keysym: fix locale dependence in xkb_keysym_from_name()

We currently use strcasecmp, which is locale-dependent. In particular,
one well-known surprise even if restricted just ASCII input is found in
the tr_TR (Turkish) locale, see e.g.
https://msdn.microsoft.com/en-us/library/ms973919.aspx#stringsinnet20_topic5

We have known to avoid locale-dependent functions before, but in this
case, we forgot.

Fix it by implementing our own simple ASCII-only strcasecmp/strncasecmp.
Might have been possible to use strcasecmp_l() with the C locale, but
went the easy route.

Side advantage is that even this non-optimized version is faster than
the optimized libc one (__strcasecmp_l_sse42) since it doesn't need to
do the locale stuff. xkb_keysym_from_name(), which uses strcasecmp
heavily, becomes faster, and so for example Compose file parsing, which
uses xkb_keysym_from_name() heavily, becomes ~20% faster.

Resolves https://github.com/xkbcommon/libxkbcommon/issues/42
Signed-off-by: Ran Benita <ran234@gmail.com>

diff --git a/configure.ac b/configure.ac
index fdab4ab..3484c8c 100644 (file)
--- a/configure.ac
+++ b/configure.ac
@@ -68,12 +68,6 @@ AS_IF([test ! -f "src/xkbcomp/parser.c" -a "x$YACC_INST" = x], [
 ])
 
 # Checks for library functions.
-AC_CHECK_FUNCS([strcasecmp strncasecmp])
-AS_IF([test "x$ac_cv_func_strcasecmp" = xno -o \
-            "x$ac_cv_func_strncasecmp" = xno], [
-    AC_MSG_ERROR([C library does not support strcasecmp/strncasecmp])
-])
-
 AC_CHECK_FUNCS([eaccess euidaccess mmap])
 
 AC_CHECK_FUNCS([secure_getenv __secure_getenv])

diff --git a/src/keysym.c b/src/keysym.c
index db0e973..9e7b4fb 100644 (file)
--- a/src/keysym.c
+++ b/src/keysym.c
@@ -76,7 +76,7 @@ compare_by_name(const void *a, const void *b)
 {
     const char *key = a;
     const struct name_keysym *entry = b;
-    return strcasecmp(key, get_name(entry));
+    return istrcmp(key, get_name(entry));
 }
 
 XKB_EXPORT int
@@ -109,7 +109,7 @@ xkb_keysym_get_name(xkb_keysym_t ks, char *buffer, size_t size)
 /*
  * Find the correct keysym if one case-insensitive match is given.
  *
- * The name_to_keysym table is sorted by strcasecmp(). So bsearch() may return
+ * The name_to_keysym table is sorted by istrcmp(). So bsearch() may return
  * _any_ of all possible case-insensitive duplicates. This function searches the
  * returned entry @entry, all previous and all next entries that match by
  * case-insensitive comparison and returns the exact match to @name. If @icase
@@ -138,7 +138,7 @@ find_sym(const struct name_keysym *entry, const char *name, bool icase)
     for (iter = entry - 1; iter >= name_to_keysym; --iter) {
         if (!icase && strcmp(get_name(iter), name) == 0)
             return iter;
-        if (strcasecmp(get_name(iter), get_name(entry)) != 0)
+        if (istrcmp(get_name(iter), get_name(entry)) != 0)
             break;
         if (icase && xkb_keysym_is_lower(iter->keysym))
             return iter;
@@ -148,7 +148,7 @@ find_sym(const struct name_keysym *entry, const char *name, bool icase)
     for (iter = entry + 1; iter < last; ++iter) {
         if (!icase && strcmp(get_name(iter), name) == 0)
             return iter;
-        if (strcasecmp(get_name(iter), get_name(entry)) != 0)
+        if (istrcmp(get_name(iter), get_name(entry)) != 0)
             break;
         if (icase && xkb_keysym_is_lower(iter->keysym))
             return iter;

diff --git a/src/utils.c b/src/utils.c
index d725bbd..a71b570 100644 (file)
--- a/src/utils.c
+++ b/src/utils.c
@@ -108,3 +108,56 @@ unmap_file(char *str, size_t size)
 }
 
