[PATCH] regex: port to recently proposed glibc regex merge

[Paul Eggert]

This patch is inspired by Adhemerval Zanella's recent proposal
https://www.sourceware.org/ml/libc-alpha/2018-06/msg00905.html
to merge glibc and Gnulib regex.  It aims to simplify the merge on
the glibc side, without keeping Gnulib portable.
* lib/regex.h: Fix a problem with glibc installed-header checking,
as follows:
(_Restrict_): Prefer __restrict if defined or if GCC 2.95 or later.
(_Restrict_arr_): Prefer __restrict_arr if defined,
otherwise prefer _Restrict_ if C99 or GCC 3.1 or later (but not C++).
* lib/regex_internal.c (re_string_realloc_buffers, build_wcs_buffer)
(build_wcs_upper_buffer, build_upper_buffer)
(re_string_translate_buffer, re_string_context_at):
Move decls here from lib/regex_internal.h, for glibc internal tests.
(build_wcs_upper_buffer): Use __wcrtomb, not wcrtomb, fixing
glibc BZ #18496.
* lib/regex_internal.h (lock_fini) [_LIBC]: Cast to 0 to pacify
-Wunused-value.
(bitset_set, bitset_clear, bitset_contain, bitset_empty)
(bitset_set_all, bitset_copy, bitset_not, bitset_merge)
(bitset_mask): Now static inline, and without any __attribute__
((unused)) decoration, for glibc internal tests.
---
 ChangeLog            | 25 +++++++++++++++++++++++++
 lib/regex.h          | 25 ++++++++++++-------------
 lib/regex_internal.c | 12 +++++++++++-
 lib/regex_internal.h | 31 ++++++++++---------------------
 4 files changed, 58 insertions(+), 35 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index a356a4086..1b2505a1a 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,28 @@
+2018-06-28  Paul Eggert  <address@hidden>
+
+       regex: port to recently proposed glibc regex merge
+       This patch is inspired by Adhemerval Zanella's recent proposal
+       https://www.sourceware.org/ml/libc-alpha/2018-06/msg00905.html
+       to merge glibc and Gnulib regex.  It aims to simplify the merge on
+       the glibc side, without keeping Gnulib portable.
+       * lib/regex.h: Fix a problem with glibc installed-header checking,
+       as follows:
+       (_Restrict_): Prefer __restrict if defined or if GCC 2.95 or later.
+       (_Restrict_arr_): Prefer __restrict_arr if defined,
+       otherwise prefer _Restrict_ if C99 or GCC 3.1 or later (but not C++).
+       * lib/regex_internal.c (re_string_realloc_buffers, build_wcs_buffer)
+       (build_wcs_upper_buffer, build_upper_buffer)
+       (re_string_translate_buffer, re_string_context_at):
+       Move decls here from lib/regex_internal.h, for glibc internal tests.
+       (build_wcs_upper_buffer): Use __wcrtomb, not wcrtomb, fixing
+       glibc BZ #18496.
+       * lib/regex_internal.h (lock_fini) [_LIBC]: Cast to 0 to pacify
+       -Wunused-value.
+       (bitset_set, bitset_clear, bitset_contain, bitset_empty)
+       (bitset_set_all, bitset_copy, bitset_not, bitset_merge)
+       (bitset_mask): Now static inline, and without any __attribute__
+       ((unused)) decoration, for glibc internal tests.
+
 2018-06-25  Bruno Haible  <address@hidden>
 
        threadlib: Fix LIBMULTITHREAD on platforms where --as-needed is enabled.
diff --git a/lib/regex.h b/lib/regex.h
index 9ed74c3df..32933bc6d 100644
--- a/lib/regex.h
+++ b/lib/regex.h
@@ -1,7 +1,6 @@
 /* Definitions for data structures and routines for the regular
    expression library.
-   Copyright (C) 1985, 1989-1993, 1995-1998, 2000-2003, 2005-2018 Free Software
-   Foundation, Inc.
+   Copyright (C) 1985, 1989-2018 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
 
