The patch titled
HFS+: refactor ASCII to unicode conversion routine for later reuse
has been added to the -mm tree. Its filename is
hfs-refactor-ascii-to-unicode-conversion-routine.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: HFS+: refactor ASCII to unicode conversion routine for later reuse
From: Duane Griffin <duaneg@xxxxxxxxx>
The HFS+ filesystem is case-insensitive and does automatic unicode
decomposition by default, but does not provide custom dentry operations. This
can lead to multiple dentries being cached for lookups on a filename with
varying case and/or character (de)composition.
These patches add custom dentry hash and comparison operations for
case-sensitive and/or automatically decomposing HFS+ filesystems. Unicode
decomposition and case-folding are performed as required to ensure equivalent
filenames are hashed to the same values and compare as equal.
This patch:
Refactor existing HFS+ ASCII to unicode string conversion routine to split out
character conversion functionality. This will be reused by the custom dentry
hash and comparison routines. This approach avoids unnecessary memory
allocation compared to using the string conversion routine directly in the new
functions.
Signed-off-by: Duane Griffin <duaneg@xxxxxxxxx>
Signed-off-by: Roman Zippel <zippel@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/hfsplus/unicode.c | 105 +++++++++++++++++++++++------------------
1 file changed, 60 insertions(+), 45 deletions(-)
diff -puN fs/hfsplus/unicode.c~hfs-refactor-ascii-to-unicode-conversion-routine fs/hfsplus/unicode.c
--- a/fs/hfsplus/unicode.c~hfs-refactor-ascii-to-unicode-conversion-routine
+++ a/fs/hfsplus/unicode.c
@@ -239,58 +239,73 @@ out:
return res;
}
-int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr, const char *astr, int len)
+/*
+ * Convert one or more ASCII characters into a single unicode character.
+ * Returns the number of ASCII characters corresponding to the unicode char.
+ */
+static inline int asc2unichar(struct super_block *sb, const char *astr, int len,
+ wchar_t *uc)
{
- struct nls_table *nls = HFSPLUS_SB(sb).nls;
- int size, off, decompose;
+ int size = HFSPLUS_SB(sb).nls->char2uni(astr, len, uc);
+ if (size <= 0) {
+ *uc = '?';
+ size = 1;
+ }
+ switch (*uc) {
+ case 0x2400:
+ *uc = 0;
+ break;
+ case ':':
+ *uc = '/';
+ break;
+ }
+ return size;
+}
+
+/* Decomposes a single unicode character. */
+static inline u16 *decompose_unichar(wchar_t uc, int *size)
+{
+ int off;
+
+ off = hfsplus_decompose_table[(uc >> 12) & 0xf];
+ if (off == 0 || off == 0xffff)
+ return NULL;
+
+ off = hfsplus_decompose_table[off + ((uc >> 8) & 0xf)];
+ if (!off)
+ return NULL;
+
+ off = hfsplus_decompose_table[off + ((uc >> 4) & 0xf)];
+ if (!off)
+ return NULL;
+
+ off = hfsplus_decompose_table[off + (uc & 0xf)];
+ *size = off & 3;
+ return hfsplus_decompose_table + (off / 4);
+}
+
+int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr,
+ const char *astr, int len)
+{
+ int size, dsize, decompose;
+ u16 *dstr, outlen = 0;
wchar_t c;
- u16 outlen = 0;
decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
-
while (outlen < HFSPLUS_MAX_STRLEN && len > 0) {
- size = nls->char2uni(astr, len, &c);
- if (size <= 0) {
- c = '?';
- size = 1;
- }
- astr += size;
- len -= size;
- switch (c) {
- case 0x2400:
- c = 0;
- break;
- case ':':
- c = '/';
- break;
- }
- if (c >= 0xc0 && decompose) {
- off = hfsplus_decompose_table[(c >> 12) & 0xf];
- if (!off)
- goto done;
- if (off == 0xffff) {
- goto done;
- }
- off = hfsplus_decompose_table[off + ((c >> 8) & 0xf)];
- if (!off)
- goto done;
- off = hfsplus_decompose_table[off + ((c >> 4) & 0xf)];
- if (!off)
- goto done;
- off = hfsplus_decompose_table[off + (c & 0xf)];
- size = off & 3;
- if (!size)
- goto done;
- off /= 4;
- if (outlen + size > HFSPLUS_MAX_STRLEN)
+ size = asc2unichar(sb, astr, len, &c);
+
+ if (decompose && (dstr = decompose_unichar(c, &dsize))) {
+ if (outlen + dsize > HFSPLUS_MAX_STRLEN)
break;
do {
- ustr->unicode[outlen++] = cpu_to_be16(hfsplus_decompose_table[off++]);
- } while (--size > 0);
- continue;
- }
- done:
- ustr->unicode[outlen++] = cpu_to_be16(c);
+ ustr->unicode[outlen++] = cpu_to_be16(*dstr++);
+ } while (--dsize > 0);
+ } else
+ ustr->unicode[outlen++] = cpu_to_be16(c);
+
+ astr += size;
+ len -= size;
}
ustr->length = cpu_to_be16(outlen);
if (len > 0)
_
Patches currently in -mm which might be from duaneg@xxxxxxxxx are
hfs-refactor-ascii-to-unicode-conversion-routine.patch
hfs-add-custom-dentry-hash-and-comparison-operations.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
