobs can be deleted", 400
else:
print(f"DEBUG: Job not found in queue", file=sys.stderr, flush=True)
return "Job not found", 404
except Exception as e:
print(f"ERROR: Exception in delete_job: {e}", file=sys.stderr, flush=True)
print(f"ERROR: Exception in delete_job: {e}", flush=True)
import traceback
traceback.print_exc(file=sys.stderr)
traceback.print_exc()
return f"Error deleting job: {str(e)}", 500
print(f"DEBUG: Redirecting to /jobs", file=sys.stderr, flush=True)
try:
return redirect('/jobs')
except Exception as e:
print(f"ERROR: Redirect failed: {e}", file=sys.stderr, flush=True)
return "Job deleted but redirect failed", 200
@app.route('/completed-jobs')
@login_required
def completed_jobs():
# Show ALL jobs with their statuses for debugging
all_jobs = job_queue
return render_template_string('''
<!DOCTYPE html>
<html>
<head>
<title>All Jobs Status</title>
<style>
body { font-family: Arial, sans-serif; background-color: #f4f4f4; margin: 0; padding: 20px; text-align: center; }
img { margin-bottom: 20px; }
h1 { color: #333; }
.job { background-color: #fff; margin: 10px auto; padding: 15px; border-radius: 10px; box-shadow: 0 0 10px rgba(0,0,0,0.1); max-width: 1000px; text-align: left; }
.status { padding: 5px 10px; border-radius: 5px; color: white; font-weight: bold; }
.status.completed { background-color: #28a745; }
.status.processing { background-color: #17a2b8; }
.status.error { background-color: #dc3545; }
.progress-text { color: #17a2b8; font-style: italic; margin-left: 10px; }
.download-btn { background-color: #007bff; color: white; text-decoration: none; padding: 8px 16px; border-radius: 5px; margin: 5px; display: inline-block; }
.download-btn:hover { background-color: #0056b3; }
.delete-btn { background-color: #dc3545; color: white; border: none; padding: 8px 16px; border-radius: 5px; margin: 5px; cursor: pointer; }
.delete-btn:hover { background-color: #c82333; }
.flash { padding: 10px; margin: 10px 0; border-radius: 5px; text-align: center; }
.flash.success { background-color: #d4edda; color: #155724; border: 1px solid #c3e6cb; }
.flash.error { background-color: #f8d7da; color: #721c24; border: 1px solid #f5c6cb; }
.logout { position: absolute; top: 20px; right: 20px; background-color: #dc3545; color: white; text-decoration: none; padding: 10px 20px; border-radius: 5px; }
.logout:hover { background-color: #c82333; }
.nav-links { margin-bottom: 20px; }
.nav-links a { color: #007bff; text-decoration: none; padding: 10px 20px; background-color: #f8f9fa; border-radius: 5px; margin: 0 10px; }
.nav-links a:hover { background-color: #e9ecef; }
.nav-btn { background-color: #007bff; color: white; text-decoration: none; padding: 10px 20px; border-radius: 5px; display: inline-block; margin: 0 10px; }
.nav-btn:hover { background-color: #0056b3; }
.job-stats { background-color: #e9ecef; padding: 10px; border-radius: 5px; margin-bottom: 15px; }
.file-count { color: #17a2b8; font-weight: bold; }
.zip-content { background-color: #f8f9fa; padding: 10px; margin: 5px 0; border-radius: 5px; border-left: 4px solid #007bff; }
.zip-toggle { cursor: pointer; background-color: #e9ecef; padding: 8px; margin: 5px 0; border-radius: 5px; border: 1px solid #dee2e6; }
.zip-toggle:hover { background-color: #dee2e6; }
.zip-details { display: none; margin-top: 10px; }
.skipped-section { background-color: #fff3cd; border: 1px solid #ffeaa7; border-radius: 5px; padding: 10px; margin: 10px 0; }
.skipped-toggle { cursor: pointer; background-color: #ffeaa7; padding: 8px; margin: 5px 0; border-radius: 5px; border: 1px solid #ffc107; font-weight: bold; color: #856404; }
.skipped-toggle:hover { background-color: #ffc107; }
