qiurui
/
glibc
mirror of git://sourceware.org/git/glibc.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

iconv: make utf-7.c able to use variants 

Add infrastructure in utf-7.c to handle variants. The approach comes from
iso646.c
The variant is defined at gconv_init time and is passed as a
supplementary variable.

Signed-off-by: Max Gautier <mg@max.gautier.name>
Reviewed-by: Adhemerval Zanella  <adhemerval.zanella@linaro.org>
This commit is contained in:
Max Gautier 2022-03-21 09:12:05 -03:00 committed by Adhemerval Zanella
parent 09abb567a9
commit ef7b963280
1 changed files with 172 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

234
iconvdata/utf-7.c
View File

@ -27,8 +27,27 @@
#include <gconv.h> #include <gconv.h>
#include <stdint.h> #include <stdint.h>
#include <stdlib.h> #include <stdlib.h>
#include <string.h>
enum variant
{
UTF7,
};
/* Must be in the same order as enum variant above. */
static const char names[] =
"UTF-7//\0"
"\0";
static uint32_t
shift_character (enum variant const var)
{
if (var == UTF7)
return '+';
else
abort ();
}
static bool static bool
between (uint32_t const ch, between (uint32_t const ch,
@ -42,30 +61,38 @@ between (uint32_t const ch,
*/ */
static bool static bool
isdirect (uint32_t ch) isdirect (uint32_t ch, enum variant var)
{ {
return (between (ch, 'A', 'Z') if (var == UTF7)
|| between (ch, 'a', 'z') return (between (ch, 'A', 'Z')
|| between (ch, '0', '9') || between (ch, 'a', 'z')
|| ch == '\'' || ch == '(' || ch == ')' || between (ch, '0', '9')
|| between (ch, ',', '/') || ch == '\'' || ch == '(' || ch == ')'
|| ch == ':' || ch == '?' || between (ch, ',', '/')
|| ch == ' ' || ch == '\t' || ch == '\n' || ch == '\r'); || ch == ':' || ch == '?'
|| ch == ' ' || ch == '\t' || ch == '\n' || ch == '\r');
abort ();
} }
/* The set of "direct and optional direct characters": /* The set of "direct and optional direct characters":
A-Z a-z 0-9 ' ( ) , - . / : ? space tab lf cr A-Z a-z 0-9 ' ( ) , - . / : ? space tab lf cr
(UTF-7 only)
! " # $ % & * ; < = > @ [ ] ^ _ ` { | } ! " # $ % & * ; < = > @ [ ] ^ _ ` { | }
*/ */
static bool static bool
isxdirect (uint32_t ch) isxdirect (uint32_t ch, enum variant var)
{ {
return (ch == '\t' if (isdirect (ch, var))
|| ch == '\n' return true;
|| ch == '\r' if (var != UTF7)
|| (between (ch, ' ', '}') && ch != '+' && ch != '\\')); return false;
return between (ch, '!', '&')
|| ch == '*'
|| between (ch, ';', '@')
|| (between (ch, '[', '`') && ch != '\\')
|| between (ch, '{', '}');
} }
@ -85,7 +112,7 @@ needs_explicit_shift (uint32_t ch)
/* Converts a value in the range 0..63 to a base64 encoded char. */ /* Converts a value in the range 0..63 to a base64 encoded char. */
static unsigned char static unsigned char
base64 (unsigned int i) base64 (unsigned int i, enum variant var)
{ {
if (i < 26) if (i < 26)
return i + 'A'; return i + 'A';
@ -95,7 +122,7 @@ base64 (unsigned int i)
return i - 52 + '0'; return i - 52 + '0';
else if (i == 62) else if (i == 62)
return '+'; return '+';
else if (i == 63) else if (i == 63 && var == UTF7)
return '/'; return '/';
else else
abort (); abort ();
@ -103,9 +130,8 @@ base64 (unsigned int i)
/* Definitions used in the body of the `gconv' function. */ /* Definitions used in the body of the `gconv' function. */
#define CHARSET_NAME "UTF-7//" #define DEFINE_INIT 0
