X-Git-Url: https://mattmccutchen.net/rsync/rsync-patches.git/blobdiff_plain/9a70b74359eebd085847e3937f59bc16919615da..refs/heads/master:/detect-renamed.diff diff --git a/detect-renamed.diff b/detect-renamed.diff index f63b881..2df5d30 100644 --- a/detect-renamed.diff +++ b/detect-renamed.diff @@ -32,49 +32,120 @@ TODO: a file that can't use it, while missing out on giving it to a file that could use it. ---- old/flist.c -+++ new/flist.c -@@ -51,6 +51,7 @@ extern int implied_dirs; +based-on: a01e3b490eb36ccf9e704840e1b6683dab867550 +diff --git a/compat.c b/compat.c +--- a/compat.c ++++ b/compat.c +@@ -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 protect_args; + extern int preserve_uid; + extern int preserve_gid; +@@ -121,6 +122,7 @@ 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 +diff --git a/delete.c b/delete.c +--- a/delete.c ++++ b/delete.c +@@ -25,6 +25,7 @@ + extern int am_root; + extern int make_backups; + extern int max_delete; ++extern int detect_renamed; + extern char *backup_dir; + extern char *backup_suffix; + extern int backup_suffix_len; +@@ -45,6 +46,8 @@ static inline int is_backup_file(char *fn) + * 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.) ++ * ++ * Note: --detect-rename may use this routine with DEL_NO_DELETIONS set! + */ + static enum delret delete_dir_contents(char *fname, uint16 flags) + { +@@ -64,7 +67,9 @@ static enum delret delete_dir_contents(char *fname, uint16 flags) + save_filters = push_local_filters(fname, dlen); + + non_perishable_cnt = 0; ++ file_extra_cnt += SUM_EXTRA_CNT; + dirlist = get_dirlist(fname, dlen, 0); ++ file_extra_cnt -= SUM_EXTRA_CNT; + ret = non_perishable_cnt ? DR_NOT_EMPTY : DR_SUCCESS; + + if (!dirlist->used) +@@ -104,7 +109,8 @@ static enum delret delete_dir_contents(char *fname, uint16 flags) + if (S_ISDIR(fp->mode)) { + if (delete_dir_contents(fname, flags | DEL_RECURSE) != DR_SUCCESS) + ret = DR_NOT_EMPTY; +- } ++ } else if (detect_renamed && S_ISREG(fp->mode)) ++ look_for_rename(fp, fname); + if (delete_item(fname, fp->mode, flags) != DR_SUCCESS) + ret = DR_NOT_EMPTY; + } +@@ -127,6 +133,8 @@ static enum delret delete_dir_contents(char *fname, uint16 flags) + * + * Note that fbuf must point to a MAXPATHLEN buffer if the mode indicates it's + * a directory! (The buffer is used for recursion, but returned unchanged.) ++ * ++ * Also note: --detect-rename may use this routine with DEL_NO_DELETIONS set! + */ + enum delret delete_item(char *fbuf, uint16 mode, uint16 flags) + { +diff --git a/flist.c b/flist.c +--- a/flist.c ++++ b/flist.c +@@ -63,6 +63,7 @@ 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; -@@ -68,6 +69,8 @@ int checksum_len; - dev_t filesystem_dev; /* used to implement -x */ - unsigned int file_struct_len; + extern int munge_symlinks; +@@ -134,6 +135,8 @@ static int64 tmp_dev, tmp_ino; + #endif + static char tmp_sum[MAX_DIGEST_LEN]; +struct file_list the_fattr_list; + - static char empty_sum[MD4_SUM_LENGTH]; - static int flist_count_offset; + static char empty_sum[MAX_DIGEST_LEN]; + static int flist_count_offset; /* for --delete --progress */ -@@ -250,6 +253,44 @@ static mode_t from_wire_mode(int mode) - return mode; +@@ -301,6 +304,45 @@ static int is_excluded(const char *fname, int is_dir, int