Recently various needs for multiple version handling were discussed
and I put forward a plan of mine. Subsequently the proposal for a
--compare-file=<FILE> switch had support, so I have implemented
this. I have also implemented an experimental --compare-auto which
decides which file to match against using a rule.
Instructions for patch:
1. Install rsync-2.5.6 source
2. "patch -p1 < rsync-2.5.6-arh1.patch" (the code below)
3. edit configure to add "arh1" to the RSYNC_VERSION string and run
./configure, or if you've already run this, edit config.h to add
"arh1" to the RSYNC_VERSION string.
4. "make proto" - to update proto.h file
5. "make"
Here's rsync-2.5.6-arh1.patch:
-----cut here-----
diff -aur rsync-2.5.6/generator.c rsync-arh/generator.c
--- rsync-2.5.6/generator.c Thu Aug 29 14:44:55 2002
+++ rsync-arh/generator.c Fri Oct 17 15:48:56 2003
@@ -5,6 +5,7 @@
Copyright (C) 1996-2000 by Andrew Tridgell
Copyright (C) Paul Mackerras 1996
Copyright (C) 2002 by Martin Pool <mbp@samba.org>
+ Copyright (C) 2003, Andy Henson, Zexia Access Ltd
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
@@ -41,6 +42,8 @@
extern int always_checksum;
extern int modify_window;
extern char *compare_dest;
+extern char *compare_file;
+extern int compare_auto;
extern int link_dest;
@@ -357,29 +360,36 @@
fnamecmp = fname;
- if ((statret == -1) && (compare_dest != NULL)) {
- /* try the file at compare_dest instead */
+ if ((statret == -1) && compare_auto) {
+ compare_file = findcomparename(fname,fnamecmpbuf);
+ } else if ((statret == -1) && (compare_dest != NULL)) {
+ snprintf(fnamecmpbuf,MAXPATHLEN,"%s/%s",
+ compare_dest,fname);
+ compare_file = fnamecmpbuf;
+ }
+
+ if ((statret == -1) && (compare_file != NULL)) {
+ /*try this file instead (--compare-dest, --compare-file, --compare-auto)*/
int saveerrno = errno;
- snprintf(fnamecmpbuf,MAXPATHLEN,"%s/%s",compare_dest,fname);
- statret = link_stat(fnamecmpbuf,&st);
+ statret = link_stat(compare_file,&st);
if (!S_ISREG(st.st_mode))
statret = -1;
if (statret == -1)
errno = saveerrno;
#if HAVE_LINK
else if (link_dest && !dry_run) {
- if (do_link(fnamecmpbuf, fname) != 0) {
+ if (do_link(compare_file, fname) != 0) {
if (verbose > 0)
rprintf(FINFO,"link %s => %s : %s\n",
- fnamecmpbuf,
+ compare_file,
fname,
strerror(errno));
}
- fnamecmp = fnamecmpbuf;
+ fnamecmp = compare_file;
}
#endif
else
- fnamecmp = fnamecmpbuf;
+ fnamecmp = compare_file;
}
if (statret == -1) {
@@ -534,3 +544,86 @@
write_int(f,-1);
}
}
+
+
+
+char * findcomparename(const char* fname, char* buf)
+ /* returns compare name, a valid file with name similar to @param fname.
+ * Implements the --compare-auto name function.
+ * May use @param buf as buffer for the name (size is MAXPATHLEN). */
+
+ /* The algorithm: scans the directory for filenames where the names
+ match once version information is stripped out. Version information
+ is assumed to be digits after one of - . ; and it continues until
+ either . and non-digit or - and non-digit, t, p, r. This rather
+ odd rule permits 2.4-test2, 2.4-rc4, 2.4-pre3 to be ignored as versions.
+ Finally it selects the most recent of these which has a size no smaller
+ than 90% of the biggest of any of them.
