Update Changelog

Also, improve handling of disassembly errors -
methods will be partially disassembled as far as possible.

CHANGELOG.md

@@ -1,36 +1,182 @@
-RABCDAsm Changelog
-==================
-
-RABCDAsm v1.3 (2010.11.11)
---------------------------
-
- * Fixed double precision problem
-   * This also fixes problems with illegal default values for function
-     parameters (default values for integer parameters are stored as doubles, 
-     which might become out-of-range due to inadequate double precision)
- * Added Changelog
- * Documentation markdown fixes
-
-RABCDAsm v1.2 (2010.11.06)
---------------------------
-
- * Fixed ref generation for orphan objects which were only referenced
-   by other orphans
- * Better error handling in `abcexport`; warn when no DoABC tags found
- * Documentation updates
-
-RABCDAsm v1.1 (2010.06.30)
---------------------------
-
- * Private namespaces are now referenced by auto-generated names
- * Use `:` to delimit namespace and name in QNames for consistency
-    * Warning: this breaks compatibility with v1.0 disassemblies
- * Fixed relative include paths
- * Add optional byte offsets to labels, which allows lossless representation
-   of jumps inside instructions and outside the function bounds
- * Documentation updates
-
-RABCDAsm v1.0 (2010.05.05)
---------------------------
-
- * Initial release.
+RABCDAsm Changelog
+==================
+
+RABCDAsm v1.17 (2014.09.10)
+---------------------------
+
+ * Do not attempt to disassemble unreachable code
+ * Improve handling of disassembly errors:
+   methods will be partially disassembled as far as possible.
+ * Fix LZMA errors with uncompressable data.
+
+RABCDAsm v1.16 (2014.04.21)
+---------------------------
+
+ * Fix handling of TypeName-kind Multinames with null parameters
+ * Fix v1.15 regression in handling very long paths on Windows
+   (DMD 2.066 is required when building from source for this to work)
+
+RABCDAsm v1.15 (2014.01.11)
+---------------------------
+
+ * Fix building on systems with a noexec `/tmp/`
+ * Improve compatibility with 3rd-party players
+   * Don't emit forward references in TypeName-kind Multinames
+ * Improve performance and memory usage
+
+RABCDAsm v1.14 (2013.08.21)
+---------------------------
+
+ * Improved refid generation
+ * Worked around liblzma dictionary size limitation, which prevented 
+   decompression of some LZMA-compressed files
+ * Added an option to `swflzmacompress` to update the SWF version number
+ * Added `finddef` instruction
+ * Added unimplemented `{get|set|delete}propertylate` instructions
+ * Documentation updates
+
+RABCDAsm v1.13 (2012.09.29)
+---------------------------
+
+ * Fixed handling of truncated SWF tags
+
+RABCDAsm v1.12 (2012.09.08)
+---------------------------
+
+ * Relaxed filename sanitization for names like "controller"
+ * Added range validation for byte literals
+ * Fixed LZMA support misdetection caused by stale rdmd cache
+ * Added coerce_b, coerce_i and coerce_d opcodes
+ * Fixed handling of recursively-nested function literals
+ * Fixed handling of homonym non-private namespaces
+   * #privatens directives are now ignored, and no longer generated
+ * Improved refid generation
+ * Bumped #version to 3 (v1.12 disassemblies are not backwards-compatible)
+ * Documentation updates
+
+RABCDAsm v1.11 (2012.03.15)
+---------------------------
+
+ * Fixed v1.10 hierarchy flattening regression
+ * Improved refid generation for protected namespaces
+ * Improved handling of overflown signed integers
+ * Fixed metadata handling (caused by error in ABC format specification)
+ * Added #version directive (v1.11 disassemblies are not backwards-compatible)
+ * Removed path length limitation on Windows
+ * Improved filename sanitization
+ * Updated asasm.hrc
+ * Documentation updates
+
+RABCDAsm v1.10 (2012.02.29)
+---------------------------
+
+ * Fixed escaping of paths with empty segments
+
+RABCDAsm v1.9 (2012.02.07)
+--------------------------
+
+ * Added support for LZMA-compressed SWF files
+ * Added swflzmacompress
+ * Fixed undiscovered private namespaces in class interfaces
+ * Fixed handling of overflown integers
+ * Documentation updates
+
+RABCDAsm v1.8 (2011.07.06)
+--------------------------
+
+ * Fixed handling of orphan methods with multiple references
+ * Treat out-of-bounds namespace/multiname indices as null
+ * Documentation updates
+
+RABCDAsm v1.7 (2011.06.14)
+--------------------------
+
+ * Fixed handling of invalid UTF-8 in strings
+ * Fixed handling of null namespaces and multinames
+ * Fixed handling of exception info in corrupted method bodies
+ * Fixed handling of orphan private namespaces
+ * Fixed handling of out-of-bounds class/method indices
+ * Disassembler now creates one file per class and script-level method
+ * Disassembler now outputs blank lines after `si32` etc. instructions as well
+ * `abcexport` now delimits the index with a dash in output filenames
+ * Improved shortening of `double` literals
+ * Documentation updates
+
+RABCDAsm v1.6 (2011.05.13)
+--------------------------
+
+ * Overhaul of the structure of disassembler-generated files
+   * Private namespace names and `refid`s for nested classes are now generated 
+     from their referenced contexts
+     * This also fixes problems caused by private namespaces being referenced 
+       in multiple distinct contexts
+   * One `#include`d file per script instead of per class
+     * Nested classes, script initializers and other script traits are now in 
+       the same file as their main class
+   * Inline methods are now in separate files, placed according to their usage 
+     context
+   * Private namespaces are sorted by their autogenerated names in the 
+     `.privatens.asasm` file
+   * No syntax changes, output is backwards-compatible
+ * Improved escaping of file names
+ * Output correct opcode error locations
+ * Disassembler will now refuse to overwrite files
+ * `rabcdasm` will now always generate output in the same directory as the 
+   input file
+ * Failure to decode a method body is now not a fatal error
+ * Aggressively try to shorten double literals to their shortest representation
+ * Added the `swfbinexport` and `swfbinreplace` utilities, to aid in 
+   manipulating contents of `DefineBinaryData` tags
+ * The package can now be built using a simple, dedicated build tool
+ * Documentation updates
+
+RABCDAsm v1.5 (2011.04.14)
+--------------------------
+
+ * Fixed v1.4 constant pool regression
+ * Added support for memory-access and sign-extend opcodes
+ * Speed optimizations
+ * Documentation updates
+
+RABCDAsm v1.4 (2011.03.07)
+--------------------------
+
+ * Source code ported to D2
+ * Add support for forward-references for TypeName-kind Multinames
+ * Correctly order classes by dependencies (extends/implements) and reference 
+   count
+ * Finish Metadata support
+ * Documentation updates
+
+RABCDAsm v1.3 (2010.11.11)
+--------------------------
+
+ * Fixed double precision problem
+   * This also fixes problems with illegal default values for function 
+     parameters (default values for integer parameters are stored as doubles, 
+     which might become out-of-range due to inadequate double precision)
+ * Added Changelog
+ * Documentation markdown fixes
+
+RABCDAsm v1.2 (2010.11.06)
+--------------------------
+
+ * Fixed ref generation for orphan objects which were only referenced by other 
+   orphans
+ * Better error handling in `abcexport`; warn when no DoABC tags found
+ * Documentation updates
+
+RABCDAsm v1.1 (2010.06.30)
+--------------------------
+
+ * Private namespaces are now referenced by auto-generated names
+ * Use `:` to delimit namespace and name in QNames for consistency
+ * Fixed relative include paths
+ * Add optional byte offsets to labels, which allows lossless representation 
+   of jumps inside instructions and outside the function bounds
+ * Documentation updates
+
+RABCDAsm v1.0 (2010.05.05)
+--------------------------
+
+ * Initial release.

