trustgraph/tests/test-load-pdf

#!/usr/bin/env python3

import pulsar
from pulsar.schema import JsonSchema
import base64

from trustgraph.schema import Document, Metadata

client = pulsar.Client("pulsar://localhost:6650", listener_name="localhost")

prod = client.create_producer(
    topic="persistent://tg/flow/document-load:0000",
    schema=JsonSchema(Document),
    chunking_enabled=True,
)

path = "../sources/Challenger-Report-Vol1.pdf"

with open(path, "rb") as f:
    blob = base64.b64encode(f.read()).decode("utf-8")

message = Document(
    metadata = Metadata(
        id = "00001",
        metadata = [],
        user="trustgraph",
        collection="default",
    ),
    data=blob
)    

prod.send(message)

prod.close()
client.close()