md5 and sha1 integer cleanup for coreutils

[Paul Eggert]

Continuing in our series of integer-arithmetic cleanups for coreutils,
here is a patch to make md5.c and sha1.c portable to hosts (like the
AS/400) which do not let you cast pointers to integers in any
meaningful way.  This also modernizes the integer terminology a bit
(using C99 names) and fixes the Autoconf macros to match the code.

2004-07-28  Paul Eggert  <address@hidden>

        * lib/md5.h: Include <stdint.h> if HAVE_STDINT_H || _LIBC, not
        ifdef _LIBC.
        (md5_uint32): Use uint32_t if available.  Simplify fallback ifdefs.
        * lib/md5.c: Don't include <sys/types.h> or <stdlib.h>; <stddef.h>
        suffices with C89 or better.
        (alignof): New macro, portable to all C89 hosts.
        (UNALIGNED): Use it.  Use uintptr_t if available, and assume
        everything is unaligned otherwise; this is more portable than
        assuming 'unsigned long int' will always work.
        * lib/sha1.c: Likewise.
        * m4/md5.m4 (gl_MD5): Do not require AC_C_INLINE, since it doesn't
        use inline any more.  Require AC_C_BIGENDIAN, though.
        * m4/sha.m4 (gl_SHA): Require AC_C_BIGENDIAN.

Index: lib/md5.h
===================================================================
RCS file: /home/eggert/coreutils/cu/lib/md5.h,v
retrieving revision 1.15
diff -p -u -r1.15 md5.h
--- lib/md5.h   2 Dec 2003 08:24:31 -0000       1.15
+++ lib/md5.h   28 Jul 2004 19:55:32 -0000
@@ -1,6 +1,9 @@
 /* md5.h - Declaration of functions and data types used for MD5 sum
    computing library functions.
-   Copyright (C) 1995, 1996, 1999, 2000, 2003 Free Software Foundation, Inc.
+
+   Copyright (C) 1995, 1996, 1999, 2000, 2003, 2004 Free Software
+   Foundation, Inc.
+
    NOTE: The canonical source of this file is maintained with the GNU C
    Library.  Bugs can be reported to address@hidden
 
@@ -25,37 +28,27 @@
 #include <limits.h>
 
 /* The following contortions are an attempt to use the C preprocessor
-   to determine an unsigned integral type that is 32 bits wide.  An
-   alternative approach is to use autoconf's AC_CHECK_SIZEOF macro, but
-   doing that would require that the configure script compile and *run*
-   the resulting executable.  Locally running cross-compiled executables
-   is usually not possible.  */
+   to determine an unsigned integral type that is exactly 32 bits wide.  */
 
-#ifdef _LIBC
+#if HAVE_STDINT_H || _LIBC
 # include <stdint.h>
+#endif
+
+#ifdef UINT32_MAX
 typedef uint32_t md5_uint32;
-typedef uintptr_t md5_uintptr;
 #else
 # define UINT_MAX_32_BITS 4294967295U
-
 # if UINT_MAX == UINT_MAX_32_BITS
    typedef unsigned int md5_uint32;
+# elif USHRT_MAX == UINT_MAX_32_BITS
+   typedef unsigned short int md5_uint32;
+# elif ULONG_MAX == UINT_MAX_32_BITS
+   typedef unsigned long md5_uint32;
 # else
-#  if USHRT_MAX == UINT_MAX_32_BITS
-    typedef unsigned short md5_uint32;
-#  else
-#   if ULONG_MAX == UINT_MAX_32_BITS
-     typedef unsigned long md5_uint32;
-#   else
-     /* The following line is intended to evoke an error.
-        Using #error is not portable enough.  */
-     "Cannot determine unsigned 32-bit data type."
-#   endif
-#  endif
+   /* The following line is intended to evoke an error.
+      Using #error is not portable enough.  */
+   "Cannot determine unsigned 32-bit data type."
 # endif
-/* We have to make a guess about the integer type equivalent in size
-   to pointers which should always be correct.  */
-typedef unsigned long int md5_uintptr;
 #endif
 
 /* Structure to save state of computation between the single steps.  */
Index: lib/md5.c
===================================================================
RCS file: /home/eggert/coreutils/cu/lib/md5.c,v
retrieving revision 1.18
diff -p -u -r1.18 md5.c
--- lib/md5.c   10 Sep 2003 08:54:26 -0000      1.18
+++ lib/md5.c   28 Jul 2004 19:55:19 -0000
@@ -1,6 +1,6 @@
 /* md5.c - Functions to compute MD5 message digest of files or memory blocks
    according to the definition of MD5 in RFC 1321 from April 1992.
-   Copyright (C) 1995, 1996, 2001, 2003 Free Software Foundation, Inc.
+   Copyright (C) 1995, 1996, 2001, 2003, 2004 Free Software Foundation, Inc.
    NOTE: The canonical source of this file is maintained with the GNU C
    Library.  Bugs can be reported to address@hidden
 
@@ -26,9 +26,7 @@
 
 #include "md5.h"
 
-#include <sys/types.h>
-
-#include <stdlib.h>
+#include <stddef.h>
 #include <string.h>
 
