Added back the alternate.c file that got lost from the patch.

[rsync/rsync-patches.git] / fuzzy.diff

Updated for current CVS version by Wayne Davison.  Passes *MOST* of the
test suite, but otherwise UNTESTED.

--- Makefile.in	15 May 2004 00:48:11 -0000	1.101
+++ Makefile.in	29 Jun 2004 15:14:48 -0000
@@ -32,7 +32,7 @@ ZLIBOBJ=zlib/deflate.o zlib/infblock.o z
 	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
+	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
 OBJS3=progress.o pipe.o
--- /dev/null	1 Jan 1970 00:00:00 -0000
+++ alternate.c	29 Jun 2004 15:14:48 -0000
@@ -0,0 +1,114 @@
+#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 = 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;
+
+	strlcpy(mangled_name, fname, sizeof mangled_name);
+
+	split_names(mangled_name, &dirname, &basename);
+	if (!(d = opendir(dirname))) {
+		rsyserr(FERROR, errno, "recv_generator opendir(%s)", dirname);
+		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 (dname[0] == '.' && (dname[1] == '\0'
+		    || (dname[1] == '.' && dname[2] == '\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];
+
+		pathjoin(fuzzyname,sizeof fuzzyname, dirname, bestname);
+		if (verbose > 2) {
+			rprintf(FINFO, "fuzzy match %s->%s\n",
+				fname, fuzzyname);
+		}
+		return do_open_regular(fuzzyname);
+	}
+	return -1;
+}
+
+int open_alternate_base_comparedir(const char *fname)
+{
+	char fnamebuf[MAXPATHLEN];
+
+	/* try the file at compare_dest instead */
+	pathjoin(fnamebuf, sizeof fnamebuf, compare_dest, fname);
+
+	/* FIXME: now follows symlinks... */
+	return do_open_regular(fnamebuf);
+}
--- generator.c	23 Jun 2004 21:21:19 -0000	1.90
+++ generator.c	29 Jun 2004 15:14:48 -0000
@@ -41,6 +41,7 @@ extern int ignore_times;
 extern int size_only;
 extern int io_timeout;
 extern int protocol_version;
+extern int fuzzy;
 extern int always_checksum;
 extern char *compare_dest;
 extern int link_dest;
@@ -256,7 +257,61 @@ static void generate_and_send_sums(struc
 	}
 }
 
+/* Returns -1 for can't open (null file), -2 for skip */
+static int open_base_file(struct file_struct *file, char *fname, int statret,
+			  STRUCT_STAT *st)
+{
+	int fd = -1;
 
+	if (statret == 0) {
+		if (S_ISREG(st->st_mode)) {
+			if (update_only
+			    && cmp_modtime(st->st_mtime, file->modtime) > 0) {
+				if (verbose > 1)
+					rprintf(FINFO, "%s is newer\n", fname);
+				return -2;
+			}
+			if (skip_file(fname, file, st)) {
+				set_perms(fname, file, st, PERMS_REPORT);
+				return -2;
+			}
+		 	fd = do_open(fname, O_RDONLY, 0);
+			if (fd == -1) {
+				rsyserr(FERROR, errno, "failed to open %s, continuing",
+				    full_fname(fname));
+				return -1;
+			}
+			return fd;
+		} else {
+			/* Try to use symlink contents */
+			if (S_ISLNK(st->st_mode)) {
+				fd = do_open_regular(fname);
+				/* Don't delete yet; receiver will need it */
+			} else {
+				if (delete_file(fname) != 0) {
+					if (fd != -1)
+						close(fd);
+					return -2;
+				}
+			}
+		}
+	}
+
+	if (fd == -1 && compare_dest != NULL)
+		fd = open_alternate_base_comparedir(fname);
+
+	if (fd == -1 && fuzzy)
+		fd = open_alternate_base_fuzzy(fname);
+
+	/* Update stat to understand size */
+	if (fd != -1) {
+		if (do_fstat(fd, st) != 0) {
+			rsyserr(FERROR, errno, "fstat %s", full_fname(fname));
+		}
+	}
+
+	return fd;
+}
 
 /**
  * Acts on file number @p i from @p flist, whose name is @p fname.
@@ -272,8 +327,6 @@ void recv_generator(char *fname, struct 
 	STRUCT_STAT st;
 	struct map_struct *mapbuf;
 	int statret;
-	char *fnamecmp;
-	char fnamecmpbuf[MAXPATHLEN];
 
 	if (list_only)
 		return;
@@ -413,109 +466,39 @@ void recv_generator(char *fname, struct 
 	}
 #endif
 
