lei q: use git approxidate with d:, dt: and rt: ranges

[public-inbox.git] / lib / PublicInbox / Search.pm

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index a4b40f94976b9c8897a322e032637d115d6dd923..f42d70e3c6c8fda84bd3be15e5d4c2a30b5bbbde 100644 (file)
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -6,8 +6,9 @@
 package PublicInbox::Search;
 use strict;
 use parent qw(Exporter);
-our @EXPORT_OK = qw(retry_reopen int_val get_pct);
+our @EXPORT_OK = qw(retry_reopen int_val get_pct xap_terms);
 use List::Util qw(max);
+use POSIX qw(strftime);
 
 # values for searching, changing the numeric value breaks
 # compatibility with old indices (so don't change them it)
@@ -259,6 +260,72 @@ sub reopen {
        $self; # make chaining easier
 }
 
+# Convert git "approxidate" ranges to something usable with our
+# Xapian indices.  At the moment, Xapian only offers a C++-only API
+# and neither the SWIG nor XS bindings allow us to use custom code
+# to parse dates (and libgit2 doesn't expose git__date_parse, either,
+# so we're running git-rev-parse(1)).
+sub date_range {
+       my ($git, $pfx, $range) = @_;
+       # are we inside a parenthesized statement?
+       my $end = $range =~ s/([\)\s]*)\z// ? $1 : '';
+       my @r = split(/\.\./, $range, 2);
+
+       # expand "d:20101002" => "d:20101002..20101003" and like
+       # n.b. git doesn't do YYYYMMDD w/o '-', it needs YYYY-MM-DD
+       if ($pfx eq 'd') {
+               if (!defined($r[1])) {
+                       $r[0] =~ s/\A([0-9]{4})([0-9]{2})([0-9]{2})\z/$1-$2-$3/;
+                       $r[0] = $git->date_parse($r[0]);
+                       $r[1] = $r[0] + 86400;
+                       for my $x (@r) {
+                               $x = strftime('%Y%m%d', gmtime($x));
+                       }
+               } else {
+                       for my $x (@r) {
+                               next if $x eq '' || $x =~ /\A[0-9]{8}\z/;
+                               $x = strftime('%Y%m%d',
+                                               gmtime($git->date_parse($x)));
+                       }
+               }
+       } elsif ($pfx eq 'dt') {
+               if (!defined($r[1])) { # git needs gaps and not /\d{14}/
+                       $r[0] =~ s/\A([0-9]{4})([0-9]{2})([0-9]{2})
+                                       ([0-9]{2})([0-9]{2})([0-9]{2})\z
+                               /$1-$2-$3 $4:$5:$6/x;
+                       $r[0] = $git->date_parse($r[0]);
+                       $r[1] = $r[0] + 86400;
+                       for my $x (@r) {
+                               $x = strftime('%Y%m%d%H%M%S', gmtime($x));
+                       }
+               } else {
+                       for my $x (@r) {
+                               next if $x eq '' || $x =~ /\A[0-9]{14}\z/;
+                               $x = strftime('%Y%m%d%H%M%S',
+                                               gmtime($git->date_parse($x)));
+                       }
+               }
+       } else { # "rt", let git interpret "YYYY", deal with Y10K later :P
+               for my $x (@r) {
+                       next if $x eq '' || $x =~ /\A[0-9]{5,}\z/;
+                       $x = $git->date_parse($x);
+               }
+               $r[1] //= $r[0] + 86400;
+       }
+       "$pfx:".join('..', @r).$end;
+}
+
+sub query_argv_to_string {
+       my (undef, $git, $argv) = @_;
+       join(' ', map {;
+               if (s!\b(d|rt|dt):(.+)\z!date_range($git, $1, $2)!sge) {
+                       $_;
+               } else {
+                       /\s/ ? (s/\A(\w+:)// ? qq{$1"$_"} : qq{"$_}) : $_
+               }
+       } @$argv);
+}
+
 # read-only
 sub mset {
        my ($self, $query_string, $opts) = @_;
@@ -336,7 +403,7 @@ sub _enquire_once { # retry_reopen callback
        }
 
        # `mairix -t / --threads' or JMAP collapseThreads
-       if ($opts->{thread} && has_threadid($self)) {
+       if ($opts->{threads} && has_threadid($self)) {
                $enquire->set_collapse_key(THREADID);
        }
        $enquire->get_mset($opts->{offset} || 0, $opts->{limit} || 50);
@@ -432,4 +499,22 @@ sub get_pct ($) { # mset item
        $n > 99 ? 99 : $n;
 }
 
+sub xap_terms ($$;@) {
+       my ($pfx, $xdb_or_doc, @docid) = @_; # @docid may be empty ()
+       my %ret;
+       eval {
+               my $end = $xdb_or_doc->termlist_end(@docid);
+               my $cur = $xdb_or_doc->termlist_begin(@docid);
+               for (; $cur != $end; $cur++) {
+                       $cur->skip_to($pfx);
+                       last if $cur == $end;
+                       my $tn = $cur->get_termname;
+                       if (index($tn, $pfx) == 0) {
+                               $ret{substr($tn, length($pfx))} = undef;
+                       }
+               }
+       };
+       \%ret;
+}
+
 1;