SEC Filings

Us Pds Normalized Text

Return bounded bytes for an exact active PDS-derived normalized-text proof.

The bytes are base64 encoded so an arbitrary byte range remains lossless even when its edge splits a UTF-8 code point. content_end_byte is exclusive. This surface is deliberately separate from canonical filing content and never falls back to a bare normalization ledger, a stale derivative, or /us/filings/{accession}/content. OCR parser suffixes are accepted only with matching source-provenance pipeline evidence.

GET

pds

submissions

{accession_number}

normalized

Us Pds Normalized Text

curl --request GET \
  --url https://corpus-api.onera.app/us/pds/submissions/{accession_number}/normalized \
  --header 'X-API-KEY: <api-key>'

import requests

url = "https://corpus-api.onera.app/us/pds/submissions/{accession_number}/normalized"

headers = {"X-API-KEY": "<api-key>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {'X-API-KEY': '<api-key>'}};

fetch('https://corpus-api.onera.app/us/pds/submissions/{accession_number}/normalized', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "accession_number": "<string>",
  "filing_type": "<string>",
  "normalized_sha256": "<string>",
  "normalized_byte_size": 123,
  "normalized_parser_version": "<string>",
  "content": "<string>",
  "content_start_byte": 1,
  "content_end_byte": 1,
  "returned_bytes": 1,
  "total_bytes": 123,
  "content_truncated": true,
  "content_range_sha256": "<string>",
  "source": {
    "pds_sha256": "<string>",
    "pds_byte_size": 123,
    "pds_parser_version": "<string>",
    "document_count": 1,
    "archive_id": "<string>",
    "archive_family": "<string>",
    "archive_url": "<string>",
    "source_kind": "<string>",
    "member_ordinal": 123,
    "member_name": "<string>",
    "source_generation_id": "<string>",
    "inventory_generation_id": "<string>",
    "archive_date": "2023-12-25"
  },
  "primary_selection": {
    "document_name": "<string>",
    "synthetic_document_name": true,
    "sha256": "<string>",
    "byte_size": 123,
    "document_type": "<string>",
    "sequence": "<string>",
    "payload_derivation": "<string>",
    "ocr_pipeline_contract": "<string>",
    "ocr_pipeline_fingerprint": "<string>"
  },
  "provenance": {
    "source_generation_id": "<string>",
    "inventory_generation_id": "<string>",
    "provider": "SEC",
    "system": "EDGAR PDS",
    "representation": "normalized_official_dissemination_submission",
    "canonical_filing_content": false,
    "completed_at": "2023-11-07T05:31:56Z"
  },
  "resource": "sec_pds_normalized_text",
  "filing_date": "2023-12-25",
  "content_type": "text/plain; charset=utf-8",
  "encoding": "base64",
  "next_start_byte": 1
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "accession_number": "<string>",
  "retry_after_seconds": 123,
  "request_id": "<string>"
}

Authorizations

X-API-KEY

string

header

required

Provisioned Corpus API key with the required jurisdiction and operation scopes.

Path Parameters

accession_number

string

required

Pattern: ^\d{10}-\d{2}-\d{6}$

Query Parameters

start_byte

integer

default:0

Required range: x >= 0

max_bytes

integer

default:50000

Required range: 1 <= x <= 75000

Response

Successful Response

accession_number

string

required

filing_type

string

required

normalized_sha256

string

required

normalized_byte_size

integer

required

normalized_parser_version

string

required

content

string

required

content_start_byte

integer

required

Required range: x >= 0

content_end_byte

integer

required

Required range: x >= 0

returned_bytes

integer

required

Required range: x >= 0

total_bytes

integer

required

content_truncated

boolean

required

content_range_sha256

string

required

source

PdsNormalizedTextSource · object

required

Show child attributes

primary_selection

PdsNormalizedTextPrimarySelection · object

required

Show child attributes

provenance

PdsNormalizedTextProvenance · object

required

Show child attributes

resource

string

default:sec_pds_normalized_text

Allowed value: "sec_pds_normalized_text"

filing_date

string<date> | null

content_type

string

default:text/plain; charset=utf-8

Allowed value: "text/plain; charset=utf-8"

encoding

string

default:base64

Allowed value: "base64"

next_start_byte

integer | null

Required range: x >= 0

Us Pds Normalized Text

curl --request GET \
  --url https://corpus-api.onera.app/us/pds/submissions/{accession_number}/normalized \
  --header 'X-API-KEY: <api-key>'

import requests

url = "https://corpus-api.onera.app/us/pds/submissions/{accession_number}/normalized"

headers = {"X-API-KEY": "<api-key>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {'X-API-KEY': '<api-key>'}};

fetch('https://corpus-api.onera.app/us/pds/submissions/{accession_number}/normalized', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "accession_number": "<string>",
  "filing_type": "<string>",
  "normalized_sha256": "<string>",
  "normalized_byte_size": 123,
  "normalized_parser_version": "<string>",
  "content": "<string>",
  "content_start_byte": 1,
  "content_end_byte": 1,
  "returned_bytes": 1,
  "total_bytes": 123,
  "content_truncated": true,
  "content_range_sha256": "<string>",
  "source": {
    "pds_sha256": "<string>",
    "pds_byte_size": 123,
    "pds_parser_version": "<string>",
    "document_count": 1,
    "archive_id": "<string>",
    "archive_family": "<string>",
    "archive_url": "<string>",
    "source_kind": "<string>",
    "member_ordinal": 123,
    "member_name": "<string>",
    "source_generation_id": "<string>",
    "inventory_generation_id": "<string>",
    "archive_date": "2023-12-25"
  },
  "primary_selection": {
    "document_name": "<string>",
    "synthetic_document_name": true,
    "sha256": "<string>",
    "byte_size": 123,
    "document_type": "<string>",
    "sequence": "<string>",
    "payload_derivation": "<string>",
    "ocr_pipeline_contract": "<string>",
    "ocr_pipeline_fingerprint": "<string>"
  },
  "provenance": {
    "source_generation_id": "<string>",
    "inventory_generation_id": "<string>",
    "provider": "SEC",
    "system": "EDGAR PDS",
    "representation": "normalized_official_dissemination_submission",
    "canonical_filing_content": false,
    "completed_at": "2023-11-07T05:31:56Z"
  },
  "resource": "sec_pds_normalized_text",
  "filing_date": "2023-12-25",
  "content_type": "text/plain; charset=utf-8",
  "encoding": "base64",
  "next_start_byte": 1
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "request_id": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "accession_number": "<string>",
  "retry_after_seconds": 123,
  "request_id": "<string>"
}

Overview

Companies

Prices

Financials

SEC Filings

Ownership and events

Search

Us Pds Normalized Text

Authorizations

Path Parameters

Query Parameters

Response