git/utf8.c

825 lines
20 KiB
C
Raw Normal View History

#include "git-compat-util.h"
#include "strbuf.h"
#include "utf8.h"
/* This code is originally from https://www.cl.cam.ac.uk/~mgk25/ucs/ */
Support working-tree-encoding "UTF-16LE-BOM" Users who want UTF-16 files in the working tree set the .gitattributes like this: test.txt working-tree-encoding=UTF-16 The unicode standard itself defines 3 allowed ways how to encode UTF-16. The following 3 versions convert all back to 'g' 'i' 't' in UTF-8: a) UTF-16, without BOM, big endian: $ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t b) UTF-16, with BOM, little endian: $ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t c) UTF-16, with BOM, big endian: $ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the working tree. After a checkout, the resulting file has a BOM and is encoded in "UTF-16", in the version (c) above. This is what iconv generates, more details follow below. iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE: d) UTF-16 $ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c 0000000 376 377 \0 g \0 i \0 t e) UTF-16LE $ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c 0000000 g \0 i \0 t \0 f) UTF-16BE $ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c 0000000 \0 g \0 i \0 t There is no way to generate version (b) from above in a Git working tree, but that is what some applications need. (All fully unicode aware applications should be able to read all 3 variants, but in practise we are not there yet). When producing UTF-16 as an output, iconv generates the big endian version with a BOM. (big endian is probably chosen for historical reasons). iconv can produce UTF-16 files with little endianess by using "UTF-16LE" as encoding, and that file does not have a BOM. Not all users (especially under Windows) are happy with this. Some tools are not fully unicode aware and can only handle version (b). Today there is no way to produce version (b) with iconv (or libiconv). Looking into the history of iconv, it seems as if version (c) will be used in all future iconv versions (for compatibility reasons). Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM". libiconv can not handle the encoding, so Git pick it up, handles the BOM and uses libiconv to convert the rest of the stream. (UTF-16BE-BOM is added for consistency) Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-30 15:01:52 +00:00
static const char utf16_be_bom[] = {'\xFE', '\xFF'};
static const char utf16_le_bom[] = {'\xFF', '\xFE'};
static const char utf32_be_bom[] = {'\0', '\0', '\xFE', '\xFF'};
static const char utf32_le_bom[] = {'\xFF', '\xFE', '\0', '\0'};
struct interval {
ucs_char_t first;
ucs_char_t last;
};
size_t display_mode_esc_sequence_len(const char *s)
{
const char *p = s;
if (*p++ != '\033')
return 0;
if (*p++ != '[')
return 0;
while (isdigit(*p) || *p == ';')
p++;
if (*p++ != 'm')
return 0;
return p - s;
}
/* auxiliary function for binary search in interval table */
static int bisearch(ucs_char_t ucs, const struct interval *table, int max)
{
int min = 0;
int mid;
if (ucs < table[0].first || ucs > table[max].last)
return 0;
while (max >= min) {
mid = min + (max - min) / 2;
if (ucs > table[mid].last)
min = mid + 1;
else if (ucs < table[mid].first)
max = mid - 1;
else
return 1;
}
return 0;
}
/* The following two functions define the column width of an ISO 10646
* character as follows:
*
* - The null character (U+0000) has a column width of 0.
*
* - Other C0/C1 control characters and DEL will lead to a return
* value of -1.
*
* - Non-spacing and enclosing combining characters (general
* category code Mn or Me in the Unicode database) have a
* column width of 0.
*
* - SOFT HYPHEN (U+00AD) has a column width of 1.
*
* - Other format characters (general category code Cf in the Unicode
* database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
*
* - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
* have a column width of 0.
*
* - Spacing characters in the East Asian Wide (W) or East Asian
* Full-width (F) category as defined in Unicode Technical
* Report #11 have a column width of 2.
*
* - All remaining characters (including all printable
* ISO 8859-1 and WGL4 characters, Unicode control characters,
* etc.) have a column width of 1.
*
* This implementation assumes that ucs_char_t characters are encoded
* in ISO 10646.
*/
static int git_wcwidth(ucs_char_t ch)
{
/*
* Sorted list of non-overlapping intervals of non-spacing characters,
*/
#include "unicode-width.h"
/* test for 8-bit control characters */
if (ch == 0)
return 0;
if (ch < 32 || (ch >= 0x7f && ch < 0xa0))
return -1;
/* binary search in table of non-spacing characters */
if (bisearch(ch, zero_width, ARRAY_SIZE(zero_width) - 1))
return 0;
/* binary search in table of double width characters */
if (bisearch(ch, double_width, ARRAY_SIZE(double_width) - 1))
return 2;
return 1;
}
/*
* Pick one ucs character starting from the location *start points at,
* and return it, while updating the *start pointer to point at the
* end of that character. When remainder_p is not NULL, the location
* holds the number of bytes remaining in the string that we are allowed
* to pick from. Otherwise we are allowed to pick up to the NUL that
* would eventually appear in the string. *remainder_p is also reduced
* by the number of bytes we have consumed.
*
* If the string was not a valid UTF-8, *start pointer is set to NULL
* and the return value is undefined.
*/
static ucs_char_t pick_one_utf8_char(const char **start, size_t *remainder_p)
{
unsigned char *s = (unsigned char *)*start;
ucs_char_t ch;
size_t remainder, incr;
/*
* A caller that assumes NUL terminated text can choose
* not to bother with the remainder length. We will
* stop at the first NUL.
*/
remainder = (remainder_p ? *remainder_p : 999);
if (remainder < 1) {
goto invalid;
} else if (*s < 0x80) {
/* 0xxxxxxx */
ch = *s;
incr = 1;
} else if ((s[0] & 0xe0) == 0xc0) {
/* 110XXXXx 10xxxxxx */
if (remainder < 2 ||
(s[1] & 0xc0) != 0x80 ||
(s[0] & 0xfe) == 0xc0)
goto invalid;
ch = ((s[0] & 0x1f) << 6) | (s[1] & 0x3f);
incr = 2;
} else if ((s[0] & 0xf0) == 0xe0) {
/* 1110XXXX 10Xxxxxx 10xxxxxx */
if (remainder < 3 ||
(s[1] & 0xc0) != 0x80 ||
(s[2] & 0xc0) != 0x80 ||
/* overlong? */
(s[0] == 0xe0 && (s[1] & 0xe0) == 0x80) ||
/* surrogate? */
(s[0] == 0xed && (s[1] & 0xe0) == 0xa0) ||
/* U+FFFE or U+FFFF? */
(s[0] == 0xef && s[1] == 0xbf &&
(s[2] & 0xfe) == 0xbe))
goto invalid;
ch = ((s[0] & 0x0f) << 12) |
((s[1] & 0x3f) << 6) | (s[2] & 0x3f);
incr = 3;
} else if ((s[0] & 0xf8) == 0xf0) {
/* 11110XXX 10XXxxxx 10xxxxxx 10xxxxxx */
if (remainder < 4 ||
(s[1] & 0xc0) != 0x80 ||
(s[2] & 0xc0) != 0x80 ||
(s[3] & 0xc0) != 0x80 ||
/* overlong? */
(s[0] == 0xf0 && (s[1] & 0xf0) == 0x80) ||
/* > U+10FFFF? */
(s[0] == 0xf4 && s[1] > 0x8f) || s[0] > 0xf4)
goto invalid;
ch = ((s[0] & 0x07) << 18) | ((s[1] & 0x3f) << 12) |
((s[2] & 0x3f) << 6) | (s[3] & 0x3f);
incr = 4;
} else {
invalid:
*start = NULL;
return 0;
}
*start += incr;
if (remainder_p)
*remainder_p = remainder - incr;
return ch;
}
/*
* This function returns the number of columns occupied by the character
* pointed to by the variable start. The pointer is updated to point at
* the next character. When remainder_p is not NULL, it points at the
* location that stores the number of remaining bytes we can use to pick
* a character (see pick_one_utf8_char() above).
*/
int utf8_width(const char **start, size_t *remainder_p)
{
ucs_char_t ch = pick_one_utf8_char(start, remainder_p);
if (!*start)
return 0;
return git_wcwidth(ch);
}
/*
* Returns the total number of columns required by a null-terminated
* string, assuming that the string is utf8. Returns strlen() instead
* if the string does not look like a valid utf8 string.
