search: force large mbox result downloads to POST

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

diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 6f6a00331fe99c2ee969383dd4509bb59d13fc10..3fd77d42bff8bc561df675438601dc7a3608df2e 100644 (file)
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -42,20 +42,25 @@ sub call {
 
        # we don't care about multi-value
        my %qp = map {
+               utf8::decode($_);
                my ($k, $v) = split('=', uri_unescape($_), 2);
                $v = '' unless defined $v;
                $v =~ tr/+/ /;
                ($k, $v)
-       } split(/[&;]/, $env->{QUERY_STRING});
+       } split(/[&;]+/, $env->{QUERY_STRING});
        $ctx->{qp} = \%qp;
 
        my $path_info = $env->{PATH_INFO};
        my $method = $env->{REQUEST_METHOD};
 
-       if ($method eq 'POST' &&
-                $path_info =~ m!$INBOX_RE/(git-upload-pack)\z!) {
-               my $path = $2;
-               return invalid_inbox($ctx, $1) || serve_git($ctx, $path);
+       if ($method eq 'POST') {
+               if ($path_info =~ m!$INBOX_RE/(git-upload-pack)\z!) {
+                       my $path = $2;
+                       return invalid_inbox($ctx, $1) ||
+                               serve_git($ctx, $path);
+               } elsif ($path_info =~ m!$INBOX_RE/!o) {
+                       return invalid_inbox($ctx, $1) || mbox_results($ctx);
+               }
        }
        elsif ($method !~ /\AGET|HEAD\z/) {
                return r(405, 'Method Not Allowed');
@@ -96,6 +101,8 @@ sub call {
 
        } elsif ($path_info =~ m!$INBOX_RE/$MID_RE/f/?\z!o) {
                r301($ctx, $1, $2);
+       } elsif ($path_info =~ m!$INBOX_RE/_/text(?:/(.*))?\z!o) {
+               get_text($ctx, $1, $2);
 
        # convenience redirects order matters
        } elsif ($path_info =~ m!$INBOX_RE/([^/]{2,})\z!o) {
@@ -110,8 +117,8 @@ sub call {
 sub preload {
        require PublicInbox::Feed;
        require PublicInbox::View;
-       require PublicInbox::Thread;
-       require Email::MIME;
+       require PublicInbox::SearchThread;
+       require PublicInbox::MIME;
        require Digest::SHA;
        require POSIX;
 
@@ -163,7 +170,7 @@ sub invalid_inbox_mid {
        my $ret = invalid_inbox($ctx, $inbox);
        return $ret if $ret;
 
-       $ctx->{mid} = $mid = uri_unescape($mid);
+       $ctx->{mid} = $mid;
        if ($mid =~ /\A[a-f0-9]{40}\z/) {
                # this is horiffically wasteful for legacy URLs:
                if ($mid = mid2blob($ctx)) {
@@ -223,8 +230,8 @@ sub get_mid_html {
        my $x = mid2blob($ctx) or return r404($ctx);
 
        require PublicInbox::View;
-       require Email::MIME;
-       my $mime = Email::MIME->new($x);
+       require PublicInbox::MIME;
+       my $mime = PublicInbox::MIME->new($x);
        searcher($ctx);
        PublicInbox::View::msg_html($ctx, $mime);
 }
@@ -238,6 +245,18 @@ sub get_thread {
        PublicInbox::View::thread_html($ctx);
 }
 
+# /$INBOX/_/text/$KEY/
+# /$INBOX/_/text/$KEY/raw
+# KEY may contain slashes
+sub get_text {
+       my ($ctx, $inbox, $key) = @_;
+       my $r404 = invalid_inbox($ctx, $inbox);
+       return $r404 if $r404;
+
+       require PublicInbox::WwwText;
+       PublicInbox::WwwText::get_text($ctx, $key);
+}
+
 sub ctx_get {
        my ($ctx, $key) = @_;
        my $val = $ctx->{$key};
@@ -385,6 +404,16 @@ sub serve_git {
        PublicInbox::GitHTTPBackend::serve($ctx->{env}, $ctx->{git}, $path);
 }
 
+sub mbox_results {
+       my ($ctx) = @_;
+       if ($ctx->{env}->{QUERY_STRING} =~ /(?:\A|[&;])q=/) {
+               searcher($ctx) or return need_search($ctx);
+               require PublicInbox::SearchView;
+               return PublicInbox::SearchView::mbox_results($ctx);
+       }
+       r404();
+}
+
 sub serve_mbox_range {
        my ($ctx, $inbox, $range) = @_;
        invalid_inbox($ctx, $inbox) || eval {