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.

diff --git a/src/regex-emacs.c b/src/regex-emacs.c
index 971a5f63749d4cd071de9814395481ef78bdbbef..904ca0c7b955c7c0592f2d959e367233b4ddc251 100644 (file)
--- a/src/regex-emacs.c
+++ b/src/regex-emacs.c
@@ -3575,9 +3575,11 @@ skip_noops (re_char *p, re_char *pend)
    opcode.  When the function finishes, *PP will be advanced past that opcode.
    C is character to test (possibly after translations) and CORIG is original
    character (i.e. without any translations).  UNIBYTE denotes whether c is
-   unibyte or multibyte character. */
+   unibyte or multibyte character.
+   CANON_TABLE is the canonicalisation table for case folding or Qnil.  */
 static bool
-execute_charset (re_char **pp, int c, int corig, bool unibyte)
+execute_charset (re_char **pp, int c, int corig, bool unibyte,
+                 Lisp_Object canon_table)
 {
   eassume (0 <= c && 0 <= corig);
   re_char *p = *pp, *rtp = NULL;
@@ -3617,11 +3619,9 @@ execute_charset (re_char **pp, int c, int corig, bool unibyte)
           (class_bits & BIT_BLANK && ISBLANK (c)) ||
          (class_bits & BIT_WORD  && ISWORD  (c)) ||
          ((class_bits & BIT_UPPER) &&
-          (ISUPPER (c) || (corig != c &&
-                           c == downcase (corig) && ISLOWER (c)))) ||
+          (ISUPPER (corig) || (!NILP (canon_table) && ISLOWER (corig)))) ||
          ((class_bits & BIT_LOWER) &&
-          (ISLOWER (c) || (corig != c &&
-                           c == upcase (corig) && ISUPPER(c)))) ||
+          (ISLOWER (corig) || (!NILP (canon_table) && ISUPPER (corig)))) ||
          (class_bits & BIT_PUNCT && ISPUNCT (c)) ||
          (class_bits & BIT_GRAPH && ISGRAPH (c)) ||
          (class_bits & BIT_PRINT && ISPRINT (c)))
@@ -3696,7 +3696,8 @@ mutually_exclusive_p (struct re_pattern_buffer *bufp, re_char *p1,
        else if ((re_opcode_t) *p1 == charset
                 || (re_opcode_t) *p1 == charset_not)
          {
-           if (!execute_charset (&p1, c, c, !multibyte || ASCII_CHAR_P (c)))
+           if (!execute_charset (&p1, c, c, !multibyte || ASCII_CHAR_P (c),
+                                  Qnil))
              {
                DEBUG_PRINT ("   No match => fast loop.\n");
                return true;
@@ -4367,7 +4368,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp,
              }
 
            p -= 1;
-           if (!execute_charset (&p, c, corig, unibyte_char))
+           if (!execute_charset (&p, c, corig, unibyte_char, translate))
              goto fail;
 
            d += len;

diff --git a/test/src/regex-emacs-tests.el b/test/src/regex-emacs-tests.el
index f9372e37b110cc75d771019cf59a374ed2b46924..576630aa5afbbfa636c1b88c3d41982ebf512502 100644 (file)
--- 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