| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
|
|
|
|
|
| |
trustdb.c (update_validity): Store temporary full & marginal counts in the
trustdb. (clear_validity, get_validity_counts): Return and clear temp
counts. (store_validation_status): Keep track of which keyids have been
stored. (validate_one_keyblock, validate_key_list): Use per-uid copies of
the full & marginal counts so they can be recalled for multiple levels.
(validate_keys): Only use unused keys for each new round.
(reset_unconnected_keys): Rename to reset_trust_records, and only skip
specifically excluded records.
|
| |
|
|
|
|
|
|
|
| |
capabilities section.
* trustdb.c (is_disabled): Remove incorrect comment.
|
|
|
|
|
|
|
|
|
|
|
| |
interactive import if status is enabled.
* keyring.c (keyring_search): skipfnc didn't work properly with non-keyid
searches. Noted by Stefan Bellon.
* getkey.c (merge_selfsigs_main): Remove some unused code and make sure
that the pk selfsigversion member accounts for 1F direct sigs.
|
|
|
|
|
|
|
|
| |
terminates but check again for the existence of the directory and
continue then.
* openfile.c (copy_options_file): Print a warning if the skeleton
file has active options.
|
|
|
|
|
|
|
|
| |
(check_key_signature2): Pass the ultimately trusted pk directly to
check_key_signature2 to avoid going through the key selection mechanism.
This prevents a deadly embrace when two keys without selfsigs each sign
the other.
|
|
|
|
|
|
|
|
| |
there are no keys to refresh or if there is no keyserver set.
* getkey.c (merge_selfsigs_main): Any valid user ID should make a key
valid, not just the last one. This also fixes Debian bug #174276.
|
|
|
|
|
|
|
|
| |
warnings are not intended to be the be-all and end-all in security checks.
Add note to --group that when used on the command line, it may be
necessary to quote the argument so it is not treated as multiple
arguments. Noted by Stefan Bellon.
|
| |
|
| |
|
|
|
|
|
|
| |
user ID. This is the same as issuing a revocation for the self-signature,
but a much simpler interface to do it.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
disabled keys. Keys specified via keyid (i.e. 0x...) are always included.
* getkey.c (get_pubkey_byname, get_seckey_byname2, get_seckey_bynames),
keyedit.c (keyedit_menu, menu_addrevoker): Include disabled keys in these
functions.
* pkclist.c (build_pk_list): Do not include disabled keys for -r or the
key prompt. Do include disabled keys for the default key and
--encrypt-to.
* trustdb.h, trustdb.c (is_disabled): New skipfnc for skipping disabled
keys.
* gpgv.c (is_disabled): Stub.
* keygen.c (keygen_add_key_expire): Properly handle updating a key
expiration to a no-expiration value.
* keyedit.c (enable_disable_key): Comment.
* import.c (import_one): When in interactive mode and --verbose, don't
repeat some key information twice.
|
| |
|
| |
|
| |
|
|
|
|
|
|
|
|
|
|
| |
* import.c (print_import_check): New.
(import_one): Use it here.
Use merge_keys_and_selfsig in the interactive mode to avoid
wrong key information.
* status.h: Add new status code.
* status.c: Ditto.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
user" rather than "owner". Noted by Stefan Bellon.
* trustdb.h, trustdb.c (trustdb_pending_check): New function to
check if the trustdb needs a check.
* import.c (import_keys_internal): Used here so we don't rebuild
the trustdb if it is still clean.
(import_one, chk_self_sigs): Only mark trustdb dirty if the key
that is being imported has any sigs other than self-sigs.
Suggested by Adrian von Bidder.
* options.skel: Include the required '=' sign in the sample
'group' option. Noted by Stefan Bellon.
* import.c (chk_self_sigs): Don't try and check a subkey as if it
was a signature.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
RECTYPE_TRUST records a bit.
* g10.c (main): Comment out --list-trust-path until it can be implemented.
* import.c (import_one): Warn when importing an Elgamal primary that this
may take some time (to verify self-sigs). (chk_self_sigs): Try and cache
all self-sigs so the keyblock is written to the keyring with a good rich
cache.
* keygen.c (ask_algo): Make the Elgamal sign+encrypt warning stronger, and
remove the RSA sign+encrypt warning.
|
|
|
|
|
|
|
|
|
|
| |
what the program actually does. Noted by Dick Gevers.
* gpg.sgml: Document %-expandos for policy URLs and notations.
* gpg.sgml: Document --pgp8. Clarify that --pgp6 and --pgp7 disable
--throw-keyid.
|
| |
|
| |
|
|
|
|
|
|
|
| |
* options.h (opt): Added mangle-dos-filenames.
* openfile.c (open_outfile) [USE_ONLY_8DOT3]: Truncate the
filename only when this option is set; this is the default.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Minimal isn't always best.
* sign.c (update_keysig_packet): Use the current time rather then a
modification of the original signature time. Make sure that this doesn't
cause a time warp.
* keygen.c (keygen_add_key_expire): Properly handle a key expiration date
in the past (use a duration of 0).
* keyedit.c (menu_expire): Use update_keysig_packet so any sig subpackets
are maintained during the update.
* build-packet.c (build_sig_subpkt): Mark sig expired or unexpired when
the sig expiration subpacket is added. (build_sig_subpkt_from_sig): Handle
making an expiration subpacket from a sig that has already expired (use a
duration of 0).
* packet.h, sign.c (update_keysig_packet), keyedit.c
(menu_set_primary_uid, menu_set_preferences): Add ability to issue 0x18
subkey binding sigs to update_keysig_packet and change all callers.
|
|
|
|
|
|
|
|
|
| |
and make sure that the version record update was successful.
