[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[SCM] gawk branch, gawk-5.1-stable, updated. gawk-4.1.0-4405-g9a1e7448
|
From: |
Arnold Robbins |
|
Subject: |
[SCM] gawk branch, gawk-5.1-stable, updated. gawk-4.1.0-4405-g9a1e7448 |
|
Date: |
Mon, 23 May 2022 16:39:16 -0400 (EDT) |
This is an automated email from the git hooks/post-receive script. It was
generated because a ref change was pushed to the repository containing
the project "gawk".
The branch, gawk-5.1-stable has been updated
via 9a1e7448b6ac3f7b468e72af9f013f61fcf63239 (commit)
from 5456e9b6c741ffb0323e862cadb0977330df51b4 (commit)
Those revisions listed above that are new to this repository have
not appeared on any other notification email; so we list those
revisions in full, below.
- Log -----------------------------------------------------------------
http://git.sv.gnu.org/cgit/gawk.git/commit/?id=9a1e7448b6ac3f7b468e72af9f013f61fcf63239
commit 9a1e7448b6ac3f7b468e72af9f013f61fcf63239
Author: Arnold D. Robbins <arnold@skeeve.com>
Date: Mon May 23 16:39:00 2022 -0400
Update support files.
diff --git a/support/ChangeLog b/support/ChangeLog
index 4948abe8..b422af16 100644
--- a/support/ChangeLog
+++ b/support/ChangeLog
@@ -1,3 +1,7 @@
+2022-05-23 Arnold D. Robbins <arnold@skeeve.com>
+
+ * cdefs.h, dfa.c, dfa.h, libc-config.h: Sync with GNULIB.
+
2022-04-27 Arnold D. Robbins <arnold@skeeve.com>
* regcomp.c (peek_token_bracket): Sync to version from GNULIB
diff --git a/support/cdefs.h b/support/cdefs.h
index cb251450..7b8ed5b3 100644
--- a/support/cdefs.h
+++ b/support/cdefs.h
@@ -164,13 +164,13 @@
|| (__builtin_constant_p (__l) && (__l) > 0))
/* Length is known to be safe at compile time if the __L * __S <= __OBJSZ
- condition can be folded to a constant and if it is true. The -1 check is
- redundant because since it implies that __glibc_safe_len_cond is true. */
+ condition can be folded to a constant and if it is true, or unknown (-1) */
#define __glibc_safe_or_unknown_len(__l, __s, __osz) \
- (__glibc_unsigned_or_positive (__l) \
- && __builtin_constant_p (__glibc_safe_len_cond ((__SIZE_TYPE__) (__l), \
- __s, __osz)) \
- && __glibc_safe_len_cond ((__SIZE_TYPE__) (__l), __s, __osz))
+ ((__osz) == (__SIZE_TYPE__) -1 \
+ || (__glibc_unsigned_or_positive (__l) \
+ && __builtin_constant_p (__glibc_safe_len_cond ((__SIZE_TYPE__) (__l), \
+ (__s), (__osz))) \
+ && __glibc_safe_len_cond ((__SIZE_TYPE__) (__l), (__s), (__osz))))
/* Conversely, we know at compile time that the length is unsafe if the
__L * __S <= __OBJSZ condition can be folded to a constant and if it is
diff --git a/support/dfa.c b/support/dfa.c
index 45adb80f..5d92b38b 100644
--- a/support/dfa.c
+++ b/support/dfa.c
@@ -44,13 +44,13 @@
#define assume_nonnull(x) assume ((x) != NULL)
static bool
-streq (char const *a, char const *b)
+str_eq (char const *a, char const *b)
{
return strcmp (a, b) == 0;
}
static bool
-isasciidigit (char c)
+c_isdigit (char c)
{
return '0' <= c && c <= '9';
}
@@ -59,6 +59,7 @@ isasciidigit (char c)