#define DEFINE_INIT 1 #define DEFINE_FINI 0
#define DEFINE_FINI 1
#define FROM_LOOP from_utf7_loop #define FROM_LOOP from_utf7_loop
#define TO_LOOP to_utf7_loop #define TO_LOOP to_utf7_loop
#define MIN_NEEDED_FROM 1 #define MIN_NEEDED_FROM 1
@ -113,12 +139,28 @@ base64 (unsigned int i)
#define MIN_NEEDED_TO 4 #define MIN_NEEDED_TO 4
#define MAX_NEEDED_TO 4 #define MAX_NEEDED_TO 4
#define ONE_DIRECTION 0 #define ONE_DIRECTION 0
#define FROM_DIRECTION (dir == from_utf7)
#define PREPARE_LOOP \ #define PREPARE_LOOP \
mbstate_t saved_state; \ mbstate_t saved_state; \
mbstate_t *statep = data->__statep; mbstate_t *statep = data->__statep; \
#define EXTRA_LOOP_ARGS , statep enum direction dir = ((struct utf7_data *) step->__data)->dir; \
enum direction var = ((struct utf7_data *) step->__data)->var;
#define EXTRA_LOOP_ARGS , statep, var
enum direction
{
illegal_dir,
from_utf7,
to_utf7
};
struct utf7_data
{
enum direction dir;
enum variant var;
};
/* Since we might have to reset input pointer we must be able to save /* Since we might have to reset input pointer we must be able to save
and restore the state. */ and restore the state. */
#define SAVE_RESET_STATE(Save) \ #define SAVE_RESET_STATE(Save) \
@ -127,6 +169,70 @@ base64 (unsigned int i)
else \ else \
*statep = saved_state *statep = saved_state
int
gconv_init (struct __gconv_step *step)
{
/* Determine which direction. */
struct utf7_data *new_data;
enum direction dir = illegal_dir;
enum variant var = 0;
for (const char *name = names; *name != '\0';
name = __rawmemchr (name, '\0') + 1)
{
if (__strcasecmp (step->__from_name, name) == 0)
{
dir = from_utf7;
break;
}
else if (__strcasecmp (step->__to_name, name) == 0)
{
dir = to_utf7;
break;
}
++var;
}
if (__glibc_likely (dir != illegal_dir))
{
new_data = malloc (sizeof (*new_data));
if (new_data == NULL)
return __GCONV_NOMEM;
new_data->dir = dir;
new_data->var = var;
step->__data = new_data;
if (dir == from_utf7)
{
step->__min_needed_from = MIN_NEEDED_FROM;
step->__max_needed_from = MAX_NEEDED_FROM;
step->__min_needed_to = MIN_NEEDED_TO;
step->__max_needed_to = MAX_NEEDED_TO;
}
else
{
step->__min_needed_from = MIN_NEEDED_TO;
step->__max_needed_from = MAX_NEEDED_TO;
step->__min_needed_to = MIN_NEEDED_FROM;
step->__max_needed_to = MAX_NEEDED_FROM;
}
}
else
return __GCONV_NOCONV;
step->__stateful = 1;
return __GCONV_OK;
}
void
gconv_end (struct __gconv_step *data)
{
free (data->__data);
}
/* First define the conversion function from UTF-7 to UCS4. /* First define the conversion function from UTF-7 to UCS4.
The state is structured as follows: The state is structured as follows:
@ -154,13 +260,13 @@ base64 (unsigned int i)
if ((statep->__count >> 3) == 0) \ if ((statep->__count >> 3) == 0) \
{ \ { \
/* base64 encoding inactive. */ \ /* base64 encoding inactive. */ \
if (isxdirect (ch)) \ if (isxdirect (ch, var)) \
{ \ { \
inptr++; \ inptr++; \
put32 (outptr, ch); \ put32 (outptr, ch); \
outptr += 4; \ outptr += 4; \
} \ } \
else if (__glibc_likely (ch == '+')) \ else if (__glibc_likely (ch == shift_character (var))) \
{ \ { \
if (__glibc_unlikely (inptr + 2 > inend)) \ if (__glibc_unlikely (inptr + 2 > inend)) \
{ \ { \
@ -285,7 +391,7 @@ base64 (unsigned int i)
} \ } \
} }
#define LOOP_NEED_FLAGS #define LOOP_NEED_FLAGS
#define EXTRA_LOOP_DECLS , mbstate_t *statep #define EXTRA_LOOP_DECLS , mbstate_t *statep, enum variant var
