Hi!
The following patch adds on top of the just posted #embed patch
a first extension, gnu::offset which allows to seek in the data
file (for seekable files, otherwise read and throw away).
I think this is useful e.g. when some binary data start with
some well known header which shouldn't be included in the data etc.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
2024-06-18 Jakub Jelinek <ja...@redhat.com>
libcpp/
* internal.h (struct cpp_embed_params): Add offset member.
* directives.cc (_cpp_parse_embed_params): Parse gnu::offset
parameter.
* files.cc (struct _cpp_file): Add offset member.
(_cpp_stack_embed): Handle params->offset.
gcc/
* doc/cpp.texi (Binary Resource Inclusion): Document gnu::offset
#embed parameter.
gcc/testsuite/
* c-c++-common/cpp/embed-15.c: New test.
* c-c++-common/cpp/embed-16.c: New test.
* gcc.dg/cpp/embed-5.c: New test.
--- libcpp/internal.h.jj 2024-06-18 08:37:55.759488622 +0200
+++ libcpp/internal.h 2024-06-18 08:38:39.355915868 +0200
@@ -630,7 +630,7 @@ struct cpp_embed_params
{
location_t loc;
bool has_embed;
- cpp_num_part limit;
+ cpp_num_part limit, offset;
cpp_embed_params_tokens prefix, suffix, if_empty;
};
--- libcpp/directives.cc.jj 2024-06-18 08:37:55.767488517 +0200
+++ libcpp/directives.cc 2024-06-18 11:32:05.073768407 +0200
@@ -1102,6 +1102,21 @@ _cpp_parse_embed_params (cpp_reader *pfi
break;
}
}
+ else if (param_prefix_len == 3 && memcmp (param_prefix, "gnu", 3) == 0)
+ {
+ struct { int len; const char *name; } gnu_params[] = {
+ { 6, "offset" }
+ };
+ for (size_t i = 0;
+ i < sizeof (gnu_params) / sizeof (gnu_params[0]); ++i)
+ if (param_name_len == gnu_params[i].len
+ && memcmp (param_name, gnu_params[i].name,
+ param_name_len) == 0)
+ {
+ param_kind = 4 + i;
+ break;
+ }
+ }
if (param_kind != (size_t) -1)
{
if ((seen & (1 << param_kind)) == 0)
@@ -1130,11 +1145,21 @@ _cpp_parse_embed_params (cpp_reader *pfi
if (param_kind != (size_t) -1 && token->type != CPP_OPEN_PAREN)
cpp_error_with_line (pfile, CPP_DL_ERROR, loc, 0,
"expected '('");
- else if (param_kind == 0)
+ else if (param_kind == 0 || param_kind == 4)
{
if (params->has_embed && pfile->op_stack == NULL)
_cpp_expand_op_stack (pfile);
- params->limit = _cpp_parse_expr (pfile, "#embed", token);
+ cpp_num_part res = _cpp_parse_expr (pfile, "#embed", token);
+ if (param_kind == 0)
+ params->limit = res;
+ else
+ {
+ if (res > INTTYPE_MAXIMUM (off_t))
+ cpp_error_with_line (pfile, CPP_DL_ERROR, loc, 0,
+ "too large 'gnu::offset' argument");
+ else
+ params->offset = res;
+ }
token = _cpp_get_token_no_padding (pfile);
}
else if (token->type == CPP_OPEN_PAREN)
--- libcpp/files.cc.jj 2024-06-18 11:24:24.598781748 +0200
+++ libcpp/files.cc 2024-06-18 11:31:42.238066309 +0200
@@ -90,6 +90,9 @@ struct _cpp_file
/* Size for #embed, perhaps smaller than st.st_size. */
size_t limit;
+ /* Offset for #embed. */
+ off_t offset;
+
/* File descriptor. Invalid if -1, otherwise open. */
int fd;
@@ -1243,8 +1246,11 @@ _cpp_stack_embed (cpp_reader *pfile, con
_cpp_file *orig_file = file;
if (file->buffer_valid
&& (!S_ISREG (file->st.st_mode)
- || (file->limit < file->st.st_size + (size_t) 0
- && file->limit < params->limit)))
+ || file->offset + (cpp_num_part) 0 > params->offset
+ || (file->limit < file->st.st_size - file->offset + (size_t) 0
+ && (params->offset - file->offset > (cpp_num_part) file->limit
+ || file->limit - (params->offset
+ - file->offset) < params->limit))))
{
bool found = false;
if (S_ISREG (file->st.st_mode))
@@ -1257,8 +1263,13 @@ _cpp_stack_embed (cpp_reader *pfile, con
&& strcmp (file->path, file->next_file->path) == 0)
{
file = file->next_file;
- if (file->limit >= file->st.st_size + (size_t) 0
- || file->limit >= params->limit)
+ if (file->offset + (cpp_num_part) 0 <= params->offset
+ && (file->limit >= (file->st.st_size - file->offset
+ + (size_t) 0)
+ || (params->offset