-	if (preserve_hard_links && hard_link_check(file, HL_CHECK_MASTER))
-		return;
-
-	if (!S_ISREG(file->mode)) {
-		rprintf(FINFO, "skipping non-regular file \"%s\"\n",fname);
-		return;
-	}
-
-	fnamecmp = fname;
-
-	if (statret == -1 && compare_dest != NULL) {
-		/* try the file at compare_dest instead */
-		int saveerrno = errno;
-		pathjoin(fnamecmpbuf, sizeof fnamecmpbuf, compare_dest, fname);
-		statret = link_stat(fnamecmpbuf, &st, 0);
-		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 (verbose > 0) {
-					rsyserr(FINFO, errno, "link %s => %s",
-						fnamecmpbuf, fname);
-				}
-			}
-			fnamecmp = fnamecmpbuf;
-		}
-#endif
-		else
-			fnamecmp = fnamecmpbuf;
-	}
-
-	if (statret == -1) {
-		if (preserve_hard_links && hard_link_check(file, HL_SKIP))
-			return;
-		if (errno == ENOENT) {
-			write_int(f_out,i);
-			if (!dry_run)
-				write_sum_head(f_out, NULL);
-		} else if (verbose > 1) {
+	/* Failed to stat for some reason besides "not found". */
+	if (statret == -1 && errno != ENOENT) {
+		if (verbose > 1) {
 			rsyserr(FERROR, errno,
-				"recv_generator: failed to open %s",
+				"recv_generator failed to stat %s",
 				full_fname(fname));
 		}
 		return;
 	}
 
-	if (!S_ISREG(st.st_mode)) {
-		if (delete_file(fname) != 0) {
-			return;
-		}
+	if ((fd = open_base_file(file, fname, statret, &st)) == -2)
+		return;
 
-		/* now pretend the file didn't exist */
+	if ((disable_deltas_p() || dry_run) && fd != -1) {
+		close(fd);
+		fd = -1;
+	}
+
+	if (fd == -1) {
+		/* the file didn't exist, or we can pretend it doesn't */
 		if (preserve_hard_links && hard_link_check(file, HL_SKIP))
 			return;
-		write_int(f_out,i);
+ 		write_int(f_out, i);
 		if (!dry_run)
 			write_sum_head(f_out, NULL);
-		return;
-	}
-
-	if (opt_ignore_existing && fnamecmp == fname) {
-		if (verbose > 1)
-			rprintf(FINFO,"%s exists\n",fname);
-		return;
-	}
+ 		return;
+ 	}
 
-	if (update_only && cmp_modtime(st.st_mtime,file->modtime)>0 && fnamecmp == fname) {
-		if (verbose > 1)
-			rprintf(FINFO,"%s is newer\n",fname);
-		return;
-	}
-
-	if (skip_file(fname, file, &st)) {
-		if (fnamecmp == fname)
-			set_perms(fname, file, &st, PERMS_REPORT);
-		return;
-	}
-
-	if (dry_run) {
-		write_int(f_out,i);
-		return;
-	}
-
-	if (disable_deltas_p()) {
-		write_int(f_out,i);
-		write_sum_head(f_out, NULL);
+	if (preserve_hard_links && hard_link_check(file, HL_CHECK_MASTER))
 		return;
-	}
 
-	/* open the file */
-	fd = do_open(fnamecmp, O_RDONLY, 0);
-
-	if (fd == -1) {
-		rsyserr(FERROR, errno, "failed to open %s, continuing",
-			full_fname(fnamecmp));
-		/* pretend the file didn't exist */
-		if (preserve_hard_links && hard_link_check(file, HL_SKIP))
-			return;
-		write_int(f_out,i);
-		write_sum_head(f_out, NULL);
+	if (!S_ISREG(file->mode)) {
+		rprintf(FINFO, "skipping non-regular file \"%s\"\n",fname);
 		return;
 	}
 
@@ -525,7 +508,7 @@ void recv_generator(char *fname, struct 
 		mapbuf = NULL;
 
 	if (verbose > 3) {
-		rprintf(FINFO,"gen mapped %s of size %.0f\n", fnamecmp,
+		rprintf(FINFO, "gen mapped %s of size %.0f\n", fname,
 			(double)st.st_size);
 	}
 
--- options.c	20 Jun 2004 19:47:05 -0000	1.157
+++ options.c	29 Jun 2004 15:14:48 -0000
@@ -94,6 +94,7 @@ int ignore_errors = 0;
 int modify_window = 0;
 int blocking_io = -1;
 int checksum_seed = 0;
+int fuzzy = 0;
 unsigned int block_size = 0;
 
