feat(output): rsync 3.4.1 selection and output parity (#291, #292)

#291:
- Compile --exclude/--include/--exclude-from/--include-from into the SAME
  ordered rule list as --filter/-f (first match wins), so the common
  `--include='*.txt' --exclude='*'` idiom and include-alone semantics match
  rsync. The legacy per-kind scanner arrays are no longer applied.
- -x/--one-file-system emits the cross-device mount-point directory entry
  (empty) instead of dropping it, in both the sequential and parallel scanners.
- Stop passing the legacy arrays to the scanner; document -f is --filter.

#292:
- New src/shared/format.c/.h: rsync "big_num" (comma-grouped integers) and
  decimal -h human sizes, %M/%t timestamp, and the STATUS_DEST_INFO codec.
- Receiver answers each STATUS_CHECK with a pre-transfer destination snapshot
  (new report_dest_info wire field + STATUS_DEST_INFO, PROTOCOL_VERSION
  2.23.0) so the sender can render true itemize columns.
- Itemize now emits rsync-correct update/type chars and c/s/t/p/o/g columns
  for files, dirs, symlinks and hard links, comparing size/time/perms/owner/
  group against the reported destination.
- --out-format gains %i %n %f %l %b %M %t %o %p %B %U %G %L; %f is the
  relative display path, %M the YYYY/MM/DD-HH:MM:SS form, %b the literal
  bytes sent.
- --list-only prints transfer-relative names, directory entries and ls-style
  grouped sizes.
- --stats prints rsync's multi-line block on stdout; -h uses decimal units.

Tests: unit tests for the filter ordering, format primitives, itemize
columns; integration + differential tests against real rsync 3.4.1 for
itemize/out-format/list-only/selection and -x. Golden wire len/hash and
protocol version strings updated for 2.23.0.
This commit is contained in:
2026-09-15 21:57:39 +02:00
parent 23552e823d
commit 84827ca617
28 changed files with 1529 additions and 300 deletions
+348 -155
View File
@@ -7,21 +7,7 @@
#include <string.h>
#include <sys/stat.h>
#include <time.h>
/* Itemize code emitted for a transferred regular file.
*
* Layout (rsync-compatible 11-char item): `>f` marks a regular file that was
* transferred to the remote host; the trailing nine markers are, in order,
* c(hecksum) s(ize) t(ime) p(erms) o(wner) g(roup) u(ser/acl) a(ttrs) x(attrs).
* Every marker is `+` (FastSync does not compare each attribute on the
* receiving side, so a sent file is reported as fully updated). Files that
* are already up to date print no line at all, matching rsync's single -i
* which only itemizes changes.
*
* Because the scanner only yields regular-file transfer candidates, `>d`
* (directory) lines are never produced; directories are not transferred as
* items by FastSync. */
#define ITEMIZE_SENT_FILE ">f+++++++++"
#include <unistd.h>
typedef struct {
char* data;
@@ -80,103 +66,14 @@ static bool strbuf_append(StrBuf* buf, const char* text) {
return true;
}
static bool strbuf_append_ull(StrBuf* buf, unsigned long long value) {
char digits[32];
int written = snprintf(digits, sizeof(digits), "%llu", value);
if (written < 0 || (size_t)written >= sizeof(digits))
return false;
return strbuf_append(buf, digits);
}
static bool strbuf_append_longlong(StrBuf* buf, long long value) {
char digits[32];
int written = snprintf(digits, sizeof(digits), "%lld", value);
if (written < 0 || (size_t)written >= sizeof(digits))
return false;
return strbuf_append(buf, digits);
}
bool change_list_enabled(const Config* config) {
return config != NULL && (config->itemize_changes || config->out_format != NULL ||
(config->log_file != NULL && config->log_file_format != NULL));
}
char* change_render_itemize(const ChangeEvent* event) {
if (event == NULL || event->decision != CHANGE_SENT)
return str_dup("");
const char* code = event->is_directory ? ">d+++++++++" : ITEMIZE_SENT_FILE;
