Fixing cpe data split for cpe fields containing colon

repology/parsers/cpe.py

@@ -0,0 +1,59 @@
+# 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 dataclasses import dataclass
+
+
+@dataclass(unsafe_hash=True)
+class CPE:
+    part:       str = '*'
+    vendor:     str = '*'
+    product:    str = '*'
+    version:    str = '*'
+    update:     str = '*'
+    edition:    str = '*'
+    lang:       str = '*'
+    sw_edition: str = '*'
+    target_sw:  str = '*'
+    target_hw:  str = '*'
+    other:      str = '*'
+
+def cpe_parse(cpe_str: str) -> CPE:
+    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)
+
+    if len(res) < 3:
+        return CPE()            # input seems to be faulty, return default CPE
+    elif res[1] == '2.3':
+        return CPE(*res[3:])    # input seems to be CPE format 2.3
+    else:
+        return CPE(*res[2:])    # input seems to be CPE format 2.2

repology/parsers/parsers/gentoo.py

@@ -17,9 +17,11 @@
 
 import os
 import xml.etree.ElementTree
+
 from dataclasses import dataclass, field
+from typing import Dict, Iterable, List, Optional, Set, Tuple
+from repology.parsers.cpe import cpe_parse
 from typing import Iterable
-
 from repology.logger import Logger
 from repology.package import PackageFlags
 from repology.packagemaker import NameType, PackageFactory, PackageMaker
@@ -179,8 +181,8 @@ def iter_parse(self, path: str, factory: PackageFactory) -> Iterable[PackageMake
                 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)
+                    pkg.add_cpe(cpe.part, cpe.vendor)
 
                 for ebuild in _iter_ebuilds(path, category, package):
                     subpkg = pkg.clone(append_ident='/' + ebuild)

repology/test/test_cpe.py

@@ -0,0 +1,45 @@
+#!/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, CPE
+
+
+class TestCpe(unittest.TestCase):
+    def test_cpe_parse(self) -> None:
+        self.assertIsInstance(cpe_parse('foo:bar'), CPE)
+        self.assertEqual(cpe_parse('foo:bar'), CPE(part='*', vendor='*', product='*', version='*', update='*', edition='*', lang='*', sw_edition='*', target_sw='*', target_hw='*', other='*'))
+        self.assertEqual(cpe_parse('foobar'), CPE(part='*', vendor='*', product='*', version='*', update='*', edition='*', lang='*', sw_edition='*', target_sw='*', target_hw='*', other='*'))
+        self.assertEqual(cpe_parse('cpe:2.3:a:andreas_mueller:cdrdao'), CPE(part='andreas_mueller', vendor='cdrdao', product='*', version='*', update='*', edition='*', lang='*', sw_edition='*', target_sw='*', target_hw='*', other='*'))
+        self.assertEqual(cpe_parse('cpe:/a:archive\\:\\:tar_project:archive\\:\\:tar'), CPE(part='archive\\:\\:tar_project', vendor='archive\\:\\:tar', product='*', version='*', update='*', edition='*', lang='*', sw_edition='*', target_sw='*', target_hw='*', other='*'))
+        self.assertEqual(cpe_parse('1:2:foo\\:bar'), CPE(part='foo\\:bar', vendor='*', product='*', version='*', update='*', edition='*', lang='*', sw_edition='*', target_sw='*', target_hw='*', other='*'))
+        self.assertEqual(cpe_parse('1:2:foo\\\\:bar'), CPE(part='foo\\\\', vendor='bar', product='*', version='*', update='*', edition='*', lang='*', sw_edition='*', target_sw='*', target_hw='*', other='*'))
+
+    @unittest.expectedFailure
+    def test_cpe_parse_failure(self) -> None:
+        self.assertEqual(cpe_parse('a:b'), CPE(part='a', vendor='b', product='*', version='*', update='*', edition='*', lang='*', sw_edition='*', target_sw='*', target_hw='*', other='*'))
+        self.assertEqual(cpe_parse('1:2:foo\\:bar'), CPE(part='foo', vendor='bar', product='*', version='*', update='*', edition='*', lang='*', sw_edition='*', target_sw='*', target_hw='*', other='*'))
+        self.assertEqual(cpe_parse('1:2:foo\\\\:bar'), CPE(part='foo', vendor='bar', product='*', version='*', update='*', edition='*', lang='*', sw_edition='*', target_sw='*', target_hw='*', other='*'))
+
+
+if __name__ == '__main__':
+    unittest.main()