summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMattias Engdegård <mattiase@acm.org>2020-12-09 13:27:16 +0100
committerMattias Engdegård <mattiase@acm.org>2020-12-09 15:29:48 +0100
commitbeebd2a85eeab5b977ca2de8ad32784f9d8bdd51 (patch)
tree2abf190d7e51d435c05c771b67316e4e8f86c3af
parent445ab5cce95aee4cd5fee8ef67c2ee24c1c8850a (diff)
downloademacs-beebd2a85eeab5b977ca2de8ad32784f9d8bdd51.tar.gz
Recognise ß properly as a lower-case letter (bug#11309)
ß was incorrectly treated as a caseless character and thus not matched by the regexp [[:lower:]] (or, in case-folding mode, [[:upper:]]). The reason is that the upcase table maps it to itself, which can be remedied by mapping it to ẞ (U+7838) instead. Doing so does not affect upcasing since the special-uppercase property maps it to SS. * lisp/international/characters.el (tbl): Map ß to ẞ in the upcase table. * test/src/regex-emacs-tests.el (regexp-eszett): Uncomment previously failing tests. Add checks to make sure that case transformations remain valid.
-rw-r--r--lisp/international/characters.el9
-rw-r--r--test/src/regex-emacs-tests.el15
2 files changed, 19 insertions, 5 deletions
diff --git a/lisp/international/characters.el b/lisp/international/characters.el
index 0b6920cf180..5f610ddf670 100644
--- a/lisp/international/characters.el
+++ b/lisp/international/characters.el
@@ -759,7 +759,14 @@ with L, LRE, or LRO Unicode bidi character type.")
(funcall map-unicode-property 'uppercase
(lambda (lc uc) (aset up lc uc) (aset up uc uc)))
(funcall map-unicode-property 'lowercase
- (lambda (uc lc) (aset down uc lc) (aset down lc lc))))))
+ (lambda (uc lc) (aset down uc lc) (aset down lc lc)))
+
+ ;; Override the Unicode uppercase property for ß, since we are
+ ;; using our case tables for determining the case of a
+ ;; character (see uppercasep and lowercasep in buffer.h).
+ ;; The special-uppercase property of ß ensures that it is
+ ;; still upcased to SS per the usual convention.
+ (aset up ?ß ?ẞ))))
;; Clear out the extra slots so that they will be recomputed from the main
;; (downcase) table and upcase table. Since we’re side-stepping the usual
diff --git a/test/src/regex-emacs-tests.el b/test/src/regex-emacs-tests.el
index 576630aa5af..34d4067db47 100644
--- a/test/src/regex-emacs-tests.el
+++ b/test/src/regex-emacs-tests.el
@@ -834,6 +834,13 @@ This evaluates the TESTS test cases from glibc."
(ert-deftest regexp-eszett ()
"Test matching of ß and ẞ."
+ ;; Sanity checks.
+ (should (equal (upcase "ß") "SS"))
+ (should (equal (downcase "ß") "ß"))
+ (should (equal (capitalize "ß") "Ss")) ; undeutsch...
+ (should (equal (upcase "ẞ") "ẞ"))
+ (should (equal (downcase "ẞ") "ß"))
+ (should (equal (capitalize "ẞ") "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))
@@ -842,8 +849,8 @@ This evaluates the TESTS test cases from glibc."
(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 "[[: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)))
@@ -854,8 +861,8 @@ This evaluates the TESTS test cases from glibc."
(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 "[[: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))))