user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 6/8] lei_input: common filehandle reader for eml + mbox
Date: Mon, 22 Mar 2021 07:54:00 +0000	[thread overview]
Message-ID: <20210322075402.27834-7-e@80x24.org> (raw)
In-Reply-To: <20210322075402.27834-1-e@80x24.org>

This improve code regularity, and will let us deal with
the "RFC822" messages with "From " line that mutt pipes
to.
---
 lib/PublicInbox/LeiConvert.pm | 30 +++++++--------------
 lib/PublicInbox/LeiImport.pm  | 50 ++++++++++++-----------------------
 lib/PublicInbox/LeiInput.pm   | 17 ++++++++++++
 3 files changed, 44 insertions(+), 53 deletions(-)

diff --git a/lib/PublicInbox/LeiConvert.pm b/lib/PublicInbox/LeiConvert.pm
index 8685c194..51a233bd 100644
--- a/lib/PublicInbox/LeiConvert.pm
+++ b/lib/PublicInbox/LeiConvert.pm
@@ -10,13 +10,18 @@ use PublicInbox::Eml;
 use PublicInbox::LeiStore;
 use PublicInbox::LeiOverview;
 
-sub mbox_cb {
+sub mbox_cb { # MboxReader callback used by PublicInbox::LeiInput::input_fh
 	my ($eml, $self) = @_;
 	my $kw = PublicInbox::MboxReader::mbox_keywords($eml);
 	$eml->header_set($_) for qw(Status X-Status);
 	$self->{wcb}->(undef, { kw => $kw }, $eml);
 }
 
+sub eml_cb { # used by PublicInbox::LeiInput::input_fh
+	my ($self, $eml) = @_;
+	$self->{wcb}->(undef, { kw => [] }, $eml);
+}
+
 sub net_cb { # callback for ->imap_each, ->nntp_each
 	my (undef, undef, $kw, $eml, $self) = @_; # @_[0,1]: url + uid ignored
 	$self->{wcb}->(undef, { kw => $kw }, $eml);
@@ -27,30 +32,15 @@ sub mdir_cb {
 	$self->{wcb}->(undef, { kw => $kw }, $eml);
 }
 
-sub convert_fh ($$$$) {
-	my ($self, $ifmt, $fh, $name) = @_;
-	if ($ifmt eq 'eml') {
-		my $buf = do { local $/; <$fh> } //
-			return $self->{lei}->child_error(1 << 8, <<"");
-error reading $name: $!
-
-		my $eml = PublicInbox::Eml->new(\$buf);
-		$self->{wcb}->(undef, { kw => [] }, $eml);
-	} else {
-		PublicInbox::MboxReader->$ifmt($fh, \&mbox_cb, $self);
-	}
-}
-
 sub do_convert { # via wq_do
 	my ($self) = @_;
 	my $lei = $self->{lei};
-	my $in_fmt = $lei->{opt}->{'in-format'};
-	my $mics;
+	my $ifmt = $lei->{opt}->{'in-format'};
 	if (my $stdin = delete $self->{0}) {
-		convert_fh($self, $in_fmt, $stdin, '<stdin>');
+		$self->input_fh($ifmt, $stdin, '<stdin>');
 	}
 	for my $input (@{$self->{inputs}}) {
-		my $ifmt = lc($in_fmt // '');
+		my $ifmt = lc($ifmt // '');
 		if ($input =~ m!\Aimaps?://!) {
 			$lei->{net}->imap_each($input, \&net_cb, $self);
 			next;
@@ -65,7 +55,7 @@ sub do_convert { # via wq_do
 					($ifmt eq 'eml' ? ['none'] :
 					PublicInbox::MboxLock->defaults);
 			my $mbl = PublicInbox::MboxLock->acq($input, 0, $m);
-			convert_fh($self, $ifmt, $mbl->{fh}, $input);
+			$self->input_fh($ifmt, $mbl->{fh}, $input);
 		} elsif (-d _) {
 			PublicInbox::MdirReader::maildir_each_eml($input,
 							\&mdir_cb, $self);
diff --git a/lib/PublicInbox/LeiImport.pm b/lib/PublicInbox/LeiImport.pm
index e587ada8..767cae60 100644
--- a/lib/PublicInbox/LeiImport.pm
+++ b/lib/PublicInbox/LeiImport.pm
@@ -9,15 +9,20 @@ use parent qw(PublicInbox::IPC PublicInbox::LeiInput);
 use PublicInbox::Eml;
 use PublicInbox::PktOp qw(pkt_do);
 