#define _(str) gettext (str)
#include <wchar.h>
+#include <wctype.h>
#include "xalloc.h"
#include "localeinfo.h"
@@ -399,15 +400,12 @@ struct regex_syntax
{
/* Syntax bits controlling the behavior of the lexical analyzer. */
reg_syntax_t syntax_bits;
+ int dfaopts;
bool syntax_bits_set;
/* Flag for case-folding letters into sets. */
bool case_fold;
- /* True if ^ and $ match only the start and end of data, and do not match
- end-of-line within data. */
- bool anchor;
-
/* End-of-line byte in data. */
unsigned char eolbyte;
@@ -836,7 +834,7 @@ unibyte_word_constituent (struct dfa const *dfa, unsigned
char c)
static int
char_context (struct dfa const *dfa, unsigned char c)
{
- if (c == dfa->syntax.eolbyte && !dfa->syntax.anchor)
+ if (c == dfa->syntax.eolbyte && !(dfa->syntax.dfaopts & DFA_ANCHOR))
return CTX_NEWLINE;
if (unibyte_word_constituent (dfa, c))
return CTX_LETTER;
@@ -930,7 +928,7 @@ static const struct dfa_ctype *_GL_ATTRIBUTE_PURE
find_pred (const char *str)
{
for (int i = 0; prednames[i].name; i++)
- if (streq (str, prednames[i].name))
+ if (str_eq (str, prednames[i].name))
return &prednames[i];
return NULL;
}
@@ -1009,8 +1007,8 @@ parse_bracket_exp (struct dfa *dfa)
worry about that possibility. */
{
char const *class
- = (dfa->syntax.case_fold && (streq (str, "upper")
- || streq (str, "lower"))
+ = (dfa->syntax.case_fold && (str_eq (str, "upper")
+ || str_eq (str, "lower"))
? "alpha" : str);
const struct dfa_ctype *pred = find_pred (class);
if (!pred)
@@ -1090,7 +1088,7 @@ parse_bracket_exp (struct dfa *dfa)
if (wc != wc2 || wc == WEOF)
{
if (dfa->localeinfo.simple
- || (isasciidigit (c) && isasciidigit (c2)))
+ || (c_isdigit (c) & c_isdigit (c2)))
{
for (int ci = c; ci <= c2; ci++)
if (dfa->syntax.case_fold && isalpha (ci))
@@ -1140,7 +1138,9 @@ parse_bracket_exp (struct dfa *dfa)
while ((wc = wc1, (c = c1) != ']'));
if (colon_warning_state == 7)
- dfawarn (_("character class syntax is [[:space:]], not [:space:]"));
+ ((dfa->syntax.dfaopts & DFA_CONFUSING_BRACKETS_ERROR
+ ? dfaerror : dfawarn)
+ (_("character class syntax is [[:space:]], not [:space:]")));
if (! known_bracket_exp)
return BACKREF;
@@ -1193,8 +1193,7 @@ lex (struct dfa *dfa)
we set the backslash flag and go through the loop again.
On the plus side, this avoids having a duplicate of the
main switch inside the backslash case. On the minus side,
- it means that just about every case begins with
- "if (backslash) ...". */
+ it means that just about every case tests the backslash flag. */
for (int i = 0; i < 2; ++i)
{
if (! dfa->lex.left)
@@ -1249,52 +1248,67 @@ lex (struct dfa *dfa)
case '7':
case '8':
case '9':
- if (backslash && !(dfa->syntax.syntax_bits & RE_NO_BK_REFS))
- {
- dfa->lex.laststart = false;
- return dfa->lex.lasttok = BACKREF;
- }
- goto normal_char;
+ if (!backslash)
+ goto normal_char;
+ if (dfa->syntax.syntax_bits & RE_NO_BK_REFS)
+ goto stray_backslash;
+
+ dfa->lex.laststart = false;
+ return dfa->lex.lasttok = BACKREF;
case '`':