+ I acknowlege these are pretty arbitrary rules - arh 17 October 2003 */
+{
+ char newname[MAXPATHLEN];
+ char tmpname[MAXPATHLEN];
+ time_t newtime=0;
+ size_t newsize=0;
+ struct dirent *di;
+ DIR *d;
+ char* dirname;
+ char *name;
+
+ strncpy(buf,fname,MAXPATHLEN);
+ dirname = buf;
+ name = strrchr(buf,'/');
+ if (name)
+ *name++ = 0; //terminate name at end of directory part
+ else {
+ name = (char*)fname;
+ dirname = ".";
+ }
+ if (compare_dest)
+ dirname = compare_dest;
+ if (verbose > 1)
+ rprintf(FINFO,"findcomparename: dir %s name %s\n",dirname,name);
+ d = opendir(dirname);
+ if (d) {
+ for (di = readdir(d); di; di = readdir(d)) {
+ char *dname = d_name(di);
+ char *p = name;
+ char *q = dname;
+ STRUCT_STAT st;
+ /* are files version-stripped names identical? */
+ while (*p && *q && *p==*q) {
+ if ((*p=='-'||*p=='.'||*p==';') &&
isdigit(p[1]))
/* skip version part */
+ do ++p; while (*p && (*p!='-' ||
isdigit(p[1])||p[1]=='t'||p[1]=='p'||p[1]=='r')
&& (*p!='.' || isdigit(p[1])));
+ if ((*q=='-'||*q=='.'||*q==';') &&
isdigit(q[1]))
/* skip version part */
+ do ++q; while (*q && (*q!='-' ||
isdigit(q[1])||q[1]=='t'||q[1]=='p'||q[1]=='r')
&& (*q!='.' || isdigit(q[1])));
+ ++p;
+ ++q;
+ }
+ if (*p != *q)
+ continue; /* not identical */
+ /* identical: take best fit */
+ if (verbose > 1)
+ rprintf(FINFO,"findcomparename: candidate %s\n",dname);
+ strcpy(tmpname,dirname);
+ strcat(tmpname,"/");
+ strncat(tmpname,dname,MAXPATHLEN-strlen(tmpname));
+ tmpname[MAXPATHLEN-1]=0;
+ (void) link_stat(tmpname,&st);
+ if ((st.st_size >= newsize*9/10 && st.st_ctime >= newtime) ||
st.st_size >=
newsize*10/9)
+ {
+ newsize=st.st_size;
+ newtime=st.st_ctime;
+ strcpy(newname,tmpname);
+ }
+ }
+ closedir(d);
+ if (newsize > 0) /* ie, if we found one... */
+ {
+ strcpy(buf,newname);
+ if (verbose > 1)
+ rprintf(FINFO,"findcomparename: chose %s\n",buf);
+ return buf;
+ }
+ }
+ return 0;
+}
diff -aur rsync-2.5.6/options.c rsync-arh/options.c
--- rsync-2.5.6/options.c Tue Jan 28 03:11:57 2003
+++ rsync-arh/options.c Fri Oct 17 15:28:18 2003
@@ -2,6 +2,7 @@
*
* Copyright (C) 1998-2001 by Andrew Tridgell <tridge@samba.org>
* Copyright (C) 2000, 2001, 2002 by Martin Pool <mbp@samba.org>
+ * Copyright (C) 2003, Andy Henson, Zexia Access Ltd
<andy.31016@zexia.co.uk>
*
* 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
@@ -83,6 +84,7 @@
int ignore_errors=0;
int modify_window=0;
int blocking_io=-1;
+int compare_auto=0;
/** Network address family. **/
@@ -104,6 +106,7 @@
char *backup_suffix = BACKUP_SUFFIX;
char *tmpdir = NULL;
char *compare_dest = NULL;
+char *compare_file = NULL;
char *config_file = NULL;
char *shell_cmd = NULL;
char *log_format = NULL;
@@ -155,7 +158,7 @@
rprintf(f, "%s version %s protocol version %d\n",
RSYNC_NAME, RSYNC_VERSION, PROTOCOL_VERSION);
rprintf(f,
- "Copyright (C) 1996-2002 by Andrew Tridgell and
others\n");
+ "Copyright (C) 1996-2003 by Andrew Tridgell and
others\n");
rprintf(f, "<http://rsync.samba.org/>\n");
rprintf(f, "Capabilities: %d-bit files, %ssocketpairs, "
"%shard links, %ssymlinks, batchfiles, \n",
@@ -247,8 +250,10 @@
rprintf(F," -I, --ignore-times don't exclude files that
match length and time\n");
rprintf(F," --size-only only use file size when
determining if a file should be
transferred\n");
rprintf(F," --modify-window=NUM Timestamp window (seconds) for
file match
(default=%d)\n",modify_window);
- rprintf(F," -T --temp-dir=DIR create temporary files in