README.md

@@ -1,447 +1,459 @@
-Robust ABC (ActionScript Bytecode) [Dis-]Assembler
-==================================================
-
-[RABCDAsm][] is a collection of utilities including an ActionScript 3
-assembler/disassembler, and a few tools to manipulate SWF files. 
-These are:
-
- * `rabcdasm` - ABC disassembler
- * `rabcasm` - ABC assembler
- * `abcexport` - extracts ABC from SWF files
- * `abcreplace` - replaces ABC in SWF files
- * `swfdecompress` - decompresses zlib-compressed SWF files
- * `swf7zcompress` - (re-)compress the contents of a SWF using 7-Zip
-
-`abcexport` and `abcreplace` are reimplementations of similar utilities from
-my [swfutilsex][] Java package, however these work faster as they do not parse 
-the SWF files as deeply.  
-`swfdecompress` is ancilliary and is only useful for debugging and studying of
-the SWF file format, and not required for ABC manipulation. It is functionally
-equivalent to [flasm][]'s `-x` option.  
-`swf7zcompress` is an utility to further reduce the size of SWF files. It uses
-[7-Zip][] to compress the data better than the standard zlib library would. It
-requires that the `7z` command-line program be installed and in `PATH`.
-
-  [RABCDAsm]: http://github.com/CyberShadow/RABCDAsm
-  [swfutilsex]: http://github.com/CyberShadow/swfutilsex
-  [flasm]: http://flasm.sourceforge.net/
-  [7-Zip]: http://www.7-zip.org/
-
-Motivation and goals
---------------------
-
-This package was created due to lack of similar software out there. 
-Particularly, I needed an utility which would allow me to edit ActionScript 3
-bytecode with the following properties:
-
- 1. Speed. Less waiting means more productivity. `rabcasm` can assemble large
-    projects (>200000 LOC) in under a second on modern machines.
- 2. Comfortably-editable output. Each class is decompiled to its own file, with
-    files arranged in subdirectories representing the package hierarchy. Class
-    files are `#include`d from the main file.
- 3. Most importantly - robustness! If the Adobe AVM can load and run the file,
-    then it must be editable - no matter if the file is obfuscated or otherwise
-    mutilated to prevent reverse-engineering. RABCDAsm achieves this by using
-    a textual representation closer to the ABC file format, rather than to what
-    an ActionScript compiler would generate.
-
-Compiling from source
----------------------
-
-RABCDAsm is written in the [D programming language, version 1][d1]. It uses one
-third-party library, [std2][] (for some fancy template stuff).
-
-Assuming you have [dmd][], [git][] and [svn][] installed, compiling should be
-as straight-forward as:
-
-    git clone git://github.com/CyberShadow/RABCDAsm.git
-    cd RABCDAsm
-    svn co http://svn.dsource.org/projects/std2/trunk/std2/std2
-    dmd rabcdasm abcfile asprogram disassembler autodata murmurhash2a
-    dmd rabcasm  abcfile asprogram    assembler autodata murmurhash2a
-    dmd abcexport     swffile zlibx
-    dmd abcreplace    swffile zlibx
-    dmd swfdecompress swffile zlibx
-    dmd swf7zcompress swffile zlibx
-
-  [d1]: http://www.digitalmars.com/d/1.0/
-  [std2]: http://dsource.org/projects/std2
-  [dmd]: http://www.digitalmars.com/d/download.html
-  [git]: http://git-scm.com/
-  [svn]: http://subversion.apache.org/
-
-Pre-compiled binaries
----------------------
-
-You can find pre-compiled Windows binaries in the [Downloads section on 
-GitHub][downloads]. However, please don't expect them to be up-to-date
-with the latest source versions.
-
-  [downloads]: http://github.com/CyberShadow/RABCDAsm/downloads
-
-Usage
------
-
-To begin hacking on a SWF file:
-
-    abcexport file.swf
-
-This will create `file0.abc` ... `fileN.abc` (often just `file0.abc`). Each 
-file corresponds to an ABC block inside the SWF file.
-
-To disassemble one of the `.abc` files:
-
-    rabcdasm file0.abc
-
-This will create a `file0` directory, which will contain `file0.main.asasm`
-(the main program file), `file0.privatens.asasm` (private namespace alias
-definitions) and a file per ActionScript class.
-
-To assemble the `.asasm` files back, and update the SWF file:
-
-    rabcasm file0/file0.main.asasm
-    abcreplace file0.swf 0 file0/file0.main.abc
-
-The second `abcreplace` argument represents the index of the ABC block in the
-SWF file, and corresponds to the number in the filename created by `abcexport`.
-
-Syntax
-======
-
-The syntax of the disassembly was designed to be very simple and allow fast 
-and easy parsing. It is a close representation of the `.abc` file format, and 
-thus it is somewhat verbose. All constant pool elements (signed/unsigned 
-integers, doubles, strings, namespaces, namespace sets, multinames) are always 
-*expanded inline*, for ease of editing. Similarly, classes, instances, methods
-and method bodies are also defined inline, in the context of their "parent"
-object. By-index references of classes and methods (used in the `newclass`, 
-`newfunction` and `callstatic` instructions) are represented via 
-automatically-generated unique "reference strings", declared as `refid` fields.
-
-If you haven't yet, I strongly recommend that you look through Adobe's
-[ActionScript Virtual Machine 2 (AVM2) Overview][avm2]. You will most likely
-need to consult it for the instruction reference anyway (although you can also 
-use [this handy list][avm2i] as well). You will find it difficult to understand
-the disassembly without good understanding of concepts such as namespaces and
-multinames.
-
-  [avm2]: http://www.adobe.com/devnet/actionscript/articles/avm2overview.pdf
-  [avm2i]: http://www.anotherbigidea.com/javaswf/avm2/AVM2Instructions.html
-
-Overview
---------
-
-In order to guarantee unambiguity and data preservation, all strings read from
-the input file - including identifiers (variable/function/class names) - are 
-represented as string literals. Thus, the syntax does not have any "reserved
-words" or such - an unrecognized word is treated as an error, not as an 
-identifier.
-
-Whitespace (outside string literals, of course) is completely ignored, except 
-where required to separate words. Comments are Intel-assembler-style: a single 
-`;` demarks a comment until the next end-of-line. Control directives (such as
-`#include`) are allowed anywhere where whitespace is allowed.
-
-The syntax is comprised of hierarchical blocks. Each block contains a number
-of fields - starting with a keyword specifying the field type. A block is 
-terminated with the `end` keyword. Some fields contain a limited number of
-parameters, and others are, or contain blocks.
-
-Hierarchy
----------
-
-The topmost block in the hierarchy is the `program` block. This must be the 
-first block in the file (thus, `program` must be the first word in the file as
-well). The `program` block contains `script` fields, and `class` / `method` 
-fields for "orphan" classes and methods (not owned by other objects in the 
-hierarchy). Orphan methods are usually anonymous functions. The file version is
-also specified in the `program` block, using the `minorversion` and 
-`majorversion` fields (both unsigned integers).
-
-`script` blocks have one mandatory `sinit` field (the script initialization 
-method) and `trait` fields.
-
-A "trait" can be one of several kinds. The kind is specified right after the
-`trait` keyword, followed by the trait name (a multiname). Following the name
-are the trait fields, varying by trait kind:
-
- * `slot` / `const` : `slotid` (unsigned integer), `type` (multiname), `value`
- * `class` : `slotid`, `class` (the actual class block)
- * `function` : `slotid`, `method` (the actual method block)
- * `method` / `getter` / `setter` : `dispid` (unsigned integer), `method`
-
-Additionally, all traits may have `flag` fields, describing the trait's 
-attributes (`FINAL` / `OVERRIDE` / `METADATA`).
-
-`class` blocks have mandatory `instance` and `cinit` fields, defining the class
-instance and the class initializer method respectively. They may also have 
-`trait` fields and a `refid` field (the `refid` field is not part of the file 
-format - it's an unique string to allow referencing the class, see above).
-
-`instance` blocks - always declared inline of their `class` block - must 
-contain one `iinit` field (the instance initializer method), and may contain 
-one `extends` field (multiname), `implements` fields (multinames), `flag` 
-fields (`SEALED` / `FINAL` / `INTERFACE` / `PROTECTEDNS`), one `protectedns` 
-field (namespace), and `trait` fields.
-
-`method` blocks may contain one `name` field (multiname), a `refid` field,
-`param` fields (multinames - this represents the parameter types), one
-`returns` field (multiname), `flag` fields (`NEED_ARGUMENTS` / 
-`NEED_ACTIVATION` / `NEED_REST` / `HAS_OPTIONAL` / `SET_DXNS` / 
-`HAS_PARAM_NAMES`), `optional` fields (values), `paramname` fields (strings), 
-and a `body` field (method body).
-
-`body` blocks - always declared inline of their `method` block - must contain
-the `maxstack`, `localcount`, `initscopedepth` and `maxscopedepth` fields 
-(unsigned integers), and a `code` field. It may also contain `try` and `trait`
-fields.
-
-`code` blocks - always declared inline of their `body` block - are somewhat 
-different in syntax from other blocks - mostly in that they may contain labels.
-Labels follow the most common syntax - a word followed by a `:` character, 
-optionally followed by a relative byte offset (in case of pointers inside 
-instructions). Multiple instruction arguments are comma-separated. Instruction 
-arguments' types depend on the instruction - see the `OpcodeInfo` array in 
-`abcfile.d` for a reference.
-
-`try` blocks - always declared inline of their `body` block - represent an
-"exception" (try/catch) block. They contain five mandatory fields: `from`,
-`to` and `target` (names of labels representing start and end of the "try"
-block, and start of the "catch" block respectively), and `type` and `name` 
-(multinames), representing the type and name of the exception variable.
-
-Values have the syntax *type* `(` *value* `)` . *type* can be one of `Integer`,
-`UInteger`, `Double`, `Utf8`, `Namespace`, `PackageNamespace`, 
-`PackageInternalNs`, `ProtectedNamespace`, `ExplicitNamespace`, 
-`StaticProtectedNs`, `PrivateNamespace`, `True`, `False`, `Null` or 
-`Undefined`. The type of the value depends on *type*. Types `True`, `False`, 
-`Null` and `Undefined` have no value.
-
-Constants
----------
-
-Multinames have the syntax *type* `(` *parameters* `)` . *type* can be one of 
-`QName` / `QNameA`, `RTQName` / `RTQNameA`, `RTQNameL` / `RTQNameLA`, 
-`Multiname` / `MultinameA`, `MultinameL` / `MultinameLA`, or `TypeName`.
-*parameters* depends on *type*:
-
- * `QName` / `QNameA` `(` *namespace* `,` *string* `)`
- * `RTQName` / `RTQNameA` `(` *string* `)`
- * `RTQNameL` / `RTQNameLA` `(` `)`
- * `Multiname` / `MultinameA` `(` *string* `,` *namespace-set* `)`
- * `MultinameL` / `MultinameLA` `(` *namespace-set* `)`
- * `TypeName` `(` *multiname* `<` *multiname [* `,` *multiname ... ]* `>` `)`
-
-Namespace sets have the syntax `[` *[ namespace [* `,` *namespace ... ] ]* `]`
-(that is, a comma-separated list of namespaces in square brackets). Empty
-namespace sets can be specified using `[]`.
-
-Namespaces have the syntax *type* `(` *parameters* `)` . For types other than
-`PrivateNamespace` there is only one parameter - a string. `PrivateNamespace`
-namespaces have a second parameter, a named alias for a particular private
-namespace. Internally (the ABC file format), private namespaces are 
-distinguished by a numerical index - `rabcdasm` will attempt to give them
-descriptive names based on their context. Aliases can be defined using the 
-`#privatens` directive. `rabcdasm` will create a separate file containing the
-aliases (`file0.privatens.asasm`).
-
-Strings have a syntax similar to C string literals. Strings start and end with
-a `"`. Supported escape sequences (a backslash followed by a letter) are `\n`
-(generates ASCII 0x0A), `\r` (ASCII 0x0D), and `\x` followed by two hexadecimal
-digits, which inserts the ASCII character with that code. Any other characters
-following a backslash generate that character - thus, you can escape 
-backslashes using `\\` and double quotes using `\"`. When decompiling, 
-high-ASCII characters (usually UTF-8) are not escaped - if you see gibberish 
-instead of international text, configure your editor to open the files in UTF-8
-encoding.
-
-Additionally, constant pool types (signed/unsigned integers, doubles, strings,
-namespaces, namespace sets and multinames) may also have the value `null`
-(which represents the index 0 in the ABC file). Note that `null` is 
-conceptually different from zero, an empty string or empty namespace set.
-
-Macros
-------
-
-RABCDAsm has some basic macro-like capabilities, controlled by directives and 
-variables. These bear some similarity to the C preprocessor, however these 
-are processed in-loop rather than as a separate pre-processing step.
-
-### Directives
-
-Directives start with a `#`, followed by a word identifying the directive:
-
-  * `#include` *string* - inserts the contents of the file by the specified
-    filename inline. Functionally equivalent to `#mixin #get` *string* , but 
-    faster.
-  * `#mixin` *string* - inserts the contents of the specified string inline.
-    Not very useful on its own.
-  * `#call` *string* `(` *[ string [* `,` *string ... ] ]* `)` - same as 
-    `#mixin`, however it additionally sets the special variables `$1`, `$2` 
-    etc. to the contents of the specified arguments. When the end of the 
-    inserted string is reached, the old values of `$1`, `$2` etc. are restored.
-  * `#get` *string* - inserts **a string containing** the contents of the 
-    file by the specified filename inline. Similar to #include, but it inserts
-    a string (surrounded by `"` etc.) instead.
-  * `#set` *word* *string* - assigns the contents of the string to the 
-    variable *word*.
-  * `#unset` *word* - deletes the variable *word*.
-  * `#privatens` defines a private namespace alias, as described above.
-
-### Variables
-
-Variables are manipulated with the `#set` and `#unset` directives, and can
-be instantiated in two ways:
-
-  1. `$`*name* - this inserts the contents of the variable inline. Note that
-     although variables are defined using a string syntax, they are not 
-     inserted as a string using this syntax. Thus, the code:
-
-         #set str "Hello, world!"
-         ...
-         pushstring $str
-
-     will expand to `pushstring Hello, world!`, which will result in an error.
-     To correct the problem, add escaped quotes around the variable contents
-     ( `#set str "\"Hello, world!\""` ), or use the second syntax:
-  
-  2. `$"`*name*`"` - this inserts a string containing the contents of the 
-     variable inline. This syntax also works for `#call` arguments (e.g. 
-     `$"1"`).
-
-### Example
-
-Here's an example of how to use the above features to create a macro which
-logs a string literal and the contents of a register:
-
-    #set log "
-        findpropstrict      QName(PackageNamespace(\"\"), \"log\")
-        pushstring          $\"1\"
-        getlocal            $2
-        callpropvoid        QName(PackageNamespace(\"\"), \"log\"), 2
-    "
-    
-    ; ...
-    
-    pushbyte 2
-    pushbyte 2
-    add_i
-    setlocal1
-    #call $"log"("two plus two equals", "1")
-     
-Highlighting
-------------
-
-Included with the project is the file `asasm.hrc`, a simple syntax definition 
-for the [Colorer take5][] syntax highlighting library. It should be 
-straight-forward to adapt it to other syntax highlighting systems.
-
-  [Colorer take5]: http://colorer.sourceforge.net/
-
-Hacking
-=======
-
-ABC is internally represented in two forms. The `ABCFile` class stores the raw 
-data structures, as they appear in the binary file. `ASProgram` uses pointers
-instead of indexes, allowing easy manipulation without having to worry about
-record order or constant pools. Conversion between various states is done as
-follows:
-
-                                 file.abc
-                                   |  ^
-                  ------ ABCReader |  | ABCWriter ----
-                 /                 v  |               \
-                /                ABCFile               \
-               /                   |  ^                 \
-        rabcdasm---------- ABCtoAS |  | AStoABC --------rabcasm
-               \                   v  |                 /
-                \               ASProgram              /
-                 \                 |  ^               /
-                  --- Disassembler |  | Assembler ----
-                                   v  |
-                                file.asasm
-
-`AStoABC` will rebuild the constant pools, in a manner similar to Adobe's
-compilers (reverse-sorted by reference count). The exact order will almost
-surely be different, however. Also, some records (classes and methods) are
-currently not sorted by reference count, which may cause `rabcasm` to generate 
-slightly larger files than the originals (due to variable-length encoding of 
-integers).
-
-Should you need to write an utility to manipulate ABC, you can use the existing
-code to load the file to either an `ABCFile` or `ASProgram` instance, and 
-perform the necessary manipulations using those classes.
-
-Tips
-====
-
-The following tips come from the author's experience and may be useful for 
-RABCDAsm users.
-
-1. Once you have disassembled a SWF file you intend to modify, you should 
-   immediately add the directory to a distributed source control system, such as 
-   [Git][] or [Mercurial][]. This will allow you to easily track and undo your 
-   changes, and easily merge your changes with new versions of SWF files.
-
-  [Git]: http://git-scm.com/
-  [Mercurial]: http://mercurial.selenic.com/
-
-2. If you plan on making non-trivial changes to SWF files, you should install 
-   the [debug Flash Player][]. This will allow you to see validation and 
-   run-time error messages, instead of simply getting a blank rectangle.
-
-  [debug Flash Player]: http://www.adobe.com/support/flashplayer/downloads.html
-
-3. The [Fiddler][] Web Debugging Proxy can be very useful for analysing 
-   websites with SWF content. The following script fragment (which is to be
-   placed in the `OnBeforeResponse` function) will automatically save all SWF 
-   files while preserving the directory structure.
-
-       if (oSession.oResponse.headers.ExistsAndContains("Content-Type", 
-               "application/x-shockwave-flash")) {
-           // Set desired path here
-           var path:String = "C:\\Temp\\FiddlerCapture\\" + 
-               oSession.host + oSession.PathAndQuery;
-           if (path.Contains('?'))
-               path = path.Substring(0, path.IndexOf('?'));
-           var dir:String = Path.GetDirectoryName(path);
-           if (!Directory.Exists(dir))
-               Directory.CreateDirectory(dir);
-           oSession.utilDecodeResponse();
-           oSession.SaveResponseBody(path);
-       }
-
-   Once you have edited a SWF file, you can use Fiddler's [AutoResponder][] to
-   replace the original file with your modified version.
-
-  [Fiddler]: http://www.fiddler2.com/fiddler2/
-  [AutoResponder]: http://www.fiddler2.com/fiddler2/help/AutoResponder.asp
-
-Limitations
-===========
-
-* Metadata is currently ignored. I haven't noticed any metadata blocks in any
-  SWF files I've disassembled.
-
-* `rabcasm` may create a broken file due to not ordering classes by ancestry.
-
-  The problem originates from the fact that a class's ancestors (extended 
-  class and implemented interfaces) are stored as multinames, and not as 
-  class indices. (This makes sense, since classes may extend objects outside 
-  the current ABC file.) Since `rabcasm` currently doesn't decode multinames, 
-  it is unaware of the class dependencies, and may thus write the classes out 
-  of order. This results in a file that, when opened, will fail to load with 
-  an error message similar to:
-
-      VerifyError: Error #1014: Class AncestorClassName could not be found.
-
-  The simple work-around is to re-order the classes as they are declared in 
-  the `.main.asasm` file, and place ancestors before descendants.
-
-License
-=======
-
-RABCDAsm is distributed under the terms of the GPL v3 or later, with the
-exception of `murmurhash2a.d` and `zlibx.d`, which are in the public domain, 
-and `asasm.hrc`, which is tri-licensed under the MPL 1.1/GPL 2.0/LGPL 2.1. The 
-full text of the GNU General Public License can be found in the file `COPYING`.
+Robust ABC (ActionScript Bytecode) [Dis-]Assembler
+==================================================
+
+[RABCDAsm][] is a collection of utilities including an ActionScript 3 
+assembler/disassembler, and a few tools to manipulate SWF files. These are:
+
+ * `rabcdasm` - ABC disassembler
+ * `rabcasm` - ABC assembler
+ * `abcexport` - extracts ABC from SWF files
+ * `abcreplace` - replaces ABC in SWF files
+ * `swfdecompress` - decompresses zlib-compressed SWF files
+ * `swf7zcompress` - (re-)compress the contents of a SWF using 7-Zip
+ * `swflzmacompress` - compress the contents of a SWF using LZMA
+ * `swfbinexport` / `swfbinreplace` - extract/replace contents of binary data 
+   tags from SWF files
+
+`abcexport` and `abcreplace` are reimplementations of similar utilities from 
+my [swfutilsex][] Java package, however these work faster as they do not parse 
+the SWF files as deeply.  
+`swfdecompress` is ancillary and is only useful for debugging and studying of 
+the SWF file format, and not required for ABC manipulation. It is functionally 
+equivalent to [flasm][]'s `-x` option. If you frequently work on compressed 
+SWF files, you may want to decompress them to speed processing up.  
+`swf7zcompress` is an utility to further reduce the size of SWF files. It uses 
+[7-Zip][] to compress the data better than the standard zlib library would. It 
+requires that the `7z` command-line program be installed and in `PATH`.  
+`swflzmacompress` compresses SWF files using the [LZMA][] algorithm, support 
+for which was introduced in Flash 11. It will only work with SWF files with 
+version 13 or higher.  
+`swfbinexport` and `swfbinreplace` aid in the manipulation of 
+`DefineBinaryData` tags in SWF files (some files may contain nested SWF files 
+stored in these tags).
+
+  [RABCDAsm]: http://github.com/CyberShadow/RABCDAsm
+  [swfutilsex]: http://github.com/CyberShadow/swfutilsex
+  [flasm]: http://flasm.sourceforge.net/
+  [7-Zip]: http://www.7-zip.org/
+  [LZMA]: http://en.wikipedia.org/wiki/Lempel-Ziv-Markov_chain_algorithm
+
+Motivation and goals
+--------------------
+
+This package was created due to lack of similar software out there. 
+Particularly, I needed an utility which would allow me to edit ActionScript 3 
+bytecode with the following properties:
+
+ 1. Speed. Less waiting means more productivity. `rabcasm` can assemble large 
+    projects (>200000 LOC) in under a second on modern machines.
+ 2. Comfortably-editable output. Each class is decompiled to its own file, 
+    with files arranged in subdirectories representing the package hierarchy. 
+    Class files are `#include`d from the main file.
+ 3. Most importantly - robustness! If the Adobe AVM can load and run the file, 
+    then it must be editable - no matter if the file is obfuscated or 
+    otherwise mutilated to prevent reverse-engineering. RABCDAsm achieves this 
+    by using a textual representation closer to the ABC file format, rather 
+    than to what an ActionScript compiler would generate.
+
+Compiling from source
+---------------------
+
+RABCDAsm is written in the [D programming language, version 2][d2].
+
+Assuming you have [git][] and a D2 compiler, such as [dmd][] or [gdc][] 
+installed, compiling should be as straight-forward as:
+
+    git clone git://github.com/CyberShadow/RABCDAsm.git
+    cd RABCDAsm
+    dmd -run build_rabcdasm.d
+
+Substitute `dmd` with `gdmd` if you're using gdc. You can use the `DC` and 
+`DCFLAGS` environment variables to override the detected compiler and default 
+compilation flags (`-O -inline`).
+
+To be able to manipulate SWF files packed with LZMA compression, you'll need 
+to have the [liblzma library][] and development files installed on your system.
+
+Note: DMD 2.066 is required for long path support on Windows since RABCDAsm 
+1.16.
+
+  [d2]: http://dlang.org/
+  [dmd]: http://www.digitalmars.com/d/download.html
+  [gdc]: http://bitbucket.org/goshawk/gdc/
+  [git]: http://git-scm.com/
+  [liblzma library]: http://tukaani.org/xz/
+
+Pre-compiled binaries
+---------------------
+
+You can find pre-compiled Windows binaries on [my website][downloads]. 
+However, please don't expect them to be up-to-date with the latest source 
+versions.
+
+  [downloads]: http://files.thecybershadow.net/RABCDAsm/
+
+Usage
+-----
+
+To begin hacking on a SWF file:
+
+    abcexport file.swf
+
+This will create `file-0.abc` ... `file-N.abc` (often just `file-0.abc`). Each 
+file corresponds to an ABC block inside the SWF file.
+
+To disassemble one of the `.abc` files:
+
+    rabcdasm file-0.abc
+
+This will create a `file-0` directory, which will contain `file-0.main.asasm` 
+(the main program file) and files for ActionScript scripts, classes, and 
+orphan and script-level methods.
+
+To assemble the `.asasm` files back, and update the SWF file:
+
+    rabcasm file-0/file-0.main.asasm
+    abcreplace file.swf 0 file-0/file-0.main.abc
+
+The second `abcreplace` argument represents the index of the ABC block in the 
+SWF file, and corresponds to the number in the filename created by `abcexport`.
+
+`swfbinexport` and `swfbinreplace` are used in the same manner as `abcexport` 
+and `abcreplace`.
+
+Syntax
+======
+
+The syntax of the disassembly was designed to be very simple and allow fast 
+and easy parsing. It is a close representation of the `.abc` file format, and 
+thus it is somewhat verbose. All constant pool elements (signed/unsigned 
+integers, doubles, strings, namespaces, namespace sets, multinames) are always 
+*expanded inline*, for ease of editing. Similarly, classes, instances, methods 
+and method bodies are also defined inline, in the context of their "parent" 
+object. By-index references of classes and methods (used in the `newclass`, 
+`newfunction` and `callstatic` instructions) are represented via 
+automatically-generated unique "reference strings", declared as `refid` fields.
+
+If you haven't yet, I strongly recommend that you look through Adobe's 
+[ActionScript Virtual Machine 2 (AVM2) Overview][avm2]. You will most likely 
+need to consult it for the instruction reference anyway (although you can also 
+use [this handy list][avm2i] as well). You will find it difficult to 
+understand the disassembly without good understanding of concepts such as 
+namespaces and multinames.
+
+  [avm2]: http://www.adobe.com/devnet-archive/actionscript/articles/avm2overview.pdf
+  [avm2i]: http://www.anotherbigidea.com/javaswf/avm2/AVM2Instructions.html
+
+Overview
+--------
+
+In order to guarantee unambiguity and data preservation, all strings read from 
+the input file - including identifiers (variable/function/class names) - are 
+represented as string literals. Thus, the syntax does not have any "reserved 
+words" or such - an unrecognized word is treated as an error, not as an 
+identifier.
+
+Whitespace (outside string literals, of course) is completely ignored, except 
+where required to separate words. Comments are Intel-assembler-style: a single 
+`;` demarks a comment until the next end-of-line. Control directives (such as 
+`#include`) are allowed anywhere where whitespace is allowed.
+
+The syntax is comprised of hierarchical blocks. Each block contains a number 
+of fields - starting with a keyword specifying the field type. A block is 
+terminated with the `end` keyword. Some fields contain a limited number of 
+parameters, and others are, or contain blocks.
+
+Hierarchy
+---------
+
+The topmost block in the hierarchy is the `program` block. This must be the 
+first block in the file (thus, `program` must be the first word in the file as 
+well). The `program` block contains `script` fields, and `class` / `method` 
+fields for "orphan" classes and methods (not owned by other objects in the 
+hierarchy). Orphan methods are usually anonymous functions. The file version 
+is also specified in the `program` block, using the `minorversion` and 
+`majorversion` fields (both unsigned integers).
+
+`script` blocks have one mandatory `sinit` field (the script initialization 
+method) and `trait` fields.
+
+A "trait" can be one of several kinds. The kind is specified right after the 
+`trait` keyword, followed by the trait name (a multiname). Following the name 
+are the trait fields, varying by trait kind:
+
+ * `slot` / `const` : `slotid` (unsigned integer), `type` (multiname), `value`
+ * `class` : `slotid`, `class` (the actual class block)
+ * `function` : `slotid`, `method` (the actual method block)
+ * `method` / `getter` / `setter` : `dispid` (unsigned integer), `method`
+
+Additionally, all traits may have `flag` fields, describing the trait's 
+attributes (`FINAL` / `OVERRIDE` / `METADATA`), and `metadata` blocks.
+
+`metadata` blocks (which are ignored by the AVM) consist of a name string, and 
+a series of `item` fields - each item having a key and value string.
+
+`class` blocks have mandatory `instance` and `cinit` fields, defining the 
+class instance and the class initializer method respectively. They may also 
+have `trait` fields and a `refid` field (the `refid` field is not part of the 
+file format - it's an unique string to allow referencing the class, see above).
+
+`instance` blocks - always declared inline of their `class` block - must 
+contain one `iinit` field (the instance initializer method), and may contain 
+one `extends` field (multiname), `implements` fields (multinames), `flag` 
+fields (`SEALED` / `FINAL` / `INTERFACE` / `PROTECTEDNS`), one `protectedns` 
+field (namespace), and `trait` fields.
+
+`method` blocks may contain one `name` field (multiname), a `refid` field, 
+`param` fields (multinames - this represents the parameter types), one 
+`returns` field (multiname), `flag` fields (`NEED_ARGUMENTS` / 
+`NEED_ACTIVATION` / `NEED_REST` / `HAS_OPTIONAL` / `SET_DXNS` / 
+`HAS_PARAM_NAMES`), `optional` fields (values), `paramname` fields (strings), 
+and a `body` field (method body).
+
+`body` blocks - always declared inline of their `method` block - must contain 
+the `maxstack`, `localcount`, `initscopedepth` and `maxscopedepth` fields 
+(unsigned integers), and a `code` field. It may also contain `try` and `trait` 
+fields.
+
+`code` blocks - always declared inline of their `body` block - are somewhat 
+different in syntax from other blocks - mostly in that they may contain 
+labels. Labels follow the most common syntax - a word followed by a `:` 
+character, optionally followed by a relative byte offset (in case of pointers 
+inside instructions). Multiple instruction arguments are comma-separated. 
+Instruction arguments' types depend on the instruction - see the `OpcodeInfo` 
+array in `abcfile.d` for a reference.
+
+`try` blocks - always declared inline of their `body` block - represent an 
+"exception" (try/catch) block. They contain five mandatory fields: `from`, 
+`to` and `target` (names of labels representing start and end of the "try" 
+block, and start of the "catch" block respectively), and `type` and `name` 
+(multinames), representing the type and name of the exception variable.
+
+Values have the syntax *type* `(` *value* `)` . *type* can be one of 
+`Integer`, `UInteger`, `Double`, `Utf8`, `Namespace`, `PackageNamespace`, 
+`PackageInternalNs`, `ProtectedNamespace`, `ExplicitNamespace`, 
+`StaticProtectedNs`, `PrivateNamespace`, `True`, `False`, `Null` or 
+`Undefined`. The type of the value depends on *type*. Types `True`, `False`, 
+`Null` and `Undefined` have no value.
+
+Constants
+---------
+
+Multinames have the syntax *type* `(` *parameters* `)` . *type* can be one of 
+`QName` / `QNameA`, `RTQName` / `RTQNameA`, `RTQNameL` / `RTQNameLA`, 
+`Multiname` / `MultinameA`, `MultinameL` / `MultinameLA`, or `TypeName`. 
+*parameters* depends on *type*:
+
+ * `QName` / `QNameA` `(` *namespace* `,` *string* `)`
+ * `RTQName` / `RTQNameA` `(` *string* `)`
+ * `RTQNameL` / `RTQNameLA` `(` `)`
+ * `Multiname` / `MultinameA` `(` *string* `,` *namespace-set* `)`
+ * `MultinameL` / `MultinameLA` `(` *namespace-set* `)`
+ * `TypeName` `(` *multiname* `<` *multiname [* `,` *multiname ... ]* `>` `)`
+
+Namespace sets have the syntax `[` *[ namespace [* `,` *namespace ... ] ]* `]` 
+(that is, a comma-separated list of namespaces in square brackets). Empty 
+namespace sets can be specified using `[]`.
+
+Namespaces have the syntax *type* `(` *string [* `,` *string ]* `)` . The 
+first string indicates the namespace name. In the case that there are multiple 
+distinct namespaces with the same type and name (as `PrivateNamespace` 
+namespaces usually are), a second parameter may be present to uniquely 
+distinguish them. Internally (the ABC file format), namespaces are 
+distinguished by their numerical index. When disassembling, `rabcdasm` will 
+attempt to assign descriptive labels to homonym namespaces based on their 
+context.
+
+Strings have a syntax similar to C string literals. Strings start and end with 
+a `"`. Supported escape sequences (a backslash followed by a letter) are `\n` 
+(generates ASCII 0x0A), `\r` (ASCII 0x0D), and `\x` followed by two 
+hexadecimal digits, which inserts the ASCII character with that code. Any 
+other characters following a backslash generate that character - thus, you can 
+escape backslashes using `\\` and double quotes using `\"`. When decompiling, 
+high-ASCII characters (usually UTF-8) are not escaped - if you see gibberish 
+instead of international text, configure your editor to open the files in 
+UTF-8 encoding.
+
+Additionally, constant pool types (signed/unsigned integers, doubles, strings, 
+namespaces, namespace sets and multinames) may also have the value `null` 
+(which represents the index 0 in the ABC file). Note that `null` is 
+conceptually different from zero, an empty string or empty namespace set.
+
+Macros
+------
+
+RABCDAsm has some basic macro-like capabilities, controlled by directives and 
+variables. These bear some similarity to the C preprocessor, however these are 
+processed in-loop rather than as a separate pre-processing step.
+
+### Directives
+
+Directives start with a `#`, followed by a word identifying the directive:
+
+  * `#include` *string* - inserts the contents of the file by the specified 
+    filename inline. Functionally equivalent to `#mixin #get` *string* , but 
+    faster.
+  * `#mixin` *string* - inserts the contents of the specified string inline. 
+    Not very useful on its own.
+  * `#call` *string* `(` *[ string [* `,` *string ... ] ]* `)` - same as 
+    `#mixin`, however it additionally sets the special variables `$1`, `$2` 
+    etc. to the contents of the specified arguments. When the end of the 
+    inserted string is reached, the old values of `$1`, `$2` etc. are restored.
+  * `#get` *string* - inserts **a string containing** the contents of the file 
+    by the specified filename inline. Similar to #include, but it inserts a 
+    string (surrounded by `"` etc.) instead.
+  * `#set` *word* *string* - assigns the contents of the string to the 
+    variable *word*.
+  * `#unset` *word* - deletes the variable *word*.
+  * `#privatens` *number* *string* - deprecated, currently ignored.
+  * `#version` specifies the syntax version of the disassembly. Newer RABCDAsm 
+    versions may emit disassembly output that is not backwards-compatible, but 
+    should still understand older disassemblies. The versions are:
+     1. The first version.
+     2. Introduced in v1.11 to work around error in ABC format specification.
+     3. Introduced in v1.12 to support multiple non-private namespaces with 
+        the same name. This is the current version.
+
+### Variables
+
+Variables are manipulated with the `#set` and `#unset` directives, and can be 
+instantiated in two ways:
+
+  1. `$`*name* - this inserts the contents of the variable inline. Note that 
+     although variables are defined using a string syntax, they are not 
+     inserted as a string using this syntax. Thus, the code:
+
+        #set str "Hello, world!"
+        ...
+        pushstring $str
+
+     will expand to `pushstring Hello, world!`, which will result in an error.
+     To correct the problem, add escaped quotes around the variable contents
+     ( `#set str "\"Hello, world!\""` ), or use the second syntax:
+  
+  2. `$"`*name*`"` - this inserts a string containing the contents of the 
+     variable inline. This syntax also works for `#call` arguments (e.g. 
+     `$"1"`).
+
+### Example
+
+Here's an example of how to use the above features to create a macro which 
+logs a string literal and the contents of a register:
+
+    #set log "
+        findpropstrict      QName(PackageNamespace(\"\"), \"log\")
+        pushstring          $\"1\"
+        getlocal            $2
+        callpropvoid        QName(PackageNamespace(\"\"), \"log\"), 2
+    "
+    
+    ; ...
+    
+    pushbyte 2
+    pushbyte 2
+    add_i
+    setlocal1
+    #call $"log"("two plus two equals", "1")
+     
+Highlighting
+------------
+
+Included with the project is the file `asasm.hrc`, a simple syntax definition 
+for the [Colorer take5][] syntax highlighting library. It should be 
+straight-forward to adapt it to other syntax highlighting systems.
+
+  [Colorer take5]: http://colorer.sourceforge.net/
+
+Hacking
+=======
+
+ABC is internally represented in two forms. The `ABCFile` class stores the raw 
+data structures, as they appear in the binary file. `ASProgram` uses pointers 
+instead of indexes, allowing easy manipulation without having to worry about 
+record order or constant pools. Conversion between various states is done as 
+follows:
+
+                                 file.abc
+                                   |  ^
+                  ------ ABCReader |  | ABCWriter ----
+                 /                 v  |               \
+                /                ABCFile               \
+               /                   |  ^                 \
+        rabcdasm---------- ABCtoAS |  | AStoABC --------rabcasm
+               \                   v  |                 /
+                \               ASProgram              /
+                 \                 |  ^               /
+                  --- Disassembler |  | Assembler ----
+                                   v  |
+                                file.asasm
+
+`AStoABC` will rebuild the constant pools, in a manner similar to Adobe's 
+compilers (reverse-sorted by reference count). The exact order will almost 
+surely be different, however.
+
+Should you need to write an utility to manipulate ABC, you can use the 
+existing code to load the file to either an `ABCFile` or `ASProgram` instance, 
+and perform the necessary manipulations using those classes.
+
+Tips
+====
+
+The following tips come from the author's experience and may be useful for 
+RABCDAsm users.
+
+1. Once you have disassembled a SWF file you intend to modify, you should 
+   immediately add the directory to a distributed source control system, such 
+   as [Git][] or [Mercurial][]. This will allow you to easily track and undo 
+   your changes, and easily merge your changes with new versions of SWF files.
+
+  [Git]: http://git-scm.com/
+  [Mercurial]: http://mercurial.selenic.com/
+
+2. If you plan on making non-trivial changes to SWF files, you should install 
+   the [debug Flash Player][]. This will allow you to see validation and 
+   run-time error messages, instead of simply getting an empty window.
+
+  [debug Flash Player]: http://www.adobe.com/support/flashplayer/downloads.html
+
+3. The [Fiddler][] Web Debugging Proxy can be very useful for analyzing 
+   websites with SWF content. The following script fragment (which is to be 
+   placed in the `OnBeforeResponse` function) will automatically save all SWF 
+   files while preserving the directory structure.
+
+        if (oSession.oResponse.headers.ExistsAndContains("Content-Type",
+                "application/x-shockwave-flash")) {
+            // Set desired path here
+            var path:String = "C:\\Temp\\FiddlerCapture\\" +
+                oSession.host + oSession.PathAndQuery;
+            if (path.Contains('?'))
+                path = path.Substring(0, path.IndexOf('?'));
+            var dir:String = Path.GetDirectoryName(path);
+            if (!Directory.Exists(dir))
+                Directory.CreateDirectory(dir);
+            oSession.utilDecodeResponse();
+            oSession.SaveResponseBody(path);
+        }
+
+   A more robust version of the above snippet is available as a Fiddler plugin 
+   [here][FiddlerAutoCapture].
+
+   Once you have edited a SWF file, you can use Fiddler's [AutoResponder][] to 
+   replace the original file with your modified version.
+
+  [Fiddler]: http://www.fiddler2.com/fiddler2/
+  [AutoResponder]: http://www.fiddler2.com/fiddler2/help/AutoResponder.asp
+  [FiddlerAutoCapture]: https://github.com/CyberShadow/FiddlerAutoCapture
+
+Limitations
+===========
+
+* None known.
+
+License
+=======
+
+RABCDAsm is distributed under the terms of the GPL v3 or later, with the 
+exception of `murmurhash2a.d`, `zlibx.d` and LZMA components, which are in the 
+public domain, and `asasm.hrc`, which is tri-licensed under the MPL 1.1/GPL 
+2.0/LGPL 2.1. The full text of the GNU General Public License can be found in 
+the file `COPYING`.

