X-Git-Url: https://mattmccutchen.net/rsync/rsync-patches.git/blobdiff_plain/9c85142a129f5df5aac5b732159abe1d695a8edd..d4dd2dd52f48a66395428810389ef31cc0488db7:/detect-renamed.diff

diff --git a/detect-renamed.diff b/detect-renamed.diff
index 591fd9c..706ccd9 100644
--- a/detect-renamed.diff
+++ b/detect-renamed.diff
@@ -34,34 +34,33 @@ TODO:
 
 --- old/compat.c
 +++ new/compat.c
-@@ -48,6 +48,7 @@ extern int preserve_hard_links;
- extern int need_messages_from_generator;
- extern int delete_mode, delete_before, delete_during, delete_after;
- extern int delete_excluded;
+@@ -41,6 +41,7 @@ extern int checksum_seed;
+ extern int basis_dir_cnt;
+ extern int prune_empty_dirs;
+ extern int protocol_version;
 +extern int detect_renamed;
- extern int make_backups;
- extern char *shell_cmd; /* contains VER.SUB string if client is a pre-release */
- extern char *backup_dir, *backup_suffix;
-@@ -208,7 +209,7 @@ void setup_protocol(int f_out,int f_in)
- 	} else if (protocol_version >= 30) {
- 		if (recurse && allow_inc_recurse && !preserve_hard_links
- 		 && !delete_before && !delete_after && !delay_updates
--		 && !prune_empty_dirs && !use_qsort)
-+		 && !prune_empty_dirs && !use_qsort && !detect_renamed)
- 			inc_recurse = 1;
- 		need_messages_from_generator = 1;
- 	}
+ extern int protect_args;
+ extern int preserve_uid;
+ extern int preserve_gid;
+@@ -107,6 +108,7 @@ void set_allow_inc_recurse(void)
+ 		allow_inc_recurse = 0;
+ 	else if (!am_sender
+ 	 && (delete_before || delete_after
++	  || detect_renamed
+ 	  || delay_updates || prune_empty_dirs))
+ 		allow_inc_recurse = 0;
+ 	else if (am_server && !local_server
 --- old/flist.c
 +++ new/flist.c
-@@ -59,6 +59,7 @@ extern int non_perishable_cnt;
+@@ -61,6 +61,7 @@ extern int non_perishable_cnt;
  extern int prune_empty_dirs;
  extern int copy_links;
  extern int copy_unsafe_links;
 +extern int detect_renamed;
  extern int protocol_version;
  extern int sanitize_paths;
- extern struct stats stats;
-@@ -97,6 +98,8 @@ static int64 tmp_dev, tmp_ino;
+ extern int need_unsorted_flist;
+@@ -117,6 +118,8 @@ static int64 tmp_dev, tmp_ino;
  #endif
  static char tmp_sum[MAX_DIGEST_LEN];
  
@@ -70,7 +69,7 @@ TODO:
  static char empty_sum[MAX_DIGEST_LEN];
  static int flist_count_offset; /* for --delete --progress */
  static int dir_count = 0;
-@@ -264,6 +267,45 @@ static int is_excluded(char *fname, int 
+@@ -256,6 +259,45 @@ static int is_excluded(char *fname, int 
  	return 0;
  }
  
@@ -116,13 +115,13 @@ TODO:
  static void send_directory(int f, struct file_list *flist,
  			   char *fbuf, int len, int flags);
  
-@@ -1911,6 +1953,25 @@ struct file_list *send_file_list(int f, 
- 	if (verbose > 2)
- 		rprintf(FINFO, "send_file_list done\n");
+@@ -2169,6 +2211,25 @@ struct file_list *recv_file_list(int f)
+ 
+ 	clean_flist(flist, relative_paths);
  