    The GNU C Library is free software; you can redistribute it and/or
@@ -608,28 +607,28 @@ extern int re_exec (const char *);
 # endif
 #endif
 
-/* GCC 2.95 and later have "__restrict"; C99 compilers have
+/* For plain 'restrict', use glibc's __restrict if defined.
+   Otherwise, GCC 2.95 and later have "__restrict"; C99 compilers have
    "restrict", and "configure" may have defined "restrict".
    Other compilers use __restrict, __restrict__, and _Restrict, and
    'configure' might #define 'restrict' to those words, so pick a
    different name.  */
 #ifndef _Restrict_
-# if 199901L <= __STDC_VERSION__
-#  define _Restrict_ restrict
-# elif 2 < __GNUC__ || (2 == __GNUC__ && 95 <= __GNUC_MINOR__)
+# if defined __restrict || 2 < __GNUC__ + (95 <= __GNUC_MINOR__)
 #  define _Restrict_ __restrict
+# elif 199901L <= __STDC_VERSION__ || defined restrict
+#  define _Restrict_ restrict
 # else
 #  define _Restrict_
 # endif
 #endif
-/* gcc 3.1 and up support the [restrict] syntax.  Don't trust
-   sys/cdefs.h's definition of __restrict_arr, though, as it
-   mishandles gcc -ansi -pedantic.  */
+/* For [restrict], use glibc's __restrict_arr if available.
+   Otherwise, GCC 3.1 (not in C++ mode) and C99 support [restrict].  */
 #ifndef _Restrict_arr_
-# if ((199901L <= __STDC_VERSION__                                     \
-       || ((3 < __GNUC__ || (3 == __GNUC__ && 1 <= __GNUC_MINOR__))    \
-          && !defined __STRICT_ANSI__))                                        
\
-      && !defined __GNUG__)
+# ifdef __restrict_arr
+#  define _Restrict_arr_ __restrict_arr
+# elif ((199901L <= __STDC_VERSION__ || 3 < __GNUC__ + (1 <= __GNUC_MINOR__)) \
+        && !defined __GNUG__)
 #  define _Restrict_arr_ _Restrict_
 # else
 #  define _Restrict_arr_
diff --git a/lib/regex_internal.c b/lib/regex_internal.c
index c08c8e465..7f0083b91 100644
--- a/lib/regex_internal.c
+++ b/lib/regex_internal.c
@@ -28,6 +28,16 @@ static re_dfastate_t *create_cd_newstate (const re_dfa_t 
*dfa,
                                          const re_node_set *nodes,
                                          unsigned int context,
                                          re_hashval_t hash);
+static reg_errcode_t re_string_realloc_buffers (re_string_t *pstr,
+                                               Idx new_buf_len);
+#ifdef RE_ENABLE_I18N
+static void build_wcs_buffer (re_string_t *pstr);
+static reg_errcode_t build_wcs_upper_buffer (re_string_t *pstr);
+#endif /* RE_ENABLE_I18N */
+static void build_upper_buffer (re_string_t *pstr);
+static void re_string_translate_buffer (re_string_t *pstr);
+static unsigned int re_string_context_at (const re_string_t *input, Idx idx,
+                                         int eflags) __attribute__ ((pure));
 
 /* Functions for string operation.  */
 
@@ -383,7 +393,7 @@ build_wcs_upper_buffer (re_string_t *pstr)
              {
                size_t mbcdlen;
 
