summary refs log tree commit diff
path: root/utf8.c
diff options
context:
space:
mode:
authorJeff King <peff@peff.net>2014-12-23 03:45:36 -0500
committerJunio C Hamano <gitster@pobox.com>2014-12-29 12:06:27 -0800
commit6aaf956b08cfab2dcaa1a1afe4192390d0ef14fd (patch)
treec7922e942a9ba4ee433446465d6ca418881c1b82 /utf8.c
parentd08c13b947335cc48ecc1a8453d97b7147c2d6d6 (diff)
is_hfs_dotgit: loosen over-eager match of \u{..47}
Our is_hfs_dotgit function relies on the hackily-implemented
next_hfs_char to give us the next character that an HFS+
filename comparison would look at. It's hacky because it
doesn't implement the full case-folding table of HFS+; it
gives us just enough to see if the path matches ".git".

At the end of next_hfs_char, we use tolower() to convert our
32-bit code point to lowercase. Our tolower() implementation
only takes an 8-bit char, though; it throws away the upper
24 bits. This means we can't have any false negatives for
is_hfs_dotgit. We only care about matching 7-bit ASCII
characters in ".git", and we will correctly process 'G' or
'g'.

However, we _can_ have false positives. Because we throw
away the upper bits, code point \u{0147} (for example) will
look like 'G' and get downcased to 'g'. It's not known
whether a sequence of code points whose truncation ends up
as ".git" is meaningful in any language, but it does not
hurt to be more accurate here. We can just pass out the full
32-bit code point, and compare it manually to the upper and
lowercase characters we care about.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'utf8.c')
-rw-r--r--utf8.c32
1 files changed, 20 insertions, 12 deletions
diff --git a/utf8.c b/utf8.c
index 2c6442cc11..9c9fa3a757 100644
--- a/utf8.c
+++ b/utf8.c
@@ -630,8 +630,8 @@ int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding)
 }
 
 /*
- * Pick the next char from the stream, folding as an HFS+ filename comparison
- * would. Note that this is _not_ complete by any means. It's just enough
+ * Pick the next char from the stream, ignoring codepoints an HFS+ would.
+ * Note that this is _not_ complete by any means. It's just enough
  * to make is_hfs_dotgit() work, and should not be used otherwise.
  */
 static ucs_char_t next_hfs_char(const char **in)
@@ -668,12 +668,7 @@ static ucs_char_t next_hfs_char(const char **in)
 			continue;
 		}
 
-		/*
-		 * there's a great deal of other case-folding that occurs,
-		 * but this is enough to catch anything that will convert
-		 * to ".git"
-		 */
-		return tolower(out);
+		return out;
 	}
 }
 
@@ -681,10 +676,23 @@ int is_hfs_dotgit(const char *path)
 {
 	ucs_char_t c;
 
-	if (next_hfs_char(&path) != '.' ||
-	    next_hfs_char(&path) != 'g' ||
-	    next_hfs_char(&path) != 'i' ||
-	    next_hfs_char(&path) != 't')
+	c = next_hfs_char(&path);
+	if (c != '.')
+		return 0;
+	c = next_hfs_char(&path);
+
+	/*
+	 * there's a great deal of other case-folding that occurs
+	 * in HFS+, but this is enough to catch anything that will
+	 * convert to ".git"
+	 */
+	if (c != 'g' && c != 'G')
+		return 0;
+	c = next_hfs_char(&path);
+	if (c != 'i' && c != 'I')
+		return 0;
+	c = next_hfs_char(&path);
+	if (c != 't' && c != 'T')
 		return 0;
 	c = next_hfs_char(&path);
 	if (c && !is_dir_sep(c))