* [PATCH 00/14] more indexing related improvements
@ 2020-08-10 2:11 6% Eric Wong
2020-08-10 2:11 7% ` [PATCH 07/14] avoid File::Temp::tempfile in more places Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-08-10 2:11 UTC (permalink / raw)
To: meta
publicInbox.indexSequentialShard now works incrementally
-convert also learned all the options -index learned,
so it can be less painful on HDDs.
Eric Wong (14):
index: require --reindex when using --xapian-only
index: --sequential-shard works incrementally
doc: index: some more notes about latest changes
doc: add some notes around -xcpdb / -edit / -purge
index+xcpdb: improve SIG{INT,TERM,HUP,PIPE} behavior
msgmap: tmp_clone: simplify + meaningful filename
avoid File::Temp::tempfile in more places
admin: use a generic veriable name
index: cleanup internal variables
searchidx: use singular `$opt' for consistency with v2
convert: support new -index options
convert: speed up --help
convert: check ARGV more correctly
convert: set No_COW on copied SQLite files
Documentation/public-inbox-convert.pod | 19 ++++
Documentation/public-inbox-edit.pod | 14 +++
Documentation/public-inbox-index.pod | 68 +++++++------
Documentation/public-inbox-init.pod | 2 +-
Documentation/public-inbox-purge.pod | 14 +++
Documentation/public-inbox-xcpdb.pod | 15 ++-
lib/PublicInbox/Admin.pm | 71 ++++++++++++--
lib/PublicInbox/Msgmap.pm | 19 ++--
lib/PublicInbox/SearchIdx.pm | 34 +++----
lib/PublicInbox/V2Writable.pm | 77 ++++++++-------
lib/PublicInbox/Xapcmd.pm | 28 ++++--
script/public-inbox-convert | 131 ++++++++++++++++---------
script/public-inbox-index | 69 ++++---------
script/public-inbox-init | 17 ++--
t/import.t | 5 +-
15 files changed, 357 insertions(+), 226 deletions(-)
^ permalink raw reply [relevance 6%]
* [PATCH 07/14] avoid File::Temp::tempfile in more places
2020-08-10 2:11 6% [PATCH 00/14] more indexing related improvements Eric Wong
@ 2020-08-10 2:11 7% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-08-10 2:11 UTC (permalink / raw)
To: meta
We can use open(..., undef) natively in Perl in t/import.t
In places where we need a pathname, the File::Temp OO API
gives us auto-unlinking for free.
---
lib/PublicInbox/V2Writable.pm | 17 +++++++++--------
script/public-inbox-init | 9 ++++-----
t/import.t | 5 ++---
3 files changed, 15 insertions(+), 16 deletions(-)
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 0b527f18..93646e57 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -20,7 +20,7 @@ use PublicInbox::Msgmap;
use PublicInbox::Spawn qw(spawn popen_rd);
use PublicInbox::SearchIdx qw(log2stack crlf_adjust is_ancestor check_size);
use IO::Handle; # ->autoflush
-use File::Temp qw(tempfile);
+use File::Temp ();
my $OID = qr/[a-f0-9]{40,}/;
# an estimate of the post-packed size to the raw uncompressed size
@@ -733,12 +733,14 @@ sub fill_alternates ($$) {
}
return unless $new;
- my ($fh, $tmp) = tempfile('alt-XXXXXXXX', DIR => $info_dir);
+ my $fh = File::Temp->new(TEMPLATE => 'alt-XXXXXXXX', DIR => $info_dir);
+ my $tmp = $fh->filename;
print $fh join("\n", sort { $alt{$b} <=> $alt{$a} } keys %alt), "\n"
or die "print $tmp: $!\n";
chmod($mode, $fh) or die "fchmod $tmp: $!\n";
close $fh or die "close $tmp $!\n";
rename($tmp, $alt) or die "rename $tmp => $alt: $!\n";
+ $fh->unlink_on_destroy(0);
}
sub git_init {
@@ -819,18 +821,17 @@ sub import_init {
sub diff ($$$) {
my ($mid, $cur, $new) = @_;
- my ($ah, $an) = tempfile('email-cur-XXXXXXXX', TMPDIR => 1);