-sub _import_eml { # MboxReader callback
-	my ($eml, $lei, $mbox_keywords) = @_;
+sub eml_cb { # used by PublicInbox::LeiInput::input_fh
+	my ($self, $eml) = @_;
 	my $vmd;
-	if ($mbox_keywords) {
-		my $kw = $mbox_keywords->($eml);
+	if ($self->{-import_kw}) { # FIXME
+		my $kw = PublicInbox::MboxReader::mbox_keywords($eml);
 		$vmd = { kw => $kw } if scalar(@$kw);
 	}
-	my $xoids = $lei->{ale}->xoids_for($eml);
-	$lei->{sto}->ipc_do('set_eml', $eml, $vmd, $xoids);
+	my $xoids = $self->{lei}->{ale}->xoids_for($eml);
+	$self->{lei}->{sto}->ipc_do('set_eml', $eml, $vmd, $xoids);
+}
+
+sub mbox_cb { # MboxReader callback used by PublicInbox::LeiInput::input_fh
+	my ($eml, $self) = @_;
+	eml_cb($self, $eml);
 }
 
 sub import_done_wait { # dwaitpid callback
@@ -46,7 +51,7 @@ sub net_merge_complete { # callback used by LeiAuth
 sub import_start {
 	my ($lei) = @_;
 	my $self = $lei->{imp};
-	$lei->ale;
+	$lei->ale; # initialize for workers to read
 	my $j = $lei->{opt}->{jobs} // scalar(@{$self->{inputs}}) || 1;
 	if (my $net = $lei->{net}) {
 		# $j = $net->net_concurrency($j); TODO
@@ -67,8 +72,8 @@ sub lei_import { # the main "lei import" method
 	my ($lei, @inputs) = @_;
 	my $sto = $lei->_lei_store(1);
 	$sto->write_prepare($lei);
-	$lei->{opt}->{kw} //= 1;
 	my $self = $lei->{imp} = bless {}, __PACKAGE__;
+	$self->{-import_kw} = $lei->{opt}->{kw} // 1;
 	$self->prepare_inputs($lei, \@inputs) or return;
 	import_start($lei);
 }
@@ -83,27 +88,6 @@ sub ipc_atfork_child {
 	undef;
 }
 
-sub _import_fh {
-	my ($lei, $fh, $input, $ifmt) = @_;
-	my $kw = $lei->{opt}->{kw} ?
-		PublicInbox::MboxReader->can('mbox_keywords') : undef;
-	eval {
-		if ($ifmt eq 'eml') {
-			my $buf = do { local $/; <$fh> } //
-				return $lei->child_error(1 << 8, <<"");
-error reading $input: $!
-
-			my $eml = PublicInbox::Eml->new(\$buf);
-			_import_eml($eml, $lei, $kw);
-		} else { # some mbox (->can already checked in call);
-			my $cb = PublicInbox::MboxReader->reads($ifmt) //
-				die "BUG: bad fmt=$ifmt";
-			$cb->(undef, $fh, \&_import_eml, $lei, $kw);
-		}
-	};
-	$lei->child_error(1 << 8, "$input: $@") if $@;
-}
-
 sub _import_maildir { # maildir_each_eml cb
 	my ($f, $kw, $eml, $sto, $set_kw) = @_;
 	$sto->ipc_do('set_eml', $eml, $set_kw ? { kw => $kw }: ());
@@ -121,7 +105,7 @@ sub import_path_url {
 	# TODO auto-detect?
 	if ($input =~ m!\Aimaps?://!i) {
 		$lei->{net}->imap_each($input, \&_import_net, $lei->{sto},
-					$lei->{opt}->{kw});
+					$self->{-import_kw});
 		return;
 	} elsif ($input =~ m!\A(?:nntps?|s?news)://!i) {
 		$lei->{net}->nntp_each($input, \&_import_net, $lei->{sto}, 0);
@@ -133,14 +117,14 @@ sub import_path_url {
 		my $m = $lei->{opt}->{'lock'} // ($ifmt eq 'eml' ? ['none'] :
 				PublicInbox::MboxLock->defaults);
 		my $mbl = PublicInbox::MboxLock->acq($input, 0, $m);
-		_import_fh($lei, $mbl->{fh}, $input, $ifmt);
+		$self->input_fh($ifmt, $mbl->{fh}, $input);
 	} elsif (-d _ && (-d "$input/cur" || -d "$input/new")) {
 		return $lei->fail(<<EOM) if $ifmt && $ifmt ne 'maildir';
 $input appears to a be a maildir, not $ifmt
 EOM
 		PublicInbox::MdirReader::maildir_each_eml($input,
 					\&_import_maildir,
-					$lei->{sto}, $lei->{opt}->{kw});
+					$lei->{sto}, $self->{-import_kw});
 	} else {
 		$lei->fail("$input unsupported (TODO)");
 	}
@@ -150,7 +134,7 @@ sub import_stdin {
 	my ($self) = @_;
 	my $lei = $self->{lei};
 	my $in = delete $self->{0};
-	_import_fh($lei, $in, '<stdin>', $lei->{opt}->{'in-format'});
+	$self->input_fh($lei->{opt}->{'in-format'}, $in, '<stdin>');
 }
 