*/
int utf8_strnwidth(const char *string, size_t len, int skip_ansi)
{
const char *orig = string;
utf8: fix overflow when returning string width The return type of both `utf8_strwidth()` and `utf8_strnwidth()` is `int`, but we operate on string lengths which are typically of type `size_t`. This means that when the string is longer than `INT_MAX`, we will overflow and thus return a negative result. This can lead to an out-of-bounds write with `--pretty=format:%<1)%B` and a commit message that is 2^31+1 bytes long: ================================================================= ==26009==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000001168 at pc 0x7f95c4e5f427 bp 0x7ffd8541c900 sp 0x7ffd8541c0a8 WRITE of size 2147483649 at 0x603000001168 thread T0 #0 0x7f95c4e5f426 in __interceptor_memcpy /usr/src/debug/gcc/libsanitizer/sanitizer_common/sanitizer_common_interceptors.inc:827 #1 0x5612bbb1068c in format_and_pad_commit pretty.c:1763 #2 0x5612bbb1087a in format_commit_item pretty.c:1801 #3 0x5612bbc33bab in strbuf_expand strbuf.c:429 #4 0x5612bbb110e7 in repo_format_commit_message pretty.c:1869 #5 0x5612bbb12d96 in pretty_print_commit pretty.c:2161 #6 0x5612bba0a4d5 in show_log log-tree.c:781 #7 0x5612bba0d6c7 in log_tree_commit log-tree.c:1117 #8 0x5612bb691ed5 in cmd_log_walk_no_free builtin/log.c:508 #9 0x5612bb69235b in cmd_log_walk builtin/log.c:549 #10 0x5612bb6951a2 in cmd_log builtin/log.c:883 #11 0x5612bb56c993 in run_builtin git.c:466 #12 0x5612bb56d397 in handle_builtin git.c:721 #13 0x5612bb56db07 in run_argv git.c:788 #14 0x5612bb56e8a7 in cmd_main git.c:923 #15 0x5612bb803682 in main common-main.c:57 #16 0x7f95c4c3c28f (/usr/lib/libc.so.6+0x2328f) #17 0x7f95c4c3c349 in __libc_start_main (/usr/lib/libc.so.6+0x23349) #18 0x5612bb5680e4 in _start ../sysdeps/x86_64/start.S:115 0x603000001168 is located 0 bytes to the right of 24-byte region [0x603000001150,0x603000001168) allocated by thread T0 here: #0 0x7f95c4ebe7ea in __interceptor_realloc /usr/src/debug/gcc/libsanitizer/asan/asan_malloc_linux.cpp:85 #1 0x5612bbcdd556 in xrealloc wrapper.c:136 #2 0x5612bbc310a3 in strbuf_grow strbuf.c:99 #3 0x5612bbc32acd in strbuf_add strbuf.c:298 #4 0x5612bbc33aec in strbuf_expand strbuf.c:418 #5 0x5612bbb110e7 in repo_format_commit_message pretty.c:1869 #6 0x5612bbb12d96 in pretty_print_commit pretty.c:2161 #7 0x5612bba0a4d5 in show_log log-tree.c:781 #8 0x5612bba0d6c7 in log_tree_commit log-tree.c:1117 #9 0x5612bb691ed5 in cmd_log_walk_no_free builtin/log.c:508 #10 0x5612bb69235b in cmd_log_walk builtin/log.c:549 #11 0x5612bb6951a2 in cmd_log builtin/log.c:883 #12 0x5612bb56c993 in run_builtin git.c:466 #13 0x5612bb56d397 in handle_builtin git.c:721 #14 0x5612bb56db07 in run_argv git.c:788 #15 0x5612bb56e8a7 in cmd_main git.c:923 #16 0x5612bb803682 in main common-main.c:57 #17 0x7f95c4c3c28f (/usr/lib/libc.so.6+0x2328f) SUMMARY: AddressSanitizer: heap-buffer-overflow /usr/src/debug/gcc/libsanitizer/sanitizer_common/sanitizer_common_interceptors.inc:827 in __interceptor_memcpy Shadow bytes around the buggy address: 0x0c067fff81d0: fd fd fd fa fa fa fd fd fd fa fa fa fd fd fd fa 0x0c067fff81e0: fa fa fd fd fd fd fa fa fd fd fd fd fa fa fd fd 0x0c067fff81f0: fd fa fa fa fd fd fd fa fa fa fd fd fd fa fa fa 0x0c067fff8200: fd fd fd fa fa fa fd fd fd fd fa fa 00 00 00 fa 0x0c067fff8210: fa fa fd fd fd fa fa fa fd fd fd fa fa fa fd fd =>0x0c067fff8220: fd fa fa fa fd fd fd fa fa fa 00 00 00[fa]fa fa 0x0c067fff8230: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8240: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8250: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8260: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8270: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa Shadow byte legend (one shadow byte represents 8 application bytes): Addressable: 00 Partially addressable: 01 02 03 04 05 06 07 Heap left redzone: fa Freed heap region: fd Stack left redzone: f1 Stack mid redzone: f2 Stack right redzone: f3 Stack after return: f5 Stack use after scope: f8 Global redzone: f9 Global init order: f6 Poisoned by user: f7 Container overflow: fc Array cookie: ac Intra object redzone: bb ASan internal: fe Left alloca redzone: ca Right alloca redzone: cb ==26009==ABORTING Now the proper fix for this would be to convert both functions to return an `size_t` instead of an `int`. But given that this commit may be part of a security release, let's instead do the minimal viable fix and die in case we see an overflow. Add a test that would have previously caused us to crash. Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-12-01 14:47:04 +00:00
size_t width = 0;
while (string && string < orig + len) {
utf8: fix overflow when returning string width The return type of both `utf8_strwidth()` and `utf8_strnwidth()` is `int`, but we operate on string lengths which are typically of type `size_t`. This means that when the string is longer than `INT_MAX`, we will overflow and thus return a negative result. This can lead to an out-of-bounds write with `--pretty=format:%<1)%B` and a commit message that is 2^31+1 bytes long: ================================================================= ==26009==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000001168 at pc 0x7f95c4e5f427 bp 0x7ffd8541c900 sp 0x7ffd8541c0a8 WRITE of size 2147483649 at 0x603000001168 thread T0 #0 0x7f95c4e5f426 in __interceptor_memcpy /usr/src/debug/gcc/libsanitizer/sanitizer_common/sanitizer_common_interceptors.inc:827 #1 0x5612bbb1068c in format_and_pad_commit pretty.c:1763 #2 0x5612bbb1087a in format_commit_item pretty.c:1801 #3 0x5612bbc33bab in strbuf_expand strbuf.c:429 #4 0x5612bbb110e7 in repo_format_commit_message pretty.c:1869 #5 0x5612bbb12d96 in pretty_print_commit pretty.c:2161 #6 0x5612bba0a4d5 in show_log log-tree.c:781 #7 0x5612bba0d6c7 in log_tree_commit log-tree.c:1117 #8 0x5612bb691ed5 in cmd_log_walk_no_free builtin/log.c:508 #9 0x5612bb69235b in cmd_log_walk builtin/log.c:549 #10 0x5612bb6951a2 in cmd_log builtin/log.c:883 #11 0x5612bb56c993 in run_builtin git.c:466 #12 0x5612bb56d397 in handle_builtin git.c:721 #13 0x5612bb56db07 in run_argv git.c:788 #14 0x5612bb56e8a7 in cmd_main git.c:923 #15 0x5612bb803682 in main common-main.c:57 #16 0x7f95c4c3c28f (/usr/lib/libc.so.6+0x2328f) #17 0x7f95c4c3c349 in __libc_start_main (/usr/lib/libc.so.6+0x23349) #18 0x5612bb5680e4 in _start ../sysdeps/x86_64/start.S:115 0x603000001168 is located 0 bytes to the right of 24-byte region [0x603000001150,0x603000001168) allocated by thread T0 here: #0 0x7f95c4ebe7ea in __interceptor_realloc /usr/src/debug/gcc/libsanitizer/asan/asan_malloc_linux.cpp:85 #1 0x5612bbcdd556 in xrealloc wrapper.c:136 #2 0x5612bbc310a3 in strbuf_grow strbuf.c:99 #3 0x5612bbc32acd in strbuf_add strbuf.c:298 #4 0x5612bbc33aec in strbuf_expand strbuf.c:418 #5 0x5612bbb110e7 in repo_format_commit_message pretty.c:1869 #6 0x5612bbb12d96 in pretty_print_commit pretty.c:2161 #7 0x5612bba0a4d5 in show_log log-tree.c:781 #8 0x5612bba0d6c7 in log_tree_commit log-tree.c:1117 #9 0x5612bb691ed5 in cmd_log_walk_no_free builtin/log.c:508 #10 0x5612bb69235b in cmd_log_walk builtin/log.c:549 #11 0x5612bb6951a2 in cmd_log builtin/log.c:883 #12 0x5612bb56c993 in run_builtin git.c:466 #13 0x5612bb56d397 in handle_builtin git.c:721 #14 0x5612bb56db07 in run_argv git.c:788 #15 0x5612bb56e8a7 in cmd_main git.c:923 #16 0x5612bb803682 in main common-main.c:57 #17 0x7f95c4c3c28f (/usr/lib/libc.so.6+0x2328f) SUMMARY: AddressSanitizer: heap-buffer-overflow /usr/src/debug/gcc/libsanitizer/sanitizer_common/sanitizer_common_interceptors.inc:827 in __interceptor_memcpy Shadow bytes around the buggy address: 0x0c067fff81d0: fd fd fd fa fa fa fd fd fd fa fa fa fd fd fd fa 0x0c067fff81e0: fa fa fd fd fd fd fa fa fd fd fd fd fa fa fd fd 0x0c067fff81f0: fd fa fa fa fd fd fd fa fa fa fd fd fd fa fa fa 0x0c067fff8200: fd fd fd fa fa fa fd fd fd fd fa fa 00 00 00 fa 0x0c067fff8210: fa fa fd fd fd fa fa fa fd fd fd fa fa fa fd fd =>0x0c067fff8220: fd fa fa fa fd fd fd fa fa fa 00 00 00[fa]fa fa 0x0c067fff8230: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8240: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8250: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8260: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8270: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa Shadow byte legend (one shadow byte represents 8 application bytes): Addressable: 00 Partially addressable: 01 02 03 04 05 06 07 Heap left redzone: fa Freed heap region: fd Stack left redzone: f1 Stack mid redzone: f2 Stack right redzone: f3 Stack after return: f5 Stack use after scope: f8 Global redzone: f9 Global init order: f6 Poisoned by user: f7 Container overflow: fc Array cookie: ac Intra object redzone: bb ASan internal: fe Left alloca redzone: ca Right alloca redzone: cb ==26009==ABORTING Now the proper fix for this would be to convert both functions to return an `size_t` instead of an `int`. But given that this commit may be part of a security release, let's instead do the minimal viable fix and die in case we see an overflow. Add a test that would have previously caused us to crash. Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-12-01 14:47:04 +00:00
