Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
Rishabh Gupta
purr-data
Commits
330f8635
Commit
330f8635
authored
Jun 10, 2016
by
Jonathan Wilkes
Browse files
add changes to windows filename handling that were accidentally left off the Pd Vanilla backport
parent
09baf869
Changes
2
Hide whitespace changes
Inline
Side-by-side
pd/src/s_utf8.c
View file @
330f8635
...
...
@@ -18,15 +18,17 @@
#include <stdio.h>
#include <string.h>
#include <stdarg.h>
#ifdef WIN32
#include <malloc.h>
#ifdef _WIN32
# include <malloc.h>
/* MSVC or mingw on windows */
#elif defined(__linux__) || defined(__APPLE__)
# include <alloca.h>
/* linux, mac, mingw, cygwin */
#else
#include <
alloca.h>
#
include <
stdlib.h>
/* BSDs for example */
#endif
#include "s_utf8.h"
static
const
u
_
int32_t
offsetsFromUTF8
[
6
]
=
{
static
const
uint32_t
offsetsFromUTF8
[
6
]
=
{
0x00000000UL
,
0x00003080UL
,
0x000E2080UL
,
0x03C82080UL
,
0xFA082080UL
,
0x82082080UL
};
...
...
@@ -59,9 +61,9 @@ int u8_seqlen(char *s)
for all the characters.
if sz = srcsz+1 (i.e. 4*srcsz+4 bytes), there will always be enough space.
*/
int
u8_toucs
(
u
_
int
32
_t
*
dest
,
int
sz
,
char
*
src
,
int
srcsz
)
int
u8_
utf8
toucs
2
(
uint
16
_t
*
dest
,
int
sz
,
char
*
src
,
int
srcsz
)
{
u
_
int
32
_t
ch
;
uint
16
_t
ch
;
char
*
src_end
=
src
+
srcsz
;
int
nb
;
int
i
=
0
;
...
...
@@ -79,10 +81,6 @@ int u8_toucs(u_int32_t *dest, int sz, char *src, int srcsz)
ch
=
0
;
switch
(
nb
)
{
/* these fall through deliberately */
#if UTF8_SUPPORT_FULL_UCS4
case
5
:
ch
+=
(
unsigned
char
)
*
src
++
;
ch
<<=
6
;
case
4
:
ch
+=
(
unsigned
char
)
*
src
++
;
ch
<<=
6
;
#endif
case
3
:
ch
+=
(
unsigned
char
)
*
src
++
;
ch
<<=
6
;
case
2
:
ch
+=
(
unsigned
char
)
*
src
++
;
ch
<<=
6
;
case
1
:
ch
+=
(
unsigned
char
)
*
src
++
;
ch
<<=
6
;
...
...
@@ -108,9 +106,9 @@ int u8_toucs(u_int32_t *dest, int sz, char *src, int srcsz)
the NUL as well.
the destination string will never be bigger than the source string.
*/
int
u8_toutf8
(
char
*
dest
,
int
sz
,
u
_
int
32
_t
*
src
,
int
srcsz
)
int
u8_
ucs2
toutf8
(
char
*
dest
,
int
sz
,
uint
16
_t
*
src
,
int
srcsz
)
{
u
_
int
32
_t
ch
;
uint
16
_t
ch
;
int
i
=
0
;
char
*
dest_end
=
dest
+
sz
;
...
...
@@ -127,21 +125,13 @@ int u8_toutf8(char *dest, int sz, u_int32_t *src, int srcsz)
*
dest
++
=
(
ch
>>
6
)
|
0xC0
;
*
dest
++
=
(
ch
&
0x3F
)
|
0x80
;
}
else
if
(
ch
<
0x10000
)
{
else
{
if
(
dest
>=
dest_end
-
2
)
return
i
;
*
dest
++
=
(
ch
>>
12
)
|
0xE0
;
*
dest
++
=
((
ch
>>
6
)
&
0x3F
)
|
0x80
;
*
dest
++
=
(
ch
&
0x3F
)
|
0x80
;
}
else
if
(
ch
<
0x110000
)
{
if
(
dest
>=
dest_end
-
3
)
return
i
;
*
dest
++
=
(
ch
>>
18
)
|
0xF0
;
*
dest
++
=
((
ch
>>
12
)
&
0x3F
)
|
0x80
;
*
dest
++
=
((
ch
>>
6
)
&
0x3F
)
|
0x80
;
*
dest
++
=
(
ch
&
0x3F
)
|
0x80
;
}
i
++
;
}
if
(
dest
<
dest_end
)
...
...
@@ -150,21 +140,16 @@ int u8_toutf8(char *dest, int sz, u_int32_t *src, int srcsz)
}
/* moo: get byte length of character number, or 0 if not supported */
int
u8_wc_nbytes
(
u
_
int32_t
ch
)
int
u8_wc_nbytes
(
uint32_t
ch
)
{
if
(
ch
<
0x80
)
return
1
;
if
(
ch
<
0x800
)
return
2
;
if
(
ch
<
0x10000
)
return
3
;
if
(
ch
<
0x200000
)
return
4
;
#if UTF8_SUPPORT_FULL_UCS4
/*-- moo: support full UCS-4 range? --*/
if
(
ch
<
0x4000000
)
return
5
;
if
(
ch
<
0x7fffffffUL
)
return
6
;
#endif
return
0
;
/*-- bad input --*/
}
int
u8_wc_toutf8
(
char
*
dest
,
u
_
int32_t
ch
)
int
u8_wc_toutf8
(
char
*
dest
,
uint32_t
ch
)
{
if
(
ch
<
0x80
)
{
dest
[
0
]
=
(
char
)
ch
;
...