.skipped-details { display: none; margin-top: 10px; }
ul { list-style-type: none; padding: 0; }
li { background-color: #ffffff; margin: 2px 0; padding: 5px; border-radius: 3px; }
</style>
</head>
<body>
<a href="/logout" class="logout">Logout</a>
<img src="/static/trbc-logo-full.png" alt="Logo" width="200">
<h1>All Jobs Status</h1>
<div class="nav-links">
<a href="/" class="nav-btn"><- Upload Files</a>
<a href="/jobs" class="nav-btn">View All Jobs -></a>
</div>
{% with messages = get_flashed_messages(with_categories=true) %}
{% if messages %}
{% for category, message in messages %}
<div class="flash {{ category }}">{{ message }}</div>
{% endfor %}
{% endif %}
{% endwith %}
{% for job_id, job in all_jobs.items() %}
<div class="job">
<h3>Job {{ job_id[:8] }} - {{ job.created_at if job.created_at else 'Unknown Date' }}</h3>
<div class="job-stats">
<span class="status {{ job.status }}">{{ job.status.title() }}</span>
<span class="file-count">{{ job.processed_files|selectattr('0', 'equalto', 'success')|list|length }} files processed</span>
{% if job.progress %}
<span class="progress-text">Progress: {{ job.progress }}</span>
{% endif %}
{% if job.skipped %}
<span style="color: #856404; font-weight: bold;">{{ job.skipped|length }} files skipped</span>
{% endif %}
</div>
{% if job.zip_contents %}
<p><strong>Original ZIP Contents:</strong></p>
{% for zip_name, pdf_files in job.zip_contents.items() %}
<div class="zip-content">
<div class="zip-toggle" onclick="toggleZipDetails(this)">
<strong>{{ zip_name }}</strong> ({{ pdf_files|length }} files) >
</div>
<div class="zip-details">
<ul>
{% for pdf_file in pdf_files %}
<li>{{ pdf_file }}</li>
{% endfor %}
</ul>
</div>
</div>
{% endfor %}
{% endif %}
{% if job.zip_name %}
<p><strong>Download:</strong> <a href="/download/{{ job.zip_name }}" class="download-btn">Download Organized ZIP ({{ job.zip_name }})</a></p>
{% endif %}
{% if job.skipped %}
<div class="skipped-section">
<div class="skipped-toggle" onclick="toggleSkippedDetails(this)">
Skipped Files ({{ job.skipped|length }}) >
</div>
<div class="skipped-details">
<ul>
{% for skip_info in job.skipped %}
<li><strong>{{ skip_info[0] }}</strong>: {{ skip_info[1] }}
{% if skip_info|length > 2 and skip_info[2] %}
<br><details><summary>Extracted Text</summary><pre style="white-space: pre-wrap; background: #f8f9fa; border: 1px solid #eee; padding: 5px;">{{ skip_info[2] }}</pre></details>
{% endif %}
</li>
{% endfor %}
</ul>
</div>
</div>
{% endif %}
<form method="post" action="/delete/{{ job_id }}" style="display: inline;">
<button type="submit" class="delete-btn" onclick="return confirm('Are you sure you want to permanently delete this completed job and its files?')">Delete Job</button>
</form>
</div>
{% endfor %}
{% if not jobs %}
<p>No completed jobs yet. <a href="/">Upload some files</a> to get started.</p>
{% endif %}
<script>
// Collapsible section functions
function toggleZipDetails(element) {
const details = element.nextElementSibling;
const isVisible = details.style.display === 'block';
details.style.display = isVisible ? 'none' : 'block';
element.innerHTML = element.innerHTML.replace(isVisible ? ' v' : ' >', isVisible ? ' >' : ' v');
}
function toggleSkippedDetails(element) {
const details = element.nextElementSibling;
const isVisible = details.style.display === 'block';
details.style.display = isVisible ? 'none' : 'block';
element.innerHTML = element.innerHTML.replace(isVisible ? ' v' : ' >', isVisible ? ' >' : ' v');
}
</script>
</body>
</html>
''', all_jobs=all_jobs)
if __name__ == '__main__':
app.run(debug=True, port=3000)
Reference in new issue View Git Blame Copy Permalink