search: query_approxidate: cleanup regexp, more tests

The cleanup doesn't seem to matter, I initially thought I needed
to handle "" (two double quotes) explicitly because that's what
Xapian does to escape a double quote inside a double-quoted
phrase.  It turns out we only need to be able to pass phrases
through to Xapian unmodified, and the existing group of
["\x{201c}\x{201d}] is sufficient for our purposes.

diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 520aa31d3a05371fd9697692e1bd1171a45c0a2a..c5a1bd69cdaa7076c8c4445457146717dd16c6a8 100644 (file)
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -357,7 +357,7 @@ sub query_approxidate {
        my $DQ = qq<"\x{201c}\x{201d}>; # Xapian can use curly quotes
        $_[2] =~ tr/\x00/ /; # Xapian doesn't do NUL, we use it as a placeholder
        my ($terms, $phrase, $to_parse);
-       $_[2] =~ s{([^$DQ]*)([${DQ}][^\"]*[$DQ])?}{
+       $_[2] =~ s{([^$DQ]*)([$DQ][^$DQ]*[$DQ])?}{
                ($terms, $phrase) = ($1, $2);
                $terms =~ s!\b(d|rt|dt):(\S+)!
                        date_parse_prepare($to_parse //= [], $1, $2)!sge;

diff --git a/t/search.t b/t/search.t
index effba1df79744e18dfef153c74f61543f659cf69..124c9acfdf18c74ec5d6ea532cfb6b2b431c7e62 100644 (file)
--- a/t/search.t
+++ b/t/search.t
@@ -603,6 +603,27 @@ SKIP: {
        is($qs, qq[f:bob "hello world" d:19931002..20101002],
                'post-phrase date corrected');
 
+       # Xapian uses "" to escape " inside phrases, we don't explictly
+       # handle that, but are able to pass the result through unchanged
+       for my $pair (["\x{201c}", "\x{201d}"], ['"', '"']) {
+               my ($x, $y) = @$pair;
+               $orig = $qs = qq[${x}hello d:1993-10-02.."" world$y];
+               $s->query_approxidate($g, $qs);
+               is($qs, $orig, 'phrases unchanged \x'.ord($x).'-\x'.ord($y));
+
+               $s->query_approxidate($g, my $tmp = "$qs d:..2010-10-02");
+               is($tmp, "$orig d:..20101002",
+                       'two phrases did not throw off date parsing');
+
+               $orig = $qs = qq[${x}hello d:1993-10-02..$y$x world$y];
+               $s->query_approxidate($g, $qs);
+               is($qs, $orig, 'phrases unchanged \x'.ord($x).'-\x'.ord($y));
+
+               $s->query_approxidate($g, $tmp = "$qs d:..2010-10-02");
+               is($tmp, "$orig d:..20101002",
+                       'two phrases did not throw off date parsing');
+       }
+
        my $x_days_ago = strftime('%Y%m%d', gmtime(time - (5 * 86400)));
        $orig = $qs = qq[broken d:5.days.ago..];
        $s->query_approxidate($g, $qs);