Split "Text encoding" op into two ops

This commit splits "Text encoding" into two operations:
+ Encode text `string -> byteArray`
+ Decode text `byteArray -> string`

Base64 and Hex support are removed "Encode text" and "Decode text" as
they have their own operations.

Encode and decode operations now have support for the following
encodings:
+ IBM EBCDIC US-Canada
+ IBM EBCDIC International
+ Windows-874 Thai
+ Japanese Shift-JIS
+ Simplified Chinese GBK
+ Korean
+ Traditional Chinese Big5
+ UTF-16, little endian
+ UTF-16, big endian
+ Windows-1250 Central European
+ Windows-1251 Cyrillic
+ Windows-1252 Latin
+ Windows-1253 Greek
+ Windows-1254 Turkish
+ Windows-1255 Hebrew
+ Windows-1256 Arabic
+ Windows-1257 Baltic
+ Windows-1258 Vietnam
+ US-ASCII
+ Russian Cyrillic KOI8-R
+ Simplified Chinese GB2312
+ KOI8-U Ukrainian Cyrillic
+ ISO-8859-1 Latin 1 (Western European)
+ ISO-8859-2 Latin 2 (Central European)
+ ISO-8859-3 Latin 3
+ ISO-8859-4 Baltic
+ ISO-8859-5 Cyrillic
+ ISO-8859-6 Arabic
+ ISO-8859-7 Greek
+ ISO-8859-8 Hebrew
+ ISO-8859-9 Turkish
+ ISO-8859-10 Latin 6
+ ISO-8859-11 Latin (Thai)
+ ISO-8859-13 Latin 7 (Estonian)
+ ISO-8859-14 Latin 8 (Celtic)
+ ISO-8859-15 Latin 9
+ ISO-8859-16 Latin 10
+ ISO-2022 JIS Japanese
+ EUC Japanese
+ EUC Korean
+ Simplified Chinese GB18030
+ UTF-7
+ UTF-8
This commit is contained in:
toby 2017-05-17 11:17:11 -04:00
parent 3c15bd9e29
commit 2b7ba594fc
5 changed files with 2119 additions and 121 deletions

View file

@ -61,7 +61,8 @@ const Categories = [
"Hex to PEM",
"Parse ASN.1 hex string",
"Change IP format",
"Text encoding",
"Encode text",
"Decode text",
"Swap endianness",
]
},
@ -143,7 +144,8 @@ const Categories = [
{
name: "Language",
ops: [
"Text encoding",
"Encode text",
"Decode text",
"Unescape Unicode Characters",
]
},

View file

@ -872,21 +872,43 @@ const OperationConfig = {
}
]
},
"Text encoding": {
description: "Translates the data between different character encodings.<br><br>Supported charsets are:<ul><li>UTF8</li><li>UTF16</li><li>UTF16LE (little-endian)</li><li>UTF16BE (big-endian)</li><li>Hex</li><li>Base64</li><li>Latin1 (ISO-8859-1)</li><li>Windows-1251</li></ul>",
run: CharEnc.run,
"Encode text": {
description: [
"Encodes text into the chosen character encoding.",
"<br><br>",
"Supported charsets are:",
"<ul>",
Object.keys(CharEnc.IO_FORMAT).map(e => `<li>${e}</li>`).join("<br>"),
"</ul>",
].join("\n"),
run: CharEnc.runEncode,
inputType: "string",
outputType: "byteArray",
args: [
{
name: "Encoding",
type: "option",
value: Object.keys(CharEnc.IO_FORMAT),
},
]
},
"Decode text": {
description: [
"Decodes text from the chosen character encoding.",
"<br><br>",
"Supported charsets are:",
"<ul>",
Object.keys(CharEnc.IO_FORMAT).map(e => `<li>${e}</li>`).join("<br>"),
"</ul>",
].join("\n"),
run: CharEnc.runDecode,
inputType: "byteArray",
outputType: "string",
args: [
{
name: "Input type",
name: "Encoding",
type: "option",
value: CharEnc.IO_FORMAT
},
{
name: "Output type",
type: "option",
value: CharEnc.IO_FORMAT
value: Object.keys(CharEnc.IO_FORMAT),
},
]
},
@ -3249,44 +3271,6 @@ const OperationConfig = {
},
]
},
"To EBCDIC": {
description: [
"This operation converts ASCII text to EBCDIC.",
"<br>",
"You can choose between a few versions of EBCDIC.",
"<br>",
"EBCDIC is a proprietary encoding pre-dating ASCII that originated at IBM.",
].join("\n"),
run: CharEnc.runToEBCDIC,
inputType: "string",
outputType: "byteArray",
args: [
{
name: "EBCDIC version",
type: "option",
value: Object.keys(CharEnc.EBCDIC_CODEPAGES_MAPPING),
},
]
},
"From EBCDIC": {
description: [
"This operation converts ASCII text from EBCDIC.",
"<br>",
"You can choose between a few versions of EBCDIC.",
"<br>",
"EBCDIC is a proprietary encoding pre-dating ASCII that originated at IBM.",
].join("\n"),
run: CharEnc.runFromEBCDIC,
inputType: "byteArray",
outputType: "string",
args: [
{
name: "EBCDIC version",
type: "option",
value: Object.keys(CharEnc.EBCDIC_CODEPAGES_MAPPING),
},
]
},
};
export default OperationConfig;