Support HTML files

8 years ago · a4d15256b9
2 changed files with 50 additions and 7 deletions
--- a/examples/html.feature
+++ b/examples/html.feature
@ -0,0 +1,24 @@
+Feature: HTML
+  Scenario: Check an empty HTML file
+    Given a file named "foo.html" with ""
+    When I successfully run `liche foo.html`
+    Then the stdout should contain exactly ""
+
+  Scenario: Check a HTML file
+    Given a file named "foo.html" with:
+    """
+    <!DOCTYPE html>
+    <html>
+    <head>
+      <title>My title</title>
+    </head>
+    <body>
+      <div>
+        <a href="https://google.com">Google</a>
+        <a href="https://yahoo.com">Yahoo</a>
+      </div>
+    </body>
+    </html>
+    """
+    When I successfully run `liche foo.html`
+    Then the stdout should contain exactly ""
--- a/file_checker.go
+++ b/file_checker.go
@ -4,6 +4,7 @@ import (
 	"bytes"
 	"io/ioutil"
 	"net/url"
+	"strings"
 	"sync"
 	"time"

@ -20,13 +21,7 @@ func newFileChecker(timeout time.Duration, s semaphore) fileChecker {
 }

 func (c fileChecker) Check(f string) ([]urlResult, error) {
-	bs, err := ioutil.ReadFile(f)
-
-	if err != nil {
-		return nil, err
-	}
-
-	n, err := html.Parse(bytes.NewReader(blackfriday.Run(bs)))
+	n, err := parseFile(f)

 	if err != nil {
 		return nil, err
@ -66,6 +61,26 @@ func (c fileChecker) CheckMany(fs []string, rc chan<- fileResult) {
 	close(rc)
 }

+func parseFile(f string) (*html.Node, error) {
+	bs, err := ioutil.ReadFile(f)
+
+	if err != nil {
+		return nil, err
+	}
+
+	if !isHTMLFile(f) {
+		bs = blackfriday.Run(bs)
+	}
+
+	n, err := html.Parse(bytes.NewReader(bs))
+
+	if err != nil {
+		return nil, err
+	}
+
+	return n, nil
+}
+
 func extractURLs(n *html.Node) []string {
 	us := make(map[string]bool)
 	ns := make([]*html.Node, 0, 1024)
@ -107,3 +122,7 @@ func isURL(s string) bool {
 	u, err := url.Parse(s)
 	return err == nil && (u.Scheme == "http" || u.Scheme == "https")
 }
+
+func isHTMLFile(f string) bool {
+	return strings.HasSuffix(f, ".html") || strings.HasSuffix(f, ".htm")
+}