abcexport.d

@@ -1,5 +1,5 @@
 /*
- *  Copyright (C) 2010 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  Copyright 2010, 2011 Vladimir Panteleev <vladimir@thecybershadow.net>
  *  This file is part of RABCDAsm.
  *
  *  RABCDAsm is free software: you can redistribute it and/or modify
@@ -20,7 +20,7 @@ module abcexport;
 
 import std.file;
 import std.path;
-import std.string;
+import std.conv;
 import std.stdio;
 import swffile;
 
@@ -45,11 +45,11 @@ void main(string[] args)
 						while (*p++) {} // skip name
 						abc = tag.data[p-tag.data.ptr..$];
 					}
-					write(getName(arg) ~ .toString(count++) ~ ".abc", abc);
+					std.file.write(stripExtension(arg) ~ "-" ~ to!string(count++) ~ ".abc", abc);
 				}
 			if (count == 0)
 				throw new Exception("No DoABC tags found");
 		}
-		catch (Object o)
-			writefln("Error while processing %s: %s", arg, o);
+		catch (Exception e)
+			writefln("Error while processing %s: %s", arg, e);
 }

abcfile.d

@@ -1,5 +1,5 @@
 /*
- *  Copyright (C) 2010 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  Copyright 2010, 2011, 2012, 2013, 2014 Vladimir Panteleev <vladimir@thecybershadow.net>
  *  This file is part of RABCDAsm.
  *
  *  RABCDAsm is free software: you can redistribute it and/or modify
@@ -19,9 +19,11 @@
 module abcfile;
 
 import std.string : format; // exception formatting
+import std.conv;
+import std.exception;
 
-/** 
- * Implements a shallow representation of an .abc file. 
+/**
+ * Implements a shallow representation of an .abc file.
  * Loading and saving an .abc file using this class should produce
  * output identical to the input.
  */
@@ -45,9 +47,13 @@ class ABCFile
 	Script[] scripts;
 	MethodBody[] bodies;
 
-	static const long NULL_INT = long.max;
-	static const ulong NULL_UINT = ulong.max;
-	static const double NULL_DOUBLE = double.init; // NaN
+	enum long NULL_INT = long.max;
+	enum ulong NULL_UINT = ulong.max;
+	enum double NULL_DOUBLE = double.init; // NaN
+
+	enum ulong MAX_UINT = (1L << 36) - 1;
+	enum long MAX_INT = MAX_UINT / 2;
+	enum long MIN_INT = -MAX_INT - 1;
 
 	this()
 	{
@@ -125,13 +131,8 @@ class ABCFile
 
 	struct Metadata
 	{
-		struct Item
-		{
-			uint key, value;
-		}
-
 		uint name;
-		Item[] items;
+		uint[] keys, values;
 	}
 
 	struct Instance
@@ -176,12 +177,12 @@ class ABCFile
 		}
 		uint[] metadata;
 
-		TraitKind kind() { return cast(TraitKind)(kindAttr&0xF); }
-		void kind(TraitKind value) { kindAttr = (kindAttr&0xF0) | value; }
+		@property TraitKind kind() { return cast(TraitKind)(kindAttr&0xF); }
+		@property void kind(TraitKind value) { kindAttr = (kindAttr&0xF0) | value; }
 
 		// TraitAttributes bitmask
-		ubyte attr() { return cast(ubyte)(kindAttr >> 4); }
-		void attr(ubyte value) { kindAttr = (kindAttr&0xF) | (value<<4); }
+		@property ubyte attr() { return cast(ubyte)(kindAttr >> 4); }
+		@property void attr(ubyte value) { kindAttr = cast(ubyte)((kindAttr&0xF) | (value<<4)); }
 	}
 
 	struct Class
@@ -206,6 +207,8 @@ class ABCFile
 		Instruction[] instructions;
 		ExceptionInfo[] exceptions;
 		TraitsInfo[] traits;
+
+		Error[] errors;
 	}
 
 	/// Destination for a jump or exception block boundary
@@ -215,13 +218,20 @@ class ABCFile
 		{
 			struct
 			{
-				uint index; /// instruction index
-				int offset; /// signed offset relative to said instruction
+				uint index = uint.max; /// instruction index
+				int offset = int.max; /// signed offset relative to said instruction
 			}
-			private int absoluteOffset; /// internal temporary value used during reading and writing
+			private ptrdiff_t absoluteOffset; /// internal temporary value used during reading and writing
 		}
 	}
 
+	/// Disassembly/decoding error
+	struct Error
+	{
+		Label loc;
+		string msg;
+	}
+
 	struct Instruction
 	{
 		Opcode opcode;
@@ -387,7 +397,7 @@ enum MethodFlags : ubyte
 	NEED_REST = 0x04, // This flag creates an ActionScript 3.0 rest arguments array. Must not be used with NEED_ARGUMENTS. See Chapter 3.
 	HAS_OPTIONAL = 0x08, // Must be set if this method has optional parameters and the options field is present in this method_info structure.
 	SET_DXNS = 0x40, // Must be set if this method uses the dxns or dxnslate opcodes.
-	HAS_PARAM_NAMES = 0x80, // Must be set when the param_names field is present in this method_info structure.	
+	HAS_PARAM_NAMES = 0x80, // Must be set when the param_names field is present in this method_info structure.
 }
 
 const string[8] MethodFlagNames = ["NEED_ARGUMENTS", "NEED_ACTIVATION", "NEED_REST", "HAS_OPTIONAL", "0x10", "0x20", "SET_DXNS", "HAS_PARAM_NAMES"];
@@ -435,6 +445,7 @@ const string[4] TraitAttributeNames = ["FINAL", "OVERRIDE", "METADATA", "0x08"];
 
 enum Opcode : ubyte
 {
+	OP_raw = 0x00, /// Used internally by RABCDAsm
 	OP_bkpt = 0x01,
 	OP_nop = 0x02,
 	OP_throw = 0x03,
@@ -655,7 +666,7 @@ struct OpcodeInfo
 }
 
 const OpcodeInfo[256] opcodeInfo = [
-	/* 0x00 */		{"0x00",				[OpcodeArgumentType.Unknown]},
+	/* 0x00 */		{"db",					[OpcodeArgumentType.UByteLiteral]},
 	/* 0x01 */		{"bkpt",				[OpcodeArgumentType.Unknown]},
 	/* 0x02 */		{"nop",					[]},
 	/* 0x03 */		{"throw",				[]},
@@ -708,16 +719,16 @@ const OpcodeInfo[256] opcodeInfo = [
 	/* 0x32 */		{"hasnext2",			[OpcodeArgumentType.UIntLiteral, OpcodeArgumentType.UIntLiteral]},
 	/* 0x33 */		{"pushdecimal",			[OpcodeArgumentType.Unknown]},
 	/* 0x34 */		{"pushdnan",			[OpcodeArgumentType.Unknown]},
-	/* 0x35 */		{"li8",					[OpcodeArgumentType.Unknown]},
-	/* 0x36 */		{"li16",				[OpcodeArgumentType.Unknown]},
-	/* 0x37 */		{"li32",				[OpcodeArgumentType.Unknown]},
-	/* 0x38 */		{"lf32",				[OpcodeArgumentType.Unknown]},
-	/* 0x39 */		{"lf64",				[OpcodeArgumentType.Unknown]},
-	/* 0x3A */		{"si8",					[OpcodeArgumentType.Unknown]},
-	/* 0x3B */		{"si16",				[OpcodeArgumentType.Unknown]},
-	/* 0x3C */		{"si32",				[OpcodeArgumentType.Unknown]},
-	/* 0x3D */		{"sf32",				[OpcodeArgumentType.Unknown]},
-	/* 0x3E */		{"sf64",				[OpcodeArgumentType.Unknown]},
+	/* 0x35 */		{"li8",					[]},
+	/* 0x36 */		{"li16",				[]},
+	/* 0x37 */		{"li32",				[]},
+	/* 0x38 */		{"lf32",				[]},
+	/* 0x39 */		{"lf64",				[]},
+	/* 0x3A */		{"si8",					[]},
+	/* 0x3B */		{"si16",				[]},
+	/* 0x3C */		{"si32",				[]},
+	/* 0x3D */		{"sf32",				[]},
+	/* 0x3E */		{"sf64",				[]},
 	/* 0x3F */		{"0x3F",				[OpcodeArgumentType.Unknown]},
 	/* 0x40 */		{"newfunction",			[OpcodeArgumentType.Method]},
 	/* 0x41 */		{"call",				[OpcodeArgumentType.UIntLiteral]},
@@ -735,9 +746,9 @@ const OpcodeInfo[256] opcodeInfo = [
 	/* 0x4D */		{"callinterface",		[OpcodeArgumentType.Unknown]},
 	/* 0x4E */		{"callsupervoid",		[OpcodeArgumentType.Multiname, OpcodeArgumentType.UIntLiteral]},
 	/* 0x4F */		{"callpropvoid",		[OpcodeArgumentType.Multiname, OpcodeArgumentType.UIntLiteral]},
-	/* 0x50 */		{"sxi1",				[OpcodeArgumentType.Unknown]},
-	/* 0x51 */		{"sxi8",				[OpcodeArgumentType.Unknown]},
-	/* 0x52 */		{"sxi16",				[OpcodeArgumentType.Unknown]},
+	/* 0x50 */		{"sxi1",				[]},
+	/* 0x51 */		{"sxi8",				[]},
+	/* 0x52 */		{"sxi16",				[]},
 	/* 0x53 */		{"applytype",			[OpcodeArgumentType.UIntLiteral]},
 	/* 0x54 */		{"0x54",				[OpcodeArgumentType.Unknown]},
 	/* 0x55 */		{"newobject",			[OpcodeArgumentType.UIntLiteral]},
@@ -750,7 +761,7 @@ const OpcodeInfo[256] opcodeInfo = [
 	/* 0x5C */		{"0x5C",				[OpcodeArgumentType.Unknown]},
 	/* 0x5D */		{"findpropstrict",		[OpcodeArgumentType.Multiname]},
 	/* 0x5E */		{"findproperty",		[OpcodeArgumentType.Multiname]},
-	/* 0x5F */		{"finddef",				[OpcodeArgumentType.Unknown]},
+	/* 0x5F */		{"finddef",				[OpcodeArgumentType.Multiname]},
 	/* 0x60 */		{"getlex",				[OpcodeArgumentType.Multiname]},
 	/* 0x61 */		{"setproperty",			[OpcodeArgumentType.Multiname]},
 	/* 0x62 */		{"getlocal",			[OpcodeArgumentType.UIntLiteral]},
@@ -758,11 +769,11 @@ const OpcodeInfo[256] opcodeInfo = [
 	/* 0x64 */		{"getglobalscope",		[]},
 	/* 0x65 */		{"getscopeobject",		[OpcodeArgumentType.UByteLiteral]},
 	/* 0x66 */		{"getproperty",			[OpcodeArgumentType.Multiname]},
-	/* 0x67 */		{"getpropertylate",		[OpcodeArgumentType.Unknown]},
+	/* 0x67 */		{"getpropertylate",		[]},
 	/* 0x68 */		{"initproperty",		[OpcodeArgumentType.Multiname]},
-	/* 0x69 */		{"setpropertylate",		[OpcodeArgumentType.Unknown]},
+	/* 0x69 */		{"setpropertylate",		[]},
 	/* 0x6A */		{"deleteproperty",		[OpcodeArgumentType.Multiname]},
-	/* 0x6B */		{"deletepropertylate",	[OpcodeArgumentType.Unknown]},
+	/* 0x6B */		{"deletepropertylate",	[]},
 	/* 0x6C */		{"getslot",				[OpcodeArgumentType.UIntLiteral]},
 	/* 0x6D */		{"setslot",				[OpcodeArgumentType.UIntLiteral]},
 	/* 0x6E */		{"getglobalslot",		[OpcodeArgumentType.UIntLiteral]},
@@ -784,10 +795,10 @@ const OpcodeInfo[256] opcodeInfo = [
 	/* 0x7E */		{"0x7E",				[OpcodeArgumentType.Unknown]},
 	/* 0x7F */		{"0x7F",				[OpcodeArgumentType.Unknown]},
 	/* 0x80 */		{"coerce",				[OpcodeArgumentType.Multiname]},
-	/* 0x81 */		{"coerce_b",			[OpcodeArgumentType.Unknown]},
+	/* 0x81 */		{"coerce_b",			[]},
 	/* 0x82 */		{"coerce_a",			[]},
-	/* 0x83 */		{"coerce_i",			[OpcodeArgumentType.Unknown]},
-	/* 0x84 */		{"coerce_d",			[OpcodeArgumentType.Unknown]},
+	/* 0x83 */		{"coerce_i",			[]},
+	/* 0x84 */		{"coerce_d",			[]},
 	/* 0x85 */		{"coerce_s",			[]},
 	/* 0x86 */		{"astype",				[OpcodeArgumentType.Multiname]},
 	/* 0x87 */		{"astypelate",			[]},
@@ -922,6 +933,16 @@ static this()
 	OpcodeByName = OpcodeByName.rehash;
 }
 
+bool[256] genLookup(Opcode[] opcodes)
+{
+	bool[256] result;
+	foreach (op; opcodes)
+		result[op] = true;
+	return result;
+}
+
+const bool[256] stopsExecution = genLookup([Opcode.OP_returnvalue, Opcode.OP_returnvoid, Opcode.OP_throw, Opcode.OP_jump, Opcode.OP_lookupswitch]);
+
 private final class ABCReader
 {
 	ubyte[] buf;
@@ -992,13 +1013,13 @@ private final class ABCReader
 			foreach (ref value; abc.bodies)
 				value = readMethodBody();
 		}
-		catch (Object o)
-			throw new Exception(format("Error at %d (0x%X): %s", pos, pos, o));
+		catch (Exception e)
+			throw new Exception(format("Error at %d (0x%X):", pos, pos), e);
 	}
 
 	ubyte readU8()
 	{
-		assert(pos < buf.length);
+		enforce(pos < buf.length, "End of file reached");
 		return buf[pos++];
 	}
 
@@ -1014,27 +1035,39 @@ private final class ABCReader
 
 	/// Note: may return values larger than 0xFFFFFFFF.
 	ulong readU32()
+	out(result)
 	{
-		ulong result = readU8();
+		assert(result <= ABCFile.MAX_UINT);
+	}
+	body
+	{
+		ulong next() { return readU8(); } // force ulong
+
+		ulong result = next();
 		if (0==(result & 0x00000080))
 			return result;
-		result = result & 0x0000007f | readU8()<<7;
+		result = result & 0x0000007f | next()<<7;
 		if (0==(result & 0x00004000))
 			return result;
-		result = result & 0x00003fff | readU8()<<14;
+		result = result & 0x00003fff | next()<<14;
 		if (0==(result & 0x00200000))
 			return result;
-		result = result & 0x001fffff | readU8()<<21;
+		result = result & 0x001fffff | next()<<21;
 		if (0==(result & 0x10000000))
 			return result;
-		return   result & 0x0fffffff | readU8()<<28;
+		return   result & 0x0fffffff | next()<<28;
 	}
 
 	long readS32()
+	out(result)
 	{
-		ulong l = readU32();
-		if (l & 0xFFFFFFFF00000000) // preserve unused bits
-			return cast(long)l;
+		assert(result >= ABCFile.MIN_INT && result <= ABCFile.MAX_INT);
+	}
+	body
+	{
+		auto l = readU32();
+		if (l & 0xFFFFFFFF_00000000) // preserve unused bits
+			return l | 0xFFFFFFF0_00000000;
 		else
 			return cast(int)l;
 	}
@@ -1046,7 +1079,7 @@ private final class ABCReader
 
 	void readExact(void* ptr, size_t len)
 	{
-		assert(pos+len <= buf.length);
+		enforce(pos+len <= buf.length, "End of file reached");
 		(cast(ubyte*)ptr)[0..len] = buf[pos..pos+len];
 		pos += len;
 	}
@@ -1061,8 +1094,9 @@ private final class ABCReader
 
 	string readString()
 	{
-		string s = new char[readU30()];
-		readExact(s.ptr, s.length);
+		char[] buf = new char[readU30()];
+		readExact(buf.ptr, buf.length);
+		string s = assumeUnique(buf);
 		if (s.length == 0)
 			s = ""; // not null!
 		return s;
@@ -1173,12 +1207,11 @@ private final class ABCReader
 	{
 		ABCFile.Metadata r;
 		r.name = readU30();
-		r.items.length = readU30();
-		foreach (ref value; r.items)
-		{
-			value.key = readU30();
-			value.value = readU30();
-		}
+		r.keys.length = r.values.length = readU30();
+		foreach (ref key; r.keys)
+			key = readU30();
+		foreach (ref value; r.values)
+			value = readU30();
 		return r;
 	}
 
