X-Git-Url: https://mattmccutchen.net/rsync/rsync-patches.git/blobdiff_plain/a94141d9fb91e0f615d8c888217e451904c7898e..a75921111fdf7354d07296084231945f01b3c644:/detect-renamed.diff diff --git a/detect-renamed.diff b/detect-renamed.diff index 3fc619a..6c300b1 100644 --- a/detect-renamed.diff +++ b/detect-renamed.diff @@ -19,10 +19,10 @@ memory than trying to keep track of the matches internally, and also allows any deletions or file-updates to occur normally without interfering with these alternate-basis discoveries. -After applying this patch, run these commands for a successful build: +To use this patch, run these commands for a successful build: - ./prepare-source - ./configure (optional if already run) + patch -p1 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) @@ -96,7 +97,7 @@ TODO: static void send_directory(int f, struct file_list *flist, char *fbuf, int len); -@@ -1387,6 +1428,25 @@ struct file_list *recv_file_list(int f) +@@ -1501,6 +1543,25 @@ struct file_list *recv_file_list(int f) clean_flist(flist, relative_paths, 1); @@ -105,7 +106,7 @@ TODO: + the_fattr_list.count = 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, @@ -113,7 +114,7 @@ TODO: + 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; @@ -124,34 +125,39 @@ TODO: --- old/generator.c +++ new/generator.c -@@ -77,6 +77,7 @@ extern char *basis_dir[]; +@@ -76,6 +76,7 @@ extern char *basis_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 read_batch; -@@ -91,14 +92,17 @@ extern char *backup_dir; + extern int new_root_dir; +@@ -91,6 +92,7 @@ extern char *backup_dir; extern char *backup_suffix; extern int backup_suffix_len; extern struct file_list *the_file_list; +extern struct file_list the_fattr_list; extern struct filter_list_struct server_filter_list; + int ignore_perishable = 0; +@@ -98,12 +100,14 @@ int non_perishable_cnt = 0; + int maybe_ATTRS_REPORT = 0; + static int deletion_count = 0; /* used to implement --max-delete */ +static int unexplored_dirs = 1; - static int can_link_symlinks = 1; /* start out optimistic */ - static int can_link_devices = 1; - --/* 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) - - -@@ -108,12 +112,120 @@ static int is_backup_file(char *fn) + static int deldelay_size = 0, deldelay_cnt = 0; + static char *deldelay_buf = NULL; + static int deldelay_fd = -1; + static BOOL solo_file = 0; + +-/* For calling delete_item() and delete_dir_contents(). */ ++/* For calling delete_item(), delete_dir_contents(), and delete_in_dir(). */ ++#define DEL_NO_DELETIONS (1<<0) + #define DEL_RECURSE (1<<1) /* recurse */ + #define DEL_DIR_IS_EMPTY (1<<2) /* internal delete_FUNCTIONS use only */ + +@@ -125,11 +129,120 @@ static int is_backup_file(char *fn) return k > 0 && strcmp(fn+k, backup_suffix) == 0; } @@ -159,7 +165,7 @@ TODO: + * 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; @@ -169,23 +175,24 @@ 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_SENT flag to indicate when we ++ * have computed the checksum for an entry. */ ++ if (!(f->flags & FLAG_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, (char*)F_SUM(f), F_LENGTH(f)); ++ f->flags |= FLAG_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; @@ -229,15 +236,14 @@ TODO: + return good_match >= 0 ? good_match : ok_match; +} + -+static void look_for_rename(struct file_struct *file, char *fname, -+ alloc_pool_t pool) ++static 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 ((ndx = fattr_find(file, fname)) < 0) + return; + + fp = the_fattr_list.files[ndx]; @@ -261,54 +267,55 @@ TODO: + if (errno != EEXIST) + handle_partial_dir(partialptr, PDIR_DELETE); +} - - /* Delete a file or directory. If DEL_FORCE_RECURSE is set in the flags, or if - * force_delete is set, this will delete recursively. ++ + /* Delete a file or directory. If DEL_RECURSE is set in the flags, this will + * delete recursively. * - * Note that fname must point to a MAXPATHLEN buffer if the mode indicates it's + * 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! ++ * Also note: --detect-rename may use this routine with DEL_NO_DELETIONS set! */ - static int delete_item(char *fname, int mode, int flags) + static enum