aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--ChangeLog6
-rw-r--r--string.c26
-rw-r--r--test/ruby/test_m17n.rb6
3 files changed, 24 insertions, 14 deletions
diff --git a/ChangeLog b/ChangeLog
index 4fc37a9431..0abf8377e1 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+Tue Apr 23 11:58:46 2013 Nobuyoshi Nakada <nobu@ruby-lang.org>
+
+ * string.c (rb_str_scrub): fix for UTF-32. strlen() on strings
+ contain NUL returns wrong result, use sizeof operator instead.
+ [ruby-dev:45975] [Feature #6752]
+
Tue Apr 23 10:26:50 2013 Akinori MUSHA <knu@iDaemons.org>
* test/ruby/test_module.rb
diff --git a/string.c b/string.c
index 7bb4d5bd90..22e98f2569 100644
--- a/string.c
+++ b/string.c
@@ -7805,6 +7805,11 @@ rb_str_scrub(int argc, VALUE *argv, VALUE str)
return rb_str_dup(str);
}
+#define DEFAULT_REPLACE_CHAR(str) do { \
+ static const char replace[sizeof(str)-1] = str; \
+ rep = replace; replen = (int)sizeof(replace); \
+ } while (0)
+
if (rb_enc_asciicompat(enc)) {
const char *p = RSTRING_PTR(str);
const char *e = RSTRING_END(str);
@@ -7824,13 +7829,11 @@ rb_str_scrub(int argc, VALUE *argv, VALUE str)
rep7bit_p = (ENC_CODERANGE(repl) == ENC_CODERANGE_7BIT);
}
else if (enc == rb_utf8_encoding()) {
- rep = "\xEF\xBF\xBD";
- replen = strlen(rep);
+ DEFAULT_REPLACE_CHAR("\xEF\xBF\xBD");
rep7bit_p = FALSE;
}
else {
- rep = "?";
- replen = strlen(rep);
+ DEFAULT_REPLACE_CHAR("?");
rep7bit_p = TRUE;
}
cr = ENC_CODERANGE_7BIT;
@@ -7938,24 +7941,19 @@ rb_str_scrub(int argc, VALUE *argv, VALUE str)
replen = RSTRING_LEN(repl);
}
else if (enc == utf16be) {
- rep = "\xFF\xFD";
- replen = strlen(rep);
+ DEFAULT_REPLACE_CHAR("\xFF\xFD");
}
else if (enc == utf16le) {
- rep = "\xFD\xFF";
- replen = strlen(rep);
+ DEFAULT_REPLACE_CHAR("\xFD\xFF");
}
else if (enc == utf32be) {
- rep = "\x00\x00\xFF\xFD";
- replen = strlen(rep);
+ DEFAULT_REPLACE_CHAR("\x00\x00\xFF\xFD");
}
else if (enc == utf32le) {
- rep = "\xFD\xFF\x00\x00";
- replen = strlen(rep);
+ DEFAULT_REPLACE_CHAR("\xFD\xFF\x00\x00");
}
else {
- rep = "?";
- replen = strlen(rep);
+ DEFAULT_REPLACE_CHAR("?");
}
while (p < e) {
diff --git a/test/ruby/test_m17n.rb b/test/ruby/test_m17n.rb
index 60834bb9c6..9d92fbc6a9 100644
--- a/test/ruby/test_m17n.rb
+++ b/test/ruby/test_m17n.rb
@@ -1522,5 +1522,11 @@ class TestM17N < Test::Unit::TestCase
assert_equal("\uFFFD\u3042".encode("UTF-16LE"),
"\x00\xD8\x42\x30".force_encoding(Encoding::UTF_16LE).
scrub)
+ assert_equal("\uFFFD".encode("UTF-32BE"),
+ "\xff".force_encoding(Encoding::UTF_32BE).
+ scrub)
+ assert_equal("\uFFFD".encode("UTF-32LE"),
+ "\xff".force_encoding(Encoding::UTF_32LE).
+ scrub)
end
end