StrBuf line = {0};
bool ok = strbuf_append(&line, code) && strbuf_append(&line, " ") &&
strbuf_append(&line, event->path != NULL ? event->path : "");
if (!ok) {
strbuf_free(&line);
return NULL;
}
return line.data;
}
/* ---- Itemize code ---- */
static const char* leaf_name(const char* path) {
if (path == NULL)
return "";
const char* slash = strrchr(path, '/');
return slash != NULL && slash[1] != '\0' ? slash + 1 : path;
}
char* change_render_format(const char* format, const ChangeEvent* event) {
if (format == NULL)
return NULL;
StrBuf line = {0};
bool ok = true;
for (const char* p = format; *p != '\0' && ok;) {
if (*p != '%') {
ok = strbuf_append_char(&line, *p);
p++;
continue;
}
char token = p[1];
if (token == '\0') {
ok = strbuf_append_char(&line, '%');
break;
}
switch (token) {
case '%':
ok = strbuf_append_char(&line, '%');
break;
case 'f':
ok = strbuf_append(&line, event->path != NULL ? event->path : "");
break;
case 'n':
ok = strbuf_append(&line, leaf_name(event->path));
break;
case 'l':
ok = strbuf_append_ull(&line, event->size);
break;
case 'b':
ok = strbuf_append_ull(&line, event->bytes_sent);
break;
case 'M':
ok = strbuf_append_longlong(&line, (long long)event->mtime_sec);
break;
default:
/* Unknown escape sequences are preserved verbatim. */
ok = strbuf_append_char(&line, '%') && strbuf_append_char(&line, token);
break;
}
p += 2;
}
if (!ok) {
strbuf_free(&line);
return NULL;
}
if (line.data == NULL) {
line.data = str_dup("");
if (!line.data)
return NULL;
}
return line.data;
}
/* Format a mode as an `ls -l` permission string, e.g. `-rw-r--r--`. */
/* Format the permission bits as an `ls -l` string, e.g. `-rw-r--r--`. */
static void mode_to_ls_string(mode_t mode, char out[11]) {
out[0] = S_ISDIR(mode) ? 'd'
: S_ISLNK(mode) ? 'l'
@@ -198,29 +95,102 @@ static void mode_to_ls_string(mode_t mode, char out[11]) {
out[10] = '\0';
}
char* change_render_list_line(mode_t mode, unsigned long long size, time_t mtime,
const char* path) {
char permission[11];
mode_to_ls_string(mode, permission);
char date[32];
struct tm broken_down;
if (localtime_r(&mtime, &broken_down) != NULL) {
if (strftime(date, sizeof(date), "%Y/%m/%d %H:%M:%S", &broken_down) == 0)
snprintf(date, sizeof(date), "?");
} else {
snprintf(date, sizeof(date), "?");
static char itemize_type_char(const ChangeEvent* event) {
if (event->is_directory)
return 'd';
if (event->is_symlink)
return 'L';
if (event->is_special) {
if (S_ISCHR(event->mode) || S_ISBLK(event->mode))
return 'D';
return 'S';
}
return 'f';
}
static bool times_match(const Config* config, const ChangeEvent* event) {
if (!event->dest.known || !event->dest.existed)
return false;
if (event->mtime_sec == event->dest.mtime_sec)
return event->mtime_nsec == event->dest.mtime_nsec;
long long delta = (long long)event->mtime_sec - (long long)event->dest.mtime_sec;
if (delta < 0)
delta = -delta;
return delta <= (long long)config->modify_window;
}
/* Fill the 11-character itemize code (10 chars + NUL). `created` means the
* destination entry did not exist, so every attribute marker is `+`. */
static void itemize_code(const Config* config, const ChangeEvent* event, char code[12]) {
bool known = event->dest.known;
bool created = !known || !event->dest.existed;
char update;
if (event->is_hardlink)
update = 'h';
else if (created)
update = (event->is_directory || event->is_symlink || event->is_special) ? 'c' : '>';
else
update = '>';
code[0] = update;
code[1] = itemize_type_char(event);
if (created) {
for (int i = 0; i < 9; i++)
code[2 + i] = '+';
code[11] = '\0';
return;
}
bool size_diff = event->size != event->dest.size;
bool time_diff = !times_match(config, event);
bool perms_diff = (event->mode & 07777) != (event->dest.mode & 07777);
