From: "Eric Wong (Contractor, The Linux Foundation)" <e@80x24.org>
To: meta@public-inbox.org
Subject: [WIP 15/17] import: pass "raw" dates to git-fast-import(1)
Date: Thu, 15 Feb 2018 11:08:38 +0000 [thread overview]
Message-ID: <20180215110840.30413-16-e@80x24.org> (raw)
In-Reply-To: <20180215110840.30413-1-e@80x24.org>
For LKML, it appears we need an even more liberal parser than
RFC2822 date parser in git. I have not validated Date::Parse
parses dates correctly, but this at least prevents
git-fast-import(1) from choking.
---
lib/PublicInbox/Import.pm | 65 +++++++++++++++++++++++++++++++++++------------
1 file changed, 49 insertions(+), 16 deletions(-)
diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 811e355..845fbb6 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -12,6 +12,8 @@ use PublicInbox::Spawn qw(spawn);
use PublicInbox::MID qw(mid_mime mid2path);
use PublicInbox::Address;
use PublicInbox::ContentId qw(content_id);
+use Date::Parse qw(str2time);
+use Time::Zone qw(tz_offset);
sub new {
my ($class, $git, $name, $email, $ibx) = @_;
@@ -57,7 +59,7 @@ sub gfi_start {
chomp($self->{tip} = $git->qx(qw(rev-parse --revs-only), $self->{ref}));
my @cmd = ('git', "--git-dir=$git_dir", qw(fast-import
- --quiet --done --date-format=rfc2822));
+ --quiet --done --date-format=raw));
my $rdr = { 0 => fileno($out_r), 1 => fileno($in_w) };
my $pid = spawn(\@cmd, undef, $rdr);
die "spawn fast-import failed: $!" unless defined $pid;
@@ -74,14 +76,7 @@ sub gfi_start {
sub wfail () { die "write to fast-import failed: $!" }
-sub now2822 () {
- my @t = gmtime(time);
- my $day = qw(Sun Mon Tue Wed Thu Fri Sat)[$t[6]];
- my $mon = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec)[$t[4]];
-
- sprintf('%s, %2d %s %d %02d:%02d:%02d +0000',
- $day, $t[3], $mon, $t[5] + 1900, $t[2], $t[1], $t[0]);
-}
+sub now_raw () { time . ' +0000' }
sub norm_body ($) {
my ($mime) = @_;
@@ -189,7 +184,7 @@ sub remove {
print $w "reset $ref\n" or wfail;
}
my $ident = $self->{ident};
- my $now = now2822();
+ my $now = now_raw();
$msg ||= 'rm';
my $len = length($msg) + 1;
print $w "commit $ref\nmark :$commit\n",
@@ -206,6 +201,43 @@ sub remove {
(($self->{tip} = ":$commit"), $cur);
}
+sub parse_date ($) {
+ my ($mime) = @_;
+ my $hdr = $mime->header_obj;
+ my $date = $hdr->header_raw('Date');
+ my ($ts, $zone);
+ my $mid = $hdr->header_raw('Message-ID');
+ if ($date) {
+ $ts = eval { str2time($date) };
+ if ($@) {
+ warn "bad Date: $date in $mid: $@\n";
+ } elsif ($date =~ /\s+([\+\-]\d+)\s*\z/) {
+ $zone = $1;
+ }
+ }
+ unless ($ts) {
+ my @recvd = $hdr->header_raw('Received');
+ foreach my $r (@recvd) {
+ $zone = undef;
+ $r =~ /\s*(\d+\s+[[:alpha:]]+\s+\d{2,4}\s+
+ \d+\D\d+(?:\D\d+)\s+([\+\-]\d+))/osx or next;
+ $zone = $2;
+ $ts = eval { str2time($1) } and last;
+ warn "no date in Received: $r\n";
+ }
+ }
+ $zone ||= '+0000';
+ # "-1200" is the furthest westermost zone offset,
+ # but git fast-import is liberal so we use "-1400"
+ if ($zone >= 1400 || $zone <= -1400) {
+ warn "bogus TZ offset: $zone, ignoring and assuming +0000\n";
+ $zone = '+0000';
+ }
+ $ts ||= time;
+ $ts = 0 if $ts < 0; # git uses unsigned times
+ "$ts $zone";
+}
+
# returns undef on duplicate
# returns the :MARK of the most recent commit
sub add {
@@ -220,7 +252,7 @@ sub add {
# <CAD0k6qSUYANxbjjbE4jTW4EeVwOYgBD=bXkSu=akiYC_CB7Ffw@mail.gmail.com>
$name =~ tr/<>//d;
- my $date = $mime->header('Date');
+ my $date_raw = parse_date($mime);
my $subject = $mime->header('Subject');
$subject = '(no subject)' unless defined $subject;
my $path_type = $self->{path_type};
@@ -246,10 +278,11 @@ sub add {
$mime = $check_cb->($mime) or return;
}
- $mime = $mime->as_string;
my $blob = $self->{mark}++;
- print $w "blob\nmark :$blob\ndata ", length($mime), "\n" or wfail;
- print $w $mime, "\n" or wfail;
+ my $str = $mime->as_string;
+ print $w "blob\nmark :$blob\ndata ", length($str), "\n" or wfail;
+ print $w $str, "\n" or wfail;
+ $str = undef;
# v2: we need this for Xapian
if ($self->{want_object_id}) {
@@ -269,8 +302,8 @@ sub add {
utf8::encode($subject);
# quiet down wide character warnings:
print $w "commit $ref\nmark :$commit\n",
- "author $name <$email> $date\n",
- "committer $self->{ident} ", now2822(), "\n" or wfail;
+ "author $name <$email> $date_raw\n",
+ "committer $self->{ident} ", now_raw(), "\n" or wfail;
print $w "data ", (length($subject) + 1), "\n",
$subject, "\n\n" or wfail;
if ($tip ne '') {
--
EW
next prev parent reply other threads:[~2018-02-15 11:08 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-09 20:51 [v2] one file to rule them all? Eric Wong
2018-02-15 10:55 ` Eric Wong
2018-02-15 11:08 ` [WIP 0/17] initial v2 work based on one-file tree Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 01/17] AUTHORS: add The Linux Foundation Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 02/17] watch_maildir: allow '-' in mail filename Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 03/17] scripts/import_vger_from_mbox: relax From_ line match slightly Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 04/17] import: stop writing legacy ssoma.index by default Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 05/17] import: begin supporting this without ssoma.lock Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 06/17] import: initial handling for v2 Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 07/17] t/import: test for last_object_id insertion Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 08/17] content_id: add test case Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 09/17] searchmsg: add mid_mime import for _extract_mid Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 10/17] scripts/import_vger_from_mbox: support --dry-run option Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 11/17] import: APIs to support v2 use Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 12/17] search: free up 'Q' prefix for a real unique identifier Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:08 ` Eric Wong
2018-02-15 11:08 ` [WIP 13/17] searchidx: fix comment around next_thread_id Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 14/17] address: extract more characters from email addresses Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` Eric Wong (Contractor, The Linux Foundation) [this message]
2018-02-15 11:08 ` [WIP 16/17] scripts/import_vger_from_mbox: use v2 layout for import Eric Wong (Contractor, The Linux Foundation)
2018-02-15 11:08 ` [WIP 17/17] import: quiet down warnings from bogus From: lines Eric Wong (Contractor, The Linux Foundation)
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://public-inbox.org/README
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180215110840.30413-16-e@80x24.org \
--to=e@80x24.org \
--cc=meta@public-inbox.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).