- if (backslash && !(dfa->syntax.syntax_bits & RE_NO_GNU_OPS))
- {
- /* FIXME: should be beginning of string */
- return dfa->lex.lasttok = BEGLINE;
- }
- goto normal_char;
+ if (!backslash)
+ goto normal_char;
+ if (dfa->syntax.syntax_bits & RE_NO_GNU_OPS)
+ goto stray_backslash;
+
+ /* FIXME: should be beginning of string */
+ return dfa->lex.lasttok = BEGLINE;
case '\'':
- if (backslash && !(dfa->syntax.syntax_bits & RE_NO_GNU_OPS))
- {
- /* FIXME: should be end of string */
- return dfa->lex.lasttok = ENDLINE;
- }
- goto normal_char;
+ if (!backslash)
+ goto normal_char;
+ if (dfa->syntax.syntax_bits & RE_NO_GNU_OPS)
+ goto stray_backslash;
+
+ /* FIXME: should be end of string */
+ return dfa->lex.lasttok = ENDLINE;
case '<':
- if (backslash && !(dfa->syntax.syntax_bits & RE_NO_GNU_OPS))
- return dfa->lex.lasttok = BEGWORD;
- goto normal_char;
+ if (!backslash)
+ goto normal_char;
+ if (dfa->syntax.syntax_bits & RE_NO_GNU_OPS)
+ goto stray_backslash;
+
+ return dfa->lex.lasttok = BEGWORD;
case '>':
- if (backslash && !(dfa->syntax.syntax_bits & RE_NO_GNU_OPS))
- return dfa->lex.lasttok = ENDWORD;
- goto normal_char;
+ if (!backslash)
+ goto normal_char;
+ if (dfa->syntax.syntax_bits & RE_NO_GNU_OPS)
+ goto stray_backslash;
+
+ return dfa->lex.lasttok = ENDWORD;
case 'b':
- if (backslash && !(dfa->syntax.syntax_bits & RE_NO_GNU_OPS))
- return dfa->lex.lasttok = LIMWORD;
- goto normal_char;
+ if (!backslash)
+ goto normal_char;
+ if (dfa->syntax.syntax_bits & RE_NO_GNU_OPS)
+ goto stray_backslash;
+
+ return dfa->lex.lasttok = LIMWORD;
case 'B':
- if (backslash && !(dfa->syntax.syntax_bits & RE_NO_GNU_OPS))
- return dfa->lex.lasttok = NOTLIMWORD;
- goto normal_char;
+ if (!backslash)
+ goto normal_char;
+ if (dfa->syntax.syntax_bits & RE_NO_GNU_OPS)
+ goto stray_backslash;
+
+ return dfa->lex.lasttok = NOTLIMWORD;
case '?':
if (dfa->syntax.syntax_bits & RE_LIMITED_OPS)
- goto normal_char;
+ goto default_case;
if (backslash != ((dfa->syntax.syntax_bits & RE_BK_PLUS_QM) != 0))
goto normal_char;
if (!(dfa->syntax.syntax_bits & RE_CONTEXT_INDEP_OPS)
@@ -1312,7 +1326,7 @@ lex (struct dfa *dfa)
case '+':
if (dfa->syntax.syntax_bits & RE_LIMITED_OPS)
- goto normal_char;
+ goto default_case;
if (backslash != ((dfa->syntax.syntax_bits & RE_BK_PLUS_QM) != 0))
goto normal_char;
if (!(dfa->syntax.syntax_bits & RE_CONTEXT_INDEP_OPS)
@@ -1322,7 +1336,7 @@ lex (struct dfa *dfa)
case '{':
if (!(dfa->syntax.syntax_bits & RE_INTERVALS))
- goto normal_char;
+ goto default_case;
if (backslash != ((dfa->syntax.syntax_bits & RE_NO_BK_BRACES) == 0))
goto normal_char;
if (!(dfa->syntax.syntax_bits & RE_CONTEXT_INDEP_OPS)
@@ -1339,7 +1353,7 @@ lex (struct dfa *dfa)
char const *p = dfa->lex.ptr;
char const *lim = p + dfa->lex.left;
dfa->lex.minrep = dfa->lex.maxrep = -1;
- for (; p != lim && isasciidigit (*p); p++)
+ for (; p != lim && c_isdigit (*p); p++)
dfa->lex.minrep = (dfa->lex.minrep < 0
? *p - '0'
: MIN (RE_DUP_MAX + 1,
@@ -1352,7 +1366,7 @@ lex (struct dfa *dfa)
{
if (dfa->lex.minrep < 0)
dfa->lex.minrep = 0;
- while (++p != lim && isasciidigit (*p))
+ while (++p != lim && c_isdigit (*p))
dfa->lex.maxrep
= (dfa->lex.maxrep < 0
? *p - '0'
@@ -1380,15 +1394,16 @@ lex (struct dfa *dfa)
case '|':
if (dfa->syntax.syntax_bits & RE_LIMITED_OPS)
- goto normal_char;
+ goto default_case;
if (backslash != ((dfa->syntax.syntax_bits & RE_NO_BK_VBAR) == 0))
goto normal_char;
dfa->lex.laststart = true;
return dfa->lex.lasttok = OR;
case '\n':
- if (dfa->syntax.syntax_bits & RE_LIMITED_OPS
- || backslash || !(dfa->syntax.syntax_bits & RE_NEWLINE_ALT))
+ if (!(dfa->syntax.syntax_bits & RE_NEWLINE_ALT))
+ goto default_case;
+ if (backslash)
goto normal_char;
dfa->lex.laststart = true;
return dfa->lex.lasttok = OR;
@@ -1434,8 +1449,11 @@ lex (struct dfa *dfa)
case 's':
case 'S':
- if (!backslash || (dfa->syntax.syntax_bits & RE_NO_GNU_OPS))
+ if (!backslash)
goto normal_char;
+ if (dfa->syntax.syntax_bits & RE_NO_GNU_OPS)
+ goto stray_backslash;
+
if (!dfa->localeinfo.multibyte)
{
charclass ccl;
@@ -1467,8 +1485,10 @@ lex (struct dfa *dfa)
case 'w':
case 'W':
- if (!backslash || (dfa->syntax.syntax_bits & RE_NO_GNU_OPS))
+ if (!backslash)
goto normal_char;
+ if (dfa->syntax.syntax_bits & RE_NO_GNU_OPS)
+ goto stray_backslash;
if (!dfa->localeinfo.multibyte)
{
@@ -1506,6 +1526,26 @@ lex (struct dfa *dfa)
return dfa->lex.lasttok = parse_bracket_exp (dfa);
default:
+ default_case:
+ if (!backslash)
+ goto normal_char;
+ stray_backslash:
+ if (dfa->syntax.dfaopts & DFA_STRAY_BACKSLASH_WARN)
+ {
+ char const *msg;
+ char msgbuf[100];
+ if (!iswprint (dfa->lex.wctok))
+ msg = _("stray \\ before unprintable character");
+ else if (iswspace (dfa->lex.wctok))
+ msg = _("stray \\ before white space");
+ else
+ {
+ int n = snprintf (msgbuf, sizeof msgbuf,
+ _("stray \\ before %lc"), dfa->lex.wctok);
+ msg = 0 <= n && n < sizeof msgbuf ? msgbuf : _("stray \\");
+ }
+ dfawarn (msg);
+ }
normal_char:
dfa->lex.laststart = false;
/* For multibyte character sets, folding is done in atom. Always
@@ -1704,7 +1744,7 @@ add_utf8_anychar (struct dfa *dfa)
/* G. ed (just a token). */
/* H. 80-9f: 2nd byte of a "GHC" sequence. */
- CHARCLASS_INIT (0, 0, 0, 0, 0xffff, 0, 0, 0),
+ CHARCLASS_INIT (0, 0, 0, 0, 0xffffffff, 0, 0, 0),
/* I. f0 (just a token). */
@@ -1717,7 +1757,7 @@ add_utf8_anychar (struct dfa *dfa)
/* L. f4 (just a token). */
/* M. 80-8f: 2nd byte of a "LMCC" sequence. */
- CHARCLASS_INIT (0, 0, 0, 0, 0xff, 0, 0, 0),
+ CHARCLASS_INIT (0, 0, 0, 0, 0xffff, 0, 0, 0),
};
/* Define the character classes that are needed below. */
@@ -4116,7 +4156,7 @@ dfamust (struct dfa const *d)
idx_t j, ln, rn, n;
/* Guaranteed to be. Unlikely, but ... */
- if (streq (lmp->is, rmp->is))
+ if (str_eq (lmp->is, rmp->is))
{
lmp->begline &= rmp->begline;
lmp->endline &= rmp->endline;
@@ -4163,7 +4203,7 @@ dfamust (struct dfa const *d)
for (idx_t i = 0; mp->in[i] != NULL; i++)
if (strlen (mp->in[i]) > strlen (result))
result = mp->in[i];
- if (streq (result, mp->is))
+ if (str_eq (result, mp->is))