 +	if (detect_renamed) {
-+		int j = flist->count;
-+		the_fattr_list.count = j;
++		int j = flist->used;
++		the_fattr_list.used = j;
 +		the_fattr_list.files = new_array(struct file_struct *, j);
 +		if (!the_fattr_list.files)
 +			out_of_memory("recv_file_list");
@@ -139,9 +138,9 @@ TODO:
 +		the_fattr_list.high = j;
 +	}
 +
- 	if (inc_recurse) {
- 		add_dirs_to_tree(-1, flist, dir_count);
- 		flist_done_allocating(flist);
+ 	if (protocol_version < 30) {
+ 		/* Recv the io_error flag */
+ 		if (ignore_errors)
 --- old/generator.c
 +++ new/generator.c
 @@ -79,6 +79,7 @@ extern char *basis_dir[];
@@ -151,16 +150,16 @@ TODO:
 +extern int detect_renamed;
  extern int whole_file;
  extern int list_only;
- extern int new_root_dir;
+ extern int read_batch;
 @@ -96,6 +97,7 @@ extern char *backup_suffix;
  extern int backup_suffix_len;
  extern struct file_list *cur_flist, *first_flist, *dir_flist;
  extern struct filter_list_struct server_filter_list;
 +extern struct file_list the_fattr_list;
- #ifdef ICONV_OPTION
- extern int ic_ndx;
- #endif
-@@ -106,6 +108,7 @@ int maybe_ATTRS_REPORT = 0;
+ 
+ int ignore_perishable = 0;
+ int non_perishable_cnt = 0;
+@@ -103,6 +105,7 @@ int maybe_ATTRS_REPORT = 0;
  
  static dev_t dev_zero;
  static int deletion_count = 0; /* used to implement --max-delete */
@@ -168,7 +167,7 @@ TODO:
  static int deldelay_size = 0, deldelay_cnt = 0;
  static char *deldelay_buf = NULL;
  static int deldelay_fd = -1;
-@@ -115,7 +118,8 @@ static int need_retouch_dir_times;
+@@ -112,7 +115,8 @@ static int need_retouch_dir_times;
  static int need_retouch_dir_perms;
  static const char *solo_file = NULL;
  
@@ -178,7 +177,7 @@ TODO:
  #define DEL_RECURSE		(1<<1) /* recurse */
  #define DEL_DIR_IS_EMPTY	(1<<2) /* internal delete_FUNCTIONS use only */
  
-@@ -137,11 +141,120 @@ static int is_backup_file(char *fn)
+@@ -134,11 +138,121 @@ static int is_backup_file(char *fn)
  	return k > 0 && strcmp(fn+k, backup_suffix) == 0;
  }
  
