Skip to content
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

Jump to bottom

JS: Enabled Regular Expression Unicode Sets #18055

Draft
wants to merge 3 commits into
base: main
Choose a base branch
from
Draft

JS: Enabled Regular Expression Unicode Sets #18055

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f5e1299
JS: Added ecma2021, thus extractor now can deal with RegExp v flag
Napalys Nov 21, 2024
2bcb7cf
JS: Added predicate to check if v flag is used on regular expression
Napalys Nov 21, 2024
f1dccaf
JS: MissingUnicodeFlag now uses flags from RegExpLiteral, upgraded to…
Napalys Nov 22, 2024
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
1 change: 1 addition & 0 deletions javascript/extractor/src/com/semmle/jcorn/Parser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -788,6 +788,7 @@ private Token readRegexp() {
String validFlags = "gim";
if (this.options.ecmaVersion() >= 6) validFlags = "gimuy";
if (this.options.ecmaVersion() >= 9) validFlags = "gimsuy";
if (this.options.ecmaVersion() >= 12) validFlags = "gimsuyv";
if (!mods.matches("^[" + validFlags + "]*$"))
this.raise(start, "Invalid regular expression flag");
if (mods.indexOf('u') >= 0) {
Expand Down
5 changes: 3 additions & 2 deletions javascript/extractor/src/com/semmle/js/extractor/ExtractorConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,8 @@ public static enum ECMAVersion {
ECMA2017(2017, 8),
ECMA2018(2018, 9),
ECMA2019(2019, 10),
ECMA2020(2020, 11);
ECMA2020(2020, 11),
ECMA2021(2021, 12);

private final int version;
public final int legacyVersion;
Expand Down Expand Up @@ -232,7 +233,7 @@ public Set<String> getPredefinedGlobals() {
private VirtualSourceRoot virtualSourceRoot;

public ExtractorConfig(boolean experimental) {
this.ecmaVersion = experimental ? ECMAVersion.ECMA2020 : ECMAVersion.ECMA2019;
this.ecmaVersion = experimental ? ECMAVersion.ECMA2021 : ECMAVersion.ECMA2019;
this.platform = Platform.AUTO;
this.jsx = true;
this.sourceType = SourceType.AUTO;
Expand Down
6 changes: 6 additions & 0 deletions javascript/ql/lib/semmle/javascript/Expr.qll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -481,6 +481,12 @@
/** Holds if this regular expression has an `s` flag. */
predicate isDotAll() { RegExp::isDotAll(this.getFlags()) }

// /** Holds if this regular expression has an `u` flag. */
predicate isUnicode() { RegExp::isUnicode(this.getFlags()) }

Check warning on line 485 in javascript/ql/lib/semmle/javascript/Expr.qll

View workflow job for this annotation

GitHub Actions / qldoc 

Missing QLdoc for member-predicate Expr::RegExpLiteral::isUnicode/0

/** Holds if this regular expression has an `v` flag. */
predicate isUnicodeSets() { RegExp::isUnicodeSets(this.getFlags()) }

override string getAPrimaryQlClass() { result = "RegExpLiteral" }
}

Expand Down
12 changes: 12 additions & 0 deletions javascript/ql/lib/semmle/javascript/Regexp.qll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1162,6 +1162,14 @@ module RegExp {
bindingset[flags]
predicate isDotAll(string flags) { flags.matches("%s%") }

/** Holds if `flags` includes the `u` flag. */
bindingset[flags]
predicate isUnicode(string flags) { flags.matches("%u%") }

/** Holds if `flags` includes the `v` flag. */
bindingset[flags]
predicate isUnicodeSets(string flags) { flags.matches("%v%") }

/** Holds if `flags` includes the `m` flag or is the unknown flag `?`. */
bindingset[flags]
predicate maybeMultiline(string flags) { flags = unknownFlag() or isMultiline(flags) }
Expand All @@ -1178,6 +1186,10 @@ module RegExp {
bindingset[flags]
predicate maybeDotAll(string flags) { flags = unknownFlag() or isDotAll(flags) }

/** Holds if `flags` includes the `s` flag or is the unknown flag `?`. */
bindingset[flags]
predicate maybeUnicodeSets(string flags) { flags = unknownFlag() or isUnicodeSets(flags) }

/** Holds if `term` and all of its disjuncts are anchored on both ends. */
predicate isFullyAnchoredTerm(RegExpTerm term) {
exists(RegExpSequence seq | term = seq |
Expand Down
2 changes: 1 addition & 1 deletion javascript/ql/test/library-tests/RegExp/MissingUnicodeFlag/MissingUnicodeFlag.ql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ import javascript
from RegExpLiteral literal, RegExpConstant wideConstant
where
wideConstant.getLiteral() = literal and
not literal.getFlags().matches("%u%") and
not (literal.isUnicode() or literal.isUnicodeSets()) and
wideConstant.getValue().length() > 1 and
(
wideConstant.getParent() instanceof RegExpCharacterClass
Expand Down
1 change: 1 addition & 0 deletions javascript/ql/test/library-tests/RegExp/MissingUnicodeFlag/tst.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,5 @@
/[𒍀-𒍅]/u; // OK
/𒍀+/; // NOT OK
/𒍀+/u; // OK
/𒍀+/v; // OK
/(𒍀)+/; // OK
Loading