Commit 3: Add test.cpp corpus wrapped in std::regex stubs; generate .expected

Introduces cpp/ql/test/library-tests/regex/test.cpp with the Ruby regex corpus mechanically translated to C++ string literals and wrapped in std::regex construction calls using fully self-contained in-file stubs (no #include of any external/standard header). Stub surface: std::basic_regex<CharT> constructor(const char*), constructor(const char*, int), assign(const char*) std::regex typedef for basic_regex<char> std::regex_match / regex_search / regex_replace free functions 1:1 corpus mapping from regexp.rb: - All Ruby /regex/ literals translated to C++ "string" literals (each backslash doubled: /\d/ -> "\\d") - Dropped: /#{A}bc/ (Ruby string interpolation, no string-literal form) - Kept: a{,8}, .*m, \A, \z, \G, \h\H, (?'foo'...) — these are removed in commits 4 and 5 (keeping them here preserves 1:1 mapping) Also removes `abstract` from RegExp class in ParseRegExp.qll so that all StringLiterals are regex candidates (trivial syntactic gate; no dataflow). .expected generated by: codeql test run --learn --search-path=. cpp/ql/test/library-tests/regex/ (CodeQL CLI 2.26.1, bundled C/C++ extractor) All 2 tests passed.
2026-07-31 23:42:59 +02:00 · 2026-07-21 10:11:27 +00:00
parent 52b35ef08e
commit d7a8f48c1c
4 changed files with 867 additions and 1 deletions
--- a/cpp/ql/lib/semmle/code/cpp/regex/internal/ParseRegExp.qll
+++ b/cpp/ql/lib/semmle/code/cpp/regex/internal/ParseRegExp.qll
@@ -11,8 +11,12 @@ private import semmle.code.cpp.exprs.Literal
 * A C++ string literal that contains a regular expression term, that is, either
 * a regular expression literal, or a string literal used in a context where
 * it is parsed as a regular expression.
+ *
+ * All string literals are considered potential regexes for now. Future work
+ * will restrict this to only string literals actually used as regular
+ * expressions (via construction-site flow analysis).
 */
-abstract class RegExp extends StringLiteral {
+class RegExp extends StringLiteral {
  /**
   * Holds if this `RegExp` has the `s` flag for multi-line matching.
   */
--- a/cpp/ql/test/library-tests/regex/parse.expected
+++ b/cpp/ql/test/library-tests/regex/parse.expected
@@ -0,0 +1,487 @@
+test.cpp:
+#   31| [RegExpConstant, RegExpNormalChar] abc
+
+#   34| [RegExpConstant, RegExpNormalChar] a
+
+#   34| [RegExpStar] a*
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+
+#   34| [RegExpSequence] a*b+c?d
+#-----| 0 -> [RegExpStar] a*
+#-----| 1 -> [RegExpPlus] b+
+#-----| 2 -> [RegExpOpt] c?
+#-----| 3 -> [RegExpConstant, RegExpNormalChar] d
+
+#   34| [RegExpConstant, RegExpNormalChar] b
+
+#   34| [RegExpPlus] b+
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] b
+
+#   34| [RegExpConstant, RegExpNormalChar] c
+
+#   34| [RegExpOpt] c?
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] c
+
+#   34| [RegExpConstant, RegExpNormalChar] d
+
+#   35| [RegExpConstant, RegExpNormalChar] a
+
+#   35| [RegExpRange] a{4,8}
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+
+#   36| [RegExpConstant, RegExpNormalChar] a
+
+#   36| [RegExpRange] a{,8}
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+
+#   37| [RegExpConstant, RegExpNormalChar] a
+
+#   37| [InfiniteRepetitionQuantifier, RegExpRange] a{3,}
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+
+#   38| [RegExpConstant, RegExpNormalChar] a
+
+#   38| [RegExpRange] a{7}
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+
+#   41| [RegExpConstant, RegExpNormalChar] foo
+
+#   41| [RegExpAlt] foo|bar
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] foo
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] bar
+
+#   41| [RegExpConstant, RegExpNormalChar] bar
+
+#   44| [RegExpCharacterClass] [abc]
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] b
+#-----| 2 -> [RegExpConstant, RegExpNormalChar] c
+
+#   44| [RegExpConstant, RegExpNormalChar] a
+
+#   44| [RegExpConstant, RegExpNormalChar] b
+
+#   44| [RegExpConstant, RegExpNormalChar] c
+
+#   45| [RegExpCharacterClass] [a-fA-F0-9_]
+#-----| 0 -> [RegExpCharacterRange] a-f
+#-----| 1 -> [RegExpCharacterRange] A-F
+#-----| 2 -> [RegExpCharacterRange] 0-9
+#-----| 3 -> [RegExpConstant, RegExpNormalChar] _
+
+#   45| [RegExpConstant, RegExpNormalChar] a
+
+#   45| [RegExpCharacterRange] a-f
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] f
+
+#   45| [RegExpConstant, RegExpNormalChar] f
+
+#   45| [RegExpConstant, RegExpNormalChar] A
+
+#   45| [RegExpCharacterRange] A-F
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] A
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] F
+
+#   45| [RegExpConstant, RegExpNormalChar] F
+
+#   45| [RegExpConstant, RegExpNormalChar] 0
+
+#   45| [RegExpCharacterRange] 0-9
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] 0
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] 9
+
+#   45| [RegExpConstant, RegExpNormalChar] 9
+
+#   45| [RegExpConstant, RegExpNormalChar] _
+
+#   46| [RegExpCaret] \A
+
+#   46| [RegExpSequence] \A[+-]?\d+
+#-----| 0 -> [RegExpCaret] \A
+#-----| 1 -> [RegExpOpt] [+-]?
