On 5 Jan 2005, Rusty Russell <[EMAIL PROTECTED]> wrote:
> On Tue, 2005-01-04 at 18:24 +0100, Robert Lemmen wrote:
> > hi rusty,
> >
> > i read on some webpage about rsync and debian that you wrote a patch to
> > rsync that let's it uses heuristics when deciding which local file to
> > use. could you tell me whether this is planned to be included in a rsync
> > release? could i have that patch?
>
> Hmm, good question. This is from 2.5.4, and can't remember how well it
> worked. Good luck!
I'm not the rsync maintainer anymore, but I think it would be cool if
this were merged, if the current team feels OK about it.
>
> Rusty.
>
> diff -urN rsync-2.5.4/Makefile.in rsync-2.5.4-fuzzy/Makefile.in
> --- rsync-2.5.4/Makefile.in 2002-02-26 05:48:25.0 +1100
> +++ rsync-2.5.4-fuzzy/Makefile.in 2002-04-03 16:35:55.0 +1000
> @@ -28,7 +28,7 @@
> ZLIBOBJ=zlib/deflate.o zlib/infblock.o zlib/infcodes.o zlib/inffast.o \
> zlib/inflate.o zlib/inftrees.o zlib/infutil.o zlib/trees.o \
> zlib/zutil.o zlib/adler32.o
> -OBJS1=rsync.o generator.o receiver.o cleanup.o sender.o exclude.o util.o
> main.o checksum.o match.o syscall.o log.o backup.o
> +OBJS1=rsync.o generator.o receiver.o cleanup.o sender.o exclude.o util.o
> main.o checksum.o match.o syscall.o log.o backup.o alternate.o
> OBJS2=options.o flist.o io.o compat.o hlink.o token.o uidlist.o socket.o
> fileio.o batch.o \
> clientname.o
> DAEMON_OBJ = params.o loadparm.o clientserver.o access.o connection.o
> authenticate.o
> diff -urN rsync-2.5.4/alternate.c rsync-2.5.4-fuzzy/alternate.c
> --- rsync-2.5.4/alternate.c 1970-01-01 10:00:00.0 +1000
> +++ rsync-2.5.4-fuzzy/alternate.c 2002-04-03 17:04:15.0 +1000
> @@ -0,0 +1,117 @@
> +#include "rsync.h"
> +
> +extern char *compare_dest;
> +extern int verbose;
> +
> +/* Alternate methods for opening files, if local doesn't exist */
> +/* Sanity check that we are about to open regular file */
> +int do_open_regular(char *fname)
> +{
> + STRUCT_STAT st;
> +
> + if (do_stat(fname, &st) == 0 && S_ISREG(st.st_mode))
> + return do_open(fname, O_RDONLY, 0);
> +
> + return -1;
> +}
> +
> +static void split_names(char *fname, char **dirname, char **basename)
> +{
> + char *slash;
> +
> + slash = strrchr(fname, '/');
> + if (slash) {
> + *dirname = fname;
> + *slash = '\0';
> + *basename = slash+1;
> + } else {
> + *basename = fname;
> + *dirname = ".";
> + }
> +}
> +
> +static unsigned int measure_name(const char *name,
> + const char *basename,
> + const char *ext)
> +{
> + int namelen = strlen(name);
> + int extlen = strlen(ext);
> + unsigned int score = 0;
> +
> + /* Extensions must match */
> + if (namelen <= extlen || strcmp(name+namelen-extlen, ext) != 0)
> + return 0;
> +
> + /* Now score depends on similarity of prefix */
> + for (; *name==*basename && *name; name++, basename++)
> + score++;
> + return score;
> +}
> +
> +int open_alternate_base_fuzzy(const char *fname)
> +{
> + DIR *d;
> + struct dirent *di;
> + char *basename, *dirname;
> + char mangled_name[MAXPATHLEN];
> + char bestname[MAXPATHLEN];
> + unsigned int bestscore = 0;
> + const char *ext;
> +
> + /* FIXME: can we assume fname fits here? */
> + strcpy(mangled_name, fname);
> +
> + split_names(mangled_name, &dirname, &basename);
> + d = opendir(dirname);
> + if (!d) {
> + rprintf(FERROR,"recv_generator opendir(%s): %s\n",
> + dirname,strerror(errno));
> + return -1;
> + }
> +
> + /* Get final extension, eg. .gz; never full basename though. */
> + ext = strrchr(basename + 1, '.');
> + if (!ext)
> + ext = basename + strlen(basename); /* ext = "" */
> +
> + while ((di = readdir(d)) != NULL) {
> + const char *dname = d_name(di);
> + unsigned int score;
> +
> + if (strcmp(dname,".")==0 ||
> + strcmp(dname,"..")==0)
> + continue;
> +
> + score = measure_name(dname, basename, ext);
> + if (verbose > 4)
> + rprintf(FINFO,"fuzzy score for %s = %u\n",
> + dname, score);
> + if (score > bestscore) {
> + strcpy(bestname, dname);
> + bestscore = score;
> + }
> + }
> + closedir(d);
> +
> + /* Found a candidate. */
> + if (bestscore != 0) {
> + char fuzzyname[MAXPATHLEN];
> +
> + snprintf(fuzzyname,MAXPATHLEN,"%s/%s", dirname, bestname);
> + if (verbose > 2)
> + rprintf(FINFO,"fuzzy match %s->%s\n",
> + fname, fuzzyname);
> + return do_open_r
