directory structure such as "/a/b/c/", then it is possible for there to be only
an entry "/a/b/c/" and the directories "/a/b/" and "/a/" may need to be created
even though they are not specified.
+
+## Format Version 4
+
+This file format is nearly identical to file format version 3, but with larger
+unsigned integer sizes for symlink count, chunk count, file count, and directory
+count.
+
+File extension is "*.simplearchive" but this isn't really checked.
+
+First 18 bytes of file will be (in ascii):
+
+ SIMPLE_ARCHIVE_VER
+
+Next 2 bytes is a 16-bit unsigned integer "version" in big-endian. It will be:
+
+ 0x00 0x04
+
+Next 4 bytes are bit-flags.
+
+1. The first byte
+ 1. The first bit is set if de/compressor is set for this archive.
+
+The remaining unused flags in the previous bit-flags bytes are reserved for
+future revisions and are currently ignored.
+
+If the previous "de/compressor is set" flag is enabled, then the next section is
+added:
+
+1. 2 bytes is 16-bit unsigned integer "compressor cmd+args" in big-endian. This
+ does not include the NULL at the end of the string.
+2. X bytes of "compressor cmd+args" (length defined by previous value). Is a
+ NULL-terminated string.
+3. 2 bytes is 16-bit unsigned integer "decompressor cmd+args" in big-endian.
+ This does not include the NULL at the end of the string.
+4. X bytes of "decompressor cmd+args" (length defined by previous value). Is a
+ NULL-terminated string.
+
+The next 8 bytes is a 64-bit unsigned integer "link count" in big-endian which
+will indicate the number of symbolic links in this archive.
+
+Following the link-count bytes, the following bytes are added for each symlink:
+
+1. 2 bytes bit-flags:
+ 1. The first byte.
+ 1. The first bit is UNSET if relative links are preferred, and is SET if
+ absolute links are preferred.
+ 2. The second bit is "user read permission".
+ 3. The third bit is "user write permission".
+ 4. The fourth bit is "user execute permission".
+ 5. The fifth bit is "group read permission".
+ 6. The sixth bit is "group write permission".
+ 7. The seventh bit is "group execute permission".
+ 8. The eighth bit is "other read permission".
+ 2. The second byte.
+ 1. The first bit is "other write permission".
+ 2. The second bit is "other execute permission".
+ 3. If this bit is set, then this entry is marked invalid. The link name
+ will be preserved in this entry, but the following link target paths
+ will be set to zero-length and will not be stored.
+ 4. If this bit is set, then this symlink points to something outside of
+ this archive.
+2. 2 bytes 16-bit unsigned integer "link name" in big-endian. This does not
+ include the NULL at the end of the string. Must not be zero.
+3. X bytes of link-name (length defined by previous value). Is a NULL-terminated
+ string.
+4. 2 bytes is 16-bit unsigned integer "link target absolute path" in
+ big-endian. This does not include the NULL at the end of the string.
+5. X bytes of link-target-absolute-path (length defined by previous value).
+ Is a NULL-terminated string. If the previous "size" value is 0, then
+ this entry does not exist and should be skipped.
+6. 2 bytes is 16-bit unsigned integer "link target relative path" in
+ big-endian. This does not include the NULL at the end of the string.
+7. X bytes of link-target-relative-path (length defined by previous value).
+ Is a NULL-terminated string. If the previous "size" value is 0, then
+ this entry does not exist and should be skipped.
+8. 4 bytes is a 32-bit unsigned integer in big-endian storing UID for this
+ symlink.
+9. 4 bytes is a 32-bit unsigned integer in big-endian storing GID for this
+ symlink.
+10. 2 bytes 16-bit unsigned integer "user name" length in big-endian. This does
+ not include the NULL at the end of the string.
+11. X bytes of user-name (length defined by previous value). Is a
+ NULL-terminated string. If the previous "size" value is 0, then this entry
+ does not exist and should be skipped.
+10. 2 bytes 16-bit unsigned integer "group name" length in big-endian. This does
+ not include the NULL at the end of the string.
+11. X bytes of group-name (length defined by previous value). Is a
+ NULL-terminated string. If the previous "size" value is 0, then this entry
+ does not exist and should be skipped.
