From 45890d532f0ea68f5879b036b22d9dbd4e19754c Mon Sep 17 00:00:00 2001 From: "Eric Wong (Contractor, The Linux Foundation)" Date: Sun, 9 Jun 2019 02:51:47 +0000 Subject: edit: new tool to perform edits This wrapper around V2Writable->replace provides a user-interface for editing messages as single-message mboxes (or the raw text via $EDITOR). --- script/public-inbox-edit | 233 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 233 insertions(+) create mode 100755 script/public-inbox-edit (limited to 'script/public-inbox-edit') diff --git a/script/public-inbox-edit b/script/public-inbox-edit new file mode 100755 index 00000000..ff0351a3 --- /dev/null +++ b/script/public-inbox-edit @@ -0,0 +1,233 @@ +#!/usr/bin/perl -w +# Copyright (C) 2019 all contributors +# License: AGPL-3.0+ +# +# Used for editing messages in a public-inbox. +# Supports v2 inboxes only, for now. +use strict; +use warnings; +use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev); +use PublicInbox::AdminEdit; +use File::Temp qw(tempfile); +use PublicInbox::ContentId qw(content_id); +use PublicInbox::MID qw(mid_clean mids); +PublicInbox::Admin::check_require('-index'); +require PublicInbox::MIME; +require PublicInbox::InboxWritable; + +my $usage = "$0 -m MESSAGE_ID [--all] [INBOX_DIRS]"; +my $opt = { verbose => 1, all => 0, -min_inbox_version => 2, raw => 0 }; +my @opt = qw(mid|m=s file|F=s raw); +GetOptions($opt, @PublicInbox::AdminEdit::OPT, @opt) or + die "bad command-line args\n$usage\n"; + +my $editor = $ENV{MAIL_EDITOR}; # e.g. "mutt -f" +unless (defined $editor) { + my $k = 'publicinbox.mailEditor'; + if (my $cfg = PublicInbox::Admin::config()) { + $editor = $cfg->{lc($k)}; + } + unless (defined $editor) { + warn "\`$k' not configured, trying \`git var GIT_EDITOR'\n"; + chomp($editor = `git var GIT_EDITOR`); + warn "Will use $editor to edit mail\n"; + } +} + +my $mid = $opt->{mid}; +my $file = $opt->{file}; +if (defined $mid && defined $file) { + die "the --mid and --file options are mutually exclusive\n"; +} + +my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt); +PublicInbox::AdminEdit::check_editable(\@ibxs); + +my $found = {}; # cid => [ [ibx, smsg] [, [ibx, smsg] ] ] + +sub find_mid ($) { + my ($mid) = @_; + foreach my $ibx (@ibxs) { + my $over = $ibx->over; + my ($id, $prev); + while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) { + my $ref = $ibx->msg_by_smsg($smsg); + my $mime = PublicInbox::MIME->new($ref); + my $cid = content_id($mime); + my $tuple = [ $ibx, $smsg ]; + push @{$found->{$cid} ||= []}, $tuple + } + delete @$ibx{qw(over mm git search)}; # cleanup + } + $found; +} + +sub show_cmd ($$) { + my ($ibx, $smsg) = @_; + " GIT_DIR=$ibx->{mainrepo}/all.git \\\n git show $smsg->{blob}\n"; +} + +sub show_found () { + foreach my $to_edit (values %$found) { + foreach my $tuple (@$to_edit) { + my ($ibx, $smsg) = @$tuple; + warn show_cmd($ibx, $smsg); + } + } +} + +if (defined($mid)) { + $mid = mid_clean($mid); + $found = find_mid($mid); + my $nr = scalar(keys %$found); + die "No message found for <$mid>\n" unless $nr; + if ($nr > 1) { + warn <<""; +Multiple messages with different content found matching +<$mid>: + + show_found(); + die "Use --force to edit all of them\n" if !