3fdb44bce2
Fetcher.Allowed and Key, the rendered comparison and the Chrome request guard accept an address only on the site's effective port (explicit, else 443 for https and 80 for http), so page code cannot make headless Chrome reach other services on the site host's address and a link to another port is not reported as a page of the site.
52 lines
1.4 KiB
Go
52 lines
1.4 KiB
Go
package crawl
|
|
|
|
import (
|
|
"net/url"
|
|
"testing"
|
|
)
|
|
|
|
// TestFetcherPortAndKey pins L3 WR-03 (and WR-04, P33-61): the fetcher
|
|
// accepts an address only on the site's effective port, so a link to
|
|
// another port is neither fetched nor reported as a page of the site.
|
|
func TestFetcherPortAndKey(t *testing.T) {
|
|
f, err := NewFetcher("https://site.test", nil)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if f.Port() != "443" {
|
|
t.Fatalf("Port = %q", f.Port())
|
|
}
|
|
parse := func(raw string) *url.URL {
|
|
u, err := url.Parse(raw)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
return u
|
|
}
|
|
for raw, want := range map[string]string{
|
|
"https://site.test:8443/x": "",
|
|
"https://site.test:443/x": "/x",
|
|
"https://www.site.test/x": "/x",
|
|
"https://site.test:80/x": "",
|
|
"http://site.test/x": "",
|
|
"https://other.test/x": "",
|
|
"https://site.test": "/",
|
|
"https://site.test/a?b=1&c=": "/a?b=1&c=",
|
|
} {
|
|
u := parse(raw)
|
|
if got := f.Key(u); got != want {
|
|
t.Errorf("Key(%s) = %q, want %q", raw, got, want)
|
|
}
|
|
if f.Allowed(u) != (want != "") {
|
|
t.Errorf("Allowed(%s) = %v", raw, f.Allowed(u))
|
|
}
|
|
}
|
|
local, err := NewFetcher("http://localhost:3000", nil)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if local.Port() != "3000" || effectivePort(parse("http://x")) != "80" || effectivePort(parse("ftp://x")) != "" || effectivePort(nil) != "" {
|
|
t.Fatal("effectivePort is wrong")
|
|
}
|
|
}
|