utils/helpers.py

import re
import os
import time
import logging
from pathlib import Path
from typing import Tuple

logger = logging.getLogger(__name__)


def reshape_arabic_text(text: str) -> str:
    """Reshape Arabic text for proper display."""
    try:
        import arabic_reshaper
        from bidi.algorithm import get_display
        reshaped = arabic_reshaper.reshape(text)
        bidi_text = get_display(reshaped)
        return bidi_text
    except Exception:
        return text


def validate_file(file_path: str, max_size_mb: int = 20) -> Tuple[bool, str]:
    """Validate uploaded file size and extension."""
    from config import SUPPORTED_FORMATS

    path = Path(file_path)

    if not path.exists():
        return False, "File does not exist"

    ext = path.suffix.lower()
    if ext not in SUPPORTED_FORMATS:
        return False, f"Unsupported format: {ext}. Supported: {', '.join(SUPPORTED_FORMATS)}"

    size_mb = path.stat().st_size / (1024 * 1024)
    if size_mb > max_size_mb:
        return False, f"File too large: {size_mb:.1f}MB. Maximum: {max_size_mb}MB"

    return True, "OK"


def format_file_size(size_bytes: int) -> str:
    """Human-readable file size."""
    if size_bytes < 1024:
        return f"{size_bytes} B"
    elif size_bytes < 1024 * 1024:
        return f"{size_bytes / 1024:.1f} KB"
    else:
        return f"{size_bytes / (1024 * 1024):.1f} MB"


def truncate_text(text: str, max_chars: int = 500) -> str:
    """Truncate long text for display."""
    if len(text) <= max_chars:
        return text
    return text[:max_chars] + "..."


def calculate_arabic_ratio(text: str) -> float:
    """Calculate ratio of Arabic characters in text."""
    if not text:
        return 0.0
    arabic_chars = len(re.findall(r'[\u0600-\u06FF]', text))
    return round(arabic_chars / len(text), 4)


def timer_ms(func):
    """Decorator to measure function execution time in ms."""
    def wrapper(*args, **kwargs):
        start = time.time()
        result = func(*args, **kwargs)
        elapsed = (time.time() - start) * 1000
        logger.info(f"{func.__name__} took {elapsed:.2f}ms")
        return result, elapsed
    return wrapper


def clean_arabic_text(text: str) -> str:
    """Basic Arabic text cleaning."""
    # Remove non-printable characters
    text = re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f\x7f-\x9f]', '', text)
    # Normalize whitespace
    text = re.sub(r'\s+', ' ', text).strip()
    # Remove standalone punctuation clusters
    text = re.sub(r'([^\w\s])\1{3,}', r'\1', text)
    return text


def build_summary_display(structured_doc: dict) -> str:
    """Build a human-readable summary of structured document."""
    if not structured_doc:
        return "No document processed yet."

    meta = structured_doc.get("metadata", {})
    analysis = structured_doc.get("document_analysis", {})
    entities = structured_doc.get("extracted_entities", {})
    dates = structured_doc.get("extracted_dates", [])
    financials = structured_doc.get("financial_data", {})

    lines = [
        f"📄 **Document ID:** {structured_doc.get('document_id', 'N/A')}",
        f"📁 **Filename:** {meta.get('filename', 'N/A')}",
        f"🔍 **Type:** {analysis.get('document_type', 'N/A')}",
        f"🌐 **Language:** {analysis.get('language', 'N/A')}",
        f"📊 **Pages:** {analysis.get('total_pages', 0)} | **Words:** {analysis.get('total_words', 0)}",
        f"⚙️ **Extraction:** {meta.get('extraction_source', 'N/A')} | **Confidence:** {meta.get('extraction_confidence', 0):.2%}",
        "",
        f"📅 **Dates Found:** {', '.join(dates) if dates else 'None'}",
        f"💰 **Amounts:** {', '.join(financials.get('amounts', [])) if financials.get('amounts') else 'None'}",
        f"📧 **Emails:** {', '.join(entities.get('emails', [])) if entities.get('emails') else 'None'}",
        f"📞 **Phones:** {', '.join(entities.get('phone_numbers', [])) if entities.get('phone_numbers') else 'None'}",
    ]

    return "\n".join(lines)