+ - file->offset <= (cpp_num_part) file->limit
+ && file->limit - (params->offset
+ - file->offset) >= params->limit)))
{
found = true;
break;
@@ -1314,8 +1325,10 @@ _cpp_stack_embed (cpp_reader *pfile, con
if (regular)
{
cpp_num_part limit;
- if (file->st.st_size + (cpp_num_part) 0 < params->limit)
- limit = file->st.st_size;
+ if (file->st.st_size + (cpp_num_part) 0 < params->offset)
+ limit = 0;
+ else if (file->st.st_size - params->offset < params->limit)
+ limit = file->st.st_size - params->offset;
else
limit = params->limit;
if (params->has_embed)
@@ -1326,6 +1339,14 @@ _cpp_stack_embed (cpp_reader *pfile, con
"%s is too large", file->path);
goto fail;
}
+ if (lseek (file->fd, params->offset, SEEK_CUR)
+ != (off_t) params->offset)
+ {
+ cpp_errno_filename (pfile, CPP_DL_ERROR, file->path,
+ params->loc);
+ goto fail;
+ }
+ file->offset = params->offset;
file->limit = limit;
size = limit;
}
@@ -1338,6 +1359,38 @@ _cpp_stack_embed (cpp_reader *pfile, con
buf = XNEWVEC (uchar, size ? size : 1);
total = 0;
+ if (!regular && params->offset)
+ {
+ uchar *buf2 = buf;
+ ssize_t size2 = size;
+ cpp_num_part total2 = params->offset;
+
+ if (params->offset > 8 * 1024 && size < 8 * 1024)
+ {
+ size2 = 32 * 1024;
+ buf2 = XNEWVEC (uchar, size2);
+ }
+ do
+ {
+ if ((cpp_num_part) size2 > total2)
+ size2 = total2;
+ count = read (file->fd, buf2, size2);
+ if (count < 0)
+ {
+ cpp_errno_filename (pfile, CPP_DL_ERROR, file->path,
+ params->loc);
+ if (buf2 != buf)
+ free (buf2);
+ free (buf);
+ goto fail;
+ }
+ total2 -= count;
+ }
+ while (total2);
+ if (buf2 != buf)
+ free (buf2);
+ }
+
while ((count = read (file->fd, buf + total, size - total)) > 0)
{
total += count;
@@ -1378,7 +1431,10 @@ _cpp_stack_embed (cpp_reader *pfile, con
file->limit = total;
}
else if (!regular)
- file->limit = total;
+ {
+ file->offset = params->offset;
+ file->limit = total;
+ }
file->buffer_start = buf;
file->buffer = buf;
@@ -1387,9 +1443,22 @@ _cpp_stack_embed (cpp_reader *pfile, con
file->fd = -1;
}
else if (params->has_embed)
- return file->limit && params->limit ? 1 : 2;
+ {
+ if (params->offset - file->offset > file->limit)
+ return 2;
+ size_t limit = file->limit - (params->offset - file->offset);
+ return limit && params->limit ? 1 : 2;
+ }
+ const uchar *buffer = file->buffer;
size_t limit = file->limit;
+ if (params->offset - file->offset > limit)
+ limit = 0;
+ else
+ {
+ buffer += params->offset - file->offset;
+ limit -= params->offset - file->offset;
+ }
if (params->limit < limit)
limit = params->limit;
@@ -1413,20 +1482,20 @@ _cpp_stack_embed (cpp_reader *pfile, con
size_t len = 0;
for (size_t i = 0; i < limit; ++i)
{
- if (file->buffer[i] < 10)
+ if (buffer[i] < 10)
len += 2;
- else if (file->buffer[i] < 100)
+ else if (buffer[i] < 100)
len += 3;
#if UCHAR_MAX == 255
else
len += 4;
#else
- else if (file->buffer[i] < 1000)
+ else if (buffer[i] < 1000)
len += 4;
else
{
char buf[64];
- len += sprintf (buf, "%d", file->buffer[i]) + 1;
+ len += sprintf (buf, "%d", buffer[i]) + 1;
}
#endif
if (len > INTTYPE_MAXIMUM (ssize_t))
@@ -1480,7 +1549,7 @@ _cpp_stack_embed (cpp_reader *pfile, con
if (i == 0)
tok->flags |= PREV_WHITE;
tok->val.str.text = s;
- tok->val.str.len = sprintf ((char *) s, "%d", file->buffer[i]);
+ tok->val.str.len = sprintf ((char *) s, "%d", buffer[i]);
s += tok->val.str.len + 1;
if (tok == &pfile->directive_result)
tok = toks;
--- gcc/doc/cpp.texi.jj 2024-06-18 16:56:16.000000000 +0200
+++ gcc/doc/cpp.texi 2024-06-18 18:04:17.384265373 +0200
@@ -3966,8 +3966,8 @@ treated the same), followed by parameter
with currently supported standard parameters @code{limit}, @code{prefix},
@code{suffix} and @code{if_empty}, or implementation defined parameters
specified by a unique vendor prefix followed by @code{::} followed by
-name of the parameter. GCC will use the @code{gnu} prefix but currently
-doesn't support any extensions.