+
+After the symlink related data, the next 8 bytes is a 64-bit unsigned integer
+"chunk count" in big-endian which will indicate the number of chunks in this
+archive.
+
+Following the chunk-count bytes, the following bytes are added for each chunk:
+
+1. 8 bytes that are a 64-bit unsigned integer "file count" in big-endian.
+
+The following bytes are added for each file within the current chunk:
+
+1. 2 bytes that are a 16-bit unsigned integer "filename length" in big-endian.
+ This does not include the NULL at the end of the string.
+2. X bytes of filename (length defined by previous value). Is a NULL-terminated
+ string.
+3. 4 bytes bit-flags.
+ 1. The first byte.
+ 1. The first bit is "user read permission".
+ 2. The second bit is "user write permission".
+ 3. The third bit is "user execute permission".
+ 4. The fourth bit is "group read permission".
+ 5. The fifth bit is "group write permission".
+ 6. The sixth bit is "group execute permission".
+ 7. The seventh bit is "other read permission".
+ 8. The eighth bit is "other write permission".
+ 2. The second byte.
+ 1. The first bit is "other execute permission".
+ 3. The third byte.
+ 1. Currently unused.
+ 4. The fourth byte.
+ 1. Currently unused.
+4. Two 4-byte unsigned integers in big-endian for UID and GID.
+ 1. A 32-bit unsigned integer in big endian that specifies the UID of the
+ file. Note that during extraction, if the user is not root, then this
+ value will be ignored.
+ 2. A 32-bit unsigned integer in big endian that specifies the GID of the
+ file. Note that during extraction, if the user is not root, then this
+ value will be ignored.
+5. 2 bytes 16-bit unsigned integer "user name" length in big-endian. This does
+ not include the NULL at the end of the string.
+6. X bytes of user-name (length defined by previous value). Is a
+ NULL-terminated string. If the previous "size" value is 0, then this entry
+ does not exist and should be skipped.
+7. 2 bytes 16-bit unsigned integer "group name" length in big-endian. This does
+ not include the NULL at the end of the string.
+8. X bytes of group-name (length defined by previous value). Is a
+ NULL-terminated string. If the previous "size" value is 0, then this entry
+ does not exist and should be skipped.
+9. A 64-bit unsigned integer in big endian for the "size of file".
+
+After the files' metadata are the current chunk's data:
+
+1. A 64-bit unsigned integer in big endian for the "size of chunk".
+2. X bytes of data for the current chunk of the previously specified size. If
+ not using de/compressor, this section is the previously mentioned files
+ concatenated with each other. If using de/compressor, this section is the
+ previously mentioned files concatenated and compressed into a single blob of
+ data.
+
+After all the chunks:
+8 bytes (a 64-bit unsigned integer) of "directory count" in big-endian.
+
+After this, for each directory of count "directory count":
+
+1. 2 bytes (16-bit unsigned integer) "directory name length" in big-endian. This
+ does not include the NULL at the end of the string.
+2. X bytes of "directory name" with length of "directory name length". Note that
+ this string is stored as a NULL-terminated string.
+3. 2 bytes permissions flags:
+ 1. The first byte's bits:
+ 1. User read permission
+ 2. User write permission
+ 3. User execute permission
+ 4. Group read permission
+ 5. Group write permission
+ 6. Group execute permission
+ 7. Other read permission
+ 8. Other write permission
+ 2. The second byte's bits (unused bits are assumed to be set to 0):
+ 1. Other execute permission
+4. Two 4-byte unsigned integers in big-endian for UID and GID.
+ 1. A 32-bit unsigned integer in big-endian that is the UID of the directory.
+ 2. A 32-bit unsigned integer in big-endian that is the GID of the directory.
+5. 2 bytes 16-bit unsigned integer "user name" length in big-endian. This does
+ not include the NULL at the end of the string.
+6. X bytes of user-name (length defined by previous value). Is a
+ NULL-terminated string. If the previous "size" value is 0, then this entry
+ does not exist and should be skipped.
+7. 2 bytes 16-bit unsigned integer "group name" length in big-endian. This does
+ not include the NULL at the end of the string.
