Import of pkgsrc-2013Q2

sysutils/same/DESCR

@@ -0,0 +1,2 @@
+The `same' utility looks for identical files and links them together
+using either hard links or symbolic links, saving disk space.

sysutils/same/Makefile

@@ -0,0 +1,20 @@
+# $NetBSD: Makefile,v 1.9 2012/10/23 19:51:22 asau Exp $
+
+DISTNAME=	same-1.8
+CATEGORIES=	sysutils
+MASTER_SITES=	ftp://ftp.bitwizard.nl/same/
+
+MAINTAINER=	pkgsrc-users@NetBSD.org
+HOMEPAGE=	http://www.bitwizard.nl/
+COMMENT=	Find identical files and link(2) them to save disk space
+
+PKG_INSTALLATION_TYPES=	overwrite pkgviews
+
+AUTO_MKDIRS=			yes
+USE_BSD_MAKEFILE=	yes
+
+post-extract:
+	cd ${FILESDIR} && cp -f Makefile same.1 same.cat1 ${WRKSRC}
+
+.include "../../devel/zlib/buildlink3.mk"
+.include "../../mk/bsd.pkg.mk"

sysutils/same/PLIST

@@ -0,0 +1,4 @@
+@comment $NetBSD: PLIST,v 1.2 2006/08/04 22:46:27 rillig Exp $
+bin/same
+man/cat1/same.0
+man/man1/same.1

sysutils/same/distinfo

@@ -0,0 +1,6 @@
+$NetBSD: distinfo,v 1.4 2006/08/04 22:59:02 rillig Exp $
+
+SHA1 (same-1.8.tar.gz) = 39d95e70c09703b5c7525a6ea896c097f744d288
+RMD160 (same-1.8.tar.gz) = 987e6dc1c99258f00ed831af3fa3f034ebe08134
+Size (same-1.8.tar.gz) = 9398 bytes
+SHA1 (patch-ac) = 872eb12f82f5875b5980a4bf43c5af18b473fbca

sysutils/same/files/Makefile

@@ -0,0 +1,6 @@
+# $NetBSD: Makefile,v 1.2 2006/08/04 22:46:27 rillig Exp $
+
+PROG=	same
+LDADD=	-lz
+
+.include <bsd.prog.mk>

