X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-init;h=ae4a575ca3ba80423fcc0fa0579256a0386baacb;hb=16870b42ac68a8704467989cb20c2c571e4749ab;hp=da683657a0b1b38fd54a44dcc35af32dbcc677b6;hpb=ca783e786a2559ecd161c33be17e46d3baaa25be;p=public-inbox.git

diff --git a/script/public-inbox-init b/script/public-inbox-init
index da683657..ae4a575c 100755
--- a/script/public-inbox-init
+++ b/script/public-inbox-init
@@ -1,58 +1,85 @@
-#!/usr/bin/perl -w
-# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
+#!perl -w
+# Copyright (C) 2014-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-#
-# Initializes a public-inbox, basically a wrapper for git-init(1)
 use strict;
-use warnings;
-sub usage {
-	print STDERR <<EOF;
-Usage: public-inbox-init NAME INBOX_DIR HTTP_URL ADDRESS [ADDRESS..]
-EOF
-	exit 1;
-}
+use v5.10.1;
 use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/;
-use PublicInbox::Admin;
-PublicInbox::Admin::require_or_die('-base');
-require PublicInbox::Config;
-require PublicInbox::InboxWritable;
-use File::Temp qw/tempfile/;
-use PublicInbox::Lock;
-use File::Basename qw/dirname/;
-use File::Path qw/mkpath/;
 use Fcntl qw(:DEFAULT);
-use Cwd qw/abs_path/;
+my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
+usage: public-inbox-init NAME INBOX_DIR HTTP_URL ADDRESS [ADDRESS..]
+
+  Initialize a public-inbox
+
+required arguments:
+
+  NAME                the name of the inbox
+  INBOX_DIR           pathname the inbox
+  HTTP_URL            HTTP (or HTTPS) URL
+  ADDRESS             email address(es), may be specified multiple times
+
+options:
+
+  -V2                 use scalable public-inbox-v2-format(5)
+  -L LEVEL            index level `basic', `medium', or `full' (default: full)
+  --ng NEWSGROUP      set NNTP newsgroup name
+  --skip-artnum=NUM   NNTP article numbers to skip
+  --skip-epoch=NUM    epochs to skip (-V2 only)
+  -J JOBS             number of indexing jobs (-V2 only), (default: 4)
+
+See public-inbox-init(1) man page for full documentation.
+EOF
 
-sub x { system(@_) and die join(' ', @_). " failed: $?\n" }
-my $version = undef;
-my $indexlevel = undef;
-my $skip_epoch;
+require PublicInbox::Admin;
+PublicInbox::Admin::require_or_die('-base');
+
+my ($version, $indexlevel, $skip_epoch, $skip_artnum, $jobs, $show_help);
+my $skip_docdata;
+my $ng = '';
 my %opts = (
 	'V|version=i' => \$version,
-	'L|indexlevel=s' => \$indexlevel,
+	'L|index-level|indexlevel=s' => \$indexlevel,
 	'S|skip|skip-epoch=i' => \$skip_epoch,
+	'skip-artnum=i' => \$skip_artnum,
+	'j|jobs=i' => \$jobs,
+	'ng|newsgroup=s' => \$ng,
+	'skip-docdata' => \$skip_docdata,
+	'help|h' => \$show_help,
 );
-GetOptions(%opts) or usage();
+my $usage_cb = sub {
+	print STDERR $help;
+	exit 1;
+};
+GetOptions(%opts) or $usage_cb->();
+if ($show_help) { print $help; exit 0 };
 PublicInbox::Admin::indexlevel_ok_or_die($indexlevel) if defined $indexlevel;
-my $name = shift @ARGV or usage();
-my $inboxdir = shift @ARGV or usage();
-my $http_url = shift @ARGV or usage();
+my $name = shift @ARGV or $usage_cb->();
+my $inboxdir = shift @ARGV or $usage_cb->();
+my $http_url = shift @ARGV or $usage_cb->();
 my (@address) = @ARGV;
-@address or usage();
-my %seen;
+@address or $usage_cb->();
+
+$ng =~ m![^A-Za-z0-9/_\.\-\~\@\+\=:]! and
+	die "--newsgroup `$ng' is not valid\n";
+($ng =~ m!\A\.! || $ng =~ m!\.\z!) and
+	die "--newsgroup `$ng' must not start or end with `.'\n";
 
+require PublicInbox::Config;
 my $pi_config = PublicInbox::Config->default_file;
-my $dir = dirname($pi_config);
-mkpath($dir); # will croak on fatal errors
+require File::Basename;
+my $dir = File::Basename::dirname($pi_config);
+require File::Path;
+File::Path::mkpath($dir); # will croak on fatal errors
 
 # first, we grab a flock to prevent simultaneous public-inbox-init
 # processes from trampling over each other, or exiting with 255 on
 # O_EXCL failure below.  This gets unlocked automatically on exit:
+require PublicInbox::Lock;
 my $lock_obj = { lock_path => "$pi_config.flock" };
 PublicInbox::Lock::lock_acquire($lock_obj);
 
