* file.c (rb_str_normalize_ospath):

  HFS Plus (Mac OS Extended) uses a variant of Normal Form D in which
  U+2000 through U+2FFF, U+F900 through U+FAFF, and U+2F800 through
  U+2FAFF are not decomposed (this avoids problems with round trip
  conversions from old Mac text encodings).
  http://developer.apple.com/library/mac/qa/qa1173/_index.html
  Therefore fix r42457 to exclude the range.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@42498 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 42 insertions, 1 deletions

diff --git a/file.c b/file.c
index 3923ddeec7..347b7e6d0e 100644
--- a/file.c
+++ b/file.c
@@ -245,7 +245,7 @@ rb_str_encode_ospath(VALUE path)
 
 #ifdef __APPLE__
 VALUE
-rb_str_normalize_ospath(const char *ptr, long len)
+rb_str_normalize_ospath0(const char *ptr, long len)
 {
     VALUE str;
     CFIndex buflen = 0;
@@ -267,6 +267,47 @@ rb_str_normalize_ospath(const char *ptr, long len)
     CFRelease(s);
     return str;
 }
+
+VALUE
+rb_str_normalize_ospath(const char *ptr, long len)
+{
+    const char *p = ptr;
+    const char *e = ptr + len;
+    const char *p1 = p;
+    VALUE str = rb_str_buf_new(len);
+    rb_encoding *enc = rb_utf8_encoding();
+    rb_enc_associate(str, enc);
+
+    while (p < e) {
+	int l;
+	int r = rb_enc_precise_mbclen(p, e, enc);
+	if (!MBCLEN_CHARFOUND_P(r)) {
+	    /* invalid byte shall not happen but */
+	    rb_str_append(str, rb_str_normalize_ospath0(p1, p-p1));
+	    rb_str_cat2(str, "\xEF\xBF\xBD");
+	    p += 1;
+	}
+	l = MBCLEN_CHARFOUND_LEN(r);
+	int c = rb_enc_mbc_to_codepoint(p, e, enc);
+	if ((0x2000 <= c && c <= 0x2FFF) || (0xF900 <= c && c <= 0xFAFF) ||
+		(0x2F800 <= c && c <= 0x2FAFF)) {
+	    if (p - p1 > 0) {
+		rb_str_append(str, rb_str_normalize_ospath0(p1, p-p1));
+	    }
+	    rb_str_cat(str, p, l);
+	    p += l;
+	    p1 = p;
+	}
+	else {
+	    p += l;
+	}
+    }
+    if (p - p1 > 0) {
+	rb_str_append(str, rb_str_normalize_ospath0(p1, p-p1));
+    }
+
+    return str;
+}
 #endif
 
 static long