* trustdb.c (validate_keys): Give a little more information while
rebuilding trustdb.
* pkclist.c (do_edit_ownertrust): Clarify "don't know".
* g10.c (main): Default to --no-mangle-dos-filenames.
show_notation): Collapse the old print_notation_data into show_policy()
and show_notation() so there is only one function to print notations and
policy URLs.
* options.h, main.h, g10.c (main), keyedit.c (print_and_check_one_sig),
keylist.c (list_one, list_keyblock_print), pkclist.c (do_edit_ownertrust),
sign.c (mk_notation_and_policy): New "list-options" and "verify-options"
commands. These replace the existing --show-photos/--no-show-photos,
--show-notation/--no-show-notation,
--show-policy-url/--no-show-policy-url, and --show-keyring options. The
new method is more flexible since a user can specify (for example) showing
photos during sig verification, but not in key listings. The old options
are emulated.
getkey.c, keydb.c, openfile.c, plaintext.c, status.c, gpgv.c, keygen.c,
options.h, sig-check.c, tdbio.h, encode.c, mainproc.c, parse-packet.c,
signal.c, textfilter.c: Edit all preprocessor instructions to remove
whitespace before the '#'. This is not required by C89, but there are some
compilers out there that don't like it.
(do_export_stream), import.c (remove_bad_stuff, import), parse-packet.c
(dump_sig_subpkt, parse_one_sig_subpkt): Remove vestigal code for the old
sig cache subpacket. This wasn't completely harmless as it caused
subpacket 101 to disappear on import and export.
* options.h, armor.c, cipher.c, g10.c, keyedit.c, pkclist.c, sign.c,
encode.c, getkey.c, revoke.c: The current flags for different levels of
PGP-ness are massively complex. This is step one in simplifying them. No
functional change yet, just use a macro to check for compliance level.
* sign.c (sign_file): Fix bug that causes spurious compression preference
warning.
* sign.c (clearsign_file): Fix bug that prevents proper warning message
from appearing when clearsigning in --pgp2 mode with a non-v3 RSA key.
* main.h, misc.c (compliance_option_string, compliance_string,
compliance_failure), pkclist.c (build_pk_list), sign.c (sign_file,
clearsign_file), encode.c (encode_crypt, write_pubkey_enc_from_list): New
functions to put the "this message may not be usable...." warning in one
place.
* options.h, g10.c (main): Part two of the simplification. Use a single
enum to indicate what we are compliant to (1991, 2440, PGPx, etc.)
* g10.c (main): Show errors for failure in export, send-keys, recv-keys,
and refresh-keys.
* options.h, g10.c (main): Give algorithm warnings for algorithms chosen
against the --pgpX and --openpgp rules.
* keydb.h, pkclist.c (algo_available): Make TIGER192 invalid in --openpgp
mode.
* sign.c (sign_file), pkclist.c (algo_available): Allow passing a hint of
0.
TM_CLASSIC or TM_PGP.
* trustdb.h, trustdb.c (trust_string, get_ownertrust_string,
get_validity_string, ask_ownertrust, validate_keys), pkclist.c
(do_edit_ownertrust): Rename trust_string to trust_value_to_string for
naming consistency.
* trustdb.h, trustdb.c (string_to_trust_value): New function to translate
a string to a trust value.
* g10.c (main): Use string_to_trust_value here for --force-ownertrust.
* options.h, g10.c (main), trustdb.c (trust_model_string, init_trustdb,
check_trustdb, update_trustdb, get_validity, validate_one_keyblock): An
"OpenPGP" trust model is misleading since there is no official OpenPGP
trust model. Use "PGP" instead.
* exec.c (exec_write): Cast NULL to void* to properly terminate varargs
list.
* keyedit.c (show_key_with_all_names): Just for safety, catch an invalid
pk algorithm.
* sign.c (make_keysig_packet): Crucial that the call to mksubpkt comes
LAST before the calls to finalize the sig as that makes it possible for
the mksubpkt function to get a reliable pointer to the subpacket area.
* pkclist.c (do_we_trust_pre): If an untrusted key was chosen by a
particular user ID, use that ID as the one to ask about when prompting
whether to use the key anyway. (build_pk_list): Similar change here when
adding keys to the recipient list.
* trustdb.c (update_validity): Fix bug that prevented more than one
validity record per trust record. (get_validity): When retrieving validity
for a (user) supplied user ID, return the validity for that user ID only,
and do not fall back to the general key validity. (validate_one_keyblock):
Some commentary on whether non-self-signed user IDs belong in the web of
trust (arguably, they do).
