Merged in the g2r-basis-filename.diff changes so that the receiver

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

Wayne Davison wrote:

I greatly simplified the changes to generator.c, making the patch
easier to maintain and fixing the failing test in the testsuite.
Very lightly tested (by me).

--- Makefile.in	15 May 2004 00:48:11 -0000	1.101
+++ Makefile.in	29 Jun 2004 17:46:12 -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 17:46:12 -0000
@@ -0,0 +1,105 @@
+#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 */
+static 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 check_alternate_base_fuzzy(char **fname_ptr, char *buf,
+			       STRUCT_STAT *st_ptr)
+{
+	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_ptr, 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, "[%s] fuzzy score for %s = %u\n",
+				who_am_i(), dname, score);
+		}
+		if (score > bestscore) {
+			strlcpy(bestname, dname, sizeof bestname);
+			bestscore = score;
+		}
+	}
+	closedir(d);
+
+	/* Found a candidate. */
+	if (bestscore != 0) {
+		pathjoin(buf, MAXPATHLEN, dirname, bestname);
+		if (verbose > 2) {
+			rprintf(FINFO, "[%s] fuzzy match %s->%s\n",
+				who_am_i(), *fname_ptr, buf);
+		}
+		*fname_ptr = buf;
+		if (st_ptr)
+			return link_stat(buf, st_ptr, 0);
+		return do_open_regular(buf);
+	}
+	return -1;
+}
--- generator.c	29 Jun 2004 16:22:54 -0000	1.91
+++ generator.c	29 Jun 2004 17:46:12 -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;
@@ -271,7 +272,7 @@ void recv_generator(char *fname, struct 
 	int fd;
 	STRUCT_STAT st;
 	struct map_struct *mapbuf;
-	int statret;
+	int statret, fuzzy_file = 0;
 	char *fnamecmp;
 	char fnamecmpbuf[MAXPATHLEN];
 
@@ -447,6 +448,15 @@ void recv_generator(char *fname, struct 
 			fnamecmp = fnamecmpbuf;
 	}
 
+	if (statret == -1 && fuzzy) {
+		statret = check_alternate_base_fuzzy(&fnamecmp, fnamecmpbuf,
+						     &st);
+		if (!S_ISREG(st.st_mode))
+			statret = -1;
+		else
+			fuzzy_file = 1;
+	}
+
 	if (statret == -1) {
 		if (preserve_hard_links && hard_link_check(file, HL_SKIP))
 			return;
@@ -489,7 +499,7 @@ void recv_generator(char *fname, struct 
 		return;
 	}
 
-	if (skip_file(fname, file, &st)) {
+	if (!fuzzy_file && skip_file(fname, file, &st)) {
 		if (fnamecmp == fname)
 			set_perms(fname, file, &st, PERMS_REPORT);
 		return;
--- options.c	20 Jun 2004 19:47:05 -0000	1.157
+++ options.c	29 Jun 2004 17:46:13 -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 17:46:13 -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)
 {
@@ -377,6 +378,11 @@ int recv_files(int f_in,struct file_list
 			fd1 = do_open(fnamecmp, O_RDONLY, 0);
 		}
 
+		if (fd1 == -1 && fuzzy) {
+			fd1 = check_alternate_base_fuzzy(&fnamecmp, fnamecmpbuf,
+							 NULL);
+		}
+
 		if (fd1 != -1 && do_fstat(fd1,&st) != 0) {
 			rsyserr(FERROR, errno, "fstat %s failed",
 				full_fname(fnamecmp));
--- rsync.yo	5 Jun 2004 16:16:30 -0000	1.171
+++ rsync.yo	29 Jun 2004 17:46:14 -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