Skip to content

Defer basic-string escape validation in tokenizer #288

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

Merged
dduan merged 1 commit into from
Dec 31, 2025
Merged

Defer basic-string escape validation in tokenizer #288

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
59 changes: 3 additions & 56 deletions Sources/TOMLDecoder/Parsing/Parser.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -253,9 +253,6 @@ struct Parser {

if ch == CodeUnits.doubleQuote {
var i = start + 1
var expectedHexDigit = 0
var localExpectedHexDigit = 0
var localEscape = false

// 8x unrolling for double-quoted strings
while i + 8 <= range.upperBound {
Expand All @@ -272,71 +269,21 @@ struct Parser {

while i < range.upperBound {
let ch = bytes[i]
if localEscape {
localEscape = false
if ch == CodeUnits.lowerB || ch == CodeUnits.lowerT
|| ch == CodeUnits.lowerN || ch == CodeUnits.lowerF
|| ch == CodeUnits.lowerR || ch == CodeUnits.doubleQuote
|| ch == CodeUnits.backslash
{
i += 1
continue
}

if ch == CodeUnits.lowerU {
localExpectedHexDigit = 4
i += 1
continue
}

if ch == CodeUnits.upperU {
localExpectedHexDigit = 8
i += 1
continue
}

// Set error flag and break
expectedHexDigit = -1
break
}

if localExpectedHexDigit > 0 {
localExpectedHexDigit -= 1
if ch.isHexDigit {
if ch == CodeUnits.backslash {
i += 1
if i < range.upperBound {
i += 1
continue
}
// Set error flag and break
expectedHexDigit = -2
break
}

if ch == CodeUnits.backslash {
localEscape = true
i += 1
continue
}

if ch == CodeUnits.singleQuote {
i += 1
continue
}

if ch == CodeUnits.lf || ch == CodeUnits.doubleQuote {
break
}
i += 1
}

expectedHexDigit = localExpectedHexDigit

if expectedHexDigit == -1 {
throw TOMLError(
.syntax(lineNumber: lineNumber, message: "expected escape char"))
}
if expectedHexDigit == -2 {
throw TOMLError(.syntax(lineNumber: lineNumber, message: "expect hex char"))
}
if i >= range.upperBound || bytes[i] != CodeUnits.doubleQuote {
throw TOMLError(
.syntax(lineNumber: lineNumber, message: "unterminated quote"))
Expand Down
Loading