2006-12-22 21:06:08 +00:00
|
|
|
#include "git-compat-util.h"
|
2008-11-10 17:47:00 +00:00
|
|
|
#include "strbuf.h"
|
2006-12-22 21:06:08 +00:00
|
|
|
#include "utf8.h"
|
|
|
|
|
|
|
|
/* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */
|
|
|
|
|
|
|
|
struct interval {
|
2014-02-16 16:06:04 +00:00
|
|
|
ucs_char_t first;
|
|
|
|
ucs_char_t last;
|
2006-12-22 21:06:08 +00:00
|
|
|
};
|
|
|
|
|
2013-04-18 23:08:52 +00:00
|
|
|
size_t display_mode_esc_sequence_len(const char *s)
|
2013-04-18 23:08:44 +00:00
|
|
|
{
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2006-12-22 21:06:08 +00:00
|
|
|
/* auxiliary function for binary search in interval table */
|
2007-11-08 23:35:32 +00:00
|
|
|
static int bisearch(ucs_char_t ucs, const struct interval *table, int max)
|
|
|
|
{
|
2006-12-22 21:06:08 +00:00
|
|
|
int min = 0;
|
|
|
|
int mid;
|
|
|
|
|
|
|
|
if (ucs < table[0].first || ucs > table[max].last)
|
|
|
|
return 0;
|
|
|
|
while (max >= min) {
|
2017-10-08 18:29:37 +00:00
|
|
|
mid = min + (max - min) / 2;
|
2006-12-22 21:06:08 +00:00
|
|
|
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.
|
|
|
|
*
|
2007-03-03 18:28:57 +00:00
|
|
|
* This implementation assumes that ucs_char_t characters are encoded
|
2006-12-22 21:06:08 +00:00
|
|
|
* in ISO 10646.
|
|
|
|
*/
|
|
|
|
|
2007-05-08 04:46:08 +00:00
|
|
|
static int git_wcwidth(ucs_char_t ch)
|
2006-12-22 21:06:08 +00:00
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Sorted list of non-overlapping intervals of non-spacing characters,
|
|
|
|
*/
|
2014-05-09 21:51:44 +00:00
|
|
|
#include "unicode_width.h"
|
2006-12-22 21:06:08 +00:00
|
|
|
|
|
|
|
/* 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 */
|
2014-05-09 21:51:44 +00:00
|
|
|
if (bisearch(ch, zero_width, sizeof(zero_width)
|
2006-12-22 21:06:08 +00:00
|
|
|
/ sizeof(struct interval) - 1))
|
|
|
|
return 0;
|
|
|
|
|
2014-05-09 21:51:38 +00:00
|
|
|
/* binary search in table of double width characters */
|
|
|
|
if (bisearch(ch, double_width, sizeof(double_width)
|
|
|
|
/ sizeof(struct interval) - 1))
|
|
|
|
return 2;
|
2006-12-22 21:06:08 +00:00
|
|
|
|
2014-05-09 21:51:38 +00:00
|
|
|
return 1;
|
2006-12-22 21:06:08 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2008-01-07 03:02:22 +00:00
|
|
|
* Pick one ucs character starting from the location *start points at,
|
|
|
|
* and return it, while updating the *start pointer to point at the
|
2008-01-02 09:49:58 +00:00
|
|
|
* 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.
|
2008-01-07 03:02:22 +00:00
|
|
|
*
|
|
|
|
* If the string was not a valid UTF-8, *start pointer is set to NULL
|
|
|
|
* and the return value is undefined.