directory DIR\n");
+ rprintf(F," -T, --temp-dir=DIR create temporary files in
directory DIR\n");
rprintf(F," --compare-dest=DIR also compare destination files
relative to DIR\n");
+ rprintf(F," --compare-file=FILE also compare to FILE\n");
+ rprintf(F," -A, --compare-auto also compare to automatically
selected file\n");
rprintf(F," -P equivalent to --partial
--progress\n");
rprintf(F," -z, --compress compress file data\n");
rprintf(F," --exclude=PATTERN exclude files matching
PATTERN\n");
@@ -345,6 +350,8 @@
{"timeout", 0, POPT_ARG_INT, &io_timeout , 0, 0, 0
},
{"temp-dir", 'T', POPT_ARG_STRING, &tmpdir , 0,
0, 0 },
{"compare-dest", 0, POPT_ARG_STRING, &compare_dest , 0, 0,
0 },
+ {"compare-file", 0, POPT_ARG_STRING, &compare_file , 0, 0,
0 },
+ {"compare-auto", 'A', POPT_ARG_NONE, 0 ,
'A', 0, 0 },
{"link-dest", 0, POPT_ARG_STRING, 0,
OPT_LINK_DEST, 0, 0 },
/* TODO: Should this take an optional int giving the compression level? */
{"compress", 'z', POPT_ARG_NONE,
&do_compression , 0, 0, 0 },
@@ -567,6 +574,10 @@
preserve_devices=1;
break;
+ case 'A':
+ compare_auto=1;
+ break;
+
case OPT_SENDER:
if (!am_server) {
usage(FERROR);
@@ -615,6 +626,13 @@
}
}
+ if ((compare_dest||compare_auto) && compare_file) {
+ snprintf(err_buf,sizeof(err_buf),
+ "--compare-file cannot be used with another --compare-xxx
option\n");
+ rprintf(FERROR,"ERROR: --compare-file cannot be used with another
--compare-xxx
option\n");
+ return 0;
+ }
+
if (write_batch && read_batch) {
snprintf(err_buf,sizeof(err_buf),
"write-batch and read-batch can not be used together\n");
@@ -841,6 +859,13 @@
args[ac++] = link_dest ? "--link-dest" :
"--compare-dest";
args[ac++] = compare_dest;
}
+ if (compare_file && am_sender) {
+ args[ac++] = "--compare-file";
+ args[ac++] = compare_file;
+ }
+ if (compare_auto && am_sender) {
+ args[ac++] = "--compare-auto";
+ }
*argc = ac;
}
diff -aur rsync-2.5.6/proto.h rsync-arh/proto.h
--- rsync-2.5.6/proto.h Mon Jan 27 03:35:09 2003
+++ rsync-arh/proto.h Fri Oct 17 08:26:52 2003
@@ -31,7 +31,7 @@
void sum_init(void);
void sum_update(char *p, int len);
void sum_end(char *sum);
-void close_all(void);
+void close_all();
void _exit_cleanup(int code, const char *file, int line);
void cleanup_disable(void);
void cleanup_set(char *fnametmp, char *fname, struct file_struct *file,
@@ -93,6 +93,7 @@
char *f_name(struct file_struct *f);
void recv_generator(char *fname, struct file_list *flist, int i, int f_out);
void generate_files(int f,struct file_list *flist,char *local_name,int f_recv);
+char * findcomparename(const char* fname, char* buf);
int main(int argc, char *argv[]);
void init_hard_links(struct file_list *flist);
int check_hard_link(struct file_struct *file);
@@ -224,7 +225,6 @@
OFF_T do_lseek(int fd, OFF_T offset, int whence);
void *do_mmap(void *start, int len, int prot, int flags, int fd, OFF_T offset);
char *d_name(struct dirent *di);
-int main(int argc, char **argv);
int main (int argc, char *argv[]);
void set_compression(char *fname);
void send_token(int f,int token,struct map_struct *buf,OFF_T offset,
@@ -232,6 +232,7 @@
int recv_token(int f,char **data);
void see_token(char *data, int toklen);
int main(int argc, char **argv);
+int main(int argc, char **argv);
void add_uid(uid_t uid);
void add_gid(gid_t gid);
void send_uid_list(int f);
diff -aur rsync-2.5.6/receiver.c rsync-arh/receiver.c
--- rsync-2.5.6/receiver.c Mon Jan 20 23:32:17 2003
