def test_nested_default_namespace(self):
"""
Tests that a default namespace that is defined in a lower level tag is
written to a bundle.
"""
filename = os.path.join(DATA_PATH, "nested_default_namespace.xml")
doc = prov.ProvDocument.deserialize(source=filename, format="xml")
ns = Namespace("", "http://example.org/0/")
self.assertEqual(len(doc._records), 1)
self.assertEqual(doc.get_default_namespace(), ns)
self.assertEqual(doc._records[0].identifier.namespace, ns)
self.assertEqual(doc._records[0].identifier.localpart, "e001")
def test_redefining_namespaces(self):
"""
Test the behaviour when namespaces are redefined at the element level.
"""
filename = os.path.join(DATA_PATH,
"namespace_redefined_but_does_not_change.xml")
doc = prov.ProvDocument.deserialize(source=filename, format="xml")
# This has one record part of the original namespace.
self.assertEqual(len(doc._records), 1)
ns = Namespace("ex", "http://example.com/ns/ex#")
self.assertEqual(doc._records[0].attributes[0][1].namespace, ns)
# This also has one record but now in a different namespace.
filename = os.path.join(DATA_PATH, "namespace_redefined.xml")
doc = prov.ProvDocument.deserialize(source=filename, format="xml")
new_ns = doc._records[0].attributes[0][1].namespace
self.assertNotEqual(new_ns, ns)
self.assertEqual(new_ns.uri, "http://example.com/ns/new_ex#")
def test_deserialization_example_7(self):
"""
Test the deserialization of example 7 which is a simple activity
description.
"""
actual_doc = prov.ProvDocument.deserialize(source=os.path.join(
DATA_PATH, "example_07.xml"),
format="xml")
expected_document = prov.ProvDocument()
ex_ns = Namespace(*EX_NS)
expected_document.add_namespace(ex_ns)
expected_document.activity(
"ex:a1", "2011-11-16T16:05:00", "2011-11-16T16:06:00",
[(prov.PROV_TYPE, QualifiedName(ex_ns, "edit")),
("ex:host", "server.example.org")])
self.assertEqual(actual_doc, expected_document)
from __future__ import (absolute_import, division, print_function,
unicode_literals)
import six
from prov.identifier import Namespace
__author__ = 'Trung Dong Huynh'
__email__ = '*****@*****.**'
XSD = Namespace('xsd', 'http://www.w3.org/2001/XMLSchema#')
PROV = Namespace('prov', 'http://www.w3.org/ns/prov#')
XSI = Namespace('xsi', 'http://www.w3.org/2001/XMLSchema-instance')
# C1. Entities/Activities
PROV_ENTITY = PROV['Entity']
PROV_ACTIVITY = PROV['Activity']
PROV_GENERATION = PROV['Generation']
PROV_USAGE = PROV['Usage']
PROV_COMMUNICATION = PROV['Communication']
PROV_START = PROV['Start']
PROV_END = PROV['End']
PROV_INVALIDATION = PROV['Invalidation']
# C2. Derivations
PROV_DERIVATION = PROV['Derivation']
# C3. Agents/Responsibility
PROV_AGENT = PROV['Agent']
PROV_ATTRIBUTION = PROV['Attribution']
PROV_ASSOCIATION = PROV['Association']
PROV_DELEGATION = PROV['Delegation']
import os
import uuid
import json
from datetime import datetime
import pathlib
from prov.identifier import Namespace
import prov.model as prov
from prov.dot import prov_to_dot
# prov namespace
PROV_ORGANISATION = prov.PROV["Organization"]
PROV_SOFTWARE_AGENT = prov.PROV["SoftwareAgent"]
# provone namespace
PROVONE = Namespace("provone",
uri="http://purl.dataone.org/provone/2015/01/15/ontology#")
PROVONE_WORKFLOW = PROVONE["Workflow"]
PROVONE_DATA = PROVONE["Data"]
PROVONE_EXECUTION = PROVONE["Execution"]
# dcterms namespace
DCTERMS = Namespace("dct", uri="http://purl.org/dc/terms/")
DCTERMS_SOURCE = DCTERMS["source"]
# roocs namespace
ROOCS = Namespace("roocs", uri="urn:roocs:")
class Provenance(object):
def __init__(self, output_dir):
if isinstance(output_dir, pathlib.Path):
from __future__ import unicode_literals
from __future__ import print_function
from __future__ import division
from __future__ import absolute_import
from future import standard_library
standard_library.install_aliases()
from prov.identifier import Namespace
HYSDS = Namespace('hysds', 'http://hysds.domain.com/hysds/0.1#')
EOS = Namespace('eos', 'http://nasa.gov/eos.owl#')
GCIS = Namespace('gcis', 'http://data.globalchange.gov/gcis.owl#')
INFO = Namespace('info', 'http://info-uri.info/')
BIBO = Namespace('bibo', 'http://purl.org/ontology/bibo/')
DCTERMS = Namespace('dcterms', 'http://purl.org/dc/terms/')
# EOS convenience defs
EOS_COLLECTION = EOS['collection']
EOS_SHORTNAME = EOS['shortName']
EOS_LONGNAME = EOS['longName']
EOS_LEVEL = EOS['level']
EOS_VERSION = EOS['version']
EOS_DATASET = EOS['dataset']
EOS_PARTOFCOLLECTION = EOS['partOfCollection']
EOS_GRANULE = EOS['granule']
EOS_PRODUCT = EOS['product']
EOS_FILE = EOS['file']
EOS_PLATFORM = EOS['platform']
EOS_INSTRUMENT = EOS['instrument']
EOS_SENSOR = EOS['sensor']
EOS_SOFTWARE = EOS['software']
EOS_ALGORITHM = EOS['algorithm']
def test_deserialization_example_04_and_05(self):
"""
Example 4 and 5 have a different type specification. They use an
xsi:type as an attribute on an entity. This can be read but if
written again it will become an XML child element. This is
semantically identical but cannot be tested with a round trip.
