[issue-465] correct regex to match spaces or tabs and add a test for this

Signed-off-by: Meret Behrens <[email protected]>

Author: meretp

spdx/parsers/lexers/tagvalue.py

@@ -235,7 +235,7 @@ def t_newline(self, t):
         t.lexer.lineno += len(t.value)
 
     def t_whitespace(self, t):
-        r"\s"
+        r"[ \t]+"
         pass
 
     def build(self, **kwargs):

tests/test_tag_value_parser.py

@@ -115,6 +115,9 @@
     'SPDXREF: SPDXRef-DOCUMENT'
 ])
 
+document_str_with_empty_line = "\n".join(
+    ['SPDXVersion: SPDX-2.1', '  ', 'DataLicense: CC0-1.0'])
+
 
 class TestLexer(TestCase):
     maxDiff = None
@@ -291,6 +294,14 @@ def test_annotation(self):
         self.token_assert_helper(self.l.token(), 'ANNOTATION_SPDX_ID', 'SPDXREF', 5)
         self.token_assert_helper(self.l.token(), 'LINE', 'SPDXRef-DOCUMENT', 5)
 
+    def test_correct_line_number_with_empty_line_between(self):
+        data = document_str_with_empty_line
+        self.l.input(data)
+        self.token_assert_helper(self.l.token(), 'DOC_VERSION', 'SPDXVersion', 1)
+        self.token_assert_helper(self.l.token(), 'LINE', 'SPDX-2.1', 1)
+        self.token_assert_helper(self.l.token(), 'DOC_LICENSE', 'DataLicense', 3)
+        self.token_assert_helper(self.l.token(), 'LINE', 'CC0-1.0', 3)
+
     def token_assert_helper(self, token, ttype, value, line):
         assert token.type == ttype
         assert token.value == value