simon/jolt
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge pull request #281 from jolt-lang/irregex-submatch-clear

Browse source 
Compile capturing regexes with the backtracking matcher
This commit is contained in:
Dmitri Sotnikov 2026-07-01 16:54:06 +00:00 • committed by GitHub
commit 53112d06fb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 17 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

17
host/chez/regex.ss
View file

@ -159,10 +159,23 @@
;; A jolt regex value: the source string (for printing / str) + the compiled
;; irregex. regex? recognizes it; the printer renders #"source".
(define-record-type regex-t (fields source irx) (nongenerative jolt-regex-v1))
;; A capturing pattern is compiled with irregex's BACKTRACKING matcher ('backtrack),
;; not its DFA. java.util.regex is itself a leftmost-first backtracking engine, so
;; this matches the JVM's submatch semantics; irregex's DFA is POSIX leftmost-longest
;; and, worse, leaks a non-participating alternation group's capture (e.g.
;; #"(?:([0-9])|([0-9])r([0-9]+))" on "2r11" left group 1 = "2"), which broke
;; tools.reader's number reader. Non-capturing patterns keep the fast DFA — with no
;; groups to read, its whole-match result is all a caller sees. The count comes from
;; a first cheap compile; a capturing pattern is recompiled once (patterns compile
;; once and cache in the regex-t).
(define (jolt-regex source)
(let-values (((opts pat) (regex-parse-flags source)))
(make-regex-t source
(apply irregex (translate-prop-classes (escape-class-shorthand-dash pat)) opts))))
(let* ((p (translate-prop-classes (escape-class-shorthand-dash pat)))
(irx (apply irregex p opts)))
(make-regex-t source
(if (> (irregex-num-submatches irx) 0)
(apply irregex p 'backtrack opts)
irx)))))
(define (jolt-regex? x) (regex-t? x))
(define (jolt-re-pattern x) (if (regex-t? x) x (jolt-regex x)))

2
test/chez/corpus.edn
View file

@ -1,5 +1,7 @@
[
{:suite "host-interop / reify ILookup" :label "(get reify k) / (:k reify) / (get reify k d) route to valAt" :expected "[1 1 :dflt]" :actual "(let [r (reify clojure.lang.ILookup (valAt [_ k] (get {:a 1} k)) (valAt [_ k d] (get {:a 1} k d)))] [(:a r) (get r :a) (get r :z :dflt)])"}
{:suite "regex / alternation submatch" :label "a non-participating alternation group is nil, not a stale capture" :expected "[\"2r11\" nil \"2\" \"11\"]" :actual "(re-matches #\"(?:([0-9])|([0-9])r([0-9]+))\" \"2r11\")"}
{:suite "regex / radix read" :label "tools.reader-style radix parse: winning branch's groups, not the losing one's" :expected "[12 255]" :actual "[(read-string \"2r1100\") (read-string \"16rFF\")]"}
{:suite "numbers / comparison error class" :label "nil operand is NPE, non-number is CCE" :expected "[\"java.lang.NullPointerException\" \"java.lang.ClassCastException\"]" :actual "[(try (> nil 5) (catch Throwable e (.getName (class e)))) (try (> :k 5) (catch Throwable e (.getName (class e))))]"}
{:suite "reader / quoted #inst constructs a value" :label "a quoted #inst literal is the constructed Date, not a tagged form" :expected "\"(f #inst \\\"1939-01-01T00:00:00.000-00:00\\\")\"" :actual "(pr-str (quote (f #inst \"1939\")))"}
{:suite "fn / kwargs trailing map" :label "(f :k v {map}) and (f {map}) both bind & {:as m}" :expected "[{:x 1 :y 2} {:x 1 :y 2}]" :actual "[((fn [a & {:as m}] m) 1 :x 1 {:y 2}) ((fn [a & {:as m}] m) 1 {:x 1 :y 2})]"}