sysutils/same/files/same.1

@@ -0,0 +1,98 @@
+.\"	$NetBSD: same.1,v 1.2 2006/08/04 22:46:27 rillig Exp $
+.Dd July 14, 2004
+.Dt SAME 1
+.Sh NAME
+.Nm same
+.Nd link identical files to save disk space
+.Sh SYNOPSIS
+.Nm
+.Fl HVcdhnstuvz
+.Sh DESCRIPTION
+.Nm
+takes a list of files (e.g. the output of find . -type f) on stdin.
+Each of the files is compared against each of the others.
+Whenever two files are found that match exactly, the two files are
+linked (soft or hard) together.
+.Ss Goal
+The goal of this program is to conserve disk space when you have
+several different trees of large projects on your disk.
+By creating hardlinks or softlinks between the files that are the same,
+you can save lots of disk space.
+For example, two different versions of the Linux kernel only differ in a
+small number of files.
+By running this program you only need to store the contents of those
+files once.
+This is especially useful if you have different versions of complete
+trees lying around.
+.Ss Implementation
+The filesize of every file is used as an indication of wether two
+files can be the same. Whenever the filesizes match, the hashes of
+these two files are compared. Whenever these match, the file
+contents are compared. For every matching pair one of the two
+files is replaced by a hard link to the other file.
+With the -s option a softlink is used.
+.Pp
+To allow you to do this incrementally, the "rm" is done on the file
+with the least links. This allows you to "merge" a new tree with
+several trees that have already been processed. The new tree has
+link count 1, while the old tree has a higher link count for those
+files that are likely candidates for linkage.
+.Pp
+The current implementation keeps the "first" incantation of a file,
+and replaces further occurrances of the same file. This is
+significant when using softlinks.
+.Ss Options
+.Bl -tag -width xxxxxx
+.It Fl H Ar n , Fl -hashstart Ar n
+Start at hash value
+.Ar n
+instead of 0.
+.It Fl V , Fl -version
+Print the version of the program and exit.
+.It Fl c Ar file , Fl -cache Ar file
+Keep a cache between runs in file
+.Ar file .
+.It Fl d , Fl -debug
+Output some debug messages.
+.It Fl h , Fl -help
+Output this page and exit successfully.
+.It Fl n , Fl -dryrun
+Only simulate.
+.It Fl s , Fl -softlinks
+Create soft links instead of hard links.
+.It Fl u , Fl -user
+Don't relink files owned by another user.
+.It Fl v , Fl -verbose
+Output verbose messages.
+.It Fl z , Fl -nullfiles
+Link empty files, too.
+By default, only non-empty files are linked.
+.El
+.Sh EXIT STATUS
+Zero on success, non-zero on failure.
+.Sh EXAMPLES
+.Bd -literal
+find . -type f -print | same
+.Ed
+.Sh SEE ALSO
+.Xr find 1
+.Sh AUTHORS
+.An "Roger E. Wolff" Aq R.E.Wolff@BitWizard.nl ,
+.An "Geert Uytterhoeven" Aq geert@linux-m68k.org ,
+.An "Roland Illig" Aq roland.illig@gmx.de .
+.Sh CAVEATS
+.Bl -bullet
+.It
+If your editor does not move the original aside before writing a
+new copy, you will change the file in ALL incarnations when
+editing a file.
+Patch works just fine: it moves the original aside before creating a new
+copy.
+I'm confident that I could learn Emacs to do it this way too.
+I'm too lazy to figure it out, so if you happen to know an easy way how
+to do this, please Email me at
+.Aq R.E.Wolff@BitWizard.nl .
+.It
+There is a 1024 (BUFSIZE) character limit to pathnames when using 
+symlinks.
+.El

sysutils/same/files/same.cat1

@@ -0,0 +1,99 @@
+SAME(1)                 NetBSD General Commands Manual                 SAME(1)
+
+NNAAMMEE
+     ssaammee -- link identical files to save disk space
+
+SSYYNNOOPPSSIISS
+     ssaammee [--HHVVccddhhnnssttuuvvzz]
+