@@ -1275,17 +1308,204 @@ private final class ABCReader
 		r.instructions = null;
 
 		size_t len = readU30();
-		uint[] instructionAtOffset = new uint[len];
+		size_t start = pos;
+		size_t end = pos + len;
+
+		pos = end;
+		r.exceptions.length = readU30();
+		foreach (ref value; r.exceptions)
+			value = readExceptionInfo();
+
+		size_t postExceptions = pos;
+
+		enum TraceState : ubyte
+		{
+			unexplored,
+			pending,
+			instruction,
+			instructionBody,
+			error,
+		}
+
+		auto traceState = new TraceState[len];
+		auto instructions = new ABCFile.Instruction[len];
+
+		@property size_t offset() { return pos - start; }
+
+		bool havePending;
+
+		void queue(size_t traceOffset)
+		{
+			if (traceOffset < len && traceState[traceOffset] == TraceState.unexplored)
+			{
+				traceState[traceOffset] = TraceState.pending;
+				havePending = true;
+			}
+		}
+
+		queue(0);
+
+		foreach (ref value; r.exceptions)
+			queue(value.target.absoluteOffset);
+
+		while (havePending)
+		{
+			havePending = false;
+			pos = start;
+			while (pos < end)
+			{
+				if (traceState[offset] == TraceState.pending)
+				{
+					size_t instructionOffset;
+
+					try
+					{
+						while (pos < end)
+						{
+							instructionOffset = offset;
+
+							enforce(traceState[instructionOffset] != TraceState.instructionBody, "Overlapping instruction");
+							if (traceState[instructionOffset] == TraceState.instruction)
+								break; // already decoded
+
+							ABCFile.Instruction instruction;
+							instruction.opcode = cast(Opcode)readU8();
+							enforce(instruction.opcode != Opcode.OP_raw, "Null opcode");
+							instruction.arguments.length = opcodeInfo[instruction.opcode].argumentTypes.length;
+							foreach (i, type; opcodeInfo[instruction.opcode].argumentTypes)
+								final switch (type)
+								{
+									case OpcodeArgumentType.Unknown:
+										throw new Exception("Don't know how to decode OP_" ~ opcodeInfo[instruction.opcode].name);
+
+									case OpcodeArgumentType.UByteLiteral:
+										instruction.arguments[i].ubytev = readU8();
+										break;
+									case OpcodeArgumentType.IntLiteral:
+										instruction.arguments[i].intv = readS32();
+										break;
+									case OpcodeArgumentType.UIntLiteral:
+										instruction.arguments[i].uintv = readU32();
+										break;
+
+									case OpcodeArgumentType.Int:
+									case OpcodeArgumentType.UInt:
+									case OpcodeArgumentType.Double:
+									case OpcodeArgumentType.String:
+									case OpcodeArgumentType.Namespace:
+									case OpcodeArgumentType.Multiname:
+									case OpcodeArgumentType.Class:
+									case OpcodeArgumentType.Method:
+									{
+										auto index = readU30();
+										size_t length;
+										switch (type)
+										{
+											case OpcodeArgumentType.Int:       length = abc.ints      .length; break;
+											case OpcodeArgumentType.UInt:      length = abc.uints     .length; break;
+											case OpcodeArgumentType.Double:    length = abc.doubles   .length; break;
+											case OpcodeArgumentType.String:    length = abc.strings   .length; break;
+											case OpcodeArgumentType.Namespace: length = abc.namespaces.length; break;
+											case OpcodeArgumentType.Multiname: length = abc.multinames.length; break;
+											case OpcodeArgumentType.Class:     length = abc.classes   .length; break;
+											case OpcodeArgumentType.Method:    length = abc.methods   .length; break;
+											default: assert(false);
+										}
+										enforce(index < length, "Out-of-bounds constant index");
+										instruction.arguments[i].index = index;
+										break;
+									}
+
+									case OpcodeArgumentType.JumpTarget:
+									{
+										auto delta = readS24();
+										auto target = offset + delta;
+										instruction.arguments[i].jumpTarget.absoluteOffset = target;
+										queue(target);
+										break;
+									}
+
+									case OpcodeArgumentType.SwitchDefaultTarget:
+									{
+										auto target = instructionOffset + readS24();
+										instruction.arguments[i].jumpTarget.absoluteOffset = target;
+										queue(target);
+										break;
+									}
+
+									case OpcodeArgumentType.SwitchTargets:
+										instruction.arguments[i].switchTargets.length = readU30()+1;
+										foreach (ref label; instruction.arguments[i].switchTargets)
+										{
+											label.absoluteOffset = instructionOffset + readS24();
+											queue(label.absoluteOffset);
+										}
+										break;
+								}
+
+							enforce(offset <= len, "Out-of-bounds code read error");
+
+							instructions[instructionOffset] = instruction;
+							traceState[instructionOffset] = TraceState.instruction;
+							traceState[instructionOffset+1..offset] = TraceState.instructionBody;
+
+							if (stopsExecution[instruction.opcode])
+								break;
+						}
+					}
+					catch (Exception e)
+					{
+						traceState[instructionOffset] = TraceState.error;
+						ABCFile.Label loc;
+						loc.absoluteOffset = instructionOffset;
+						r.errors ~= ABCFile.Error(loc, e.msg);
+
+						pos = start + instructionOffset + 1;
+					}
+				}
+				else
+					pos++;
+			}
+		}
+
+		size_t[] instructionOffsets;
+		auto instructionAtOffset = new uint[len];
+		instructionAtOffset[] = uint.max;
+
+		void addInstruction(ref ABCFile.Instruction i, size_t offset)
+		{
+			instructionAtOffset[offset] = to!uint(r.instructions.length);
+			r.instructions ~= i;
+			instructionOffsets ~= offset;
+		}
+
+		foreach (o, state; traceState)
+		{
+			assert(state != TraceState.pending);
+			if (state == TraceState.instruction)
+				addInstruction(instructions[o], o);
+			else
+			if (state == TraceState.unexplored || state == TraceState.error)
+			{
+				ABCFile.Instruction instruction;
+				instruction.opcode = Opcode.OP_raw;
+				instruction.arguments.length = 1;
+				instruction.arguments[0].ubytev = buf[start + o];
+				addInstruction(instruction, o);
+			}
+			else
+				assert(state == TraceState.instructionBody);
+		}
 
 		void translateLabel(ref ABCFile.Label label)
 		{
-			int absoluteOffset = label.absoluteOffset;
-			int instructionOffset = absoluteOffset;
+			auto absoluteOffset = label.absoluteOffset;
+			auto instructionOffset = absoluteOffset;
 			while (true)
 			{
-				if (instructionOffset >= cast(int)len)
+				if (instructionOffset >= len)
 				{
-					label.index = r.instructions.length;
+					label.index = to!uint(r.instructions.length);
 					instructionOffset = len;
 					break;
 				}
@@ -1302,103 +1522,40 @@ private final class ABCReader
 				}
 				instructionOffset--;
 			}
-			label.offset = absoluteOffset-instructionOffset;
+			label.offset = to!int(absoluteOffset-instructionOffset);
 		}
 
-		{
-			size_t start = pos;
-			size_t end = pos + len;
+		// convert jump target offsets to instruction indices
+		foreach (ii, ref instruction; r.instructions)
+			foreach (i, type; opcodeInfo[instruction.opcode].argumentTypes)
+				switch (type)
+				{
+					case OpcodeArgumentType.JumpTarget:
+					case OpcodeArgumentType.SwitchDefaultTarget:
+						translateLabel(instruction.arguments[i].jumpTarget);
+						break;
+					case OpcodeArgumentType.SwitchTargets:
+						foreach (ref x; instruction.arguments[i].switchTargets)
+							translateLabel(x);
+						break;
+					default:
+						break;
+				}
 
-			uint offset() { return pos - start; }
+		// convert error offsets to instruction indices
+		foreach (ref e; r.errors)
+			translateLabel(e.loc);
 
-			instructionAtOffset[] = uint.max;
-			uint[] instructionOffsets;
-			while (pos < end)
-			{
-				uint instructionOffset = offset;
-				instructionAtOffset[instructionOffset] = r.instructions.length;
-				ABCFile.Instruction instruction;
-				instruction.opcode = cast(Opcode)readU8();
-				instruction.arguments.length = opcodeInfo[instruction.opcode].argumentTypes.length;
-				foreach (i, type; opcodeInfo[instruction.opcode].argumentTypes)
-					switch (type)
-					{
-						case OpcodeArgumentType.Unknown:
-							throw new Exception("Don't know how to decode OP_" ~ opcodeInfo[instruction.opcode].name);
-
-						case OpcodeArgumentType.UByteLiteral:
-							instruction.arguments[i].ubytev = readU8();
-							break;
-						case OpcodeArgumentType.IntLiteral:
-							instruction.arguments[i].intv = readS32();
-							break;
-						case OpcodeArgumentType.UIntLiteral:
-							instruction.arguments[i].uintv = readU32();
-							break;
-
-						case OpcodeArgumentType.Int:
-						case OpcodeArgumentType.UInt:
-						case OpcodeArgumentType.Double:
-						case OpcodeArgumentType.String:
-						case OpcodeArgumentType.Namespace:
-						case OpcodeArgumentType.Multiname:
-						case OpcodeArgumentType.Class:
-						case OpcodeArgumentType.Method:
-							instruction.arguments[i].index = readU30();
-							break;
-
-						case OpcodeArgumentType.JumpTarget:
-							int delta = readS24();
-							instruction.arguments[i].jumpTarget.absoluteOffset = offset + delta;
-							break;
-
-						case OpcodeArgumentType.SwitchDefaultTarget:
-							instruction.arguments[i].jumpTarget.absoluteOffset = instructionOffset + readS24();
-							break;
-
-						case OpcodeArgumentType.SwitchTargets:
-							instruction.arguments[i].switchTargets.length = readU30()+1;
-							foreach (ref label; instruction.arguments[i].switchTargets)
-								label.absoluteOffset = instructionOffset + readS24();
-							break;
-
-						default:
-							assert(0);
-					}
-				r.instructions ~= instruction;
-				instructionOffsets ~= instructionOffset;
-			}
-
-			if (pos > end)
-				throw new Exception("Out-of-bounds code read error");
-
-			// convert jump target offsets to instruction indices
-			foreach (ii, ref instruction; r.instructions)
-				foreach (i, type; opcodeInfo[instruction.opcode].argumentTypes)
-					switch (type)
-					{
-						case OpcodeArgumentType.JumpTarget:
-						case OpcodeArgumentType.SwitchDefaultTarget:
-							translateLabel(instruction.arguments[i].jumpTarget);
-							break;
-						case OpcodeArgumentType.SwitchTargets:
-							foreach (ref x; instruction.arguments[i].switchTargets)
-								translateLabel(x);
-							break;
-						default:
-							break;
-					}
-			pos = end;
-		}
-
-		r.exceptions.length = readU30();
+		// convert exception offsets to instruction indices
 		foreach (ref value; r.exceptions)
 		{
-			value = readExceptionInfo();
 			translateLabel(value.from);
 			translateLabel(value.to);
 			translateLabel(value.target);
 		}
+
+		pos = postExceptions;
+
 		r.traits.length = readU30();
 		foreach (ref value; r.traits)
 			value = readTrait();
@@ -1471,7 +1628,7 @@ private final class ABCWriter
 		foreach (ref value; abc.instances)
 			writeInstance(value);
 
-		assert(abc.classes.length == abc.instances.length);
+		assert(abc.classes.length == abc.instances.length, "Number of classes and instances differs");
 		foreach (ref value; abc.classes)
 			writeClass(value);
 
@@ -1506,7 +1663,6 @@ private final class ABCWriter
 		writeU8(cast(ubyte)(v>>16));
 	}
 
-	/// Note: may return values larger than 0xFFFFFFFF.
 	void writeU32(ulong v)
 	{
 		if ( v < 128)
@@ -1546,12 +1702,13 @@ private final class ABCWriter
 		writeU32(cast(ulong)v);
 	}
 
-	void writeU30(uint v)
+	void writeU30(ulong v)
 	{
+		enforce(v < (1<<30));
 		writeU32(v);
 	}
 
-	void writeExact(void* ptr, size_t len)
+	void writeExact(const(void)* ptr, size_t len)
 	{
 		while (pos+len > buf.length)
 			buf.length = buf.length * 2;
@@ -1643,7 +1800,7 @@ private final class ABCWriter
 		}
 		if (v.flags & MethodFlags.HAS_PARAM_NAMES)
 		{
-			assert(v.paramNames.length == v.paramTypes.length);
+			assert(v.paramNames.length == v.paramTypes.length, "Mismatching number of parameter names and types");
 			foreach (value; v.paramNames)
 				writeU30(value);
 		}
@@ -1658,12 +1815,12 @@ private final class ABCWriter
 	void writeMetadata(ref ABCFile.Metadata v)
 	{
 		writeU30(v.name);
-		writeU30(v.items.length);
-		foreach (ref value; v.items)
-		{
-			writeU30(value.key);
-			writeU30(value.value);
-		}
+		assert(v.keys.length == v.values.length);
+		writeU30(v.keys.length);
+		foreach (key; v.keys)
+			writeU30(key);
+		foreach (value; v.values)
+			writeU30(value);
 	}
 
 	void writeInstance(ref ABCFile.Instance v)
@@ -1716,7 +1873,7 @@ private final class ABCWriter
 		if (v.attr & TraitAttributes.Metadata)
 		{
 			writeU30(v.metadata.length);
-			foreach (ref value; v.metadata)
+			foreach (value; v.metadata)
 				writeU30(value);
 		}
 	}
@@ -1745,23 +1902,24 @@ private final class ABCWriter
 		writeU30(v.initScopeDepth);
 		writeU30(v.maxScopeDepth);
 
-		uint[] instructionOffsets = new uint[v.instructions.length+1];
+		auto instructionOffsets = new size_t[v.instructions.length+1];
 
-		uint resolveLabel(ref ABCFile.Label label) { return instructionOffsets[label.index]+label.offset; }
+		ptrdiff_t resolveLabel(ref ABCFile.Label label) { return instructionOffsets[label.index]+label.offset; }
 
 		{
 			// we don't know the length before writing all the instructions - swap buffer with a temporary one
 			auto globalBuf = buf;
 			auto globalPos = pos;
-			buf = new ubyte[1024];
+			static ubyte[1024*16] methodBuf;
+			buf = methodBuf[];
 			pos = 0;
 
-			struct Fixup { ABCFile.Label target; uint pos, base; }
+			struct Fixup { ABCFile.Label target; size_t pos, base; }
 			Fixup[] fixups;
 
 			foreach (ii, ref instruction; v.instructions)
 			{
-				uint instructionOffset = pos;
+				auto instructionOffset = pos;
 				instructionOffsets[ii] = instructionOffset;
 
 				writeU8(instruction.opcode);
@@ -1770,7 +1928,7 @@ private final class ABCWriter
 					throw new Exception("Mismatching number of arguments");
 
 				foreach (i, type; opcodeInfo[instruction.opcode].argumentTypes)
-					switch (type)
+					final switch (type)
 					{
 						case OpcodeArgumentType.Unknown:
 							throw new Exception("Don't know how to encode OP_" ~ opcodeInfo[instruction.opcode].name);
@@ -1816,9 +1974,6 @@ private final class ABCWriter
 								writeS24(0);
 							}
 							break;
-
-						default:
-							assert(0);
 					}
 			}
 
@@ -1828,7 +1983,7 @@ private final class ABCWriter
 			foreach (ref fixup; fixups)
 			{
 				pos = fixup.pos;
-				writeS24(resolveLabel(fixup.target)-fixup.base);
+				writeS24(to!int(cast(ptrdiff_t)(resolveLabel(fixup.target)-fixup.base)));
 			}
 
 			auto code = buf;

abcreplace.d

@@ -1,5 +1,5 @@
 /*
- *  Copyright (C) 2010 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  Copyright 2010, 2011, 2012 Vladimir Panteleev <vladimir@thecybershadow.net>
  *  This file is part of RABCDAsm.
  *
  *  RABCDAsm is free software: you can redistribute it and/or modify
@@ -27,7 +27,7 @@ void main(string[] args)
 	if (args.length != 4)
 		throw new Exception("Bad arguments. Usage: abcreplace file.swf index code.abc");
 	auto swf = SWFFile.read(cast(ubyte[])read(args[1]));
-	auto index = toUint(args[2]);
+	auto index = to!uint(args[2]);
 	uint count;
 	foreach (ref tag; swf.tags)
 		if ((tag.type == TagType.DoABC || tag.type == TagType.DoABC2) && count++ == index)
@@ -41,6 +41,7 @@ void main(string[] args)
 				while (*p++) {} // skip name
 				tag.data = tag.data[0..p-tag.data.ptr] ~ abc;
 			}
+			tag.length = cast(uint)tag.data.length;
 			write(args[1], swf.write());
 			return;
 		}

asasm.hrc

@@ -4,7 +4,7 @@
 <hrc version="take5" xmlns="http://colorer.sf.net/2003/hrc"
      xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
      xsi:schemaLocation="http://colorer.sf.net/2003/hrc http://colorer.sf.net/2003/hrc.xsd">
-  
+
   <type name="asasm">
     <annotation><documentation>
       ActionScript Assembler Syntax (RABCDAsm variant)
@@ -31,20 +31,24 @@
 
       <!-- Decimal numbers -->
       <regexp match="/\b[0-9]+\b/" region0="def:NumberDec"/>
-      
+
       <!-- Paired brackets -->
       <block start="/(\()/" end="/(\))/" scheme="asasm" region00="def:Symbol" region01="def:PairStart" region10="def:Symbol" region11="def:PairEnd"/>
       <block start="/(\[)/" end="/(\])/" scheme="asasm" region00="def:Symbol" region01="def:PairStart" region10="def:Symbol" region11="def:PairEnd"/>
       <block start="/(\<)/" end="/(\>)/" scheme="asasm" region00="def:Symbol" region01="def:PairStart" region10="def:Symbol" region11="def:PairEnd"/>
 
       <!-- Outliner for refids -->
-      <regexp match="/(\brefid\b)\s*((?{def:StringEdge}&#34;))((?{def:String}[^&#34;]*))((?{def:StringEdge}&#34;))/" region1="def:Keyword" region2="def:PairStart" region3="def:Outlined" region4="def:PairEnd"/> <!-- BUG: does not support escape sequences -->
+      <!--regexp match="/(\brefid\b)\s*((?{def:StringEdge}&#34;))((?{def:String}[^&#34;]*))((?{def:StringEdge}&#34;))/" region1="def:Keyword" region2="def:PairStart" region3="def:Outlined" region4="def:PairEnd"/--> <!-- BUG: does not support escape sequences -->
+      <regexp
+        match="/(\brefid\b)\M\s*&#34;(.*)&#34;$/"
+        region1="def:Keyword"
+        region2="def:Outlined"/>
       <!--block start="/(\brefid\b)\s*(?{def:StringEdge}&#34;)/" end="/(?{def:StringEdge}&#34;)/" scheme="StringContent" region="def:Outlined" inner-region="yes" region00="def:PairStart" region10="def:PairEnd"/-->
 
       <!-- Symbol/keyword highlighting below -->
 
       <keywords region="def:Symbol">
-         <symb name=","/>
+        <symb name=","/>
       </keywords>
 
       <keywords ignorecase="no" region="def:Directive">
@@ -55,6 +59,7 @@
         <word name="#privatens"/>
         <word name="#set"/>
         <word name="#unset"/>
+        <word name="#version"/>
       </keywords>
 
       <keywords ignorecase="no" region="def:Keyword">
@@ -74,10 +79,12 @@
         <word name="implements"/>
         <word name="initscopedepth"/>
         <word name="instance"/>
+        <word name="item"/>
         <word name="localcount"/>
         <word name="majorversion"/>
         <word name="maxscopedepth"/>
         <word name="maxstack"/>
+        <word name="metadata"/>
         <word name="method"/>
         <word name="minorversion"/>
         <word name="name"/>

autodata.d

@@ -1,5 +1,5 @@
 /*
- *  Copyright (C) 2010 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  Copyright 2010, 2011, 2012, 2014 Vladimir Panteleev <vladimir@thecybershadow.net>
  *  This file is part of RABCDAsm.
  *
  *  RABCDAsm is free software: you can redistribute it and/or modify
@@ -19,61 +19,68 @@
 module autodata;
 
 import murmurhash2a;
-import std2.traits;
+import std.traits;
+public import std.conv;
 
 string addAutoField(string name, bool reverseSort = false)
 {
-	//return `mixin(handler.process!(typeof(` ~ name ~ `), "` ~ name ~ `")());`; // doesn't work due to DMD bug 3959
-	return `{ static const _AutoDataStr = handler.process!(typeof(this.` ~ name ~ `), "` ~ name ~ `", ` ~ (reverseSort ? "true" : "false") ~`)(); mixin(_AutoDataStr); }`;
+	return `mixin(typeof(handler).getMixin!(typeof(` ~ name ~ `), "` ~ name ~ `", ` ~ (reverseSort ? "true" : "false") ~`));`;
 }
 
 template AutoCompare()
 {
-	hash_t toHash()
+	static if (is(typeof(this)==class))
+	{
+		alias typeof(this) _AutoDataTypeReference;
+		alias Object _AutoDataOtherTypeReference;
+
+		override hash_t toHash() const { try { return _AutoDataHash(); } catch(object.Exception e) { assert(0, e.msg); } }
+		override bool opEquals(Object o) const { return _AutoDataEquals(o); }
+		override int opCmp(Object o) const { return _AutoDataCmp(o); }
+	}
+	else // struct
+	{
+		alias const(typeof(this)*) _AutoDataTypeReference;
+		alias const(typeof(this)*) _AutoDataOtherTypeReference;
+
+		hash_t toHash() const { return _AutoDataHash(); }
+		bool opEquals(ref const typeof(this) s) const { return _AutoDataEquals(&s); }
+		int opCmp(ref const typeof(this) s) const { return _AutoDataCmp(&s); }
+	}
+
+	@trusted private hash_t _AutoDataHash() const
 	{
 		HashDataHandler handler;
 		handler.hasher.Begin();
-		processData!(void, "", "")(handler);
+		processData!(void, q{}, q{})(handler);
 		return handler.hasher.End();
 	}
 