+++ rsync-arh/receiver.c Fri Oct 17 09:57:48 2003
@@ -2,6 +2,7 @@
Copyright (C) 1996-2000 by Andrew Tridgell
Copyright (C) Paul Mackerras 1996
+ Copyright (C) 2003, Andy Henson, Zexia Access Ltd
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
@@ -34,6 +35,8 @@
extern int io_error;
extern char *tmpdir;
extern char *compare_dest;
+extern char *compare_file;
+extern int compare_auto;
extern int make_backups;
extern char *backup_suffix;
@@ -373,11 +376,17 @@
/* open the file */
fd1 = do_open(fnamecmp, O_RDONLY, 0);
- if ((fd1 == -1) && (compare_dest != NULL)) {
- /* try the file at compare_dest instead */
+ if ((fd1 == -1) && compare_auto) {
+ compare_file = findcomparename(fname,fnamecmpbuf);
+ } else if ((fd1 == -1) && (compare_dest != NULL)) {
snprintf(fnamecmpbuf,MAXPATHLEN,"%s/%s",
compare_dest,fname);
- fnamecmp = fnamecmpbuf;
+ compare_file = fnamecmpbuf;
+ }
+
+ if ((fd1 == -1) && (compare_file != NULL)) {
+ /*try this file instead (--compare-dest, --compare-file, --compare-auto)*/
+ fnamecmp = compare_file;
fd1 = do_open(fnamecmp, O_RDONLY, 0);
}
@@ -446,6 +455,8 @@
if (!am_server) {
log_transfer(file, fname);
+ if (compare_auto && (verbose > 1))
+ rprintf(FINFO,"(compare-file %s)\n",fnamecmp);
}
/* recv file data */
diff -aur rsync-2.5.6/rsync.1 rsync-arh/rsync.1
--- rsync-2.5.6/rsync.1 Tue Jan 28 03:11:57 2003
+++ rsync-arh/rsync.1 Fri Oct 17 10:42:54 2003
@@ -364,6 +364,8 @@
--modify-window=NUM Timestamp window (seconds) for file match
(default=0)
-T --temp-dir=DIR create temporary files in directory DIR
--compare-dest=DIR also compare destination files relative to DIR
+ --compare-file=FILE also compare to FILE
+ -A --compare-auto also compare to automatically selected file
--link-dest=DIR create hardlinks to DIR for unchanged files
-P equivalent to --partial --progress
-z, --compress compress file data
@@ -781,8 +783,8 @@
.IP "\fB--compare-dest=DIR\fP"
This option instructs rsync to use DIR on
the destination machine as an additional directory to compare destination
-files against when doing transfers if the files are missing in the
-destination directory\&. This is useful for doing transfers to a new
+files against when doing transfers {if the files are missing in the
+destination directory}\&. This is useful for doing transfers to a new
destination while leaving existing files intact, and then doing a
flash-cutover when all files have been successfully transferred (for
example by moving directories around and removing the old directory,
@@ -792,6 +794,18 @@
have a chance to be completed\&. If DIR is a relative path, it is relative
to the destination directory\&.
.IP
+.IP "\fB--compare-file=FILE\fP"
+This option instructs rsync to use FILE on the destination machine as
+an additional file to compare against when doing transfers {if the
+files are missing in the destination directory}\&.
+.IP
+.IP "\fB--compare-auto\fP"
+This option instructs rsync to automatically select a file on the destination
+machine to compare against when doing transfers {if the
+files are missing in the destination directory}\&. The file will be
selected
+from the files in the same directory unless --compare-dest is used to select
+another directory\&.
+.IP
.IP "\fB--link-dest=DIR\fP"
This option behaves like \fB--compare-dest\fP but
also will create hard links from \fIDIR\fP to the destination directory for
-----cut here-----
Andy Henson
Zexia Access Ltd
