from fastapi import FastAPI
from fastapi.responses import RedirectResponse
import fitz  # PyMuPDF
import docx
import pptx
import openpyxl
import io
from PIL import Image
import gradio as gr
from transformers import pipeline

# Load models
summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
image_captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")

app = FastAPI()

# -------------------------
# File Text Extractors
# -------------------------

def extract_text_from_pdf(file):
    try:
        file.seek(0)
        data = file.read()
        with fitz.open(stream=data, filetype="pdf") as doc:
            return "\n".join([page.get_text() for page in doc])
    except Exception as e:
        return f"❌ PDF error: {e}"

def extract_text_from_docx(file):
    try:
        file.seek(0)
        data = file.read()
        doc = docx.Document(io.BytesIO(data))
        return "\n".join(p.text for p in doc.paragraphs if p.text.strip())
    except Exception as e:
        return f"❌ DOCX error: {e}"

def extract_text_from_pptx(file):
    try:
        file.seek(0)
        data = file.read()
        prs = pptx.Presentation(io.BytesIO(data))
        text = []
        for slide in prs.slides:
            for shape in slide.shapes:
                if hasattr(shape, "text"):
                    text.append(shape.text)
        return "\n".join(text)
    except Exception as e:
        return f"❌ PPTX error: {e}"

def extract_text_from_xlsx(file):
    try:
        file.seek(0)
        data = file.read()
        wb = openpyxl.load_workbook(io.BytesIO(data))
        text = []
        for sheet in wb.sheetnames:
            ws = wb[sheet]
            for row in ws.iter_rows(values_only=True):
                line = " ".join(str(cell) for cell in row if cell)
                text.append(line)
        return "\n".join(text)
    except Exception as e:
        return f"❌ XLSX error: {e}"

# -------------------------
# Main Logic
# -------------------------

def summarize_document(file):
    filename = file.name.lower()

    if filename.endswith(".pdf"):
        text = extract_text_from_pdf(file)
    elif filename.endswith(".docx"):
        text = extract_text_from_docx(file)
    elif filename.endswith(".pptx"):
        text = extract_text_from_pptx(file)
    elif filename.endswith(".xlsx"):
        text = extract_text_from_xlsx(file)
    else:
        return "❌ Unsupported file format."

    if not text.strip():
        return "❗ No extractable text."

    try:
        summary = summarizer(text[:3000], max_length=150, min_length=30, do_sample=False)
        return f"📄 Summary:\n{summary[0]['summary_text']}"
    except Exception as e:
        return f"⚠️ Summarization error: {e}"

def interpret_image(image):
    try:
        return f"🖼️ Caption:\n{image_captioner(image)[0]['generated_text']}"
    except Exception as e:
        return f"⚠️ Image captioning error: {e}"

# -------------------------
# Gradio Interfaces
# -------------------------

doc_summary = gr.Interface(
    fn=summarize_document,
    inputs=gr.File(label="Upload a Document"),
    outputs="text",
    title="📄 Document Summarizer"
)

img_caption = gr.Interface(
    fn=interpret_image,
    inputs=gr.Image(type="pil", label="Upload an Image"),
    outputs="text",
    title="🖼️ Image Captioning"
)

# -------------------------
# Launch via FastAPI
# -------------------------

demo = gr.TabbedInterface([doc_summary, img_caption], ["Document Summary", "Image Captioning"])
app = gr.mount_gradio_app(app, demo, path="/")

@app.get("/")
def root():
    return RedirectResponse(url="/")