From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 4/6] searchidx: simplify quote-splitting in index_body
Date: Fri, 3 Jan 2020 08:46:01 +0000 [thread overview]
Message-ID: <20200103084603.8405-5-e@80x24.org> (raw)
In-Reply-To: <20200103084603.8405-1-e@80x24.org>
We now use the same regexp View::add_text_body uses.
---
lib/PublicInbox/SearchIdx.pm | 28 ++++++++--------------------
1 file changed, 8 insertions(+), 20 deletions(-)
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 62e836e0..47537ed4 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -199,12 +199,12 @@ sub index_old_diff_fn {
}
sub index_diff ($$$) {
- my ($self, $lines, $doc) = @_;
+ my ($self, $txt, $doc) = @_;
my %seen;
my $in_diff;
my @xnq;
my $xnq = \@xnq;
- foreach (@$lines) {
+ foreach (split(/\n/, $txt)) {
if ($in_diff && s/^ //) { # diff context
index_diff_inc($self, $_, 'XDFCTX', $xnq);
} elsif (/^-- $/) { # email signature begins
@@ -278,20 +278,17 @@ sub index_diff ($$$) {
}
sub index_body ($$$) {
- my ($self, $lines, $doc) = @_;
- my $txt = join("\n", @$lines);
+ my ($self, $txt, $doc) = @_;
if ($doc) {
# does it look like a diff?
if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
- $txt = undef;
- index_diff($self, $lines, $doc);
+ index_diff($self, $txt, $doc);
} else {
index_text($self, $txt, 1, 'XNQ');
}
} else {
index_text($self, $txt, 0, 'XQUOT');
}
- @$lines = ();
}
sub index_xapian { # msg_iter callback
@@ -306,19 +303,10 @@ sub index_xapian { # msg_iter callback
my ($s, undef) = msg_part_text($part, $ct);
defined $s or return;
- my (@orig, @quot);
- my @lines = split(/\n/, $s);
- while (defined(my $l = shift @lines)) {
- if ($l =~ /^>/) {
- index_body($self, \@orig, $doc) if @orig;
- push @quot, $l;
- } else {
- index_body($self, \@quot, 0) if @quot;
- push @orig, $l;
- }
- }
- index_body($self, \@quot, 0) if @quot;
- index_body($self, \@orig, $doc) if @orig;
+ # split off quoted and unquoted blocks:
+ my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s);
+ $part = $s = undef;
+ index_body($self, $_, /\A>/ ? 0 : $doc) for @sections;
}
sub add_xapian ($$$$$$) {
next prev parent reply other threads:[~2020-01-03 8:46 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-03 8:45 [PATCH 0/6] searchidx: minor fix and some cleanups Eric Wong
2020-01-03 8:45 ` [PATCH 1/6] searchidx: index_diff: allow /^$/ line as diff context Eric Wong
2020-01-03 8:45 ` [PATCH 2/6] searchidx: split off index_xapian for msg_iter Eric Wong
2020-01-03 8:46 ` [PATCH 3/6] searchidx: add_message: fix and make use of prototypes Eric Wong
2020-01-03 8:46 ` Eric Wong [this message]
2020-01-03 8:46 ` [PATCH 5/6] searchidx: index_text: use Xapian parameter names Eric Wong
2020-01-03 8:46 ` [PATCH 6/6] searchidx: remove_message: pedantic fix for v1 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=20200103084603.8405-5-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).