+#-----| 2 -> [RegExpPlus] \d+
+
+#   46| [RegExpCharacterClass] [+-]
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] +
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] -
+
+#   46| [RegExpOpt] [+-]?
+#-----| 0 -> [RegExpCharacterClass] [+-]
+
+#   46| [RegExpConstant, RegExpNormalChar] +
+
+#   46| [RegExpConstant, RegExpNormalChar] -
+
+#   46| [RegExpCharacterClassEscape] \d
+
+#   46| [RegExpPlus] \d+
+#-----| 0 -> [RegExpCharacterClassEscape] \d
+
+#   47| [RegExpCharacterClass] [\w]
+#-----| 0 -> [RegExpCharacterClassEscape] \w
+
+#   47| [RegExpPlus] [\w]+
+#-----| 0 -> [RegExpCharacterClass] [\w]
+
+#   47| [RegExpCharacterClassEscape] \w
+
+#   48| [RegExpConstant, RegExpEscape] \[
+
+#   48| [RegExpSequence] \[\][123]
+#-----| 0 -> [RegExpConstant, RegExpEscape] \[
+#-----| 1 -> [RegExpConstant, RegExpEscape] \]
+#-----| 2 -> [RegExpCharacterClass] [123]
+
+#   48| [RegExpConstant, RegExpEscape] \]
+
+#   48| [RegExpCharacterClass] [123]
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] 1
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] 2
+#-----| 2 -> [RegExpConstant, RegExpNormalChar] 3
+
+#   48| [RegExpConstant, RegExpNormalChar] 1
+
+#   48| [RegExpConstant, RegExpNormalChar] 2
+
+#   48| [RegExpConstant, RegExpNormalChar] 3
+
+#   49| [RegExpCharacterClass] [^A-Z]
+#-----| 0 -> [RegExpCharacterRange] A-Z
+
+#   49| [RegExpConstant, RegExpNormalChar] A
+
+#   49| [RegExpCharacterRange] A-Z
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] A
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] Z
+
+#   49| [RegExpConstant, RegExpNormalChar] Z
+
+#   50| [RegExpCharacterClass] []]
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] ]
+
+#   50| [RegExpConstant, RegExpNormalChar] ]
+
+#   51| [RegExpCharacterClass] [^]]
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] ]
+
+#   51| [RegExpConstant, RegExpNormalChar] ]
+
+#   52| [RegExpCharacterClass] [^-]
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] -
+
+#   52| [RegExpConstant, RegExpNormalChar] -
+
+#   53| [RegExpCharacterClass] [|]
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] |
+
+#   53| [RegExpConstant, RegExpNormalChar] |
+
+#   56| [RegExpCharacterClass] [[a-f]
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] [
+#-----| 1 -> [RegExpCharacterRange] a-f
+
+#   56| [RegExpSequence] [[a-f]A-F]
+#-----| 0 -> [RegExpCharacterClass] [[a-f]
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] A-F]
+
+#   56| [RegExpConstant, RegExpNormalChar] [
+
+#   56| [RegExpConstant, RegExpNormalChar] a
+
+#   56| [RegExpCharacterRange] a-f
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] f
+
+#   56| [RegExpConstant, RegExpNormalChar] f
+
+#   56| [RegExpConstant, RegExpNormalChar] A-F]
+
+#   59| [RegExpDot] .
+
+#   59| [RegExpStar] .*
+#-----| 0 -> [RegExpDot] .
+
+#   60| [RegExpDot] .
+
+#   60| [RegExpStar] .*
+#-----| 0 -> [RegExpDot] .
+
+#   61| [RegExpCharacterClassEscape] \w
+
+#   61| [RegExpPlus] \w+
+#-----| 0 -> [RegExpCharacterClassEscape] \w
+
+#   61| [RegExpSequence] \w+\W
+#-----| 0 -> [RegExpPlus] \w+
+#-----| 1 -> [RegExpCharacterClassEscape] \W
+
+#   61| [RegExpCharacterClassEscape] \W
+
+#   62| [RegExpCharacterClassEscape] \s
+
+#   62| [RegExpSequence] \s\S
+#-----| 0 -> [RegExpCharacterClassEscape] \s
+#-----| 1 -> [RegExpCharacterClassEscape] \S
+
+#   62| [RegExpCharacterClassEscape] \S
+
+#   63| [RegExpCharacterClassEscape] \d
+
+#   63| [RegExpSequence] \d\D
+#-----| 0 -> [RegExpCharacterClassEscape] \d
+#-----| 1 -> [RegExpCharacterClassEscape] \D
+
+#   63| [RegExpCharacterClassEscape] \D
+
+#   64| [RegExpCharacterClassEscape] \h
+
+#   64| [RegExpSequence] \h\H
+#-----| 0 -> [RegExpCharacterClassEscape] \h
+#-----| 1 -> [RegExpCharacterClassEscape] \H
+
+#   64| [RegExpCharacterClassEscape] \H
+
+#   65| [RegExpConstant, RegExpEscape] \n
+
+#   65| [RegExpSequence] \n\r\t
+#-----| 0 -> [RegExpConstant, RegExpEscape] \n
+#-----| 1 -> [RegExpConstant, RegExpEscape] \r
+#-----| 2 -> [RegExpConstant, RegExpEscape] \t
+
+#   65| [RegExpConstant, RegExpEscape] \r
