bsie extraction and info apps

3 files changed, 232 insertions, 0 deletions

diff --git a/test/lib/__init__.py b/test/lib/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/test/lib/__init__.py
diff --git a/test/lib/test_bsie.py b/test/lib/test_bsie.py
new file mode 100644
index 0000000..277ac67
--- /dev/null
+++ b/test/lib/test_bsie.py
@@ -0,0 +1,231 @@
+"""
+
+Part of the bsie test suite.
+A copy of the license is provided with the project.
+Author: Matthias Baumgartner, 2022
+"""
+# imports
+import os
+import unittest
+
+# bsie imports
+from bsie.tools import builder
+from bsie.utils import ns
+from bsie.utils.bsfs import URI, schema
+from bsie.utils.node import Node
+
+# objects to test
+from bsie.lib.bsie import BSIE
+
+
+## code ##
+
+class TestBSIE(unittest.TestCase):
+    def setUp(self):
+        # reader builder
+        rbuild = builder.ReaderBuilder({})
+        # extractor builder
+        ebuild = builder.ExtractorBuilder([
+            {'bsie.extractor.generic.path.Path': {}},
+            {'bsie.extractor.generic.stat.Stat': {}},
+            {'bsie.extractor.generic.constant.Constant': dict(
+                tuples=[('http://bsfs.ai/schema/Entity#author', 'Me, myself, and I')],
+                schema='''
+                    bse:author rdfs:subClassOf bsfs:Predicate ;
+                        rdfs:domain bsfs:Entity ;
+                        rdfs:range xsd:string ;
+                        bsfs:unique "true"^^xsd:boolean .
+                    ''',
+                )},
+            ])
+        # build pipeline
+        self.prefix = URI('http://example.com/local/file#')
+        pbuild = builder.PipelineBuilder(self.prefix, rbuild, ebuild)
+        self.pipeline = pbuild.build()
+
+    def test_construction(self):
+        # pipeline only
+        lib = BSIE(self.pipeline)
+        self.assertSetEqual(lib.predicates, {
+            ns.bse.filename,
+            ns.bse.filesize,
+            ns.bse.author,
+            })
+        self.assertEqual(lib.schema, schema.Schema.from_string('''
+            prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+            prefix xsd: <http://www.w3.org/2001/XMLSchema#>
+            prefix bsfs: <http://bsfs.ai/schema/>
+            prefix bse: <http://bsfs.ai/schema/Entity#>
+            # essential nodes
+            bsfs:Entity rdfs:subClassOf bsfs:Node .
+            # common definitions
+            xsd:string rdfs:subClassOf bsfs:Literal .
+            xsd:integer rdfs:subClassOf bsfs:Literal .
+
+            bse:filename rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsfs:Entity ;
+                rdfs:range xsd:string ;
+                bsfs:unique "false"^^xsd:boolean .
+
+            bse:filesize rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsfs:Entity ;
+                rdfs:range xsd:integer;
+                bsfs:unique "false"^^xsd:boolean .
+
+            bse:author rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsfs:Entity ;
+                rdfs:range xsd:string ;
+                bsfs:unique "true"^^xsd:boolean .
+
+            '''))
+
+        # specify collect
+        lib = BSIE(self.pipeline, collect={
+            ns.bse.filesize,
+            ns.bse.author,
+            ns.bse.inexistent,
+            })
+        self.assertSetEqual(lib.predicates, {
+            ns.bse.filesize,
+            ns.bse.author,
+            })
+        self.assertEqual(lib.schema, schema.Schema.from_string('''
+            prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+            prefix xsd: <http://www.w3.org/2001/XMLSchema#>
+            prefix bsfs: <http://bsfs.ai/schema/>
+            prefix bse: <http://bsfs.ai/schema/Entity#>
+            # essential nodes
+            bsfs:Entity rdfs:subClassOf bsfs:Node .
+            # common definitions
+            xsd:string rdfs:subClassOf bsfs:Literal .
+            xsd:integer rdfs:subClassOf bsfs:Literal .
+
+            bse:filesize rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsfs:Entity ;
+                rdfs:range xsd:integer;
+                bsfs:unique "false"^^xsd:boolean .
+
+            bse:author rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsfs:Entity ;
+                rdfs:range xsd:string ;
+                bsfs:unique "true"^^xsd:boolean .