|
2006-12-22 21:06:08 +00:00
|
|
|
*/
|
2010-01-12 06:32:29 +00:00
|
|
|
static ucs_char_t pick_one_utf8_char(const char **start, size_t *remainder_p)
|
2006-12-22 21:06:08 +00:00
|
|
|
{
|
|
|
|
unsigned char *s = (unsigned char *)*start;
|
2007-03-03 18:28:57 +00:00
|
|
|
ucs_char_t ch;
|
2008-01-02 09:49:58 +00:00
|
|
|
size_t remainder, incr;
|
2006-12-22 21:06:08 +00:00
|
|
|
|
2008-01-02 09:49:58 +00:00
|
|
|
/*
|
|
|
|
* 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) {
|
2006-12-22 21:06:08 +00:00
|
|
|
/* 0xxxxxxx */
|
|
|
|
ch = *s;
|
2008-01-02 09:49:58 +00:00
|
|
|
incr = 1;
|
2006-12-22 21:06:08 +00:00
|
|
|
} else if ((s[0] & 0xe0) == 0xc0) {
|
|
|
|
/* 110XXXXx 10xxxxxx */
|
2008-01-02 09:49:58 +00:00
|
|
|
if (remainder < 2 ||
|
|
|
|
(s[1] & 0xc0) != 0x80 ||
|
|
|
|
(s[0] & 0xfe) == 0xc0)
|
2006-12-22 21:06:08 +00:00
|
|
|
goto invalid;
|
|
|
|
ch = ((s[0] & 0x1f) << 6) | (s[1] & 0x3f);
|
2008-01-02 09:49:58 +00:00
|
|
|
incr = 2;
|
2006-12-22 21:06:08 +00:00
|
|
|
} else if ((s[0] & 0xf0) == 0xe0) {
|
|
|
|
/* 1110XXXX 10Xxxxxx 10xxxxxx */
|
2008-01-02 09:49:58 +00:00
|
|
|
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))
|
2006-12-22 21:06:08 +00:00
|
|
|
goto invalid;
|
|
|
|
ch = ((s[0] & 0x0f) << 12) |
|
|
|
|
((s[1] & 0x3f) << 6) | (s[2] & 0x3f);
|
2008-01-02 09:49:58 +00:00
|
|
|
incr = 3;
|
2006-12-22 21:06:08 +00:00
|
|
|
} else if ((s[0] & 0xf8) == 0xf0) {
|
|
|
|
/* 11110XXX 10XXxxxx 10xxxxxx 10xxxxxx */
|
2008-01-02 09:49:58 +00:00
|
|
|
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)
|
2006-12-22 21:06:08 +00:00
|
|
|
goto invalid;
|
|
|
|
ch = ((s[0] & 0x07) << 18) | ((s[1] & 0x3f) << 12) |
|
|
|
|
((s[2] & 0x3f) << 6) | (s[3] & 0x3f);
|
2008-01-02 09:49:58 +00:00
|
|
|
incr = 4;
|
2006-12-22 21:06:08 +00:00
|
|
|
} else {
|
|
|
|
invalid:
|
|
|
|
*start = NULL;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2008-01-02 09:49:58 +00:00
|
|
|
*start += incr;
|
|
|
|
if (remainder_p)
|
|
|
|
*remainder_p = remainder - incr;
|
2008-01-07 03:02:22 +00:00
|
|
|
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
|
2008-01-02 09:49:58 +00:00
|
|
|
* 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).
