Skip to content

implement isURLCodePoint #59

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 9 commits into
base: main
Choose a base branch
from
Open

implement isURLCodePoint #59

Changes from 6 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
8957d33
implement isURLCodePoint
cammytown Nov 27, 2016
bb23d43
Update url-state-machine.js
cammytown Nov 27, 2016
6e619fd
implement isURLCodePoint
cammytown Nov 27, 2016
93643a6
implement isURLCodePoint
cammytown Nov 27, 2016
a9d9133
implement isURLCodePoint()
cammytown Nov 27, 2016
0ac0e1d
implement isURLCodePoint()
cammytown Nov 27, 2016
6329e6b
implement isURLCodePoint()
cammytown Nov 27, 2016
404af4e
missing paren typo
cammytown Nov 27, 2016
734970e
implement isURLCodePoint()
cammytown Nov 27, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 47 additions & 5 deletions src/url-state-machine.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,41 @@ function isASCIIHex(c) {
return isASCIIDigit(c) || (c >= 0x41 && c <= 0x46) || (c >= 0x61 && c <= 0x66);
}

function isURLCodePoint(c) {
return (
isASCIIAlphanumeric(c) ||
c === 0x21 ||
Copy link
Member

@Sebmaster Sebmaster Nov 27, 2016 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you switch these over to use the notation used in the URL spec (that is, use the literal chars, pass them through our conversion p transform). Optionally change it to an array (not sure if that makes copying them off the spec easier)?

c === 0x24 ||
(c >= 0x26 && c <= 0x2F) ||
c === 0x3A ||
c === 0x3B ||
c === 0x3D ||
c === 0x3F ||
c === 0x40 ||
c === 0x5F ||
c === 0x7E ||
(c >= 0xA0 && c <= 0xD7FF) ||
(c >= 0xE000 && c <= 0xFDCF) ||
(c >= 0xFDF0 && c <= 0xFFFD) ||
(c >= 0x10000 && c <= 0x1FFFD) ||
(c >= 0x20000 && c <= 0x2FFFD) ||
(c >= 0x30000 && c <= 0x3FFFD) ||
(c >= 0x40000 && c <= 0x4FFFD) ||
(c >= 0x50000 && c <= 0x5FFFD) ||
(c >= 0x60000 && c <= 0x6FFFD) ||
(c >= 0x70000 && c <= 0x7FFFD) ||
(c >= 0x80000 && c <= 0x8FFFD) ||
(c >= 0x90000 && c <= 0x9FFFD) ||
(c >= 0xA0000 && c <= 0xAFFFD) ||
(c >= 0xB0000 && c <= 0xBFFFD) ||
(c >= 0xC0000 && c <= 0xCFFFD) ||
(c >= 0xD0000 && c <= 0xDFFFD) ||
(c >= 0xE0000 && c <= 0xEFFFD) ||
(c >= 0xF0000 && c <= 0xFFFFD) ||
(c >= 0x100000 && c <= 0x10FFFD)
);
}

function isSingleDot(buffer) {
return buffer === "." || buffer.toLowerCase() === "%2e";
}
Expand Down Expand Up @@ -946,7 +981,9 @@ URLStateMachine.prototype["parse path"] = function parsePath(c) {
this.state = "fragment";
}
} else {
// TODO: If c is not a URL code point and not "%", parse error.
if (!isURLCodePoint(c) && c !== p("%")) {
this.parseError = true;
}

if (c === p("%") &&
(!isASCIIHex(this.input[this.pointer + 1]) ||
Expand Down Expand Up @@ -975,8 +1012,7 @@ URLStateMachine.prototype["parse cannot-be-a-base-URL path"] = function parseCan
this.url.fragment = "";
this.state = "fragment";
} else {
// TODO: Add: not a URL code point
if (!isNaN(c) && c !== p("%")) {
if (!isNaN(c) && !isURLCodePoint(c) && c !== p("%")) {
this.parseError = true;
}

Expand Down Expand Up @@ -1016,7 +1052,10 @@ URLStateMachine.prototype["parse query"] = function parseQuery(c, cStr) {
this.state = "fragment";
}
} else {
// TODO: If c is not a URL code point and not "%", parse error.
if (!isURLCodePoint(c) && c !== p("%")) {
this.parseError = true;
}

if (c === p("%") &&
(!isASCIIHex(this.input[this.pointer + 1]) ||
!isASCIIHex(this.input[this.pointer + 2]))) {
Expand All @@ -1034,7 +1073,10 @@ URLStateMachine.prototype["parse fragment"] = function parseFragment(c, cStr) {
} else if (c === 0x0) {
this.parseError = true;
} else {
// TODO: If c is not a URL code point and not "%", parse error.
if (!isURLCodePoint(c) && c !== "%") {
this.parseError = true;
}

if (c === p("%") &&
(!isASCIIHex(this.input[this.pointer + 1]) ||
!isASCIIHex(this.input[this.pointer + 2]))) {
Expand Down