#include <iconv/loop.c> #include <iconv/loop.c>
@ -316,7 +422,7 @@ base64 (unsigned int i)
if ((statep->__count & 0x18) == 0) \ if ((statep->__count & 0x18) == 0) \
{ \ { \
/* base64 encoding inactive */ \ /* base64 encoding inactive */ \
if (isdirect (ch)) \ if (isdirect (ch, var)) \
{ \ { \
*outptr++ = (unsigned char) ch; \ *outptr++ = (unsigned char) ch; \
} \ } \
@ -324,7 +430,7 @@ base64 (unsigned int i)
{ \ { \
size_t count; \ size_t count; \
\ \
if (ch == '+') \ if (ch == shift_character (var)) \
count = 2; \ count = 2; \
else if (ch < 0x10000) \ else if (ch < 0x10000) \
count = 3; \ count = 3; \
@ -339,13 +445,13 @@ base64 (unsigned int i)
break; \ break; \
} \ } \
\ \
*outptr++ = '+'; \ *outptr++ = shift_character (var); \
if (ch == '+') \ if (ch == shift_character (var)) \
*outptr++ = '-'; \ *outptr++ = '-'; \
else if (ch < 0x10000) \ else if (ch < 0x10000) \
{ \ { \
*outptr++ = base64 (ch >> 10); \ *outptr++ = base64 (ch >> 10, var); \
*outptr++ = base64 ((ch >> 4) & 0x3f); \ *outptr++ = base64 ((ch >> 4) & 0x3f, var); \
statep->__count = ((ch & 15) << 5) | (3 << 3); \ statep->__count = ((ch & 15) << 5) | (3 << 3); \
} \ } \
else if (ch < 0x110000) \ else if (ch < 0x110000) \
@ -354,11 +460,11 @@ base64 (unsigned int i)
uint32_t ch2 = 0xdc00 + ((ch - 0x10000) & 0x3ff); \ uint32_t ch2 = 0xdc00 + ((ch - 0x10000) & 0x3ff); \
\ \
ch = (ch1 << 16) | ch2; \ ch = (ch1 << 16) | ch2; \
*outptr++ = base64 (ch >> 26); \ *outptr++ = base64 (ch >> 26, var); \
*outptr++ = base64 ((ch >> 20) & 0x3f); \ *outptr++ = base64 ((ch >> 20) & 0x3f, var); \
*outptr++ = base64 ((ch >> 14) & 0x3f); \ *outptr++ = base64 ((ch >> 14) & 0x3f, var); \
*outptr++ = base64 ((ch >> 8) & 0x3f); \ *outptr++ = base64 ((ch >> 8) & 0x3f, var); \
*outptr++ = base64 ((ch >> 2) & 0x3f); \ *outptr++ = base64 ((ch >> 2) & 0x3f, var); \
statep->__count = ((ch & 3) << 7) | (2 << 3); \ statep->__count = ((ch & 3) << 7) | (2 << 3); \
} \ } \
else \ else \
@ -368,7 +474,7 @@ base64 (unsigned int i)
else \ else \
{ \ { \
/* base64 encoding active */ \ /* base64 encoding active */ \
if (isdirect (ch)) \ if (isdirect (ch, var)) \
{ \ { \
/* deactivate base64 encoding */ \ /* deactivate base64 encoding */ \
size_t count; \ size_t count; \
@ -382,7 +488,7 @@ base64 (unsigned int i)
} \ } \
\ \
if ((statep->__count & 0x18) >= 0x10) \ if ((statep->__count & 0x18) >= 0x10) \
*outptr++ = base64 ((statep->__count >> 3) & ~3); \ *outptr++ = base64 ((statep->__count >> 3) & ~3, var); \
if (needs_explicit_shift (ch)) \ if (needs_explicit_shift (ch)) \
*outptr++ = '-'; \ *outptr++ = '-'; \
*outptr++ = (unsigned char) ch; \ *outptr++ = (unsigned char) ch; \
@ -410,22 +516,24 @@ base64 (unsigned int i)
switch ((statep->__count >> 3) & 3) \ switch ((statep->__count >> 3) & 3) \
{ \ { \
case 1: \ case 1: \
*outptr++ = base64 (ch >> 10); \ *outptr++ = base64 (ch >> 10, var); \
*outptr++ = base64 ((ch >> 4) & 0x3f); \ *outptr++ = base64 ((ch >> 4) & 0x3f, var); \
statep->__count = ((ch & 15) << 5) | (3 << 3); \ statep->__count = ((ch & 15) << 5) | (3 << 3); \
break; \ break; \
case 2: \ case 2: \
*outptr++ = \ *outptr++ = \
base64 (((statep->__count >> 3) & ~3) | (ch >> 12)); \ base64 (((statep->__count >> 3) & ~3) | (ch >> 12), \
*outptr++ = base64 ((ch >> 6) & 0x3f); \ var); \