"""
# Example 4.
xml_string = """
<prov:document
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns:prov="http://www.w3.org/ns/prov#"
xmlns:ex="http://example.com/ns/ex#"
xmlns:tr="http://example.com/ns/tr#">
<prov:entity prov:id="tr:WD-prov-dm-20111215" xsi:type="prov:Plan">
<prov:type xsi:type="xsd:QName">ex:Workflow</prov:type>
</prov:entity>
</prov:document>
"""
with io.StringIO() as xml:
xml.write(xml_string)
xml.seek(0, 0)
actual_document = prov.ProvDocument.deserialize(source=xml,
format="xml")
expected_document = prov.ProvDocument()
ex_ns = Namespace(*EX_NS)
expected_document.add_namespace(ex_ns)
expected_document.add_namespace(*EX_TR)
# The xsi:type attribute is mapped to a proper PROV attribute.
expected_document.entity(
"tr:WD-prov-dm-20111215",
(
(prov.PROV_TYPE, QualifiedName(ex_ns, "Workflow")),
(prov.PROV_TYPE, PROV["Plan"]),
),
)
self.assertEqual(actual_document, expected_document, "example_04")
# Example 5.
xml_string = """
<prov:document
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns:prov="http://www.w3.org/ns/prov#"
xmlns:ex="http://example.com/ns/ex#"
xmlns:tr="http://example.com/ns/tr#">
<prov:entity prov:id="tr:WD-prov-dm-20111215" xsi:type="prov:Plan">
<prov:type xsi:type="xsd:QName">ex:Workflow</prov:type>
<prov:type xsi:type="xsd:QName">prov:Plan</prov:type> <!-- inferred -->
<prov:type xsi:type="xsd:QName">prov:Entity</prov:type> <!-- inferred -->
</prov:entity>
</prov:document>
"""
with io.StringIO() as xml:
xml.write(xml_string)
xml.seek(0, 0)
actual_document = prov.ProvDocument.deserialize(source=xml,
format="xml")
expected_document = prov.ProvDocument()
expected_document.add_namespace(*EX_NS)
expected_document.add_namespace(*EX_TR)
# The xsi:type attribute is mapped to a proper PROV attribute.
expected_document.entity(
"tr:WD-prov-dm-20111215",
(
(prov.PROV_TYPE, QualifiedName(ex_ns, "Workflow")),
(prov.PROV_TYPE, PROV["Entity"]),
(prov.PROV_TYPE, PROV["Plan"]),
),
)
self.assertEqual(actual_document, expected_document, "example_05")
# 1. Bump major number if removing/"breaking" resources or PROV statements
# 2. Bump minor number if adding resources or PROV statements
# 3. Bump patch number for non-breaking non-adding changes,
# e.g. fixing broken relative paths
CWLPROV_VERSION = "https://w3id.org/cwl/prov/0.6.0"
# Research Object folders
METADATA = "metadata"
DATA = "data"
WORKFLOW = "workflow"
SNAPSHOT = "snapshot"
# sub-folders
MAIN = os.path.join(WORKFLOW, "main")
PROVENANCE = os.path.join(METADATA, "provenance")
LOGS = os.path.join(METADATA, "logs")
WFDESC = Namespace("wfdesc", "http://purl.org/wf4ever/wfdesc#")
WFPROV = Namespace("wfprov", "http://purl.org/wf4ever/wfprov#")
WF4EVER = Namespace("wf4ever", "http://purl.org/wf4ever/wf4ever#")
RO = Namespace("ro", "http://purl.org/wf4ever/ro#")
ORE = Namespace("ore", "http://www.openarchives.org/ore/terms/")
FOAF = Namespace("foaf", "http://xmlns.com/foaf/0.1/")
SCHEMA = Namespace("schema", "http://schema.org/")
CWLPROV = Namespace("cwlprov", "https://w3id.org/cwl/prov#")
ORCID = Namespace("orcid", "https://orcid.org/")
UUID = Namespace("id", "urn:uuid:")
# BagIt and YAML always use UTF-8
ENCODING = "UTF-8"
TEXT_PLAIN = 'text/plain; charset="%s"' % ENCODING
# sha1, compatible with the File type's "checksum" field
# # PROV record constants - PROV-DM
# Built-in namespaces
from prov.identifier import Namespace
XSD = Namespace('xsd', 'http://www.w3.org/2001/XMLSchema#')
PROV = Namespace('prov', 'http://www.w3.org/ns/prov#')
# C1. Entities/Activities
PROV_ENTITY = PROV['Entity']
PROV_ACTIVITY = PROV['Activity']
PROV_GENERATION = PROV['Generation']
PROV_USAGE = PROV['Usage']
PROV_COMMUNICATION = PROV['Communication']
PROV_START = PROV['Start']
PROV_END = PROV['End']
PROV_INVALIDATION = PROV['Invalidation']
# C2. Derivations
PROV_DERIVATION = PROV['Derivation']
# C3. Agents/Responsibility
PROV_AGENT = PROV['Agent']
PROV_ATTRIBUTION = PROV['Attribution']
PROV_ASSOCIATION = PROV['Association']
PROV_DELEGATION = PROV['Delegation']
PROV_INFLUENCE = PROV['Influence']
# C4. Bundles
PROV_BUNDLE = PROV['Bundle']
# C5. Alternate
PROV_ALTERNATE = PROV['Alternate']