+
+#   65| [RegExpConstant, RegExpEscape] \t
+
+#   68| [RegExpSpecialChar] \G
+
+#   68| [RegExpSequence] \Gabc
+#-----| 0 -> [RegExpSpecialChar] \G
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] abc
+
+#   68| [RegExpConstant, RegExpNormalChar] abc
+
+#   69| [RegExpSpecialChar] \b
+
+#   69| [RegExpSequence] \b!a\B
+#-----| 0 -> [RegExpSpecialChar] \b
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] !a
+#-----| 2 -> [RegExpNonWordBoundary] \B
+
+#   69| [RegExpConstant, RegExpNormalChar] !a
+
+#   69| [RegExpNonWordBoundary] \B
+
+#   72| [RegExpGroup] (foo)
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] foo
+
+#   72| [RegExpStar] (foo)*
+#-----| 0 -> [RegExpGroup] (foo)
+
+#   72| [RegExpSequence] (foo)*bar
+#-----| 0 -> [RegExpStar] (foo)*
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] bar
+
+#   72| [RegExpConstant, RegExpNormalChar] foo
+
+#   72| [RegExpConstant, RegExpNormalChar] bar
+
+#   73| [RegExpConstant, RegExpNormalChar] fo
+
+#   73| [RegExpSequence] fo(o|b)ar
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] fo
+#-----| 1 -> [RegExpGroup] (o|b)
+#-----| 2 -> [RegExpConstant, RegExpNormalChar] ar
+
+#   73| [RegExpGroup] (o|b)
+#-----| 0 -> [RegExpAlt] o|b
+
+#   73| [RegExpConstant, RegExpNormalChar] o
+
+#   73| [RegExpAlt] o|b
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] o
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] b
+
+#   73| [RegExpConstant, RegExpNormalChar] b
+
+#   73| [RegExpConstant, RegExpNormalChar] ar
+
+#   74| [RegExpGroup] (a|b|cd)
+#-----| 0 -> [RegExpAlt] a|b|cd
+
+#   74| [RegExpSequence] (a|b|cd)e
+#-----| 0 -> [RegExpGroup] (a|b|cd)
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] e
+
+#   74| [RegExpConstant, RegExpNormalChar] a
+
+#   74| [RegExpAlt] a|b|cd
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] b
+#-----| 2 -> [RegExpConstant, RegExpNormalChar] cd
+
+#   74| [RegExpConstant, RegExpNormalChar] b
+
+#   74| [RegExpConstant, RegExpNormalChar] cd
+
+#   74| [RegExpConstant, RegExpNormalChar] e
+
+#   75| [RegExpGroup] (?::+)
+#-----| 0 -> [RegExpPlus] :+
+
+#   75| [RegExpSequence] (?::+)\w
+#-----| 0 -> [RegExpGroup] (?::+)
+#-----| 1 -> [RegExpCharacterClassEscape] \w
+
+#   75| [RegExpConstant, RegExpNormalChar] :
+
+#   75| [RegExpPlus] :+
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] :
+
+#   75| [RegExpCharacterClassEscape] \w
+
+#   78| [RegExpGroup] (?<id>\w+)
+#-----| 0 -> [RegExpPlus] \w+
+
+#   78| [RegExpCharacterClassEscape] \w
+
+#   78| [RegExpPlus] \w+
+#-----| 0 -> [RegExpCharacterClassEscape] \w
+
+#   79| [RegExpGroup] (?'foo'fo+)
+#-----| 0 -> [RegExpSequence] fo+
+
+#   79| [RegExpConstant, RegExpNormalChar] f
+
+#   79| [RegExpSequence] fo+
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] f
+#-----| 1 -> [RegExpPlus] o+
+
+#   79| [RegExpConstant, RegExpNormalChar] o
+
+#   79| [RegExpPlus] o+
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] o
+
+#   82| [RegExpGroup] (a+)
+#-----| 0 -> [RegExpPlus] a+
+
+#   82| [RegExpSequence] (a+)b+\1
+#-----| 0 -> [RegExpGroup] (a+)
+#-----| 1 -> [RegExpPlus] b+
+#-----| 2 -> [RegExpBackRef] \1
+
+#   82| [RegExpConstant, RegExpNormalChar] a
+
+#   82| [RegExpPlus] a+
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+
+#   82| [RegExpConstant, RegExpNormalChar] b
+
+#   82| [RegExpPlus] b+
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] b
+
+#   82| [RegExpBackRef] \1
+
+#   83| [RegExpGroup] (?<qux>q+)
+#-----| 0 -> [RegExpPlus] q+
+
+#   83| [RegExpSequence] (?<qux>q+)\s+\k<qux>+
+#-----| 0 -> [RegExpGroup] (?<qux>q+)
+#-----| 1 -> [RegExpPlus] \s+
+#-----| 2 -> [RegExpPlus] \k<qux>+
+
+#   83| [RegExpConstant, RegExpNormalChar] q
+
+#   83| [RegExpPlus] q+
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] q
+
+#   83| [RegExpCharacterClassEscape] \s
+
+#   83| [RegExpPlus] \s+
+#-----| 0 -> [RegExpCharacterClassEscape] \s
+
+#   83| [RegExpBackRef] \k<qux>
+
+#   83| [RegExpPlus] \k<qux>+
+#-----| 0 -> [RegExpBackRef] \k<qux>
+
+#   86| [RegExpNamedCharacterProperty] \p{Word}