*outptr++ = base64 (ch & 0x3f); \ *outptr++ = base64 ((ch >> 6) & 0x3f, var); \
*outptr++ = base64 (ch & 0x3f, var); \
statep->__count = (1 << 3); \ statep->__count = (1 << 3); \
break; \ break; \
case 3: \ case 3: \
*outptr++ = \ *outptr++ = \
base64 (((statep->__count >> 3) & ~3) | (ch >> 14)); \ base64 (((statep->__count >> 3) & ~3) | (ch >> 14), \
*outptr++ = base64 ((ch >> 8) & 0x3f); \ var); \
*outptr++ = base64 ((ch >> 2) & 0x3f); \ *outptr++ = base64 ((ch >> 8) & 0x3f, var); \
*outptr++ = base64 ((ch >> 2) & 0x3f, var); \
statep->__count = ((ch & 3) << 7) | (2 << 3); \ statep->__count = ((ch & 3) << 7) | (2 << 3); \
break; \ break; \
default: \ default: \
@ -441,30 +549,32 @@ base64 (unsigned int i)
switch ((statep->__count >> 3) & 3) \ switch ((statep->__count >> 3) & 3) \
{ \ { \
case 1: \ case 1: \
*outptr++ = base64 (ch >> 26); \ *outptr++ = base64 (ch >> 26, var); \
*outptr++ = base64 ((ch >> 20) & 0x3f); \ *outptr++ = base64 ((ch >> 20) & 0x3f, var); \
*outptr++ = base64 ((ch >> 14) & 0x3f); \ *outptr++ = base64 ((ch >> 14) & 0x3f, var); \
*outptr++ = base64 ((ch >> 8) & 0x3f); \ *outptr++ = base64 ((ch >> 8) & 0x3f, var); \
*outptr++ = base64 ((ch >> 2) & 0x3f); \ *outptr++ = base64 ((ch >> 2) & 0x3f, var); \
statep->__count = ((ch & 3) << 7) | (2 << 3); \ statep->__count = ((ch & 3) << 7) | (2 << 3); \
break; \ break; \
case 2: \ case 2: \
*outptr++ = \ *outptr++ = \
base64 (((statep->__count >> 3) & ~3) | (ch >> 28)); \ base64 (((statep->__count >> 3) & ~3) | (ch >> 28), \
*outptr++ = base64 ((ch >> 22) & 0x3f); \ var); \
*outptr++ = base64 ((ch >> 16) & 0x3f); \ *outptr++ = base64 ((ch >> 22) & 0x3f, var); \
*outptr++ = base64 ((ch >> 10) & 0x3f); \ *outptr++ = base64 ((ch >> 16) & 0x3f, var); \
*outptr++ = base64 ((ch >> 4) & 0x3f); \ *outptr++ = base64 ((ch >> 10) & 0x3f, var); \
*outptr++ = base64 ((ch >> 4) & 0x3f, var); \
statep->__count = ((ch & 15) << 5) | (3 << 3); \ statep->__count = ((ch & 15) << 5) | (3 << 3); \
break; \ break; \
case 3: \ case 3: \
*outptr++ = \ *outptr++ = \
base64 (((statep->__count >> 3) & ~3) | (ch >> 30)); \ base64 (((statep->__count >> 3) & ~3) | (ch >> 30), \
*outptr++ = base64 ((ch >> 24) & 0x3f); \ var); \
*outptr++ = base64 ((ch >> 18) & 0x3f); \ *outptr++ = base64 ((ch >> 24) & 0x3f, var); \
*outptr++ = base64 ((ch >> 12) & 0x3f); \ *outptr++ = base64 ((ch >> 18) & 0x3f, var); \
*outptr++ = base64 ((ch >> 6) & 0x3f); \ *outptr++ = base64 ((ch >> 12) & 0x3f, var); \
*outptr++ = base64 (ch & 0x3f); \ *outptr++ = base64 ((ch >> 6) & 0x3f, var); \
*outptr++ = base64 (ch & 0x3f, var); \
statep->__count = (1 << 3); \ statep->__count = (1 << 3); \
break; \ break; \
default: \ default: \
@ -480,7 +590,7 @@ base64 (unsigned int i)
inptr += 4; \ inptr += 4; \
} }
#define LOOP_NEED_FLAGS #define LOOP_NEED_FLAGS
#define EXTRA_LOOP_DECLS , mbstate_t *statep #define EXTRA_LOOP_DECLS , mbstate_t *statep, enum variant var
#include <iconv/loop.c> #include <iconv/loop.c>
@ -510,7 +620,7 @@ base64 (unsigned int i)
{ \ { \
/* Write out the shift sequence. */ \ /* Write out the shift sequence. */ \
if ((state & 0x18) >= 0x10) \ if ((state & 0x18) >= 0x10) \
*outbuf++ = base64 ((state >> 3) & ~3); \ *outbuf++ = base64 ((state >> 3) & ~3, var); \
*outbuf++ = '-'; \ *outbuf++ = '-'; \
\ \
data->__statep->__count = 0; \ data->__statep->__count = 0; \