 no warnings 'once'; # the following works even when LeiAuth is lazy-loaded
diff --git a/lib/PublicInbox/LeiInput.pm b/lib/PublicInbox/LeiInput.pm
index 776b3151..c62b0893 100644
--- a/lib/PublicInbox/LeiInput.pm
+++ b/lib/PublicInbox/LeiInput.pm
@@ -23,6 +23,23 @@ sub check_input_format ($;$) {
 	1;
 }
 
+# import a single file handle of $name
+# Subclass must define ->eml_cb and ->mbox_cb
+sub input_fh {
+	my ($self, $ifmt, $fh, $name, @args) = @_;
+	if ($ifmt eq 'eml') {
+		my $buf = do { local $/; <$fh> } //
+			return $self->{lei}->child_error(1 << 8, <<"");
+error reading $name: $!
+
+		$self->eml_cb(PublicInbox::Eml->new(\$buf), @args);
+	} else {
+		# prepare_inputs already validated $ifmt
+		my $cb = PublicInbox::MboxReader->reads($ifmt) //
+				die "BUG: bad fmt=$ifmt";
+		$cb->(undef, $fh, $self->can('mbox_cb'), $self, @args);
+	}
+}
 
 sub prepare_inputs {
 	my ($self, $lei, $inputs) = @_;

  parent reply	other threads:[~2021-03-22  7:54 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-22  7:53 [PATCH 0/8] lei input handling improvements Eric Wong
2021-03-22  7:53 ` [PATCH 1/8] lei: support -c <name>=<value> to overrides Eric Wong
2021-03-22  7:53 ` [PATCH 2/8] net_reader: escape nasty chars from Net::NNTP->message Eric Wong
2021-03-22  7:53 ` [PATCH 3/8] lei: share input code between convert and import Eric Wong
2021-03-22  7:53 ` [PATCH 4/8] lei: simplify workers_start and callers Eric Wong
2021-03-22  7:53 ` [PATCH 5/8] mbox_reader: add ->reads method to avoid nonsensical formats Eric Wong
2021-03-22  7:54 ` Eric Wong [this message]
2021-03-22  7:54 ` [PATCH 7/8] lei_input: drop "From " line on single "eml" (message/rfc822) Eric Wong
2021-03-22  7:54 ` [PATCH 8/8] lei import: ignore Status headers in "eml" messages Eric Wong

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=20210322075402.27834-7-e@80x24.org \
    --to=e@80x24.org \
    --cc=meta@public-inbox.org \
    --subject='Re: [PATCH 6/8] lei_input: common filehandle reader for eml + mbox' \
    /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

Code repositories for project(s) associated with this 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).