+
+#   86| [RegExpStar] \p{Word}*
+#-----| 0 -> [RegExpNamedCharacterProperty] \p{Word}
+
+#   87| [RegExpNamedCharacterProperty] \P{Digit}
+
+#   87| [RegExpPlus] \P{Digit}+
+#-----| 0 -> [RegExpNamedCharacterProperty] \P{Digit}
+
+#   88| [RegExpNamedCharacterProperty] \p{^Alnum}
+
+#   88| [RegExpRange] \p{^Alnum}{2,3}
+#-----| 0 -> [RegExpNamedCharacterProperty] \p{^Alnum}
+
+#   89| [RegExpCharacterClass] [a-f\p{Digit}]
+#-----| 0 -> [RegExpCharacterRange] a-f
+#-----| 1 -> [RegExpNamedCharacterProperty] \p{Digit}
+
+#   89| [RegExpPlus] [a-f\p{Digit}]+
+#-----| 0 -> [RegExpCharacterClass] [a-f\p{Digit}]
+
+#   89| [RegExpConstant, RegExpNormalChar] a
+
+#   89| [RegExpCharacterRange] a-f
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] f
+
+#   89| [RegExpConstant, RegExpNormalChar] f
+
+#   89| [RegExpNamedCharacterProperty] \p{Digit}
+
+#   92| [RegExpCharacterClass] [[:alpha:]]
+#-----| 0 -> [RegExpNamedCharacterProperty] [:alpha:]
+
+#   92| [RegExpSequence] [[:alpha:]][[:digit:]]
+#-----| 0 -> [RegExpCharacterClass] [[:alpha:]]
+#-----| 1 -> [RegExpCharacterClass] [[:digit:]]
+
+#   92| [RegExpNamedCharacterProperty] [:alpha:]
+
+#   92| [RegExpCharacterClass] [[:digit:]]
+#-----| 0 -> [RegExpNamedCharacterProperty] [:digit:]
+
+#   92| [RegExpNamedCharacterProperty] [:digit:]
+
+#   95| [RegExpCharacterClass] [[:alpha:][:digit:]]
+#-----| 0 -> [RegExpNamedCharacterProperty] [:alpha:]
+#-----| 1 -> [RegExpNamedCharacterProperty] [:digit:]
+
+#   95| [RegExpNamedCharacterProperty] [:alpha:]
+
+#   95| [RegExpNamedCharacterProperty] [:digit:]
+
+#   98| [RegExpCharacterClass] [A-F[:digit:]a-f]
+#-----| 0 -> [RegExpCharacterRange] A-F
+#-----| 1 -> [RegExpNamedCharacterProperty] [:digit:]
+#-----| 2 -> [RegExpCharacterRange] a-f
+
+#   98| [RegExpConstant, RegExpNormalChar] A
+
+#   98| [RegExpCharacterRange] A-F
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] A
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] F
+
+#   98| [RegExpConstant, RegExpNormalChar] F
+
+#   98| [RegExpNamedCharacterProperty] [:digit:]
+
+#   98| [RegExpConstant, RegExpNormalChar] a
+
+#   98| [RegExpCharacterRange] a-f
+#-----| 0 -> [RegExpConstant, RegExpNormalChar] a
+#-----| 1 -> [RegExpConstant, RegExpNormalChar] f
+
+#   98| [RegExpConstant, RegExpNormalChar] f
+
+#  101| [RegExpNamedCharacterProperty] [:digit:]
+
+#  106| [RegExpConstant, RegExpEscape] \u{987
--- a/cpp/ql/test/library-tests/regex/regexp.expected
+++ b/cpp/ql/test/library-tests/regex/regexp.expected
@@ -0,0 +1,268 @@
+groupName
+| test.cpp:78:21:78:30 | (?<id>\\w+) | id |
+| test.cpp:79:21:79:31 | (?'foo'fo+) | foo |
+| test.cpp:83:23:83:32 | (?<qux>q+) | qux |
+groupNumber
+| test.cpp:72:22:72:26 | (foo) | 1 |
+| test.cpp:73:24:73:28 | (o\|b) | 1 |
+| test.cpp:74:22:74:29 | (a\|b\|cd) | 1 |
+| test.cpp:79:21:79:31 | (?'foo'fo+) | 1 |
+| test.cpp:82:23:82:26 | (a+) | 1 |
+term
+| test.cpp:31:21:31:23 | abc | RegExpConstant,RegExpNormalChar |
+| test.cpp:34:22:34:22 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:34:22:34:23 | a* | RegExpStar |
+| test.cpp:34:22:34:28 | a*b+c?d | RegExpSequence |
+| test.cpp:34:24:34:24 | b | RegExpConstant,RegExpNormalChar |
+| test.cpp:34:24:34:25 | b+ | RegExpPlus |
+| test.cpp:34:26:34:26 | c | RegExpConstant,RegExpNormalChar |
+| test.cpp:34:26:34:27 | c? | RegExpOpt |
+| test.cpp:34:28:34:28 | d | RegExpConstant,RegExpNormalChar |
+| test.cpp:35:22:35:22 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:35:22:35:27 | a{4,8} | RegExpRange |
+| test.cpp:36:22:36:22 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:36:22:36:26 | a{,8} | RegExpRange |
+| test.cpp:37:22:37:22 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:37:22:37:26 | a{3,} | InfiniteRepetitionQuantifier,RegExpRange |
+| test.cpp:38:22:38:22 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:38:22:38:25 | a{7} | RegExpRange |
+| test.cpp:41:21:41:23 | foo | RegExpConstant,RegExpNormalChar |
+| test.cpp:41:21:41:27 | foo\|bar | RegExpAlt |
+| test.cpp:41:25:41:27 | bar | RegExpConstant,RegExpNormalChar |
