From 299834174a6c1814a5f9c08c5abea76042779839 Mon Sep 17 00:00:00 2001
From: Simone Basso <bassosimone@gmail.com>
Date: Wed, 13 Oct 2021 13:50:22 +0200
Subject: [PATCH] fix(webconnectivity): gather longer HTML titles (#542)

Allows us to get http://www.isa.gov.il/Pages/default.aspx's one.

Discovered when working on https://github.com/ooni/probe/issues/1707.
---
 internal/engine/experiment/webconnectivity/httpanalysis.go | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/internal/engine/experiment/webconnectivity/httpanalysis.go b/internal/engine/experiment/webconnectivity/httpanalysis.go
index f81baf1..757acac 100644
--- a/internal/engine/experiment/webconnectivity/httpanalysis.go
+++ b/internal/engine/experiment/webconnectivity/httpanalysis.go
@@ -186,7 +186,9 @@ func HTTPHeadersMatch(tk urlgetter.TestKeys, ctrl ControlResponse) *bool {
 
 // GetTitle returns the title or an empty string.
 func GetTitle(measurementBody string) string {
-	re := regexp.MustCompile(`(?i)<title>([^<]{1,128})</title>`) // like MK
+	// MK used {1,128} but we're making it larger here to get longer titles
+	// e.g. <http://www.isa.gov.il/Pages/default.aspx>'s one
+	re := regexp.MustCompile(`(?i)<title>([^<]{1,512})</title>`)
 	v := re.FindStringSubmatch(measurementBody)
 	if len(v) < 2 {
 		return ""