xz: Add incomplete support for --block-list.

It's broken with threads and when also --block-size is used.

src/xz/args.c

@@ -54,6 +54,67 @@ parse_memlimit(const char *name, const char *name_percentage, char *str,
 }
 
 
+static void
+parse_block_list(char *str)
+{
+	// It must be non-empty and not begin with a comma.
+	if (str[0] == '\0' || str[0] == ',')
+		message_fatal(_("%s: Invalid argument to --block-list"), str);
+
+	// Count the number of comma-separated strings.
+	size_t count = 1;
+	for (size_t i = 0; str[i] != '\0'; ++i)
+		if (str[i] == ',')
+			++count;
+
+	// Prevent an unlikely integer overflow.
+	if (count > SIZE_MAX / sizeof(uint64_t) - 1)
+		message_fatal(_("%s: Too many arguments to --block-list"),
+				str);
+
+	// Allocate memory to hold all the sizes specified.
+	// If --block-list was specified already, its value is forgotten.
+	free(opt_block_list);
+	opt_block_list = xmalloc((count + 1) * sizeof(uint64_t));
+
+	for (size_t i = 0; i < count; ++i) {
+		// Locate the next comma and replace it with \0.
+		char *p = strchr(str, ',');
+		if (p != NULL)
+			*p = '\0';
+
+		if (str[0] == '\0') {
+			// There is no string, that is, a comma follows
+			// another comma. Use the previous value.
+			//
+			// NOTE: We checked earler that the first char
+			// of the whole list cannot be a comma.
+			assert(i > 0);
+			opt_block_list[i] = opt_block_list[i - 1];
+		} else {
+			opt_block_list[i] = str_to_uint64("block-list", str,
+					0, UINT64_MAX);
+
+			// Zero indicates no more new Blocks.
+			if (opt_block_list[i] == 0) {
+				if (i + 1 != count)
+					message_fatal(_("0 can only be used "
+							"as the last element "
+							"in --block-list"));
+
+				opt_block_list[i] = UINT64_MAX;
+			}
+		}
+
+		str = p + 1;
+	}
+
+	// Terminate the array.
+	opt_block_list[count] = 0;
+	return;
+}
+
+
 static void
 parse_real(args_info *args, int argc, char **argv)
 {
@@ -73,6 +134,7 @@ parse_real(args_info *args, int argc, char **argv)
 		OPT_FILES,
 		OPT_FILES0,
 		OPT_BLOCK_SIZE,
+		OPT_BLOCK_LIST,
 		OPT_MEM_COMPRESS,
 		OPT_MEM_DECOMPRESS,
 		OPT_NO_ADJUST,
@@ -107,6 +169,7 @@ parse_real(args_info *args, int argc, char **argv)
 		{ "format",       required_argument, NULL,  'F' },
 		{ "check",        required_argument, NULL,  'C' },
 		{ "block-size",   required_argument, NULL,  OPT_BLOCK_SIZE },
+		{ "block-list",  required_argument, NULL,  OPT_BLOCK_LIST },
 		{ "memlimit-compress",   required_argument, NULL, OPT_MEM_COMPRESS },
 		{ "memlimit-decompress", required_argument, NULL, OPT_MEM_DECOMPRESS },
 		{ "memlimit",     required_argument, NULL,  'M' },
@@ -378,6 +441,11 @@ parse_real(args_info *args, int argc, char **argv)
 					0, LZMA_VLI_MAX);
 			break;
 
+		case OPT_BLOCK_LIST: {
+			parse_block_list(optarg);
+			break;
+		}
+
 		case OPT_SINGLE_STREAM:
 			opt_single_stream = true;
 			break;
@@ -590,3 +658,13 @@ args_parse(args_info *args, int argc, char **argv)
 
 	return;
 }
+
+
+#ifndef NDEBUG
+extern void
+args_free(void)
+{
+	free(opt_block_list);
+	return;
+}
+#endif

src/xz/args.h

@@ -40,3 +40,4 @@ extern bool opt_robot;
 extern const char stdin_filename[];
 
 extern void args_parse(args_info *args, int argc, char **argv);
+extern void args_free(void);

src/xz/coder.c

@@ -26,6 +26,7 @@ enum format_type opt_format = FORMAT_AUTO;
 bool opt_auto_adjust = true;
 bool opt_single_stream = false;
 uint64_t opt_block_size = 0;
+uint64_t *opt_block_list = NULL;
 
 
 /// Stream used to communicate with liblzma
@@ -522,16 +523,37 @@ coder_normal(file_pair *pair)
 	// Assume that something goes wrong.
 	bool success = false;
 