filter_level) + return 0; } +static int fattr_compare(struct file_struct **file1, struct file_struct **file2) +{ + struct file_struct *f1 = *file1; + struct file_struct *f2 = *file2; ++ int64 len1 = F_LENGTH(f1), len2 = F_LENGTH(f2); + int diff; + -+ if (!f1->basename || !S_ISREG(f1->mode) || !f1->length) { -+ if (!f2->basename || !S_ISREG(f2->mode) || !f2->length) ++ if (!f1->basename || !S_ISREG(f1->mode) || !len1) { ++ if (!f2->basename || !S_ISREG(f2->mode) || !len2) + return 0; + return 1; + } -+ if (!f2->basename || !S_ISREG(f2->mode) || !f2->length) ++ if (!f2->basename || !S_ISREG(f2->mode) || !len2) + return -1; + + /* Don't use diff for values that are longer than an int. */ -+ if (f1->length != f2->length) -+ return f1->length < f2->length ? -1 : 1; ++ if (len1 != len2) ++ return len1 < len2 ? -1 : 1; + + if (always_checksum) { -+ diff = u_memcmp(f1->u.sum, f2->u.sum, checksum_len); ++ diff = u_memcmp(F_SUM(f1), F_SUM(f2), checksum_len); + if (diff) + return diff; + } else if (f1->modtime != f2->modtime) @@ -94,70 +165,187 @@ TODO: +} + static void send_directory(int f, struct file_list *flist, - char *fbuf, int len); + char *fbuf, int len, int flags); -@@ -1379,6 +1420,25 @@ struct file_list *recv_file_list(int f) +@@ -2548,6 +2590,25 @@ struct file_list *recv_file_list(int f) - clean_flist(flist, relative_paths, 1); + flist_sort_and_clean(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) -+ goto oom; ++ out_of_memory("recv_file_list"); + memcpy(the_fattr_list.files, flist->files, + j * sizeof (struct file_struct *)); + qsort(the_fattr_list.files, j, -+ sizeof the_fattr_list.files[0], (int (*)())fattr_compare); ++ sizeof the_fattr_list.files[0], (int (*)())fattr_compare); + the_fattr_list.low = 0; + while (j-- > 0) { + struct file_struct *fp = the_fattr_list.files[j]; -+ if (fp->basename && S_ISREG(fp->mode) && fp->length) ++ if (fp->basename && S_ISREG(fp->mode) && F_LENGTH(fp)) + break; + } + the_fattr_list.high = j; + } + - if (f >= 0) { - recv_uid_list(f, flist); - ---- old/generator.c -+++ new/generator.c -@@ -76,6 +76,7 @@ extern char *basis_dir[]; + if (protocol_version < 30) { + /* Recv the io_error flag */ + int err = read_int(f); +diff --git a/generator.c b/generator.c +--- a/generator.c ++++ b/generator.c +@@ -80,6 +80,7 @@ extern char *partial_dir; extern int compare_dest; extern int copy_dest; extern int link_dest; +extern int detect_renamed; extern int whole_file; extern int list_only; - extern int new_root_dir; -@@ -91,12 +92,15 @@ extern char *backup_dir; - extern char *backup_suffix; - extern int backup_suffix_len; - extern struct file_list *the_file_list; + extern int read_batch; +@@ -97,10 +98,12 @@ extern char *tmpdir; + extern char *basis_dir[MAX_BASIS_DIRS+1]; + extern struct file_list *cur_flist, *first_flist, *dir_flist; + extern filter_rule_list filter_list, daemon_filter_list; +extern struct file_list the_fattr_list; - extern struct filter_list_struct server_filter_list; - static int deletion_count = 0; /* used to implement --max-delete */ + int maybe_ATTRS_REPORT = 0; + + static dev_t dev_zero; +static int unexplored_dirs = 1; + static int deldelay_size = 0, deldelay_cnt = 0; + static char *deldelay_buf = NULL; + static int deldelay_fd = -1; +@@ -180,6 +183,8 @@ static int remember_delete(struct file_struct *file, const char *fname, int flag + if (!flush_delete_delay()) + return 0; + } ++ if (flags & DEL_NO_DELETIONS) ++ return DR_SUCCESS; + + return 1; + } +@@ -271,13 +276,18 @@ static void do_delayed_deletions(char *delbuf) + * 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 +- * on exit). */ +-static void delete_in_dir(char *fbuf, struct file_struct *file, dev_t *fs_dev) ++ * on exit). ++ * ++ * Note: --detect-rename may use this routine with DEL_NO_DELETIONS set! ++ */ ++static void delete_in_dir(char *fbuf, struct file_struct *file, dev_t *fs_dev, ++ int del_flags) + { + static int already_warned = 0; + struct file_list *dirlist; +- char delbuf[MAXPATHLEN]; +- int dlen, i; ++ char *p, delbuf[MAXPATHLEN]; ++ unsigned remainder; ++ int dlen, i, restore_dot = 0; + int save_uid_ndx = uid_ndx; + + if (!fbuf) { +@@ -292,17 +302,22 @@ static void delete_in_dir(char *fbuf, struct file_struct *file, dev_t *fs_dev) + maybe_send_keepalive(time(NULL), True); + + if (io_error && !ignore_errors) { +- if (already_warned) ++ if (!already_warned) { ++ rprintf(FINFO, ++ "IO error encountered -- skipping file deletion\n"); ++ already_warned = 1; ++ } ++ if (!detect_renamed) + return; +- rprintf(FINFO, +- "IO error encountered -- skipping file deletion\n"); +- already_warned = 1; +- return; ++ del_flags |= DEL_NO_DELETIONS; + } --/* For calling delete_file() */ -+/* For calling delete_item() and delete_in_dir() */ - #define DEL_FORCE_RECURSE (1<<1) /* recurse even w/o --force */ -+#define DEL_NO_DELETIONS (1<<2) - #define DEL_TERSE (1<<3) + dlen = strlen(fbuf); + change_local_filter_dir(fbuf, dlen, F_DEPTH(file)); - enum nonregtype { -@@ -109,12 +113,120 @@ static int is_backup_file(char *fn) - return k > 0 && strcmp(fn+k, backup_suffix) == 0; ++ if (detect_renamed) ++ unexplored_dirs--; ++ + if (one_file_system) { + if (file->flags & FLAG_TOP_DIR) + filesystem_dev = *fs_dev; +@@ -315,6 +330,14 @@ static void delete_in_dir(char *fbuf, struct file_struct *file, dev_t *fs_dev) + + dirlist = get_dirlist(fbuf, dlen, 0); + ++ p = fbuf + dlen; ++ 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--; ) { +@@ -327,6 +350,10 @@ static void delete_in_dir(char *fbuf, struct file_struct *file, dev_t *fs_dev) + f_name(fp, NULL)); + continue; + } ++ if (detect_renamed && S_ISREG(fp->mode)) { ++ strlcpy(p, fp->basename, remainder); ++ look_for_rename(fp, fbuf); ++ } + /* Here we want to match regardless of file type. Replacement + * of a file with one of another type is handled separately by + * a delete_item call with a DEL_MAKE_ROOM flag. */ +@@ -335,14 +362,19 @@ static void delete_in_dir(char *fbuf, struct file_struct *file, dev_t *fs_dev) + if (!(fp->mode & S_IWUSR) && !am_root && (uid_t)F_OWNER(fp) == our_uid) + flags |= DEL_NO_UID_WRITE; + f_name(fp, delbuf); +- if (delete_during == 2) { +- if (!remember_delete(fp, delbuf, flags)) ++ if (delete_during == 2 && !