+name of the parameter. GCC uses the @code{gnu} prefix for vendor
+parameters and currently supports the @code{gnu::offset} parameter.
The @code{limit} parameter argument is a constant expression which
specifies the maximum number of bytes included by the directive,
@@ -3977,6 +3977,10 @@ that sequence is not empty and @code{if_
sequence which is used as expansion for @code{#embed} directive if the
resource is empty.
+The @code{gnu::offset} parameter argument is a constant expression
+which specifies how many bytes to skip from the start of the resource.
+@code{limit} is then counted from that position.
+
The @code{#embed} directive is not supported in the Traditional Mode
(@pxref{Traditional Mode}).
--- gcc/testsuite/c-c++-common/cpp/embed-15.c.jj 2024-06-18
12:15:42.157715550 +0200
+++ gcc/testsuite/c-c++-common/cpp/embed-15.c 2024-06-18 12:49:07.726616236
+0200
@@ -0,0 +1,88 @@
+/* { dg-do run } */
+/* { dg-options "--embed-dir=${srcdir}/c-c++-common/cpp/embed-dir" } */
+/* { dg-additional-options "-std=gnu99" { target c } } */
+
+#if __has_embed (__FILE__ gnu::offset (4 + FOOBAR) limit (3)) !=
__STDC_EMBED_FOUND__
+#error "__has_embed fail"
+#endif
+
+#embed <magna-carta.txt> limit(1) gnu::offset (0) prefix(int a = ) suffix (;)
+#embed <magna-carta.txt> limit(1) __gnu__::offset (1 * 1) prefix(int b = )
suffix (;)
+#embed <magna-carta.txt> limit(1) gnu::__offset__ (1 + 1) prefix(int c = )
suffix (;)
+#embed <magna-carta.txt> __limit__(1) __gnu__::__offset__ (1 + (1 \
+ + 1)) __prefix__(int d = ) __suffix__ (;)
+const unsigned char e[] = {
+ #embed <magna-carta.txt> limit(5) gnu::offset (999)
+};
+const unsigned char f[] = {
+ #embed <magna-carta.txt> limit(7) gnu::offset (998)
+};
+const unsigned char g[] = {
+ #embed <magna-carta.txt> limit(8) gnu::offset (998)
+};
+const unsigned char h[] = {
+ #embed <magna-carta.txt> limit(8) gnu::offset (997)
+};
+const unsigned char i[] = {
+ #embed <magna-carta.txt> limit(9) gnu::offset (997)
+};
+const unsigned char j[] = {
+ #embed <magna-carta.txt> limit(30) gnu::offset (990)
+};
+const unsigned char k[] = {
+ #embed <magna-carta.txt> limit(26) gnu::offset (992)
+};
+const unsigned char l[] = {
+ #embed <magna-carta.txt>
+};
+const unsigned char m[] = {
+ #embed <magna-carta.txt> __limit__ (1000) __gnu__::__offset__ (32)
+};
+#if __has_embed (<magna-carta.txt> limit(5) gnu::offset (999)) !=
__STDC_EMBED_FOUND__ \
+ || __has_embed (<magna-carta.txt> limit(5) gnu::offset (999)) !=
__STDC_EMBED_FOUND__ \
+ || __has_embed (<magna-carta.txt> limit(7) gnu::offset (998)) !=
__STDC_EMBED_FOUND__ \
+ || __has_embed (<magna-carta.txt> limit(8) gnu::offset (998)) !=
__STDC_EMBED_FOUND__ \
+ || __has_embed (<magna-carta.txt> limit(8) gnu::offset (997)) !=
__STDC_EMBED_FOUND__ \
+ || __has_embed (<magna-carta.txt> limit(9) gnu::offset (997)) !=
