def view(document_id):
enable_cache()
data = get_index_document(document_id)
document = get_db_document(document_id)
data['headers'] = document.headers
# TODO: should this be it's own API? Probably so, but for that it would
# be unclear if we should JSON wrap it, or serve plain with the correct
# MIME type?
if Document.SCHEMA_HTML in document.model.names:
data['html'] = sanitize_html(document.body_raw, document.source_url)
if Document.SCHEMA_TEXT in document.model.names:
data['text'] = document.body_text
return jsonify(data, schema=CombinedSchema)
def view(document_id):
enable_cache()
document = get_index_document(document_id)
# TODO: should this be it's own API? Probably so, but for that it would
# be unclear if we should JSON wrap it, or serve plain with the correct
# MIME type?
if document.get('type') == Document.TYPE_SCROLL:
obj = get_document(document_id)
document['text'] = obj.body_text
elif document.get('type') == Document.TYPE_HTML:
obj = get_document(document_id)
document['html'] = sanitize_html(obj.body_raw)
return jsonify(document, schema=DocumentSchema)
def view(document_id):
enable_cache()
document = get_index_document(document_id)
return jsonify(document, schema=DocumentSchema)
