* [PATCH 6/6] viewdiff: favor `qr' to precompile regexps
2020-03-19 8:32 7% [PATCH 0/6] daemon: reduce fragmentation via preload Eric Wong
@ 2020-03-19 8:32 6% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-03-19 8:32 UTC (permalink / raw)
To: meta
We can also avoid `o' regexp modifier, since it isn't
recommended by Perl upstream, anymore (although we don't
have any bugs or unintended behavior because of it).
---
lib/PublicInbox/ViewDiff.pm | 47 ++++++++++++++++++++-----------------
1 file changed, 26 insertions(+), 21 deletions(-)
diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm
index 57a1b5d6..d22c80b9 100644
--- a/lib/PublicInbox/ViewDiff.pm
+++ b/lib/PublicInbox/ViewDiff.pm
@@ -25,7 +25,23 @@ my $ANY = qr![^\n]!;
my $FN = qr!(?:"?[^/\n]+/[^\n]+|/dev/null)!;
# cf. git diff.c :: get_compact_summary
-my $DIFFSTAT_COMMENT = qr/\((?:new|gone|(?:(?:new|mode) [\+\-][lx]))\)/;
+my $DIFFSTAT_COMMENT =
+ qr/(?: *\((?:new|gone|(?:(?:new|mode) [\+\-][lx]))\))? *\z/s;
+my $NULL_TO_BLOB = qr/^(index $OID_NULL\.\.)($OID_BLOB)\b/ms;
+my $BLOB_TO_NULL = qr/^index ($OID_BLOB)(\.\.$OID_NULL)\b/ms;
+my $BLOB_TO_BLOB = qr/^index ($OID_BLOB)\.\.($OID_BLOB)/ms;
+my $EXTRACT_DIFFS = qr/(
+ (?: # begin header stuff, don't capture filenames, here,
+ # but instead wait for the --- and +++ lines.
+ (?:^diff\x20--git\x20$FN\x20$FN$LF)
+
+ # old mode || new mode || copy|rename|deleted|...
+ (?:^[a-z]$ANY+$LF)*
+ )? # end of optional stuff, everything below is required
+ ^index\x20($OID_BLOB)\.\.($OID_BLOB)$ANY*$LF
+ ^---\x20($FN)$LF
+ ^\+{3}\x20($FN)$LF)/msx;
+my $IS_OID = qr/\A$OID_BLOB\z/s;
# link to line numbers in blobs
sub diff_hunk ($$$$) {
@@ -62,7 +78,7 @@ sub anchor0 ($$$$) {
# So only do best-effort handling of renames for common cases;
# which works well in practice. If projects put "=>", or trailing
# spaces in filenames, oh well :P
- $fn =~ s/(?: *$DIFFSTAT_COMMENT)? *\z//so;
+ $fn =~ s/$DIFFSTAT_COMMENT//;
$fn =~ s/{(?:.+) => (.+)}/$1/ or $fn =~ s/.* => (.+)/$1/;
$fn = git_unquote($fn);
@@ -132,18 +148,17 @@ sub diff_header ($$$$) {
# no need to capture oid_a and oid_b on add/delete,
# we just linkify OIDs directly via s///e in conditional
- if (($$x =~ s/^(index $OID_NULL\.\.)($OID_BLOB)\b/
- $1 . oid($dctx, $spfx, $2)/emos) ||
- ($$x =~ s/^index ($OID_BLOB)(\.\.$OID_NULL)\b/
- 'index ' . oid($dctx, $spfx, $1) . $2/emos)) {
- } elsif ($$x =~ /^index ($OID_BLOB)\.\.($OID_BLOB)/mos) {
+ if (($$x =~ s/$NULL_TO_BLOB/$1 . oid($dctx, $spfx, $2)/e) ||
+ ($$x =~ s/$BLOB_TO_NULL/
+ 'index ' . oid($dctx, $spfx, $1) . $2/e)) {
+ } elsif ($$x =~ $BLOB_TO_BLOB) {
# modification-only, not add/delete:
# linkify hunk headers later using oid_a and oid_b
@$dctx{qw(oid_a oid_b)} = ($1, $2);
} else {
warn "BUG? <$$x> had no ^index line";
}
- $$x =~ s!^diff --git!anchor1($ctx, $pb) // 'diff --git'!emos;
+ $$x =~ s!^diff --git!anchor1($ctx, $pb) // 'diff --git'!ems;
$$dst .= qq(<span\nclass="head">);
$$dst .= $$x;
$$dst .= '</span>';
@@ -174,17 +189,7 @@ sub diff_before_or_after ($$$) {
sub flush_diff ($$$) {
my ($dst, $ctx, $cur) = @_;
- my @top = split(/(
- (?: # begin header stuff, don't capture filenames, here,
- # but instead wait for the --- and +++ lines.
