Add: extract-urls processor

go.mod

@@ -43,4 +43,5 @@ require (
 	golang.org/x/text v0.14.0 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
+	mvdan.cc/xurls/v2 v2.5.0 // indirect
 )

go.sum

@@ -106,3 +106,5 @@ gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
 gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+mvdan.cc/xurls/v2 v2.5.0 h1:lyBNOm8Wo71UknhUs4QTFUNNMyxy2JEIaKKo0RWOh+8=
+mvdan.cc/xurls/v2 v2.5.0/go.mod h1:yQgaGQ1rFtJUzkmKiHYSSfuQxqfYmd//X6PxvholpeE=

processors/processor.go

@@ -24,6 +24,7 @@ var List = []list.Item{
 	CountWords{},
 	EscapeQuotes{},
 	ExtractEmails{},
+	ExtractURLs{},
 	ExtractIPs{},
 	FormatJSON{},
 	HexDecode{},

processors/url.go

@@ -2,7 +2,9 @@ package processors
 
 import (
 	"fmt"
+	"mvdan.cc/xurls/v2"
 	"net/url"
+	"strings"
 )
 
 // URLEncode encode url string.
@@ -69,3 +71,46 @@ func (p URLDecode) Description() string {
 func (p URLDecode) FilterValue() string {
 	return p.Title()
 }
+
+// ExtractURLs decode url string.
+type ExtractURLs struct{}
+
+func (p ExtractURLs) Name() string {
+	return "extract-url"
+}
+
+func (p ExtractURLs) Alias() []string {
+	return []string{"url-ext", "extract-urls", "ext-url"}
+}
+
+func (p ExtractURLs) Transform(data []byte, _ ...Flag) (string, error) {
+	rxRelaxed := xurls.Relaxed()
+	urls := rxRelaxed.FindAllString(string(data), -1)
+
+	var output string
+
+	for _, u := range urls {
+		output = output + u + "\n"
+	}
+
+	output = strings.TrimSuffix(output, "\n")
+
+	return output, nil
+}
+
+func (p ExtractURLs) Flags() []Flag {
+	return nil
+}
+
+func (p ExtractURLs) Title() string {
+	title := "Extract URLs"
+	return fmt.Sprintf("%s (%s)", title, p.Name())
+}
+
+func (p ExtractURLs) Description() string {
+	return "Extract URLs from text"
+}
+
+func (p ExtractURLs) FilterValue() string {
+	return p.Title()
+}

processors/url_test.go

@@ -116,6 +116,85 @@ func TestURLDecode_Command(t *testing.T) {
 	}
 }
 
+func TestExtractURL_Command(t *testing.T) {
+	test := struct {
+		alias       []string
+		description string
+		filterValue string
+		flags       []Flag
+		name        string
+		title       string
+	}{
+		alias:       []string{"url-ext", "extract-urls", "ext-url"},
+		description: "Extract URLs from text",
+		filterValue: "Extract URLs (extract-url)",
+		flags:       nil,
+		name:        "extract-url",
+		title:       "Extract URLs (extract-url)",
+	}
+	p := ExtractURLs{}
+	if got := p.Alias(); !reflect.DeepEqual(got, test.alias) {
+		t.Errorf("Alias() = %v, want %v", got, test.alias)
+	}
+	if got := p.Description(); got != test.description {
+		t.Errorf("Description() = %v, want %v", got, test.description)
+	}
+	if got := p.FilterValue(); got != test.filterValue {
+		t.Errorf("FilterValue() = %v, want %v", got, test.filterValue)
+	}
+	if got := p.Flags(); !reflect.DeepEqual(got, test.flags) {
+		t.Errorf("Flags() = %v, want %v", got, test.flags)
+	}
+	if got := p.Name(); got != test.name {
+		t.Errorf("Name() = %v, want %v", got, test.name)
+	}
+	if got := p.Title(); got != test.title {
+		t.Errorf("Title() = %v, want %v", got, test.title)
+	}
+}
+
+func TestExtractURL_Transform(t *testing.T) {
+	type args struct {
+		data []byte
+		in1  []Flag
+	}
+	tests := []struct {
+		name    string
+		args    args
+		want    string
+		wantErr bool
+	}{
+		{
+			name: "Should extract http://foo.com/",
+			args: args{data: []byte("must have scheme: http://foo.com/.")},
+			want: "http://foo.com/",
+		},
+		{
+			name: "Should extract foo.com",
+			args: args{data: []byte("must have scheme: foo.com/.")},
+			want: "foo.com/",
+		},
+		{
+			name: "multiple urls foo.com example.com",
+			args: args{data: []byte("multiple urls foo.com example.com")},
+			want: "foo.com\nexample.com",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			p := ExtractURLs{}
+			got, err := p.Transform(tt.args.data, tt.args.in1...)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Transform() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			if got != tt.want {
+				t.Errorf("Transform() got = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
+
 func TestURLDecode_Transform(t *testing.T) {
 	type args struct {
 		data []byte