From c4dda89f07ce26c9ace2971777fd447f7b847710 Mon Sep 17 00:00:00 2001
From: Lucas Bremgartner <lucas@bremis.ch>
Date: Fri, 16 Apr 2021 19:46:25 +0200
Subject: [PATCH] Add escape/unescape for Logstash strings

Based on https://www.elastic.co/guide/en/logstash/current/configuration-file-structure.html#_escape_sequences
---
 ast/astutil/escape.go      | 69 ++++++++++++++++++++++++++++++++
 ast/astutil/escape_test.go | 81 ++++++++++++++++++++++++++++++++++++++
 go.sum                     |  2 +
 3 files changed, 152 insertions(+)
 create mode 100644 ast/astutil/escape.go
 create mode 100644 ast/astutil/escape_test.go

diff --git a/ast/astutil/escape.go b/ast/astutil/escape.go
new file mode 100644
index 0000000..1c42b0d
--- /dev/null
+++ b/ast/astutil/escape.go
@@ -0,0 +1,69 @@
+package astutil
+
+import (
+	"regexp"
+)
+
+var unescapeRe = regexp.MustCompile(`\\.`)
+
+// Unescape converts an input containing escape sequences as understood by
+// Logstash (https://www.elastic.co/guide/en/logstash/current/configuration-file-structure.html#_escape_sequences)
+// to an unescaped string.
+//
+// Unescaped character sequences:
+//
+//     \r : carriage return (ASCII 13)
+//     \n : new line (ASCII 10)
+//     \t : tab (ASCII 9)
+//     \\ : backslash (ASCII 92)
+//     \" : double quote (ASCII 34)
+//     \' : single quote (ASCII 39)
+//
+// Based on:
+// https://github.com/elastic/logstash/blob/e9c9865f4066b54048f8d708612a72d25e2fe5d9/logstash-core/lib/logstash/config/string_escape.rb
+func Unescape(value string) string {
+	return unescapeRe.ReplaceAllStringFunc(value, func(s string) string {
+		switch s[1] {
+		case '"', '\'', '\\':
+			return string(s[1])
+		case 'n':
+			return "\n"
+		case 'r':
+			return "\r"
+		case 't':
+			return "\t"
+		default:
+			return s
+		}
+	})
+}
+
+var escapeRe = regexp.MustCompile(`(?s:.)`)
+
+// Escape converts an input to an escaped representation as understood by
+// Logstash (https://www.elastic.co/guide/en/logstash/current/configuration-file-structure.html#_escape_sequences).
+//
+// Escaped characters:
+//
+//     \r : carriage return (ASCII 13)
+//     \n : new line (ASCII 10)
+//     \t : tab (ASCII 9)
+//     \  : backslash (ASCII 92)
+//     "  : double quote (ASCII 34)
+//     '  : single quote (ASCII 39)
+func Escape(value string) string {
+	return escapeRe.ReplaceAllStringFunc(value, func(s string) string {
+		switch s {
+		case `"`, `'`, `\`:
+			return `\` + s
+		case "\n":
+			return `\n`
+		case "\r":
+			return `\r`
+		case "\t":
+			return `\t`
+		default:
+			return s
+		}
+	})
+}
diff --git a/ast/astutil/escape_test.go b/ast/astutil/escape_test.go
new file mode 100644
index 0000000..7d19a1c
--- /dev/null
+++ b/ast/astutil/escape_test.go
@@ -0,0 +1,81 @@
+package astutil_test
+
+import (
+	"testing"
+
+	"github.com/breml/logstash-config/ast/astutil"
+)
+
+var tt = []struct {
+	name      string
+	escaped   string
+	unescaped string
+}{
+	{
+		name:      "carriage return (ASCII 13)",
+		escaped:   `\r`,
+		unescaped: "\r",
+	},
+	{
+		name:      "new line (ASCII 10)",
+		escaped:   `\n`,
+		unescaped: "\n",
+	},
+	{
+		name:      "tab (ASCII 9)",
+		escaped:   `\t`,
+		unescaped: "\t",
+	},
+	{
+		name:      "backslash (ASCII 92)",
+		escaped:   `\\`,
+		unescaped: `\`,
+	},
+	{
+		name:      "double quote (ASCII 34)",
+		escaped:   `\"`,
+		unescaped: `"`,
+	},
+	{
+		name:      "single quote (ASCII 39)",
+		escaped:   `\'`,
+		unescaped: `'`,
+	},
+	{
+		name:      "value containing all special characters",
+		escaped:   `foo\r\n\t\\\"\'bar`,
+		unescaped: "foo\r\n\t\\\"'bar",
+	},
+}
+
+func TestEscape(t *testing.T) {
+	for _, tc := range tt {
+		t.Run(tc.name, func(t *testing.T) {
+			got := astutil.Escape(tc.unescaped)
+			if tc.escaped != got {
+				t.Errorf("Escape(%q) != %q, got: %q", tc.unescaped, tc.escaped, got)
+			}
+		})
+	}
+}
+
+func TestUnescape(t *testing.T) {
+	tt := append(tt, struct {
+		name      string
+		escaped   string
+		unescaped string
+	}{
+		name:      "not valid escape",
+		escaped:   `\x`,
+		unescaped: "\\x",
+	})
+
+	for _, tc := range tt {
+		t.Run(tc.name, func(t *testing.T) {
+			got := astutil.Unescape(tc.escaped)
+			if tc.unescaped != got {
+				t.Errorf("Unescape(%q) != %q, got: %q", tc.escaped, tc.unescaped, got)
+			}
+		})
+	}
+}
diff --git a/go.sum b/go.sum
index 4dedeae..b4845ed 100644
--- a/go.sum
+++ b/go.sum
@@ -3,6 +3,7 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
+github.com/kr/pty v1.1.1 h1:VkoXIwSboBpnk99O/KFauAEILuNHv5DVFKZMBN/gUgw=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
@@ -10,6 +11,7 @@ github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZb
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/sergi/go-diff v1.1.0 h1:we8PVUC3FE2uYfodKH/nBHMSetSfHDR6scGdBi+erh0=
 github.com/sergi/go-diff v1.1.0/go.mod h1:STckp+ISIX8hZLjrqAeVduY0gWCT9IjLuqbuNXdaHfM=
+github.com/stretchr/objx v0.1.0 h1:4G4v2dO3VZwixGIRoQ5Lfboy6nUhCyYzaqnIAPPhYs4=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/testify v1.4.0 h1:2E4SXV/wtOkTonXsotYi4li6zVWxYlZuYNCXe9XRJyk=
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=