@@ -210,7 +209,7 @@ TODO:
 +				if (fmid->modtime == f->modtime
 +				 && f_name_cmp(fmid, f) == 0)
 +					return -1; /* assume we can't help */
-+				file_checksum(fname, (char*)F_SUM(f), F_LENGTH(f));
++				file_checksum(fname, F_SUM(f), F_LENGTH(f));
 +				f->flags |= FLAG_FILE_SENT;
 +			}
 +			diff = u_memcmp(F_SUM(fmid), F_SUM(f), checksum_len);
@@ -264,7 +263,7 @@ TODO:
 +	STRUCT_STAT st;
 +	int ndx;
 +
-+	if ((ndx = fattr_find(file, fname)) < 0)
++	if (!partial_dir || (ndx = fattr_find(file, fname)) < 0)
 +		return;
 +
 +	fp = the_fattr_list.files[ndx];
@@ -272,21 +271,22 @@ TODO:
 +	/* We don't provide an alternate-basis file if there is a basis file. */
 +	if (link_stat(fn, &st, 0) == 0)
 +		return;
-+	if ((partialptr = partial_dir_fname(fn)) == NULL
-+	 || !handle_partial_dir(partialptr, PDIR_CREATE))
-+		return;
 +
-+	/* We only use the file if we can hard-link it into our tmp dir. */
-+	if (link(fname, partialptr) == 0) {
-+		if (verbose > 2) {
-+			rprintf(FINFO, "found renamed: %s => %s\n",
-+				fname, partialptr);
++	if (!dry_run) {
++		if ((partialptr = partial_dir_fname(fn)) == NULL
++		 || !handle_partial_dir(partialptr, PDIR_CREATE))
++			return;
++		/* We only use the file if we can hard-link it into our tmp dir. */
++		if (link(fname, partialptr) != 0) {
++			if (errno != EEXIST)
++				handle_partial_dir(partialptr, PDIR_DELETE);
++			return;
 +		}
-+		return;
 +	}
 +
-+	if (errno != EEXIST)
-+		handle_partial_dir(partialptr, PDIR_DELETE);
++	/* I think this falls into the -vv category with "%s is uptodate", etc. */
++	if (verbose > 1)
++		rprintf(FINFO, "found renamed: %s => %s\n", fname, fn);
 +}
 +
  /* Delete a file or directory.  If DEL_RECURSE is set in the flags, this will
@@ -299,7 +299,7 @@ TODO:
   */
  static enum delret delete_item(char *fbuf, int mode, char *replace, int flags)
  {
-@@ -163,6 +276,8 @@ static enum delret delete_item(char *fbu
+@@ -160,6 +274,8 @@ static enum delret delete_item(char *fbu
  			goto check_ret;
  		/* OK: try to delete the directory. */
  	}
@@ -308,7 +308,7 @@ TODO:
  
  	if (!replace && max_delete >= 0 && ++deletion_count > max_delete)
  		return DR_AT_LIMIT;
-@@ -209,6 +324,8 @@ static enum delret delete_item(char *fbu
+@@ -206,6 +322,8 @@ static enum delret delete_item(char *fbu
   * its contents, otherwise just checks for content.  Returns DR_SUCCESS or
   * DR_NOT_EMPTY.  Note that fname must point to a MAXPATHLEN buffer!  (The
   * buffer is used for recursion, but returned unchanged.)
@@ -317,7 +317,7 @@ TODO:
   */
  static enum delret delete_dir_contents(char *fname, int flags)
  {
-@@ -228,7 +345,9 @@ static enum delret delete_dir_contents(c
+@@ -225,7 +343,9 @@ static enum delret delete_dir_contents(c
  	save_filters = push_local_filters(fname, dlen);
  
  	non_perishable_cnt = 0;
@@ -327,7 +327,7 @@ TODO:
  	ret = non_perishable_cnt ? DR_NOT_EMPTY : DR_SUCCESS;
  
  	if (!dirlist->used)
-@@ -265,6 +384,8 @@ static enum delret delete_dir_contents(c
+@@ -262,6 +382,8 @@ static enum delret delete_dir_contents(c
  		if (S_ISDIR(fp->mode)
  		 && delete_dir_contents(fname, flags | DEL_RECURSE) != DR_SUCCESS)
  			ret = DR_NOT_EMPTY;
@@ -336,7 +336,7 @@ TODO:
  		if (delete_item(fname, fp->mode, NULL, flags) != DR_SUCCESS)
  			ret = DR_NOT_EMPTY;
  	}
-@@ -417,12 +538,17 @@ static void do_delayed_deletions(char *d
+@@ -414,13 +536,18 @@ static void do_delayed_deletions(char *d
   * all the --delete-WHEN options.  Note that the fbuf pointer must point to a
   * MAXPATHLEN buffer with the name of the directory in it (the functions we
   * call will append names onto the end, but the old dir value will be restored
@@ -352,12 +352,14 @@ TODO:
  	static int already_warned = 0;
  	struct file_list *dirlist;
 -	char delbuf[MAXPATHLEN];
+-	int dlen, i;
 +	char *p, delbuf[MAXPATHLEN];
 +	unsigned remainder;
- 	int dlen, i;
++	int dlen, i, restore_dot = 0;
  
  	if (!fbuf) {
-@@ -433,21 +559,28 @@ static void delete_in_dir(char *fbuf, st
+ 		change_local_filter_dir(NULL, 0, 0);
+@@ -430,21 +557,28 @@ static void delete_in_dir(char *fbuf, st
  	if (verbose > 2)
  		rprintf(FINFO, "delete_in_dir(%s)\n", fbuf);
  