$opt->{force}; + warn "Will edit all of them\n"; + } +} else { + open my $fh, '<', $file or die "open($file) failed: $!"; + my $orig = do { local $/; <$fh> }; + my $mime = PublicInbox::MIME->new(\$orig); + my $mids = mids($mime->header_obj); + find_mid($_) for (@$mids); # populates $found + my $cid = content_id($mime); + my $to_edit = $found->{$cid}; + unless ($to_edit) { + my $nr = scalar(keys %$found); + if ($nr > 0) { + warn <<""; +$nr matches to Message-ID(s) in $file, but none matched content +Partial matches below: + + show_found(); + } elsif ($nr == 0) { + $mids = join('', map { " <$_>\n" } @$mids); + warn <<""; +No matching messages found matching Message-ID(s) in $file +$mids + + } + exit 1; + } + $found = { $cid => $to_edit }; +} + +my $tmpl = 'public-inbox-edit-XXXXXX'; +foreach my $to_edit (values %$found) { + my ($edit_fh, $edit_fn) = tempfile($tmpl, TMPDIR => 1); + $edit_fh->autoflush(1); + my ($ibx, $smsg) = @{$to_edit->[0]}; + my $old_raw = $ibx->msg_by_smsg($smsg); + delete @$ibx{qw(over mm git search)}; # cleanup + + my $tmp = $$old_raw; + if (!$opt->{raw}) { + my $oid = $smsg->{blob}; + print $edit_fh "From mboxrd\@$oid Thu Jan 1 00:00:00 1970\n"; + $tmp =~ s/^(>*From )/>$1/gm; + } + print $edit_fh $tmp or + die "failed to write tempfile for editing: $!"; + + # run the editor, respecting spaces/quote +retry_edit: + if (system(qw(sh -c), qq(eval "$editor" '"\$@"'), '--', $edit_fn)) { + if (!(-t STDIN) && !$opt->{force}) { + die "E: $editor failed: $?\n"; + } + print STDERR "$editor failed, "; + print STDERR "continuing as forced\n" if $opt->{force}; + while (!$opt->{force}) { + print STDERR "(r)etry, (c)ontinue, (q)uit?\n"; + chomp(my $op = || ''); + $op = lc($op); + goto retry_edit if $op eq 'r'; + exit $? if $op eq 'q'; + last if $op eq 'c'; # continuing + print STDERR "\`$op' not recognized\n"; + } + } + + # reread the edited file, not using $edit_fh since $EDITOR may + # rename/relink $edit_fn + open my $new_fh, '<', $edit_fn or + die "can't read edited file ($edit_fn): $!\n"; + my $new_raw = do { local $/; <$new_fh> }; + + if (!$opt->{raw}) { + # get rid of the From we added + $new_raw =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s; + + # check if user forgot to purge (in mutt) after editing + if ($new_raw =~ /^From /sm) { + if (-t STDIN) { + print STDERR <<''; +Extra "From " lines detected in new mbox. +Did you forget to purge the original message from the mbox after editing? + + while (1) { + print STDERR <<""; +(y)es to re-edit, (n)o to continue + + chomp(my $op = || ''); + $op = lc($op); + goto retry_edit if $op eq 'y'; + last if $op eq 'n'; # continuing + print STDERR "\`$op' not recognized\n"; + } + } else { # non-interactive path + # unlikely to happen, as extra From lines are + # only a common mistake (for me) with + # interactive use + warn <<""; +W: possible message boundary splitting error + + } + } + # unescape what we escaped: + $new_raw =~ s/^>(>*From )/$1/gm; + } + + my $new_mime = PublicInbox::MIME->new(\$new_raw); + my $old_mime = PublicInbox::MIME->new($old_raw); + + # allow changing Received: and maybe other headers which can + # contain sensitive info. + my $nhdr = $new_mime->header_obj; + my $ohdr = $old_mime->header_obj; + if (($nhdr->as_string eq $ohdr->as_string) && + (content_id($new_mime) eq content_id($old_mime))) { + warn "No change detected to:\n", show_cmd($ibx, $smsg); + + next unless $opt->{verbose}; + # should we consider this machine-parseable? + print "$ibx->{mainrepo}:\n\tNONE\n"; + next; + } + + foreach my $tuple (@$to_edit) { + $ibx = PublicInbox::InboxWritable->new($tuple->[0]); + $smsg = $tuple->[1]; + my $im = $ibx->importer(0); + my $commits = $im->replace($old_mime, $new_mime); + $im->done; + unless ($commits) { + warn "Failed to replace:\n", show_cmd($ibx, $smsg); + next; + } + next unless $opt->{verbose}; + # should we consider this machine-parseable? + print "$ibx->{mainrepo}:"; + if (scalar @$commits) { + print join("\n\t", '', @$commits), "\n"; + } else { + print "\tNONE\n"; + } + } +} -- cgit v1.2.3-24-ge0c7