 
@@ -270,6 +271,7 @@ void usage(enum logcode F)
   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,"     --link-dest=DIR         create hardlinks to DIR for unchanged files\n");
+  rprintf(F,"     --fuzzy                 use similar file as basis if basis doesn't exist\n");
   rprintf(F," -P                          equivalent to --partial --progress\n");
   rprintf(F," -z, --compress              compress file data\n");
   rprintf(F," -C, --cvs-exclude           auto ignore files in the same way CVS does\n");
@@ -368,6 +370,7 @@ static struct poptOption long_options[] 
   {"temp-dir",        'T', POPT_ARG_STRING, &tmpdir, 0, 0, 0 },
   {"compare-dest",     0,  POPT_ARG_STRING, &compare_dest, 0, 0, 0 },
   {"link-dest",        0,  POPT_ARG_STRING, &compare_dest,  OPT_LINK_DEST, 0, 0 },
+  {"fuzzy",            0,  POPT_ARG_NONE,   &fuzzy, 0, 0, 0 },
   /* TODO: Should this take an optional int giving the compression level? */
   {"compress",        'z', POPT_ARG_NONE,   &do_compression, 0, 0, 0 },
   {"daemon",           0,  POPT_ARG_NONE,   &daemon_opt, 0, 0, 0 },
@@ -989,6 +992,9 @@ void server_options(char **args,int *arg
 		}
 	}
 
+	if (fuzzy && am_sender)
+		args[ac++] = "--fuzzy";
+
 	*argc = ac;
 	return;
 
--- receiver.c	29 Jun 2004 15:12:01 -0000	1.83
+++ receiver.c	29 Jun 2004 15:14:48 -0000
@@ -48,6 +48,7 @@ extern int ignore_errors;
 extern int orig_umask;
 extern int keep_partial;
 extern int checksum_seed;
+extern int fuzzy;
 
 static void delete_one(char *fn, int is_dir)
 {
@@ -300,8 +301,6 @@ int recv_files(int f_in,struct file_list
 	char *fname, fbuf[MAXPATHLEN];
 	char template[MAXPATHLEN];
 	char fnametmp[MAXPATHLEN];
-	char *fnamecmp;
-	char fnamecmpbuf[MAXPATHLEN];
 	struct map_struct *mapbuf;
 	struct file_struct *file;
 	struct stats initial_stats;
@@ -364,35 +363,31 @@ int recv_files(int f_in,struct file_list
 		if (verbose > 2)
 			rprintf(FINFO,"recv_files(%s)\n",fname);
 
-		fnamecmp = fname;
-
 		/* open the file */
-		fd1 = do_open(fnamecmp, O_RDONLY, 0);
+		fd1 = do_open(fname, O_RDONLY, 0);
 
-		if (fd1 == -1 && compare_dest != NULL) {
-			/* try the file at compare_dest instead */
-			pathjoin(fnamecmpbuf, sizeof fnamecmpbuf,
-				 compare_dest, fname);
-			fnamecmp = fnamecmpbuf;
-			fd1 = do_open(fnamecmp, O_RDONLY, 0);
-		}
+		if (fd1 == -1 && compare_dest != NULL)
+			fd1 = open_alternate_base_comparedir(fname);
+
+		if (fd1 == -1 && fuzzy)
+			fd1 = open_alternate_base_fuzzy(fname);
 
 		if (fd1 != -1 && do_fstat(fd1,&st) != 0) {
 			rsyserr(FERROR, errno, "fstat %s failed",
-				full_fname(fnamecmp));
+				full_fname(fname));
 			receive_data(f_in,NULL,-1,NULL,file->length);
 			close(fd1);
 			continue;
 		}
 
-		if (fd1 != -1 && S_ISDIR(st.st_mode) && fnamecmp == fname) {
+		if (fd1 != -1 && S_ISDIR(st.st_mode)) {
 			/* this special handling for directories
 			 * wouldn't be necessary if robust_rename()
 			 * and the underlying robust_unlink could cope
 			 * with directories
 			 */
 			rprintf(FERROR,"recv_files: %s is a directory\n",
-				full_fname(fnamecmp));
+				full_fname(fname));
 			receive_data(f_in, NULL, -1, NULL, file->length);
 			close(fd1);
 			continue;
@@ -415,7 +410,7 @@ int recv_files(int f_in,struct file_list
 			mapbuf = map_file(fd1,st.st_size);
 			if (verbose > 2) {
 				rprintf(FINFO, "recv mapped %s of size %.0f\n",
-					fnamecmp, (double)st.st_size);
+					fname, (double)st.st_size);
 			}
 		} else
 			mapbuf = NULL;
--- rsync.yo	5 Jun 2004 16:16:30 -0000	1.171
+++ rsync.yo	29 Jun 2004 15:14:49 -0000
@@ -325,6 +325,7 @@ verb(
  -T  --temp-dir=DIR          create temporary files in directory DIR
      --compare-dest=DIR      also compare received files relative to DIR
      --link-dest=DIR         create hardlinks to DIR for unchanged files
+     --fuzzy                 use similar file as basis if basis is gone
  -P                          equivalent to --partial --progress
  -z, --compress              compress file data
  -C, --cvs-exclude           auto ignore files in the same way CVS does