@@ -391,19 +393,22 @@ TODO:
  	if (one_file_system) {
  		if (file->flags & FLAG_TOP_DIR)
  			filesystem_dev = *fs_dev;
-@@ -457,6 +590,11 @@ static void delete_in_dir(char *fbuf, st
+@@ -454,6 +588,14 @@ static void delete_in_dir(char *fbuf, st
  
  	dirlist = get_dirlist(fbuf, dlen, 0);
  
 +	p = fbuf + dlen;
-+	if (dlen != 1 || *fbuf != '/')
++	if (dlen == 1 && *fbuf == '.') {
++		restore_dot = 1;
++		p = fbuf;
++	} else if (dlen != 1 || *fbuf != '/')
 +		*p++ = '/';
 +	remainder = MAXPATHLEN - (p - fbuf);
 +
  	/* If an item in dirlist is not found in flist, delete it
  	 * from the filesystem. */
  	for (i = dirlist->used; i--; ) {
-@@ -469,16 +607,23 @@ static void delete_in_dir(char *fbuf, st
+@@ -466,16 +608,25 @@ static void delete_in_dir(char *fbuf, st
  					f_name(fp, NULL));
  			continue;
  		}
@@ -425,12 +430,14 @@ TODO:
 +			unexplored_dirs++;
  	}
  
++	if (restore_dot)
++		fbuf[0] = '.';
 +	fbuf[dlen] = '\0';
 +
  	flist_free(dirlist);
  }
  
-@@ -508,9 +653,9 @@ static void do_delete_pass(void)
+@@ -505,9 +656,9 @@ static void do_delete_pass(void)
  		 || !S_ISDIR(st.st_mode))
  			continue;
  
@@ -442,21 +449,21 @@ TODO:
  
  	if (do_progress && !am_server)
  		rprintf(FINFO, "                    \r");
-@@ -1073,6 +1218,7 @@ static int try_dests_non(struct file_str
- 	return j;
+@@ -1139,6 +1290,7 @@ static void list_file_entry(struct file_
+ 	}
  }
  
 +static struct bitbag *delayed_bits = NULL;
  static int phase = 0;
  static int dflt_perms;
  
-@@ -1288,8 +1434,12 @@ static void recv_generator(char *fname, 
+@@ -1383,8 +1535,12 @@ static void recv_generator(char *fname, 
  			}
  		}
  		else if (delete_during && f_out != -1 && !phase && dry_run < 2
--		    && (file->flags & FLAG_XFER_DIR))
+-		    && (file->flags & FLAG_CONTENT_DIR))
 -			delete_in_dir(fname, file, &real_sx.st.st_dev);
-+		    && (file->flags & FLAG_XFER_DIR)) {
++		    && (file->flags & FLAG_CONTENT_DIR)) {
 +			if (detect_renamed && real_ret != 0)
 +				unexplored_dirs++;
 +			delete_in_dir(fname, file, &real_sx.st.st_dev,
@@ -465,9 +472,9 @@ TODO:
  		goto cleanup;
  	}
  
-@@ -1561,8 +1711,14 @@ static void recv_generator(char *fname, 
- 		if (preserve_hard_links && F_HLINK_NOT_LAST(file))
+@@ -1662,8 +1818,14 @@ static void recv_generator(char *fname, 
  			goto cleanup;
+ 		}
  #endif
 -		if (stat_errno == ENOENT)
 +		if (stat_errno == ENOENT) {
@@ -481,12 +488,12 @@ TODO:
  		rsyserr(FERROR, stat_errno, "recv_generator: failed to stat %s",
  			full_fname(fname));
  		goto cleanup;
-@@ -1882,6 +2038,12 @@ void generate_files(int f_out, const cha
+@@ -2000,6 +2162,12 @@ void generate_files(int f_out, const cha
  	if (verbose > 2)
  		rprintf(FINFO, "generator starting pid=%ld\n", (long)getpid());
  