* trustdb.h, trustdb.c (trust_letter): Make static. (get_ownertrust_info,
get_validity_info): Don't mask the trust level twice.
* trustdb.h, gpgv.c, trustdb.c (get_validity, get_validity_info),
keylist.c (list_keyblock_colon), keyedit.c (show_key_with_all_names_colon,
menu_revuid): Pass a user ID in rather than a namehash, so we only have to
do the hashing in one place.
* packet.h, pkclist.c (build_pk_list), free-packet.c
(release_public_key_parts): Remove unused namehash element for public
keys.
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.
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.
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.
"openpgp" which is classic+trustsigs, "classic" which is classic only, and
"always" which is the same as the current option --always-trust (which
still works). Default is "openpgp".
* trustdb.c (validate_one_keyblock): Use "openpgp" trust model to enable
trust sigs.
* gpgv.c (main), mainproc.c (check_sig_and_print), pkclist.c (do_we_trust,
do_we_trust_pre, check_signatures_trust): Use new --trust-model option in
place of --always-trust.
Prompt for and create a trust signature with "tsign". This is functional,
but needs better UI text.
* build-packet.c (build_sig_subpkt): Able to build trust and regexp
subpackets.
* pkclist.c (do_edit_ownertrust): Comment.
* keydb.h, encode.c (write_pubkey_enc_from_list), g10.c (main), pkclist.c
(build_pk_list): Add --hidden-recipient (-R) and --hidden-encrypt-to,
which do a single-user variation on --throw-keyid. The "hide this key"
flag is carried in bit 0 of the pk_list flags field.
* keyserver.c (parse_keyrec): Fix shadowing warning.
like "fully trusted", "marginally trusted", etc. (get_min_ownertrust):
New. Return minimum ownertrust. (update_min_ownertrust): New. Set
minimum ownertrust. (check_regexp): New. Check a regular epression
against a user ID. (ask_ownertrust): Allow specifying a minimum value.
(get_ownertrust_info): Follow the minimum ownertrust when returning a
letter. (clear_validity): Remove minimum ownertrust when a key becomes
invalid. (release_key_items): Release regexp along with the rest of the
info. (validate_one_keyblock, validate_keys): Build a trust sig chain
while validating. Call check_regexp for regexps. Use the minimum
ownertrust if the user does not specify a genuine ownertrust.
* pkclist.c (do_edit_ownertrust): Only allow user to select a trust level
greater than the minimum value.
* parse-packet.c (can_handle_critical): Can handle critical trust and
regexp subpackets.
* trustdb.h, trustdb.c (clear_ownertrusts), delkey.c (do_delete_key),
import.c (import_one): Rename clear_ownertrust to clear_ownertrusts and
have it clear the min_ownertrust value as well.
* keylist.c (list_keyblock_print): Indent uid to match pub and sig.
* options.skel: The PGP LDAP keyserver is back. Use MIT keyserver as a
sample rather than cryptnet as cryptnet does not support searching yet.
* keyedit.c (show_key_with_all_names): Fix error message (preferences are
userid/selfsig and not key specific).
* encode.c (encode_simple,encode_crypt): Use new style CTB for
compressssed packets when using MDC. We need to do this so that
concatenated messages are properly decrypted. Old style
compression assumes that it is the last packet; given that we
can't determine the length in advance, the uncompressor does not
know where to start. Actually we should use the new CTB always
but this would break PGP 2 compatibility.
* parse-packet.c (parse): Special treatment for new style CTB
compressed packets.
* build-packet.c (do_mdc): Removed. Was not used.
(do_encrypted_mdc): Count the version number and the MDC packet.
* export.c (do_export_stream): Fix noop bug in exporting sensitive
revocation keys.
* pkclist.c (do_edit_ownertrust): Comment out the option for showing trust
paths until it can be implemented.
symmetric compressed files.
* encode.c (encode_simple, encode_crypt): If we are not using a MDC,
compress even if a file is already compressed. This is to help against
the chosen ciphertext attack.
* pkclist.c (select_algo_from_prefs): Fix requested algorithm bug so the
request succeeds even if the requested algorithm is not the first found.
* cipher.c (write_header), encode.c (use_mdc, encode_simple, encode_crypt,
encrypt_filter), g10.c (main): Be more eager to use a MDC. We use a MDC
if the keys directly support it, if the keys list AES (any) or TWOFISH
anywhere in the prefs, or if the cipher chosen does not have a 64 bit
blocksize.
David Shaw