From 4cd67e7234943baf31b2e122f8ee3c70c21fb489 Mon Sep 17 00:00:00 2001
From: ale <ale@incal.net>
Date: Tue, 19 Dec 2017 00:12:11 +0000
Subject: Add tags (primary/related) to links

This change allows more complex scope boundaries, including loosening
edges a bit to include related resources of HTML pages (which makes
for more complete archives if desired).
---
 crawler_test.go | 58 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)
 create mode 100644 crawler_test.go

(limited to 'crawler_test.go')

diff --git a/crawler_test.go b/crawler_test.go
new file mode 100644
index 0000000..66acbe4
--- /dev/null
+++ b/crawler_test.go
@@ -0,0 +1,58 @@
+package crawl
+
+import (
+	"fmt"
+	"io"
+	"io/ioutil"
+	"log"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"testing"
+)
+
+func TestCrawler(t *testing.T) {
+	dir, err := ioutil.TempDir("", "")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer os.RemoveAll(dir)
+
+	// Run a trivial test http server just so our test Fetcher can
+	// return a real http.Response object.
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		io.WriteString(w, "hello")
+	}))
+	defer srv.Close()
+
+	seeds := MustParseURLs([]string{srv.URL})
+	scope := AND(
+		NewSchemeScope([]string{"http"}),
+		NewSeedScope(seeds),
+		NewDepthScope(2),
+	)
+
+	var crawledPages int
+	h := HandlerFunc(func(c *Crawler, u string, depth int, resp *http.Response, err error) error {
+		crawledPages++
+		next := fmt.Sprintf(srv.URL+"/page/%d", crawledPages)
+		log.Printf("%s -> %s", u, next)
+		c.Enqueue(Outlink{
+			URL: mustParseURL(next),
+			Tag: TagPrimary,
+		}, depth+1)
+		return nil
+	})
+
+	crawler, err := NewCrawler(dir+"/crawl.db", seeds, scope, FetcherFunc(http.Get), NewRedirectHandler(h))
+	if err != nil {
+		t.Fatal("NewCrawler", err)
+	}
+
+	crawler.Run(1)
+	crawler.Close()
+
+	if crawledPages != 2 {
+		t.Fatalf("incomplete/bad crawl (%d pages, expected %d)", crawledPages, 10)
+	}
+}
-- 
cgit v1.2.3-54-g00ecf