+DDEESSCCRRIIPPTTIIOONN
+     ssaammee takes a list of files (e.g. the output of find . -type f) on stdin.
+     Each of the files is compared against each of the others.  Whenever two
+     files are found that match exactly, the two files are linked (soft or
+     hard) together.
+
+   GGooaall
+     The goal of this program is to conserve disk space when you have several
+     different trees of large projects on your disk.  By creating hardlinks or
+     softlinks between the files that are the same, you can save lots of disk
+     space.  For example, two different versions of the Linux kernel only dif-
+     fer in a small number of files.  By running this program you only need to
+     store the contents of those files once.  This is especially useful if you
+     have different versions of complete trees lying around.
+
+   IImmpplleemmeennttaattiioonn
+     The filesize of every file is used as an indication of wether two files
+     can be the same. Whenever the filesizes match, the hashes of these two
+     files are compared. Whenever these match, the file contents are compared.
+     For every matching pair one of the two files is replaced by a hard link
+     to the other file.  With the -s option a softlink is used.
+
+     To allow you to do this incrementally, the "rm" is done on the file with
+     the least links. This allows you to "merge" a new tree with several trees
+     that have already been processed. The new tree has link count 1, while
+     the old tree has a higher link count for those files that are likely can-
+     didates for linkage.
+
+     The current implementation keeps the "first" incantation of a file, and
+     replaces further occurrances of the same file. This is significant when
+     using softlinks.
+
+   OOppttiioonnss
+     --HH _n, ----hhaasshhssttaarrtt _n
+             Start at hash value _n instead of 0.
+
+     --VV, ----vveerrssiioonn
+             Print the version of the program and exit.
+
+     --cc _f_i_l_e, ----ccaacchhee _f_i_l_e
+             Keep a cache between runs in file _f_i_l_e.
+
+     --dd, ----ddeebbuugg
+             Output some debug messages.
+
+     --hh, ----hheellpp
+             Output this page and exit successfully.
+
+     --nn, ----ddrryyrruunn
+             Only simulate.
+
+     --ss, ----ssooffttlliinnkkss
+             Create soft links instead of hard links.
+
+     --uu, ----uusseerr
+             Don't relink files owned by another user.
+
+     --vv, ----vveerrbboossee
+             Output verbose messages.
+
+     --zz, ----nnuullllffiilleess
+             Link empty files, too.  By default, only non-empty files are
+             linked.
+
+EEXXIITT SSTTAATTUUSS
+     Zero on success, non-zero on failure.
+
+EEXXAAMMPPLLEESS
+     find . -type f -print | same
+
+SSEEEE AALLSSOO
+     find(1)
+
+AAUUTTHHOORRSS
+     Roger E. Wolff <R.E.Wolff@BitWizard.nl>,
+     Geert Uytterhoeven <geert@linux-m68k.org>,
+     Roland Illig <roland.illig@gmx.de>.
+
+CCAAVVEEAATTSS
+     ··   If your editor does not move the original aside before writing a new
+         copy, you will change the file in ALL incarnations when editing a
+         file.  Patch works just fine: it moves the original aside before cre-
+         ating a new copy.  I'm confident that I could learn Emacs to do it
+         this way too.  I'm too lazy to figure it out, so if you happen to
+         know an easy way how to do this, please Email me at
+         <R.E.Wolff@BitWizard.nl>.
+
+     ··   There is a 1024 (BUFSIZE) character limit to pathnames when using
+         symlinks.
+
+NetBSD 4.0                       July 14, 2004                      NetBSD 4.0