(del_flags & DEL_NO_DELETIONS)) { ++ if (!remember_delete(fp, delbuf, del_flags | flags)) + break; + } else +- delete_item(delbuf, fp->mode, flags); +- } ++ delete_item(delbuf, fp->mode, del_flags | flags); ++ } else if (detect_renamed && S_ISDIR(fp->mode)) ++ unexplored_dirs++; + } + ++ if (restore_dot) ++ fbuf[0] = '.'; ++ fbuf[dlen] = '\0'; ++ + flist_free(dirlist); + + if (!save_uid_ndx) { +@@ -380,14 +412,122 @@ static void do_delete_pass(void) + || !S_ISDIR(st.st_mode)) + continue; + +- delete_in_dir(fbuf, file, &st.st_dev); ++ delete_in_dir(fbuf, file, &st.st_dev, 0); + } +- delete_in_dir(NULL, NULL, &dev_zero); ++ delete_in_dir(NULL, NULL, &dev_zero, 0); + + if (INFO_GTE(FLIST, 2) && !am_server) + rprintf(FINFO, " \r"); } +/* Search for a regular file that matches either (1) the size & modified + * time (plus the basename, if possible) or (2) the size & checksum. If + * we find an exact match down to the dirname, return -1 because we found + * an up-to-date file in the transfer, not a renamed file. */ -+static int fattr_find(struct file_struct *f, char *fname, alloc_pool_t pool) ++static int fattr_find(struct file_struct *f, char *fname) +{ + int low = the_fattr_list.low, high = the_fattr_list.high; + int mid, ok_match = -1, good_match = -1; @@ -167,23 +355,24 @@ TODO: + while (low <= high) { + mid = (low + high) / 2; + fmid = the_fattr_list.files[mid]; -+ if (fmid->length != f->length) { -+ if (fmid->length < f->length) ++ if (F_LENGTH(fmid) != F_LENGTH(f)) { ++ if (F_LENGTH(fmid) < F_LENGTH(f)) + low = mid + 1; + else + high = mid - 1; + continue; + } + if (always_checksum) { -+ if (!f->u.sum) { ++ /* We use the FLAG_FILE_SENT flag to indicate when we ++ * have computed the checksum for an entry. */ ++ if (!(f->flags & FLAG_FILE_SENT)) { + if (fmid->modtime == f->modtime + && f_name_cmp(fmid, f) == 0) + return -1; /* assume we can't help */ -+ f->u.sum = pool_alloc(pool, MD4_SUM_LENGTH, -+ "fattr_find"); -+ file_checksum(fname, f->u.sum, f->length); ++ file_checksum(fname, F_SUM(f), F_LENGTH(f)); ++ f->flags |= FLAG_FILE_SENT; + } -+ diff = u_memcmp(fmid->u.sum, f->u.sum, checksum_len); ++ diff = u_memcmp(F_SUM(fmid), F_SUM(f), checksum_len); + if (diff) { + if (diff < 0) + low = mid + 1; @@ -227,15 +416,14 @@ TODO: + return good_match >= 0 ? good_match : ok_match; +} + -+static void look_for_rename(struct file_struct *file, char *fname, -+ alloc_pool_t pool) ++void look_for_rename(struct file_struct *file, char *fname) +{ + struct file_struct *fp; + char *partialptr, *fn; + STRUCT_STAT st; + int ndx; + -+ if ((ndx = fattr_find(file, fname, pool)) < 0) ++ if (!partial_dir || (ndx = fattr_find(file, fname)) < 0) + return; + + fp = the_fattr_list.files[ndx]; @@ -243,270 +431,133 @@ 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 (INFO_GTE(MISC, 2)) ++ rprintf(FINFO, "found renamed: %s => %s\n", fname, fn); +} - - /* Delete a file or directory. If DEL_FORCE_RECURSE is set in the flags, or if - * force_delete is set, this will delete recursively. - * - * Note that fname must point to a MAXPATHLEN buffer if the mode indicates it's - * a directory! (The buffer is used for recursion, but returned unchanged.) -+ * -+ * Also Note: --detect-rename may use this routine with DEL_NO_DELETIONS set! - */ - static int delete_item(char *fname, int mode, int flags) - { -@@ -125,6 +237,8 @@ static int delete_item(char *fname, int - char *p; - - if (!S_ISDIR(mode)) { -+ if (flags & DEL_NO_DELETIONS) -+ return 0; - if (max_delete && ++deletion_count > max_delete) - return 0; - if (make_backups && (backup_dir || !is_backup_file(fname))) -@@ -147,6 +261,7 @@ static int delete_item(char *fname, int - - zap_dir = flags & DEL_FORCE_RECURSE || force_delete; - if ((max_delete && ++deletion_count > max_delete) -+ || flags & DEL_NO_DELETIONS - || (dry_run && zap_dir)) { - ok = 0; - errno = ENOTEMPTY; -@@ -189,6 +304,8 @@ static int delete_item(char *fname, int - continue; - - strlcpy(p, fp->basename, remainder); -+ if (detect_renamed && S_ISREG(fp->mode)) -+ look_for_rename(fp, fname, dirlist->file_pool); - delete_item(fname, fp->mode, flags & ~DEL_TERSE); - } - flist_free(dirlist); -@@ -197,7 +314,8 @@ static int delete_item(char *fname, int - - pop_local_filters(save_filters); - -- if (max_delete && ++deletion_count > max_delete) -+ if (flags & DEL_NO_DELETIONS -+ || (max_delete && ++deletion_count > max_delete)) - return 0; - - if (do_rmdir(fname) == 0) { -@@ -217,15 +335,19 @@ static int delete_item(char *fname, int - * 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 -- * on exit). */ -+ * on exit). -+ * -+ * Note: --detect-rename may use this routine with DEL_NO_DELETIONS set! -+ */ - static void delete_in_dir(struct file_list *flist, char *fbuf, -- struct file_struct *file, STRUCT_STAT *stp) -+ struct file_struct *file, STRUCT_STAT *stp, int flags) - { - static int min_depth = MAXPATHLEN, cur_depth = -1; - static void *filt_array[MAXPATHLEN/2+1]; - static int already_warned = 0; - struct file_list *dirlist; -- char delbuf[MAXPATHLEN]; -+ char *p, delbuf[MAXPATHLEN]; -+ unsigned remainder; - int dlen, i; - - if (!flist) { -@@ -239,6 +361,8 @@ static void delete_in_dir(struct file_li - if (verbose > 2) - rprintf(FINFO, "delete_in_dir(%s)\n", fbuf); - -+ flags |= DEL_FORCE_RECURSE; -+ - if (allowed_lull) - maybe_send_keepalive(); - -@@ -246,12 +370,14 @@ static void delete_in_dir(struct file_li - return; /* Impossible... */ - - if (io_error && !(lp_ignore_errors(module_id) || ignore_errors)) { -- if (already_warned) -+ if (!already_warned) { -+ rprintf(FINFO, -+ "IO error encountered -- skipping file deletion\n"); -+ already_warned = 1; -+ } -+ if (!detect_renamed) - return; -- rprintf(FINFO, -- "IO error encountered -- skipping file deletion\n"); -- already_warned = 1; -- return; -+ flags |= DEL_NO_DELETIONS; - } - - while (cur_depth >= file->dir.depth && cur_depth >= min_depth) -@@ -262,6 +388,9 @@ static void delete_in_dir(struct file_li - dlen = strlen(fbuf); - filt_array[cur_depth] = push_local_filters(fbuf, dlen); - -+ if (detect_renamed) -+ unexplored_dirs--; -+ - if (one_file_system) { - if (file->flags & FLAG_TOP_DIR) - filesystem_dev = stp->st_dev; -@@ -271,18 +400,30 @@ static void delete_in_dir(struct file_li - - dirlist = get_dirlist(fbuf, dlen, 0); - -+ p = fbuf + dlen; -+ 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->count; i--; ) { - struct file_struct *fp = dirlist->files[i]; - if (!fp->basename || fp->flags & FLAG_MOUNT_POINT) - continue; -+ if (detect_renamed && S_ISREG(fp->mode)) { -+ strlcpy(p, fp->basename, remainder); -+ look_for_rename(fp, fbuf, dirlist->file_pool); -+ } - if (flist_find(flist, fp) < 0) { - f_name(fp, delbuf); -- delete_item(delbuf, fp->mode, DEL_FORCE_RECURSE); -- } -+ delete_item(delbuf, fp->mode, flags); -+ } else if (detect_renamed && S_ISDIR(fp->mode)) -+ unexplored_dirs++; - } - -+ fbuf[dlen] = '\0'; -+ - flist_free(dirlist); - } - -@@ -312,9 +453,9 @@ static void do_delete_pass(struct file_l - || !S_ISDIR(st.st_mode)) - continue; - -- delete_in_dir(flist, fbuf, file, &st); -+ delete_in_dir(flist, fbuf, file, &st, 0); + int unchanged_attrs(const char *fname, struct file_struct *file, stat_x *sxp) + { + #ifndef CAN_SET_SYMLINK_TIMES +@@ -1048,6 +1188,7 @@ static void list_file_entry(struct file_struct *f) } -- delete_in_dir(NULL, NULL, NULL, NULL); -+ delete_in_dir(NULL, NULL, NULL, NULL, 0); - - if (do_progress && !am_server) - rprintf(FINFO, " \r"); -@@ -843,6 +984,7 @@ static int try_dests_non(struct file_str - return j; } +static struct bitbag *delayed_bits = NULL; static int phase = 0; + static int dflt_perms; - /* Acts on the_file_list->file's ndx'th item, whose name is fname. If a dir, -@@ -1028,8 +1170,12 @@ static void recv_generator(char *fname, - if (real_ret != 0 && one_file_system) - real_st.st_dev = filesystem_dev; - if (delete_during && f_out != -1 && !phase && dry_run < 2 -- && (file->flags & FLAG_DEL_HERE)) -- delete_in_dir(the_file_list, fname, file, &real_st); -+ && (file->flags & FLAG_DEL_HERE)) { -+ if (detect_renamed && real_ret != 0) -+ unexplored_dirs++; -+ delete_in_dir(the_file_list, fname, file, &real_st, -+ delete_during < 0 ? DEL_NO_DELETIONS : 0); -+ } - return; - } - -@@ -1273,8 +1419,14 @@ static void recv_generator(char *fname, - && hard_link_check(file, ndx, fname, statret, &st, - itemizing, code, HL_SKIP)) - return; +@@ -1327,9 +1468,12 @@ static void recv_generator(char *fname, struct file_struct *file, int ndx, + } + else if (delete_during && f_out != -1 && !phase + && !(file->flags & FLAG_MISSING_DIR)) { +- if (file->flags & FLAG_CONTENT_DIR) +- delete_in_dir(fname, file, &real_sx.st.st_dev); +- else ++ if (file->flags & FLAG_CONTENT_DIR) { ++ if (detect_renamed && real_ret != 0) ++ unexplored_dirs++; ++ delete_in_dir(fname, file, &real_sx.st.st_dev, ++ delete_during < 0 ? DEL_NO_DELETIONS : 0); ++ } else + change_local_filter_dir(fname, strlen(fname), F_DEPTH(file)); + } + goto cleanup; +@@ -1588,8 +1732,14 @@ static void recv_generator(char *fname, struct file_struct *file, int ndx, + goto cleanup; + } + #endif - if (stat_errno == ENOENT) + if (stat_errno == ENOENT) { + if (detect_renamed && unexplored_dirs > 0 -+ && file->length) { ++ && F_LENGTH(file)) { + bitbag_set_bit(delayed_bits, ndx); + return; + } goto notify_others; + } - rsyserr(FERROR, stat_errno, "recv_generator: failed to stat %s", + rsyserr(FERROR_XFER, stat_errno, "recv_generator: failed to stat %s", full_fname(fname)); - return; -@@ -1460,11 +1612,17 @@ void generate_files(int f_out, struct fi - (long)getpid(), flist->count); - } + goto cleanup; +@@ -2056,6 +2206,12 @@ void generate_files(int f_out, const char *local_name) + if (DEBUG_GTE(GENR, 1)) + rprintf(FINFO, "generator starting pid=%ld\n", (long)getpid()); + if (detect_renamed) { -+ delayed_bits = bitbag_create(flist->count); ++ delayed_bits = bitbag_create(cur_flist->used); + if (!delete_before && !delete_during) + delete_during = -1; + } + - if (delete_before && !local_name && flist->count > 0) - do_delete_pass(flist); - do_progress = 0; + if (delete_before && !solo_file && cur_flist->used > 0) + do_delete_pass(); + if (delete_during == 2) { +@@ -2066,7 +2222,7 @@ void generate_files(int f_out, const char *local_name) + } + info_levels[INFO_FLIST] = info_levels[INFO_PROGRESS] = 0; -- if (append_mode || whole_file < 0) -+ if (append_mode || detect_renamed || whole_file < 0) +- if (append_mode > 0 || whole_file < 0) ++ if (append_mode > 0 || detect_renamed || whole_file < 0) whole_file = 0; - if (verbose >= 2) { + if (DEBUG_GTE(FLIST, 1)) { rprintf(FINFO, "delta-transmission %s\n", -@@ -1519,7 +1677,23 @@ void generate_files(int f_out, struct fi - } - recv_generator(NULL, NULL, 0, 0, 0, code, -1); +@@ -2102,7 +2258,7 @@ void generate_files(int f_out, const char *local_name) + dirdev = MAKEDEV(DEV_MAJOR(devp), DEV_MINOR(devp)); + } else + dirdev = MAKEDEV(0, 0); +- delete_in_dir(fbuf, fp, &dirdev); ++ delete_in_dir(fbuf, fp, &dirdev, 0); + } else + change_local_filter_dir(fbuf, strlen(fbuf), F_DEPTH(fp)); + } +@@ -2149,7 +2305,21 @@ void generate_files(int f_out, const char *local_name) + } while ((cur_flist = cur_flist->next) != NULL); + if (delete_during) -- delete_in_dir(NULL, NULL, NULL, NULL); -+ delete_in_dir(NULL, NULL, NULL, NULL, 0); -+ +- delete_in_dir(NULL, NULL, &dev_zero); ++ delete_in_dir(NULL, NULL, &dev_zero, 0); + if (detect_renamed) { + if (delete_during < 0) + delete_during = 0; + detect_renamed = 0; + + for (i = -1; (i = bitbag_next_bit(delayed_bits, i)) >= 0; ) { -+ struct file_struct *file = flist->files[i]; ++ struct file_struct *file = cur_flist->files[i]; + if (local_name) + strlcpy(fbuf, local_name, sizeof fbuf); + else + f_name(file, fbuf); -+ recv_generator(fbuf, file, i, itemizing, -+ maybe_ATTRS_REPORT, code, f_out); ++ recv_generator(fbuf, file, i, itemizing, code, f_out); + } + } - phase++; - csum_length = SUM_LENGTH; ---- old/options.c -+++ new/options.c -@@ -78,6 +78,7 @@ int am_generator = 0; + if (DEBUG_GTE(GENR, 1)) + rprintf(FINFO, "generate_files phase=%d\n", phase); +diff --git a/options.c b/options.c +--- a/options.c ++++ b/options.c +@@ -80,6 +80,7 @@ int am_server = 0; + int am_sender = 0; int am_starting_up = 1; int relative_paths = -1; - int implied_dirs = 1; +int detect_renamed = 0; + int implied_dirs = 1; + int missing_args = 0; /* 0 = FERROR_XFER, 1 = ignore, 2 = delete */ int numeric_ids = 0; - int allow_8bit_chars = 0; - int force_delete = 0; -@@ -346,6 +347,7 @@ void usage(enum logcode F) +@@ -743,6 +744,7 @@ 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"); @@ -514,15 +565,15 @@ 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"); -@@ -499,6 +501,7 @@ static struct poptOption long_options[] +@@ -938,6 +940,7 @@ 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 }, + {"detect-renamed", 0, POPT_ARG_NONE, &detect_renamed, 0, 0, 0 }, - {"fuzzy", 'y', POPT_ARG_NONE, &fuzzy_basis, 0, 0, 0 }, - {"compress", 'z', POPT_ARG_NONE, 0, 'z', 0, 0 }, - {"compress-level", 0, POPT_ARG_INT, &def_compress_level, 'z', 0, 0 }, -@@ -1362,7 +1365,7 @@ int parse_arguments(int *argc, const cha + {"fuzzy", 'y', POPT_ARG_VAL, &fuzzy_basis, 1, 0, 0 }, + {"no-fuzzy", 0, POPT_ARG_VAL, &fuzzy_basis, 0, 0, 0 }, + {"no-y", 0, POPT_ARG_VAL, &fuzzy_basis, 0, 0, 0 }, +@@ -2157,7 +2160,7 @@ int parse_arguments(int *argc_p, const char ***argv_p) inplace = 1; } @@ -531,7 +582,7 @@ TODO: partial_dir = tmp_partialdir; if (inplace) { -@@ -1371,6 +1374,7 @@ int parse_arguments(int *argc, const cha +@@ -2166,6 +2169,7 @@ int parse_arguments(int *argc_p, const char ***argv_p) snprintf(err_buf, sizeof err_buf, "--%s cannot be used with --%s\n", append_mode ? "append" : "inplace", @@ -539,18 +590,39 @@ TODO: delay_updates ? "delay-updates" : "partial-dir"); return 0; } -@@ -1674,6 +1678,8 @@ void server_options(char **args,int *arg +@@ -2528,6 +2532,8 @@ void server_options(char **args, int *argc_p) args[ac++] = "--super"; if (size_only) args[ac++] = "--size-only"; + if (detect_renamed) + args[ac++] = "--detect-renamed"; - } - - if (modify_window_set) { ---- old/rsync.yo -+++ new/rsync.yo -@@ -363,6 +363,7 @@ to the detailed description below for a + if (do_stats) + args[ac++] = "--stats"; + } else { +diff --git a/rsync.h b/rsync.h +--- a/rsync.h ++++ b/rsync.h +@@ -246,7 +246,7 @@ enum msgcode { + #define NDX_DEL_STATS -3 + #define NDX_FLIST_OFFSET -101 + +-/* For calling delete_item() and delete_dir_contents(). */ ++/* For calling delete_item(), delete_dir_contents(), and delete_in_dir(). */ + #define DEL_NO_UID_WRITE (1<<0) /* file/dir has our uid w/o write perm */ + #define DEL_RECURSE (1<<1) /* if dir, delete all contents */ + #define DEL_DIR_IS_EMPTY (1<<2) /* internal delete_FUNCTIONS use only */ +@@ -256,6 +256,7 @@ enum msgcode { + #define DEL_FOR_DEVICE (1<<6) /* making room for a replacement device */ + #define DEL_FOR_SPECIAL (1<<7) /* making room for a replacement special */ + #define DEL_FOR_BACKUP (1<<8) /* the delete is for a backup operation */ ++#define DEL_NO_DELETIONS (1<<9) /* just check for renames w/o deleting */ + + #define DEL_MAKE_ROOM (DEL_FOR_FILE|DEL_FOR_DIR|DEL_FOR_SYMLINK|DEL_FOR_DEVICE|DEL_FOR_SPECIAL) + +diff --git a/rsync.yo b/rsync.yo +--- a/rsync.yo ++++ b/rsync.yo +@@ -397,6 +397,7 @@ to the detailed description below for a complete description. verb( --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 @@ -558,13 +630,19 @@ 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 -@@ -1259,6 +1260,15 @@ Note that the use of the bf(--delete) op +@@ -1640,6 +1641,21 @@ Note that the use of the bf(--delete) option might get rid of any potential 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 @@ -574,10 +652,11 @@ TODO: dit(bf(--compare-dest=DIR)) This option instructs rsync to use em(DIR) on the destination machine as an additional hierarchy to compare destination files against doing transfers (if the files are missing in the destination ---- old/util.c -+++ new/util.c -@@ -1025,6 +1025,32 @@ int handle_partial_dir(const char *fname - return 1; +diff --git a/util.c b/util.c +--- a/util.c ++++ b/util.c +@@ -1088,6 +1088,32 @@ char *normalize_path(char *path, BOOL force_newbuf, unsigned int *len_ptr) + return path; } +/* We need to supply our own strcmp function for file list comparisons @@ -607,5 +686,5 @@ TODO: +} + /** - * Determine if a symlink points outside the current directory tree. - * This is considered "unsafe" because e.g. when mirroring somebody + * Return a quoted string with the full pathname of the indicated filename. + * The string " (in MODNAME)" may also be appended. The returned pointer