bool owner_diff = event->uid != (uid_t)event->dest.uid;
bool group_diff = event->gid != (gid_t)event->dest.gid;
code[2] = '.'; /* checksum: no destination digest available */
code[3] = size_diff ? 's' : '.';
code[4] = time_diff ? 't' : '.';
code[5] = (config->preserve_perms && perms_diff) ? 'p' : '.';
code[6] = (config->preserve_owner && owner_diff) ? 'o' : '.';
code[7] = (config->preserve_group && group_diff) ? 'g' : '.';
code[8] = '.'; /* reserved */
code[9] = '.'; /* acl: not compared */
code[10] = '.';
code[11] = '\0';
}
char* change_render_itemize_code(const Config* config, const ChangeEvent* event) {
if (event == NULL || event->decision != CHANGE_SENT)
return str_dup("");
char code[12];
itemize_code(config, event, code);
return str_dup(code);
}
/* rsync %n: the transfer-relative name, with a trailing slash for directories. */
static bool append_name(StrBuf* buf, const ChangeEvent* event) {
if (!strbuf_append(buf, event->name != NULL ? event->name : ""))
return false;
if (event->is_directory && (event->name == NULL || event->name[0] == '\0' ||
event->name[strlen(event->name) - 1] != '/'))
return strbuf_append_char(buf, '/');
return true;
}
/* rsync %L: " -> target" for a symlink, " => target" for a hard link, else "". */
static bool append_link_suffix(StrBuf* buf, const ChangeEvent* event) {
if (event->is_symlink && event->symlink_target != NULL)
return strbuf_append(buf, " -> ") && strbuf_append(buf, event->symlink_target);
if (event->is_hardlink && event->hardlink_target != NULL)
return strbuf_append(buf, " => ") && strbuf_append(buf, event->hardlink_target);
return true;
}
char* change_render_itemize(const Config* config, const ChangeEvent* event) {
if (event == NULL || event->decision != CHANGE_SENT)
return str_dup("");
char code[12];
itemize_code(config, event, code);
StrBuf line = {0};
char size_field[32];
int written = snprintf(size_field, sizeof(size_field), "%llu", size);
if (written < 0 || (size_t)written >= sizeof(size_field)) {
strbuf_free(&line);
return NULL;
}
bool ok = strbuf_append(&line, permission) && strbuf_append_char(&line, ' ') &&
strbuf_append(&line, size_field) && strbuf_append_char(&line, ' ') &&
strbuf_append(&line, date) && strbuf_append_char(&line, ' ') &&
strbuf_append(&line, path != NULL ? path : "");
bool ok = strbuf_append(&line, code) && strbuf_append_char(&line, ' ') &&
append_name(&line, event) && append_link_suffix(&line, event);
if (!ok) {
strbuf_free(&line);
return NULL;
@@ -228,6 +198,141 @@ char* change_render_list_line(mode_t mode, unsigned long long size, time_t mtime
return line.data;
}
/* ---- --out-format / --log-file-format ---- */
char* change_render_format(const char* format, const Config* config, const ChangeEvent* event) {
if (format == NULL || event == NULL)
return NULL;
StrBuf line = {0};
bool ok = true;
for (const char* p = format; *p != '\0' && ok;) {
if (*p != '%') {
ok = strbuf_append_char(&line, *p);
p++;
continue;
}
char token = p[1];
if (token == '\0') {
ok = strbuf_append_char(&line, '%');
break;
}
switch (token) {
case '%':
ok = strbuf_append_char(&line, '%');
break;
case 'i': {
char code[12];
itemize_code(config, event, code);
ok = strbuf_append(&line, code);
break;
}
case 'f':
ok = strbuf_append(&line, event->path != NULL ? event->path : "");
break;
case 'n':
ok = append_name(&line, event);
break;
case 'L':
ok = append_link_suffix(&line, event);
break;
case 'l': {
char digits[32];
int written = snprintf(digits, sizeof(digits), "%llu", event->size);
ok = written >= 0 && (size_t)written < sizeof(digits) && strbuf_append(&line, digits);
} break;
case 'b': {
char digits[32];
int written = snprintf(digits, sizeof(digits), "%llu", event->bytes_sent);
ok = written >= 0 && (size_t)written < sizeof(digits) && strbuf_append(&line, digits);
} break;
case 'M': {