...
@@ -192,7 +177,7 @@ int u8_wc_toutf8(char *dest, u_int32_t ch)
}
/*-- moo --*/
int
u8_wc_toutf8_nul
(
char
*
dest
,
u
_
int32_t
ch
)
int
u8_wc_toutf8_nul
(
char
*
dest
,
uint32_t
ch
)
{
int
sz
=
u8_wc_toutf8
(
dest
,
ch
);
dest
[
sz
]
=
'\0'
;
...
...
@@ -230,12 +215,12 @@ int u8_charnum(char *s, int offset)
char
*
const
end
=
string
+
offset
;
while
(
string
<
end
&&
*
string
!=
'\0'
)
{
if
(
*
string
++
&
0x80
&&
string
!=
end
)
{
if
(
string
<
end
&&
!
isutf
(
*
string
))
{
if
(
*
string
++
&
0x80
)
{
if
(
!
isutf
(
*
string
))
{
++
string
;
if
(
string
<
end
&&
!
isutf
(
*
string
))
{
if
(
!
isutf
(
*
string
))
{
++
string
;
if
(
string
<
end
&&
!
isutf
(
*
string
))
{
if
(
!
isutf
(
*
string
))
{
++
string
;
}
}
...
...
@@ -247,9 +232,9 @@ int u8_charnum(char *s, int offset)
}
/* reads the next utf-8 sequence out of a string, updating an index */
u
_
int32_t
u8_nextchar
(
char
*
s
,
int
*
i
)
uint32_t
u8_nextchar
(
char
*
s
,
int
*
i
)
{
u
_
int32_t
ch
=
0
;
uint32_t
ch
=
0
;
int
sz
=
0
;
do
{
...
...
@@ -295,16 +280,3 @@ void u8_dec(char *s, int *i)
isutf
(
s
[
--
(
*
i
)])
||
--
(
*
i
));
}
/*-- moo --*/
void
u8_inc_ptr
(
char
**
sp
)
{
(
void
)(
isutf
(
*
(
++
(
*
sp
)))
||
isutf
(
*
(
++
(
*
sp
)))
||
isutf
(
*
(
++
(
*
sp
)))
||
++
(
*
sp
));
}
/*-- moo --*/
void
u8_dec_ptr
(
char
**
sp
)
{
(
void
)(
isutf
(
*
(
--
(
*
sp
)))
||
isutf
(
*
(
--
(
*
sp
)))
||
isutf
(
*
(
--
(
*
sp
)))
||
--
(
*
sp
));
}
pd/src/s_utf8.h
View file @
330f8635
#ifndef S_UTF8_H
#define S_UTF8_H
/*--moo--*/
#ifndef u_int32_t
# define u_int32_t unsigned int
#endif
#include "m_pd.h"
#ifndef UCS4
# define UCS4 u
_
int32_t
# define UCS4 uint32_t
#endif
/* UTF8_SUPPORT_FULL_UCS4
...
...
@@ -20,7 +17,7 @@
/* UTF8_MAXBYTES
* maximum number of bytes required to represent a single character in UTF-8
*
* UTF8_MAXBYTES1 = UTF8_MAXBYTES+1
* UTF8_MAXBYTES1 = UTF8_MAXBYTES+1
* maximum bytes per character including NUL terminator
*/
#ifdef UTF8_SUPPORT_FULL_UCS4
...
...
@@ -43,23 +40,23 @@
/* is c the start of a utf8 sequence? */
#define isutf(c) (((c)&0xC0)!=0x80)
/* convert UTF-8 data to wide character */
int
u8_toucs
(
u
_
int
32
_t
*
dest
,
int
sz
,
char
*
src
,
int
srcsz
);
/* convert UTF-8 data to
UCS-2
wide character */
int
u8_
utf8
toucs
2
(
uint
16
_t
*
dest
,
int
sz
,
char
*
src
,
int
srcsz
);
/* the opposite conversion */
int
u8_toutf8
(
char
*
dest
,
int
sz
,
u
_
int
32
_t
*
src
,
int
srcsz
);
int
u8_
ucs2
toutf8
(
char
*
dest
,
int
sz
,
uint
16
_t
*
src
,
int
srcsz
);
/* moo: get byte length of character number, or 0 if not supported */
int
u8_wc_nbytes
(
u
_
int32_t
ch
);
int
u8_wc_nbytes
(
uint32_t
ch
);
/* moo: compute required storage for UTF-8 encoding of 's[0..n-1]' */
int
u8_wcs_nbytes
(
u
_
int32_t
*
ucs
,
int
size
);
int
u8_wcs_nbytes
(
uint32_t
*
ucs
,
int
size
);
/* single character to UTF-8, no NUL termination */
int
u8_wc_toutf8
(
char
*
dest
,
u
_
int32_t
ch
);
int
u8_wc_toutf8
(
char
*
dest
,
uint32_t
ch
);
/* moo: single character to UTF-8, with NUL termination */
int
u8_wc_toutf8_nul
(
char
*
dest
,
u
_
int32_t
ch
);
int
u8_wc_toutf8_nul
(
char
*
dest
,
uint32_t
ch
);
/* character number to byte offset */
int
u8_offset
(
char
*
str
,
int
charnum
);
...
...
@@ -68,7 +65,7 @@ int u8_offset(char *str, int charnum);
int
u8_charnum
(
char
*
s
,
int
offset
);
/* return next character, updating an index variable */
u
_
int32_t
u8_nextchar
(
char
*
s
,
int
*
i
);
uint32_t
u8_nextchar
(
char
*
s
,
int
*
i
);
/* move to next character */
void
u8_inc
(
char
*
s
,
int
*
i
);
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment