Merge pull request #3 from INCATools/fix-lang-tags

fixing language tags

Author: hrshdhgd

src/rdf_sql_bulkloader/loaders/bulkloader.py

@@ -14,8 +14,9 @@
 
 re_untyped_literal = re.compile(r'^"(.*)"$')
 re_typed_literal = re.compile(r'^"(.*)"\^\^<([\S^"]+)>$')
-re_lang_literal = re.compile(r'^"(.*)"@(\w+)$')
-re_blank_node = re.compile(r"^riog(\d+)$")
+re_lang_literal = re.compile(r'^"(.*)"@([\-\w]+)$')
+re_blank_node = re.compile(r'^riog(\d+)$')
+
 
 
 DDL = """

tests/__init__.py

@@ -9,6 +9,9 @@
 
 TEST_BASE = "go-nucleus"
 TEST_INPUT_OWL = INPUT_DIR / f"{TEST_BASE}.owl"
+TEST_LANG_BASE = "lang-example"
+TEST_LANG_INPUT_OWL = INPUT_DIR / f"{TEST_LANG_BASE}.owl"
+TEST_LANG_INPUT_TTL = INPUT_DIR / f"{TEST_LANG_BASE}.ttl"
 
 
 def output_path(fn: str) -> str:

tests/input/go-nucleus.owl

@@ -30,7 +30,7 @@
     <!-- http://purl.obolibrary.org/obo/IAO_0000115 -->
 
     <owl:AnnotationProperty rdf:about="http://purl.obolibrary.org/obo/IAO_0000115">
-        <rdfs:label xml:lang="en">definition</rdfs:label>
+        <rdfs:label xml:lang="en-US">definition</rdfs:label>
     </owl:AnnotationProperty>
 
 

tests/input/lang-example.owl

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="utf-8"?>
+<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+            xmlns:dc="http://purl.org/dc/elements/1.1/">
+
+  <rdf:Description rdf:about="http://www.w3.org/TR/rdf-syntax-grammar">
+    <dc:title>RDF 1.1 XML Syntax</dc:title>
+    <dc:title xml:lang="en">RDF 1.1 XML Syntax</dc:title>
+    <dc:title xml:lang="en-US">RDF 1.1 XML Syntax</dc:title>
+  </rdf:Description>
+
+  <rdf:Description rdf:about="http://example.org/buecher/baum" xml:lang="de">
+    <dc:title>Der Baum</dc:title>
+    <dc:description>Das Buch ist außergewöhnlich</dc:description>
+    <dc:title xml:lang="en">The Tree</dc:title>
+  </rdf:Description>
+
+</rdf:RDF>
+

tests/input/lang-example.ttl

@@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="utf-8"?>
+<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+         xmlns:dc="http://purl.org/dc/elements/1.1/">
+  <rdf:Description rdf:about="http://www.w3.org/TR/rdf-syntax-grammar">
+    <dc:title>RDF/XML Syntax Specification (Revised)</dc:title>
+    <dc:title xml:lang="en">RDF/XML Syntax Specification (Revised)</dc:title>
+    <dc:title xml:lang="en-US">RDF/XML Syntax Specification (Revised)</dc:title>
+  </rdf:Description>
+
+  <rdf:Description rdf:about="http://example.org/buecher/baum" xml:lang="de">
+    <dc:title>Der Baum</dc:title>
+    <dc:description>Das Buch ist außergewöhnlich</dc:description>
+    <dc:title xml:lang="en">The Tree</dc:title>
+  </rdf:Description>
+</rdf:RDF>

tests/test_sqlite3_bulkloader.py

@@ -3,7 +3,8 @@
 import unittest
 
 from rdf_sql_bulkloader import SqliteBulkloader
-from tests import NUCLEUS, TEST_INPUT_OWL
+
+from tests import TEST_INPUT_OWL, NUCLEUS, TEST_PREFIX_MAP, TEST_LANG_INPUT_OWL, TEST_LANG_INPUT_TTL
 
 DEFN = (
     "A membrane-bounded organelle of eukaryotic cells in which chromosomes "
@@ -13,6 +14,7 @@
     + "RNA metabolism or DNA replication may be absent."
 )
 
+
 CASES = [
     (None, "GO:0005634", "RO:0002161", "NCBITaxon:2", None, None, None, None),
     (
@@ -43,3 +45,26 @@ def test_bulkload(self):
             print(s)
         for case in CASES:
             self.assertIn(case, stmts)
+            
+    def test_lang_tags(self):
+        """
+        Test language tags
+
+        https://www.w3.org/TR/rdf-syntax-grammar/#section-Syntax-languages
+        :return:
+        """
+        loader = SqliteBulkloader(path=":memory:")
+        loader.bulkload(TEST_LANG_INPUT_OWL)
+
+        def test_lang_tags_ttl(self):
+            """
+            Test language tags
+
+            https://www.w3.org/TR/rdf-syntax-grammar/#section-Syntax-languages
+            :return:
+            """
+            loader = SqliteBulkloader(path=":memory:")
+            loader.bulkload(TEST_LANG_INPUT_TTL)
+
+
+