char when[32];
if (format_rsync_datetime(event->mtime_sec, true, when, sizeof(when)))
ok = strbuf_append(&line, when);
} break;
case 't': {
char when[32];
if (format_rsync_datetime(time(NULL), false, when, sizeof(when)))
ok = strbuf_append(&line, when);
} break;
case 'o':
ok = strbuf_append(&line, "send");
break;
case 'p': {
char digits[32];
int written = snprintf(digits, sizeof(digits), "%ld", (long)getpid());
ok = written >= 0 && (size_t)written < sizeof(digits) && strbuf_append(&line, digits);
} break;
case 'B': {
char permission[11];
mode_to_ls_string(event->mode, permission);
ok = strbuf_append(&line, permission + 1);
} break;
case 'U': {
char digits[32];
int written = snprintf(digits, sizeof(digits), "%u", (unsigned)event->uid);
ok = written >= 0 && (size_t)written < sizeof(digits) && strbuf_append(&line, digits);
} break;
case 'G': {
char digits[32];
int written = snprintf(digits, sizeof(digits), "%u", (unsigned)event->gid);
ok = written >= 0 && (size_t)written < sizeof(digits) && strbuf_append(&line, digits);
} break;
default:
/* Unknown escape sequences are preserved verbatim. */
ok = strbuf_append_char(&line, '%') && strbuf_append_char(&line, token);
break;
}
p += 2;
}
if (!ok) {
strbuf_free(&line);
return NULL;
}
if (line.data == NULL) {
line.data = str_dup("");
if (!line.data)
return NULL;
}
return line.data;
}
/* ---- --list-only ---- */
char* change_render_list_line(const Config* config, const ChangeEvent* event) {
(void)config;
if (event == NULL)
return NULL;
char permission[11];
mode_to_ls_string(event->mode, permission);
char date[32];
if (!format_rsync_datetime(event->mtime_sec, false, date, sizeof(date)))
snprintf(date, sizeof(date), "?");
StrBuf line = {0};
char size_field[40];
char grouped[32];
if (!format_big_num(event->size, false, grouped, sizeof(grouped))) {
strbuf_free(&line);
return NULL;
}
int written = snprintf(size_field, sizeof(size_field), "%15s", grouped);
if (written < 0 || (size_t)written >= sizeof(size_field)) {
strbuf_free(&line);
return NULL;
}
const char* name = event->name != NULL && event->name[0] != '\0' ? event->name : ".";
bool ok = strbuf_append(&line, permission) && strbuf_append(&line, size_field) &&
strbuf_append_char(&line, ' ') && strbuf_append(&line, date) &&
strbuf_append_char(&line, ' ') && strbuf_append(&line, name);
if (!ok) {
strbuf_free(&line);
return NULL;
}
return line.data;
}
/* ---- Event emission ---- */
static void print_escaped_line(FILE* stream, const char* line, bool eight_bit_output) {
char* escaped = output_escape(line, eight_bit_output);
if (escaped != NULL) {
@@ -247,15 +352,16 @@ void change_emit(const Config* config, const ChangeEvent* event) {
bool to_stdout = config->itemize_changes || config->out_format != NULL;
bool to_log = config->log_file != NULL && config->log_file_format != NULL;
if (to_stdout) {
char* line = config->out_format != NULL ? change_render_format(config->out_format, event)
: change_render_itemize(event);
char* line = config->out_format != NULL
? change_render_format(config->out_format, config, event)
: change_render_itemize(config, event);
if (line != NULL) {
print_escaped_line(stdout, line, config->eight_bit_output);
free(line);
}
}
if (to_log) {
char* line = change_render_format(config->log_file_format, event);
char* line = change_render_format(config->log_file_format, config, event);
if (line != NULL) {
print_escaped_line(config->log_file, line, config->eight_bit_output);
free(line);
@@ -266,9 +372,6 @@ void change_emit(const Config* config, const ChangeEvent* event) {
static bool format_uses_mtime(const char* format) {
if (format == NULL)
return false;
/* Mirror change_render_format's tokenizer: "%%" is a literal percent (so
* "%%M" does NOT expand %M) and unknown "%X" escapes consume both chars.