|
2008-01-07 03:02:22 +00:00
|
|
|
*/
|
2008-01-02 09:49:58 +00:00
|
|
|
int utf8_width(const char **start, size_t *remainder_p)
|
2008-01-07 03:02:22 +00:00
|
|
|
{
|
2008-01-02 09:49:58 +00:00
|
|
|
ucs_char_t ch = pick_one_utf8_char(start, remainder_p);
|
2008-01-07 03:02:22 +00:00
|
|
|
if (!*start)
|
|
|
|
return 0;
|
2007-05-08 04:46:08 +00:00
|
|
|
return git_wcwidth(ch);
|
2006-12-22 21:06:08 +00:00
|
|
|
}
|
|
|
|
|
2009-01-30 09:41:28 +00:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2013-04-18 23:08:45 +00:00
|
|
|
int utf8_strnwidth(const char *string, int len, int skip_ansi)
|
2009-01-30 09:41:28 +00:00
|
|
|
{
|
|
|
|
int width = 0;
|
|
|
|
const char *orig = string;
|
|
|
|
|
2013-04-18 23:08:45 +00:00
|
|
|
if (len == -1)
|
|
|
|
len = strlen(string);
|
|
|
|
while (string && string < orig + len) {
|
|
|
|
int skip;
|
|
|
|
while (skip_ansi &&
|
|
|
|
(skip = display_mode_esc_sequence_len(string)) != 0)
|
|
|
|
string += skip;
|
2009-01-30 09:41:28 +00:00
|
|
|
width += utf8_width(&string, NULL);
|
|
|
|
}
|
2013-04-18 23:08:45 +00:00
|
|
|
return string ? width : len;
|
|
|
|
}
|
|
|
|
|
|
|
|
int utf8_strwidth(const char *string)
|
|
|
|
{
|
|
|
|
return utf8_strnwidth(string, -1, 0);
|
2009-01-30 09:41:28 +00:00
|
|
|
}
|
|
|
|
|
2006-12-22 21:06:08 +00:00
|
|
|
int is_utf8(const char *text)
|
|
|
|
{
|
|
|
|
while (*text) {
|
|
|
|
if (*text == '\n' || *text == '\t' || *text == '\r') {
|
|
|
|
text++;
|
|
|
|
continue;
|
|
|
|
}
|
2008-01-02 09:49:58 +00:00
|
|
|
utf8_width(&text, NULL);
|
2006-12-22 21:06:08 +00:00
|
|
|
if (!text)
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2009-11-22 16:15:29 +00:00
|
|
|
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++;
|
2010-02-19 22:15:55 +00:00
|
|
|
strbuf_addchars(buf, ' ', indent);
|
2010-02-19 22:16:45 +00:00
|
|
|
strbuf_add(buf, text, eol - text);
|
2009-11-22 16:15:29 +00:00
|
|
|
text = eol;
|
|
|
|
indent = indent2;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2006-12-22 21:06:08 +00:00
|
|
|
/*
|
|
|
|
* Wrap the text, if necessary. The variable indent is the indent for the
|
|
|
|
* first line, indent2 is the indent for all other lines.
|
2007-02-27 15:20:31 +00:00
|
|
|
* If indent is negative, assume that already -indent columns have been
|
|
|
|
* consumed (and no extra indent is necessary for the first line).
|
2006-12-22 21:06:08 +00:00
|
|
|
*/
|
2012-12-11 05:59:22 +00:00
|
|
|
void strbuf_add_wrapped_text(struct strbuf *buf,
|
2010-02-19 22:20:44 +00:00
|
|
|
const char *text, int indent1, int indent2, int width)
|
2006-12-22 21:06:08 +00:00
|
|
|
{
|
2010-02-19 22:20:44 +00:00
|
|
|
int indent, w, assume_utf8 = 1;
|
|
|
|
const char *bol, *space, *start = text;
|
|
|
|
size_t orig_len = buf->len;
|
2006-12-22 21:06:08 +00:00
|
|
|
|
2009-10-19 06:40:35 +00:00
|
|
|
if (width <= 0) {
|
2010-02-19 22:20:44 +00:00
|
|
|
strbuf_add_indented_text(buf, text, indent1, indent2);
|
2012-12-11 05:59:22 +00:00
|
|
|
return;
|
2009-10-19 06:40:35 +00:00
|
|
|
}
|
|
|
|
|
2010-02-19 22:20:44 +00:00
|
|
|
retry:
|
|
|
|
bol = text;
|
|
|
|
w = indent = indent1;
|
|
|
|
space = NULL;
|
2007-02-27 15:20:31 +00:00
|
|
|
if (indent < 0) {
|
|
|
|
w = -indent;
|
|
|
|
space = text;
|
|
|
|
}
|
|
|
|
|
2006-12-22 21:06:08 +00:00
|
|
|
for (;;) {
|
2009-11-23 22:40:03 +00:00
|
|
|
char c;
|
|
|
|
size_t skip;
|
|
|
|
|
|
|
|
while ((skip = display_mode_esc_sequence_len(text)))
|
|
|
|
text += skip;
|
|
|
|
|
|
|
|
c = *text;
|
2006-12-22 21:06:08 +00:00
|
|
|
if (!c || isspace(c)) {
|
utf8: fix off-by-one wrapping of text
The wrapping logic in strbuf_add_wrapped_text() does currently not allow
lines that entirely fill the allowed width, instead it wraps the line one
character too early.