-               mbcdlen = wcrtomb ((char *) buf, wcu, &prev_st);
+               mbcdlen = __wcrtomb ((char *) buf, wcu, &prev_st);
                if (BE (mbclen == mbcdlen, 1))
                  memcpy (pstr->mbs + byte_idx, buf, mbclen);
                else if (mbcdlen != (size_t) -1)
diff --git a/lib/regex_internal.h b/lib/regex_internal.h
index bc7c600a3..b27afbda2 100644
--- a/lib/regex_internal.h
+++ b/lib/regex_internal.h
@@ -39,7 +39,7 @@
 # include <libc-lock.h>
 # define lock_define(name) __libc_lock_define (, name)
 # define lock_init(lock) (__libc_lock_init (lock), 0)
-# define lock_fini(lock) 0
+# define lock_fini(lock) ((void) 0)
 # define lock_lock(lock) __libc_lock_lock (lock)
 # define lock_unlock(lock) __libc_lock_unlock (lock)
 #elif defined GNULIB_LOCK && !defined USE_UNLOCKED_IO
@@ -441,17 +441,6 @@ typedef struct re_dfa_t re_dfa_t;
 # define IS_IN(libc) false
 #endif
 
-static reg_errcode_t re_string_realloc_buffers (re_string_t *pstr,
-                                               Idx new_buf_len);
-#ifdef RE_ENABLE_I18N
-static void build_wcs_buffer (re_string_t *pstr);
-static reg_errcode_t build_wcs_upper_buffer (re_string_t *pstr);
-#endif /* RE_ENABLE_I18N */
-static void build_upper_buffer (re_string_t *pstr);
-static void re_string_translate_buffer (re_string_t *pstr);
-static unsigned int re_string_context_at (const re_string_t *input, Idx idx,
-                                         int eflags) __attribute__ ((pure));
-
 #define re_string_peek_byte(pstr, offset) \
   ((pstr)->mbs[(pstr)->cur_idx + offset])
 #define re_string_fetch_byte(pstr) \
@@ -757,31 +746,31 @@ typedef struct
 
 /* Functions for bitset_t operation.  */
 
-static void
+static inline void
 bitset_set (bitset_t set, Idx i)
 {
   set[i / BITSET_WORD_BITS] |= (bitset_word_t) 1 << i % BITSET_WORD_BITS;
 }
 
-static void
+static inline void
 bitset_clear (bitset_t set, Idx i)
 {
   set[i / BITSET_WORD_BITS] &= ~ ((bitset_word_t) 1 << i % BITSET_WORD_BITS);
 }
 
-static bool
+static inline bool
 bitset_contain (const bitset_t set, Idx i)
 {
   return (set[i / BITSET_WORD_BITS] >> i % BITSET_WORD_BITS) & 1;
 }
 
-static void
+static inline void
 bitset_empty (bitset_t set)
 {
   memset (set, '\0', sizeof (bitset_t));
 }
 
-static void
+static inline void
 bitset_set_all (bitset_t set)
 {
   memset (set, -1, sizeof (bitset_word_t) * (SBC_MAX / BITSET_WORD_BITS));
@@ -790,13 +779,13 @@ bitset_set_all (bitset_t set)
       ((bitset_word_t) 1 << SBC_MAX % BITSET_WORD_BITS) - 1;
 }
 
-static void
+static inline void
 bitset_copy (bitset_t dest, const bitset_t src)
 {
   memcpy (dest, src, sizeof (bitset_t));
 }
 
-static void __attribute__ ((unused))
+static inline void
 bitset_not (bitset_t set)
 {
   int bitset_i;
@@ -808,7 +797,7 @@ bitset_not (bitset_t set)
        & ~set[BITSET_WORDS - 1]);
 }
 
-static void __attribute__ ((unused))
+static inline void
 bitset_merge (bitset_t dest, const bitset_t src)
 {
   int bitset_i;
@@ -816,7 +805,7 @@ bitset_merge (bitset_t dest, const bitset_t src)
     dest[bitset_i] |= src[bitset_i];
 }
 
-static void __attribute__ ((unused))
+static inline void
 bitset_mask (bitset_t dest, const bitset_t src)
 {
   int bitset_i;
-- 
2.17.1