+ my $ah = File::Temp->new(TEMPLATE => 'email-cur-XXXXXXXX', TMPDIR => 1);
print $ah $cur->as_string or die "print: $!";
- close $ah or die "close: $!";
- my ($bh, $bn) = tempfile('email-new-XXXXXXXX', TMPDIR => 1);
+ $ah->flush or die "flush: $!";
PublicInbox::Import::drop_unwanted_headers($new);
+ my $bh = File::Temp->new(TEMPLATE => 'email-new-XXXXXXXX', TMPDIR => 1);
print $bh $new->as_string or die "print: $!";
- close $bh or die "close: $!";
- my $cmd = [ qw(diff -u), $an, $bn ];
+ $bh->flush or die "flush: $!";
+ my $cmd = [ qw(diff -u), $ah->filename, $bh->filename ];
print STDERR "# MID conflict <$mid>\n";
my $pid = spawn($cmd, undef, { 1 => 2 });
waitpid($pid, 0) == $pid or die "diff did not finish";
- unlink($an, $bn);
}
sub get_blob ($$) {
diff --git a/script/public-inbox-init b/script/public-inbox-init
index b8d71f35..6a959db7 100755
--- a/script/public-inbox-init
+++ b/script/public-inbox-init
@@ -17,7 +17,7 @@ PublicInbox::Admin::require_or_die('-base');
use PublicInbox::Config;
use PublicInbox::InboxWritable;
use PublicInbox::Import;
-use File::Temp qw/tempfile/;
+use File::Temp;
use PublicInbox::Lock;
use File::Basename qw/dirname/;
use File::Path qw/mkpath/;
@@ -52,8 +52,7 @@ my $lock_obj = { lock_path => "$pi_config.flock" };
PublicInbox::Lock::lock_acquire($lock_obj);
# git-config will operate on this (and rename on success):
-my ($fh, $pi_config_tmp) = tempfile('pi-init-XXXXXXXX', DIR => $dir);
-my $cfg_tmp = UnlinkMe->new($pi_config_tmp);
+my $fh = File::Temp->new(TEMPLATE => 'pi-init-XXXXXXXX', DIR => $dir);
# Now, we grab another lock to use git-config(1) locking, so it won't
# wait on the lock, unlike some of our internal flock()-based locks.
@@ -110,7 +109,8 @@ if (-e $pi_config) {
}
}
}
-close $fh or die "failed to close $pi_config_tmp: $!\n";
+my $pi_config_tmp = $fh->filename;
+close($fh) or die "failed to close $pi_config_tmp: $!\n";
my $pfx = "publicinbox.$name";
my @x = (qw/git config/, "--file=$pi_config_tmp");
@@ -177,7 +177,6 @@ if (defined $perm) {
rename $pi_config_tmp, $pi_config or
die "failed to rename `$pi_config_tmp' to `$pi_config': $!\n";
-delete $cfg_tmp->{file};
$auto_unlink->DESTROY;
package UnlinkMe;
diff --git a/t/import.t b/t/import.t
index 440e8994..9a88416f 100644
--- a/t/import.t
+++ b/t/import.t
@@ -9,7 +9,6 @@ use PublicInbox::Git;
use PublicInbox::Import;
use PublicInbox::Spawn qw(spawn);
use Fcntl qw(:DEFAULT SEEK_SET);
-use File::Temp qw/tempfile/;
use PublicInbox::TestCommon;
use MIME::Base64 3.05; # Perl 5.10.0 / 5.9.2
my ($dir, $for_destroy) = tmpdir();
@@ -37,11 +36,11 @@ if ($v2) {
is($mime->as_string, $$raw_email, 'string matches');
is($smsg->{raw_bytes}, length($$raw_email), 'length matches');
my @cmd = ('git', "--git-dir=$git->{git_dir}", qw(hash-object --stdin));
- my $in = tempfile();
+ open my $in, '+<', undef or BAIL_OUT "open(+<): $!";
print $in $mime->as_string or die "write failed: $!";
$in->flush or die "flush failed: $!";
seek($in, 0, SEEK_SET);
- my $out = tempfile();
+ open my $out, '+<', undef or BAIL_OUT "open(+<): $!";
my $pid = spawn(\@cmd, {}, { 0 => $in, 1 => $out });
is(waitpid($pid, 0), $pid, 'waitpid succeeds on hash-object');
is($?, 0, 'hash-object');
^ permalink raw reply related [relevance 7%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2020-08-10 2:11 6% [PATCH 00/14] more indexing related improvements Eric Wong
2020-08-10 2:11 7% ` [PATCH 07/14] avoid File::Temp::tempfile in more places 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).