flow: Closed <feature> 'remove_error_from_parselinks'.

docs/TODO.md

@@ -5,7 +5,6 @@
 * deal with anchor issue (repeatedly crawling index.html#about, index.html#contact, etc.)
   * should only crawl these pages once
   * but should be included in the links part
-* when sorting links, "uniq" them as well
 * be smart about index.html?
 
 ## Cleanup

src/docrawler/docrawler.go

@@ -8,7 +8,7 @@ import (
 )
 
 // docrawl begins crawling the site at "homeurl"
-func docrawl(homeurl string) itemSlice {
+func doCrawl(homeurl string) itemSlice {
 	// set of what we have already crawled
 	crawled := make(itemMap)
 
@@ -102,7 +102,7 @@ func crawlItem(item *httpItem, rchan chan<- *httpItem) {
 	}
 
 	// parse links
-	title, links, _ := parseLinks(text) // TODO remove error from parseLinks, not needed
+	title, links := parseLinks(text) // TODO remove error from parseLinks, not needed
 	if err != nil {
 		item.linkType = tBroken
 		rchan <- item
@@ -126,7 +126,7 @@ func crawlItem(item *httpItem, rchan chan<- *httpItem) {
 func main() {
 	// crawl each URL on the command line
 	for _, u := range os.Args[1:] {
-		pages := docrawl(u)
+		pages := doCrawl(u)
 		l := sitemapToLocations(pages)
 		j, _ := locationsToJSON(l)
 		fmt.Println(j)

src/docrawler/docrawler_test.go

@@ -76,7 +76,7 @@ func TestSimpleFetch(t *testing.T) {
 
 // TestSimpleMap figures out the site map for the site in baseURL
 func TestSimpleMap(t *testing.T) {
-	pages := docrawl(baseURL)
+	pages := doCrawl(baseURL)
 
 	// because our crawl is non-deterministic, we have to do a complete
 	// cycle through every page, counting stuff, finding specific pages
@@ -185,7 +185,7 @@ func TestHeaderFetching(t *testing.T) {
 
 // TestJsonOutput gets a sitemap and then converts it to json
 func TestJsonOutput(t *testing.T) {
-	pages := docrawl(baseURL)
+	pages := doCrawl(baseURL)
 	l := sitemapToLocations(pages)
 	if len(l) != 2 {
 		t.Error("sitemapToLocations has the wrong number of locations")

src/docrawler/fetch.go

@@ -7,6 +7,7 @@ import (
 	"net/http"
 )
 
+// custom errors
 var (
 	errContentTypeNotFound = errors.New("no Content-Type header found")
 	errFetchError          = errors.New("couldn't fetch item")

src/docrawler/item.go

@@ -13,6 +13,7 @@ type itemMap map[string]*httpItem
 // itemType is an enum so we know how to classify each item
 type itemType int
 
+// enums for itemType
 const (
 	tUnknown itemType = iota
 	tHTMLPage

src/docrawler/output.go

@@ -77,6 +77,7 @@ func sitemapToLocations(pages itemSlice) []*Location {
 	return locations
 }
 
+// locationsToJSON takes a *Location slice and marshals it into a JSON string
 func locationsToJSON(locations []*Location) (string, error) {
 	b, err := json.Marshal(locations)
 	if err != nil {

src/docrawler/parse.go

@@ -11,7 +11,7 @@ var reTitle = regexp.MustCompile(`(?i)<\s*title\s*>([^<]*)<\s*\/\s*title`)
 
 // parseLinks takes a string and attempts to parse any html title and all links out of it,
 // and returns a slice of the captures found
-func parseLinks(s string) (string, []string, error) {
+func parseLinks(s string) (string, []string) {
 	// find the title, or default to empty
 	title := ""
 	titleMatches := reTitle.FindStringSubmatch(s)
@@ -25,5 +25,5 @@ func parseLinks(s string) (string, []string, error) {
 	for _, match := range reURL.FindAllStringSubmatch(s, -1) {
 		results = append(results, match[2])
 	}
-	return title, results, nil
+	return title, results
 }

src/docrawler/parse_test.go

@@ -16,10 +16,7 @@ func TestSimpleParse(t *testing.T) {
 		<script href="scripts/blah.js"/>
 	</body>
 </html>`
-	title, matches, err := parseLinks(doc)
-	if err != nil {
-		t.Error(err)
-	}
+	title, matches := parseLinks(doc)
 	if title != "Test Page" {
 		t.Error("got wrong title")
 	}

src/docrawler/url.go

@@ -6,6 +6,7 @@ import (
 	"strings"
 )
 
+// custom errors
 var (
 	errInvalidURL = errors.New("this URL can't be parsed successfully")
 )
@@ -50,6 +51,9 @@ func resolveURL(referringURL string, currentURL string) (*url.URL, error) {
 	return uResolved, checkURL(uResolved)
 }
 
+// stripAnchorFromURL returns a version of the URL with out the "Fragment" part,
+// which is anything after the '#' character, so:
+// http://a.com/blah.html#anchor becomes http://a.com/blah.html
 func stripAnchorFromURL(u *url.URL) string {
 	// copy the url locally
 	ucopy := *u

src/docrawler/url_test.go

@@ -69,6 +69,7 @@ func TestBadResolve(t* testing.T) {
 }
 */
 
+// TestURLStripAnchor tests the stripAnchorFromURL() function
 func TestURLStripAnchor(t *testing.T) {
 	u, err := url.Parse("http://swaits:pass@somehost.com:8765/blah/blah.html?x=y#foo")
 	if err != nil {

src/docrawler/util_test.go

@@ -5,6 +5,8 @@ import (
 	"testing"
 )
 
+// TestUniqStrings passes a slice of strings to uniqStrings() to see if it removes
+// all duplicates
 func TestUniqStrings(t *testing.T) {
 	strs := []string{"a", "a", "b", "a", "b", "c", "d", "a", "b", "e", "d"}
 	uniq := uniqStrings(strs)
@@ -17,6 +19,7 @@ func TestUniqStrings(t *testing.T) {
 	}
 }
 
+// TestUniqStringsNilParm passes a nil slice to uniqStrings to be sure it returns nil
 func TestUniqStringsNilParm(t *testing.T) {
 	uniq := uniqStrings(nil)
 	if uniq != nil {