int glyph_width;
size_t skip;
while (skip_ansi &&
(skip = display_mode_esc_sequence_len(string)) != 0)
string += skip;
glyph_width = utf8_width(&string, NULL);
if (glyph_width > 0)
width += glyph_width;
}
utf8: fix overflow when returning string width The return type of both `utf8_strwidth()` and `utf8_strnwidth()` is `int`, but we operate on string lengths which are typically of type `size_t`. This means that when the string is longer than `INT_MAX`, we will overflow and thus return a negative result. This can lead to an out-of-bounds write with `--pretty=format:%<1)%B` and a commit message that is 2^31+1 bytes long: ================================================================= ==26009==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000001168 at pc 0x7f95c4e5f427 bp 0x7ffd8541c900 sp 0x7ffd8541c0a8 WRITE of size 2147483649 at 0x603000001168 thread T0 #0 0x7f95c4e5f426 in __interceptor_memcpy /usr/src/debug/gcc/libsanitizer/sanitizer_common/sanitizer_common_interceptors.inc:827 #1 0x5612bbb1068c in format_and_pad_commit pretty.c:1763 #2 0x5612bbb1087a in format_commit_item pretty.c:1801 #3 0x5612bbc33bab in strbuf_expand strbuf.c:429 #4 0x5612bbb110e7 in repo_format_commit_message pretty.c:1869 #5 0x5612bbb12d96 in pretty_print_commit pretty.c:2161 #6 0x5612bba0a4d5 in show_log log-tree.c:781 #7 0x5612bba0d6c7 in log_tree_commit log-tree.c:1117 #8 0x5612bb691ed5 in cmd_log_walk_no_free builtin/log.c:508 #9 0x5612bb69235b in cmd_log_walk builtin/log.c:549 #10 0x5612bb6951a2 in cmd_log builtin/log.c:883 #11 0x5612bb56c993 in run_builtin git.c:466 #12 0x5612bb56d397 in handle_builtin git.c:721 #13 0x5612bb56db07 in run_argv git.c:788 #14 0x5612bb56e8a7 in cmd_main git.c:923 #15 0x5612bb803682 in main common-main.c:57 #16 0x7f95c4c3c28f (/usr/lib/libc.so.6+0x2328f) #17 0x7f95c4c3c349 in __libc_start_main (/usr/lib/libc.so.6+0x23349) #18 0x5612bb5680e4 in _start ../sysdeps/x86_64/start.S:115 0x603000001168 is located 0 bytes to the right of 24-byte region [0x603000001150,0x603000001168) allocated by thread T0 here: #0 0x7f95c4ebe7ea in __interceptor_realloc /usr/src/debug/gcc/libsanitizer/asan/asan_malloc_linux.cpp:85 #1 0x5612bbcdd556 in xrealloc wrapper.c:136 #2 0x5612bbc310a3 in strbuf_grow strbuf.c:99 #3 0x5612bbc32acd in strbuf_add strbuf.c:298 #4 0x5612bbc33aec in strbuf_expand strbuf.c:418 #5 0x5612bbb110e7 in repo_format_commit_message pretty.c:1869 #6 0x5612bbb12d96 in pretty_print_commit pretty.c:2161 #7 0x5612bba0a4d5 in show_log log-tree.c:781 #8 0x5612bba0d6c7 in log_tree_commit log-tree.c:1117 #9 0x5612bb691ed5 in cmd_log_walk_no_free builtin/log.c:508 #10 0x5612bb69235b in cmd_log_walk builtin/log.c:549 #11 0x5612bb6951a2 in cmd_log builtin/log.c:883 #12 0x5612bb56c993 in run_builtin git.c:466 #13 0x5612bb56d397 in handle_builtin git.c:721 #14 0x5612bb56db07 in run_argv git.c:788 #15 0x5612bb56e8a7 in cmd_main git.c:923 #16 0x5612bb803682 in main common-main.c:57 #17 0x7f95c4c3c28f (/usr/lib/libc.so.6+0x2328f) SUMMARY: AddressSanitizer: heap-buffer-overflow /usr/src/debug/gcc/libsanitizer/sanitizer_common/sanitizer_common_interceptors.inc:827 in __interceptor_memcpy Shadow bytes around the buggy address: 0x0c067fff81d0: fd fd fd fa fa fa fd fd fd fa fa fa fd fd fd fa 0x0c067fff81e0: fa fa fd fd fd fd fa fa fd fd fd fd fa fa fd fd 0x0c067fff81f0: fd fa fa fa fd fd fd fa fa fa fd fd fd fa fa fa 0x0c067fff8200: fd fd fd fa fa fa fd fd fd fd fa fa 00 00 00 fa 0x0c067fff8210: fa fa fd fd fd fa fa fa fd fd fd fa fa fa fd fd =>0x0c067fff8220: fd fa fa fa fd fd fd fa fa fa 00 00 00[fa]fa fa 0x0c067fff8230: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8240: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8250: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8260: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa 0x0c067fff8270: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa Shadow byte legend (one shadow byte represents 8 application bytes): Addressable: 00 Partially addressable: 01 02 03 04 05 06 07 Heap left redzone: fa Freed heap region: fd Stack left redzone: f1 Stack mid redzone: f2 Stack right redzone: f3 Stack after return: f5 Stack use after scope: f8 Global redzone: f9 Global init order: f6 Poisoned by user: f7 Container overflow: fc Array cookie: ac Intra object redzone: bb ASan internal: fe Left alloca redzone: ca Right alloca redzone: cb ==26009==ABORTING Now the proper fix for this would be to convert both functions to return an `size_t` instead of an `int`. But given that this commit may be part of a security release, let's instead do the minimal viable fix and die in case we see an overflow. Add a test that would have previously caused us to crash. Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-12-01 14:47:04 +00:00
/*
* TODO: fix the interface of this function and `utf8_strwidth()` to
* return `size_t` instead of `int`.
*/
return cast_size_t_to_int(string ? width : len);
}
int utf8_strwidth(const char *string)
{
return utf8_strnwidth(string, strlen(string), 0);
}
int is_utf8(const char *text)
{
while (*text) {
if (*text == '\n' || *text == '\t' || *text == '\r') {
text++;
continue;
}
utf8_width(&text, NULL);
if (!text)
return 0;
}
return 1;
}
static void strbuf_add_indented_text(struct strbuf *buf, const char *text,
int indent, int indent2)
{
if (indent < 0)
indent = 0;
while (*text) {
const char *eol = strchrnul(text, '\n');
if (*eol == '\n')
eol++;
strbuf_addchars(buf, ' ', indent);
strbuf_add(buf, text, eol - text);
text = eol;
indent = indent2;
}
}
/*
* Wrap the text, if necessary. The variable indent is the indent for the
* first line, indent2 is the indent for all other lines.
* If indent is negative, assume that already -indent columns have been
* consumed (and no extra indent is necessary for the first line).
*/
void strbuf_add_wrapped_text(struct strbuf *buf,
const char *text, int indent1, int indent2, int width)
{
int indent, w, assume_utf8 = 1;
const char *bol, *space, *start = text;
size_t orig_len = buf->len;
if (width <= 0) {
strbuf_add_indented_text(buf, text, indent1, indent2);
return;
}
retry:
bol = text;
w = indent = indent1;
space = NULL;
if (indent < 0) {
w = -indent;
space = text;
}
for (;;) {
char c;
size_t skip;
while ((skip = display_mode_esc_sequence_len(text)))
text += skip;
c = *text;
if (!c || isspace(c)) {
if (w <= width || !space) {
const char *start = bol;
if (!c && text == start)
return;
if (space)
start = space;
else
strbuf_addchars(buf, ' ', indent);
strbuf_add(buf, start, text - start);
if (!c)
return;
space = text;
if (c == '\t')
w |= 0x07;
else if (c == '\n') {
space++;
if (*space == '\n') {
strbuf_addch(buf, '\n');
goto new_line;
}
else if (!isalnum(*space))
goto new_line;
else
strbuf_addch(buf, ' ');
}
w++;
text++;
}
else {
new_line:
strbuf_addch(buf, '\n');
text = bol = space + isspace(*space);
space = NULL;
w = indent = indent2;
}
continue;
}
if (assume_utf8) {
w += utf8_width(&text, NULL);
if (!text) {
assume_utf8 = 0;
text = start;
strbuf_setlen(buf, orig_len);
goto retry;
}
} else {
w++;
text++;
}
}
}
void strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len,
int indent, int indent2, int width)
{
char *tmp = xstrndup(data, len);
strbuf_add_wrapped_text(buf, tmp, indent, indent2, width);
free(tmp);
}
void strbuf_utf8_replace(struct strbuf *sb_src, int pos, int width,
const char *subst)
{
const char *src = sb_src->buf, *end = sb_src->buf + sb_src->len;
struct strbuf dst;
int w = 0;
strbuf_init(&dst, sb_src->len);
while (src < end) {
const char *old;
int glyph_width;
size_t n;
while ((n = display_mode_esc_sequence_len(src))) {
strbuf_add(&dst, src, n);
src += n;
}
if (src >= end)
break;
old = src;
glyph_width = utf8_width((const char**)&src, NULL);
if (!src) /* broken utf-8, do nothing */
goto out;
/*
* In case we see a control character we copy it into the
* buffer, but don't add it to the width.
*/
if (glyph_width < 0)
glyph_width = 0;
if (glyph_width && w >= pos && w < pos + width) {
if (subst) {
strbuf_addstr(&dst, subst);
subst = NULL;
}
} else {
strbuf_add(&dst, old, src - old);
}
w += glyph_width;
}
strbuf_swap(sb_src, &dst);
out:
strbuf_release(&dst);
}
/*
* Returns true (1) if the src encoding name matches the dst encoding
* name directly or one of its alternative names. E.g. UTF-16BE is the
* same as UTF16BE.
