1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
|
from __future__ import print_function
import argparse
import logging
import sys
import traceback
import json
import os
import urlparse
import pkg_resources # part of setuptools
from typing import Any, Dict, List, Union
from rdflib import Graph, plugin
from rdflib.serializer import Serializer
from . import schema
from . import jsonld_context
from . import makedoc
from . import validate
from .sourceline import strip_dup_lineno
from .ref_resolver import Loader
_logger = logging.getLogger("salad")
from rdflib.plugin import register, Parser
register('json-ld', Parser, 'rdflib_jsonld.parser', 'JsonLDParser')
def printrdf(workflow, # type: str
wf, # type: Union[List[Dict[unicode, Any]], Dict[unicode, Any]]
ctx, # type: Dict[unicode, Any]
sr # type: str
):
# type: (...) -> None
g = jsonld_context.makerdf(workflow, wf, ctx)
print(g.serialize(format=sr))
def main(argsl=None): # type: (List[str]) -> int
if argsl is None:
argsl = sys.argv[1:]
parser = argparse.ArgumentParser()
parser.add_argument("--rdf-serializer",
help="Output RDF serialization format used by --print-rdf (one of turtle (default), n3, nt, xml)",
default="turtle")
exgroup = parser.add_mutually_exclusive_group()
exgroup.add_argument("--print-jsonld-context", action="store_true",
help="Print JSON-LD context for schema")
exgroup.add_argument(
"--print-rdfs", action="store_true", help="Print RDF schema")
exgroup.add_argument("--print-avro", action="store_true",
help="Print Avro schema")
exgroup.add_argument("--print-rdf", action="store_true",
help="Print corresponding RDF graph for document")
exgroup.add_argument("--print-pre", action="store_true",
help="Print document after preprocessing")
exgroup.add_argument(
"--print-index", action="store_true", help="Print node index")
exgroup.add_argument("--print-metadata",
action="store_true", help="Print document metadata")
exgroup.add_argument("--version", action="store_true",
help="Print version")
exgroup = parser.add_mutually_exclusive_group()
exgroup.add_argument("--strict", action="store_true", help="Strict validation (unrecognized or out of place fields are error)",
default=True, dest="strict")
exgroup.add_argument("--non-strict", action="store_false", help="Lenient validation (ignore unrecognized fields)",
default=True, dest="strict")
exgroup = parser.add_mutually_exclusive_group()
exgroup.add_argument("--verbose", action="store_true",
help="Default logging")
exgroup.add_argument("--quiet", action="store_true",
help="Only print warnings and errors.")
exgroup.add_argument("--debug", action="store_true",
help="Print even more logging")
parser.add_argument("schema", type=str)
parser.add_argument("document", type=str, nargs="?", default=None)
args = parser.parse_args(argsl)
if args.quiet:
_logger.setLevel(logging.WARN)
if args.debug:
_logger.setLevel(logging.DEBUG)
pkg = pkg_resources.require("schema_salad")
if pkg:
if args.version:
print("%s %s" % (sys.argv[0], pkg[0].version))
return 0
else:
_logger.info("%s %s", sys.argv[0], pkg[0].version)
# Get the metaschema to validate the schema
metaschema_names, metaschema_doc, metaschema_loader = schema.get_metaschema()
# Load schema document and resolve refs
schema_uri = args.schema
if not urlparse.urlparse(schema_uri)[0]:
schema_uri = "file://" + os.path.abspath(schema_uri)
schema_raw_doc = metaschema_loader.fetch(schema_uri)
try:
schema_doc, schema_metadata = metaschema_loader.resolve_all(
schema_raw_doc, schema_uri)
except (validate.ValidationException) as e:
_logger.error("Schema `%s` failed link checking:\n%s",
args.schema, e, exc_info=(True if args.debug else False))
_logger.debug("Index is %s", metaschema_loader.idx.keys())
_logger.debug("Vocabulary is %s", metaschema_loader.vocab.keys())
return 1
except (RuntimeError) as e:
_logger.error("Schema `%s` read error:\n%s",
args.schema, e, exc_info=(True if args.debug else False))
return 1
# Optionally print the schema after ref resolution
if not args.document and args.print_pre:
print(json.dumps(schema_doc, indent=4))
return 0
if not args.document and args.print_index:
print(json.dumps(metaschema_loader.idx.keys(), indent=4))
return 0
# Validate the schema document against the metaschema
try:
schema.validate_doc(metaschema_names, schema_doc,
metaschema_loader, args.strict,
source=schema_metadata["name"])
except validate.ValidationException as e:
_logger.error("While validating schema `%s`:\n%s" %
(args.schema, str(e)))
return 1
# Get the json-ld context and RDFS representation from the schema
metactx = {} # type: Dict[str, str]
if isinstance(schema_raw_doc, dict):
metactx = schema_raw_doc.get("$namespaces", {})
if "$base" in schema_raw_doc:
metactx["@base"] = schema_raw_doc["$base"]
(schema_ctx, rdfs) = jsonld_context.salad_to_jsonld_context(schema_doc, metactx)
# Create the loader that will be used to load the target document.
document_loader = Loader(schema_ctx)
# Make the Avro validation that will be used to validate the target
# document
if isinstance(schema_doc, list):
(avsc_names, avsc_obj) = schema.make_avro_schema(
schema_doc, document_loader)
else:
_logger.error("Schema `%s` must be a list.", args.schema)
return 1
if isinstance(avsc_names, Exception):
_logger.error("Schema `%s` error:\n%s", args.schema,
avsc_names, exc_info=((type(avsc_names), avsc_names,
None) if args.debug else None))
if args.print_avro:
print(json.dumps(avsc_obj, indent=4))
return 1
# Optionally print Avro-compatible schema from schema
if args.print_avro:
print(json.dumps(avsc_obj, indent=4))
return 0
# Optionally print the json-ld context from the schema
if args.print_jsonld_context:
j = {"@context": schema_ctx}
print(json.dumps(j, indent=4, sort_keys=True))
return 0
# Optionally print the RDFS graph from the schema
if args.print_rdfs:
print(rdfs.serialize(format=args.rdf_serializer))
return 0
if args.print_metadata and not args.document:
print(json.dumps(schema_metadata, indent=4))
return 0
# If no document specified, all done.
if not args.document:
print("Schema `%s` is valid" % args.schema)
return 0
# Load target document and resolve refs
try:
uri = args.document
if not urlparse.urlparse(uri)[0]:
doc = "file://" + os.path.abspath(uri)
document, doc_metadata = document_loader.resolve_ref(uri)
except (validate.ValidationException, RuntimeError) as e:
_logger.error("Document `%s` failed validation:\n%s",
args.document, strip_dup_lineno(unicode(e)), exc_info=args.debug)
return 1
# Optionally print the document after ref resolution
if args.print_pre:
print(json.dumps(document, indent=4))
return 0
if args.print_index:
print(json.dumps(document_loader.idx.keys(), indent=4))
return 0
# Validate the schema document against the metaschema
try:
schema.validate_doc(avsc_names, document,
document_loader, args.strict)
except validate.ValidationException as e:
_logger.error("While validating document `%s`:\n%s" %
(args.document, str(e)))
return 1
# Optionally convert the document to RDF
if args.print_rdf:
if isinstance(document, (dict, list)):
printrdf(args.document, document, schema_ctx, args.rdf_serializer)
return 0
else:
print("Document must be a dictionary or list.")
return 1
if args.print_metadata:
print(json.dumps(doc_metadata, indent=4))
return 0
print("Document `%s` is valid" % args.document)
return 0
if __name__ == "__main__":
sys.exit(main(sys.argv[1:]))
|