For example, the text "This is the sixth commit." formatted via
"%w(11,1,2)" (wrap at 11 characters, 1 char indent of first line, 2 char
indent of following lines) results in four lines: " This is", " the",
" sixth", " commit." This is wrong, because " the sixth" is exactly
11 characters long, and thus allowed.
Fix this by allowing the (width+1) character of a line to be a valid
wrapping point if it is a whitespace character.
Signed-off-by: Jan H. Schönherr <schnhrr@cs.tu-berlin.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-10-18 14:43:28 +00:00
|
|
|
if (w <= width || !space) {
|
2006-12-22 21:06:08 +00:00
|
|
|
const char *start = bol;
|
2007-11-11 14:14:15 +00:00
|
|
|
if (!c && text == start)
|
2012-12-11 05:59:22 +00:00
|
|
|
return;
|
2006-12-22 21:06:08 +00:00
|
|
|
if (space)
|
|
|
|
start = space;
|
|
|
|
else
|
2010-02-19 22:15:55 +00:00
|
|
|
strbuf_addchars(buf, ' ', indent);
|
2010-02-19 22:16:45 +00:00
|
|
|
strbuf_add(buf, start, text - start);
|
2007-02-27 15:20:31 +00:00
|
|
|
if (!c)
|
2012-12-11 05:59:22 +00:00
|
|
|
return;
|
2006-12-22 21:06:08 +00:00
|
|
|
space = text;
|
2007-11-11 14:14:15 +00:00
|
|
|
if (c == '\t')
|
|
|
|
w |= 0x07;
|
|
|
|
else if (c == '\n') {
|
|
|
|
space++;
|
|
|
|
if (*space == '\n') {
|
2010-02-19 22:16:45 +00:00
|
|
|
strbuf_addch(buf, '\n');
|
2007-11-11 14:14:15 +00:00
|
|
|
goto new_line;
|
|
|
|
}
|
|
|
|
else if (!isalnum(*space))
|
|
|
|
goto new_line;
|
|
|
|
else
|
2010-02-19 22:16:45 +00:00
|
|
|
strbuf_addch(buf, ' ');
|
2007-11-11 14:14:15 +00:00
|
|
|
}
|
2006-12-22 21:06:08 +00:00
|
|
|
w++;
|
|
|
|
text++;
|
|
|
|
}
|
|
|
|
else {
|
2007-11-11 14:14:15 +00:00
|
|
|
new_line:
|
2010-02-19 22:16:45 +00:00
|
|
|
strbuf_addch(buf, '\n');
|
2007-03-02 14:28:00 +00:00
|
|
|
text = bol = space + isspace(*space);
|
2006-12-22 21:06:08 +00:00
|
|
|
space = NULL;
|
|
|
|
w = indent = indent2;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
2010-02-19 22:20:44 +00:00
|
|
|
if (assume_utf8) {
|
2008-01-02 09:49:58 +00:00
|
|
|
w += utf8_width(&text, NULL);
|
2010-02-19 22:20:44 +00:00
|
|
|
if (!text) {
|
|
|
|
assume_utf8 = 0;
|
|
|
|
text = start;
|
|
|
|
strbuf_setlen(buf, orig_len);
|
|
|
|
goto retry;
|
|
|
|
}
|
|
|
|
} else {
|
2006-12-22 21:06:08 +00:00
|
|
|
w++;
|
|
|
|
text++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2006-12-24 07:36:55 +00:00
|
|
|
|
2012-12-11 05:59:22 +00:00
|
|
|
void strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len,
|
2011-02-23 09:50:19 +00:00
|
|
|
int indent, int indent2, int width)
|
|
|
|
{
|
|
|
|
char *tmp = xstrndup(data, len);
|
2012-12-11 05:59:22 +00:00
|
|
|
strbuf_add_wrapped_text(buf, tmp, indent, indent2, width);
|
2011-02-23 09:50:19 +00:00
|
|
|
free(tmp);
|
|
|
|
}
|
|
|
|
|
2013-04-18 23:08:51 +00:00
|
|
|
void strbuf_utf8_replace(struct strbuf *sb_src, int pos, int width,
|
|
|
|
const char *subst)
|
|
|
|
{
|
|
|
|
struct strbuf sb_dst = STRBUF_INIT;
|
|
