flow: Closed <feature> 'unique_links_from_each_page'.

* crawled is now a map to httpItem's (instead of struct{}) so we can connect pages mid-crawl
* added duplicate link to html site, test updated to match
* now any httpItem with linkType == tUnknown is listed as "Broken" in the output

docs/TODO.md

@@ -13,6 +13,7 @@
 * helper function to do the whole crawl process
 * document code better
   * test with godoc
+* omit fields in json when nil? (Broken, etc.)
 
 ## Features
 

src/docrawler/docrawler.go

@@ -10,7 +10,7 @@ import (
 // docrawl begins crawling the site at "homeurl"
 func docrawl(homeurl string) itemSlice {
 	// set of what we have already crawled
-	crawled := make(map[string]struct{})
+	crawled := make(itemMap)
 
 	// map (of urlString -> httpItem) of our results
 	results := make(itemMap)
@@ -31,7 +31,7 @@ func docrawl(homeurl string) itemSlice {
 	crawlingCount := 1
 
 	// start the home page crawl
-	crawled[homeitem.url.String()] = struct{}{}
+	crawled[homeitem.url.String()] = homeitem
 	go crawlItem(homeitem, rchan)
 
 	// wait for results
@@ -46,19 +46,24 @@ func docrawl(homeurl string) itemSlice {
 
 			// start crawly any new child pages we haven't yet crawled
 			for i, c := range r.children {
-				// see if we already have a result for this page, if so, point to that result
+				// see if we already have a result for this page
+				// if so, point to that result
 				if existing, ok := results[c.url.String()]; ok {
 					r.children[i] = existing
 					continue
 				}
 
 				// see if we're already crawling this page (but maybe don't have results yet)
-				if _, ok := crawled[c.url.String()]; !ok {
-					// haven't crawled this one yet, do so now
-					crawlingCount++
-					crawled[c.url.String()] = struct{}{}
-					go crawlItem(c, rchan)
+				// if so, point to that item (we will have it as a result later!)
+				if existing, ok := crawled[c.url.String()]; ok {
+					r.children[i] = existing
+					continue
 				}
+
+				// haven't crawled this one yet, do so now
+				crawlingCount++
+				crawled[c.url.String()] = c
+				go crawlItem(c, rchan)
 			}
 
 		case <-ticker: // our regular ticker. for status output and checking for completion.

src/docrawler/docrawler_test.go

@@ -102,7 +102,7 @@ func TestSimpleMap(t *testing.T) {
 		t.Logf("got %v, wanted %v\n", len(pages), 6)
 		t.Fatal("got wrong number of pages")
 	}
-	if children != 8 {
+	if children != 9 {
 		t.Logf("got %v, wanted %v\n", children, 8)
 		t.Fatal("got wrong number of total children")
 	}
@@ -117,7 +117,7 @@ func TestSimpleMap(t *testing.T) {
 	}
 
 	// specific page number of children
-	if len(homepage.children) != 4 {
+	if len(homepage.children) != 5 {
 		t.Logf("got %v, wanted %v\n", len(homepage.children), 4)
 		t.Fatal("got wrong number of links")
 	}

src/docrawler/output.go

@@ -48,12 +48,20 @@ func sitemapToLocations(pages itemSlice) []*Location {
 					l.Links = append(l.Links, c.url.String())
 				} else if c.linkType == tBroken {
 					l.Broken = append(l.Broken, c.url.String())
-				} else {
+				} else if c.linkType == tAsset {
 					l.Assets = append(l.Assets, c.url.String())
+				} else {
+					// unknown link here, which means it failed to crawl, let's call it "broken"
+					l.Broken = append(l.Broken, c.url.String())
 				}
+
 			}
 
-			// now sort the children slices
+			// now uniq & sort the children slices
+			l.Remote = uniqStrings(l.Remote)
+			l.Links = uniqStrings(l.Links)
+			l.Broken = uniqStrings(l.Broken)
+			l.Assets = uniqStrings(l.Assets)
 			sort.Strings(l.Remote)
 			sort.Strings(l.Links)
 			sort.Strings(l.Broken)

src/docrawler/testsite/index.html

@@ -5,6 +5,7 @@
 	<body>
 		<img src="/assets/image.png"/>
 		<a href="/about.html">fooey!</a>
+		<a href="/about.html">duplicate!</a>
 		<script src="scripts/blah.js"/>
 		<a href="/zzzbroken.html">oops!</a>
 	</body>

src/docrawler/url.go

@@ -49,3 +49,12 @@ func resolveURL(referringURL string, currentURL string) (*url.URL, error) {
 	// return the URL we ended up with, and the error from checkURL
 	return uResolved, checkURL(uResolved)
 }
+
+func stripAnchorFromURL(u *url.URL) string {
+	// copy the url locally
+	ucopy := *u
+
+	// blank out the anchor, return URI string
+	ucopy.Fragment = ""
+	return ucopy.String()
+}

src/docrawler/url_test.go

@@ -68,3 +68,14 @@ func TestBadResolve(t* testing.T) {
 	}
 }
 */
+
+func TestURLStripAnchor(t *testing.T) {
+	u, err := url.Parse("http://swaits:pass@somehost.com:8765/blah/blah.html?x=y#foo")
+	if err != nil {
+		t.Fatal("couldn't parse a URL")
+	}
+	stripped := stripAnchorFromURL(u)
+	if stripped != "http://swaits:pass@somehost.com:8765/blah/blah.html?x=y" {
+		t.Error("stripping anchor #foo from URL failed")
+	}
+}

src/docrawler/util.go

@@ -0,0 +1,23 @@
+package main
+
+// uniqStrings takes a slice of strings and removes any duplicates
+// note: does not guarantee any order (or stability of order)
+func uniqStrings(strs []string) []string {
+	// handle special case of a nil parameter
+	if strs == nil {
+		return nil
+	}
+
+	// add each string to the slice as keys (used like a "set")
+	set := make(map[string]struct{})
+	for _, s := range strs {
+		set[s] = struct{}{}
+	}
+
+	// now copy all the keys over to a new slice and return it
+	result := []string{}
+	for key := range set {
+		result = append(result, key)
+	}
+	return result
+}

src/docrawler/util_test.go

@@ -0,0 +1,25 @@
+package main
+
+import (
+	"sort"
+	"testing"
+)
+
+func TestUniqStrings(t *testing.T) {
+	strs := []string{"a", "a", "b", "a", "b", "c", "d", "a", "b", "e", "d"}
+	uniq := uniqStrings(strs)
+	if len(uniq) != 5 {
+		t.Error("wrong number of strings after uniq'ing")
+	}
+	sort.Strings(uniq)
+	if uniq[0] != "a" || uniq[1] != "b" || uniq[2] != "c" || uniq[3] != "d" || uniq[4] != "e" {
+		t.Error("uniq values are in correct!")
+	}
+}
+
+func TestUniqStringsNilParm(t *testing.T) {
+	uniq := uniqStrings(nil)
+	if uniq != nil {
+		t.Error("uniqStrings should return a nil slice when passed a nil slice")
+	}
+}

util/testfilter.sh

@@ -2,6 +2,6 @@
 
 # colorize the output of "go test"
 
-sed ''/ok/s//$(printf "\033[32;1m&\033[0m")/''       | \
+sed ''/^ok/s//$(printf "\033[32;1m&\033[0m")/''       | \
 	sed ''/PASS/s//$(printf "\033[32;1m&\033[0m")/''   | \
 	sed ''/FAIL/s//$(printf "\033[31;1m&\033[0m")/''