Update is_valid_uri() for checking Unicode letter

is_valid_uri() checked only 'in' criteria so that it couldn't check URI which includes Unicode letter other than ASCII zone.
ex. http://ex.com/漢字 should be valid but not
Change: use unicodedata.category for checking Unicode Category, 'Lx' category is valid. If not, use same logic as before.
See: https://www.unicode.org/reports/tr44/#General_Category

1 files changed, 6 insertions, 4 deletions

diff --git a/rdflib/term.py b/rdflib/term.py
index 3665ff22..5f06e95b 100644
--- a/rdflib/term.py
+++ b/rdflib/term.py
@@ -50,6 +50,7 @@ import xml.dom.minidom
 from datetime import date, time, datetime, timedelta
 from re import sub, compile
 from collections import defaultdict
+from unicodedata import category
 
 from isodate import parse_time, parse_date, parse_datetime, Duration, parse_duration, duration_isoformat
 
@@ -73,10 +74,11 @@ _invalid_uri_chars = '<>" {}|\\^`'
 
 
 def _is_valid_uri(uri):
-    for c in _invalid_uri_chars:
-        if c in uri:
-            return False
-    return True
+    """
+    Verify invalid chars other than Unicode Letter (Category: Lx)
+    Ref: https://www.unicode.org/reports/tr44/#General_Category
+    """
+    return all(map(lambda c: category(c).startswith('L') or not c in _invalid_uri_chars, uri))
 
 
 _lang_tag_regex = compile('^[a-zA-Z]+(?:-[a-zA-Z0-9]+)*$')