"""
context_acquisition.py

Functions for acquiring context from various sources including PDF text extraction,
GitHub profiles, and job posting text.
"""

import re
import logging
import io
import os
import json
from pathlib import Path
from datetime import datetime
import PyPDF2

# pylint: disable=broad-exception-caught

# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)


def check_default_linkedin_pdf():
    """Check if default LinkedIn PDF exists in data directory."""

    # Get the project root directory (parent of functions directory)
    project_root = Path(__file__).parent.parent
    default_pdf = f'{project_root}/data/linkedin_profile.pdf'

    if not Path(default_pdf).exists():
        logger.warning("Default LinkedIn PDF not found at %s", default_pdf)

        return False, None

    return True, default_pdf


def extract_text_from_linkedin_pdf(pdf_file) -> dict:
    """
    Extract and structure text content from an uploaded LinkedIn resume export PDF file
    for optimal LLM processing.

    Args:
        pdf_file: The file path string to the uploaded PDF file

    Returns:
        dict: Dictionary containing extraction status, structured text content, and metadata

    Example:
        {
            "status": "success",
            "structured_text": {
                "sections": {...},
                "full_text": "...",
                "llm_formatted": "...",
                "summary": "..."
            },
            "metadata": {...}
        }
    """
    if pdf_file is None:
        return {"status": "error", "message": "No PDF file provided"}

    try:
        # Get filename from path
        filename = os.path.basename(pdf_file)

        # Read the PDF file from the file path
        with open(pdf_file, 'rb') as file:
            file_content = file.read()
            file_size = len(file_content)

        # Create PDF reader from the file content
        pdf_reader = PyPDF2.PdfReader(io.BytesIO(file_content))

        # Extract text from all pages
        extracted_text = ""
        num_pages = len(pdf_reader.pages)

        for page_num in range(num_pages):
            try:
                page = pdf_reader.pages[page_num]
                page_text = page.extract_text()
                extracted_text += page_text + "\n\n"

            except Exception as e:
                logger.warning("Error extracting text from page %d: %s", page_num + 1, str(e))

                continue

        # Clean and structure the extracted text for LLM consumption
        structured_content = _structure_resume_text(extracted_text)

        if not structured_content["full_text"].strip():
            return {
                "status": "warning",
                "structured_text": structured_content,
                "metadata": {
                    "filename": filename,
                    "file_size": file_size,
                    "pages": num_pages
                },
                "message": "PDF processed but no text content was extracted"
            }

        logger.info(
            "Successfully extracted and structured %d characters from %s",
            len(structured_content['full_text']),
            filename
        )

        result = {
            "status": "success",
            "structured_text": structured_content,
            "metadata": {
                "filename": filename,
                "file_size": file_size,
                "pages": num_pages,
                "sections_found": list(structured_content["sections"].keys())
            },
            "message": f"Text extracted and structured successfully from {num_pages} pages"
        }

        # Save results to JSON file
        try:
            linkedin_profile_dir = Path(__file__).parent.parent / "data" / "linkedin_profile"
            linkedin_profile_dir.mkdir(parents=True, exist_ok=True)

            # Create timestamped filename
            timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
            output_file = linkedin_profile_dir / f"linkedin_resume_{timestamp}.json"

            with open(output_file, 'w', encoding='utf-8') as f:
                json.dump(result, f, indent=2, ensure_ascii=False)

            logger.info("LinkedIn resume extraction saved to %s", output_file)

        except Exception as save_error:
            logger.warning("Failed to save LinkedIn resume extraction to file: %s", str(save_error))

        return result

    except Exception as e:
        logger.error("Error processing PDF file: %s", str(e))

        return {
            "status": "error",
            "message": f"Failed to extract text from PDF: {str(e)}"
        }


def _structure_resume_text(text: str) -> dict:
    """
    Structure resume text into logical sections for optimal LLM processing.

    Args:
        text (str): Raw extracted text from PDF

    Returns:
        dict: Structured text with sections, full text, and summary
    """
    if not text:
        return {
            "sections": {},
            "full_text": "",
            "llm_formatted": "",
            "summary": "",
            "format": "structured_resume",
            "word_count": 0,
            "section_count": 0
        }

    # Clean the text first
    cleaned_text = _clean_extracted_text(text)

    # Define section patterns (common LinkedIn export sections)
    section_patterns = {
        "contact_info": r"(?i)(contact|personal|profile)\s*(?:information)?",
        "summary": r"(?i)(summary|about|overview|profile)",
        "experience": r"(?i)(experience|work|employment|professional)",
        "education": r"(?i)(education|academic|university|college|school)",
        "skills": r"(?i)(skills|competencies|technologies|technical)",
        "certifications": r"(?i)(certification|certificate|license)",
    }

