fix: add more type-hinting for SPARQL plugin (#2265)

Here, adding type-hints to some of the SPARQL parser plugin code.

Includes a couple of small consequent changes:

1. Minor refactor of `prettify_parsetree()`, separating the public-facing callable from the internal code that does not need to be public-facing.  That allows the public-facing callable to have more informative and restrictive type-hints for its arguments.
2. Added some test-coverage for `expandUnicodeEscapes()` - initially for my own understanding, but seems useful to leave it in place since I didn't see test-coverage for that function.

There should be no backwards-incompatible changes in this PR - at least, not intentionally.

---------

Co-authored-by: Iwan Aucamp <aucampia@gmail.com>

1 files changed, 23 insertions, 1 deletions

diff --git a/test/test_sparql/test_sparql.py b/test/test_sparql/test_sparql.py
index 02406bdf..80768604 100644
--- a/test/test_sparql/test_sparql.py
+++ b/test/test_sparql/test_sparql.py
@@ -16,7 +16,7 @@ from rdflib.plugins.sparql import prepareQuery, sparql
 from rdflib.plugins.sparql.algebra import translateQuery
 from rdflib.plugins.sparql.evaluate import evalPart
 from rdflib.plugins.sparql.evalutils import _eval
-from rdflib.plugins.sparql.parser import parseQuery
+from rdflib.plugins.sparql.parser import expandUnicodeEscapes, parseQuery
 from rdflib.plugins.sparql.parserutils import prettify_parsetree
 from rdflib.plugins.sparql.sparql import SPARQLError
 from rdflib.query import Result, ResultRow
@@ -957,3 +957,25 @@ def test_sparql_describe(
     subjects = {s for s in r.graph.subjects() if not isinstance(s, BNode)}
     assert subjects == expected_subjects
     assert len(r.graph) == expected_size
+
+
+@pytest.mark.parametrize(
+    "arg, expected_result, expected_valid",
+    [
+        ("abc", "abc", True),
+        ("1234", "1234", True),
+        (r"1234\u0050", "1234P", True),
+        (r"1234\u00e3", "1234\u00e3", True),
+        (r"1234\u00e3\u00e5", "1234ãå", True),
+        (r"1234\u900000e5", "", False),
+        (r"1234\u010000e5", "", False),
+        (r"1234\u001000e5", "1234\U001000e5", True),
+    ],
+)
+def test_expand_unicode_escapes(arg: str, expected_result: str, expected_valid: bool):
+    if expected_valid:
+        actual_result = expandUnicodeEscapes(arg)
+        assert actual_result == expected_result
+    else:
+        with pytest.raises(ValueError, match="Invalid unicode code point"):
+            _ = expandUnicodeEscapes(arg)