-	static if (is(typeof(this)==class))
-		alias Object _AutoDataOtherType;
-	else
-		alias typeof(this) _AutoDataOtherType;
-
-	int opEquals(_AutoDataOtherType other)
+	private bool _AutoDataEquals(_AutoDataOtherTypeReference other) const
 	{
-		EqualsDataHandler!(typeof(this)) handler;
-		static if (is(typeof(this)==class))
-		{
-			handler.other = cast(typeof(this)) other;
-			if (handler.other is null)
-				return false;
-		}
-		else
-			handler.other = other;
-		return processData!(bool, "auto _AutoDataOther = handler.other;", "return true;")(handler);
+		auto handler = EqualsDataHandler!_AutoDataTypeReference(cast(_AutoDataTypeReference) other);
+		if (handler.other is null)
+			return false;
+		return processData!(bool, q{auto _AutoDataOther = handler.other;}, q{return true;})(handler);
 	}
 
-	int opCmp(_AutoDataOtherType other)
+	private int _AutoDataCmp(_AutoDataOtherTypeReference other) const
 	{
-		CmpDataHandler!(typeof(this)) handler;
-		static if (is(typeof(this)==class))
-		{
-			handler.other = cast(typeof(this)) other;
-			if (handler.other is null)
-				return -1;
-		}
-		else
-			handler.other = other;
-		return processData!(int, "auto _AutoDataOther = handler.other;", "return 0;")(handler);
+		auto handler = CmpDataHandler!_AutoDataTypeReference(cast(_AutoDataTypeReference) other);
+		if (handler.other is null)
+			return false;
+		return processData!(int, q{auto _AutoDataOther = handler.other;}, "return 0;")(handler);
 	}
 }
 
 template AutoToString()
 {
-	string toString()
+	static if (is(typeof(this)==class))
+		override string toString() const { return _AutoDataToString(); }
+	else // struct
+		string toString() const { return _AutoDataToString(); }
+
+	string _AutoDataToString() const
 	{
 		ToStringDataHandler handler;
 		return processData!(string, "string _AutoDataResult;", "return _AutoDataResult;")(handler);
@@ -82,20 +89,11 @@ template AutoToString()
 
 template ProcessAllData()
 {
-	R processData(R, string prolog, string epilog, H)(ref H handler)
+	R processData(R, string prolog, string epilog, H)(ref H handler) const
 	{
 		mixin(prolog);
 		foreach (i, T; this.tupleof)
-		{
-			//mixin(addAutoField(T.stringof)); // doesn't work
-			static if (this.tupleof[i].stringof == typeof(this.tupleof[i]).stringof)
-				static assert(0, "DMD bug 2881 detected - can't use enums with ProcessAllData");
-			else
-			static if (is (typeof(this) == class))
-				mixin(addAutoField(this.tupleof[i].stringof[5..$])); // remove "this."
-			else
-				mixin(addAutoField(this.tupleof[i].stringof[8..$])); // remove "(*this)."
-		}
+			mixin(addAutoField(this.tupleof[i].stringof[5..$])); // remove "this."
 		mixin(epilog);
 	}
 }
@@ -103,29 +101,30 @@ template ProcessAllData()
 /// For data handlers that only need to look at the raw data (currently only HashDataHandler)
 template RawDataHandlerWrapper()
 {
-	static string process(T, string name, bool reverseSort)()
+	template getMixin(T, string name, bool reverseSort)
 	{
-		return processRecursive!(T, "this." ~ name, "");
+		enum getMixin = getMixinRecursive!(T, "this." ~ name, "");
 	}
 
-	static string processRecursive(T, string name, string loopDepth)()
+	template getMixinRecursive(T, string name, string loopDepth)
 	{
-		static if (!hasAliasing!(T))
-			return processRaw("&" ~ name, name ~ ".sizeof");
-		else
 		static if (is(T U : U[]))
-		{
-			string s = "{ bool _AutoDataNullTest = " ~ name ~ " is null; " ~ processRaw("&_AutoDataNullTest", "bool.sizeof") ~ "}";
-			static if (!hasAliasing!(U))
-				s ~= processRaw(name ~ ".ptr", name ~ ".length");
-			else
-				s ~= "foreach (ref _AutoDataArrayItem" ~ loopDepth ~ "; " ~ name ~ ") {" ~ processRecursive!(U, "_AutoDataArrayItem" ~ loopDepth, loopDepth~"Item")() ~ "}";
-			return s;
-		}
+			enum getMixinRecursive =
+				"{ bool _AutoDataNullTest = " ~ name ~ " is null; " ~ getRawMixin!("&_AutoDataNullTest", "bool.sizeof") ~ "}" ~
+				(!hasAliasing!(U) ?
+					getRawMixin!(name ~ ".ptr", name ~ ".length")
+				:
+					"foreach (ref _AutoDataArrayItem" ~ loopDepth ~ "; " ~ name ~ ") {" ~ getMixinRecursive!(U, "_AutoDataArrayItem" ~ loopDepth, loopDepth~"Item") ~ "}"
+				);
 		else
-		static if (is(typeof((new T).toHash())))
-			//static assert(0, "aoeu: " ~ T.stringof);
-			return name ~ ".processData!(void, ``, ``)(handler);";
+		static if (!hasAliasing!(T))
+			enum getMixinRecursive = getRawMixin!("&" ~ name, name ~ ".sizeof");
+		else
+		static if (is(T==struct))
+			enum getMixinRecursive = name ~ ".processData!(void, ``, ``)(handler);";
+		else
+		static if (is(T==class))
+			enum getMixinRecursive = "if ("~name~" !is null) " ~ name ~ ".processData!(void, ``, ``)(handler);";
 		else
 			static assert(0, "Don't know how to process type: " ~ T.stringof);
 	}
@@ -137,9 +136,9 @@ struct HashDataHandler
 
 	MurmurHash2A hasher;
 
-	static string processRaw(string ptr, string len)
+	template getRawMixin(string ptr, string len)
 	{
-		return "handler.hasher.Add(" ~ ptr ~ ", " ~ len ~ ");";
+		enum getRawMixin = "handler.hasher.Add(" ~ ptr ~ ", to!int(" ~ len ~ "));";
 	}
 }
 
@@ -147,13 +146,17 @@ struct EqualsDataHandler(O)
 {
 	O other;
 
-	static string process(T, string name, bool reverseSort)()
+	template nullCheck(T, string name)
 	{
-		string s;
-		static if (is(T U : U[]))
-			s ~= " if ((this." ~ name ~ " is null) != (_AutoDataOther." ~ name ~ " is null)) return false;";
-		s ~= "if (this." ~ name ~ " != _AutoDataOther." ~ name ~ ") return false;";
-		return s;
+		static if (is(typeof(T.init is null)))
+			enum nullCheck = "if ((this." ~ name ~ " is null) != (_AutoDataOther." ~ name ~ " is null)) return false;";
+		else
+			enum nullCheck = "";
+	}
+
+	template getMixin(T, string name, bool reverseSort)
+	{
+		enum getMixin = nullCheck!(T, name) ~ "if (this." ~ name ~ " != _AutoDataOther." ~ name ~ ") return false;";
 	}
 }
 
@@ -161,32 +164,94 @@ struct CmpDataHandler(O)
 {
 	O other;
 
-	static string process(T, string name, bool reverseSort)()
+	template getMixin(T, string name, bool reverseSort)
 	{
-		string reverseStr = reverseSort ? "-" : "";
-		string s;
+		enum getMixin = getMixinComposite!(T, name, reverseSort).code;
+	}
+
+	template nullCheck(T, string name, string reverseStr)
+	{
+		static if (is(typeof(T.init is null)))
+			enum nullCheck = "
+				if (this."~name~" is null && _AutoDataOther."~name~" is null)
+					{ /* skip */ }
+				else
+				if (this."~name~" is null && _AutoDataOther."~name~" !is null)
+					return " ~ reverseStr ~ "(-1);
+				else
+				if (this."~name~" !is null && _AutoDataOther."~name~" is null)
+					return " ~ reverseStr ~ "( 1);
+				else";
+		else
+			enum nullCheck = "";
+	}
+
+	template getMixinComposite(T, string name, bool reverseSort)
+	{
+		enum reverseStr = reverseSort ? "-" : "";
 		static if (is(T U : U[]))
-			s ~= "{ int _AutoDataCmp = cast(int)(this." ~ name ~ " !is null) - cast(int)(_AutoDataOther." ~ name ~ " !is null); if (_AutoDataCmp != 0) return " ~ reverseStr ~ "_AutoDataCmp; }";
+			enum arrCode = "{ int _AutoDataCmp = cast(int)(this." ~ name ~ " !is null) - cast(int)(_AutoDataOther." ~ name ~ " !is null); if (_AutoDataCmp != 0) return " ~ reverseStr ~ "_AutoDataCmp; }";
+		else
+			enum arrCode = "";
 
 		static if (is(T == string) && is(std.string.cmp))
-			s ~= "{ int _AutoDataCmp = std.string.cmp(this." ~ name ~ ", _AutoDataOther." ~ name ~ "); if (_AutoDataCmp != 0) return " ~ reverseStr ~ "_AutoDataCmp; }";
+			enum dataCode = "{ int _AutoDataCmp = std.string.cmp(this." ~ name ~ ", _AutoDataOther." ~ name ~ "); if (_AutoDataCmp != 0) return " ~ reverseStr ~ "_AutoDataCmp; }";
 		else
 		static if (is(T == int))
-			s ~= "{ int _AutoDataCmp = this." ~ name ~ " - _AutoDataOther." ~ name ~ "; if (_AutoDataCmp != 0) return " ~ reverseStr ~ "_AutoDataCmp; }"; // TODO: use long?
+			enum dataCode = "{ int _AutoDataCmp = this." ~ name ~ " - _AutoDataOther." ~ name ~ "; if (_AutoDataCmp != 0) return " ~ reverseStr ~ "_AutoDataCmp; }"; // TODO: use long?
 		else
 		static if (is(typeof(T.opCmp)))
-			s ~= "{ int _AutoDataCmp = this." ~ name ~ ".opCmp(_AutoDataOther." ~ name ~ "); if (_AutoDataCmp != 0) return " ~ reverseStr ~ "_AutoDataCmp; }";
+			enum dataCode = nullCheck!(T, name, reverseStr)
+			              ~ "{ int _AutoDataCmp = this." ~ name ~ ".opCmp(cast()_AutoDataOther." ~ name ~ "); if (_AutoDataCmp != 0) return " ~ reverseStr ~ "_AutoDataCmp; }";
 		else
-			s ~= "if (this." ~ name ~ " < _AutoDataOther." ~ name ~ ") return " ~ reverseStr ~ "(-1);" ~ 
-			     "if (this." ~ name ~ " > _AutoDataOther." ~ name ~ ") return " ~ reverseStr ~ "( 1);";
-		return s;
+			enum dataCode = "if (this." ~ name ~ " < _AutoDataOther." ~ name ~ ") return " ~ reverseStr ~ "(-1);" ~
+			                "if (this." ~ name ~ " > _AutoDataOther." ~ name ~ ") return " ~ reverseStr ~ "( 1);";
+		enum code = arrCode ~ dataCode;
 	}
 }
 
 struct ToStringDataHandler
 {
-	static string process(T, string name, bool reverseSort)()
+	template getMixinSingle(T, string name)
 	{
-		return "_AutoDataResult ~= format(`%s = %s `, `" ~ name ~ "`, this." ~ name ~ ");";
+/*
+		enum getMixinSingle = "
+				static if (is(typeof(_AutoDataResult ~= " ~ name ~ ".toString())))
+					_AutoDataResult ~= " ~ name ~ ".toString();
+				else
+					_AutoDataResult ~= to!string(" ~ name ~ ");
+		";
+*/
+		static if (is(typeof(T.init is null)))
+			enum getMixinSingle = "_AutoDataResult ~= " ~ name ~ " ? to!string(" ~ name ~ ") : `null`;";
+		else
+			enum getMixinSingle = "_AutoDataResult ~= to!string(" ~ name ~ ");";
+	}
+
+	template getMixinBody(T, string name)
+	{
+		// TODO: arrays of arrays
+		static if (is(T U : U[]) && !is(T : const(char)[]))
+		{
+			enum getMixinBody = "
+				_AutoDataResult ~= ` [ `;
+				foreach (_AutoDataArrayIndex, _AutoDataArrayItem; " ~ name ~ ")
+				{
+					if (_AutoDataArrayIndex) _AutoDataResult ~= ` , `;
+					" ~ getMixinSingle!(U, "_AutoDataArrayItem") ~ "
+				}
+				_AutoDataResult ~= ` ] `;
+			";
+		}
+		else
+			enum getMixinBody = getMixinSingle!(T, name);
+	}
+
+	template getMixin(T, string name, bool reverseSort)
+	{
+		enum getMixin =
+			"_AutoDataResult ~= `" ~ name ~ " = `;" ~
+			getMixinBody!(T, name) ~
+			"_AutoDataResult ~= ` `;";
 	}
 }

build_rabcdasm.d

@@ -0,0 +1,132 @@
+/*
+ *  Copyright 2010, 2011, 2012, 2013 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  This file is part of RABCDAsm.
+ *
+ *  RABCDAsm is free software: you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation, either version 3 of the License, or
+ *  (at your option) any later version.
+ *
+ *  RABCDAsm is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with RABCDAsm.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/// A simple tool to build RABCDAsm in one command.
+/// You can use the DC and DCFLAGS environment variables to override the detected compiler and compilation flags.
+/// You can also pass program names or compilation options on the command-line to override the default ones.
+
+module build_rabcdasm;
+
+version(D_Version2)
+	{ /* All OK */ }
+else
+	static assert(false, "Unsupported D version.\nThis software requires a D2 ( http://dlang.org/ ) compiler to build.");
+
+version(D_Version2):
+
+version(DigitalMars)
+	const DEFAULT_COMPILER = "dmd";
+else
+	const DEFAULT_COMPILER = "gdmd";
+
+const DEFAULT_FLAGS = "-O -inline";
+const LZMA_FLAGS = "-version=HAVE_LZMA";
+
+import std.exception;
+import std.file;
+import std.process;
+import std.stdio;
+import std.string;
+
+string compiler, flags;
+
+void compile(string program)
+{
+	stderr.writeln("* Building ", program);
+	enforce(system(format("rdmd --build-only --compiler=%s %s %s", compiler, flags, program)) == 0, "Compilation of " ~ program ~ " failed");
+}
+
+void test(string code, string extraFlags=null)
+{
+	const BASE = "build_rabcdasm_buildtest";
+	const FN = BASE ~ ".d";
+	std.file.write(FN, code);
+	scope(exit) foreach (de; dirEntries(".", BASE ~ "*", SpanMode.shallow)) remove(de.name);
+	enforce(system(format("rdmd --force --compiler=%s -od. %s %s %s", compiler, flags, extraFlags, FN)) == 0, "Test failed");
+	stderr.writeln(" >>> OK");
+}
+
+int main(string[] args)
+{
+	try
+	{
+		auto programs = ["rabcasm", "rabcdasm", "abcexport", "abcreplace", "swfbinexport", "swfbinreplace", "swfdecompress", "swf7zcompress"];
+
+		compiler = getenv("DC");
+		if (compiler is null)
+			compiler = DEFAULT_COMPILER;
+
+		flags = getenv("DCFLAGS");
+		if (flags is null)
+			flags = DEFAULT_FLAGS;
+
+		string[] optionArgs, programArgs;
+		foreach (arg; args[1..$])
+			(arg.startsWith("-") ? optionArgs : programArgs) ~= arg;
+
+		if (optionArgs.length)
+			flags = optionArgs.join(" ");
+		if (programArgs.length)
+			programs = programArgs;
+
+		stderr.writeln("* Checking for working compiler...");
+		test(`
+			void main() {}
+		`);
+
+		bool haveLZMA;
+
+		stderr.writeln("* Checking for LZMA...");
+		try
+		{
+			test(`
+				import lzma, std.exception;
+				void main()
+				{
+					LZMAHeader header;
+					auto data = cast(immutable(ubyte)[])"Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.";
+					auto cdata = lzmaCompress(data, &header);
+					header.decompressedSize = data.length;
+					auto ddata = lzmaDecompress(header, cdata);
+					enforce(data == ddata);
+				}
+			`, LZMA_FLAGS);
+
+			// Test succeeded
+			haveLZMA = true;
+		}
+		catch (Exception e)
+			stderr.writeln(" >>> LZMA not found, building without LZMA support.");
+
+		if (haveLZMA)
+			flags ~= " " ~ LZMA_FLAGS;
+
+		foreach (program; programs)
+			compile(program);
+
+		if (haveLZMA)
+			compile("swflzmacompress");
+
+		return 0;
+	}
+	catch (Exception e)
+	{
+		stderr.writeln("Error: ", e.msg);
+		return 1;
+	}
+}

common.d

@@ -0,0 +1,90 @@
+/*
+ *  Copyright 2012, 2014 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  This file is part of RABCDAsm.
+ *
+ *  RABCDAsm is free software: you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation, either version 3 of the License, or
+ *  (at your option) any later version.
+ *
+ *  RABCDAsm is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with RABCDAsm.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+module common;
+
+import std.array;
+import std.path;
+import std.stdio;
+import std.string;
+
+string longPath(string s)
+{
+	version(Windows)
+	{
+		if (s.startsWith(`\\`))
+			return s;
+		else
+			return `\\?\` ~ s.absolutePath().buildNormalizedPath().replace(`/`, `\`);
+	}
+	else
+		return s;
+}
+
+File openFile(string fn, string mode)
+{
+	File f;
+	static if (is(typeof(&f.windowsHandleOpen)))
+	{
+		import core.sys.windows.windows;
+
+		import std.exception;
+		import std.utf;
+		import std.windows.syserror;
+
+		string winMode;
+		foreach (c; mode)
+			switch (c)
+			{
+				case 'r':
+				case 'w':
+				case 'a':
+				case '+':
+					winMode ~= c;
+					break;
+				case 'b':
+				case 't':
+					break;
+				default:
+					assert(false, "Unknown character in mode");
+			}
+		DWORD access, creation;
+		bool append;
+		switch (winMode)
+		{
+			case "r" : access = GENERIC_READ                ; creation = OPEN_EXISTING; break;
+			case "r+": access = GENERIC_READ | GENERIC_WRITE; creation = OPEN_EXISTING; break;
+			case "w" : access =                GENERIC_WRITE; creation = OPEN_ALWAYS  ; break;
+			case "w+": access = GENERIC_READ | GENERIC_WRITE; creation = OPEN_ALWAYS  ; break;
+			case "a" : access =                GENERIC_WRITE; creation = OPEN_ALWAYS  ; append = true; break;
+			case "a+": assert(false, "Not implemented"); // requires two file pointers
+			default: assert(false, "Bad file mode: " ~ mode);
+		}
+
+		auto pathW = toUTF16z(longPath(fn));
+		auto h = CreateFileW(pathW, access, FILE_SHARE_READ, null, creation, 0, HANDLE.init);
+		enforce(h != INVALID_HANDLE_VALUE, "Failed to open file \"" ~ fn ~ "\": " ~ sysErrorString(GetLastError()));
+
+		assert(!append, "'a' mode not implemented");
+
+		f.windowsHandleOpen(h, mode);
+	}
+	else
+		f.open(fn, mode);
+	return f;
+}

deimos/lzma.d

@@ -0,0 +1,83 @@
+/**
+ * \file        api/lzma.h
+ * \brief       The public API of liblzma data compression library
+ *
+ * liblzma is a public domain general-purpose data compression library with
+ * a zlib-like API. The native file format is .xz, but also the old .lzma
+ * format and raw (no headers) streams are supported. Multiple compression
+ * algorithms (filters) are supported. Currently LZMA2 is the primary filter.
+ *
+ * liblzma is part of XZ Utils <http://tukaani.org/xz/>. XZ Utils includes
+ * a gzip-like command line tool named xz and some other tools. XZ Utils
+ * is developed and maintained by Lasse Collin.
+ *
+ * Major parts of liblzma are based on Igor Pavlov's public domain LZMA SDK
+ * <http://7-zip.org/sdk.html>.
+ *
+ * The SHA-256 implementation is based on the public domain code found from
+ * 7-Zip <http://7-zip.org/>, which has a modified version of the public
+ * domain SHA-256 code found from Crypto++ <http://www.cryptopp.com/>.
+ * The SHA-256 code in Crypto++ was written by Kevin Springle and Wei Dai.
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+module deimos.lzma;
+
+/***********
+ * nothrow *
+ ***********/
+
+/*
+ * None of the functions in liblzma may throw an exception. Even
+ * the functions that use callback functions won't throw exceptions,
+ * because liblzma would break if a callback function threw an exception.
+ */
+//lzma_nothrow --> nothrow
+
+
+/********************
+ * GNU C extensions *
+ ********************/
+
+/*
+ * GNU C extensions are used conditionally in the public API. It doesn't
+ * break anything if these are sometimes enabled and sometimes not, only
+ * affects warnings and optimizations.
+ */
+
+//lzma_attr_pure --> pure
+//lzma_attr_const --> const
+//lzma_attr_warn_unused_result --> n/a
+
+
+/**************
+ * Subheaders *
+ **************/
+public import deimos.lzma_.version_;
+public import deimos.lzma_.base;
+public import deimos.lzma_.vli;
+public import deimos.lzma_.check;
+
+/* Filters */
+public import deimos.lzma_.filter;
+public import deimos.lzma_.bcj;
+public import deimos.lzma_.delta;
+public import deimos.lzma_.lzma;
+
+/* Container formats */
+public import deimos.lzma_.container;
+
+/* Advanced features */
+public import deimos.lzma_.stream_flags;
+public import deimos.lzma_.block;
+public import deimos.lzma_.index;
+public import deimos.lzma_.index_hash;
+
+/* Hardware information */
+public import deimos.lzma_.hardware;