+
+            '''))
+        # empty collect is disregarded
+        lib = BSIE(self.pipeline, collect={})
+        self.assertSetEqual(lib.predicates, {
+            ns.bse.filename,
+            ns.bse.filesize,
+            ns.bse.author,
+            })
+        self.assertEqual(lib.schema, schema.Schema.from_string('''
+            prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+            prefix xsd: <http://www.w3.org/2001/XMLSchema#>
+            prefix bsfs: <http://bsfs.ai/schema/>
+            prefix bse: <http://bsfs.ai/schema/Entity#>
+            # essential nodes
+            bsfs:Entity rdfs:subClassOf bsfs:Node .
+            # common definitions
+            xsd:string rdfs:subClassOf bsfs:Literal .
+            xsd:integer rdfs:subClassOf bsfs:Literal .
+
+            bse:filename rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsfs:Entity ;
+                rdfs:range xsd:string ;
+                bsfs:unique "false"^^xsd:boolean .
+
+            bse:filesize rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsfs:Entity ;
+                rdfs:range xsd:integer;
+                bsfs:unique "false"^^xsd:boolean .
+
+            bse:author rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsfs:Entity ;
+                rdfs:range xsd:string ;
+                bsfs:unique "true"^^xsd:boolean .
+
+            '''))
+
+        # specify discard
+        lib = BSIE(self.pipeline, discard={
+            ns.bse.filesize,
+            ns.bse.filename,
+            ns.bse.inexistent,
+            })
+        self.assertSetEqual(lib.predicates, {
+            ns.bse.author,
+            })
+        self.assertEqual(lib.schema, schema.Schema.from_string('''
+            prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+            prefix xsd: <http://www.w3.org/2001/XMLSchema#>
+            prefix bsfs: <http://bsfs.ai/schema/>
+            prefix bse: <http://bsfs.ai/schema/Entity#>
+            # essential nodes
+            bsfs:Entity rdfs:subClassOf bsfs:Node .
+            # common definitions
+            xsd:string rdfs:subClassOf bsfs:Literal .
+
+            bse:author rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsfs:Entity ;
+                rdfs:range xsd:string ;
+                bsfs:unique "true"^^xsd:boolean .
+
+            '''))
+
+        # specify collect and discard
+        lib = BSIE(self.pipeline,
+            collect={ns.bse.filesize, ns.bse.author, ns.bse.foo, ns.bse.bar},
+            discard={ns.bse.author, ns.bse.foo, ns.bse.foobar},
+            )
+        self.assertSetEqual(lib.predicates, {
+            ns.bse.filesize,
+            })
+        self.assertEqual(lib.schema, schema.Schema.from_string('''
+            prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+            prefix xsd: <http://www.w3.org/2001/XMLSchema#>
+            prefix bsfs: <http://bsfs.ai/schema/>
+            prefix bse: <http://bsfs.ai/schema/Entity#>
+            # essential nodes
+            bsfs:Entity rdfs:subClassOf bsfs:Node .
+            # common definitions
+            xsd:integer rdfs:subClassOf bsfs:Literal .
+
+            bse:filesize rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsfs:Entity ;
+                rdfs:range xsd:integer;
+                bsfs:unique "false"^^xsd:boolean .
+
+            '''))
+
+
+    def test_from_file(self):
+        # setup
+        lib = BSIE(self.pipeline)
+        self.assertSetEqual(set(lib.predicates), {
+            ns.bse.filesize,
+            ns.bse.filename,
+            ns.bse.author,
+            })
+        content_hash = 'a948904f2f0f479b8f8197694b30184b0d2ed1c1cd2a1ec0fb85d299a192a447'
+        subject = Node(ns.bsfs.Entity, self.prefix + content_hash)
+        testfile = os.path.join(os.path.dirname(__file__), 'testfile.t')
+
+        # from_file extracts all available triples
+        self.assertSetEqual(set(lib.from_file(testfile)), {
+            (subject, lib.schema.predicate(ns.bse.filename), 'testfile.t'),
+            (subject, lib.schema.predicate(ns.bse.filesize), 12),
+            (subject, lib.schema.predicate(ns.bse.author), 'Me, myself, and I'),
+            })
+
+        # from_file respects predicate argument
+        self.assertSetEqual(set(lib.from_file(testfile, {ns.bse.filename, ns.bse.invalid})), {
+            (subject, lib.schema.predicate(ns.bse.filename), 'testfile.t'),
+            })
+
+
+## main ##
+
+if __name__ == '__main__':
+    unittest.main()
+
+## EOF ##
diff --git a/test/lib/testfile.t b/test/lib/testfile.t
new file mode 100644
index 0000000..3b18e51
--- /dev/null
+++ b/test/lib/testfile.t
@@ -0,0 +1 @@
+hello world