-
-
Notifications
You must be signed in to change notification settings - Fork 94
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Spec update: make everything use percent-encode sets
Follows whatwg/url#518. This generally tries to make the code correspond more explicitly to the specification in a few ways. It doesn't handle non-UTF-8 encodings yet, though. Supersedes #152.
- Loading branch information
Showing
7 changed files
with
232 additions
and
172 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,18 @@ | ||
| "use strict"; | ||
| const { TextEncoder, TextDecoder } = require("util"); | ||
|
|
||
| const utf8Encoder = new TextEncoder(); | ||
| const utf8Decoder = new TextDecoder("utf-8", { ignoreBOM: true }); | ||
|
|
||
| function utf8Encode(string) { | ||
| return utf8Encoder.encode(string); | ||
| } | ||
|
|
||
| function utf8DecodeWithoutBOM(bytes) { | ||
| return utf8Decoder.decode(bytes); | ||
| } | ||
|
|
||
| module.exports = { | ||
| utf8Encode, | ||
| utf8DecodeWithoutBOM | ||
| }; |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,139 @@ | ||
| "use strict"; | ||
| const { isASCIIHex } = require("./infra"); | ||
| const { utf8Encode } = require("./encoding"); | ||
|
|
||
| function p(char) { | ||
| return char.codePointAt(0); | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#percent-encode | ||
| function percentEncode(c) { | ||
| let hex = c.toString(16).toUpperCase(); | ||
| if (hex.length === 1) { | ||
| hex = "0" + hex; | ||
| } | ||
|
|
||
| return "%" + hex; | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#percent-decode | ||
| function percentDecodeBytes(input) { | ||
| const output = new Uint8Array(input.byteLength); | ||
| let outputIndex = 0; | ||
| for (let i = 0; i < input.byteLength; ++i) { | ||
| const byte = input[i]; | ||
| if (byte !== 0x25) { | ||
| output[outputIndex++] = byte; | ||
| } else if (byte === 0x25 && (!isASCIIHex(input[i + 1]) || !isASCIIHex(input[i + 2]))) { | ||
| output[outputIndex++] = byte; | ||
| } else { | ||
| const bytePoint = parseInt(String.fromCodePoint(input[i + 1], input[i + 2]), 16); | ||
| output[outputIndex++] = bytePoint; | ||
| i += 2; | ||
| } | ||
| } | ||
|
|
||
| return output.slice(0, outputIndex); | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#string-percent-decode | ||
| function percentDecodeString(input) { | ||
| const bytes = utf8Encode(input); | ||
| return percentDecodeBytes(bytes); | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#c0-control-percent-encode-set | ||
| function isC0ControlPercentEncode(c) { | ||
| return c <= 0x1F || c > 0x7E; | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#fragment-percent-encode-set | ||
| const extraFragmentPercentEncodeSet = new Set([p(" "), p("\""), p("<"), p(">"), p("`")]); | ||
| function isFragmentPercentEncode(c) { | ||
| return isC0ControlPercentEncode(c) || extraFragmentPercentEncodeSet.has(c); | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#query-percent-encode-set | ||
| const extraQueryPercentEncodeSet = new Set([p(" "), p("\""), p("#"), p("<"), p(">")]); | ||
| function isQueryPercentEncode(c) { | ||
| return isC0ControlPercentEncode(c) || extraQueryPercentEncodeSet.has(c); | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#special-query-percent-encode-set | ||
| function isSpecialQueryPercentEncode(c) { | ||
| return isQueryPercentEncode(c) || c === p("'"); | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#path-percent-encode-set | ||
| const extraPathPercentEncodeSet = new Set([p("?"), p("`"), p("{"), p("}")]); | ||
| function isPathPercentEncode(c) { | ||
| return isQueryPercentEncode(c) || extraPathPercentEncodeSet.has(c); | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#userinfo-percent-encode-set | ||
| const extraUserinfoPercentEncodeSet = | ||
| new Set([p("/"), p(":"), p(";"), p("="), p("@"), p("["), p("\\"), p("]"), p("^"), p("|")]); | ||
| function isUserinfoPercentEncode(c) { | ||
| return isPathPercentEncode(c) || extraUserinfoPercentEncodeSet.has(c); | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#application-x-www-form-urlencoded-percent-encode-set | ||
| const extraURLEncodedPercentEncodeSet = new Set([ | ||
| p("!"), p("$"), p("%"), p("&"), p("'"), | ||
| p("("), p(")"), p("+"), p(","), p("~") | ||
| ]); | ||
| function isURLEncodedPercentEncode(c) { | ||
| return isUserinfoPercentEncode(c) || extraURLEncodedPercentEncodeSet.has(c); | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#code-point-percent-encode-after-encoding | ||
| // https://whatpr.org/url/518.html#utf-8-percent-encode | ||
| // Assuming encoding is always utf-8 allows us to trim one of the logic branches. TODO: support encoding. | ||
| // The "-Internal" variant here has code points as JS strings. The external version used by other files has code points | ||
| // as JS numbers, like the rest of the codebase. | ||
| function utf8PercentEncodeCodePointInternal(codePoint, percentEncodePredicate) { | ||
| const bytes = utf8Encode(codePoint); | ||
| let output = ""; | ||
| for (const byte of bytes) { | ||
| // Our percentEncodePredicate operates on bytes, not code points, so this is slightly different from the spec. | ||
| if (!percentEncodePredicate(byte)) { | ||
| output += String.fromCharCode(byte); | ||
| } else { | ||
| output += percentEncode(byte); | ||
| } | ||
| } | ||
|
|
||
| return output; | ||
| } | ||
|
|
||
| function utf8PercentEncodeCodePoint(codePoint, percentEncodePredicate) { | ||
| return utf8PercentEncodeCodePointInternal(String.fromCodePoint(codePoint), percentEncodePredicate); | ||
| } | ||
|
|
||
| // https://whatpr.org/url/518.html#string-percent-encode-after-encoding | ||
| // https://whatpr.org/url/518.html#string-utf-8-percent-encode | ||
| function utf8PercentEncodeString(input, percentEncodePredicate, spaceAsPlus = false) { | ||
| let output = ""; | ||
| for (const codePoint of input) { | ||
| if (spaceAsPlus && codePoint === " ") { | ||
| output += "+"; | ||
| } else { | ||
| output += utf8PercentEncodeCodePointInternal(codePoint, percentEncodePredicate); | ||
| } | ||
| } | ||
| return output; | ||
| } | ||
|
|
||
| module.exports = { | ||
| isC0ControlPercentEncode, | ||
| isFragmentPercentEncode, | ||
| isQueryPercentEncode, | ||
| isSpecialQueryPercentEncode, | ||
| isPathPercentEncode, | ||
| isUserinfoPercentEncode, | ||
| isURLEncodedPercentEncode, | ||
| percentDecodeString, | ||
| percentDecodeBytes, | ||
| utf8PercentEncodeString, | ||
| utf8PercentEncodeCodePoint | ||
| }; |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.