Correct Regular Expressions Behavior Related to Annex B #58320
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -2638,6 +2638,10 @@ export function createScanner(languageVersion: ScriptTarget, skipTrivia: boolean | |
| const digitsStart = pos; | ||
| scanDigits(); | ||
| const min = tokenValue; | ||
| if (annexB && !min) { | ||
| isPreviousTermQuantifiable = true; | ||
| break; | ||
| } | ||
| if (text.charCodeAt(pos) === CharacterCodes.comma) { | ||
| pos++; | ||
| scanDigits(); | ||
|
|
@@ -2647,25 +2651,28 @@ export function createScanner(languageVersion: ScriptTarget, skipTrivia: boolean | |
| error(Diagnostics.Incomplete_quantifier_Digit_expected, digitsStart, 0); | ||
| } | ||
| else { | ||
| error(Diagnostics.Unexpected_0_Did_you_mean_to_escape_it_with_backslash, start, 1, String.fromCharCode(ch)); | ||
| isPreviousTermQuantifiable = true; | ||
| break; | ||
| } | ||
| } | ||
| else if (max && Number.parseInt(min) > Number.parseInt(max) && (!annexB || text.charCodeAt(pos) === CharacterCodes.closeBrace)) { | ||
| error(Diagnostics.Numbers_out_of_order_in_quantifier, digitsStart, pos - digitsStart); | ||
| } | ||
| } | ||
| else if (!min) { | ||
| if (!annexB) { | ||
| error(Diagnostics.Unexpected_0_Did_you_mean_to_escape_it_with_backslash, start, 1, String.fromCharCode(ch)); | ||
| } | ||
| isPreviousTermQuantifiable = true; | ||
| break; | ||
| } | ||
| if (!annexB) { | ||
| scanExpectedChar(CharacterCodes.closeBrace); | ||
| } | ||
| else if (text.charCodeAt(pos) === CharacterCodes.closeBrace) { | ||
| pos++; | ||
| } | ||
| pos--; | ||
| // falls through | ||
| case CharacterCodes.asterisk: | ||
|
|
@@ -2707,7 +2714,7 @@ export function createScanner(languageVersion: ScriptTarget, skipTrivia: boolean | |
| // Assume what starting from the character to be outside of the regex | ||
| return; | ||
| } | ||
| if (!annexB || ch === CharacterCodes.closeParen) { | ||
| error(Diagnostics.Unexpected_0_Did_you_mean_to_escape_it_with_backslash, pos, 1, String.fromCharCode(ch)); | ||
| } | ||
| pos++; | ||
|
|
@@ -2767,7 +2774,10 @@ export function createScanner(languageVersion: ScriptTarget, skipTrivia: boolean | |
| scanGroupName(/*isReference*/ true); | ||
| scanExpectedChar(CharacterCodes.greaterThan); | ||
| } | ||
| else { | ||
| // This actually is allowed in Annex B if there are no named capturing groups in the regex, | ||
| // but if we were going to slience these errors, we would have to record the positions of all '\k's | ||
| // and defer the errors until after the scanning to know if the regex has any named capturing groups. | ||
| error(Diagnostics.k_must_be_followed_by_a_capturing_group_name_enclosed_in_angle_brackets, pos - 2, 2); | ||
| } | ||
| break; | ||
|
|
@@ -3390,7 +3400,7 @@ export function createScanner(languageVersion: ScriptTarget, skipTrivia: boolean | |
| error(Diagnostics.Unicode_property_value_expressions_are_only_available_when_the_Unicode_u_flag_or_the_Unicode_Sets_v_flag_is_set, start, pos - start); | ||
| } | ||
| } | ||
| else if (!annexB) { | ||
|
There was a problem hiding this comment. In Annex B, braces after There was a problem hiding this comment. Not really outdated There was a problem hiding this comment. The outdated label is just because the comment is on an old revision of the PR and GitHub can't figure out where the comment goes after. There was a problem hiding this comment. Agreed. I could’ve removed the review and re-comment but finally chose not to. |
||
| error(Diagnostics._0_must_be_followed_by_a_Unicode_property_value_expression_enclosed_in_braces, pos - 2, 2, String.fromCharCode(ch)); | ||
| } | ||
| return true; | ||
|
|
||
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
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Though it may be redundant, I think it might be better to still indicate
unicodeModehere so that someone editing this code in the future doesn't mistakenly think this only applies to non-Annex B code. It may be better to useunicodeMode || !annexBand remove theif (unicodeMode) { annexB = false; }at the top ofscanRegularExpressionWorker.The same would go for other uses of
annexBas well.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Are you sure you are really fine with a dozen of occurrences of
unicodeMode || !annexB?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
No, but
would work.