    # Split text into lines for processing
    lines = cleaned_text.split('\n')
    sections = {}
    current_section = "general"
    current_content = []

    for line in lines:
        line = line.strip()

        if not line:
            continue

        # Check if line is a section header
        section_found = None

        for section_name, pattern in section_patterns.items():
            if re.match(pattern, line):

                section_found = section_name
                break

        if section_found:

            # Save previous section content
            if current_content:
                sections[current_section] = '\n'.join(current_content)

            # Start new section
            current_section = section_found
            current_content = [line]

        else:
            current_content.append(line)

    # Save the last section
    if current_content:
        sections[current_section] = '\n'.join(current_content)

    # Create a structured summary for LLM context
    summary_parts = []

    if "contact_info" in sections:
        summary_parts.append(f"CONTACT: {sections['contact_info'][:200]}...")

    if "summary" in sections:
        summary_parts.append(f"SUMMARY: {sections['summary']}")

    if "experience" in sections:
        summary_parts.append(f"EXPERIENCE: {sections['experience'][:300]}...")

    if "education" in sections:
        summary_parts.append(f"EDUCATION: {sections['education']}")

    if "skills" in sections:
        summary_parts.append(f"SKILLS: {sections['skills']}")

    # Create LLM-optimized format
    llm_formatted_text = _format_for_llm(sections)

    return {
        "sections": sections,
        "full_text": cleaned_text,
        "llm_formatted": llm_formatted_text,
        "summary": '\n\n'.join(summary_parts),
        "format": "structured_resume",
        "word_count": len(cleaned_text.split()),
        "section_count": len(sections)
    }


def _format_for_llm(sections: dict) -> str:
    """
    Format the resume sections in an optimal way for LLM processing.

    Args:
        sections (dict): Structured sections
        full_text (str): Full cleaned text

    Returns:
        str: LLM-optimized formatted text
    """
    formatted_parts = ["=== RESUME CONTENT ===\n"]

    # Prioritize sections in logical order for LLM
    priority_order = ["summary", "contact_info", "experience", "education", "skills",
                     "certifications", "projects", "achievements", "languages", "volunteer"]

    # Add prioritized sections
    for section_name in priority_order:
        if section_name in sections:

            formatted_parts.append(f"[{section_name.upper().replace('_', ' ')}]")
            formatted_parts.append(sections[section_name])
            formatted_parts.append("")  # Empty line between sections

    # Add any remaining sections
    for section_name, content in sections.items():
        if section_name not in priority_order and section_name != "general":

            formatted_parts.append(f"[{section_name.upper().replace('_', ' ')}]")
            formatted_parts.append(content)
            formatted_parts.append("")

    # Add general content if exists
    if "general" in sections:

        formatted_parts.append("[ADDITIONAL INFORMATION]")
        formatted_parts.append(sections["general"])

    formatted_parts.append("\n=== END RESUME ===")

    return '\n'.join(formatted_parts)


def _clean_extracted_text(text: str) -> str:
    """
    Clean and normalize extracted text from PDF for better LLM processing.

    Args:
        text (str): Raw extracted text

    Returns:
        str: Cleaned text optimized for LLM consumption
    """
    if not text:
        return ""

    # Remove excessive whitespace and normalize line endings
    text = re.sub(r'\r\n', '\n', text)
    text = re.sub(r'\r', '\n', text)

    # Split into lines and clean each line
    lines = text.split('\n')
    cleaned_lines = []

    for line in lines:

        # Strip whitespace
        cleaned_line = line.strip()

        # Skip empty lines and very short lines (likely artifacts)
        if len(cleaned_line) < 2:
            continue

        # Remove common PDF artifacts
        cleaned_line = re.sub(r'^\d+$', '', cleaned_line)  # Page numbers
        cleaned_line = re.sub(r'^[|\-_=]+$', '', cleaned_line)  # Separator lines

        if cleaned_line:
            cleaned_lines.append(cleaned_line)

    # Join lines and normalize spacing
    cleaned_text = '\n'.join(cleaned_lines)

    # Normalize multiple spaces to single spaces
    cleaned_text = re.sub(r' +', ' ', cleaned_text)

    # Normalize multiple newlines to maximum of 2
    cleaned_text = re.sub(r'\n{3,}', '\n\n', cleaned_text)

    return cleaned_text.strip()


def get_llm_context_from_resume(extraction_result: dict) -> str:
    """
    Extract the best formatted text for LLM context from the extraction result.

    Args:
        extraction_result (dict): Result from extract_text_from_linkedin_pdf

    Returns:
        str: Formatted text ready for LLM context
    """
    if extraction_result.get("status") != "success":
        return ""

    structured_text = extraction_result.get("structured_text", {})

    # Return the LLM-formatted version if available, otherwise fall back to full text
    return structured_text.get("llm_formatted", structured_text.get("full_text", ""))