+| test.cpp:44:21:44:25 | [abc] | RegExpCharacterClass |
+| test.cpp:44:22:44:22 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:44:23:44:23 | b | RegExpConstant,RegExpNormalChar |
+| test.cpp:44:24:44:24 | c | RegExpConstant,RegExpNormalChar |
+| test.cpp:45:21:45:32 | [a-fA-F0-9_] | RegExpCharacterClass |
+| test.cpp:45:22:45:22 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:45:22:45:24 | a-f | RegExpCharacterRange |
+| test.cpp:45:24:45:24 | f | RegExpConstant,RegExpNormalChar |
+| test.cpp:45:25:45:25 | A | RegExpConstant,RegExpNormalChar |
+| test.cpp:45:25:45:27 | A-F | RegExpCharacterRange |
+| test.cpp:45:27:45:27 | F | RegExpConstant,RegExpNormalChar |
+| test.cpp:45:28:45:28 | 0 | RegExpConstant,RegExpNormalChar |
+| test.cpp:45:28:45:30 | 0-9 | RegExpCharacterRange |
+| test.cpp:45:30:45:30 | 9 | RegExpConstant,RegExpNormalChar |
+| test.cpp:45:31:45:31 | _ | RegExpConstant,RegExpNormalChar |
+| test.cpp:46:21:46:22 | \\A | RegExpCaret |
+| test.cpp:46:21:46:30 | \\A[+-]?\\d+ | RegExpSequence |
+| test.cpp:46:23:46:26 | [+-] | RegExpCharacterClass |
+| test.cpp:46:23:46:27 | [+-]? | RegExpOpt |
+| test.cpp:46:24:46:24 | + | RegExpConstant,RegExpNormalChar |
+| test.cpp:46:25:46:25 | - | RegExpConstant,RegExpNormalChar |
+| test.cpp:46:28:46:29 | \\d | RegExpCharacterClassEscape |
+| test.cpp:46:28:46:30 | \\d+ | RegExpPlus |
+| test.cpp:47:21:47:24 | [\\w] | RegExpCharacterClass |
+| test.cpp:47:21:47:25 | [\\w]+ | RegExpPlus |
+| test.cpp:47:22:47:23 | \\w | RegExpCharacterClassEscape |
+| test.cpp:48:21:48:22 | \\[ | RegExpConstant,RegExpEscape |
+| test.cpp:48:21:48:29 | \\[\\][123] | RegExpSequence |
+| test.cpp:48:23:48:24 | \\] | RegExpConstant,RegExpEscape |
+| test.cpp:48:25:48:29 | [123] | RegExpCharacterClass |
+| test.cpp:48:26:48:26 | 1 | RegExpConstant,RegExpNormalChar |
+| test.cpp:48:27:48:27 | 2 | RegExpConstant,RegExpNormalChar |
+| test.cpp:48:28:48:28 | 3 | RegExpConstant,RegExpNormalChar |
+| test.cpp:49:21:49:26 | [^A-Z] | RegExpCharacterClass |
+| test.cpp:49:23:49:23 | A | RegExpConstant,RegExpNormalChar |
+| test.cpp:49:23:49:25 | A-Z | RegExpCharacterRange |
+| test.cpp:49:25:49:25 | Z | RegExpConstant,RegExpNormalChar |
+| test.cpp:50:21:50:23 | []] | RegExpCharacterClass |
+| test.cpp:50:22:50:22 | ] | RegExpConstant,RegExpNormalChar |
+| test.cpp:51:21:51:24 | [^]] | RegExpCharacterClass |
+| test.cpp:51:23:51:23 | ] | RegExpConstant,RegExpNormalChar |
+| test.cpp:52:21:52:24 | [^-] | RegExpCharacterClass |
+| test.cpp:52:23:52:23 | - | RegExpConstant,RegExpNormalChar |
+| test.cpp:53:22:53:24 | [\|] | RegExpCharacterClass |
+| test.cpp:53:23:53:23 | \| | RegExpConstant,RegExpNormalChar |
+| test.cpp:56:24:56:29 | [[a-f] | RegExpCharacterClass |
+| test.cpp:56:24:56:33 | [[a-f]A-F] | RegExpSequence |
+| test.cpp:56:25:56:25 | [ | RegExpConstant,RegExpNormalChar |
+| test.cpp:56:26:56:26 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:56:26:56:28 | a-f | RegExpCharacterRange |
+| test.cpp:56:28:56:28 | f | RegExpConstant,RegExpNormalChar |
+| test.cpp:56:30:56:33 | A-F] | RegExpConstant,RegExpNormalChar |
+| test.cpp:59:23:59:23 | . | RegExpDot |
+| test.cpp:59:23:59:24 | .* | RegExpStar |
+| test.cpp:60:24:60:24 | . | RegExpDot |
+| test.cpp:60:24:60:25 | .* | RegExpStar |
+| test.cpp:61:23:61:24 | \\w | RegExpCharacterClassEscape |
+| test.cpp:61:23:61:25 | \\w+ | RegExpPlus |
+| test.cpp:61:23:61:27 | \\w+\\W | RegExpSequence |
+| test.cpp:61:26:61:27 | \\W | RegExpCharacterClassEscape |
+| test.cpp:62:23:62:24 | \\s | RegExpCharacterClassEscape |
+| test.cpp:62:23:62:26 | \\s\\S | RegExpSequence |
+| test.cpp:62:25:62:26 | \\S | RegExpCharacterClassEscape |
+| test.cpp:63:23:63:24 | \\d | RegExpCharacterClassEscape |
+| test.cpp:63:23:63:26 | \\d\\D | RegExpSequence |
+| test.cpp:63:25:63:26 | \\D | RegExpCharacterClassEscape |
+| test.cpp:64:23:64:24 | \\h | RegExpCharacterClassEscape |
+| test.cpp:64:23:64:26 | \\h\\H | RegExpSequence |
+| test.cpp:64:25:64:26 | \\H | RegExpCharacterClassEscape |
+| test.cpp:65:23:65:24 | \\n | RegExpConstant,RegExpEscape |