deimos/lzma_/base.d

@@ -0,0 +1,582 @@
+/**
+ * \file        lzma/base.h
+ * \brief       Data types and functions used in many places in liblzma API
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.base;
+import deimos.lzma;
+
+extern(C):
+
+/**
+ * \brief       Boolean
+ *
+ * This is here because C89 doesn't have stdbool.h. To set a value for
+ * variables having type lzma_bool, you can use
+ *   - C99's `true' and `false' from stdbool.h;
+ *   - C++'s internal `true' and `false'; or
+ *   - integers one (true) and zero (false).
+ */
+alias bool lzma_bool;
+
+
+/**
+ * \brief       Type of reserved enumeration variable in structures
+ *
+ * To avoid breaking library ABI when new features are added, several
+ * structures contain extra variables that may be used in future. Since
+ * sizeof(enum) can be different than sizeof(int), and sizeof(enum) may
+ * even vary depending on the range of enumeration constants, we specify
+ * a separate type to be used for reserved enumeration variables. All
+ * enumeration constants in liblzma API will be non-negative and less
+ * than 128, which should guarantee that the ABI won't break even when
+ * new constants are added to existing enumerations.
+ */
+enum lzma_reserved_enum
+{
+	LZMA_RESERVED_ENUM      = 0
+}
+
+
+/**
+ * \brief       Return values used by several functions in liblzma
+ *
+ * Check the descriptions of specific functions to find out which return
+ * values they can return. With some functions the return values may have
+ * more specific meanings than described here; those differences are
+ * described per-function basis.
+ */
+enum lzma_ret
+{
+	LZMA_OK                 = 0,
+		/**<
+		 * \brief       Operation completed successfully
+		 */
+
+	LZMA_STREAM_END         = 1,
+		/**<
+		 * \brief       End of stream was reached
+		 *
+		 * In encoder, LZMA_SYNC_FLUSH, LZMA_FULL_FLUSH, or
+		 * LZMA_FINISH was finished. In decoder, this indicates
+		 * that all the data was successfully decoded.
+		 *
+		 * In all cases, when LZMA_STREAM_END is returned, the last
+		 * output bytes should be picked from strm->next_out.
+		 */
+
+	LZMA_NO_CHECK           = 2,
+		/**<
+		 * \brief       Input stream has no integrity check
+		 *
+		 * This return value can be returned only if the
+		 * LZMA_TELL_NO_CHECK flag was used when initializing
+		 * the decoder. LZMA_NO_CHECK is just a warning, and
+		 * the decoding can be continued normally.
+		 *
+		 * It is possible to call lzma_get_check() immediately after
+		 * lzma_code has returned LZMA_NO_CHECK. The result will
+		 * naturally be LZMA_CHECK_NONE, but the possibility to call
+		 * lzma_get_check() may be convenient in some applications.
+		 */
+
+	LZMA_UNSUPPORTED_CHECK  = 3,
+		/**<
+		 * \brief       Cannot calculate the integrity check
+		 *
+		 * The usage of this return value is different in encoders
+		 * and decoders.
+		 *
+		 * Encoders can return this value only from the initialization
+		 * function. If initialization fails with this value, the
+		 * encoding cannot be done, because there's no way to produce
+		 * output with the correct integrity check.
+		 *
+		 * Decoders can return this value only from lzma_code() and
+		 * only if the LZMA_TELL_UNSUPPORTED_CHECK flag was used when
+		 * initializing the decoder. The decoding can still be
+		 * continued normally even if the check type is unsupported,
+		 * but naturally the check will not be validated, and possible
+		 * errors may go undetected.
+		 *
+		 * With decoder, it is possible to call lzma_get_check()
+		 * immediately after lzma_code() has returned
+		 * LZMA_UNSUPPORTED_CHECK. This way it is possible to find
+		 * out what the unsupported Check ID was.
+		 */
+
+	LZMA_GET_CHECK          = 4,
+		/**<
+		 * \brief       Integrity check type is now available
+		 *
+		 * This value can be returned only by the lzma_code() function
+		 * and only if the decoder was initialized with the
+		 * LZMA_TELL_ANY_CHECK flag. LZMA_GET_CHECK tells the
+		 * application that it may now call lzma_get_check() to find
+		 * out the Check ID. This can be used, for example, to
+		 * implement a decoder that accepts only files that have
+		 * strong enough integrity check.
+		 */
+
+	LZMA_MEM_ERROR          = 5,
+		/**<
+		 * \brief       Cannot allocate memory
+		 *
+		 * Memory allocation failed, or the size of the allocation
+		 * would be greater than SIZE_MAX.
+		 *
+		 * Due to internal implementation reasons, the coding cannot
+		 * be continued even if more memory were made available after
+		 * LZMA_MEM_ERROR.
+		 */
+
+	LZMA_MEMLIMIT_ERROR     = 6,
+		/**
+		 * \brief       Memory usage limit was reached
+		 *
+		 * Decoder would need more memory than allowed by the
+		 * specified memory usage limit. To continue decoding,
+		 * the memory usage limit has to be increased with
+		 * lzma_memlimit_set().
+		 */
+
+	LZMA_FORMAT_ERROR       = 7,
+		/**<
+		 * \brief       File format not recognized
+		 *
+		 * The decoder did not recognize the input as supported file
+		 * format. This error can occur, for example, when trying to
+		 * decode .lzma format file with lzma_stream_decoder,
+		 * because lzma_stream_decoder accepts only the .xz format.
+		 */
+
+	LZMA_OPTIONS_ERROR      = 8,
+		/**<
+		 * \brief       Invalid or unsupported options
+		 *
+		 * Invalid or unsupported options, for example
+		 *  - unsupported filter(s) or filter options; or
+		 *  - reserved bits set in headers (decoder only).
+		 *
+		 * Rebuilding liblzma with more features enabled, or
+		 * upgrading to a newer version of liblzma may help.
+		 */
+
+	LZMA_DATA_ERROR         = 9,
+		/**<
+		 * \brief       Data is corrupt
+		 *
+		 * The usage of this return value is different in encoders
+		 * and decoders. In both encoder and decoder, the coding
+		 * cannot continue after this error.
+		 *
+		 * Encoders return this if size limits of the target file
+		 * format would be exceeded. These limits are huge, thus
+		 * getting this error from an encoder is mostly theoretical.
+		 * For example, the maximum compressed and uncompressed
+		 * size of a .xz Stream is roughly 8 EiB (2^63 bytes).
+		 *
+		 * Decoders return this error if the input data is corrupt.
+		 * This can mean, for example, invalid CRC32 in headers
+		 * or invalid check of uncompressed data.
+		 */
+
+	LZMA_BUF_ERROR          = 10,
+		/**<
+		 * \brief       No progress is possible
+		 *
+		 * This error code is returned when the coder cannot consume
+		 * any new input and produce any new output. The most common
+		 * reason for this error is that the input stream being
+		 * decoded is truncated or corrupt.
+		 *
+		 * This error is not fatal. Coding can be continued normally
+		 * by providing more input and/or more output space, if
+		 * possible.
+		 *
+		 * Typically the first call to lzma_code() that can do no
+		 * progress returns LZMA_OK instead of LZMA_BUF_ERROR. Only
+		 * the second consecutive call doing no progress will return
+		 * LZMA_BUF_ERROR. This is intentional.
+		 *
+		 * With zlib, Z_BUF_ERROR may be returned even if the
+		 * application is doing nothing wrong, so apps will need
+		 * to handle Z_BUF_ERROR specially. The above hack
+		 * guarantees that liblzma never returns LZMA_BUF_ERROR
+		 * to properly written applications unless the input file
+		 * is truncated or corrupt. This should simplify the
+		 * applications a little.
+		 */
+
+	LZMA_PROG_ERROR         = 11,
+		/**<
+		 * \brief       Programming error
+		 *
+		 * This indicates that the arguments given to the function are
+		 * invalid or the internal state of the decoder is corrupt.
+		 *   - Function arguments are invalid or the structures
+		 *     pointed by the argument pointers are invalid
+		 *     e.g. if strm->next_out has been set to NULL and
+		 *     strm->avail_out > 0 when calling lzma_code().
+		 *   - lzma_* functions have been called in wrong order
+		 *     e.g. lzma_code() was called right after lzma_end().
+		 *   - If errors occur randomly, the reason might be flaky
+		 *     hardware.
+		 *
+		 * If you think that your code is correct, this error code
+		 * can be a sign of a bug in liblzma. See the documentation
+		 * how to report bugs.
+		 */
+}
+
+
+/**
+ * \brief       The `action' argument for lzma_code()
+ *
+ * After the first use of LZMA_SYNC_FLUSH, LZMA_FULL_FLUSH, or LZMA_FINISH,
+ * the same `action' must is used until lzma_code() returns LZMA_STREAM_END.
+ * Also, the amount of input (that is, strm->avail_in) must not be modified
+ * by the application until lzma_code() returns LZMA_STREAM_END. Changing the
+ * `action' or modifying the amount of input will make lzma_code() return
+ * LZMA_PROG_ERROR.
+ */
+enum lzma_action
+{
+	LZMA_RUN = 0,
+		/**<
+		 * \brief       Continue coding
+		 *
+		 * Encoder: Encode as much input as possible. Some internal
+		 * buffering will probably be done (depends on the filter
+		 * chain in use), which causes latency: the input used won't
+		 * usually be decodeable from the output of the same
+		 * lzma_code() call.
+		 *
+		 * Decoder: Decode as much input as possible and produce as
+		 * much output as possible.
+		 */
+
+	LZMA_SYNC_FLUSH = 1,
+		/**<
+		 * \brief       Make all the input available at output
+		 *
+		 * Normally the encoder introduces some latency.
+		 * LZMA_SYNC_FLUSH forces all the buffered data to be
+		 * available at output without resetting the internal
+		 * state of the encoder. This way it is possible to use
+		 * compressed stream for example for communication over
+		 * network.
+		 *
+		 * Only some filters support LZMA_SYNC_FLUSH. Trying to use
+		 * LZMA_SYNC_FLUSH with filters that don't support it will
+		 * make lzma_code() return LZMA_OPTIONS_ERROR. For example,
+		 * LZMA1 doesn't support LZMA_SYNC_FLUSH but LZMA2 does.
+		 *
+		 * Using LZMA_SYNC_FLUSH very often can dramatically reduce
+		 * the compression ratio. With some filters (for example,
+		 * LZMA2), fine-tuning the compression options may help
+		 * mitigate this problem significantly (for example,
+		 * match finder with LZMA2).
+		 *
+		 * Decoders don't support LZMA_SYNC_FLUSH.
+		 */
+
+	LZMA_FULL_FLUSH = 2,
+		/**<
+		 * \brief       Finish encoding of the current Block
+		 *
+		 * All the input data going to the current Block must have
+		 * been given to the encoder (the last bytes can still be
+		 * pending in* next_in). Call lzma_code() with LZMA_FULL_FLUSH
+		 * until it returns LZMA_STREAM_END. Then continue normally
+		 * with LZMA_RUN or finish the Stream with LZMA_FINISH.
+		 *
+		 * This action is currently supported only by Stream encoder
+		 * and easy encoder (which uses Stream encoder). If there is
+		 * no unfinished Block, no empty Block is created.
+		 */
+
+	LZMA_FINISH = 3
+		/**<
+		 * \brief       Finish the coding operation
+		 *
+		 * All the input data must have been given to the encoder
+		 * (the last bytes can still be pending in next_in).
+		 * Call lzma_code() with LZMA_FINISH until it returns
+		 * LZMA_STREAM_END. Once LZMA_FINISH has been used,
+		 * the amount of input must no longer be changed by
+		 * the application.
+		 *
+		 * When decoding, using LZMA_FINISH is optional unless the
+		 * LZMA_CONCATENATED flag was used when the decoder was
+		 * initialized. When LZMA_CONCATENATED was not used, the only
+		 * effect of LZMA_FINISH is that the amount of input must not
+		 * be changed just like in the encoder.
+		 */
+}
+
+
+/**
+ * \brief       Custom functions for memory handling
+ *
+ * A pointer to lzma_allocator may be passed via lzma_stream structure
+ * to liblzma, and some advanced functions take a pointer to lzma_allocator
+ * as a separate function argument. The library will use the functions
+ * specified in lzma_allocator for memory handling instead of the default
+ * malloc() and free(). C++ users should note that the custom memory
+ * handling functions must not throw exceptions.
+ *
+ * liblzma doesn't make an internal copy of lzma_allocator. Thus, it is
+ * OK to change these function pointers in the middle of the coding
+ * process, but obviously it must be done carefully to make sure that the
+ * replacement `free' can deallocate memory allocated by the earlier
+ * `alloc' function(s).
+ */
+struct lzma_allocator
+{
+	/**
+	 * \brief       Pointer to a custom memory allocation function
+	 *
+	 * If you don't want a custom allocator, but still want
+	 * custom free(), set this to NULL and liblzma will use
+	 * the standard malloc().
+	 *
+	 * \param       opaque  lzma_allocator.opaque (see below)
+	 * \param       nmemb   Number of elements like in calloc(). liblzma
+	 *                      will always set nmemb to 1, so it is safe to
+	 *                      ignore nmemb in a custom allocator if you like.
+	 *                      The nmemb argument exists only for
+	 *                      compatibility with zlib and libbzip2.
+	 * \param       size    Size of an element in bytes.
+	 *                      liblzma never sets this to zero.
+	 *
+	 * \return      Pointer to the beginning of a memory block of
+	 *              `size' bytes, or NULL if allocation fails
+	 *              for some reason. When allocation fails, functions
+	 *              of liblzma return LZMA_MEM_ERROR.
+	 *
+	 * The allocator should not waste time zeroing the allocated buffers.
+	 * This is not only about speed, but also memory usage, since the
+	 * operating system kernel doesn't necessarily allocate the requested
+	 * memory in physical memory until it is actually used. With small
+	 * input files, liblzma may actually need only a fraction of the
+	 * memory that it requested for allocation.
+	 *
+	 * \note        LZMA_MEM_ERROR is also used when the size of the
+	 *              allocation would be greater than SIZE_MAX. Thus,
+	 *              don't assume that the custom allocator must have
+	 *              returned NULL if some function from liblzma
+	 *              returns LZMA_MEM_ERROR.
+	 */
+	void* function(void *opaque, size_t nmemb, size_t size) alloc;
+
+	/**
+	 * \brief       Pointer to a custom memory freeing function
+	 *
+	 * If you don't want a custom freeing function, but still
+	 * want a custom allocator, set this to NULL and liblzma
+	 * will use the standard free().
+	 *
+	 * \param       opaque  lzma_allocator.opaque (see below)
+	 * \param       ptr     Pointer returned by lzma_allocator.alloc(),
+	 *                      or when it is set to NULL, a pointer returned
+	 *                      by the standard malloc().
+	 */
+	void function(void *opaque, void *ptr) free;
+
+	/**
+	 * \brief       Pointer passed to .alloc() and .free()
+	 *
+	 * opaque is passed as the first argument to lzma_allocator.alloc()
+	 * and lzma_allocator.free(). This intended to ease implementing
+	 * custom memory allocation functions for use with liblzma.
+	 *
+	 * If you don't need this, you should set this to NULL.
+	 */
+	void *opaque;
+}
+
+
+/**
+ * \brief       Internal data structure
+ *
+ * The contents of this structure is not visible outside the library.
+ */
+struct lzma_internal {}
+
+
+/**
+ * \brief       Passing data to and from liblzma
+ *
+ * The lzma_stream structure is used for
+ *  - passing pointers to input and output buffers to liblzma;
+ *  - defining custom memory hander functions; and
+ *  - holding a pointer to coder-specific internal data structures.
+ *
+ * Typical usage:
+ *
+ *  - After allocating lzma_stream (on stack or with malloc()), it must be
+ *    initialized to LZMA_STREAM_INIT (see LZMA_STREAM_INIT for details).
+ *
+ *  - Initialize a coder to the lzma_stream, for example by using
+ *    lzma_easy_encoder() or lzma_auto_decoder(). Some notes:
+ *      - In contrast to zlib, strm->next_in and strm->next_out are
+ *        ignored by all initialization functions, thus it is safe
+ *        to not initialize them yet.
+ *      - The initialization functions always set strm->total_in and
+ *        strm->total_out to zero.
+ *      - If the initialization function fails, no memory is left allocated
+ *        that would require freeing with lzma_end() even if some memory was
+ *        associated with the lzma_stream structure when the initialization
+ *        function was called.
+ *
+ *  - Use lzma_code() to do the actual work.
+ *
+ *  - Once the coding has been finished, the existing lzma_stream can be
+ *    reused. It is OK to reuse lzma_stream with different initialization
+ *    function without calling lzma_end() first. Old allocations are
+ *    automatically freed.
+ *
+ *  - Finally, use lzma_end() to free the allocated memory. lzma_end() never
+ *    frees the lzma_stream structure itself.
+ *
+ * Application may modify the values of total_in and total_out as it wants.
+ * They are updated by liblzma to match the amount of data read and
+ * written, but aren't used for anything else.
+ */
+struct lzma_stream
+{
+	const(ubyte)* next_in; /**< Pointer to the next input byte. */
+	size_t avail_in;    /**< Number of available input bytes in next_in. */
+	ulong total_in;  /**< Total number of bytes read by liblzma. */
+
+	ubyte* next_out;  /**< Pointer to the next output position. */
+	size_t avail_out;   /**< Amount of free space in next_out. */
+	ulong total_out; /**< Total number of bytes written by liblzma. */
+
+	/**
+	 * \brief       Custom memory allocation functions
+	 *
+	 * In most cases this is NULL which makes liblzma use
+	 * the standard malloc() and free().
+	 */
+	lzma_allocator *allocator;
+
+	/** Internal state is not visible to applications. */
+	lzma_internal *internal;
+
+	/*
+	 * Reserved space to allow possible future extensions without
+	 * breaking the ABI. Excluding the initialization of this structure,
+	 * you should not touch these, because the names of these variables
+	 * may change.
+	 */
+	void *reserved_ptr1;
+	void *reserved_ptr2;
+	void *reserved_ptr3;
+	void *reserved_ptr4;
+	ulong reserved_int1;
+	ulong reserved_int2;
+	size_t reserved_int3;
+	size_t reserved_int4;
+	lzma_reserved_enum reserved_enum1;
+	lzma_reserved_enum reserved_enum2;
+}
+
+/**
+ * Initialization for lzma_stream
+ *
+ * Not needed in d, just use lzma_stream.init
+ */
+//void LZMA_STREAM_INIT(){};
+
+
+/**
+ * \brief       Encode or decode data
+ *
+ * Once the lzma_stream has been successfully initialized (e.g. with
+ * lzma_stream_encoder()), the actual encoding or decoding is done
+ * using this function. The application has to update strm->next_in,
+ * strm->avail_in, strm->next_out, and strm->avail_out to pass input
+ * to and get output from liblzma.
+ *
+ * See the description of the coder-specific initialization function to find
+ * out what `action' values are supported by the coder.
+ */
+nothrow lzma_ret lzma_code(lzma_stream *strm, lzma_action action);
+
+
+/**
+ * \brief       Free memory allocated for the coder data structures
+ *
+ * \param       strm    Pointer to lzma_stream that is at least initialized
+ *                      with LZMA_STREAM_INIT.
+ *
+ * After lzma_end(strm), strm->internal is guaranteed to be NULL. No other
+ * members of the lzma_stream structure are touched.
+ *
+ * \note        zlib indicates an error if application end()s unfinished
+ *              stream structure. liblzma doesn't do this, and assumes that
+ *              application knows what it is doing.
+ */
+nothrow void lzma_end(lzma_stream *strm);
+
+
+/**
+ * \brief       Get the memory usage of decoder filter chain
+ *
+ * This function is currently supported only when *strm has been initialized
+ * with a function that takes a memlimit argument. With other functions, you
+ * should use e.g. lzma_raw_encoder_memusage() or lzma_raw_decoder_memusage()
+ * to estimate the memory requirements.
+ *
+ * This function is useful e.g. after LZMA_MEMLIMIT_ERROR to find out how big
+ * the memory usage limit should have been to decode the input. Note that
+ * this may give misleading information if decoding .xz Streams that have
+ * multiple Blocks, because each Block can have different memory requirements.
+ *
+ * \return      How much memory is currently allocated for the filter
+ *              decoders. If no filter chain is currently allocated,
+ *              some non-zero value is still returned, which is less than
+ *              or equal to what any filter chain would indicate as its
+ *              memory requirement.
+ *
+ *              If this function isn't supported by *strm or some other error
+ *              occurs, zero is returned.
+ */
+nothrow pure ulong lzma_memusage(const lzma_stream *strm);
+
+
+/**
+ * \brief       Get the current memory usage limit
+ *
+ * This function is supported only when *strm has been initialized with
+ * a function that takes a memlimit argument.
+ *
+ * \return      On success, the current memory usage limit is returned
+ *              (always non-zero). On error, zero is returned.
+ */
+nothrow pure ulong lzma_memlimit_get(const lzma_stream *strm);
+
+/**
+ * \brief       Set the memory usage limit
+ *
+ * This function is supported only when *strm has been initialized with
+ * a function that takes a memlimit argument.
+ *
+ * \return      - LZMA_OK: New memory usage limit successfully set.
+ *              - LZMA_MEMLIMIT_ERROR: The new limit is too small.
+ *                The limit was not changed.
+ *              - LZMA_PROG_ERROR: Invalid arguments, e.g. *strm doesn't
+ *                support memory usage limit or memlimit was zero.
+ */
+nothrow lzma_ret lzma_memlimit_set(lzma_stream *strm, ulong memlimit);