*/
static int same_utf_encoding(const char *src, const char *dst)
{
if (skip_iprefix(src, "utf", &src) && skip_iprefix(dst, "utf", &dst)) {
skip_prefix(src, "-", &src);
skip_prefix(dst, "-", &dst);
return !strcasecmp(src, dst);
}
return 0;
}
int is_encoding_utf8(const char *name)
{
if (!name)
return 1;
if (same_utf_encoding("utf-8", name))
return 1;
return 0;
}
int same_encoding(const char *src, const char *dst)
{
static const char utf8[] = "UTF-8";
if (!src)
src = utf8;
if (!dst)
dst = utf8;
if (same_utf_encoding(src, dst))
return 1;
return !strcasecmp(src, dst);
}
/*
* Wrapper for fprintf and returns the total number of columns required
* for the printed string, assuming that the string is utf8.
*/
int utf8_fprintf(FILE *stream, const char *format, ...)
{
struct strbuf buf = STRBUF_INIT;
va_list arg;
int columns;
va_start(arg, format);
strbuf_vaddf(&buf, format, arg);
va_end(arg);
columns = fputs(buf.buf, stream);
if (0 <= columns) /* keep the error from the I/O */
columns = utf8_strwidth(buf.buf);
strbuf_release(&buf);
return columns;
}
/*
* Given a buffer and its encoding, return it re-encoded
* with iconv. If the conversion fails, returns NULL.
*/
#ifndef NO_ICONV
#if defined(OLD_ICONV) || (defined(__sun__) && !defined(_XPG6))
typedef const char * iconv_ibp;
#else
typedef char * iconv_ibp;
#endif
Support working-tree-encoding "UTF-16LE-BOM" Users who want UTF-16 files in the working tree set the .gitattributes like this: test.txt working-tree-encoding=UTF-16 The unicode standard itself defines 3 allowed ways how to encode UTF-16. The following 3 versions convert all back to 'g' 'i' 't' in UTF-8: a) UTF-16, without BOM, big endian: $ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t b) UTF-16, with BOM, little endian: $ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t c) UTF-16, with BOM, big endian: $ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the working tree. After a checkout, the resulting file has a BOM and is encoded in "UTF-16", in the version (c) above. This is what iconv generates, more details follow below. iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE: d) UTF-16 $ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c 0000000 376 377 \0 g \0 i \0 t e) UTF-16LE $ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c 0000000 g \0 i \0 t \0 f) UTF-16BE $ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c 0000000 \0 g \0 i \0 t There is no way to generate version (b) from above in a Git working tree, but that is what some applications need. (All fully unicode aware applications should be able to read all 3 variants, but in practise we are not there yet). When producing UTF-16 as an output, iconv generates the big endian version with a BOM. (big endian is probably chosen for historical reasons). iconv can produce UTF-16 files with little endianess by using "UTF-16LE" as encoding, and that file does not have a BOM. Not all users (especially under Windows) are happy with this. Some tools are not fully unicode aware and can only handle version (b). Today there is no way to produce version (b) with iconv (or libiconv). Looking into the history of iconv, it seems as if version (c) will be used in all future iconv versions (for compatibility reasons). Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM". libiconv can not handle the encoding, so Git pick it up, handles the BOM and uses libiconv to convert the rest of the stream. (UTF-16BE-BOM is added for consistency) Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-30 15:01:52 +00:00
char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv,
size_t bom_len, size_t *outsz_p)
{
git on Mac OS and precomposed unicode Mac OS X mangles file names containing unicode on file systems HFS+, VFAT or SAMBA. When a file using unicode code points outside ASCII is created on a HFS+ drive, the file name is converted into decomposed unicode and written to disk. No conversion is done if the file name is already decomposed unicode. Calling open("\xc3\x84", ...) with a precomposed "Ä" yields the same result as open("\x41\xcc\x88",...) with a decomposed "Ä". As a consequence, readdir() returns the file names in decomposed unicode, even if the user expects precomposed unicode. Unlike on HFS+, Mac OS X stores files on a VFAT drive (e.g. an USB drive) in precomposed unicode, but readdir() still returns file names in decomposed unicode. When a git repository is stored on a network share using SAMBA, file names are send over the wire and written to disk on the remote system in precomposed unicode, but Mac OS X readdir() returns decomposed unicode to be compatible with its behaviour on HFS+ and VFAT. The unicode decomposition causes many problems: - The names "git add" and other commands get from the end user may often be precomposed form (the decomposed form is not easily input from the keyboard), but when the commands read from the filesystem to see what it is going to update the index with already is on the filesystem, readdir() will give decomposed form, which is different. - Similarly "git log", "git mv" and all other commands that need to compare pathnames found on the command line (often but not always precomposed form; a command line input resulting from globbing may be in decomposed) with pathnames found in the tree objects (should be precomposed form to be compatible with other systems and for consistency in general). - The same for names stored in the index, which should be precomposed, that may need to be compared with the names read from readdir(). NFS mounted from Linux is fully transparent and does not suffer from the above. As Mac OS X treats precomposed and decomposed file names as equal, we can - wrap readdir() on Mac OS X to return the precomposed form, and - normalize decomposed form given from the command line also to the precomposed form, to ensure that all pathnames used in Git are always in the precomposed form. This behaviour can be requested by setting "core.precomposedunicode" configuration variable to true. The code in compat/precomposed_utf8.c implements basically 4 new functions: precomposed_utf8_opendir(), precomposed_utf8_readdir(), precomposed_utf8_closedir() and precompose_argv(). The first three are to wrap opendir(3), readdir(3), and closedir(3) functions. The argv[] conversion allows to use the TAB filename completion done by the shell on command line. It tolerates other tools which use readdir() to feed decomposed file names into git. When creating a new git repository with "git init" or "git clone", "core.precomposedunicode" will be set "false". The user needs to activate this feature manually. She typically sets core.precomposedunicode to "true" on HFS and VFAT, or file systems mounted via SAMBA. Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-07-08 13:50:25 +00:00
size_t outsz, outalloc;
char *out, *outpos;
iconv_ibp cp;
outsz = insz;
Support working-tree-encoding "UTF-16LE-BOM" Users who want UTF-16 files in the working tree set the .gitattributes like this: test.txt working-tree-encoding=UTF-16 The unicode standard itself defines 3 allowed ways how to encode UTF-16. The following 3 versions convert all back to 'g' 'i' 't' in UTF-8: a) UTF-16, without BOM, big endian: $ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t b) UTF-16, with BOM, little endian: $ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t c) UTF-16, with BOM, big endian: $ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the working tree. After a checkout, the resulting file has a BOM and is encoded in "UTF-16", in the version (c) above. This is what iconv generates, more details follow below. iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE: d) UTF-16 $ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c 0000000 376 377 \0 g \0 i \0 t e) UTF-16LE $ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c 0000000 g \0 i \0 t \0 f) UTF-16BE $ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c 0000000 \0 g \0 i \0 t There is no way to generate version (b) from above in a Git working tree, but that is what some applications need. (All fully unicode aware applications should be able to read all 3 variants, but in practise we are not there yet). When producing UTF-16 as an output, iconv generates the big endian version with a BOM. (big endian is probably chosen for historical reasons). iconv can produce UTF-16 files with little endianess by using "UTF-16LE" as encoding, and that file does not have a BOM. Not all users (especially under Windows) are happy with this. Some tools are not fully unicode aware and can only handle version (b). Today there is no way to produce version (b) with iconv (or libiconv). Looking into the history of iconv, it seems as if version (c) will be used in all future iconv versions (for compatibility reasons). Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM". libiconv can not handle the encoding, so Git pick it up, handles the BOM and uses libiconv to convert the rest of the stream. (UTF-16BE-BOM is added for consistency) Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-30 15:01:52 +00:00
outalloc = st_add(outsz, 1 + bom_len); /* for terminating NUL */
out = xmalloc(outalloc);
Support working-tree-encoding "UTF-16LE-BOM" Users who want UTF-16 files in the working tree set the .gitattributes like this: test.txt working-tree-encoding=UTF-16 The unicode standard itself defines 3 allowed ways how to encode UTF-16. The following 3 versions convert all back to 'g' 'i' 't' in UTF-8: a) UTF-16, without BOM, big endian: $ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t b) UTF-16, with BOM, little endian: $ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t c) UTF-16, with BOM, big endian: $ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the working tree. After a checkout, the resulting file has a BOM and is encoded in "UTF-16", in the version (c) above. This is what iconv generates, more details follow below. iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE: d) UTF-16 $ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c 0000000 376 377 \0 g \0 i \0 t e) UTF-16LE $ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c 0000000 g \0 i \0 t \0 f) UTF-16BE $ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c 0000000 \0 g \0 i \0 t There is no way to generate version (b) from above in a Git working tree, but that is what some applications need. (All fully unicode aware applications should be able to read all 3 variants, but in practise we are not there yet). When producing UTF-16 as an output, iconv generates the big endian version with a BOM. (big endian is probably chosen for historical reasons). iconv can produce UTF-16 files with little endianess by using "UTF-16LE" as encoding, and that file does not have a BOM. Not all users (especially under Windows) are happy with this. Some tools are not fully unicode aware and can only handle version (b). Today there is no way to produce version (b) with iconv (or libiconv). Looking into the history of iconv, it seems as if version (c) will be used in all future iconv versions (for compatibility reasons). Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM". libiconv can not handle the encoding, so Git pick it up, handles the BOM and uses libiconv to convert the rest of the stream. (UTF-16BE-BOM is added for consistency) Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-30 15:01:52 +00:00
outpos = out + bom_len;
cp = (iconv_ibp)in;
while (1) {
size_t cnt = iconv(conv, &cp, &insz, &outpos, &outsz);
if (cnt == (size_t) -1) {
size_t sofar;
if (errno != E2BIG) {
free(out);
return NULL;
}
/* insz has remaining number of bytes.
* since we started outsz the same as insz,
* it is likely that insz is not enough for
* converting the rest.