|
|
char *src = sb_src->buf;
|
|
|
|
char *end = src + sb_src->len;
|
|
|
|
char *dst;
|
|
|
|
int w = 0, subst_len = 0;
|
|
|
|
|
|
|
|
if (subst)
|
|
|
|
subst_len = strlen(subst);
|
|
|
|
strbuf_grow(&sb_dst, sb_src->len + subst_len);
|
|
|
|
dst = sb_dst.buf;
|
|
|
|
|
|
|
|
while (src < end) {
|
|
|
|
char *old;
|
|
|
|
size_t n;
|
|
|
|
|
|
|
|
while ((n = display_mode_esc_sequence_len(src))) {
|
|
|
|
memcpy(dst, src, n);
|
|
|
|
src += n;
|
|
|
|
dst += n;
|
|
|
|
}
|
|
|
|
|
2014-08-10 07:05:21 +00:00
|
|
|
if (src >= end)
|
|
|
|
break;
|
|
|
|
|
2013-04-18 23:08:51 +00:00
|
|
|
old = src;
|
|
|
|
n = utf8_width((const char**)&src, NULL);
|
|
|
|
if (!src) /* broken utf-8, do nothing */
|
2017-08-30 18:20:16 +00:00
|
|
|
goto out;
|
2013-04-18 23:08:51 +00:00
|
|
|
if (n && w >= pos && w < pos + width) {
|
|
|
|
if (subst) {
|
|
|
|
memcpy(dst, subst, subst_len);
|
|
|
|
dst += subst_len;
|
|
|
|
subst = NULL;
|
|
|
|
}
|
|
|
|
w += n;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
memcpy(dst, old, src - old);
|
|
|
|
dst += src - old;
|
|
|
|
w += n;
|
|
|
|
}
|
|
|
|
strbuf_setlen(&sb_dst, dst - sb_dst.buf);
|
pretty: Fix bug in truncation support for %>, %< and %><
Some systems experience failures in t4205-*.sh (tests 18-20, 27)
which all relate to the use of truncation with the %< padding
placeholder. This capability was added in the commit a7f01c6b
("pretty: support truncating in %>, %< and %><", 19-04-2013).
The truncation support was implemented with the assistance of a
new strbuf function (strbuf_utf8_replace). This function contains
the following code:
strbuf_attach(sb_src, strbuf_detach(&sb_dst, NULL),
sb_dst.len, sb_dst.alloc);
Unfortunately, this code is subject to unspecified behaviour. In
particular, the order of evaluation of the argument expressions
(along with the associated side effects) is not specified by the
C standard. Note that the second argument expression is a call to
strbuf_detach() which, as a side effect, sets the 'len' and 'alloc'
fields of the sb_dst argument to zero. Depending on the order of
evaluation of the argument expressions to the strbuf_attach call,
this can lead to assigning an empty string to 'sb_src'.
In order to remove the undesired behaviour, we replace the above
line of code with:
strbuf_swap(sb_src, &sb_dst);
strbuf_release(&sb_dst);
which achieves the desired effect without provoking unspecified
behaviour.
Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk>
Acked-by: Duy Nguyen <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-27 19:43:36 +00:00
|
|
|
strbuf_swap(sb_src, &sb_dst);
|
2017-08-30 18:20:16 +00:00
|
|
|
out:
|
pretty: Fix bug in truncation support for %>, %< and %><
Some systems experience failures in t4205-*.sh (tests 18-20, 27)
which all relate to the use of truncation with the %< padding
placeholder. This capability was added in the commit a7f01c6b
("pretty: support truncating in %>, %< and %><", 19-04-2013).
