Update the code to mostly match the new simpler file format

specification. Simplify things by removing most of the
support for known uncompressed size in most places.
There are some miscellaneous changes here and there too.

The API of liblzma has got many changes and still some
more will be done soon. While most of the code has been
updated, some things are not fixed (the command line tool
will choke with invalid filter chain, if nothing else).

Subblock filter is somewhat broken for now. It will be
updated once the encoded format of the Subblock filter
has been decided.

1 files changed, 47 insertions, 52 deletions

diff --git a/src/liblzma/common/alone_encoder.c b/src/liblzma/common/alone_encoder.c
index 7629aa77..f94a21c1 100644
--- a/src/liblzma/common/alone_encoder.c
+++ b/src/liblzma/common/alone_encoder.c
@@ -21,19 +21,19 @@
 #include "lzma_encoder.h"
 
 
+#define ALONE_HEADER_SIZE (1 + 4 + 8)
+
+
 struct lzma_coder_s {
 	lzma_next_coder next;
 
 	enum {
-		SEQ_PROPERTIES,
-		SEQ_DICTIONARY_SIZE,
-		SEQ_UNCOMPRESSED_SIZE,
+		SEQ_HEADER,
 		SEQ_CODE,
 	} sequence;
 
-	size_t pos;
-
-	lzma_options_alone options;
+	size_t header_pos;
+	uint8_t header[ALONE_HEADER_SIZE];
 };
 
 
@@ -47,47 +47,23 @@ alone_encode(lzma_coder *coder,
 {
 	while (*out_pos < out_size)
 	switch (coder->sequence) {
-	case SEQ_PROPERTIES:
-		if (lzma_lzma_encode_properties(
-				&coder->options.lzma, out + *out_pos)) {
-			return LZMA_PROG_ERROR;
-		}
-
-		coder->sequence = SEQ_DICTIONARY_SIZE;
-		++*out_pos;
-		break;
-
-	case SEQ_DICTIONARY_SIZE:
-		out[*out_pos] = coder->options.lzma.dictionary_size
-				>> (coder->pos * 8);
-
-		if (++coder->pos == 4) {
-			coder->pos = 0;
-			coder->sequence = SEQ_UNCOMPRESSED_SIZE;
-		}
-
-		++*out_pos;
-		break;
-
-	case SEQ_UNCOMPRESSED_SIZE:
-		out[*out_pos] = coder->options.uncompressed_size
-				>> (coder->pos * 8);
-
-		if (++coder->pos == 8) {
-			coder->pos = 0;
-			coder->sequence = SEQ_CODE;
-		}
-
-		++*out_pos;
+	case SEQ_HEADER:
+		bufcpy(coder->header, &coder->header_pos,
+				ALONE_HEADER_SIZE,
+				out, out_pos, out_size);
+		if (coder->header_pos < ALONE_HEADER_SIZE)
+			return LZMA_OK;
+
+		coder->sequence = SEQ_CODE;
 		break;
 
-	case SEQ_CODE: {
+	case SEQ_CODE:
 		return coder->next.code(coder->next.coder,
 				allocator, in, in_pos, in_size,
 				out, out_pos, out_size, action);
-	}
 
 	default:
+		assert(0);
 		return LZMA_PROG_ERROR;
 	}
 
@@ -107,7 +83,7 @@ alone_encoder_end(lzma_coder *coder, lzma_allocator *allocator)
 // At least for now, this is not used by any internal function.
 static lzma_ret
 alone_encoder_init(lzma_next_coder *next, lzma_allocator *allocator,
-		const lzma_options_alone *options)
+		const lzma_options_lzma *options)
 {
 	if (next->coder == NULL) {
 		next->coder = lzma_alloc(sizeof(lzma_coder), allocator);
@@ -119,23 +95,42 @@ alone_encoder_init(lzma_next_coder *next, lzma_allocator *allocator,
 		next->coder->next = LZMA_NEXT_CODER_INIT;
 	}
 
-	// Initialize the LZMA_Alone coder variables.
-	next->coder->sequence = SEQ_PROPERTIES;
-	next->coder->pos = 0;
-	next->coder->options = *options;
+	// Basic initializations
+	next->coder->sequence = SEQ_HEADER;
+	next->coder->header_pos = 0;
 
-	// Verify uncompressed_size since the other functions assume that
-	// it is valid.
-	if (!lzma_vli_is_valid(next->coder->options.uncompressed_size))
+	// Encode the header:
+	// - Properties (1 byte)
+	if (lzma_lzma_encode_properties(options, next->coder->header))
 		return LZMA_PROG_ERROR;
 
+	// - Dictionary size (4 bytes)
+	if (options->dictionary_size < LZMA_DICTIONARY_SIZE_MIN
+			|| options->dictionary_size > LZMA_DICTIONARY_SIZE_MAX)
+		return LZMA_PROG_ERROR;
+
+	// Round up to to the next 2^n or 2^n + 2^(n - 1) depending on which
+	// one is the next. While the header would allow any 32-bit integer,
+	// we do this to keep the decoder of liblzma accepting the resulting
+	// files.
+	uint32_t d = options->dictionary_size - 1;
+	d |= d >> 2;
+	d |= d >> 3;
+	d |= d >> 4;
+	d |= d >> 8;
+	d |= d >> 16;
+	++d;
+
+	integer_write_32(next->coder->header + 1, d);
+
+	// - Uncompressed size (always unknown and using EOPM)
+	memset(next->coder->header + 1 + 4, 0xFF, 8);
+
 	// Initialize the LZMA encoder.
 	const lzma_filter_info filters[2] = {
 		{
 			.init = &lzma_lzma_encoder_init,
-			.options = &next->coder->options.lzma,
-			.uncompressed_size = next->coder->options
-					.uncompressed_size,
+			.options = (void *)(options),
 		}, {
 			.init = NULL,
 		}
@@ -156,7 +151,7 @@ lzma_alone_encoder_init(lzma_next_coder *next, lzma_allocator *allocator,
 
 
 extern LZMA_API lzma_ret
-lzma_alone_encoder(lzma_stream *strm, const lzma_options_alone *options)
+lzma_alone_encoder(lzma_stream *strm, const lzma_options_lzma *options)
 {
 	lzma_next_strm_init(strm, alone_encoder_init, options);