*/
sofar = outpos - out;
reencode_string: use st_add/st_mult helpers When converting a string with iconv, if the output buffer isn't big enough, we grow it. But our growth is done without any concern for integer overflow. So when we add: outalloc = sofar + insz * 2 + 32; we may end up wrapping outalloc (which is a size_t), and allocating a too-small buffer. We then manipulate it further: outsz = outalloc - sofar - 1; and feed outsz back to iconv. If outalloc is wrapped and smaller than sofar, we'll end up with a small allocation but feed a very large outsz to iconv, which could result in it overflowing the buffer. Can we use this to construct an attack wherein the victim clones a repository with a very large commit object with an encoding header, and running "git log" reencodes it into utf8, causing an overflow? An attack of this sort is likely impossible in practice. "sofar" is how many output bytes we've written total, and "insz" is the number of input bytes remaining. Imagine our input doubles in size as we output it (which is easy to do by converting latin1 to utf8, for example), and that we start with N input bytes. Our initial output buffer also starts at N bytes, so after the first call we'd have N/2 input bytes remaining (insz), and have written N bytes (sofar). That means our next allocation will be (N + N/2 * 2 + 32) bytes, or (2N + 32). We can therefore overflow a 32-bit size_t with a commit message that's just under 2^31 bytes, assuming it consists mostly of "doubling" sequences (e.g., latin1 0xe1 which becomes utf8 0xc3 0xa1). But we'll never make it that far with such a message. We'll be spending 2^31 bytes on the original string. And our initial output buffer will also be 2^31 bytes. Which is not going to succeed on a system with a 32-bit size_t, since there will be other things using the address space, too. The initial malloc will fail. If we imagine instead that we can triple the size when converting, then our second allocation becomes (N + 2/3N * 2 + 32), or (7/3N + 32). That still requires two allocations of 3/7 of our address space (6/7 of the total) to succeed. If we imagine we can quadruple, it becomes (5/2N + 32); we need to be able to allocate 4/5 of the address space to succeed. This might start to get plausible. But is it possible to get a 4-to-1 increase in size? Probably if you're converting to some obscure encoding. But since git defaults to utf8 for its output, that's the likely destination encoding for an attack. And while there are 4-character utf8 sequences, it's unlikely that you'd be able find a single-byte source sequence in any encoding. So this is certainly buggy code which should be fixed, but it is probably not a useful attack vector. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-07-24 10:50:10 +00:00
outalloc = st_add3(sofar, st_mult(insz, 2), 32);
out = xrealloc(out, outalloc);
outpos = out + sofar;
outsz = outalloc - sofar - 1;
}
else {
*outpos = '\0';
if (outsz_p)
*outsz_p = outpos - out;
break;
}
}
git on Mac OS and precomposed unicode Mac OS X mangles file names containing unicode on file systems HFS+, VFAT or SAMBA. When a file using unicode code points outside ASCII is created on a HFS+ drive, the file name is converted into decomposed unicode and written to disk. No conversion is done if the file name is already decomposed unicode. Calling open("\xc3\x84", ...) with a precomposed "Ä" yields the same result as open("\x41\xcc\x88",...) with a decomposed "Ä". As a consequence, readdir() returns the file names in decomposed unicode, even if the user expects precomposed unicode. Unlike on HFS+, Mac OS X stores files on a VFAT drive (e.g. an USB drive) in precomposed unicode, but readdir() still returns file names in decomposed unicode. When a git repository is stored on a network share using SAMBA, file names are send over the wire and written to disk on the remote system in precomposed unicode, but Mac OS X readdir() returns decomposed unicode to be compatible with its behaviour on HFS+ and VFAT. The unicode decomposition causes many problems: - The names "git add" and other commands get from the end user may often be precomposed form (the decomposed form is not easily input from the keyboard), but when the commands read from the filesystem to see what it is going to update the index with already is on the filesystem, readdir() will give decomposed form, which is different. - Similarly "git log", "git mv" and all other commands that need to compare pathnames found on the command line (often but not always precomposed form; a command line input resulting from globbing may be in decomposed) with pathnames found in the tree objects (should be precomposed form to be compatible with other systems and for consistency in general). - The same for names stored in the index, which should be precomposed, that may need to be compared with the names read from readdir(). NFS mounted from Linux is fully transparent and does not suffer from the above. As Mac OS X treats precomposed and decomposed file names as equal, we can - wrap readdir() on Mac OS X to return the precomposed form, and - normalize decomposed form given from the command line also to the precomposed form, to ensure that all pathnames used in Git are always in the precomposed form. This behaviour can be requested by setting "core.precomposedunicode" configuration variable to true. The code in compat/precomposed_utf8.c implements basically 4 new functions: precomposed_utf8_opendir(), precomposed_utf8_readdir(), precomposed_utf8_closedir() and precompose_argv(). The first three are to wrap opendir(3), readdir(3), and closedir(3) functions. The argv[] conversion allows to use the TAB filename completion done by the shell on command line. It tolerates other tools which use readdir() to feed decomposed file names into git. When creating a new git repository with "git init" or "git clone", "core.precomposedunicode" will be set "false". The user needs to activate this feature manually. She typically sets core.precomposedunicode to "true" on HFS and VFAT, or file systems mounted via SAMBA. Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-07-08 13:50:25 +00:00
return out;
}
static const char *fallback_encoding(const char *name)
{
/*
* Some platforms do not have the variously spelled variants of
* UTF-8, so let's fall back to trying the most official
* spelling. We do so only as a fallback in case the platform
* does understand the user's spelling, but not our official
* one.
*/
if (is_encoding_utf8(name))
return "UTF-8";
/*
* Even though latin-1 is still seen in e-mail
* headers, some platforms only install ISO-8859-1.
*/
if (!strcasecmp(name, "latin-1"))
return "ISO-8859-1";
return name;
}
char *reencode_string_len(const char *in, size_t insz,
const char *out_encoding, const char *in_encoding,
size_t *outsz)
git on Mac OS and precomposed unicode Mac OS X mangles file names containing unicode on file systems HFS+, VFAT or SAMBA. When a file using unicode code points outside ASCII is created on a HFS+ drive, the file name is converted into decomposed unicode and written to disk. No conversion is done if the file name is already decomposed unicode. Calling open("\xc3\x84", ...) with a precomposed "Ä" yields the same result as open("\x41\xcc\x88",...) with a decomposed "Ä". As a consequence, readdir() returns the file names in decomposed unicode, even if the user expects precomposed unicode. Unlike on HFS+, Mac OS X stores files on a VFAT drive (e.g. an USB drive) in precomposed unicode, but readdir() still returns file names in decomposed unicode. When a git repository is stored on a network share using SAMBA, file names are send over the wire and written to disk on the remote system in precomposed unicode, but Mac OS X readdir() returns decomposed unicode to be compatible with its behaviour on HFS+ and VFAT. The unicode decomposition causes many problems: - The names "git add" and other commands get from the end user may often be precomposed form (the decomposed form is not easily input from the keyboard), but when the commands read from the filesystem to see what it is going to update the index with already is on the filesystem, readdir() will give decomposed form, which is different. - Similarly "git log", "git mv" and all other commands that need to compare pathnames found on the command line (often but not always precomposed form; a command line input resulting from globbing may be in decomposed) with pathnames found in the tree objects (should be precomposed form to be compatible with other systems and for consistency in general). - The same for names stored in the index, which should be precomposed, that may need to be compared with the names read from readdir(). NFS mounted from Linux is fully transparent and does not suffer from the above. As Mac OS X treats precomposed and decomposed file names as equal, we can - wrap readdir() on Mac OS X to return the precomposed form, and - normalize decomposed form given from the command line also to the precomposed form, to ensure that all pathnames used in Git are always in the precomposed form. This behaviour can be requested by setting "core.precomposedunicode" configuration variable to true. The code in compat/precomposed_utf8.c implements basically 4 new functions: precomposed_utf8_opendir(), precomposed_utf8_readdir(), precomposed_utf8_closedir() and precompose_argv(). The first three are to wrap opendir(3), readdir(3), and closedir(3) functions. The argv[] conversion allows to use the TAB filename completion done by the shell on command line. It tolerates other tools which use readdir() to feed decomposed file names into git. When creating a new git repository with "git init" or "git clone", "core.precomposedunicode" will be set "false". The user needs to activate this feature manually. She typically sets core.precomposedunicode to "true" on HFS and VFAT, or file systems mounted via SAMBA. Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-07-08 13:50:25 +00:00
{
iconv_t conv;
char *out;
