trustgraph/test-api/test-load-document

#!/usr/bin/env python3

import requests
import json
import sys
import base64

url = "http://localhost:8088/api/v1/"

############################################################################

text = open("../sources/Challenger-Report-Vol1.pdf", "rb").read()

# Some random identifiers.  The doc ID is important, as extracted knowledge
# is linked back to this identifier
org_id = "https://trustgraph.ai/org/1dd51ece-8bd3-48b8-98ce-1ac9164c5214"
doc_id = "https://trustgraph.ai/doc/72ef3374-af7a-40c4-8c7b-45050aef5b90"
pub_id = "https://trustgraph.ai/pubev/59012ae1-65d4-441f-8288-b6f3c6c15333"

# Organization metadata
org_facts = [
    [org_id, "http://www.w3.org/1999/02/22-rdf-syntax-ns#type",
     "https://schema.org/Organization"],
    [org_id, "http://www.w3.org/2000/01/rdf-schema#label", "NASA"],
    [org_id, "https://schema.org/name", "NASA"]
]

# Publication metadata.  Note how it links to the Organization
pub_facts = [
    [pub_id, "http://www.w3.org/1999/02/22-rdf-syntax-ns#type",
     "https://schema.org/PublicationEvent"],
    [pub_id, "https://schema.org/description", "Uploading to Github"],
    [pub_id, "https://schema.org/endDate", "1986-06-06"],
    [pub_id, "https://schema.org/publishedBy", org_id],
    [pub_id, "https://schema.org/startDate", "1986-06-06"]
]

# Document metadata.  Note how it links to the publication event
doc_facts = [
    [doc_id, "http://www.w3.org/1999/02/22-rdf-syntax-ns#type",
     "https://schema.org/DigitalDocument"],
    [doc_id, "http://www.w3.org/2000/01/rdf-schema#label",
     "Challenger Report Volume 1"],
    [doc_id, "https://schema.org/copyrightHolder", "US Government"],
    [doc_id, "https://schema.org/copyrightNotice",
     "Work of the US Gov. Public Use Permitted"],
    [doc_id, "https://schema.org/copyrightYear", "1986"],
    [doc_id, "https://schema.org/description",
     "The findings of the Presidential Commission regarding the circumstances surrounding the Challenger accident are reported and recommendations for corrective action are outlined"
     ],
    [doc_id, "https://schema.org/keywords", "nasa"],
    [doc_id, "https://schema.org/keywords", "challenger"],
    [doc_id, "https://schema.org/keywords", "space-shuttle"],
    [doc_id, "https://schema.org/keywords", "shuttle"],
    [doc_id, "https://schema.org/keywords", "orbiter"],
    [doc_id, "https://schema.org/name", "Challenger Report Volume 1"],
    [doc_id, "https://schema.org/publication", pub_id],
    [doc_id, "https://schema.org/url",
     "https://ntrs.nasa.gov/citations/19860015255"]
]

def to_value(x):
    if x.startswith("https://"):
        return { "v": x, "e": True }
    if x.startswith("http://"):
        return { "v": x, "e": True }
    return { "v": x, "e": False }

# Convert the above metadata into the right form
metadata = [
    { "s": to_value(t[0]), "p": to_value(t[1]), "o": to_value(t[2]) }
    for t in org_facts + pub_facts + doc_facts
]

input = {
    
    # Document identifer.  Knowledge derived by TrustGraph is linked to this
    # identifier, so the additional metadata specified above is linked to the
    # derived knowledge and users of the knowledge graph could see
    # information about the source of knowledge
    "id": doc_id,
    
    # Additional metadata in the form of RDF triples
    "metadata": metadata,
    
    # Text character set.  Default is UTF-8
    "charset": "utf-8",
    
    # The PDF document, is presented as a base64 encoded document.
    "data": base64.b64encode(text).decode("utf-8")

}

resp = requests.post(
    f"{url}load/document",
    json=input,
)

resp = resp.json()

if "error" in resp:
    print(f"Error: {resp['error']}")
    sys.exit(1)

print(resp)