 +	if (detect_renamed) {
-+		delayed_bits = bitbag_create(cur_flist->count);
++		delayed_bits = bitbag_create(cur_flist->used);
 +		if (!delete_before && !delete_during)
 +			delete_during = -1;
 +	}
@@ -494,7 +501,7 @@ TODO:
  	if (delete_before && !solo_file && cur_flist->used > 0)
  		do_delete_pass();
  	if (delete_during == 2) {
-@@ -1892,7 +2054,7 @@ void generate_files(int f_out, const cha
+@@ -2010,7 +2178,7 @@ void generate_files(int f_out, const cha
  	}
  	do_progress = 0;
  
@@ -503,7 +510,7 @@ TODO:
  		whole_file = 0;
  	if (verbose >= 2) {
  		rprintf(FINFO, "delta-transmission %s\n",
-@@ -1923,7 +2085,7 @@ void generate_files(int f_out, const cha
+@@ -2048,7 +2216,7 @@ void generate_files(int f_out, const cha
  						dirdev = MAKEDEV(DEV_MAJOR(devp), DEV_MINOR(devp));
  					} else
  						dirdev = MAKEDEV(0, 0);
@@ -512,7 +519,7 @@ TODO:
  				}
  			}
  		}
-@@ -1976,7 +2138,21 @@ void generate_files(int f_out, const cha
+@@ -2091,7 +2259,21 @@ void generate_files(int f_out, const cha
  	} while ((cur_flist = cur_flist->next) != NULL);
  
  	if (delete_during)
@@ -537,7 +544,7 @@ TODO:
  		rprintf(FINFO, "generate_files phase=%d\n", phase);
 --- old/options.c
 +++ new/options.c
-@@ -78,6 +78,7 @@ int am_generator = 0;
+@@ -80,6 +80,7 @@ int am_generator = 0;
  int am_starting_up = 1;
  int relative_paths = -1;
  int implied_dirs = 1;
@@ -545,7 +552,7 @@ TODO:
  int numeric_ids = 0;
  int allow_8bit_chars = 0;
  int force_delete = 0;
-@@ -373,6 +374,7 @@ void usage(enum logcode F)
+@@ -383,6 +384,7 @@ void usage(enum logcode F)
    rprintf(F,"     --modify-window=NUM     compare mod-times with reduced accuracy\n");
    rprintf(F," -T, --temp-dir=DIR          create temporary files in directory DIR\n");
    rprintf(F," -y, --fuzzy                 find similar file for basis if no dest file\n");
@@ -553,7 +560,7 @@ TODO:
    rprintf(F,"     --compare-dest=DIR      also compare destination files relative to DIR\n");
    rprintf(F,"     --copy-dest=DIR         ... and include copies of unchanged files\n");
    rprintf(F,"     --link-dest=DIR         hardlink to files in DIR when unchanged\n");
-@@ -545,6 +547,7 @@ static struct poptOption long_options[] 
+@@ -561,6 +563,7 @@ static struct poptOption long_options[] 
    {"compare-dest",     0,  POPT_ARG_STRING, 0, OPT_COMPARE_DEST, 0, 0 },
    {"copy-dest",        0,  POPT_ARG_STRING, 0, OPT_COPY_DEST, 0, 0 },
    {"link-dest",        0,  POPT_ARG_STRING, 0, OPT_LINK_DEST, 0, 0 },
@@ -561,7 +568,7 @@ TODO:
    {"fuzzy",           'y', POPT_ARG_NONE,   &fuzzy_basis, 0, 0, 0 },
    {"compress",        'z', POPT_ARG_NONE,   0, 'z', 0, 0 },
    {"no-compress",      0,  POPT_ARG_VAL,    &do_compression, 0, 0, 0 },
-@@ -1487,7 +1490,7 @@ int parse_arguments(int *argc, const cha
+@@ -1532,7 +1535,7 @@ int parse_arguments(int *argc_p, const c
  		inplace = 1;
  	}
  
