CLJS-2979: re-seq is relying on undefined behavior of subs

This commit makes re-seq only do a call to subs with defined values. It also optimizes the code. Tests for re-seq regarding CLJS-810 are provided as well.

Author: borkdude

src/main/cljs/cljs/core.cljs

@@ -9845,15 +9845,25 @@ reduces them without incurring seq initialization"
  (vec matches))))
  (throw (js/TypeError. "re-find must match against a string."))))
 
+(defn- re-seq* [re s]
+ (when-some [matches (.exec re s)]
+ (let [match-str (aget matches 0)
+ match-vals (if (== (.-length matches) 1)
+ match-str
+ (vec matches))]
+ (cons match-vals
+ (lazy-seq
+ (let [post-idx (+ (.-index matches)
+ (max 1 (.-length match-str)))]
+ (when (<= post-idx (.-length s))
+ (re-seq* re (subs s post-idx)))))))))
+
 (defn re-seq
  "Returns a lazy sequence of successive matches of re in s."
  [re s]
- (let [match-data (re-find re s)
- match-idx (.search s re)
- match-str (if (coll? match-data) (first match-data) match-data)
- post-idx (+ match-idx (max 1 (count match-str)))
- post-match (subs s post-idx)]
- (when match-data (lazy-seq (cons match-data (when (<= post-idx (count s)) (re-seq re post-match)))))))
+ (if (string? s)
+ (re-seq* re s)
+ (throw (js/TypeError. "re-seq must match against a string."))))
 
 (defn re-pattern
  "Returns an instance of RegExp which has compiled the provided string."

src/test/cljs/cljs/core_test.cljs

@@ -957,6 +957,10 @@
  (is (every? #(= :failed (try (re-find #"nomatch" %)
  (catch js/TypeError _ :failed))) not-strings))
  (is (every? #(= :failed (try (re-matches #"nomatch" %)
+ (catch js/TypeError _ :failed))) not-strings))
+ (is (every? #(= :failed (try (re-seq #"." %)
+ (catch js/TypeError _ :failed))) not-strings))
+ (is (every? #(= :failed (try (re-seq #"nomatch" %)
  (catch js/TypeError _ :failed))) not-strings)))))
 
 (deftest test-853