* This keeps the optional stat() fallback below in step with the renderer. */
for (const char* p = format; *p != '\0';) {
if (*p != '%') {
p++;
@@ -284,46 +387,136 @@ static bool format_uses_mtime(const char* format) {
return false;
}
/* Relative path of an entry below the transfer root (no leading slash). Uses
* the sender-side send_path override when present (bare-relative -R layout). */
static char* relative_name(const Config* config, const File* file) {
const char* full = file_wire_path(file);
if (file->send_path != NULL)
return str_dup(full != NULL ? full : "");
const char* root = config->send_directory;
if (root == NULL || full == NULL)
return str_dup(full != NULL ? full : "");
size_t root_len = strlen(root);
while (root_len > 1 && root[root_len - 1] == '/')
root_len--;
if (strncmp(root, full, root_len) == 0) {
if (full[root_len] == '\0')
return str_dup("");
if (full[root_len] == '/')
return str_dup(full + root_len + 1);
}
return str_dup(full);
}
/* rsync %f long form: the source argument as typed (leading '/' removed,
* trailing '/' removed, leading "./" removed) joined to the relative name. */
static char* display_name(const Config* config, const char* name) {
const char* root = config->send_directory;
if (root == NULL)
return str_dup(name != NULL ? name : "");
const char* p = root;
while (*p == '/')
p++;
if (p[0] == '.' && p[1] == '/')
p += 2;
size_t root_len = strlen(p);
while (root_len > 0 && p[root_len - 1] == '/')
root_len--;
size_t name_len = name != NULL ? strlen(name) : 0;
if (root_len == 0 && name_len == 0)
return str_dup("");
char* out = malloc(root_len + (root_len > 0 && name_len > 0 ? 1 : 0) + name_len + 1);
if (!out)
return NULL;
size_t offset = 0;
if (root_len > 0) {
memcpy(out, p, root_len);
offset = root_len;
}
if (root_len > 0 && name_len > 0)
out[offset++] = '/';
if (name_len > 0)
memcpy(out + offset, name, name_len);
out[offset + name_len] = '\0';
return out;
}
static void fill_event_from_file(const Config* config, const File* file, ChangeEvent* event,
char** name_out, char** path_out) {
char* name = relative_name(config, file);
char* path = display_name(config, name);
event->name = name;
event->path = path;
*name_out = name;
*path_out = path;
if (file->metadata != NULL) {
event->mtime_sec = file->metadata->mtime_sec;
event->mtime_nsec = file->metadata->mtime_nsec;
event->mode = file->metadata->mode;
event->uid = file->metadata->uid;
event->gid = file->metadata->gid;
} else if (format_uses_mtime(config->out_format) || format_uses_mtime(config->log_file_format)) {
struct stat st;
if (file->path != NULL && stat(file->path, &st) == 0) {
event->mtime_sec = st.st_mtime;
event->mtime_nsec = st.st_mtim.tv_nsec;
}
}
}
void change_emit_file_sent(const Config* config, const File* file) {
if (file == NULL || !change_list_enabled(config))
return;
ChangeEvent event;
memset(&event, 0, sizeof(event));
/* The displayed path is the one transmitted (with -R + --files-from this is
the bare relative destination path); the metadata fallback below still
stats the local absolute path. */
event.path = file_wire_path(file);
event.decision = CHANGE_SENT;
event.is_directory = false;
event.is_symlink = false;
event.is_special = false;
event.is_hardlink = false;
event.size = file->data != NULL ? file->data->size : 0;
/* FastSync has no wire-byte counter yet, so %b reports the source length
* that had to be delivered (always equal to %l); the actual bytes written
* to the socket (compressed/delta) are not measured. */
event.bytes_sent = event.size;
if (file->metadata != NULL) {
event.mtime_sec = file->metadata->mtime_sec;
} else if (format_uses_mtime(config->out_format) || format_uses_mtime(config->log_file_format)) {
/* Best-effort fallback for %M when no metadata was captured (no -M): the
* path is stat()ed just to fill the field, and any failure leaves 0. */
struct stat st;
if (file->path != NULL && stat(file->path, &st) == 0)
event.mtime_sec = st.st_mtime;
event.dest = file->dest_state;
if (file->is_symlink) {
event.is_symlink = true;
event.symlink_target = file->symlink_target;
event.size = file->symlink_target != NULL ? strlen(file->symlink_target) : 0;
event.bytes_sent = 0;
} else if (file->is_special) {
event.is_special = true;
event.bytes_sent = 0;
} else if (file->link_group != 0 && !file->link_first) {
event.is_hardlink = true;
event.hardlink_target = file->hardlink_target;
event.bytes_sent = 0;
} else {
/* Literal payload bytes delivered; compressed/delta wire bytes are not
* separately counted. */
event.bytes_sent = event.size;
}
change_emit(config, &event);
char* name = NULL;
char* path = NULL;
fill_event_from_file(config, file, &event, &name, &path);
if (name != NULL && path != NULL)
change_emit(config, &event);
free(name);
free(path);
}
/* Build and emit a CHANGE_SENT event for an explicit directory entry (-d). */
void change_emit_dir_sent(const Config* config, const File* file) {
if (file == NULL || !change_list_enabled(config))
return;
ChangeEvent event;
memset(&event, 0, sizeof(event));
event.path = file_wire_path(file);
event.decision = CHANGE_SENT;
event.is_directory = true;
event.size = 0;
event.bytes_sent = 0;
if (file->metadata != NULL)
event.mtime_sec = file->metadata->mtime_sec;
change_emit(config, &event);
event.dest = file->dest_state;
char* name = NULL;
char* path = NULL;
fill_event_from_file(config, file, &event, &name, &path);
if (name != NULL && path != NULL)
change_emit(config, &event);
free(name);
free(path);
}