Fixing cpe data split for cpe fields containing colon

repology/parsers/cpe.py

@@ -0,0 +1,39 @@
+# Copyright (C) 2019 Dmitry Marakasov <[email protected]>
+#
+# This file is part of repology
+#
+# repology is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# repology is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with repology.  If not, see <http://www.gnu.org/licenses/>.
+
+from typing import List
+
+
+def cpe_parse(cpe_str: str) -> List[str]:
+    escaped = False
+    current = ''
+    res = []
+
+    for char in cpe_str:
+        if escaped:
+            current += '\\' + char
+            escaped = False
+        elif char == '\\':
+            escaped = True
+        elif char == ':':
+            res.append(current)
+            current = ''
+        else:
+            current += char
+
+    res.append(current)
+    return res

repology/parsers/parsers/gentoo.py

@@ -24,6 +24,7 @@
 from repology.package import PackageFlags
 from repology.packagemaker import NameType, PackageFactory, PackageMaker
 from repology.parsers import Parser
+from repology.parsers.cpe import cpe_parse
 from repology.parsers.maintainers import extract_maintainers
 from repology.parsers.versions import VersionStripper
 from repology.transformer import PackageTransformer
@@ -180,8 +181,13 @@ def iter_parse(self, path: str, factory: PackageFactory, transformer: PackageTra
                 pkg.add_maintainers(xml_metadata.maintainers)
 
                 if xml_metadata.cpe is not None:
-                    cpe = xml_metadata.cpe.split(':')
-                    pkg.add_cpe(cpe[2], cpe[3])
+                    cpe = cpe_parse(xml_metadata.cpe)
+
+                    # distinguish between cpe format 2.2 or 2.3
+                    if cpe[1] == '2.3':
+                        pkg.add_cpe(cpe[3], cpe[4])
+                    else:
+                        pkg.add_cpe(cpe[2], cpe[3])
 
                 for ebuild in _iter_ebuilds(path, category, package):
                     subpkg = pkg.clone(append_ident='/' + ebuild)

repology/test/test_cpe.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+#
+# Copyright (C) 2021 Dmitry Marakasov <[email protected]>
+#
+# This file is part of repology
+#
+# repology is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# repology is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with repology.  If not, see <http://www.gnu.org/licenses/>.
+
+# mypy: no-disallow-untyped-calls
+
+import unittest
+
+from repology.parsers.cpe import cpe_parse
+
+
+class TestCpe(unittest.TestCase):
+    def test_cpe_parse(self) -> None:
+        self.assertEqual(cpe_parse('foo:bar'), ['foo', 'bar'])
+        self.assertEqual(cpe_parse('foobar'), ['foobar'])
+        self.assertEqual(cpe_parse('cpe:2.3:a:andreas_mueller:cdrdao'), ['cpe', '2.3', 'a', 'andreas_mueller', 'cdrdao'])
+        self.assertEqual(cpe_parse('cpe:/a:archive\\:\\:tar_project:archive\\:\\:tar'), ['cpe', '/a', 'archive\\:\\:tar_project', 'archive\\:\\:tar'])
+        self.assertEqual(cpe_parse('foo\\:bar'), ['foo\\:bar'])
+        self.assertEqual(cpe_parse('foo\\\\:bar'), ['foo\\\\', 'bar'])
+
+    @unittest.expectedFailure
+    def test_cpe_parse_failure(self) -> None:
+        self.assertEqual(cpe_parse('a:b'), ['ab'])
+        self.assertEqual(cpe_parse('foo\\:bar'), ['foo:bar'])
+        self.assertEqual(cpe_parse('foo\\\\:bar'), ['foo', 'bar'])
+
+
+if __name__ == '__main__':
+    unittest.main()