support more charset

ISO-8859-1.go

@@ -4,7 +4,6 @@ import (
 	"bytes"
 	"errors"
 	"io"
-	"strings"
 	"unicode/utf8"
 )
 
@@ -41,16 +40,6 @@ func (cs *charsetISO88591er) Read(p []byte) (int, error) {
 	return 0, errors.New("Use ReadByte()")
 }
 
-func isCharset(charset string, names []string) bool {
-	charset = strings.ToLower(charset)
-	for _, n := range names {
-		if charset == strings.ToLower(n) {
-			return true
-		}
-	}
-	return false
-}
-
 func isCharsetISO88591(charset string) bool {
 	// http://www.iana.org/assignments/character-sets
 	// (last updated 2010-11-04)
@@ -70,22 +59,3 @@ func isCharsetISO88591(charset string) bool {
 	}
 	return isCharset(charset, names)
 }
-
-func isCharsetUTF8(charset string) bool {
-	names := []string{
-		"UTF-8",
-		// Default
-		"",
-	}
-	return isCharset(charset, names)
-}
-
-func charsetReader(charset string, input io.Reader) (io.Reader, error) {
-	switch {
-	case isCharsetUTF8(charset):
-		return input, nil
-	case isCharsetISO88591(charset):
-		return newCharsetISO88591(input), nil
-	}
-	return nil, errors.New("CharsetReader: unexpected charset: " + charset)
-}

README.md

@@ -9,6 +9,11 @@ and it seems to work fine with them.
 If anyone has any problems with feeds being parsed incorrectly, please let me know so that
 I can debug and improve the package.
 
+Dependencies:
+```bash
+go get github.com/axgle/mahonia
+```
+
 Example usage:
 ```go
 package main

charset-reader.go

@@ -0,0 +1,47 @@
+package rss
+
+import (
+	"errors"
+	"io"
+	"strings"
+
+	"github.com/axgle/mahonia"
+)
+
+func charsetReader(charset string, input io.Reader) (io.Reader, error) {
+	switch {
+	case isCharsetUTF8(charset):
+		return input, nil
+	case isCharsetISO88591(charset):
+		return newCharsetISO88591(input), nil
+	default:
+		decoder := mahonia.NewDecoder(charset)
+		if decoder == nil {
+			goto invalidCharset
+		}
+
+		return decoder.NewReader(input), nil
+	}
+
+invalidCharset:
+	return nil, errors.New("CharsetReader: unexpected charset: " + charset)
+}
+
+func isCharset(charset string, names []string) bool {
+	charset = strings.ToLower(charset)
+	for _, n := range names {
+		if charset == strings.ToLower(n) {
+			return true
+		}
+	}
+	return false
+}
+
+func isCharsetUTF8(charset string) bool {
+	names := []string{
+		"UTF-8",
+		// Default
+		"",
+	}
+	return isCharset(charset, names)
+}