- (?:^diff\x20--git\x20$FN\x20$FN$LF)
-
- # old mode || new mode || copy|rename|deleted|...
- (?:^[a-z]$ANY+$LF)*
- )? # end of optional stuff, everything below is required
- ^index\x20($OID_BLOB)\.\.($OID_BLOB)$ANY*$LF
- ^---\x20($FN)$LF
- ^\+{3}\x20($FN)$LF)/smxo, $$cur);
+ my @top = split($EXTRACT_DIFFS, $$cur);
$$cur = undef;
my $linkify = $ctx->{-linkify};
@@ -192,8 +197,8 @@ sub flush_diff ($$$) {
while (defined(my $x = shift @top)) {
if (scalar(@top) >= 4 &&
- $top[1] =~ /\A$OID_BLOB\z/os &&
- $top[0] =~ /\A$OID_BLOB\z/os) {
+ $top[1] =~ $IS_OID &&
+ $top[0] =~ $IS_OID) {
$dctx = diff_header($dst, \$x, $ctx, \@top);
} elsif ($dctx) {
my $after = '';
^ permalink raw reply related [relevance 6%]
* [PATCH 0/6] daemon: reduce fragmentation via preload
@ 2020-03-19 8:32 7% Eric Wong
2020-03-19 8:32 6% ` [PATCH 6/6] viewdiff: favor `qr' to precompile regexps Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-03-19 8:32 UTC (permalink / raw)
To: meta
For long-lived daemons, perform immortal allocations as early as
possible to reduce the likelyhood of heap fragmentation due to
mixed-lifetime allocations happening once the process is fully
loaded and serving requests, since per-request allocations
should all be short-lived.
On a side note, I'm wondering if WWW should just preload by
default. I'm not sure if anybody uses public-inbox.cgi (or
should be using it :P). It's not like we don't ship
public-inbox-httpd; and any PSGI implementation could be used
for smaller inboxes (or powerful-enough hardware).
Eric Wong (6):
www: update ->preload for newer modules
wwwlisting: favor "use" over require
wwwlisting: avoid lazy loading JSON module
www: avoid `state' usage to perform allocations up-front
daemon: do more immortal allocations up front
viewdiff: favor `qr' to precompile regexps
lib/PublicInbox/NNTPD.pm | 4 +++
lib/PublicInbox/SolverGit.pm | 13 +++++----
lib/PublicInbox/ViewDiff.pm | 53 +++++++++++++++++++----------------
lib/PublicInbox/WWW.pm | 29 ++++++++++++++-----
lib/PublicInbox/WwwListing.pm | 30 +++++++++-----------
t/www_listing.t | 4 +--
6 files changed, 78 insertions(+), 55 deletions(-)
^ permalink raw reply [relevance 7%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2020-03-19 8:32 7% [PATCH 0/6] daemon: reduce fragmentation via preload Eric Wong
2020-03-19 8:32 6% ` [PATCH 6/6] viewdiff: favor `qr' to precompile regexps 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).