The truncation support was implemented with the assistance of a
new strbuf function (strbuf_utf8_replace). This function contains
the following code:
strbuf_attach(sb_src, strbuf_detach(&sb_dst, NULL),
sb_dst.len, sb_dst.alloc);
Unfortunately, this code is subject to unspecified behaviour. In
particular, the order of evaluation of the argument expressions
(along with the associated side effects) is not specified by the
C standard. Note that the second argument expression is a call to
strbuf_detach() which, as a side effect, sets the 'len' and 'alloc'
fields of the sb_dst argument to zero. Depending on the order of
evaluation of the argument expressions to the strbuf_attach call,
this can lead to assigning an empty string to 'sb_src'.
In order to remove the undesired behaviour, we replace the above
line of code with:
strbuf_swap(sb_src, &sb_dst);
strbuf_release(&sb_dst);
which achieves the desired effect without provoking unspecified
behaviour.
Signed-off-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk>
Acked-by: Duy Nguyen <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-27 19:43:36 +00:00
|
|
|
strbuf_release(&sb_dst);
|
2013-04-18 23:08:51 +00:00
|
|
|
}
|
|
|
|
|
2018-04-15 18:16:04 +00:00
|
|
|
/*
|
|
|
|
* 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 (istarts_with(src, "utf") && istarts_with(dst, "utf")) {
|
|
|
|
/* src[3] or dst[3] might be '\0' */
|
|
|
|
int i = (src[3] == '-' ? 4 : 3);
|
|
|
|
int j = (dst[3] == '-' ? 4 : 3);
|
|
|
|
return !strcasecmp(src+i, dst+j);
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-12-30 20:20:43 +00:00
|
|
|
int is_encoding_utf8(const char *name)
|
|
|
|
{
|
|
|
|
if (!name)
|
|
|
|
return 1;
|
2018-04-15 18:16:04 +00:00
|
|
|
if (same_utf_encoding("utf-8", name))
|
2006-12-30 20:20:43 +00:00
|
|
|
return 1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-10-19 05:41:56 +00:00
|
|
|
int same_encoding(const char *src, const char *dst)
|
|
|
|
{
|
2018-04-15 18:16:04 +00:00
|
|
|
static const char utf8[] = "UTF-8";
|
|
|
|
|
|
|
|
if (!src)
|
|
|
|
src = utf8;
|
|
|
|
if (!dst)
|
|
|
|
dst = utf8;
|
|
|
|
if (same_utf_encoding(src, dst))
|
2012-10-19 05:41:56 +00:00
|
|
|
return 1;
|
|
|
|
return !strcasecmp(src, dst);
|
|
|
|
}
|
|
|
|
|
2013-02-09 06:31:09 +00:00
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
}
|
|
|
|
|
2006-12-24 07:36:55 +00:00
|
|
|
/*
|
|
|
|
* Given a buffer and its encoding, return it re-encoded
|
|
|
|
* with iconv. If the conversion fails, returns NULL.
