"""
utils.py — PDF extraction, Gemini LLM, and Manim code helpers.
"""

from __future__ import annotations

import re

from google import genai
from google.genai import types


# ── PDF Text Extraction ───────────────────────────────────────────────────────

def extract_pdf_text(pdf_path: str) -> str:
    """Extract plain text from a PDF using pypdf."""
    from pypdf import PdfReader

    reader = PdfReader(pdf_path)
    pages = []
    for page in reader.pages:
        text = page.extract_text()
        if text:
            pages.append(text)
    return "\n\n".join(pages)


# ── Gemini LLM ────────────────────────────────────────────────────────────────

def generate_manim_code(prompt_text: str, api_key: str) -> str:
    """Stream Manim code from Gemini 3 Flash Preview and return it as a string."""

    client = genai.Client(api_key=api_key)
    model = "gemini-3-flash-preview"

    # Robust system prompt
    system_prompt = """
You are an expert Python developer and Manim animation engineer.
Always produce code that:
- Is fully correct and runnable with Manim v1.0+.
- Uses clear, readable structure, proper imports, and PEP8-compliant formatting.
- Produces visually correct animations based on the user's description.
- Minimizes unnecessary complexity but keeps clarity.
- Names the main scene class `OutputVideo`.
- Returns code only, without extra explanation or markdown fences.
- Handles edge cases gracefully.
- Uses comments sparingly, only when clarifying complex parts.
- When in doubt, use Google search effectively to verify facts, functions, or best practices.
Always ensure your output is precise, accurate, and complete.
"""

    contents = [
        types.Content(
            role="system",
            parts=[types.Part.from_text(text=system_prompt)]
        ),
        types.Content(
            role="user",
            parts=[types.Part.from_text(text=prompt_text)]
        )
    ]

    config = types.GenerateContentConfig(
        thinking_config=types.ThinkingConfig(
            thinking_level="HIGH"
        )
    )

    code = ""
    for chunk in client.models.generate_content_stream(
        model=model,
        contents=contents,
        config=config
    ):
        if chunk.text:
            code += chunk.text
            print(chunk.text, end="", flush=True)

    return code

# ── Manim Code Sanitisation ───────────────────────────────────────────────────

def sanitize_manim_code(raw: str) -> str:
    """
    Strip markdown fences, ensure correct imports and class name.
    """
    code = re.sub(r"^```(?:python)?\s*", "", raw.strip(), flags=re.MULTILINE)
    code = re.sub(r"\s*```$", "", code.strip(), flags=re.MULTILINE)

    if "from manim import" not in code and "import manim" not in code:
        code = "from manim import *\n\n" + code

    # Ensure class is named OutputVideo
    code = re.sub(r"class\s+\w+\s*\(\s*Scene\s*\)", "class OutputVideo(Scene)", code)

    return code