 #endif
+
+// ASCII lower-case map.
+static const unsigned char lower_map[] = {
+    0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
+    21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39,
+    40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58,
+    59, 60, 61, 62, 63, 64, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107,
+    108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122,
+    91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107,
+    108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122,
+    123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137,
+    138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152,
+    153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167,
+    168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182,
+    183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197,
+    198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212,
+    213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227,
+    228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242,
+    243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255
+};
+
+// ASCII tolower (to avoid locale issues).
+char
+to_lower(char c)
+{
+    return (char) lower_map[(unsigned char) c];
+}
+
+// ASCII strcasecmp (to avoid locale issues).
+int
+istrcmp(const char *a, const char *b)
+{
+    for (size_t i = 0; ; i++) {
+        if (to_lower(a[i]) != to_lower(b[i]))
+            return (int) to_lower(a[i]) - (int) to_lower(b[i]);
+        if (!a[i])
+            break;
+    }
+    return 0;
+}
+
+// ASCII strncasecmp (to avoid locale issues).
+int
+istrncmp(const char *a, const char *b, size_t n)
+{
+    for (size_t i = 0; i < n; i++) {
+        if (to_lower(a[i]) != to_lower(b[i]))
+            return (int) to_lower(a[i]) - (int) to_lower(b[i]);
+        if (!a[i])
+            break;
+    }
+    return 0;
+}

diff --git a/src/utils.h b/src/utils.h
index d63d23a..cb98e8e 100644 (file)
--- a/src/utils.h
+++ b/src/utils.h
@@ -29,7 +29,6 @@
 #include <stdbool.h>
 #include <stdio.h>
 #include <string.h>
-#include <strings.h>
 
 #include "darray.h"
 
@@ -44,6 +43,15 @@
     switch (0) { case 0: case (expr): ; } \
 } while (0)
 
+char
+to_lower(char c);
+
+int
+istrcmp(const char *a, const char *b);
+
+int
+istrncmp(const char *a, const char *b, size_t n);
+
 static inline bool
 streq(const char *s1, const char *s2)
 {
@@ -61,13 +69,13 @@ streq_not_null(const char *s1, const char *s2)
 static inline bool
 istreq(const char *s1, const char *s2)
 {
-    return strcasecmp(s1, s2) == 0;
+    return istrcmp(s1, s2) == 0;
 }
 
 static inline bool
 istreq_prefix(const char *s1, const char *s2)
 {
-    return strncasecmp(s1, s2, strlen(s1)) == 0;
+    return istrncmp(s1, s2, strlen(s1)) == 0;
 }
 
 static inline char *

diff --git a/test/keysym.c b/test/keysym.c
index 439622c..4414523 100644 (file)
--- a/test/keysym.c
+++ b/test/keysym.c
@@ -20,6 +20,7 @@
  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
  * DEALINGS IN THE SOFTWARE.
  */
+#include <locale.h>
 
 #include "test.h"
 #include "keysym.h" /* For unexported is_lower/upper/keypad() */
@@ -81,6 +82,25 @@ test_utf8(xkb_keysym_t keysym, const char *expected)
     return streq(s, expected);
 }
 
+static void
+test_github_issue_42(void)
+{
+    // Verify we are not dependent on locale, Turkish-i problem in particular.
+    if (setlocale(LC_CTYPE, "tr_TR.UTF-8") == NULL) {
+        // The locale is not available, probably; skip.
+        return;
+    }
+
+    assert(test_string("i", XKB_KEY_i));
+    assert(test_string("I", XKB_KEY_I));
+    assert(test_casestring("i", XKB_KEY_i));
+    assert(test_casestring("I", XKB_KEY_i));
+    assert(xkb_keysym_to_upper(XKB_KEY_i) == XKB_KEY_I);
+    assert(xkb_keysym_to_lower(XKB_KEY_I) == XKB_KEY_i);
+
+    setlocale(LC_CTYPE, "C");
+}
+
 int
 main(void)
 {
@@ -196,5 +216,7 @@ main(void)
     assert(xkb_keysym_to_upper(XKB_KEY_eacute) == XKB_KEY_Eacute);
     assert(xkb_keysym_to_lower(XKB_KEY_Eacute) == XKB_KEY_eacute);
 
+    test_github_issue_42();
+
     return 0;
 }