deimos/lzma_/bcj.d

@@ -0,0 +1,91 @@
+/**
+ * \file        lzma/bcj.h
+ * \brief       Branch/Call/Jump conversion filters
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.bcj;
+import deimos.lzma;
+
+extern(C):
+
+/* Filter IDs for lzma_filter.id */
+
+enum LZMA_FILTER_X86 = 0x04UL;
+	/**<
+	 * Filter for x86 binaries
+	 */
+
+
+enum LZMA_FILTER_POWERPC = 0x05UL;
+	/**<
+	 * Filter for Big endian PowerPC binaries
+	 */
+
+enum LZMA_FILTER_IA64 = 0x06UL;
+	/**<
+	 * Filter for IA-64 (Itanium) binaries.
+	 */
+
+enum LZMA_FILTER_ARM = 0x07UL;
+	/**<
+	 * Filter for ARM binaries.
+	 */
+
+enum LZMA_FILTER_ARMTHUMB = 0x08UL;
+	/**<
+	 * Filter for ARM-Thumb binaries.
+	 */
+
+enum LZMA_FILTER_SPARC = 0x09UL;
+	/**<
+	 * Filter for SPARC binaries.
+	 */
+
+
+/**
+ * \brief       Options for BCJ filters
+ *
+ * The BCJ filters never change the size of the data. Specifying options
+ * for them is optional: if pointer to options is NULL, default value is
+ * used. You probably never need to specify options to BCJ filters, so just
+ * set the options pointer to NULL and be happy.
+ *
+ * If options with non-default values have been specified when encoding,
+ * the same options must also be specified when decoding.
+ *
+ * \note        At the moment, none of the BCJ filters support
+ *              LZMA_SYNC_FLUSH. If LZMA_SYNC_FLUSH is specified,
+ *              LZMA_OPTIONS_ERROR will be returned. If there is need,
+ *              partial support for LZMA_SYNC_FLUSH can be added in future.
+ *              Partial means that flushing would be possible only at
+ *              offsets that are multiple of 2, 4, or 16 depending on
+ *              the filter, except x86 which cannot be made to support
+ *              LZMA_SYNC_FLUSH predictably.
+ */
+struct lzma_options_bcj
+{
+	/**
+	 * \brief       Start offset for conversions
+	 *
+	 * This setting is useful only when the same filter is used
+	 * _separately_ for multiple sections of the same executable file,
+	 * and the sections contain cross-section branch/call/jump
+	 * instructions. In that case it is beneficial to set the start
+	 * offset of the non-first sections so that the relative addresses
+	 * of the cross-section branch/call/jump instructions will use the
+	 * same absolute addresses as in the first section.
+	 *
+	 * When the pointer to options is NULL, the default value (zero)
+	 * is used.
+	 */
+	uint start_offset;
+}

deimos/lzma_/block.d

@@ -0,0 +1,523 @@
+/**
+ * \file        lzma/block.h
+ * \brief       .xz Block handling
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.block;
+import deimos.lzma;
+
+extern(C):
+
+//TODO: initialize fields to void?
+/**
+ * \brief       Options for the Block and Block Header encoders and decoders
+ *
+ * Different Block handling functions use different parts of this structure.
+ * Some read some members, other functions write, and some do both. Only the
+ * members listed for reading need to be initialized when the specified
+ * functions are called. The members marked for writing will be assigned
+ * new values at some point either by calling the given function or by
+ * later calls to lzma_code().
+ */
+struct lzma_block
+{
+	/**
+	 * \brief       Block format version
+	 *
+	 * To prevent API and ABI breakages if new features are needed in
+	 * the Block field, a version number is used to indicate which
+	 * fields in this structure are in use. For now, version must always
+	 * be zero. With non-zero version, most Block related functions will
+	 * return LZMA_OPTIONS_ERROR.
+	 *
+	 * Read by:
+	 *  - All functions that take pointer to lzma_block as argument,
+	 *    including lzma_block_header_decode().
+	 *
+	 * Written by:
+	 *  - lzma_block_header_decode()
+	 */
+	uint version_;
+
+	/**
+	 * \brief       Size of the Block Header field
+	 *
+	 * This is always a multiple of four.
+	 *
+	 * Read by:
+	 *  - lzma_block_header_encode()
+	 *  - lzma_block_header_decode()
+	 *  - lzma_block_compressed_size()
+	 *  - lzma_block_unpadded_size()
+	 *  - lzma_block_total_size()
+	 *  - lzma_block_decoder()
+	 *  - lzma_block_buffer_decode()
+	 *
+	 * Written by:
+	 *  - lzma_block_header_size()
+	 *  - lzma_block_buffer_encode()
+	 */
+
+	uint header_size;
+	enum LZMA_BLOCK_HEADER_SIZE_MIN = 8;
+	enum LZMA_BLOCK_HEADER_SIZE_MAX = 1024;
+
+	/**
+	 * \brief       Type of integrity Check
+	 *
+	 * The Check ID is not stored into the Block Header, thus its value
+	 * must be provided also when decoding.
+	 *
+	 * Read by:
+	 *  - lzma_block_header_encode()
+	 *  - lzma_block_header_decode()
+	 *  - lzma_block_compressed_size()
+	 *  - lzma_block_unpadded_size()
+	 *  - lzma_block_total_size()
+	 *  - lzma_block_encoder()
+	 *  - lzma_block_decoder()
+	 *  - lzma_block_buffer_encode()
+	 *  - lzma_block_buffer_decode()
+	 */
+	lzma_check check;
+
+	/**
+	 * \brief       Size of the Compressed Data in bytes
+	 *
+	 * Encoding: If this is not LZMA_VLI_UNKNOWN, Block Header encoder
+	 * will store this value to the Block Header. Block encoder doesn't
+	 * care about this value, but will set it once the encoding has been
+	 * finished.
+	 *
+	 * Decoding: If this is not LZMA_VLI_UNKNOWN, Block decoder will
+	 * verify that the size of the Compressed Data field matches
+	 * compressed_size.
+	 *
+	 * Usually you don't know this value when encoding in streamed mode,
+	 * and thus cannot write this field into the Block Header.
+	 *
+	 * In non-streamed mode you can reserve space for this field before
+	 * encoding the actual Block. After encoding the data, finish the
+	 * Block by encoding the Block Header. Steps in detail:
+	 *
+	 *  - Set compressed_size to some big enough value. If you don't know
+	 *    better, use LZMA_VLI_MAX, but remember that bigger values take
+	 *    more space in Block Header.
+	 *
+	 *  - Call lzma_block_header_size() to see how much space you need to
+	 *    reserve for the Block Header.
+	 *
+	 *  - Encode the Block using lzma_block_encoder() and lzma_code().
+	 *    It sets compressed_size to the correct value.
+	 *
+	 *  - Use lzma_block_header_encode() to encode the Block Header.
+	 *    Because space was reserved in the first step, you don't need
+	 *    to call lzma_block_header_size() anymore, because due to
+	 *    reserving, header_size has to be big enough. If it is "too big",
+	 *    lzma_block_header_encode() will add enough Header Padding to
+	 *    make Block Header to match the size specified by header_size.
+	 *
+	 * Read by:
+	 *  - lzma_block_header_size()
+	 *  - lzma_block_header_encode()
+	 *  - lzma_block_compressed_size()
+	 *  - lzma_block_unpadded_size()
+	 *  - lzma_block_total_size()
+	 *  - lzma_block_decoder()
+	 *  - lzma_block_buffer_decode()
+	 *
+	 * Written by:
+	 *  - lzma_block_header_decode()
+	 *  - lzma_block_compressed_size()
+	 *  - lzma_block_encoder()
+	 *  - lzma_block_decoder()
+	 *  - lzma_block_buffer_encode()
+	 *  - lzma_block_buffer_decode()
+	 */
+	lzma_vli compressed_size;
+
+	/**
+	 * \brief       Uncompressed Size in bytes
+	 *
+	 * This is handled very similarly to compressed_size above.
+	 *
+	 * uncompressed_size is needed by fewer functions than
+	 * compressed_size. This is because uncompressed_size isn't
+	 * needed to validate that Block stays within proper limits.
+	 *
+	 * Read by:
+	 *  - lzma_block_header_size()
+	 *  - lzma_block_header_encode()
+	 *  - lzma_block_decoder()
+	 *  - lzma_block_buffer_decode()
+	 *
+	 * Written by:
+	 *  - lzma_block_header_decode()
+	 *  - lzma_block_encoder()
+	 *  - lzma_block_decoder()
+	 *  - lzma_block_buffer_encode()
+	 *  - lzma_block_buffer_decode()
+	 */
+	lzma_vli uncompressed_size;
+
+	/**
+	 * \brief       Array of filters
+	 *
+	 * There can be 1-4 filters. The end of the array is marked with
+	 * .id = LZMA_VLI_UNKNOWN.
+	 *
+	 * Read by:
+	 *  - lzma_block_header_size()
+	 *  - lzma_block_header_encode()
+	 *  - lzma_block_encoder()
+	 *  - lzma_block_decoder()
+	 *  - lzma_block_buffer_encode()
+	 *  - lzma_block_buffer_decode()
+	 *
+	 * Written by:
+	 *  - lzma_block_header_decode(): Note that this does NOT free()
+	 *    the old filter options structures. All unused filters[] will
+	 *    have .id == LZMA_VLI_UNKNOWN and .options == NULL. If
+	 *    decoding fails, all filters[] are guaranteed to be
+	 *    LZMA_VLI_UNKNOWN and NULL.
+	 *
+	 * \note        Because of the array is terminated with
+	 *              .id = LZMA_VLI_UNKNOWN, the actual array must
+	 *              have LZMA_FILTERS_MAX + 1 members or the Block
+	 *              Header decoder will overflow the buffer.
+	 */
+	lzma_filter *filters;
+
+	/**
+	 * \brief       Raw value stored in the Check field
+	 *
+	 * After successful coding, the first lzma_check_size(check) bytes
+	 * of this array contain the raw value stored in the Check field.
+	 *
+	 * Note that CRC32 and CRC64 are stored in little endian byte order.
+	 * Take it into account if you display the Check values to the user.
+	 *
+	 * Written by:
+	 *  - lzma_block_encoder()
+	 *  - lzma_block_decoder()
+	 *  - lzma_block_buffer_encode()
+	 *  - lzma_block_buffer_decode()
+	 */
+	ubyte[LZMA_CHECK_SIZE_MAX] raw_check;
+
+	/*
+	 * Reserved space to allow possible future extensions without
+	 * breaking the ABI. You should not touch these, because the names
+	 * of these variables may change. These are and will never be used
+	 * with the currently supported options, so it is safe to leave these
+	 * uninitialized.
+	 */
+	void *reserved_ptr1;
+	void *reserved_ptr2;
+	void *reserved_ptr3;
+	uint reserved_int1;
+	uint reserved_int2;
+	lzma_vli reserved_int3;
+	lzma_vli reserved_int4;
+	lzma_vli reserved_int5;
+	lzma_vli reserved_int6;
+	lzma_vli reserved_int7;
+	lzma_vli reserved_int8;
+	lzma_reserved_enum reserved_enum1;
+	lzma_reserved_enum reserved_enum2;
+	lzma_reserved_enum reserved_enum3;
+	lzma_reserved_enum reserved_enum4;
+	lzma_bool reserved_bool1;
+	lzma_bool reserved_bool2;
+	lzma_bool reserved_bool3;
+	lzma_bool reserved_bool4;
+	lzma_bool reserved_bool5;
+	lzma_bool reserved_bool6;
+	lzma_bool reserved_bool7;
+	lzma_bool reserved_bool8;
+}
+
+
+/**
+ * \brief       Decode the Block Header Size field
+ *
+ * To decode Block Header using lzma_block_header_decode(), the size of the
+ * Block Header has to be known and stored into lzma_block.header_size.
+ * The size can be calculated from the first byte of a Block using this macro.
+ * Note that if the first byte is 0x00, it indicates beginning of Index; use
+ * this macro only when the byte is not 0x00.
+ *
+ * There is no encoding macro, because Block Header encoder is enough for that.
+ */
+template lzma_block_header_size_decode(uint b)
+{
+    enum lzma_block_header_size_decode = (b+1)*4;
+}
+
+
+/**
+ * \brief       Calculate Block Header Size
+ *
+ * Calculate the minimum size needed for the Block Header field using the
+ * settings specified in the lzma_block structure. Note that it is OK to
+ * increase the calculated header_size value as long as it is a multiple of
+ * four and doesn't exceed LZMA_BLOCK_HEADER_SIZE_MAX. Increasing header_size
+ * just means that lzma_block_header_encode() will add Header Padding.
+ *
+ * \return      - LZMA_OK: Size calculated successfully and stored to
+ *                block->header_size.
+ *              - LZMA_OPTIONS_ERROR: Unsupported version, filters or
+ *                filter options.
+ *              - LZMA_PROG_ERROR: Invalid values like compressed_size == 0.
+ *
+ * \note        This doesn't check that all the options are valid i.e. this
+ *              may return LZMA_OK even if lzma_block_header_encode() or
+ *              lzma_block_encoder() would fail. If you want to validate the
+ *              filter chain, consider using lzma_memlimit_encoder() which as
+ *              a side-effect validates the filter chain.
+ */
+nothrow lzma_ret lzma_block_header_size(lzma_block *block);
+
+
+/**
+ * \brief       Encode Block Header
+ *
+ * The caller must have calculated the size of the Block Header already with
+ * lzma_block_header_size(). If a value larger than the one calculated by
+ * lzma_block_header_size() is used, the Block Header will be padded to the
+ * specified size.
+ *
+ * \param       out         Beginning of the output buffer. This must be
+ *                          at least block->header_size bytes.
+ * \param       block       Block options to be encoded.
+ *
+ * \return      - LZMA_OK: Encoding was successful. block->header_size
+ *                bytes were written to output buffer.
+ *              - LZMA_OPTIONS_ERROR: Invalid or unsupported options.
+ *              - LZMA_PROG_ERROR: Invalid arguments, for example
+ *                block->header_size is invalid or block->filters is NULL.
+ */
+nothrow lzma_ret lzma_block_header_encode(const (lzma_block)* block, ubyte* out_);
+
+
+/**
+ * \brief       Decode Block Header
+ *
+ * block->version should be set to the highest value supported by the
+ * application; currently the only possible version is zero. This function
+ * will set version to the lowest value that still supports all the features
+ * required by the Block Header.
+ *
+ * The size of the Block Header must have already been decoded with
+ * lzma_block_header_size_decode() macro and stored to block->header_size.
+ *
+ * block->filters must have been allocated, but they don't need to be
+ * initialized (possible existing filter options are not freed).
+ *
+ * \param       block       Destination for Block options.
+ * \param       allocator   lzma_allocator for custom allocator functions.
+ *                          Set to NULL to use malloc() (and also free()
+ *                          if an error occurs).
+ * \param       in          Beginning of the input buffer. This must be
+ *                          at least block->header_size bytes.
+ *
+ * \return      - LZMA_OK: Decoding was successful. block->header_size
+ *                bytes were read from the input buffer.
+ *              - LZMA_OPTIONS_ERROR: The Block Header specifies some
+ *                unsupported options such as unsupported filters. This can
+ *                happen also if block->version was set to a too low value
+ *                compared to what would be required to properly represent
+ *                the information stored in the Block Header.
+ *              - LZMA_DATA_ERROR: Block Header is corrupt, for example,
+ *                the CRC32 doesn't match.
+ *              - LZMA_PROG_ERROR: Invalid arguments, for example
+ *                block->header_size is invalid or block->filters is NULL.
+ */
+nothrow lzma_ret lzma_block_header_decode(lzma_block* block,
+		lzma_allocator* allocator, const(ubyte)* in_);
+
+
+/**
+ * \brief       Validate and set Compressed Size according to Unpadded Size
+ *
+ * Block Header stores Compressed Size, but Index has Unpadded Size. If the
+ * application has already parsed the Index and is now decoding Blocks,
+ * it can calculate Compressed Size from Unpadded Size. This function does
+ * exactly that with error checking:
+ *
+ *  - Compressed Size calculated from Unpadded Size must be positive integer,
+ *    that is, Unpadded Size must be big enough that after Block Header and
+ *    Check fields there's still at least one byte for Compressed Size.
+ *
+ *  - If Compressed Size was present in Block Header, the new value
+ *    calculated from Unpadded Size is compared against the value
+ *    from Block Header.
+ *
+ * \note        This function must be called _after_ decoding the Block Header
+ *              field so that it can properly validate Compressed Size if it
+ *              was present in Block Header.
+ *
+ * \return      - LZMA_OK: block->compressed_size was set successfully.
+ *              - LZMA_DATA_ERROR: unpadded_size is too small compared to
+ *                block->header_size and lzma_check_size(block->check).
+ *              - LZMA_PROG_ERROR: Some values are invalid. For example,
+ *                block->header_size must be a multiple of four and
+ *                between 8 and 1024 inclusive.
+ */
+nothrow lzma_ret lzma_block_compressed_size(
+		lzma_block* block, lzma_vli unpadded_size);
+
+
+/**
+ * \brief       Calculate Unpadded Size
+ *
+ * The Index field stores Unpadded Size and Uncompressed Size. The latter
+ * can be taken directly from the lzma_block structure after coding a Block,
+ * but Unpadded Size needs to be calculated from Block Header Size,
+ * Compressed Size, and size of the Check field. This is where this function
+ * is needed.
+ *
+ * \return      Unpadded Size on success, or zero on error.
+ */
+nothrow lzma_vli lzma_block_unpadded_size(const lzma_block* block);
+
+
+/**
+ * \brief       Calculate the total encoded size of a Block
+ *
+ * This is equivalent to lzma_block_unpadded_size() except that the returned
+ * value includes the size of the Block Padding field.
+ *
+ * \return      On success, total encoded size of the Block. On error,
+ *              zero is returned.
+ */
+nothrow pure lzma_vli lzma_block_total_size(const(lzma_block*) block);
+
+
+/**
+ * \brief       Initialize .xz Block encoder
+ *
+ * Valid actions for lzma_code() are LZMA_RUN, LZMA_SYNC_FLUSH (only if the
+ * filter chain supports it), and LZMA_FINISH.
+ *
+ * \return      - LZMA_OK: All good, continue with lzma_code().
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_UNSUPPORTED_CHECK: block->check specifies a Check ID
+ *                that is not supported by this buid of liblzma. Initializing
+ *                the encoder failed.
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_block_encoder(
+		lzma_stream* strm, lzma_block* block);
+
+
+/**
+ * \brief       Initialize .xz Block decoder
+ *
+ * Valid actions for lzma_code() are LZMA_RUN and LZMA_FINISH. Using
+ * LZMA_FINISH is not required. It is supported only for convenience.
+ *
+ * \return      - LZMA_OK: All good, continue with lzma_code().
+ *              - LZMA_UNSUPPORTED_CHECK: Initialization was successful, but
+ *                the given Check ID is not supported, thus Check will be
+ *                ignored.
+ *              - LZMA_PROG_ERROR
+ *              - LZMA_MEM_ERROR
+ */
+nothrow lzma_ret lzma_block_decoder(
+		lzma_stream *strm, lzma_block *block);
+
+
+/**
+ * \brief       Calculate maximum output size for single-call Block encoding
+ *
+ * This is equivalent to lzma_stream_buffer_bound() but for .xz Blocks.
+ * See the documentation of lzma_stream_buffer_bound().
+ */
+nothrow size_t lzma_block_buffer_bound(size_t uncompressed_size);
+
+
+/**
+ * \brief       Single-call .xz Block encoder
+ *
+ * In contrast to the multi-call encoder initialized with
+ * lzma_block_encoder(), this function encodes also the Block Header. This
+ * is required to make it possible to write appropriate Block Header also
+ * in case the data isn't compressible, and different filter chain has to be
+ * used to encode the data in uncompressed form using uncompressed chunks
+ * of the LZMA2 filter.
+ *
+ * When the data isn't compressible, header_size, compressed_size, and
+ * uncompressed_size are set just like when the data was compressible, but
+ * it is possible that header_size is too small to hold the filter chain
+ * specified in block->filters, because that isn't necessarily the filter
+ * chain that was actually used to encode the data. lzma_block_unpadded_size()
+ * still works normally, because it doesn't read the filters array.
+ *
+ * \param       block       Block options: block->version, block->check,
+ *                          and block->filters must have been initialized.
+ * \param       allocator   lzma_allocator for custom allocator functions.
+ *                          Set to NULL to use malloc() and free().
+ * \param       in          Beginning of the input buffer
+ * \param       in_size     Size of the input buffer
+ * \param       out         Beginning of the output buffer
+ * \param       out_pos     The next byte will be written to out[*out_pos].
+ *                          *out_pos is updated only if encoding succeeds.
+ * \param       out_size    Size of the out buffer; the first byte into
+ *                          which no data is written to is out[out_size].
+ *
+ * \return      - LZMA_OK: Encoding was successful.
+ *              - LZMA_BUF_ERROR: Not enough output buffer space.
+ *              - LZMA_UNSUPPORTED_CHECK
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_DATA_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_block_buffer_encode(
+		lzma_block *block, lzma_allocator *allocator,
+		const(ubyte)* in_, size_t in_size,
+		ubyte* out_, size_t *out_pos, size_t out_size);
+
+
+/**
+ * \brief       Single-call .xz Block decoder
+ *
+ * This is single-call equivalent of lzma_block_decoder(), and requires that
+ * the caller has already decoded Block Header and checked its memory usage.
+ *
+ * \param       block       Block options just like with lzma_block_decoder().
+ * \param       allocator   lzma_allocator for custom allocator functions.
+ *                          Set to NULL to use malloc() and free().
+ * \param       in          Beginning of the input buffer
+ * \param       in_pos      The next byte will be read from in[*in_pos].
+ *                          *in_pos is updated only if decoding succeeds.
+ * \param       in_size     Size of the input buffer; the first byte that
+ *                          won't be read is in[in_size].
+ * \param       out         Beginning of the output buffer
+ * \param       out_pos     The next byte will be written to out[*out_pos].
+ *                          *out_pos is updated only if encoding succeeds.
+ * \param       out_size    Size of the out buffer; the first byte into
+ *                          which no data is written to is out[out_size].
+ *
+ * \return      - LZMA_OK: Decoding was successful.
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_DATA_ERROR
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_BUF_ERROR: Output buffer was too small.
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_block_buffer_decode(
+		lzma_block *block, lzma_allocator *allocator,
+		const(ubyte)* in_, size_t *in_pos, size_t in_size,
+		ubyte* out_, size_t *out_pos, size_t out_size);