{
if ((!need_begline || mp->begline) && (!need_endline
|| mp->endline))
@@ -4327,9 +4367,9 @@ dfasyntax (struct dfa *dfa, struct localeinfo const
*linfo,
dfa->canychar = -1;
dfa->syntax.syntax_bits_set = true;
dfa->syntax.case_fold = (bits & RE_ICASE) != 0;
- dfa->syntax.anchor = (dfaopts & DFA_ANCHOR) != 0;
dfa->syntax.eolbyte = dfaopts & DFA_EOL_NUL ? '\0' : '\n';
dfa->syntax.syntax_bits = bits;
+ dfa->syntax.dfaopts = dfaopts;
for (int i = CHAR_MIN; i <= CHAR_MAX; ++i)
{
diff --git a/support/dfa.h b/support/dfa.h
index e94e4354..8674929e 100644
--- a/support/dfa.h
+++ b/support/dfa.h
@@ -73,7 +73,14 @@ enum
DFA_ANCHOR = 1 << 0,
/* '\0' in data is end-of-line, instead of the traditional '\n'. */
- DFA_EOL_NUL = 1 << 1
+ DFA_EOL_NUL = 1 << 1,
+
+ /* Treat [:alpha:] etc. as an error at the top level, instead of
+ merely a warning. */
+ DFA_CONFUSING_BRACKETS_ERROR = 1 << 2,
+
+ /* Warn about stray backslashes before ordinary characters. */
+ DFA_STRAY_BACKSLASH_WARN = 1 << 3,
};
/* Initialize or reinitialize a DFA. The arguments are:
diff --git a/support/libc-config.h b/support/libc-config.h
index 8fec4893..a56665b1 100644
--- a/support/libc-config.h
+++ b/support/libc-config.h
@@ -121,6 +121,7 @@
# undef __attr_dealloc
# undef __attr_dealloc_free
# undef __attribute__
+# undef __attribute_alloc_align__
# undef __attribute_alloc_size__
# undef __attribute_artificial__
# undef __attribute_const__
@@ -129,6 +130,7 @@
# undef __attribute_format_arg__
# undef __attribute_format_strfmon__
# undef __attribute_malloc__
+# undef __attribute_maybe_unused__
# undef __attribute_noinline__
# undef __attribute_nonstring__
# undef __attribute_pure__
@@ -142,16 +144,24 @@
# undef __extern_always_inline
# undef __extern_inline
# undef __flexarr
+# undef __fortified_attr_access
# undef __fortify_function
# undef __glibc_c99_flexarr_available
+# undef __glibc_fortify
+# undef __glibc_fortify_n
# undef __glibc_has_attribute
# undef __glibc_has_builtin
# undef __glibc_has_extension
+# undef __glibc_likely
# undef __glibc_macro_warning
# undef __glibc_macro_warning1
# undef __glibc_objsize
# undef __glibc_objsize0
+# undef __glibc_safe_len_cond
+# undef __glibc_safe_or_unknown_len
# undef __glibc_unlikely
+# undef __glibc_unsafe_len
+# undef __glibc_unsigned_or_positive
# undef __inline
# undef __ptr_t
# undef __restrict
@@ -159,6 +169,7 @@
# undef __va_arg_pack
# undef __va_arg_pack_len
# undef __warnattr
+# undef __wur
/* Include our copy of glibc <sys/cdefs.h>. */
# include <cdefs.h>
-----------------------------------------------------------------------
Summary of changes:
support/ChangeLog | 4 ++
support/cdefs.h | 12 ++--
support/dfa.c | 158 +++++++++++++++++++++++++++++++-------------------
support/dfa.h | 9 ++-
support/libc-config.h | 11 ++++
5 files changed, 128 insertions(+), 66 deletions(-)
hooks/post-receive
--
gawk
| [Prev in Thread] |
Current Thread |
[Next in Thread] |
- [SCM] gawk branch, gawk-5.1-stable, updated. gawk-4.1.0-4405-g9a1e7448,
Arnold Robbins <=