app.py

# -*- encoding: utf-8 -*-
# @Author: SWHL
# @Contact: liekkaskono@163.com
import hashlib
import io

import numpy as np
import pandas as pd
import pypdfium2
import streamlit as st
from PIL import Image
from rapid_latex_ocr import LatexOCR
from streamlit_drawable_canvas import st_canvas

MAX_WIDTH = 800
MAX_HEIGHT = 1000

st.set_page_config(layout="wide")


@st.cache_resource()
def load_model_cached():
    return LatexOCR()


def get_canvas_hash(pil_image):
    return hashlib.md5(pil_image.tobytes()).hexdigest()


def open_pdf(pdf_file):
    stream = io.BytesIO(pdf_file.getvalue())
    return pypdfium2.PdfDocument(stream)


@st.cache_data()
def page_count(pdf_file):
    doc = open_pdf(pdf_file)
    return len(doc)


@st.cache_data()
def get_page_image(pdf_file, page_num, dpi=96):
    doc = open_pdf(pdf_file)
    renderer = doc.render(
        pypdfium2.PdfBitmap.to_pil,
        page_indices=[page_num - 1],
        scale=dpi / 72,
    )
    png = list(renderer)[0]
    png_image = png.convert("RGB")
    return png_image


@st.cache_data()
def get_uploaded_image(in_file):
    if isinstance(in_file, Image.Image):
        return in_file.convert("RGB")
    return Image.open(in_file).convert("RGB")


def resize_image(pil_image):
    if pil_image is None:
        return
    pil_image.thumbnail((MAX_WIDTH, MAX_HEIGHT), Image.Resampling.LANCZOS)


@st.cache_data()
def get_image_size(pil_image):
    if pil_image is None:
        return MAX_HEIGHT, MAX_WIDTH
    height, width = pil_image.height, pil_image.width
    return height, width


if __name__ == "__main__":
    st.markdown(
        "<h1 style='text-align: center;'><a href='https://github.com/RapidAI/RapidLatexOCR' style='text-decoration: none'>Rapid ⚡︎ LaTeX OCR</a></h1>",
        unsafe_allow_html=True,
    )
    st.markdown(
        """
    <p align="center">
        <a href=""><img src="https://img.shields.io/badge/Python->=3.6,<3.12-aff.svg"></a>
        <a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-pink.svg"></a>
        <a href="https://pepy.tech/project/rapid_latex_ocr"><img src="https://static.pepy.tech/personalized-badge/rapid_latex_ocr?period=total&units=abbreviation&left_color=grey&right_color=blue&left_text=Downloads"></a>
        <a href="https://pypi.org/project/rapid_latex_ocr/"><img alt="PyPI" src="https://img.shields.io/pypi/v/rapid_latex_ocr"></a>
        <a href="https://semver.org/"><img alt="SemVer2.0" src="https://img.shields.io/badge/SemVer-2.0-brightgreen"></a>
        <a href="https://github.com/psf/black"><img src="https://img.shields.io/badge/code%20style-black-000000.svg"></a>
        <a href="https://github.com/RapidAI/RapidLatexOCR"><img src="https://img.shields.io/badge/Github-link-brightgreen.svg"></a>
    </p>
    """,
        unsafe_allow_html=True,
    )

    col1, col2 = st.columns([0.5, 0.5])

    in_file = st.sidebar.file_uploader(
        "PDF file or image:", type=["pdf", "png", "jpg", "jpeg", "gif", "webp"]
    )

    if in_file is None:
        st.stop()

    filetype = in_file.type
    if "pdf" in filetype:
        page_count = page_count(in_file)
        page_number = st.sidebar.number_input(
            f"Page number out of {page_count}:",
            min_value=1,
            value=1,
            max_value=page_count,
        )
        pil_image = get_page_image(in_file, page_number)
    else:
        pil_image = get_uploaded_image(in_file)

    resize_image(pil_image)
    canvas_hash = get_canvas_hash(pil_image) if pil_image else "canvas"

    model = load_model_cached()
    with col1:
        canvas_result = st_canvas(
            fill_color="rgba(255, 165, 0, 0.1)",
            stroke_width=1,
            stroke_color="#FFAA00",
            background_color="#FFF",
            background_image=pil_image,
            update_streamlit=True,
            height=get_image_size(pil_image)[0],
            width=get_image_size(pil_image)[1],
            drawing_mode="rect",
            point_display_radius=0,
            key=canvas_hash,
        )

    if canvas_result.json_data is not None:
        objects = pd.json_normalize(canvas_result.json_data["objects"])
        bbox_list = None
        if objects.shape[0] > 0:
            boxes = objects[objects["type"] == "rect"][
                ["left", "top", "width", "height"]
            ]
            boxes["right"] = boxes["left"] + boxes["width"]
            boxes["bottom"] = boxes["top"] + boxes["height"]
            bbox_list = boxes[["left", "top", "right", "bottom"]].values.tolist()

        if bbox_list:
            with col2:
                bbox_nums = len(bbox_list)
                for i, bbox in enumerate(bbox_list):
                    input_img = pil_image.crop(bbox)
                    rec_res, elapse = model(np.array(input_img))
                    st.markdown(f"#### {i + 1}")
                    st.latex(rec_res)
                    st.code(rec_res)