|
|
|
|
*/
|
|
|
|
#ifndef NO_ICONV
|
2009-06-05 23:36:12 +00:00
|
|
|
#if defined(OLD_ICONV) || (defined(__sun__) && !defined(_XPG6))
|
2007-03-03 18:29:03 +00:00
|
|
|
typedef const char * iconv_ibp;
|
|
|
|
#else
|
|
|
|
typedef char * iconv_ibp;
|
|
|
|
#endif
|
2013-04-18 23:08:46 +00:00
|
|
|
char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outsz_p)
|
2006-12-24 07:36:55 +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
|
|
|
size_t outsz, outalloc;
|
2007-03-03 18:29:03 +00:00
|
|
|
char *out, *outpos;
|
|
|
|
iconv_ibp cp;
|
2006-12-24 07:36:55 +00:00
|
|
|
|
|
|
|
outsz = insz;
|
|
|
|
outalloc = outsz + 1; /* for terminating NUL */
|
|
|
|
out = xmalloc(outalloc);
|
|
|
|
outpos = out;
|
2007-03-03 18:29:03 +00:00
|
|
|
cp = (iconv_ibp)in;
|
2006-12-24 07:36:55 +00:00
|
|
|
|
|
|
|
while (1) {
|
|
|
|
size_t cnt = iconv(conv, &cp, &insz, &outpos, &outsz);
|
|
|
|
|
2014-02-16 16:06:03 +00:00
|
|
|
if (cnt == (size_t) -1) {
|
2006-12-24 07:36:55 +00:00
|
|
|
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;
|
|
|
|
outalloc = sofar + insz * 2 + 32;
|
|
|
|
out = xrealloc(out, outalloc);
|
|
|
|
outpos = out + sofar;
|
|
|
|
outsz = outalloc - sofar - 1;
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
*outpos = '\0';
|
2013-04-18 23:08:46 +00:00
|
|
|
if (outsz_p)
|
|
|
|
*outsz_p = outpos - out;
|
2006-12-24 07:36:55 +00:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2016-09-27 01:09:48 +00:00
|
|
|
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";
|
|
|
|
|
2016-09-27 01:09:48 +00:00
|
|
|
/*
|
|
|
|
* 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";
|
|
|
|
|
2016-09-27 01:09:48 +00:00
|
|
|
return name;
|
|
|
|
}
|
|
|
|
|
2013-04-18 23:08:46 +00:00
|
|
|
char *reencode_string_len(const char *in, int insz,
|
|
|
|
const char *out_encoding, const char *in_encoding,
|
|
|
|
int *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;
|
|
|
|
|
|
|
|
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
|
|
|
|
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) {
|
2016-09-27 01:09:48 +00:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2013-04-18 23:08:46 +00:00
|
|
|
out = reencode_string_iconv(in, insz, conv, outsz);
|
2006-12-24 07:36:55 +00:00
|
|
|
iconv_close(conv);
|
|
|
|
return out;
|
|
|
|
}
|
|
|
|
#endif
|
2013-03-07 10:55:07 +00:00
|
|
|
|
2018-04-15 18:16:05 +00:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
|
|
|
static const char utf16_be_bom[] = {0xFE, 0xFF};
|
|
|
|
static const char utf16_le_bom[] = {0xFF, 0xFE};
|
|
|
|
static const char utf32_be_bom[] = {0x00, 0x00, 0xFE, 0xFF};
|
|
|
|
static const char utf32_le_bom[] = {0xFF, 0xFE, 0x00, 0x00};
|
|
|
|
|
|
|
|
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)))
|
|
|
|
);
|
|
|
|
}
|
|
|
|
|
2018-04-15 18:16:06 +00:00
|
|
|
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)))
|
|
|
|
);
|
|
|
|
}
|
|
|
|
|
2013-03-07 10:55:07 +00:00
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
}
|
2014-12-15 22:56:59 +00:00
|
|
|
|
|
|
|
/*
|
2014-12-23 08:45:36 +00:00
|
|
|
* 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
|
2014-12-15 22:56:59 +00:00
|
|
|
* 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;
|
|
|
|
}
|
|
|
|
|
2014-12-23 08:45:36 +00:00
|
|
|
return out;
|
2014-12-15 22:56:59 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
int is_hfs_dotgit(const char *path)
|
|
|
|
{
|
|
|
|
ucs_char_t c;
|
|
|
|
|
2014-12-23 08:45:36 +00:00
|
|
|
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')
|
2014-12-15 22:56:59 +00:00
|
|
|
return 0;
|
|
|
|
c = next_hfs_char(&path);
|
|
|
|
if (c && !is_dir_sep(c))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
}
|
2015-04-16 17:45:29 +00:00
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
2015-09-10 15:48:19 +00:00
|
|
|
|
|
|
|
void strbuf_utf8_align(struct strbuf *buf, align_type position, unsigned int width,
|
|
|
|
const char *s)
|
|
|
|
{
|
|
|
|
int 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);
|
|
|
|
}
|