+8. X bytes of group-name (length defined by previous value). Is a
+ NULL-terminated string. If the previous "size" value is 0, then this entry
+ does not exist and should be skipped.
+
+Note that it is possible for directory entries to consist of only the "tail end"
+directory and not specify "intermediate" directories. For example, if there is a
+directory structure such as "/a/b/c/", then it is possible for there to be only
+an entry "/a/b/c/" and the directories "/a/b/" and "/a/" may need to be created
+even though they are not specified.
}
}
-int internal_write_dir_entries_v2_v3(void *data, void *ud) {
+int internal_write_dir_entries_v2_v3_v4(void *data, void *ud) {
const char *dir = data;
void **ptrs = ud;
FILE *out_f = ptrs[0];
return 1;
}
- if (state->parsed->write_version == 3) {
+ if (state->parsed->write_version == 3 || state->parsed->write_version == 4) {
u32 = stat_buf.st_uid;
if (state->parsed->flags & 0x400) {
u32 = state->parsed->uid;
void_ptrs[1] = state;
if (simple_archiver_list_get(dirs_list,
- internal_write_dir_entries_v2_v3,
+ internal_write_dir_entries_v2_v3_v4,
void_ptrs)) {
free(void_ptrs);
return SDAS_INTERNAL_ERROR;
void_ptrs[1] = state;
if (simple_archiver_list_get(dirs_list,
- internal_write_dir_entries_v2_v3,
+ internal_write_dir_entries_v2_v3_v4,
void_ptrs)) {
free(void_ptrs);
return SDAS_INTERNAL_ERROR;
uint64_t chunk_idx = 0;
SDArchiverLLNode *node = file_info_list->head;
- uint16_t file_idx = 0;
+ uint32_t file_idx = 0;
#if SIMPLE_ARCHIVER_PLATFORM == SIMPLE_ARCHIVER_PLATFORM_COSMOPOLITAN || \
SIMPLE_ARCHIVER_PLATFORM == SIMPLE_ARCHIVER_PLATFORM_MAC || \
const SDArchiverInternalFileInfo *file_info = node->data;
if (file_info->other_flags & 2) {
fprintf(stderr,
- " FILE %3" PRIu16 " of %3" PRIu32 ": %s\n",
+ " FILE %3" PRIu32 " of %3" PRIu32 ": %s\n",
++file_idx,
file_count,
file_info->filename);
const SDArchiverInternalFileInfo *file_info = node->data;
if (file_info->other_flags & 2) {
fprintf(stderr,
- " FILE %3" PRIu16 " of %3" PRIu32 ": %s\n",
+ " FILE %3" PRIu32 " of %3" PRIu32 ": %s\n",
++file_idx,
file_count,
file_info->filename);
uint64_t chunk_idx = 0;
SDArchiverLLNode *node = file_info_list->head;
- uint16_t file_idx = 0;
+ uint32_t file_idx = 0;
#if SIMPLE_ARCHIVER_PLATFORM == SIMPLE_ARCHIVER_PLATFORM_COSMOPOLITAN || \
SIMPLE_ARCHIVER_PLATFORM == SIMPLE_ARCHIVER_PLATFORM_MAC || \
}
node = node->next;
const SDArchiverInternalFileInfo *file_info = node->data;
+ ++file_idx;
if (file_info->other_flags & 2) {
fprintf(stderr,
- " FILE %3" PRIu16 " of %3" PRIu32 ": %s\n",
+ " FILE %3" PRIu32 " of %3" PRIu32 ": %s\n",
file_idx,
file_count,
file_info->filename);
}
- ++file_idx;
const size_t filename_length = strlen(file_info->filename);
}
node = node->next;
const SDArchiverInternalFileInfo *file_info = node->data;
+ ++file_idx;
if (file_info->other_flags & 2) {
fprintf(stderr,
- " FILE %3" PRIu16 " of %3" PRIu32 ": %s\n",
+ " FILE %3" PRIu32 " of %3" PRIu32 ": %s\n",
file_idx,
file_count,
file_info->filename);
}
- ++file_idx;
chunk_idx += file_info->file_size;
if (chunk_idx > chunk_size) {
fprintf(stderr, "ERROR Files in chunk is larger than chunk!\n");
projects / SimpleArchiver / commitdiff