sysutils/same/patches/patch-ac

@@ -0,0 +1,151 @@
+$NetBSD: patch-ac,v 1.2 2006/08/04 22:59:02 rillig Exp $
+
+--- same.c.orig	2004-07-16 19:30:01.000000000 +0200
++++ same.c	2006-08-05 00:57:39.680842400 +0200
+@@ -106,10 +106,9 @@
+  * - There is a 1024 (BUFSIZE) character limit to pathnames when using 
+  *   symlinks.
+  *
+- * - The same source is not exactly 32kbytes long.  However this comment 
+- *   seems to fix that.
+  * */
+ 
++#define _FILE_OFFSET_BITS	64
+ 
+ #include <assert.h>
+ #include <stdio.h>
+@@ -123,16 +122,8 @@
+ #include <sys/times.h>
+ #include <zlib.h>
+ #include <limits.h>
+-
+-#define __USE_LARGEFILE64
+ #include <sys/stat.h>
+ 
+-#if 1
+-/* Why the *&^#$ doesn't sys/stat define this??? */
+-extern int lstat64 (__const char *__restrict __file,
+-                    struct stat64 *__restrict __buf) __THROW;
+-#endif
+-
+ #ifdef __linux__
+ #include <asm/page.h>
+ #else /* !__linux__ */
+@@ -157,6 +148,11 @@ extern int lstat64 (__const char *__rest
+ #define true		1
+ #define false		0
+ 
++#if defined(__GNUC__)
++#  define attribute_unused __attribute__((__unused__))
++#else
++#  define attribute_unused /**/
++#endif
+ 
+ static volatile int stop;
+ static volatile int doing_input;
+@@ -184,7 +180,7 @@ static const char *o_cache;
+ 
+ struct name_entry {
+     struct name_entry *next;
+-    char name[0];
++    char name[1];
+ };
+ 
+ #define F_CRC_VALID		(1 << 0)
+@@ -196,7 +192,7 @@ struct inode_entry {
+     struct name_entry *names;
+     int flags;			/* See F_* definitions above */
+     /* The two fields below may have been read from the cache */
+-    loff_t size;
++    off_t size;
+     unsigned int crc;		/* valid if flags & F_CRC_VALID only */
+     /* The four fields below are valid if flags & F_STAT_VALID only */
+     dev_t device;
+@@ -288,7 +284,7 @@ static void read_list(void);
+ static const char *get_fname(void);
+ static struct inode_entry *get_entry(void);
+ static int __get_stat(struct inode_entry *entry);
+-static unsigned int calc_hash(const struct stat64 *sb);
++static unsigned int calc_hash(const struct stat *sb);
+ static int __get_crc(struct inode_entry *entry);
+ static int cmp(const struct inode_entry *entry1,
+ 	       const struct inode_entry *entry2);
+@@ -379,7 +375,7 @@ static void dump_inode_entry(const struc
+ 
+     printf("%sentry %p size %lu crc %08x device %lx inode %lx nlink %d uid "
+ 	   "%lx\n",
+-	   indent, entry, (unsigned long)entry->size, entry->crc,
++	   indent, (void *)entry, (unsigned long)entry->size, entry->crc,
+ 	   (unsigned long)entry->device, (unsigned long)entry->inode,
+ 	   entry->nlink, (unsigned long)entry->uid);
+     for (names = entry->names; names; names = names->next)
+@@ -429,7 +425,7 @@ static void load_cache(void)
+     gzFile *in;
+     unsigned long line = 0;
+     char *s;
+-    loff_t size;
++    off_t size;
+     unsigned int crc;
+     const char *name;
+     unsigned int hash = 0;
+@@ -659,7 +655,7 @@ static struct name_entry *alloc_name_ent
+     return entry;
+ }
+ 
+-static void delete_name_entry(struct name_entry *entry __attribute__((__unused__)))
++static void delete_name_entry(struct name_entry *entry attribute_unused)
+ {
+     /*
+      *  We don't free names allocated from the pool
+@@ -1168,7 +1164,7 @@ static struct inode_entry *get_entry(voi
+ {
+     const char *buf;
+     struct inode_entry *entry;
+-    struct stat64 sb;
++    struct stat sb;
+     unsigned int hash;
+ 
+     do {
+@@ -1176,7 +1172,7 @@ static struct inode_entry *get_entry(voi
+ 	if (buf == NULL)
+ 	    return NULL;
+ 	stat_stat++;
+-	if (lstat64(buf, &sb) < 0) {
++	if (lstat(buf, &sb) < 0) {
+ 	    fprintf(stderr, "stat %s: %s\n", buf, strerror(errno));
+ 	    exit(1);
+ 	}
+@@ -1204,13 +1200,13 @@ static struct inode_entry *get_entry(voi
+ 
+ static int __get_stat(struct inode_entry *entry)
+ {
+-    struct stat64 sb;
++    struct stat sb;
+     struct name_entry *name;
+ 
+     /* Loop until we find a file that does exist */
+     while ((name = entry->names) != 0) {
+ 	stat_stat++;
+-	if (lstat64(name->name, &sb) < 0)
++	if (lstat(name->name, &sb) < 0)
+ 	    fprintf(stderr, "stat %s: %s\n", name->name, strerror(errno));
+ 	else if (S_ISREG(sb.st_mode)) {
+ 	    entry->device = sb.st_dev;
+@@ -1231,7 +1227,7 @@ static int __get_stat(struct inode_entry
+      *  Calculate the Hash Value for an Inode Entry
+      */
+ 
+-static unsigned int calc_hash(const struct stat64 *sb)
++static unsigned int calc_hash(const struct stat *sb)
+ {
+     return (sb->st_size) % MAXHASH;
+ }
+@@ -1256,7 +1252,7 @@ static int __get_crc(struct inode_entry 
+     }
+ 
+     while ((n = read(f1, b1, BUFSIZE)) > 0)
+-	crc = crc32(crc, b1, n);
++	crc = crc32(crc, (void *)b1, n);
+     close(f1);
+     if (n < 0) {
+ 	fprintf(stderr, "read %s: %s\n", entry->names->name, strerror(errno));