Fix [:upper:] and [:lower:] for Unicode characters (bug#11309)

* src/regex-emacs.c (execute_charset): Add canon_table argument to
allow expression of a correct predicate for [:upper:] and [:lower:].
(mutually_exclusive_p, re_match_2_internal): Pass extra argument.
* test/src/regex-emacs-tests.el (regexp-case-fold, regexp-eszett):
New tests.  Parts of regexp-eszett still fail and are commented out.

1 files changed, 57 insertions, 0 deletions

diff --git a/test/src/regex-emacs-tests.el b/test/src/regex-emacs-tests.el
index f9372e37b11..576630aa5af 100644
--- a/test/src/regex-emacs-tests.el
+++ b/test/src/regex-emacs-tests.el
@@ -803,4 +803,61 @@ This evaluates the TESTS test cases from glibc."
   (should-not (string-match "å" "\xe5"))
   (should-not (string-match "[å]" "\xe5")))
 
+(ert-deftest regexp-case-fold ()
+  "Test case-sensitive and case-insensitive matching."
+  (let ((case-fold-search nil))
+    (should (equal (string-match "aB" "ABaB") 2))
+    (should (equal (string-match "åÄ" "ÅäåäÅÄåÄ") 6))
+    (should (equal (string-match "λΛ" "lΛλλΛ") 3))
+    (should (equal (string-match "шШ" "zШшшШ") 3))
+    (should (equal (string-match "[[:alpha:]]+" ".3aBåÄßλΛшШ中﷽") 2))
+    (should (equal (match-end 0) 12))
+    (should (equal (string-match "[[:alnum:]]+" ".3aBåÄßλΛшШ中﷽") 1))
+    (should (equal (match-end 0) 12))
+    (should (equal (string-match "[[:upper:]]+" ".3aåλшBÄΛШ中﷽") 6))
+    (should (equal (match-end 0) 10))
+    (should (equal (string-match "[[:lower:]]+" ".3BÄΛШaåλш中﷽") 6))
+    (should (equal (match-end 0) 10)))
+  (let ((case-fold-search t))
+    (should (equal (string-match "aB" "ABaB") 0))
+    (should (equal (string-match "åÄ" "ÅäåäÅÄåÄ") 0))
+    (should (equal (string-match "λΛ" "lΛλλΛ") 1))
+    (should (equal (string-match "шШ" "zШшшШ") 1))
+    (should (equal (string-match "[[:alpha:]]+" ".3aBåÄßλΛшШ中﷽") 2))
+    (should (equal (match-end 0) 12))
+    (should (equal (string-match "[[:alnum:]]+" ".3aBåÄßλΛшШ中﷽") 1))
+    (should (equal (match-end 0) 12))
+    (should (equal (string-match "[[:upper:]]+" ".3aåλшBÄΛШ中﷽") 2))
+    (should (equal (match-end 0) 10))
+    (should (equal (string-match "[[:lower:]]+" ".3BÄΛШaåλш中﷽") 2))
+    (should (equal (match-end 0) 10))))
+
+(ert-deftest regexp-eszett ()
+  "Test matching of ß and ẞ."
+  ;; ß is a lower-case letter (Ll); ẞ is an upper-case letter (Lu).
+  (let ((case-fold-search nil))
+    (should (equal (string-match "ß" "ß") 0))
+    (should (equal (string-match "ß" "ẞ") nil))
+    (should (equal (string-match "ẞ" "ß") nil))
+    (should (equal (string-match "ẞ" "ẞ") 0))
+    (should (equal (string-match "[[:alpha:]]" "ß") 0))
+    ;; bug#11309
+    ;;(should (equal (string-match "[[:lower:]]" "ß") 0))
+    ;;(should (equal (string-match "[[:upper:]]" "ß") nil))
+    (should (equal (string-match "[[:alpha:]]" "ẞ") 0))
+    (should (equal (string-match "[[:lower:]]" "ẞ") nil))
+    (should (equal (string-match "[[:upper:]]" "ẞ") 0)))
+  (let ((case-fold-search t))
+    (should (equal (string-match "ß" "ß") 0))
+    (should (equal (string-match "ß" "ẞ") 0))
+    (should (equal (string-match "ẞ" "ß") 0))
+    (should (equal (string-match "ẞ" "ẞ") 0))
+    (should (equal (string-match "[[:alpha:]]" "ß") 0))
+    ;; bug#11309
+    ;;(should (equal (string-match "[[:lower:]]" "ß") 0))
+    ;;(should (equal (string-match "[[:upper:]]" "ß") 0))
+    (should (equal (string-match "[[:alpha:]]" "ẞ") 0))
+    (should (equal (string-match "[[:lower:]]" "ẞ") 0))
+    (should (equal (string-match "[[:upper:]]" "ẞ") 0))))
+
 ;;; regex-emacs-tests.el ends here