Support working-tree-encoding "UTF-16LE-BOM" Users who want UTF-16 files in the working tree set the .gitattributes like this: test.txt working-tree-encoding=UTF-16 The unicode standard itself defines 3 allowed ways how to encode UTF-16. The following 3 versions convert all back to 'g' 'i' 't' in UTF-8: a) UTF-16, without BOM, big endian: $ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t b) UTF-16, with BOM, little endian: $ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t c) UTF-16, with BOM, big endian: $ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the working tree. After a checkout, the resulting file has a BOM and is encoded in "UTF-16", in the version (c) above. This is what iconv generates, more details follow below. iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE: d) UTF-16 $ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c 0000000 376 377 \0 g \0 i \0 t e) UTF-16LE $ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c 0000000 g \0 i \0 t \0 f) UTF-16BE $ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c 0000000 \0 g \0 i \0 t There is no way to generate version (b) from above in a Git working tree, but that is what some applications need. (All fully unicode aware applications should be able to read all 3 variants, but in practise we are not there yet). When producing UTF-16 as an output, iconv generates the big endian version with a BOM. (big endian is probably chosen for historical reasons). iconv can produce UTF-16 files with little endianess by using "UTF-16LE" as encoding, and that file does not have a BOM. Not all users (especially under Windows) are happy with this. Some tools are not fully unicode aware and can only handle version (b). Today there is no way to produce version (b) with iconv (or libiconv). Looking into the history of iconv, it seems as if version (c) will be used in all future iconv versions (for compatibility reasons). Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM". libiconv can not handle the encoding, so Git pick it up, handles the BOM and uses libiconv to convert the rest of the stream. (UTF-16BE-BOM is added for consistency) Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-30 15:01:52 +00:00
const char *bom_str = NULL;
size_t bom_len = 0;
git on Mac OS and precomposed unicode Mac OS X mangles file names containing unicode on file systems HFS+, VFAT or SAMBA. When a file using unicode code points outside ASCII is created on a HFS+ drive, the file name is converted into decomposed unicode and written to disk. No conversion is done if the file name is already decomposed unicode. Calling open("\xc3\x84", ...) with a precomposed "Ä" yields the same result as open("\x41\xcc\x88",...) with a decomposed "Ä". As a consequence, readdir() returns the file names in decomposed unicode, even if the user expects precomposed unicode. Unlike on HFS+, Mac OS X stores files on a VFAT drive (e.g. an USB drive) in precomposed unicode, but readdir() still returns file names in decomposed unicode. When a git repository is stored on a network share using SAMBA, file names are send over the wire and written to disk on the remote system in precomposed unicode, but Mac OS X readdir() returns decomposed unicode to be compatible with its behaviour on HFS+ and VFAT. The unicode decomposition causes many problems: - The names "git add" and other commands get from the end user may often be precomposed form (the decomposed form is not easily input from the keyboard), but when the commands read from the filesystem to see what it is going to update the index with already is on the filesystem, readdir() will give decomposed form, which is different. - Similarly "git log", "git mv" and all other commands that need to compare pathnames found on the command line (often but not always precomposed form; a command line input resulting from globbing may be in decomposed) with pathnames found in the tree objects (should be precomposed form to be compatible with other systems and for consistency in general). - The same for names stored in the index, which should be precomposed, that may need to be compared with the names read from readdir(). NFS mounted from Linux is fully transparent and does not suffer from the above. As Mac OS X treats precomposed and decomposed file names as equal, we can - wrap readdir() on Mac OS X to return the precomposed form, and - normalize decomposed form given from the command line also to the precomposed form, to ensure that all pathnames used in Git are always in the precomposed form. This behaviour can be requested by setting "core.precomposedunicode" configuration variable to true. The code in compat/precomposed_utf8.c implements basically 4 new functions: precomposed_utf8_opendir(), precomposed_utf8_readdir(), precomposed_utf8_closedir() and precompose_argv(). The first three are to wrap opendir(3), readdir(3), and closedir(3) functions. The argv[] conversion allows to use the TAB filename completion done by the shell on command line. It tolerates other tools which use readdir() to feed decomposed file names into git. When creating a new git repository with "git init" or "git clone", "core.precomposedunicode" will be set "false". The user needs to activate this feature manually. She typically sets core.precomposedunicode to "true" on HFS and VFAT, or file systems mounted via SAMBA. Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-07-08 13:50:25 +00:00
if (!in_encoding)
return NULL;
utf8: accept alternate spellings of UTF-8 The iconv implementation on many platforms will accept variants of UTF-8, including "UTF8", "utf-8", and "utf8", but some do not. We make allowances in our code to treat them all identically, but we sometimes hand the string from the user directly to iconv. In this case, the platform iconv may or may not work. There are really four levels of platform iconv support for these synonyms: 1. All synonyms understood (e.g., glibc). 2. Only the official "UTF-8" understood (e.g., Windows). 3. Official "UTF-8" not understood, but some other synonym understood (it's not known whether such a platform exists). 4. Neither "UTF-8" nor any synonym understood (e.g., ancient systems, or ones without utf8 support installed). This patch teaches git to fall back to using the official "UTF-8" spelling when iconv_open fails (and the encoding was one of the synonym spellings). This makes things more convenient to users of type 2 systems, as they can now use any of the synonyms for the log output encoding. Type 1 systems are not affected, as iconv already works on the first try. Type 4 systems are not affected, as both attempts already fail. Type 3 systems will not benefit from the feature, but because we only use "UTF-8" as a fallback, they will not be regressed (i.e., you can continue to use "utf8" if your platform supports it). We could try all the various synonyms, but since such systems are not even known to exist, it's not worth the effort. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-02-25 20:31:00 +00:00
Support working-tree-encoding "UTF-16LE-BOM" Users who want UTF-16 files in the working tree set the .gitattributes like this: test.txt working-tree-encoding=UTF-16 The unicode standard itself defines 3 allowed ways how to encode UTF-16. The following 3 versions convert all back to 'g' 'i' 't' in UTF-8: a) UTF-16, without BOM, big endian: $ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t b) UTF-16, with BOM, little endian: $ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t c) UTF-16, with BOM, big endian: $ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the working tree. After a checkout, the resulting file has a BOM and is encoded in "UTF-16", in the version (c) above. This is what iconv generates, more details follow below. iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE: d) UTF-16 $ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c 0000000 376 377 \0 g \0 i \0 t e) UTF-16LE $ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c 0000000 g \0 i \0 t \0 f) UTF-16BE $ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c 0000000 \0 g \0 i \0 t There is no way to generate version (b) from above in a Git working tree, but that is what some applications need. (All fully unicode aware applications should be able to read all 3 variants, but in practise we are not there yet). When producing UTF-16 as an output, iconv generates the big endian version with a BOM. (big endian is probably chosen for historical reasons). iconv can produce UTF-16 files with little endianess by using "UTF-16LE" as encoding, and that file does not have a BOM. Not all users (especially under Windows) are happy with this. Some tools are not fully unicode aware and can only handle version (b). Today there is no way to produce version (b) with iconv (or libiconv). Looking into the history of iconv, it seems as if version (c) will be used in all future iconv versions (for compatibility reasons). Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM". libiconv can not handle the encoding, so Git pick it up, handles the BOM and uses libiconv to convert the rest of the stream. (UTF-16BE-BOM is added for consistency) Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-30 15:01:52 +00:00
/* UTF-16LE-BOM is the same as UTF-16 for reading */
if (same_utf_encoding("UTF-16LE-BOM", in_encoding))
in_encoding = "UTF-16";
/*
* For writing, UTF-16 iconv typically creates "UTF-16BE-BOM"
* Some users under Windows want the little endian version
utf8: handle systems that don't write BOM for UTF-16 When serializing UTF-16 (and UTF-32), there are three possible ways to write the stream. One can write the data with a BOM in either big-endian or little-endian format, or one can write the data without a BOM in big-endian format. Most systems' iconv implementations choose to write it with a BOM in some endianness, since this is the most foolproof, and it is resistant to misinterpretation on Windows, where UTF-16 and the little-endian serialization are very common. For compatibility with Windows and to avoid accidental misuse there, Git always wants to write UTF-16 with a BOM, and will refuse to read UTF-16 without it. However, musl's iconv implementation writes UTF-16 without a BOM, relying on the user to interpret it as big-endian. This causes t0028 and the related functionality to fail, since Git won't read the file without a BOM. Add a Makefile and #define knob, ICONV_OMITS_BOM, that can be set if the iconv implementation has this behavior. When set, Git will write a BOM manually for UTF-16 and UTF-32 and then force the data to be written in UTF-16BE or UTF-32BE. We choose big-endian behavior here because the tests use the raw "UTF-16" encoding, which will be big-endian when the implementation requires this knob to be set. Update the tests to detect this case and write test data with an added BOM if necessary. Always write the BOM in the tests in big-endian format, since all iconv implementations that omit a BOM must use big-endian serialization according to the Unicode standard. Preserve the existing behavior for systems which do not have this knob enabled, since they may use optimized implementations, including defaulting to the native endianness, which may improve performance. Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-02-12 00:52:06 +00:00
*
* We handle UTF-16 and UTF-32 ourselves only if the platform does not
* provide a BOM (which we require), since we want to match the behavior
* of the system tools and libc as much as possible.