+| test.cpp:65:23:65:28 | \\n\\r\\t | RegExpSequence |
+| test.cpp:65:25:65:26 | \\r | RegExpConstant,RegExpEscape |
+| test.cpp:65:27:65:28 | \\t | RegExpConstant,RegExpEscape |
+| test.cpp:68:22:68:23 | \\G | RegExpSpecialChar |
+| test.cpp:68:22:68:26 | \\Gabc | RegExpSequence |
+| test.cpp:68:24:68:26 | abc | RegExpConstant,RegExpNormalChar |
+| test.cpp:69:22:69:23 | \\b | RegExpSpecialChar |
+| test.cpp:69:22:69:27 | \\b!a\\B | RegExpSequence |
+| test.cpp:69:24:69:25 | !a | RegExpConstant,RegExpNormalChar |
+| test.cpp:69:26:69:27 | \\B | RegExpNonWordBoundary |
+| test.cpp:72:22:72:26 | (foo) | RegExpGroup |
+| test.cpp:72:22:72:27 | (foo)* | RegExpStar |
+| test.cpp:72:22:72:30 | (foo)*bar | RegExpSequence |
+| test.cpp:72:23:72:25 | foo | RegExpConstant,RegExpNormalChar |
+| test.cpp:72:28:72:30 | bar | RegExpConstant,RegExpNormalChar |
+| test.cpp:73:22:73:23 | fo | RegExpConstant,RegExpNormalChar |
+| test.cpp:73:22:73:30 | fo(o\|b)ar | RegExpSequence |
+| test.cpp:73:24:73:28 | (o\|b) | RegExpGroup |
+| test.cpp:73:25:73:25 | o | RegExpConstant,RegExpNormalChar |
+| test.cpp:73:25:73:27 | o\|b | RegExpAlt |
+| test.cpp:73:27:73:27 | b | RegExpConstant,RegExpNormalChar |
+| test.cpp:73:29:73:30 | ar | RegExpConstant,RegExpNormalChar |
+| test.cpp:74:22:74:29 | (a\|b\|cd) | RegExpGroup |
+| test.cpp:74:22:74:30 | (a\|b\|cd)e | RegExpSequence |
+| test.cpp:74:23:74:23 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:74:23:74:28 | a\|b\|cd | RegExpAlt |
+| test.cpp:74:25:74:25 | b | RegExpConstant,RegExpNormalChar |
+| test.cpp:74:27:74:28 | cd | RegExpConstant,RegExpNormalChar |
+| test.cpp:74:30:74:30 | e | RegExpConstant,RegExpNormalChar |
+| test.cpp:75:22:75:27 | (?::+) | RegExpGroup |
+| test.cpp:75:22:75:29 | (?::+)\\w | RegExpSequence |
+| test.cpp:75:25:75:25 | : | RegExpConstant,RegExpNormalChar |
+| test.cpp:75:25:75:26 | :+ | RegExpPlus |
+| test.cpp:75:28:75:29 | \\w | RegExpCharacterClassEscape |
+| test.cpp:78:21:78:30 | (?<id>\\w+) | RegExpGroup |
+| test.cpp:78:27:78:28 | \\w | RegExpCharacterClassEscape |
+| test.cpp:78:27:78:29 | \\w+ | RegExpPlus |
+| test.cpp:79:21:79:31 | (?'foo'fo+) | RegExpGroup |
+| test.cpp:79:28:79:28 | f | RegExpConstant,RegExpNormalChar |
+| test.cpp:79:28:79:30 | fo+ | RegExpSequence |
+| test.cpp:79:29:79:29 | o | RegExpConstant,RegExpNormalChar |
+| test.cpp:79:29:79:30 | o+ | RegExpPlus |
+| test.cpp:82:23:82:26 | (a+) | RegExpGroup |
+| test.cpp:82:23:82:30 | (a+)b+\\1 | RegExpSequence |
+| test.cpp:82:24:82:24 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:82:24:82:25 | a+ | RegExpPlus |
+| test.cpp:82:27:82:27 | b | RegExpConstant,RegExpNormalChar |
+| test.cpp:82:27:82:28 | b+ | RegExpPlus |
+| test.cpp:82:29:82:30 | \\1 | RegExpBackRef |
+| test.cpp:83:23:83:32 | (?<qux>q+) | RegExpGroup |
+| test.cpp:83:23:83:43 | (?<qux>q+)\\s+\\k<qux>+ | RegExpSequence |
+| test.cpp:83:30:83:30 | q | RegExpConstant,RegExpNormalChar |
+| test.cpp:83:30:83:31 | q+ | RegExpPlus |
+| test.cpp:83:33:83:34 | \\s | RegExpCharacterClassEscape |
+| test.cpp:83:33:83:35 | \\s+ | RegExpPlus |
+| test.cpp:83:36:83:42 | \\k<qux> | RegExpBackRef |
+| test.cpp:83:36:83:43 | \\k<qux>+ | RegExpPlus |
+| test.cpp:86:23:86:30 | \\p{Word} | RegExpNamedCharacterProperty |
+| test.cpp:86:23:86:31 | \\p{Word}* | RegExpStar |
+| test.cpp:87:23:87:31 | \\P{Digit} | RegExpNamedCharacterProperty |
+| test.cpp:87:23:87:32 | \\P{Digit}+ | RegExpPlus |
+| test.cpp:88:23:88:32 | \\p{^Alnum} | RegExpNamedCharacterProperty |
+| test.cpp:88:23:88:37 | \\p{^Alnum}{2,3} | RegExpRange |
+| test.cpp:89:23:89:36 | [a-f\\p{Digit}] | RegExpCharacterClass |
+| test.cpp:89:23:89:37 | [a-f\\p{Digit}]+ | RegExpPlus |
+| test.cpp:89:24:89:24 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:89:24:89:26 | a-f | RegExpCharacterRange |
+| test.cpp:89:26:89:26 | f | RegExpConstant,RegExpNormalChar |
+| test.cpp:89:27:89:35 | \\p{Digit} | RegExpNamedCharacterProperty |
+| test.cpp:92:24:92:34 | [[:alpha:]] | RegExpCharacterClass |
+| test.cpp:92:24:92:45 | [[:alpha:]][[:digit:]] | RegExpSequence |
