from typing import List
from mmda.parsers.symbol_scraper_parser import SymbolScraperParser
from mmda.rasterizers.rasterizer import PDF2ImageRasterizer 
from mmda.types.document import Document
from mmda.types.image import PILImage

# PDF to text
ssparser = SymbolScraperParser(sscraper_bin_path='...')
doc: Document = ssparser.parse(input_pdf_path='...pdf')

# PDF to images
pdf2img_rasterizer = PDF2ImageRasterizer()
images: List[PILImage] = pdf2img_rasterizer.rasterize(input_pdf_path='...pdf', dpi=72)

# attach those images to the document
doc.annotate_images(images=images)

import os
import json

# usually, you'll probably want to save the text & images separately:
with open('...json', 'w') as f_out:
    json.dump(doc.to_json(with_images=False), f_out, indent=4)

os.makedirs('.../', exist_ok=True)
for i, image in enumerate(doc.images):
    image.save(os.path.join('.../', f'{i}.png'))
    
    
# you can also save images as base64 strings within the JSON object
with open('...json', 'w') as f_out:
    json.dump(doc.to_json(with_images=True), f_out, indent=4)

from mmda.types.image import PILImage, pilimage

# directly from a JSON.  This should handle also the case where `images` were serialized as base64 strings.
with open('...json') as f_in:
    doc_dict = json.load(f_in)
    doc = Document.from_json(doc_dict=doc_dict)
    
# if you saved your images separately, then you'll want to reconstruct them & re-attach
images: List[PILImage] = []
for i, page in enumerate(doc.pages):
    image_path = os.path.join(outdir, f'{i}.png')
    assert os.path.exists(image_path), f'Missing file for page {i}'
    image = pilimage.open(image_path)
    images.append(image)
doc.annotate_images(images=images)

doc.symbols
> "Language Models as Knowledge Bases?\nFabio Petroni1 Tim Rockt..."

for page in doc.pages:
    print(f'\n=== PAGE: {page.id} ===\n\n')
    for row in page.rows:
        print(row.symbols)
        
> ...
> === PAGE: 5 ===
> ['tence x, s′ will be linked to s and o′ to o. In']
> ['practice, this means RE can return the correct so-']
> ['lution o if any relation instance of the right type']
> ['was extracted from x, regardless of whether it has']
> ...

for page in doc.pages:
    for paragraph in page.paragraphs:
        for sent in paragraph.sents:
            for row in sent.rows:
                for token in sent.tokens:
                    pass

doc.fields
> ['pages', 'tokens', 'rows']