utils.py

import json
import time
import os
import zipfile
import io
from pathlib import Path
import streamlit as st
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
from reportlab.lib.units import inch
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.enums import TA_LEFT, TA_CENTER


def save_user_preferences(prefs):
    """Save user preferences to local file"""
    prefs_file = Path.home() / ".scriptflow_prefs.json"
    try:
        with open(prefs_file, 'w') as f:
            json.dump(prefs, f)
    except Exception:
        pass  # Fail silently if can't save


def load_user_preferences():
    """Load user preferences from local file"""
    prefs_file = Path.home() / ".scriptflow_prefs.json"
    try:
        if prefs_file.exists():
            with open(prefs_file, 'r') as f:
                return json.load(f)
    except Exception:
        pass

    # Default preferences
    return {
        'model_size_index': 1,
        'output_dir': str(Path.home() / "Transcriptions"),
        'formats': ['txt', 'srt'],
        'quality': '720p'
    }


def create_cta_section():
    """Create 🧠 VidMind CTA section"""
    st.markdown("""
    <div style='background-color: #f0f2f6; padding: 20px; border-radius: 10px; text-align: center; margin: 10px 0; color: #31333F;'>
        <h4 style='margin: 0; color: #31333F;'>🧠 Supercharge Your Learning with VidMind</h4>
        <p style='margin: 5px 0; font-size: 14px;'>Transform any content into a personalized learning experience with AI-powered summaries, flashcards, quizzes, and more.</p>
        <a href="https://github.com/yomazini/media-downloader-andtrascript" target="_blank" style="text-decoration: none;">
            <button style="background-color: #ff4b4b; color: white; border: none; padding: 10px 20px; border-radius: 5px; cursor: pointer;">
                🚀 Explore VidMind for FREE
            </button>
        </a>
    </div>
    """, unsafe_allow_html=True)


def format_file_size(bytes_size):
    """Format file size in human readable format"""
    for unit in ['B', 'KB', 'MB', 'GB']:
        if bytes_size < 1024:
            return f"{bytes_size:.1f} {unit}"
        bytes_size /= 1024
    return f"{bytes_size:.1f} TB"


def create_pdf_from_text(text, title="Transcript"):
    """Create PDF from text with basic formatting"""
    buffer = io.BytesIO()

    # Create PDF
    doc = SimpleDocTemplate(buffer, pagesize=letter,
                            rightMargin=72, leftMargin=72,
                            topMargin=72, bottomMargin=18)

    # Styles
    styles = getSampleStyleSheet()
    title_style = ParagraphStyle(
        'CustomTitle',
        parent=styles['Heading1'],
        fontSize=18,
        alignment=TA_CENTER,
        spaceAfter=30
    )

    body_style = ParagraphStyle(
        'CustomBody',
        parent=styles['Normal'],
        fontSize=11,
        alignment=TA_LEFT,
        spaceAfter=12,
        leading=16
    )

    # Build PDF content
    story = []

    # Title
    story.append(Paragraph(title, title_style))
    story.append(Spacer(1, 20))

    # Body text - split into paragraphs
    paragraphs = text.split('\n\n')
    for para in paragraphs:
        if para.strip():
            # Escape special characters for ReportLab
            para_clean = para.replace('<', '&lt;').replace(
                '>', '&gt;').replace('&', '&amp;')
            story.append(Paragraph(para_clean, body_style))

    # Build PDF
    doc.build(story)

    # Get PDF data
    pdf_data = buffer.getvalue()
    buffer.close()

    return pdf_data


def merge_transcripts(results, format_type="Plain Text", separator="=== TITLE ==="):
    """Merge multiple transcripts into one document"""
    merged_content = []

    for i, result in enumerate(results):
        title = result['title']
        text = result['text']

        if format_type == "Plain Text":
            section_header = separator.replace("TITLE", title)
            merged_content.append(f"{section_header}\n{text}")

        elif format_type == "With Timestamps":
            section_header = separator.replace(
                "TITLE", f"{title} ({result.get('duration', 0):.1f}s)")
            merged_content.append(f"{section_header}\n{text}")

        elif format_type == "Sectioned by Title":
            merged_content.append(f"# {title}\n\n{text}")

        # Add spacing between sections
        if i < len(results) - 1:
            merged_content.append("\n" + "="*50 + "\n")

    return "\n\n".join(merged_content)


def create_batch_zip(results):
    """Create ZIP file containing all transcripts"""
    zip_buffer = io.BytesIO()

    with zipfile.ZipFile(zip_buffer, 'w', zipfile.ZIP_DEFLATED) as zip_file:
        for i, result in enumerate(results):
            # Add text file
            filename = f"{i+1:02d}_{result['title'][:30]}.txt"
            # Clean filename
            filename = "".join(c for c in filename if c.isalnum()
                               or c in (' ', '-', '_', '.')).rstrip()
            zip_file.writestr(filename, result['text'])

        # Add summary file
        summary = f"Batch Export Summary\n"
        summary += f"Generated: {time.strftime('%Y-%m-%d %H:%M:%S')}\n"
        summary += f"Total Files: {len(results)}\n"
        summary += f"Total Duration: {sum(r.get('duration', 0) for r in results):.1f}s\n"
        summary += f"Total Words: {sum(len(r['text'].split()) for r in results):,}\n\n"

        summary += "Files included:\n"
        for i, result in enumerate(results, 1):
            summary += f"{i:02d}. {result['title']} ({result.get('language', 'unknown')}, {result.get('duration', 0):.1f}s)\n"

        zip_file.writestr("_SUMMARY.txt", summary)

    return zip_buffer.getvalue()