(init_trustdb): If the current parameters aren't what was used for
building the trustdb, the trustdb is invalid.
* tbio.c (tdbio_db_matches_options): Update to work with new trustdbs.
|
|
|
|
|
|
|
|
|
|
|
|
| |
model in the trustdb version record. (tdbio_update_version_record): New
function to update version record values during a trustdb check or update.
(tdbio_dump_record): Show trust model in dump.
* trustdb.c (validate_keys): Call tdbio_update_version_record on success
so that the correct options are stored in the trustdb.
* options.h: rearrange trust models so that CLASSIC is 0 and OPENPGP is 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
pkclist.c (algo_available), revoke.c (gen_revoke): Add --pgp8 mode. This
is basically identical to --pgp7 in all ways except that signing subkeys,
v4 data sigs (including expiration), and SK comments are allowed.
* getkey.c (finish_lookup): Comment.
* main.h, keylist.c (reorder_keyblock), keyedit.c (keyedit_menu): Reorder
user ID display in the --edit-key menu to match that of the --list-keys
display.
* g10.c (add_notation_data): Fix initialization.
|
| |
|
|
|
|
|
|
|
|
|
| |
--pgpX than forcing an algorithm manually. Better still not to use
anything, of course. CVS:
----------------------------------------------------------------------
gpg.sgml CVS:
----------------------------------------------------------------------
|
|
|
|
|
|
|
| |
* convert-from-106: Script to automate the 1.0.6->later conversion. It
marks all secret keys as ultimately trusted, adds the signature caches,
and checks the trustdb.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
expiration date of a subkey. This is not the most optimal solution, but
it is minimal change on the stable branch.
* main.h, keygen.c (do_copy_key_flags): New function to copy key flags, if
any, from one sig to another. (do_add_key_expire): New function to add key
expiration to a sig. (keygen_copy_flags_add_expire): New version of
keygen_add_key_expire that also copies key flags.
(keygen_add_key_flags_and_expire): Use do_add_key_expire.
* import.c (fix_hkp_corruption): Comment.
|
|
|
|
|
|
|
| |
default algorithms from --personal-xxxx, --primary-keyring, changes with
--s2k-digest-algo, the new anonymous recipient improvements, and
non-optimized memory wiping.
|
|
|
|
|
|
| |
--s2k-digest-algo, --personal-cipher-preferences,
--personal-digest-preferences, and --personal-compress-preferences.
|
|
|
|
|
|
|
| |
--cert-notation. Clarify --show-notation and --show-policy-url that
policy URLs and notations can be used in data signatures as well. Add
note about '@' being a required character in notation names.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Return the default algorithm by trying --cipher-algo/--compress-algo, then
the first item in the pref list, then s2k-cipher-algo or ZIP.
* sign.c (sign_file, sign_symencrypt_file), encode.c (encode_simple,
encode_crypt): Call default_cipher_algo and default_compress_algo to get
algorithms.
* g10.c (main): Allow pref selection for compress algo with --openpgp.
|
|
|
|
|
| |
mangling rather than --digest-algo.
|
|
|
|
|
|
|
|
| |
--personal-digest-preferences is, then use the first hash algorithm in the
personal list. If the signing algorithm is DSA, then use the first
160-bit hash algorithm in the personal list. If --pgp2 is set and it's a
v3 RSA key, use MD5.
|
|
|
|
|
|
| |
Rename --default-keyring as --primary-keyring. Stefan wins the naming
contest.
|
|
|
|
|
|
|
|
|
|
|
| |
'@', unless --expert is set. This is to help prevent people from
polluting the (as yet unused) IETF namespace.
* main.h: Comments about default algorithms.
* photoid.c (image_type_to_string): Comments about 3-letter file
extensions.
|
|
|
|
|
|
| |
(sign_symencrypt_file): Use --s2k-digest-algo for passphrase mangling
rather than --digest-algo.
|
| |
|
|
|
|
|
|
|
|
| |
string.
* misc.c (string_to_compress_algo): "none" is a bad choice since it
conflicts with the "none" in setpref.
|
|
|
|
|
| |
version.
|
|
|
|
|
| |
by Haakon Riiser.
|
|
|
|
|
| |
Successfully tested by Gordon Worley.
|
|
|
|
|
|
|
|
| |
* gpg.sgml: Document --trust-model.
* README.W32: Add blurb on how to create a ZIP file, changed requirement
for mingw32 to 0.3.2.
|
|
|
|
|
|
|
|
|
| |
--compress-algo. The old algorithm names still work for backwards
compatibility.
* misc.c (string_to_compress_algo): Allow "none" as an alias for
"uncompressed".
|
|
|
|
|
| |
that was not available when running without verbose on. Noted by Stefan.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
partial length encoding. This is required because OpenPGP allows only for
32 bit length fields. From Werner on stable branch.
* getkey.c (get_pubkey_direct): Renamed to... (get_pubkey_fast): this and
made extern. (get_pubkey_byfprint_fast): New. From Werner on stable
branch.
* keydb.h, import.c (import_one): Use get_pubkey_fast instead of
get_pubkey. We don't need a merged key and actually this might lead to
recursions. (revocation_present): Likewise for search by fingerprint.
From Werner on stable branch.
* g10.c (main): Try to create the trustdb even for non-colon-mode list-key
operations. This is required because getkey needs to know whether a a key
is ultimately trusted. From Werner on stable branch.
|