Support working-tree-encoding "UTF-16LE-BOM" Users who want UTF-16 files in the working tree set the .gitattributes like this: test.txt working-tree-encoding=UTF-16 The unicode standard itself defines 3 allowed ways how to encode UTF-16. The following 3 versions convert all back to 'g' 'i' 't' in UTF-8: a) UTF-16, without BOM, big endian: $ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t b) UTF-16, with BOM, little endian: $ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t c) UTF-16, with BOM, big endian: $ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the working tree. After a checkout, the resulting file has a BOM and is encoded in "UTF-16", in the version (c) above. This is what iconv generates, more details follow below. iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE: d) UTF-16 $ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c 0000000 376 377 \0 g \0 i \0 t e) UTF-16LE $ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c 0000000 g \0 i \0 t \0 f) UTF-16BE $ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c 0000000 \0 g \0 i \0 t There is no way to generate version (b) from above in a Git working tree, but that is what some applications need. (All fully unicode aware applications should be able to read all 3 variants, but in practise we are not there yet). When producing UTF-16 as an output, iconv generates the big endian version with a BOM. (big endian is probably chosen for historical reasons). iconv can produce UTF-16 files with little endianess by using "UTF-16LE" as encoding, and that file does not have a BOM. Not all users (especially under Windows) are happy with this. Some tools are not fully unicode aware and can only handle version (b). Today there is no way to produce version (b) with iconv (or libiconv). Looking into the history of iconv, it seems as if version (c) will be used in all future iconv versions (for compatibility reasons). Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM". libiconv can not handle the encoding, so Git pick it up, handles the BOM and uses libiconv to convert the rest of the stream. (UTF-16BE-BOM is added for consistency) Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-30 15:01:52 +00:00
*/
if (same_utf_encoding("UTF-16LE-BOM", out_encoding)) {
bom_str = utf16_le_bom;
bom_len = sizeof(utf16_le_bom);
out_encoding = "UTF-16LE";
} else if (same_utf_encoding("UTF-16BE-BOM", out_encoding)) {
bom_str = utf16_be_bom;
bom_len = sizeof(utf16_be_bom);
out_encoding = "UTF-16BE";
utf8: handle systems that don't write BOM for UTF-16 When serializing UTF-16 (and UTF-32), there are three possible ways to write the stream. One can write the data with a BOM in either big-endian or little-endian format, or one can write the data without a BOM in big-endian format. Most systems' iconv implementations choose to write it with a BOM in some endianness, since this is the most foolproof, and it is resistant to misinterpretation on Windows, where UTF-16 and the little-endian serialization are very common. For compatibility with Windows and to avoid accidental misuse there, Git always wants to write UTF-16 with a BOM, and will refuse to read UTF-16 without it. However, musl's iconv implementation writes UTF-16 without a BOM, relying on the user to interpret it as big-endian. This causes t0028 and the related functionality to fail, since Git won't read the file without a BOM. Add a Makefile and #define knob, ICONV_OMITS_BOM, that can be set if the iconv implementation has this behavior. When set, Git will write a BOM manually for UTF-16 and UTF-32 and then force the data to be written in UTF-16BE or UTF-32BE. We choose big-endian behavior here because the tests use the raw "UTF-16" encoding, which will be big-endian when the implementation requires this knob to be set. Update the tests to detect this case and write test data with an added BOM if necessary. Always write the BOM in the tests in big-endian format, since all iconv implementations that omit a BOM must use big-endian serialization according to the Unicode standard. Preserve the existing behavior for systems which do not have this knob enabled, since they may use optimized implementations, including defaulting to the native endianness, which may improve performance. Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-02-12 00:52:06 +00:00
#ifdef ICONV_OMITS_BOM
} else if (same_utf_encoding("UTF-16", out_encoding)) {
bom_str = utf16_be_bom;
bom_len = sizeof(utf16_be_bom);
out_encoding = "UTF-16BE";
} else if (same_utf_encoding("UTF-32", out_encoding)) {
bom_str = utf32_be_bom;
bom_len = sizeof(utf32_be_bom);
out_encoding = "UTF-32BE";
#endif
Support working-tree-encoding "UTF-16LE-BOM" Users who want UTF-16 files in the working tree set the .gitattributes like this: test.txt working-tree-encoding=UTF-16 The unicode standard itself defines 3 allowed ways how to encode UTF-16. The following 3 versions convert all back to 'g' 'i' 't' in UTF-8: a) UTF-16, without BOM, big endian: $ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t b) UTF-16, with BOM, little endian: $ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t c) UTF-16, with BOM, big endian: $ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the working tree. After a checkout, the resulting file has a BOM and is encoded in "UTF-16", in the version (c) above. This is what iconv generates, more details follow below. iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE: d) UTF-16 $ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c 0000000 376 377 \0 g \0 i \0 t e) UTF-16LE $ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c 0000000 g \0 i \0 t \0 f) UTF-16BE $ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c 0000000 \0 g \0 i \0 t There is no way to generate version (b) from above in a Git working tree, but that is what some applications need. (All fully unicode aware applications should be able to read all 3 variants, but in practise we are not there yet). When producing UTF-16 as an output, iconv generates the big endian version with a BOM. (big endian is probably chosen for historical reasons). iconv can produce UTF-16 files with little endianess by using "UTF-16LE" as encoding, and that file does not have a BOM. Not all users (especially under Windows) are happy with this. Some tools are not fully unicode aware and can only handle version (b). Today there is no way to produce version (b) with iconv (or libiconv). Looking into the history of iconv, it seems as if version (c) will be used in all future iconv versions (for compatibility reasons). Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM". libiconv can not handle the encoding, so Git pick it up, handles the BOM and uses libiconv to convert the rest of the stream. (UTF-16BE-BOM is added for consistency) Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-30 15:01:52 +00:00
}
git on Mac OS and precomposed unicode Mac OS X mangles file names containing unicode on file systems HFS+, VFAT or SAMBA. When a file using unicode code points outside ASCII is created on a HFS+ drive, the file name is converted into decomposed unicode and written to disk. No conversion is done if the file name is already decomposed unicode. Calling open("\xc3\x84", ...) with a precomposed "Ä" yields the same result as open("\x41\xcc\x88",...) with a decomposed "Ä". As a consequence, readdir() returns the file names in decomposed unicode, even if the user expects precomposed unicode. Unlike on HFS+, Mac OS X stores files on a VFAT drive (e.g. an USB drive) in precomposed unicode, but readdir() still returns file names in decomposed unicode. When a git repository is stored on a network share using SAMBA, file names are send over the wire and written to disk on the remote system in precomposed unicode, but Mac OS X readdir() returns decomposed unicode to be compatible with its behaviour on HFS+ and VFAT. The unicode decomposition causes many problems: - The names "git add" and other commands get from the end user may often be precomposed form (the decomposed form is not easily input from the keyboard), but when the commands read from the filesystem to see what it is going to update the index with already is on the filesystem, readdir() will give decomposed form, which is different. - Similarly "git log", "git mv" and all other commands that need to compare pathnames found on the command line (often but not always precomposed form; a command line input resulting from globbing may be in decomposed) with pathnames found in the tree objects (should be precomposed form to be compatible with other systems and for consistency in general). - The same for names stored in the index, which should be precomposed, that may need to be compared with the names read from readdir(). NFS mounted from Linux is fully transparent and does not suffer from the above. As Mac OS X treats precomposed and decomposed file names as equal, we can - wrap readdir() on Mac OS X to return the precomposed form, and - normalize decomposed form given from the command line also to the precomposed form, to ensure that all pathnames used in Git are always in the precomposed form. This behaviour can be requested by setting "core.precomposedunicode" configuration variable to true. The code in compat/precomposed_utf8.c implements basically 4 new functions: precomposed_utf8_opendir(), precomposed_utf8_readdir(), precomposed_utf8_closedir() and precompose_argv(). The first three are to wrap opendir(3), readdir(3), and closedir(3) functions. The argv[] conversion allows to use the TAB filename completion done by the shell on command line. It tolerates other tools which use readdir() to feed decomposed file names into git. When creating a new git repository with "git init" or "git clone", "core.precomposedunicode" will be set "false". The user needs to activate this feature manually. She typically sets core.precomposedunicode to "true" on HFS and VFAT, or file systems mounted via SAMBA. Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-07-08 13:50:25 +00:00
conv = iconv_open(out_encoding, in_encoding);
utf8: accept alternate spellings of UTF-8 The iconv implementation on many platforms will accept variants of UTF-8, including "UTF8", "utf-8", and "utf8", but some do not. We make allowances in our code to treat them all identically, but we sometimes hand the string from the user directly to iconv. In this case, the platform iconv may or may not work. There are really four levels of platform iconv support for these synonyms: 1. All synonyms understood (e.g., glibc). 2. Only the official "UTF-8" understood (e.g., Windows). 3. Official "UTF-8" not understood, but some other synonym understood (it's not known whether such a platform exists). 4. Neither "UTF-8" nor any synonym understood (e.g., ancient systems, or ones without utf8 support installed). This patch teaches git to fall back to using the official "UTF-8" spelling when iconv_open fails (and the encoding was one of the synonym spellings). This makes things more convenient to users of type 2 systems, as they can now use any of the synonyms for the log output encoding. Type 1 systems are not affected, as iconv already works on the first try. Type 4 systems are not affected, as both attempts already fail. Type 3 systems will not benefit from the feature, but because we only use "UTF-8" as a fallback, they will not be regressed (i.e., you can continue to use "utf8" if your platform supports it). We could try all the various synonyms, but since such systems are not even known to exist, it's not worth the effort. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-02-25 20:31:00 +00:00