+| test.cpp:92:25:92:33 | [:alpha:] | RegExpNamedCharacterProperty |
+| test.cpp:92:35:92:45 | [[:digit:]] | RegExpCharacterClass |
+| test.cpp:92:36:92:44 | [:digit:] | RegExpNamedCharacterProperty |
+| test.cpp:95:24:95:43 | [[:alpha:][:digit:]] | RegExpCharacterClass |
+| test.cpp:95:25:95:33 | [:alpha:] | RegExpNamedCharacterProperty |
+| test.cpp:95:34:95:42 | [:digit:] | RegExpNamedCharacterProperty |
+| test.cpp:98:24:98:40 | [A-F[:digit:]a-f] | RegExpCharacterClass |
+| test.cpp:98:25:98:25 | A | RegExpConstant,RegExpNormalChar |
+| test.cpp:98:25:98:27 | A-F | RegExpCharacterRange |
+| test.cpp:98:27:98:27 | F | RegExpConstant,RegExpNormalChar |
+| test.cpp:98:28:98:36 | [:digit:] | RegExpNamedCharacterProperty |
+| test.cpp:98:37:98:37 | a | RegExpConstant,RegExpNormalChar |
+| test.cpp:98:37:98:39 | a-f | RegExpCharacterRange |
+| test.cpp:98:39:98:39 | f | RegExpConstant,RegExpNormalChar |
+| test.cpp:101:24:101:32 | [:digit:] | RegExpNamedCharacterProperty |
+| test.cpp:106:21:106:26 | \\u{987 | RegExpConstant,RegExpEscape |
+regExpNormalCharValue
+| test.cpp:31:21:31:23 | abc | abc |
+| test.cpp:34:22:34:22 | a | a |
+| test.cpp:34:24:34:24 | b | b |
+| test.cpp:34:26:34:26 | c | c |
+| test.cpp:34:28:34:28 | d | d |
+| test.cpp:35:22:35:22 | a | a |
+| test.cpp:36:22:36:22 | a | a |
+| test.cpp:37:22:37:22 | a | a |
+| test.cpp:38:22:38:22 | a | a |
+| test.cpp:41:21:41:23 | foo | foo |
+| test.cpp:41:25:41:27 | bar | bar |
+| test.cpp:44:22:44:22 | a | a |
+| test.cpp:44:23:44:23 | b | b |
+| test.cpp:44:24:44:24 | c | c |
+| test.cpp:45:22:45:22 | a | a |
+| test.cpp:45:24:45:24 | f | f |
+| test.cpp:45:25:45:25 | A | A |
+| test.cpp:45:27:45:27 | F | F |
+| test.cpp:45:28:45:28 | 0 | 0 |
+| test.cpp:45:30:45:30 | 9 | 9 |
+| test.cpp:45:31:45:31 | _ | _ |
+| test.cpp:46:24:46:24 | + | + |
+| test.cpp:46:25:46:25 | - | - |
+| test.cpp:46:28:46:29 | \\d | d |
+| test.cpp:47:22:47:23 | \\w | w |
+| test.cpp:48:21:48:22 | \\[ | [ |
+| test.cpp:48:23:48:24 | \\] | ] |
+| test.cpp:48:26:48:26 | 1 | 1 |
+| test.cpp:48:27:48:27 | 2 | 2 |
+| test.cpp:48:28:48:28 | 3 | 3 |
+| test.cpp:49:23:49:23 | A | A |
+| test.cpp:49:25:49:25 | Z | Z |
+| test.cpp:50:22:50:22 | ] | ] |
+| test.cpp:51:23:51:23 | ] | ] |
+| test.cpp:52:23:52:23 | - | - |
+| test.cpp:53:23:53:23 | \| | \| |
+| test.cpp:56:25:56:25 | [ | [ |
+| test.cpp:56:26:56:26 | a | a |
+| test.cpp:56:28:56:28 | f | f |
+| test.cpp:56:30:56:33 | A-F] | A-F] |
+| test.cpp:61:23:61:24 | \\w | w |
+| test.cpp:61:26:61:27 | \\W | W |
+| test.cpp:62:23:62:24 | \\s | s |
+| test.cpp:62:25:62:26 | \\S | S |
+| test.cpp:63:23:63:24 | \\d | d |
+| test.cpp:63:25:63:26 | \\D | D |
+| test.cpp:64:23:64:24 | \\h | h |
+| test.cpp:64:25:64:26 | \\H | H |
+| test.cpp:65:23:65:24 | \\n | \n |
+| test.cpp:65:25:65:26 | \\r | \r |
+| test.cpp:65:27:65:28 | \\t | \t |
+| test.cpp:68:24:68:26 | abc | abc |
+| test.cpp:69:24:69:25 | !a | !a |
+| test.cpp:72:23:72:25 | foo | foo |
+| test.cpp:72:28:72:30 | bar | bar |
+| test.cpp:73:22:73:23 | fo | fo |
+| test.cpp:73:25:73:25 | o | o |
+| test.cpp:73:27:73:27 | b | b |
+| test.cpp:73:29:73:30 | ar | ar |
+| test.cpp:74:23:74:23 | a | a |
+| test.cpp:74:25:74:25 | b | b |
+| test.cpp:74:27:74:28 | cd | cd |
+| test.cpp:74:30:74:30 | e | e |
+| test.cpp:75:25:75:25 | : | : |
+| test.cpp:75:28:75:29 | \\w | w |
+| test.cpp:78:27:78:28 | \\w | w |
+| test.cpp:79:28:79:28 | f | f |
+| test.cpp:79:29:79:29 | o | o |
+| test.cpp:82:24:82:24 | a | a |
+| test.cpp:82:27:82:27 | b | b |
+| test.cpp:83:30:83:30 | q | q |
+| test.cpp:83:33:83:34 | \\s | s |
+| test.cpp:89:24:89:24 | a | a |
+| test.cpp:89:26:89:26 | f | f |
+| test.cpp:98:25:98:25 | A | A |
+| test.cpp:98:27:98:27 | F | F |
+| test.cpp:98:37:98:37 | a | a |
+| test.cpp:98:39:98:39 | f | f |
+| test.cpp:106:21:106:26 | \\u{987 | \u0987 |
--- a/cpp/ql/test/library-tests/regex/test.cpp
+++ b/cpp/ql/test/library-tests/regex/test.cpp
@@ -0,0 +1,107 @@
+// Minimal stubs for std::regex surface — no #include of any external header.