@@ -570,7 +577,7 @@ TODO:
  		partial_dir = tmp_partialdir;
  
  	if (inplace) {
-@@ -1496,6 +1499,7 @@ int parse_arguments(int *argc, const cha
+@@ -1541,6 +1544,7 @@ int parse_arguments(int *argc_p, const c
  			snprintf(err_buf, sizeof err_buf,
  				 "--%s cannot be used with --%s\n",
  				 append_mode ? "append" : "inplace",
@@ -578,18 +585,18 @@ TODO:
  				 delay_updates ? "delay-updates" : "partial-dir");
  			return 0;
  		}
-@@ -1838,6 +1842,8 @@ void server_options(char **args,int *arg
+@@ -1885,6 +1889,8 @@ void server_options(char **args, int *ar
  			args[ac++] = "--super";
  		if (size_only)
  			args[ac++] = "--size-only";
 +		if (detect_renamed)
 +			args[ac++] = "--detect-renamed";
- 	}
- 
- 	if (modify_window_set) {
+ 	} else {
+ 		if (skip_compress) {
+ 			if (asprintf(&arg, "--skip-compress=%s", skip_compress) < 0)
 --- old/rsync.yo
 +++ new/rsync.yo
-@@ -373,6 +373,7 @@ to the detailed description below for a 
+@@ -384,6 +384,7 @@ to the detailed description below for a 
       --modify-window=NUM     compare mod-times with reduced accuracy
   -T, --temp-dir=DIR          create temporary files in directory DIR
   -y, --fuzzy                 find similar file for basis if no dest file
@@ -597,13 +604,19 @@ TODO:
       --compare-dest=DIR      also compare received files relative to DIR
       --copy-dest=DIR         ... and include copies of unchanged files
       --link-dest=DIR         hardlink to files in DIR when unchanged
-@@ -1353,6 +1354,15 @@ Note that the use of the bf(--delete) op
+@@ -1438,6 +1439,21 @@ Note that the use of the bf(--delete) op
  fuzzy-match files, so either use bf(--delete-after) or specify some
  filename exclusions if you need to prevent this.
  
-+dit(bf(--detect-renamed)) This option tells rsync to scan the receiving
-+side for files that have been renamed, and to use any that are found as
-+alternate basis files to help speed up the transfer.
++dit(bf(--detect-renamed)) With this option, for each new source file
++(call it em(src/S)), rsync looks for a file em(dest/D) anywhere in the
++destination that passes the quick check with em(src/S).  If such a em(dest/D)
++is found, rsync uses it as an alternate basis for transferring em(S).  The
++idea is that if em(src/S) was renamed from em(src/D) (as opposed to em(src/S)
++passing the quick check with em(dest/D) by coincidence), the delta-transfer
++algorithm will find that all the data matches between em(src/S) and em(dest/D),
++and the transfer will be really fast.
++
 +By default, alternate-basis files are hard-linked into a directory named
 +".~tmp~" in each file's destination directory, but if you've specified
 +the bf(--partial-dir) option, that directory will be used instead.  These
@@ -615,7 +628,7 @@ TODO:
  files against doing transfers (if the files are missing in the destination
 --- old/util.c
 +++ new/util.c
-@@ -1028,6 +1028,32 @@ int handle_partial_dir(const char *fname
+@@ -1042,6 +1042,32 @@ int handle_partial_dir(const char *fname
  	return 1;
  }