-	// block_remaining indicates how many input bytes to encode until
+	// block_remaining indicates how many input bytes to encode before
 	// finishing the current .xz Block. The Block size is set with
-	// --block-size=SIZE. It has an effect only when compressing
+	// --block-size=SIZE and --block-list. They have an effect only when
-	// to the .xz format. If block_remaining == UINT64_MAX, only
+	// compressing to the .xz format. If block_remaining == UINT64_MAX,
-	// a single block is created.
+	// only a single block is created.
 	uint64_t block_remaining = UINT64_MAX;
-	if (hardware_threads_get() == 1 && opt_mode == MODE_COMPRESS
+
-			&& opt_format == FORMAT_XZ && opt_block_size > 0)
+	// Position in opt_block_list. Unused if --block-list wasn't used.
+	size_t list_pos = 0;
+
+	// Handle --block-size for single-threaded mode and the first step
+	// of --block-list.
+	if (opt_mode == MODE_COMPRESS && opt_format == FORMAT_XZ) {
+		// --block-size doesn't do anything here in threaded mode,
+		// because the threaded encoder will take care of splitting
+		// to fixed-sized Blocks.
+		if (hardware_threads_get() == 1 && opt_block_size > 0)
 			block_remaining = opt_block_size;
 
+		// If --block-list was used, start with the first size.
+		//
+		// FIXME: Currently this overrides --block-size but this isn't
+		// good. For threaded case, we want --block-size to specify
+		// how big Blocks the encoder needs to be prepared to create
+		// at maximum and --block-list will simultaneously cause new
+		// Blocks to be started at specified intervals. To keep things
+		// logical, the same should be done in single-threaded mode.
+		if (opt_block_list != NULL)
+			block_remaining = opt_block_list[list_pos];
+	}
+
 	strm.next_out = out_buf.u8;
 	strm.avail_out = IO_BUFFER_SIZE;
 
@@ -575,7 +597,17 @@ coder_normal(file_pair *pair)
 		if (ret == LZMA_STREAM_END && action == LZMA_FULL_FLUSH) {
 			// Start a new Block.
 			action = LZMA_RUN;
+
+			if (opt_block_list == NULL) {
 				block_remaining = opt_block_size;
+			} else {
+				// FIXME: Make it work together with
+				// --block-size.
+				if (opt_block_list[list_pos + 1] != 0)
+					++list_pos;
+
+				block_remaining = opt_block_list[list_pos];
+			}
 
 		} else if (ret != LZMA_OK) {
 			// Determine if the return value indicates that we

src/xz/coder.h

@@ -48,6 +48,10 @@ extern bool opt_single_stream;
 /// of input. This has an effect only when compressing to the .xz format.
 extern uint64_t opt_block_size;
 
+/// This is non-NULL if --block-list was used. This contains the Block sizes
+/// as an array that is terminated with 0.
+extern uint64_t *opt_block_list;
+
 /// Set the integrity check type used when compressing
 extern void coder_set_check(lzma_check check);
 

src/xz/main.c

@@ -277,6 +277,7 @@ main(int argc, char **argv)
 
 #ifndef NDEBUG
 	coder_free();
+	args_free();
 #endif
 
 	// If we have got a signal, raise it to kill the program instead

src/xz/message.c

@@ -1153,10 +1153,16 @@ message_help(bool long_help)
 "                      does not affect decompressor memory requirements"));
 
 	if (long_help) {
+		// FIXME? Mention something about threading?
 		puts(_(
 "      --block-size=SIZE\n"
 "                      when compressing to the .xz format, start a new block\n"
 "                      after every SIZE bytes of input; 0=disabled (default)"));
+		// FIXME
+		puts(_(
+"      --block-list=SIZES\n"
+"                      when compressing to the .xz format, start a new block\n"
+"                      after the given intervals of uncompressed data"));
 		puts(_( // xgettext:no-c-format
 "      --memlimit-compress=LIMIT\n"
 "      --memlimit-decompress=LIMIT\n"

src/xz/xz.1

@@ -5,7 +5,7 @@
 .\" This file has been put into the public domain.
 .\" You can do whatever you want with this file.
 .\"
-.TH XZ 1 "2012-07-01" "Tukaani" "XZ Utils"
+.TH XZ 1 "2012-07-03" "Tukaani" "XZ Utils"
 .
 .SH NAME
 xz, unxz, xzcat, lzma, unlzma, lzcat \- Compress or decompress .xz and .lzma files
@@ -807,7 +807,26 @@ format, split the input data into blocks of
 .I size
 bytes.
 The blocks are compressed independently from each other.
-.\" FIXME: Explain how to his can be used for random access and threading.
+.\" FIXME: Explain how to these can be used for random access and threading.
+.TP
+.BI \-\-block\-list= sizes
+When compressing to the
+.B .xz
+format, start a new block after
+the given intervals of uncompressed data.
+.IP ""
+The uncompressed
+.I sizes
+of the blocks are specified as a comma-separated list.
+Omitting a size (two or more consecutive commas) is a shorthand
+to use the size of the previous block.
+A special value of
+.B 0
+may be used as the last value to indicate that
+the rest of the file should be encoded as a single block.
+.IP ""
+.B "Currently this option is badly broken if used together with"
+.B "\-\-block\-size or with multithreading."
 .TP
 .BI \-\-memlimit\-compress= limit
 Set a memory usage limit for compression.