__STDC_EMBED_FOUND__ \
+ || __has_embed (<magna-carta.txt> limit(30) gnu::offset (990)) !=
__STDC_EMBED_FOUND__ \
+ || __has_embed (<magna-carta.txt> limit(26) gnu::offset (992)) !=
__STDC_EMBED_FOUND__ \
+ || __has_embed (<magna-carta.txt>) != __STDC_EMBED_FOUND__ \
+ || __has_embed (<magna-carta.txt> limit(26) gnu::offset (992)) !=
__STDC_EMBED_FOUND__
+#error "__has_embed fail"
+#endif
+
+#ifdef __cplusplus
+#define C "C"
+#else
+#define C
+#endif
+extern C void abort (void);
+extern C int memcmp (const void *, const void *, __SIZE_TYPE__);
+
+int
+main ()
+{
+ if (a != 'H' || b != 'e' || c != 'n' || d != 'r')
+ abort ();
+ if (sizeof (e) != 5
+ || sizeof (f) != 7
+ || sizeof (g) != 8
+ || sizeof (h) != 8
+ || sizeof (i) != 9
+ || sizeof (j) != 30
+ || sizeof (k) != 26
+ || sizeof (l) < 1032
+ || sizeof (m) != 1000)
+ abort ();
+ if (memcmp (e, l + 999, 5)
+ || memcmp (f, l + 998, 7)
+ || memcmp (g, l + 998, 8)
+ || memcmp (h, l + 997, 8)
+ || memcmp (i, l + 997, 9)
+ || memcmp (j, l + 990, 30)
+ || memcmp (k, l + 992, 26)
+ || memcmp (m, l + 32, 1000))
+ abort ();
+ if (l[0] != 'H' || l[1] != 'e' || l[2] != 'n' || l[3] != 'r')
+ abort ();
+}
--- gcc/testsuite/c-c++-common/cpp/embed-16.c.jj 2024-06-18
12:44:40.375102653 +0200
+++ gcc/testsuite/c-c++-common/cpp/embed-16.c 2024-06-18 13:02:11.043397739
+0200
@@ -0,0 +1,19 @@
+/* { dg-do preprocess } */
+/* { dg-options "" } */
+
+#embed __FILE__ gnu::offset(1) gnu::offset(1) /* { dg-error "duplicate embed
parameter 'gnu::offset'" } */
+#embed __FILE__ gnu::offset prefix() suffix() /* { dg-error "expected '\\\('"
} */
+#embed __FILE__ gnu::offset (1 / 0) /* { dg-error "division by zero in #embed"
} */
+#embed __FILE__ __gnu__::__offset__ (+ + +) /* { dg-error "operator '\\\+' has
no right operand" } */
+#define FOO 1
+#embed __FILE__ gnu::offset(0 + defined(FOO)) /* { dg-error "'defined' in
#embed parameter" } */
+#if 1 + __has_embed (__FILE__ gnu::offset(1) __gnu__::__offset__(1)) /* {
dg-error "duplicate embed parameter 'gnu::offset'" } */
+#endif
+#if 1 + __has_embed (__FILE__ __gnu__::__offset__ prefix() suffix()) /* {
dg-error "expected '\\\('" } */
+#endif
+#if 1 + __has_embed (__FILE__ gnu::offset(1/0)) /* { dg-error "division by
zero in #embed" } */
+#endif
+#if 1 + __has_embed (__FILE__ gnu::offset(+ + +)) /* { dg-error "operator
'\\\+' has no right operand" } */
+#endif
+#if 1 + __has_embed (__FILE__ gnu::offset(0 + defined(FOO))) /* { dg-error
"'defined' in #embed parameter" } */
+#endif
--- gcc/testsuite/gcc.dg/cpp/embed-5.c.jj 2024-06-18 12:48:49.208857727
+0200
+++ gcc/testsuite/gcc.dg/cpp/embed-5.c 2024-06-18 12:49:26.230374939 +0200
@@ -0,0 +1,4 @@
+/* { dg-do run } */
+/* { dg-options "-std=c23 -pedantic-errors
--embed-dir=${srcdir}/c-c++-common/cpp/embed-dir" } */
+
+#include "../../c-c++-common/cpp/embed-15.c"
Jakub