+// Provides just enough of the std:: regex API that the C++ extractor
+// creates StringLiteral nodes for each regex pattern, using real qualified
+// names so a future flow-config PR can identify them unchanged.
+namespace std {
+  template <class CharT>
+  class basic_regex {
+  public:
+    basic_regex(const char *s) {}
+    basic_regex(const char *s, int flags) {}
+    basic_regex &assign(const char *s) { return *this; }
+  };
+  typedef basic_regex<char> regex;
+
+  template <class CharT>
+  bool regex_match(const char *s, const basic_regex<CharT> &re) { return false; }
+
+  template <class CharT>
+  bool regex_search(const char *s, const basic_regex<CharT> &re) { return false; }
+
+  template <class CharT>
+  const char *regex_replace(const char *s, const basic_regex<CharT> &re,
+                            const char *fmt) { return s; }
+} // namespace std
+
+void test() {
+  // Empty
+  std::regex r_empty("");
+
+  // Basic sequence
+  std::regex r_abc("abc");
+
+  // Repetition
+  std::regex r_rep1("a*b+c?d");
+  std::regex r_rep2("a{4,8}");
+  std::regex r_rep3("a{,8}");
+  std::regex r_rep4("a{3,}");
+  std::regex r_rep5("a{7}");
+
+  // Alternation
+  std::regex r_alt("foo|bar");
+
+  // Character classes
+  std::regex r_cc1("[abc]");
+  std::regex r_cc2("[a-fA-F0-9_]");
+  std::regex r_cc3("\\A[+-]?\\d+");
+  std::regex r_cc4("[\\w]+");
+  std::regex r_cc5("\\[\\][123]");
+  std::regex r_cc6("[^A-Z]");
+  std::regex r_cc7("[]]");   // MRI gives a warning, but accepts this as matching ']'
+  std::regex r_cc8("[^]]"); // MRI gives a warning, but accepts this as matching anything except ']'
+  std::regex r_cc9("[^-]");
+  std::regex r_cc10("[|]");
+
+  // Nested character classes (BAD - not parsed correctly)
+  std::regex r_nested("[[a-f]A-F]");
+
+  // Meta-character classes
+  std::regex r_meta1(".*");
+  std::regex r_meta1m(".*"); // /.*/m mode variant — mode flags are constructor args in C++
+  std::regex r_meta2("\\w+\\W");
+  std::regex r_meta3("\\s\\S");
+  std::regex r_meta4("\\d\\D");
+  std::regex r_meta5("\\h\\H");
+  std::regex r_meta6("\\n\\r\\t");
+
+  // Anchors
+  std::regex r_anc1("\\Gabc");
+  std::regex r_anc2("\\b!a\\B");
+
+  // Groups
+  std::regex r_grp1("(foo)*bar");
+  std::regex r_grp2("fo(o|b)ar");
+  std::regex r_grp3("(a|b|cd)e");
+  std::regex r_grp4("(?::+)\\w"); // Non-capturing group matching colons
+
+  // Named groups
+  std::regex r_ng1("(?<id>\\w+)");
+  std::regex r_ng2("(?'foo'fo+)"); // single-quote named-group form
+
+  // Backreferences
+  std::regex r_bref1("(a+)b+\\1");
+  std::regex r_bref2("(?<qux>q+)\\s+\\k<qux>+");
+
+  // Named character properties using the p-style syntax
+  std::regex r_prop1("\\p{Word}*");
+  std::regex r_prop2("\\P{Digit}+");
+  std::regex r_prop3("\\p{^Alnum}{2,3}");
+  std::regex r_prop4("[a-f\\p{Digit}]+"); // Also valid inside character classes
+
+  // Two separate character classes, each containing a single POSIX bracket expression
+  std::regex r_posix1("[[:alpha:]][[:digit:]]");
+
+  // A single character class containing two POSIX bracket expressions
+  std::regex r_posix2("[[:alpha:][:digit:]]");
+
+  // A single character class containing two ranges and one POSIX bracket expression
+  std::regex r_posix3("[A-F[:digit:]a-f]");
+
+  // *Not* a POSIX bracket expression; just a regular character class.
+  std::regex r_posix4("[:digit:]");
+
+  // Dropped: /#{A}bc/ — Ruby string interpolation, no C++ string-literal form.
+
+  // unicode: \u{9879} in C++ (Ruby unicode escape syntax)
+  std::regex r_uni("\\u{9879}");
+}