fix: parse filenames with urls // fix #50

media/movie_test.go

@@ -104,6 +104,13 @@ func TestForeignMovie(t *testing.T) {
 	assert.Equal(t, 2003, m.Year())
 }
 
+func TestMovieWebsite(t *testing.T) {
+	m, err := NewMovie("[www.example.com] Inception (2010) x264 1080p")
+	require.NoError(t, err)
+	assert.Equal(t, "Inception", m.MovieName())
+	assert.Equal(t, 2010, m.Year())
+}
+
 func TestMovieJSON(t *testing.T) {
 	m, err := NewMovie("Inception.2010.720p")
 	require.NoError(t, err)

parse/parse.go

@@ -84,9 +84,12 @@ func isAbbreviation(str string) bool {
 var abbreviationRegexp = regexp.MustCompile(`\b[A-Za-z]([\s\.][A-Za-z])+\b`)
 var illegalcharsRegexp = regexp.MustCompile(`[^\p{L}0-9\s&'_\(\)\-,:]`)
 var spaceReplaceRegexp = regexp.MustCompile(`[\.\s_]+`)
+var websiteRegexp = regexp.MustCompile(`((https?|ftp|smtp):\/\/)?(www.)[a-z0-9]+\.[a-z]+(\/[a-zA-Z0-9#]+\/?)*`)
+var trimRegexp = regexp.MustCompile(`^[^\p{L}0-9]*(.+?[\.\)]?)[^\p{L}0-9]*$`)
 
 // CleanName returns the media name cleaned from punctuation
 func CleanName(name string) string {
+	name = websiteRegexp.ReplaceAllString(name, "")
 	name = spaceReplaceRegexp.ReplaceAllString(name, " ")
 	name = illegalcharsRegexp.ReplaceAllString(name, "")
 
@@ -103,7 +106,13 @@ func CleanName(name string) string {
 
 	name = Capitalize(name)
 
-	return strings.TrimSpace(name)
+	match := trimRegexp.FindStringSubmatch(name)
+
+	if len(match) > 1 {
+		return match[1]
+	} else {
+		return ""
+	}
 }
 
 var illegalIdentity = regexp.MustCompile(`[^\p{L}0-9]`)

parse/parse_test.go

@@ -51,6 +51,11 @@ func TestCleanNameMovieTitles(t *testing.T) {
 	}
 }
 
+func TestCleanNameWebsites(t *testing.T) {
+	assert.Equal(t, "Inception", CleanName("www.example.com - Inception"))
+	assert.Equal(t, "Inception", CleanName("[www.example.com].Inception"))
+}
+
 func TestIdentity(t *testing.T) {
 	assert.Equal(t, "thisisatest", Identity("thìs is â tést"))
 	assert.Equal(t, "vyzkousejtetentoretezec", Identity("vyzkoušejte tento řetězec"))