Use were possible IANA names and provide function to lookup golang.org/x/text encoding for name

README.md

@@ -29,7 +29,7 @@ go get github.com/joshtechnologygroup/chardet
 <details>
   <summary>Expand the list of supported encodings</summary>
 
-- **Ascii**
+- **ASCII** (“US-ASCII”)
 - **UTF-8**
 - **UTF-8-SIG**
 - **UTF-16**
@@ -40,13 +40,13 @@ go get github.com/joshtechnologygroup/chardet
 - **UTF-32LE**
 - **GB2312**
 - **HZ-GB-2312**
-- **SHIFT_JIS**
+- **Shift_JIS**
 - **Big5**
-- **Johab**
+- **Johab** (“KS_C_5601-1987”)
 - **KOI8-R**
 - **TIS-620**
 - **MacCyrillic**
-- **MacRoman**
+- **MacRoman** (“macintosh”)
 - **EUC-TW**
 - **EUC-KR**
 - **EUC-JP**
@@ -112,7 +112,7 @@ func main() {
 	data := []byte("Your text data here...")
 	result := chardet.Detect(data)
 	fmt.Printf("Detected result: %+v\n", result)
-    //Output: Detected result: {Encoding:Ascii Confidence:1 Language:}
+    //Output: Detected result: {Encoding:US-ASCII Confidence:1 Language:}
 }
 ```
 
@@ -139,7 +139,7 @@ func main() {
 	// Get the result
 	result := detector.GetResult()
 	fmt.Printf("Detected result: %+v\n", result)
-	// Output: Detected result: {Encoding:Ascii Confidence:1 Language:}
+	// Output: Detected result: {Encoding:US-ASCII Confidence:1 Language:}
 }
 ```
 

consts/const.go

@@ -12,8 +12,11 @@ const (
 	Turkish   = "Turkish"
 )
 
+// Please use IANA names when extending this
+//
+// http://www.iana.org/assignments/character-sets/character-sets.xhtml
 const (
-	Ascii   = "Ascii"
+	Ascii   = "US-ASCII"  // IANA Name
 	UTF8    = "UTF-8"
 	UTF8SIG = "UTF-8-SIG"
 	UTF16   = "UTF-16"
@@ -25,21 +28,21 @@ const (
 
 	GB2312   = "GB2312"
 	HzGB2312 = "HZ-GB-2312"
-	ShiftJis = "SHIFT_JIS"
+	ShiftJis = "Shift_JIS"
 	Big5     = "Big5"
-	Johab    = "Johab"
+	Johab    = "KS_C_5601-1987"  // IANA name
 	Koi8R    = "KOI8-R"
 	TIS620   = "TIS-620"
 
-	MacCyrillic = "MacCyrillic"
-	MacRoman    = "MacRoman"
+	MacCyrillic = "MacCyrillic"  // Not in IANA
+	MacRoman    = "macintosh"    // IANA name
 
-	EucTw = "EUC-TW"
+	EucTw = "EUC-TW"  // Not in IANA
 	EucKr = "EUC-KR"
 	EucJp = "EUC-JP"
 
-	CP932 = "CP932"
-	CP949 = "CP949"
+	CP932 = "CP932"  // Not in IANA
+	CP949 = "CP949"  // Not in IANA
 
 	Windows1250 = "Windows-1250"
 	Windows1251 = "Windows-1251"
@@ -61,8 +64,8 @@ const (
 	ISO2022CN = "ISO-2022-CN"
 	ISO2022JP = "ISO-2022-JP"
 	ISO2022KR = "ISO-2022-KR"
-	UCS43412  = "X-ISO-10646-UCS-4-3412"
-	UCS42143  = "X-ISO-10646-UCS-4-2143"
+	UCS43412  = "X-ISO-10646-UCS-4-3412"  // Testing “Unusual Octet” byte order
+	UCS42143  = "X-ISO-10646-UCS-4-2143"  // Testing “Unusual Octet” byte order
 
 	IBM855 = "IBM855"
 	IBM866 = "IBM866"

go.mod

@@ -1,3 +1,7 @@
 module github.com/joshtechnologygroup/chardet
 
-go 1.20
+go 1.24.0
+
+toolchain go1.24.4
+
+require golang.org/x/text v0.32.0 // indirect

go.sum

@@ -0,0 +1,2 @@
+golang.org/x/text v0.32.0 h1:ZD01bjUt1FQ9WJ0ClOL5vxgxOI/sVCNgX1YtKwcY0mU=
+golang.org/x/text v0.32.0/go.mod h1:o/rUWzghvpD5TXrTIBuJU77MTaN0ljMWE47kxGJQ7jY=

lookup/lookup.go

@@ -0,0 +1,61 @@
+package lookup
+
+import (
+	"strings"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/charmap"
+	"golang.org/x/text/encoding/ianaindex"
+	"golang.org/x/text/encoding/simplifiedchinese"
+	"golang.org/x/text/encoding/unicode/utf32"
+)
+
+// Looks up an `golang.org/x/text/encoding` encoding by name
+//
+// Recognizes all encodings returned by this library for which a corresponding
+// or compatible superset encoder exists.
+//
+// Like `golang.org/x/text/encoding/ianaindex.IANA.Encoding`, this returns
+// `encoding, nil` on success, `nil, err` on error and `nil, nil` if the name
+// was correct but has no corresponding encoder.
+func LookupEncoding(name string) (encoding.Encoding, error) {
+	name = strings.ToLower(name)
+
+	// First try stdlib lookup function
+	encoding, err := ianaindex.IANA.Encoding(name)
+	if encoding != nil {
+		return encoding, nil
+	}
+
+	switch name {
+		// UTF-32 family appears to be an omission
+		case "utf-32", "csutf32":
+			return utf32.UTF32(utf32.BigEndian, utf32.UseBOM), nil
+		case "utf-32be", "csutf32be":
+			return utf32.UTF32(utf32.BigEndian, utf32.IgnoreBOM), nil
+		case "utf-32le", "csutf32le":
+			return utf32.UTF32(utf32.LittleEndian, utf32.IgnoreBOM), nil
+
+		// GB2312 is a subset of GBK which in turn is a subset of GB18030
+		case "gb2312", "csgb2319",
+		     "gbk", "cp936", "ms936", "windows-936", "csgbk":
+			return simplifiedchinese.GB18030, nil
+
+		// MacCyrillic is missing IANA designation
+		case "maccyrillic", "x-mac-cyrillic":
+			return charmap.MacintoshCyrillic, nil
+
+		// Not supported and not in IANA are:
+		case "euc-tw",
+		     "cp932", "ms932", "windows-932", "windows-31j",  // Similar to Shift-JIS
+		     "cp949", "ms949", "windows-949":                 // Similar to Johab
+			return nil, nil
+
+		// Not supported but in IANA are (`err` will be `nil` for these):
+		//  * ISO-2022-CN
+		//  * ISO-2022-KR
+		//  * TIS-620
+		default:
+			return nil, err
+	}
+}