 #include "unlocked-io.h"
@@ -246,12 +244,11 @@ md5_process_bytes (const void *buffer, s
   if (len >= 64)
     {
 #if !_STRING_ARCH_unaligned
-/* To check alignment gcc has an appropriate operator.  Other
-   compilers don't.  */
-# if __GNUC__ >= 2
-#  define UNALIGNED_P(p) (((md5_uintptr) p) % __alignof__ (md5_uint32) != 0)
+# define alignof(type) offsetof (struct { char c; type x; }, x)
+# ifdef UINTPTR_MAX
+#  define UNALIGNED_P(p) (((uintptr_t) p) % alignof (md5_uint32) != 0)
 # else
-#  define UNALIGNED_P(p) (((md5_uintptr) p) % sizeof (md5_uint32) != 0)
+#  define UNALIGNED_P(p) 1
 # endif
       if (UNALIGNED_P (buffer))
        while (len > 64)
Index: lib/sha1.c
===================================================================
RCS file: /home/eggert/coreutils/cu/lib/sha1.c,v
retrieving revision 1.1
diff -p -u -r1.1 sha1.c
--- lib/sha1.c  2 Dec 2003 09:05:40 -0000       1.1
+++ lib/sha1.c  28 Jul 2004 19:56:04 -0000
@@ -1,7 +1,7 @@
 /* sha.c - Functions to compute SHA1 message digest of files or
    memory blocks according to the NIST specification FIPS-180-1.
 
-   Copyright (C) 2000, 2001, 2003 Free Software Foundation, Inc.
+   Copyright (C) 2000, 2001, 2003, 2004 Free Software Foundation, Inc.
 
    This program is free software; you can redistribute it and/or modify it
    under the terms of the GNU General Public License as published by the
@@ -28,9 +28,7 @@
 
 #include "sha1.h"
 
-#include <sys/types.h>
-
-#include <stdlib.h>
+#include <stddef.h>
 #include <string.h>
 
 #include "unlocked-io.h"
@@ -244,12 +242,11 @@ sha_process_bytes (const void *buffer, s
   if (len >= 64)
     {
 #if !_STRING_ARCH_unaligned
-/* To check alignment gcc has an appropriate operator.  Other
-   compilers don't.  */
-# if __GNUC__ >= 2
-#  define UNALIGNED_P(p) (((md5_uintptr) p) % __alignof__ (md5_uint32) != 0)
+# define alignof(type) offsetof (struct { char c; type x; }, x)
+# ifdef UINTPTR_MAX
+#  define UNALIGNED_P(p) (((uintptr_t) p) % alignof (md5_uint32) != 0)
 # else
-#  define UNALIGNED_P(p) (((md5_uintptr) p) % sizeof (md5_uint32) != 0)
+#  define UNALIGNED_P(p) 1
 # endif
       if (UNALIGNED_P (buffer))
        while (len > 64)
Index: m4/md5.m4
===================================================================
RCS file: /home/eggert/coreutils/cu/m4/md5.m4,v
retrieving revision 1.1
diff -p -u -r1.1 md5.m4
--- m4/md5.m4   12 Sep 2003 21:11:30 -0000      1.1
+++ m4/md5.m4   28 Jul 2004 19:55:03 -0000
@@ -1,5 +1,5 @@
-# md5.m4 serial 3
-dnl Copyright (C) 2002-2003 Free Software Foundation, Inc.
+# md5.m4 serial 4
+dnl Copyright (C) 2002, 2003, 2004 Free Software Foundation, Inc.
 dnl This file is free software, distributed under the terms of the GNU
 dnl General Public License.  As a special exception to the GNU General
 dnl Public License, this file may be distributed as part of a program
@@ -8,8 +8,9 @@ dnl the same distribution terms as the r
 
 AC_DEFUN([gl_MD5],
 [
-  dnl Prerequisites of lib/md5.h.
-  AC_REQUIRE([AC_C_INLINE])
+  dnl No prerequisites of lib/md5.h.
 
-  dnl No prerequisites of lib/md5.c.
+  dnl Prerequisites of lib/md5.c.
+  AC_REQUIRE([AC_C_BIGENDIAN])
+  :
 ])
Index: m4/sha.m4
===================================================================
RCS file: /home/eggert/coreutils/cu/m4/sha.m4,v
retrieving revision 1.2
diff -p -u -r1.2 sha.m4
--- m4/sha.m4   12 Sep 2003 21:08:06 -0000      1.2
+++ m4/sha.m4   28 Jul 2004 19:54:52 -0000
@@ -1,5 +1,5 @@
-# sha.m4 serial 2
-dnl Copyright (C) 2002, 2003 Free Software Foundation, Inc.
+# sha.m4 serial 3
+dnl Copyright (C) 2002, 2003, 2004 Free Software Foundation, Inc.
 dnl This file is free software, distributed under the terms of the GNU
 dnl General Public License.  As a special exception to the GNU General
 dnl Public License, this file may be distributed as part of a program
@@ -8,6 +8,7 @@ dnl the same distribution terms as the r
 
 AC_DEFUN([gl_SHA],
 [
-  dnl Prerequisites of lib/sha.c.
+  dnl Prerequisites of lib/sha1.c.
+  AC_REQUIRE([AC_C_BIGENDIAN])
   :
 ])