feature(keyringctl): rework str simplification for printable uids

libkeyringctl/keyring.py

@@ -5,9 +5,7 @@ from collections.abc import Iterable
 from itertools import chain
 from logging import debug
 from pathlib import Path
-from re import escape
 from re import match
-from re import sub
 from shutil import copytree
 from tempfile import NamedTemporaryFile
 from tempfile import mkdtemp
@@ -33,6 +31,7 @@ from .types import Username
 from .util import filter_fingerprints_by_trust
 from .util import get_cert_paths
 from .util import get_fingerprint_from_partial
+from .util import simplify_ascii
 from .util import transform_fd_to_tmpfile
 
 
@@ -161,7 +160,7 @@ def convert_certificate(  # noqa: ignore=C901
         elif packet.name.endswith("--UserID"):
             current_packet_mode = "uid"
             current_packet_fingerprint = None
-            current_packet_uid = simplify_user_id(Uid(packet_dump_field(packet, "Value")))
+            current_packet_uid = Uid(simplify_ascii(packet_dump_field(packet, "Value")))
 
             uids[current_packet_uid] = packet
         elif packet.name.endswith("--PublicSubkey"):
@@ -493,24 +492,6 @@ def persist_uid_revocations(
             packet_join(packets=[revocation], output=output_file, force=True)
 
 
-def simplify_user_id(user_id: Uid) -> Uid:
-    """Simplify the User ID string to contain more filesystem friendly characters
-
-    Parameters
-    ----------
-    user_id: A User ID string (e.g. 'Foobar McFooface <foobar@foo.face>')
-
-    Returns
-    -------
-    The simplified representation of user_id
-    """
-
-    user_id_str: str = user_id.replace("@", "_at_")
-    user_id_str = sub("[<>]", "", user_id_str)
-    user_id_str = sub("[" + escape(r" !@#$%^&*()_-+=[]{}\|;:,.<>/?") + "]", "_", user_id_str)
-    return Uid(user_id_str)
-
-
 def derive_username_from_fingerprint(keyring_dir: Path, certificate_fingerprint: Fingerprint) -> Optional[Username]:
     """Attempt to derive the username of a public key fingerprint from a keyring directory
 

libkeyringctl/util.py

@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-3.0-or-later
-
 from collections.abc import Iterable
 from collections.abc import Iterator
 from contextlib import contextmanager
@@ -7,7 +6,11 @@ from os import chdir
 from os import environ
 from os import getcwd
 from pathlib import Path
+from re import escape
 from re import split
+from re import sub
+from string import ascii_letters
+from string import digits
 from subprocess import STDOUT
 from subprocess import CalledProcessError
 from subprocess import check_output
@@ -263,3 +266,51 @@ def filter_fingerprints_by_trust(trusts: Dict[Fingerprint, Trust], trust: Trust)
             filter(lambda item: trust == item[1], trusts.items()),
         )
     )
+
+
+simple_printable: str = ascii_letters + digits + "_-.+@"
+ascii_mapping: Dict[str, str] = {
+    "àáâãäæąăǎа": "a",
+    "ćçĉċč": "c",
+    "ďđ": "d",
+    "éèêëęēĕėěɇ": "e",
+    "ĝğġģ": "g",
+    "ĥħȟ": "h",
+    "ìíîïĩīĭįıij": "i",
+    "ĵɉ": "j",
+    "ķ": "k",
+    "ł": "l",
+    "ńņň": "n",
+    "òóôõöøŏőðȍǿ": "o",
+    "śș": "s",
+    "ß": "ss",
+    "ț": "t",
+    "úûüȗűȕù": "u",
+    "ýÿ": "y",
+    "źż": "z",
+}
+ascii_mapping_lookup: Dict[str, str] = {}
+for key, value in ascii_mapping.items():
+    for c in key:
+        if c in ascii_mapping_lookup:
+            raise Exception(f"duplicate ascii mapping: {c}")
+        ascii_mapping_lookup[c] = value
+        ascii_mapping_lookup[c.upper()] = value.upper()
+
+
+def simplify_ascii(_str: str) -> str:
+    """Simplify a string to contain more filesystem and printable friendly characters
+
+    Parameters
+    ----------
+    _str: A string to simplify (e.g. 'Foobar McFooface <foobar@foo.face>')
+
+    Returns
+    -------
+    The simplified representation of _str
+    """
+    _str = _str.strip("<")
+    _str = _str.strip(">")
+    _str = "".join([ascii_mapping_lookup.get(char) or char for char in _str])
+    _str = sub("[^" + escape(simple_printable) + "]", "_", _str)
+    return _str

libkeyringctl/verify.py

@@ -10,7 +10,6 @@ from typing import Set
 from libkeyringctl.keyring import export
 from libkeyringctl.keyring import get_fingerprints_from_paths
 from libkeyringctl.keyring import is_pgp_fingerprint
-from libkeyringctl.keyring import simplify_user_id
 from libkeyringctl.keyring import transform_fingerprint_to_keyring_path
 from libkeyringctl.keyring import transform_username_to_keyring_path
 from libkeyringctl.sequoia import packet_dump_field
@@ -20,6 +19,7 @@ from libkeyringctl.types import PacketKind
 from libkeyringctl.types import Uid
 from libkeyringctl.util import get_cert_paths
 from libkeyringctl.util import get_fingerprint_from_partial
+from libkeyringctl.util import simplify_ascii
 from libkeyringctl.util import system
 
 
@@ -161,7 +161,7 @@ def verify_integrity(certificate: Path, all_fingerprints: Set[Fingerprint]) -> N
                             kind = kinds[0]
                             if kind != "User":
                                 raise Exception(f"Unexpected packet in file {str(uid_path)}: {kind}")
-                            uid_value = simplify_user_id(Uid(packet_dump_field(packet=uid_path, field="Value")))
+                            uid_value = Uid(simplify_ascii(packet_dump_field(packet=uid_path, field="Value")))
                             if uid_value != uid.name:
                                 raise Exception(f"Unexpected uid in file {str(uid_path)}: {uid_value}")
                         elif not uid_path.is_dir():

tests/conftest.py

@@ -25,7 +25,6 @@ from pytest import fixture
 from libkeyringctl.keyring import convert_certificate
 from libkeyringctl.keyring import export
 from libkeyringctl.keyring import get_fingerprints_from_keyring_files
-from libkeyringctl.keyring import simplify_user_id
 from libkeyringctl.sequoia import certify
 from libkeyringctl.sequoia import key_extract_certificate
 from libkeyringctl.sequoia import key_generate
@@ -35,6 +34,7 @@ from libkeyringctl.types import Fingerprint
 from libkeyringctl.types import Uid
 from libkeyringctl.types import Username
 from libkeyringctl.util import cwd
+from libkeyringctl.util import simplify_ascii
 from libkeyringctl.util import system
 
 test_keys: Dict[Username, List[Path]] = defaultdict(list)
@@ -133,7 +133,7 @@ def create_uid_certification(
             certificate: Path = test_certificates[certified][0]
             fingerprint: Fingerprint = Fingerprint(test_keyring_certificates[certified][0].name)
             issuer_fingerprint: Fingerprint = Fingerprint(test_keyring_certificates[issuer][0].name)
-            simplified_uid = simplify_user_id(uid)
+            simplified_uid = Uid(simplify_ascii(uid))
 
             output: Path = (
                 working_dir