if (conv == (iconv_t) -1) {
in_encoding = fallback_encoding(in_encoding);
out_encoding = fallback_encoding(out_encoding);
utf8: accept alternate spellings of UTF-8 The iconv implementation on many platforms will accept variants of UTF-8, including "UTF8", "utf-8", and "utf8", but some do not. We make allowances in our code to treat them all identically, but we sometimes hand the string from the user directly to iconv. In this case, the platform iconv may or may not work. There are really four levels of platform iconv support for these synonyms: 1. All synonyms understood (e.g., glibc). 2. Only the official "UTF-8" understood (e.g., Windows). 3. Official "UTF-8" not understood, but some other synonym understood (it's not known whether such a platform exists). 4. Neither "UTF-8" nor any synonym understood (e.g., ancient systems, or ones without utf8 support installed). This patch teaches git to fall back to using the official "UTF-8" spelling when iconv_open fails (and the encoding was one of the synonym spellings). This makes things more convenient to users of type 2 systems, as they can now use any of the synonyms for the log output encoding. Type 1 systems are not affected, as iconv already works on the first try. Type 4 systems are not affected, as both attempts already fail. Type 3 systems will not benefit from the feature, but because we only use "UTF-8" as a fallback, they will not be regressed (i.e., you can continue to use "utf8" if your platform supports it). We could try all the various synonyms, but since such systems are not even known to exist, it's not worth the effort. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-02-25 20:31:00 +00:00
conv = iconv_open(out_encoding, in_encoding);
if (conv == (iconv_t) -1)
return NULL;
}
Support working-tree-encoding "UTF-16LE-BOM" Users who want UTF-16 files in the working tree set the .gitattributes like this: test.txt working-tree-encoding=UTF-16 The unicode standard itself defines 3 allowed ways how to encode UTF-16. The following 3 versions convert all back to 'g' 'i' 't' in UTF-8: a) UTF-16, without BOM, big endian: $ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t b) UTF-16, with BOM, little endian: $ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t c) UTF-16, with BOM, big endian: $ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the working tree. After a checkout, the resulting file has a BOM and is encoded in "UTF-16", in the version (c) above. This is what iconv generates, more details follow below. iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE: d) UTF-16 $ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c 0000000 376 377 \0 g \0 i \0 t e) UTF-16LE $ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c 0000000 g \0 i \0 t \0 f) UTF-16BE $ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c 0000000 \0 g \0 i \0 t There is no way to generate version (b) from above in a Git working tree, but that is what some applications need. (All fully unicode aware applications should be able to read all 3 variants, but in practise we are not there yet). When producing UTF-16 as an output, iconv generates the big endian version with a BOM. (big endian is probably chosen for historical reasons). iconv can produce UTF-16 files with little endianess by using "UTF-16LE" as encoding, and that file does not have a BOM. Not all users (especially under Windows) are happy with this. Some tools are not fully unicode aware and can only handle version (b). Today there is no way to produce version (b) with iconv (or libiconv). Looking into the history of iconv, it seems as if version (c) will be used in all future iconv versions (for compatibility reasons). Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM". libiconv can not handle the encoding, so Git pick it up, handles the BOM and uses libiconv to convert the rest of the stream. (UTF-16BE-BOM is added for consistency) Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-30 15:01:52 +00:00
out = reencode_string_iconv(in, insz, conv, bom_len, outsz);
iconv_close(conv);
Support working-tree-encoding "UTF-16LE-BOM" Users who want UTF-16 files in the working tree set the .gitattributes like this: test.txt working-tree-encoding=UTF-16 The unicode standard itself defines 3 allowed ways how to encode UTF-16. The following 3 versions convert all back to 'g' 'i' 't' in UTF-8: a) UTF-16, without BOM, big endian: $ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t b) UTF-16, with BOM, little endian: $ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t c) UTF-16, with BOM, big endian: $ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c 0000000 g i t Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the working tree. After a checkout, the resulting file has a BOM and is encoded in "UTF-16", in the version (c) above. This is what iconv generates, more details follow below. iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE: d) UTF-16 $ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c 0000000 376 377 \0 g \0 i \0 t e) UTF-16LE $ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c 0000000 g \0 i \0 t \0 f) UTF-16BE $ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c 0000000 \0 g \0 i \0 t There is no way to generate version (b) from above in a Git working tree, but that is what some applications need. (All fully unicode aware applications should be able to read all 3 variants, but in practise we are not there yet). When producing UTF-16 as an output, iconv generates the big endian version with a BOM. (big endian is probably chosen for historical reasons). iconv can produce UTF-16 files with little endianess by using "UTF-16LE" as encoding, and that file does not have a BOM. Not all users (especially under Windows) are happy with this. Some tools are not fully unicode aware and can only handle version (b). Today there is no way to produce version (b) with iconv (or libiconv). Looking into the history of iconv, it seems as if version (c) will be used in all future iconv versions (for compatibility reasons). Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM". libiconv can not handle the encoding, so Git pick it up, handles the BOM and uses libiconv to convert the rest of the stream. (UTF-16BE-BOM is added for consistency) Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-30 15:01:52 +00:00
if (out && bom_str && bom_len)
memcpy(out, bom_str, bom_len);
return out;
}
#endif
static int has_bom_prefix(const char *data, size_t len,
const char *bom, size_t bom_len)
{
return data && bom && (len >= bom_len) && !memcmp(data, bom, bom_len);
}
int has_prohibited_utf_bom(const char *enc, const char *data, size_t len)
{
return (
(same_utf_encoding("UTF-16BE", enc) ||
same_utf_encoding("UTF-16LE", enc)) &&
(has_bom_prefix(data, len, utf16_be_bom, sizeof(utf16_be_bom)) ||
has_bom_prefix(data, len, utf16_le_bom, sizeof(utf16_le_bom)))
) || (
(same_utf_encoding("UTF-32BE", enc) ||
same_utf_encoding("UTF-32LE", enc)) &&
(has_bom_prefix(data, len, utf32_be_bom, sizeof(utf32_be_bom)) ||
has_bom_prefix(data, len, utf32_le_bom, sizeof(utf32_le_bom)))
);
}
int is_missing_required_utf_bom(const char *enc, const char *data, size_t len)
{
return (
(same_utf_encoding(enc, "UTF-16")) &&
!(has_bom_prefix(data, len, utf16_be_bom, sizeof(utf16_be_bom)) ||
has_bom_prefix(data, len, utf16_le_bom, sizeof(utf16_le_bom)))
) || (
(same_utf_encoding(enc, "UTF-32")) &&
!(has_bom_prefix(data, len, utf32_be_bom, sizeof(utf32_be_bom)) ||
has_bom_prefix(data, len, utf32_le_bom, sizeof(utf32_le_bom)))
);
}
/*
* Returns first character length in bytes for multi-byte `text` according to
* `encoding`.
*
* - The `text` pointer is updated to point at the next character.
* - When `remainder_p` is not NULL, on entry `*remainder_p` is how much bytes
* we can consume from text, and on exit `*remainder_p` is reduced by returned
* character length. Otherwise `text` is treated as limited by NUL.
*/
int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding)
{
int chrlen;
const char *p = *text;
size_t r = (remainder_p ? *remainder_p : SIZE_MAX);
if (r < 1)
return 0;
if (is_encoding_utf8(encoding)) {
pick_one_utf8_char(&p, &r);
chrlen = p ? (p - *text)
: 1 /* not valid UTF-8 -> raw byte sequence */;
}
else {
/*
* TODO use iconv to decode one char and obtain its chrlen
* for now, let's treat encodings != UTF-8 as one-byte
*/
chrlen = 1;
}
*text += chrlen;
if (remainder_p)
*remainder_p -= chrlen;
return chrlen;
}
/*
* 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)
{
while (1) {
ucs_char_t out = pick_one_utf8_char(in, NULL);
/*
* check for malformed utf8. Technically this
* gets converted to a percent-sequence, but
* returning 0 is good enough for is_hfs_dotgit
* to realize it cannot be .git
*/
if (!*in)
return 0;
/* these code points are ignored completely */
switch (out) {
case 0x200c: /* ZERO WIDTH NON-JOINER */
case 0x200d: /* ZERO WIDTH JOINER */
case 0x200e: /* LEFT-TO-RIGHT MARK */
case 0x200f: /* RIGHT-TO-LEFT MARK */
case 0x202a: /* LEFT-TO-RIGHT EMBEDDING */
case 0x202b: /* RIGHT-TO-LEFT EMBEDDING */
case 0x202c: /* POP DIRECTIONAL FORMATTING */
case 0x202d: /* LEFT-TO-RIGHT OVERRIDE */
case 0x202e: /* RIGHT-TO-LEFT OVERRIDE */
case 0x206a: /* INHIBIT SYMMETRIC SWAPPING */
case 0x206b: /* ACTIVATE SYMMETRIC SWAPPING */
case 0x206c: /* INHIBIT ARABIC FORM SHAPING */
case 0x206d: /* ACTIVATE ARABIC FORM SHAPING */
case 0x206e: /* NATIONAL DIGIT SHAPES */
case 0x206f: /* NOMINAL DIGIT SHAPES */
case 0xfeff: /* ZERO WIDTH NO-BREAK SPACE */
continue;
}
return out;
}
}
static int is_hfs_dot_generic(const char *path,
const char *needle, size_t needle_len)
{
ucs_char_t c;
c = next_hfs_char(&path);
if (c != '.')
return 0;
/*
* there's a great deal of other case-folding that occurs
* in HFS+, but this is enough to catch our fairly vanilla
* hard-coded needles.
*/
for (; needle_len > 0; needle++, needle_len--) {
c = next_hfs_char(&path);
/*
* We know our needles contain only ASCII, so we clamp here to
* make the results of tolower() sane.
*/
if (c > 127)
return 0;
if (tolower(c) != *needle)
return 0;
}
c = next_hfs_char(&path);
if (c && !is_dir_sep(c))
return 0;
return 1;
}
/*
* Inline wrapper to make sure the compiler resolves strlen() on literals at
* compile time.
*/
static inline int is_hfs_dot_str(const char *path, const char *needle)
{
return is_hfs_dot_generic(path, needle, strlen(needle));
}
int is_hfs_dotgit(const char *path)
{
return is_hfs_dot_str(path, "git");
}
int is_hfs_dotgitmodules(const char *path)
{
return is_hfs_dot_str(path, "gitmodules");
}
int is_hfs_dotgitignore(const char *path)
{
return is_hfs_dot_str(path, "gitignore");
}
int is_hfs_dotgitattributes(const char *path)
{
return is_hfs_dot_str(path, "gitattributes");
}
int is_hfs_dotmailmap(const char *path)
{
return is_hfs_dot_str(path, "mailmap");
}
const char utf8_bom[] = "\357\273\277";
int skip_utf8_bom(char **text, size_t len)
{
if (len < strlen(utf8_bom) ||
memcmp(*text, utf8_bom, strlen(utf8_bom)))
return 0;
*text += strlen(utf8_bom);
return 1;
}
void strbuf_utf8_align(struct strbuf *buf, align_type position, unsigned int width,
const char *s)
{
size_t slen = strlen(s);
int display_len = utf8_strnwidth(s, slen, 0);
int utf8_compensation = slen - display_len;
if (display_len >= width) {
strbuf_addstr(buf, s);
return;
}
if (position == ALIGN_LEFT)
strbuf_addf(buf, "%-*s", width + utf8_compensation, s);
else if (position == ALIGN_MIDDLE) {
int left = (width - display_len) / 2;
strbuf_addf(buf, "%*s%-*s", left, "", width - left + utf8_compensation, s);
} else if (position == ALIGN_RIGHT)
strbuf_addf(buf, "%*s", width + utf8_compensation, s);
}