delret delete_item(char *fbuf, int mode, char *replace, int flags) { -@@ -124,6 +236,8 @@ 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))) -@@ -146,6 +260,7 @@ 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; -@@ -188,6 +303,8 @@ static int delete_item(char *fname, int - continue; - - strlcpy(p, fp->basename, remainder); +@@ -151,6 +264,8 @@ static enum delret delete_item(char *fbu + goto check_ret; + /* OK: try to delete the directory. */ + } ++ if (flags & DEL_NO_DELETIONS) ++ return DR_SUCCESS; + + if (!replace && max_delete >= 0 && ++deletion_count > max_delete) + return DR_AT_LIMIT; +@@ -197,6 +312,8 @@ 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.) ++ * ++ * Note: --detect-rename may use this routine with DEL_NO_DELETIONS set! + */ + static enum delret delete_dir_contents(char *fname, int flags) + { +@@ -216,7 +333,9 @@ static enum delret delete_dir_contents(c + 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->count) +@@ -253,6 +372,8 @@ 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; + if (detect_renamed && S_ISREG(fp->mode)) -+ look_for_rename(fp, fname, dirlist->file_pool); - delete_item(fname, fp->mode, flags & ~DEL_TERSE); ++ look_for_rename(fp, fname); + if (delete_item(fname, fp->mode, NULL, flags) != DR_SUCCESS) + ret = DR_NOT_EMPTY; } - flist_free(dirlist); -@@ -196,7 +313,8 @@ 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) { -@@ -216,15 +334,19 @@ static int delete_item(char *fname, int +@@ -405,15 +526,19 @@ 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 @@ -331,19 +338,19 @@ TODO: int dlen, i; if (!flist) { -@@ -238,6 +360,8 @@ static void delete_in_dir(struct file_li +@@ -427,6 +552,8 @@ static void delete_in_dir(struct file_li if (verbose > 2) rprintf(FINFO, "delete_in_dir(%s)\n", fbuf); -+ flags |= DEL_FORCE_RECURSE; ++ flags |= DEL_RECURSE; + if (allowed_lull) maybe_send_keepalive(); -@@ -245,12 +369,14 @@ static void delete_in_dir(struct file_li +@@ -434,12 +561,14 @@ static void delete_in_dir(struct file_li return; /* Impossible... */ - if (io_error && !(lp_ignore_errors(module_id) || ignore_errors)) { + if (io_error && !ignore_errors) { - if (already_warned) + if (!already_warned) { + rprintf(FINFO, @@ -359,8 +366,8 @@ TODO: + flags |= DEL_NO_DELETIONS; } - while (cur_depth >= file->dir.depth && cur_depth >= min_depth) -@@ -261,6 +387,9 @@ static void delete_in_dir(struct file_li + while (cur_depth >= F_DEPTH(file) && cur_depth >= min_depth) +@@ -450,6 +579,9 @@ static void delete_in_dir(struct file_li dlen = strlen(fbuf); filt_array[cur_depth] = push_local_filters(fbuf, dlen); @@ -370,7 +377,7 @@ TODO: if (one_file_system) { if (file->flags & FLAG_TOP_DIR) filesystem_dev = stp->st_dev; -@@ -270,18 +399,30 @@ static void delete_in_dir(struct file_li +@@ -459,6 +591,11 @@ static void delete_in_dir(struct file_li dirlist = get_dirlist(fbuf, dlen, 0); @@ -382,18 +389,24 @@ TODO: /* 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) +@@ -471,16 +608,23 @@ static void delete_in_dir(struct file_li + f_name(fp, NULL)); continue; + } + if (detect_renamed && S_ISREG(fp->mode)) { + strlcpy(p, fp->basename, remainder); -+ look_for_rename(fp, fbuf, dirlist->file_pool); ++ look_for_rename(fp, fbuf); + } if (flist_find(flist, fp) < 0) { f_name(fp, delbuf); -- delete_item(delbuf, fp->mode, DEL_FORCE_RECURSE); +- if (delete_during == 2) { ++ if (delete_during == 2 && !(flags & DEL_NO_DELETIONS)) { + if (!remember_delete(fp, delbuf)) + break; + } else +- delete_item(delbuf, fp->mode, NULL, DEL_RECURSE); - } -+ delete_item(delbuf, fp->mode, flags); ++ delete_item(delbuf, fp->mode, NULL, flags); + } else if (detect_renamed && S_ISDIR(fp->mode)) + unexplored_dirs++; } @@ -403,7 +416,7 @@ TODO: flist_free(dirlist); } -@@ -311,9 +452,9 @@ static void do_delete_pass(struct file_l +@@ -510,9 +654,9 @@ static void do_delete_pass(struct file_l || !S_ISDIR(st.st_mode)) continue; @@ -415,37 +428,37 @@ TODO: if (do_progress && !am_server) rprintf(FINFO, " \r"); -@@ -752,6 +893,7 @@ static int try_dests_non(struct file_str - return -1; +@@ -1047,6 +1191,7 @@ static int try_dests_non(struct file_str + return j; } +static