* [PATCH 2/3] import_mbox: use MboxReader
2021-02-12 7:05 6% [PATCH 0/3] MboxReader usage and changes Eric Wong
@ 2021-02-12 7:05 7% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2021-02-12 7:05 UTC (permalink / raw)
To: meta
It supports more mbox variants and it's trailing newline
behavior is probably more correct despite the previous change
to PublicInbox::Filter::Vger.
---
lib/PublicInbox/InboxWritable.pm | 44 +++++++-------------------------
1 file changed, 9 insertions(+), 35 deletions(-)
diff --git a/lib/PublicInbox/InboxWritable.pm b/lib/PublicInbox/InboxWritable.pm
index c3acc4f9..d4a9040f 100644
--- a/lib/PublicInbox/InboxWritable.pm
+++ b/lib/PublicInbox/InboxWritable.pm
@@ -158,49 +158,23 @@ sub import_maildir {
$im->done;
}
-# asctime: From example@example.com Fri Jun 23 02:56:55 2000
-my $from_strict = qr/^From \S+ +\S+ \S+ +\S+ [^:]+:[^:]+:[^:]+ [^:]+/;
-
-sub mb_add ($$$$) {
- my ($im, $variant, $filter, $msg) = @_;
- $$msg =~ s/(\r?\n)+\z/$1/s;
- if ($variant eq 'mboxrd') {
- $$msg =~ s/^>(>*From )/$1/gms;
- } elsif ($variant eq 'mboxo') {
- $$msg =~ s/^>From /From /gms;
- }
- my $mime = PublicInbox::Eml->new($msg);
+sub _mbox_eml_cb { # MboxReader->mbox* callback
+ my ($eml, $im, $filter) = @_;
if ($filter) {
- my $ret = $filter->scrub($mime) or return;
+ my $ret = $filter->scrub($eml) or return;
return if $ret == REJECT();
- $mime = $ret;
+ $eml = $ret;
}
- $im->add($mime)
+ $im->add($eml);
}
sub import_mbox {
my ($self, $fh, $variant) = @_;
- if ($variant !~ /\A(?:mboxrd|mboxo)\z/) {
- die "variant must be 'mboxrd' or 'mboxo'\n";
- }
+ require PublicInbox::MboxReader;
+ my $cb = PublicInbox::MboxReader->can($variant) or
+ die "$variant not supported\n";
my $im = $self->importer(1);
- my $prev = undef;
- my $msg = '';
- my $filter = $self->filter;
- while (defined(my $l = <$fh>)) {
- if ($l =~ /$from_strict/o) {
- if (!defined($prev) || $prev =~ /^\r?$/) {
- mb_add($im, $variant, $filter, \$msg) if $msg;
- $msg = '';
- $prev = $l;
- next;
- }
- warn "W[$.] $l\n";
- }
- $prev = $l;
- $msg .= $l;
- }
- mb_add($im, $variant, $filter, \$msg) if $msg;
+ $cb->(undef, $fh, \&_mbox_eml_cb, $im, $self->filter);
$im->done;
}
^ permalink raw reply related [relevance 7%]
* [PATCH 0/3] MboxReader usage and changes
@ 2021-02-12 7:05 6% Eric Wong
2021-02-12 7:05 7% ` [PATCH 2/3] import_mbox: use MboxReader Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2021-02-12 7:05 UTC (permalink / raw)
To: meta
*** BLURB HERE ***
Eric Wong (3):
filter/vger: kill trailing newlines aggressively
import_mbox: use MboxReader
mbox_reader: do not chomp non-blank EOL
lib/PublicInbox/Filter/Vger.pm | 2 +-
lib/PublicInbox/InboxWritable.pm | 44 +++++++-------------------------
lib/PublicInbox/MboxReader.pm | 2 +-
t/mbox_reader.t | 22 +++++++++++++++-
4 files changed, 32 insertions(+), 38 deletions(-)
^ permalink raw reply [relevance 6%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2021-02-12 7:05 6% [PATCH 0/3] MboxReader usage and changes Eric Wong
2021-02-12 7:05 7% ` [PATCH 2/3] import_mbox: use MboxReader Eric Wong
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).