 # git-config will operate on this (and rename on success):
-my ($fh, $pi_config_tmp) = tempfile('pi-init-XXXXXXXX', DIR => $dir);
+require File::Temp;
+my $fh = File::Temp->new(TEMPLATE => 'pi-init-XXXXXXXX', DIR => $dir);
 
 # Now, we grab another lock to use git-config(1) locking, so it won't
 # wait on the lock, unlike some of our internal flock()-based locks.
@@ -65,7 +92,7 @@ sysopen($lockfh, $lockfile, O_RDWR|O_CREAT|O_EXCL) or do {
 	exit(255);
 };
 my $auto_unlink = UnlinkMe->new($lockfile);
-my $perm;
+my ($perm, %seen);
 if (-e $pi_config) {
 	open(my $oh, '<', $pi_config) or die "unable to read $pi_config: $!\n";
 	my @st = stat($oh);
@@ -103,36 +130,35 @@ if (-e $pi_config) {
 	exit(1) if $conflict;
 
 	my $ibx = $cfg->lookup_name($name);
-	if ($ibx) {
-		if (!defined($indexlevel) && $ibx->{indexlevel}) {
-			$indexlevel = $ibx->{indexlevel};
-		}
-	}
+	$indexlevel //= $ibx->{indexlevel} if $ibx;
 }
-close $fh or die "failed to close $pi_config_tmp: $!\n";
+my $pi_config_tmp = $fh->filename;
+close($fh) or die "failed to close $pi_config_tmp: $!\n";
 
 my $pfx = "publicinbox.$name";
 my @x = (qw/git config/, "--file=$pi_config_tmp");
 
-$inboxdir = abs_path($inboxdir);
+require Cwd;
+$inboxdir = Cwd::abs_path($inboxdir);
+die "`\\n' not allowed in `$inboxdir'\n" if $inboxdir =~ /\n/s;
 if (-f "$inboxdir/inbox.lock") {
 	if (!defined $version) {
 		$version = 2;
 	} elsif ($version != 2) {
-		die "$inboxdir is a -V2 repo, -V$version specified\n"
+		die "$inboxdir is a -V2 inbox, -V$version specified\n"
 	}
 } elsif (-d "$inboxdir/objects") {
 	if (!defined $version) {
 		$version = 1;
 	} elsif ($version != 1) {
-		die "$inboxdir is a -V1 repo, -V$version specified\n"
+		die "$inboxdir is a -V1 inbox, -V$version specified\n"
 	}
 }
 
 $version = 1 unless defined $version;
 
 if ($version == 1 && defined $skip_epoch) {
-	die "--skip-epoch is only supported for -V2 repos\n";
+	die "--skip-epoch is only supported for -V2 inboxes\n";
 }
 
 my $ibx = PublicInbox::Inbox->new({
@@ -144,21 +170,36 @@ my $ibx = PublicInbox::Inbox->new({
 });
 
 my $creat_opt = {};
-PublicInbox::InboxWritable->new($ibx, $creat_opt)->init_inbox(0, $skip_epoch);
+if (defined $jobs) {
+	die "--jobs is only supported for -V2 inboxes\n" if $version == 1;
+	die "--jobs=$jobs must be >= 1\n" if $jobs <= 0;
+	$creat_opt->{nproc} = $jobs;
+}
+
+require PublicInbox::InboxWritable;
+$ibx = PublicInbox::InboxWritable->new($ibx, $creat_opt);
+if ($skip_docdata) {
+	$ibx->{indexlevel} //= 'full'; # ensure init_inbox writes xdb
+	$ibx->{indexlevel} eq 'basic' and
+		die "--skip-docdata ignored with --indexlevel=basic\n";
+	$ibx->{-skip_docdata} = $skip_docdata;
+}
+$ibx->init_inbox(0, $skip_epoch, $skip_artnum);
 
 # needed for git prior to v2.1.0
 umask(0077) if defined $perm;
 
 foreach my $addr (@address) {
 	next if $seen{lc($addr)};
-	x(@x, "--add", "$pfx.address", $addr);
+	PublicInbox::Import::run_die([@x, "--add", "$pfx.address", $addr]);
 }
-x(@x, "$pfx.url", $http_url);
-x(@x, "$pfx.inboxdir", $inboxdir);
+PublicInbox::Import::run_die([@x, "$pfx.url", $http_url]);
+PublicInbox::Import::run_die([@x, "$pfx.inboxdir", $inboxdir]);
 
 if (defined($indexlevel)) {
-	x(@x, "$pfx.indexlevel", $indexlevel);
+	PublicInbox::Import::run_die([@x, "$pfx.indexlevel", $indexlevel]);
 }
+PublicInbox::Import::run_die([@x, "$pfx.newsgroup", $ng]) if $ng ne '';
 
 # needed for git prior to v2.1.0
 if (defined $perm) {