struct bitbag *delayed_bits = NULL; static int phase = 0; /* Acts on the_file_list->file's ndx'th item, whose name is fname. If a dir, -@@ -906,8 +1048,12 @@ static void recv_generator(char *fname, - && verbose && code && f_out != -1) - rprintf(code, "%s/\n", fname); +@@ -1232,8 +1377,12 @@ 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, &st); -+ && (file->flags & FLAG_DEL_HERE)) { -+ if (detect_renamed && statret != 0) +- && (file->flags & FLAG_XFER_DIR)) +- delete_in_dir(the_file_list, fname, file, &real_st); ++ && (file->flags & FLAG_XFER_DIR)) { ++ if (detect_renamed && real_ret != 0) + unexplored_dirs++; -+ delete_in_dir(the_file_list, fname, file, &st, ++ delete_in_dir(the_file_list, fname, file, &real_st, + delete_during < 0 ? DEL_NO_DELETIONS : 0); + } return; } -@@ -1145,8 +1291,14 @@ static void recv_generator(char *fname, - && hard_link_check(file, ndx, fname, statret, &st, - itemizing, code, HL_SKIP)) +@@ -1497,8 +1646,14 @@ static void recv_generator(char *fname, + if (preserve_hard_links && F_HLINK_NOT_LAST(file)) return; + #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; + } @@ -454,7 +467,7 @@ TODO: rsyserr(FERROR, stat_errno, "recv_generator: failed to stat %s", full_fname(fname)); return; -@@ -1323,11 +1475,17 @@ void generate_files(int f_out, struct fi +@@ -1688,6 +1843,12 @@ void generate_files(int f_out, struct fi (long)getpid(), flist->count); } @@ -466,6 +479,9 @@ TODO: + if (delete_before && !local_name && flist->count > 0) do_delete_pass(flist); + if (delete_during == 2) { +@@ -1698,7 +1859,7 @@ void generate_files(int f_out, struct fi + } do_progress = 0; - if (append_mode || whole_file < 0) @@ -473,9 +489,9 @@ TODO: whole_file = 0; if (verbose >= 2) { rprintf(FINFO, "delta-transmission %s\n", -@@ -1382,7 +1540,23 @@ void generate_files(int f_out, struct fi +@@ -1754,7 +1915,22 @@ void generate_files(int f_out, struct fi } - recv_generator(NULL, NULL, 0, 0, 0, code, -1); + recv_generator(NULL, NULL, 0, 0, code, -1); if (delete_during) - delete_in_dir(NULL, NULL, NULL, NULL); + delete_in_dir(NULL, NULL, NULL, NULL, 0); @@ -491,8 +507,7 @@ TODO: + 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); + } + } @@ -508,7 +523,7 @@ TODO: int numeric_ids = 0; int allow_8bit_chars = 0; int force_delete = 0; -@@ -336,6 +337,7 @@ void usage(enum logcode F) +@@ -342,6 +343,7 @@ 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"); @@ -516,7 +531,7 @@ 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"); -@@ -483,6 +485,7 @@ static struct poptOption long_options[] +@@ -496,6 +498,7 @@ 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 }, @@ -524,7 +539,7 @@ TODO: {"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 }, -@@ -1343,7 +1346,7 @@ int parse_arguments(int *argc, const cha +@@ -1355,7 +1358,7 @@ int parse_arguments(int *argc, const cha inplace = 1; } @@ -533,7 +548,7 @@ TODO: partial_dir = tmp_partialdir; if (inplace) { -@@ -1352,6 +1355,7 @@ int parse_arguments(int *argc, const cha +@@ -1364,6 +1367,7 @@ int parse_arguments(int *argc, const cha snprintf(err_buf, sizeof err_buf, "--%s cannot be used with --%s\n", append_mode ? "append" : "inplace", @@ -541,7 +556,7 @@ TODO: delay_updates ? "delay-updates" : "partial-dir"); return 0; } -@@ -1654,6 +1658,8 @@ void server_options(char **args,int *arg +@@ -1674,6 +1678,8 @@ void server_options(char **args,int *arg args[ac++] = "--super"; if (size_only) args[ac++] = "--size-only"; @@ -552,7 +567,7 @@ TODO: if (modify_window_set) { --- old/rsync.yo +++ new/rsync.yo -@@ -362,6 +362,7 @@ to the detailed description below for a +@@ -364,6 +364,7 @@ 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 @@ -560,7 +575,7 @@ 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 -@@ -1240,6 +1241,15 @@ Note that the use of the bf(--delete) op +@@ -1272,6 +1273,15 @@ 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. @@ -578,7 +593,7 @@ TODO: files against doing transfers (if the files are missing in the destination --- old/util.c +++ new/util.c -@@ -1013,6 +1013,32 @@ int handle_partial_dir(const char *fname +@@ -1027,6 +1027,32 @@ int handle_partial_dir(const char *fname return 1; }