1 files changed, 75 insertions, 0 deletions
diff --git a/test/extractor/text/test_metrics.py b/test/extractor/text/test_metrics.py
new file mode 100644
index 0000000..9cc6a94
--- /dev/null
+++ b/test/extractor/text/test_metrics.py
@@ -0,0 +1,75 @@
+
+# standard imports
+import os
+import unittest
+
+# bsie imports
+from bsie.extractor import base
+from bsie.matcher import nodes
+from bsie.reader.document import Document
+from bsie.utils import bsfs, ns
+
+# objects to test
+from bsie.extractor.text.metrics import TextMetrics
+
+
+## code ##
+
+class TestTextMetrics(unittest.TestCase):
+
+    def test_schema(self):
+        self.assertEqual(TextMetrics().schema,
+            bsfs.schema.from_string(base.SCHEMA_PREAMBLE + '''
+            bse:num_characters rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsn:Entity ;
+                rdfs:range xsd:integer ;
+                bsfs:unique "true"^^xsd:boolean .
+
+            bse:num_paragraphs rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsn:Entity ;
+                rdfs:range xsd:integer ;
+                bsfs:unique "true"^^xsd:boolean .
+
+            bse:num_words rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsn:Entity ;
+                rdfs:range xsd:integer ;
+                bsfs:unique "true"^^xsd:boolean .
+
+            bse:vocabulary_size rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsn:Entity ;
+                rdfs:range xsd:integer ;
+                bsfs:unique "true"^^xsd:boolean .
+
+            bse:vocabulary_entropy rdfs:subClassOf bsfs:Predicate ;
+                rdfs:domain bsn:Entity ;
+                rdfs:range xsd:float ;
+                bsfs:unique "true"^^xsd:boolean .
+            '''))
+
+    def test_extract(self):
+        # setup
+        rdr = Document()
+        ext = TextMetrics()
+        subject = nodes.Entity(ucid='abc123')
+        principals = set(ext.principals)
+        path = os.path.join(os.path.dirname(__file__), 'example-en.txt')
+        # fetch document
+        text = rdr(path)
+        triples = set(ext.extract(subject, text, principals))
+
+        self.assertSetEqual({(s,p,o) for s,p,o in triples if p.uri != ns.bse.vocabulary_entropy}, {
+            (subject, ext.schema.predicate(ns.bse.num_characters), 21997),
+            (subject, ext.schema.predicate(ns.bse.num_paragraphs), 48),
+            (subject, ext.schema.predicate(ns.bse.num_words), 4234),
+            (subject, ext.schema.predicate(ns.bse.vocabulary_size), 3510),
+        })
+        entropy = {o for s,p,o in triples if p.uri == ns.bse.vocabulary_entropy}
+        self.assertEqual(len(entropy), 1)
+        self.assertAlmostEqual(list(entropy)[0], 8.830360505)
+
+## main ##
+
+if __name__ == '__main__':
+    unittest.main()
+
+## EOF ##