deimos/lzma_/check.d

@@ -0,0 +1,141 @@
+/**
+ * \file        lzma/check.h
+ * \brief       Integrity checks
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.check;
+import deimos.lzma;
+
+extern(C):
+
+/**
+ * \brief       Type of the integrity check (Check ID)
+ *
+ * The .xz format supports multiple types of checks that are calculated
+ * from the uncompressed data. They vary in both speed and ability to
+ * detect errors.
+ */
+enum lzma_check
+{
+	LZMA_CHECK_NONE     = 0,
+		/**<
+		 * No Check is calculated.
+		 *
+		 * Size of the Check field: 0 bytes
+		 */
+
+	LZMA_CHECK_CRC32    = 1,
+		/**<
+		 * CRC32 using the polynomial from the IEEE 802.3 standard
+		 *
+		 * Size of the Check field: 4 bytes
+		 */
+
+	LZMA_CHECK_CRC64    = 4,
+		/**<
+		 * CRC64 using the polynomial from the ECMA-182 standard
+		 *
+		 * Size of the Check field: 8 bytes
+		 */
+
+	LZMA_CHECK_SHA256   = 10
+}
+
+
+/**
+ * \brief       Maximum valid Check ID
+ *
+ * The .xz file format specification specifies 16 Check IDs (0-15). Some
+ * of them are only reserved, that is, no actual Check algorithm has been
+ * assigned. When decoding, liblzma still accepts unknown Check IDs for
+ * future compatibility. If a valid but unsupported Check ID is detected,
+ * liblzma can indicate a warning; see the flags LZMA_TELL_NO_CHECK,
+ * LZMA_TELL_UNSUPPORTED_CHECK, and LZMA_TELL_ANY_CHECK in container.h.
+ */
+enum LZMA_CHECK_ID_MAX = 15;
+
+
+/**
+ * \brief       Test if the given Check ID is supported
+ *
+ * Return true if the given Check ID is supported by this liblzma build.
+ * Otherwise false is returned. It is safe to call this with a value that
+ * is not in the range [0, 15]; in that case the return value is always false.
+ *
+ * You can assume that LZMA_CHECK_NONE and LZMA_CHECK_CRC32 are always
+ * supported (even if liblzma is built with limited features).
+ */
+nothrow lzma_bool lzma_check_is_supported(lzma_check check);
+
+
+/**
+ * \brief       Get the size of the Check field with the given Check ID
+ *
+ * Although not all Check IDs have a check algorithm associated, the size of
+ * every Check is already frozen. This function returns the size (in bytes) of
+ * the Check field with the specified Check ID. The values are:
+ * { 0, 4, 4, 4, 8, 8, 8, 16, 16, 16, 32, 32, 32, 64, 64, 64 }
+ *
+ * If the argument is not in the range [0, 15], UINT32_MAX is returned.
+ */
+nothrow uint lzma_check_size(lzma_check check);
+
+
+/**
+ * \brief       Maximum size of a Check field
+ */
+enum LZMA_CHECK_SIZE_MAX = 64;
+
+
+/**
+ * \brief       Calculate CRC32
+ *
+ * Calculate CRC32 using the polynomial from the IEEE 802.3 standard.
+ *
+ * \param       buf     Pointer to the input buffer
+ * \param       size    Size of the input buffer
+ * \param       crc     Previously returned CRC value. This is used to
+ *                      calculate the CRC of a big buffer in smaller chunks.
+ *                      Set to zero when starting a new calculation.
+ *
+ * \return      Updated CRC value, which can be passed to this function
+ *              again to continue CRC calculation.
+ */
+nothrow pure uint lzma_crc32(
+		const(ubyte)* buf, size_t size, uint crc);
+
+
+/**
+ * \brief       Calculate CRC64
+ *
+ * Calculate CRC64 using the polynomial from the ECMA-182 standard.
+ *
+ * This function is used similarly to lzma_crc32(). See its documentation.
+ */
+nothrow pure ulong lzma_crc64(
+		const(ubyte)* buf, size_t size, ulong crc);
+
+
+/*
+ * SHA-256 functions are currently not exported to public API.
+ * Contact Lasse Collin if you think it should be.
+ */
+
+
+/**
+ * \brief       Get the type of the integrity check
+ *
+ * This function can be called only immediately after lzma_code() has
+ * returned LZMA_NO_CHECK, LZMA_UNSUPPORTED_CHECK, or LZMA_GET_CHECK.
+ * Calling this function in any other situation has undefined behavior.
+ */
+nothrow lzma_check lzma_get_check(const lzma_stream *strm);

deimos/lzma_/container.d

@@ -0,0 +1,413 @@
+/**
+ * \file        lzma/container.h
+ * \brief       File formats
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.container;
+import deimos.lzma;
+
+extern(C):
+
+/************
+ * Encoding *
+ ************/
+
+/**
+ * \brief       Default compression preset
+ *
+ * It's not straightforward to recommend a default preset, because in some
+ * cases keeping the resource usage relatively low is more important that
+ * getting the maximum compression ratio.
+ */
+enum uint LZMA_PRESET_DEFAULT = 6U;
+
+
+/**
+ * \brief       Mask for preset level
+ *
+ * This is useful only if you need to extract the level from the preset
+ * variable. That should be rare.
+ */
+enum uint LZMA_PRESET_LEVEL_MASK = 0x1FU;
+
+
+/*
+ * Preset flags
+ *
+ * Currently only one flag is defined.
+ */
+
+/**
+ * \brief       Extreme compression preset
+ *
+ * This flag modifies the preset to make the encoding significantly slower
+ * while improving the compression ratio only marginally. This is useful
+ * when you don't mind wasting time to get as small result as possible.
+ *
+ * This flag doesn't affect the memory usage requirements of the decoder (at
+ * least not significantly). The memory usage of the encoder may be increased
+ * a little but only at the lowest preset levels (0-3).
+ */
+enum uint LZMA_PRESET_EXTREME = (1U << 31);
+
+
+/**
+ * \brief       Calculate approximate memory usage of easy encoder
+ *
+ * This function is a wrapper for lzma_raw_encoder_memusage().
+ *
+ * \param       preset  Compression preset (level and possible flags)
+ *
+ * \return      Number of bytes of memory required for the given
+ *              preset when encoding. If an error occurs, for example
+ *              due to unsupported preset, UINT64_MAX is returned.
+ */
+nothrow pure ulong lzma_easy_encoder_memusage(uint preset);
+
+
+/**
+ * \brief       Calculate approximate decoder memory usage of a preset
+ *
+ * This function is a wrapper for lzma_raw_decoder_memusage().
+ *
+ * \param       preset  Compression preset (level and possible flags)
+ *
+ * \return      Number of bytes of memory required to decompress a file
+ *              that was compressed using the given preset. If an error
+ *              occurs, for example due to unsupported preset, UINT64_MAX
+ *              is returned.
+ */
+nothrow pure ulong lzma_easy_decoder_memusage(uint preset);
+
+
+/**
+ * \brief       Initialize .xz Stream encoder using a preset number
+ *
+ * This function is intended for those who just want to use the basic features
+ * if liblzma (that is, most developers out there).
+ *
+ * \param       strm    Pointer to lzma_stream that is at least initialized
+ *                      with LZMA_STREAM_INIT.
+ * \param       preset  Compression preset to use. A preset consist of level
+ *                      number and zero or more flags. Usually flags aren't
+ *                      used, so preset is simply a number [0, 9] which match
+ *                      the options -0 ... -9 of the xz command line tool.
+ *                      Additional flags can be be set using bitwise-or with
+ *                      the preset level number, e.g. 6 | LZMA_PRESET_EXTREME.
+ * \param       check   Integrity check type to use. See check.h for available
+ *                      checks. The xz command line tool defaults to
+ *                      LZMA_CHECK_CRC64, which is a good choice if you are
+ *                      unsure. LZMA_CHECK_CRC32 is good too as long as the
+ *                      uncompressed file is not many gigabytes.
+ *
+ * \return      - LZMA_OK: Initialization succeeded. Use lzma_code() to
+ *                encode your data.
+ *              - LZMA_MEM_ERROR: Memory allocation failed.
+ *              - LZMA_OPTIONS_ERROR: The given compression preset is not
+ *                supported by this build of liblzma.
+ *              - LZMA_UNSUPPORTED_CHECK: The given check type is not
+ *                supported by this liblzma build.
+ *              - LZMA_PROG_ERROR: One or more of the parameters have values
+ *                that will never be valid. For example, strm == NULL.
+ *
+ * If initialization fails (return value is not LZMA_OK), all the memory
+ * allocated for *strm by liblzma is always freed. Thus, there is no need
+ * to call lzma_end() after failed initialization.
+ *
+ * If initialization succeeds, use lzma_code() to do the actual encoding.
+ * Valid values for `action' (the second argument of lzma_code()) are
+ * LZMA_RUN, LZMA_SYNC_FLUSH, LZMA_FULL_FLUSH, and LZMA_FINISH. In future,
+ * there may be compression levels or flags that don't support LZMA_SYNC_FLUSH.
+ */
+nothrow lzma_ret lzma_easy_encoder(
+		lzma_stream *strm, uint preset, lzma_check check);
+
+
+/**
+ * \brief       Single-call .xz Stream encoding using a preset number
+ *
+ * The maximum required output buffer size can be calculated with
+ * lzma_stream_buffer_bound().
+ *
+ * \param       preset      Compression preset to use. See the description
+ *                          in lzma_easy_encoder().
+ * \param       check       Type of the integrity check to calculate from
+ *                          uncompressed data.
+ * \param       allocator   lzma_allocator for custom allocator functions.
+ *                          Set to NULL to use malloc() and free().
+ * \param       in          Beginning of the input buffer
+ * \param       in_size     Size of the input buffer
+ * \param       out         Beginning of the output buffer
+ * \param       out_pos     The next byte will be written to out[*out_pos].
+ *                          *out_pos is updated only if encoding succeeds.
+ * \param       out_size    Size of the out buffer; the first byte into
+ *                          which no data is written to is out[out_size].
+ *
+ * \return      - LZMA_OK: Encoding was successful.
+ *              - LZMA_BUF_ERROR: Not enough output buffer space.
+ *              - LZMA_UNSUPPORTED_CHECK
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_DATA_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_easy_buffer_encode(
+		uint preset, lzma_check check,
+		lzma_allocator *allocator, const(ubyte)* in_, size_t in_size,
+		ubyte* out_, size_t *out_pos, size_t out_size);
+
+
+/**
+ * \brief       Initialize .xz Stream encoder using a custom filter chain
+ *
+ * \param       strm    Pointer to properly prepared lzma_stream
+ * \param       filters Array of filters. This must be terminated with
+ *                      filters[n].id = LZMA_VLI_UNKNOWN. See filter.h for
+ *                      more information.
+ * \param       check   Type of the integrity check to calculate from
+ *                      uncompressed data.
+ *
+ * \return      - LZMA_OK: Initialization was successful.
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_UNSUPPORTED_CHECK
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_stream_encoder(lzma_stream *strm,
+		const lzma_filter *filters, lzma_check check);
+
+
+/**
+ * \brief       Initialize .lzma encoder (legacy file format)
+ *
+ * The .lzma format is sometimes called the LZMA_Alone format, which is the
+ * reason for the name of this function. The .lzma format supports only the
+ * LZMA1 filter. There is no support for integrity checks like CRC32.
+ *
+ * Use this function if and only if you need to create files readable by
+ * legacy LZMA tools such as LZMA Utils 4.32.x. Moving to the .xz format
+ * is strongly recommended.
+ *
+ * The valid action values for lzma_code() are LZMA_RUN and LZMA_FINISH.
+ * No kind of flushing is supported, because the file format doesn't make
+ * it possible.
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_alone_encoder(
+		lzma_stream *strm, const lzma_options_lzma *options);
+
+
+/**
+ * \brief       Calculate output buffer size for single-call Stream encoder
+ *
+ * When trying to compress uncompressible data, the encoded size will be
+ * slightly bigger than the input data. This function calculates how much
+ * output buffer space is required to be sure that lzma_stream_buffer_encode()
+ * doesn't return LZMA_BUF_ERROR.
+ *
+ * The calculated value is not exact, but it is guaranteed to be big enough.
+ * The actual maximum output space required may be slightly smaller (up to
+ * about 100 bytes). This should not be a problem in practice.
+ *
+ * If the calculated maximum size doesn't fit into size_t or would make the
+ * Stream grow past LZMA_VLI_MAX (which should never happen in practice),
+ * zero is returned to indicate the error.
+ *
+ * \note        The limit calculated by this function applies only to
+ *              single-call encoding. Multi-call encoding may (and probably
+ *              will) have larger maximum expansion when encoding
+ *              uncompressible data. Currently there is no function to
+ *              calculate the maximum expansion of multi-call encoding.
+ */
+nothrow size_t lzma_stream_buffer_bound(size_t uncompressed_size);
+
+
+/**
+ * \brief       Single-call .xz Stream encoder
+ *
+ * \param       filters     Array of filters. This must be terminated with
+ *                          filters[n].id = LZMA_VLI_UNKNOWN. See filter.h
+ *                          for more information.
+ * \param       check       Type of the integrity check to calculate from
+ *                          uncompressed data.
+ * \param       allocator   lzma_allocator for custom allocator functions.
+ *                          Set to NULL to use malloc() and free().
+ * \param       in          Beginning of the input buffer
+ * \param       in_size     Size of the input buffer
+ * \param       out         Beginning of the output buffer
+ * \param       out_pos     The next byte will be written to out[*out_pos].
+ *                          *out_pos is updated only if encoding succeeds.
+ * \param       out_size    Size of the out buffer; the first byte into
+ *                          which no data is written to is out[out_size].
+ *
+ * \return      - LZMA_OK: Encoding was successful.
+ *              - LZMA_BUF_ERROR: Not enough output buffer space.
+ *              - LZMA_UNSUPPORTED_CHECK
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_DATA_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_stream_buffer_encode(
+		lzma_filter *filters, lzma_check check,
+		lzma_allocator *allocator, const(ubyte)* in_, size_t in_size,
+		ubyte* out_, size_t *out_pos, size_t out_size);
+
+
+/************
+ * Decoding *
+ ************/
+
+/**
+ * This flag makes lzma_code() return LZMA_NO_CHECK if the input stream
+ * being decoded has no integrity check. Note that when used with
+ * lzma_auto_decoder(), all .lzma files will trigger LZMA_NO_CHECK
+ * if LZMA_TELL_NO_CHECK is used.
+ */
+enum uint LZMA_TELL_NO_CHECK = 0x01U;
+
+
+/**
+ * This flag makes lzma_code() return LZMA_UNSUPPORTED_CHECK if the input
+ * stream has an integrity check, but the type of the integrity check is not
+ * supported by this liblzma version or build. Such files can still be
+ * decoded, but the integrity check cannot be verified.
+ */
+enum uint  LZMA_TELL_UNSUPPORTED_CHECK = 0x02U;
+
+
+/**
+ * This flag makes lzma_code() return LZMA_GET_CHECK as soon as the type
+ * of the integrity check is known. The type can then be got with
+ * lzma_get_check().
+ */
+enum uint LZMA_TELL_ANY_CHECK = 0x04U;
+
+
+/**
+ * This flag enables decoding of concatenated files with file formats that
+ * allow concatenating compressed files as is. From the formats currently
+ * supported by liblzma, only the .xz format allows concatenated files.
+ * Concatenated files are not allowed with the legacy .lzma format.
+ *
+ * This flag also affects the usage of the `action' argument for lzma_code().
+ * When LZMA_CONCATENATED is used, lzma_code() won't return LZMA_STREAM_END
+ * unless LZMA_FINISH is used as `action'. Thus, the application has to set
+ * LZMA_FINISH in the same way as it does when encoding.
+ *
+ * If LZMA_CONCATENATED is not used, the decoders still accept LZMA_FINISH
+ * as `action' for lzma_code(), but the usage of LZMA_FINISH isn't required.
+ */
+enum uint LZMA_CONCATENATED = 0x08U;
+
+
+/**
+ * \brief       Initialize .xz Stream decoder
+ *
+ * \param       strm        Pointer to properly prepared lzma_stream
+ * \param       memlimit    Memory usage limit as bytes. Use UINT64_MAX
+ *                          to effectively disable the limiter.
+ * \param       flags       Bitwise-or of zero or more of the decoder flags:
+ *                          LZMA_TELL_NO_CHECK, LZMA_TELL_UNSUPPORTED_CHECK,
+ *                          LZMA_TELL_ANY_CHECK, LZMA_CONCATENATED
+ *
+ * \return      - LZMA_OK: Initialization was successful.
+ *              - LZMA_MEM_ERROR: Cannot allocate memory.
+ *              - LZMA_OPTIONS_ERROR: Unsupported flags
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_stream_decoder(
+		lzma_stream *strm, ulong memlimit, uint flags);
+
+
+/**
+ * \brief       Decode .xz Streams and .lzma files with autodetection
+ *
+ * This decoder autodetects between the .xz and .lzma file formats, and
+ * calls lzma_stream_decoder() or lzma_alone_decoder() once the type
+ * of the input file has been detected.
+ *
+ * \param       strm        Pointer to properly prepared lzma_stream
+ * \param       memlimit    Memory usage limit as bytes. Use UINT64_MAX
+ *                          to effectively disable the limiter.
+ * \param       flags       Bitwise-or of flags, or zero for no flags.
+ *
+ * \return      - LZMA_OK: Initialization was successful.
+ *              - LZMA_MEM_ERROR: Cannot allocate memory.
+ *              - LZMA_OPTIONS_ERROR: Unsupported flags
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_auto_decoder(
+		lzma_stream *strm, ulong memlimit, uint flags);
+
+
+/**
+ * \brief       Initialize .lzma decoder (legacy file format)
+ *
+ * Valid `action' arguments to lzma_code() are LZMA_RUN and LZMA_FINISH.
+ * There is no need to use LZMA_FINISH, but allowing it may simplify
+ * certain types of applications.
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_alone_decoder(
+		lzma_stream *strm, ulong memlimit);
+
+
+/**
+ * \brief       Single-call .xz Stream decoder
+ *
+ * \param       memlimit    Pointer to how much memory the decoder is allowed
+ *                          to allocate. The value pointed by this pointer is
+ *                          modified if and only if LZMA_MEMLIMIT_ERROR is
+ *                          returned.
+ * \param       flags       Bitwise-or of zero or more of the decoder flags:
+ *                          LZMA_TELL_NO_CHECK, LZMA_TELL_UNSUPPORTED_CHECK,
+ *                          LZMA_CONCATENATED. Note that LZMA_TELL_ANY_CHECK
+ *                          is not allowed and will return LZMA_PROG_ERROR.
+ * \param       allocator   lzma_allocator for custom allocator functions.
+ *                          Set to NULL to use malloc() and free().
+ * \param       in          Beginning of the input buffer
+ * \param       in_pos      The next byte will be read from in[*in_pos].
+ *                          *in_pos is updated only if decoding succeeds.
+ * \param       in_size     Size of the input buffer; the first byte that
+ *                          won't be read is in[in_size].
+ * \param       out         Beginning of the output buffer
+ * \param       out_pos     The next byte will be written to out[*out_pos].
+ *                          *out_pos is updated only if decoding succeeds.
+ * \param       out_size    Size of the out buffer; the first byte into
+ *                          which no data is written to is out[out_size].
+ *
+ * \return      - LZMA_OK: Decoding was successful.
+ *              - LZMA_FORMAT_ERROR
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_DATA_ERROR
+ *              - LZMA_NO_CHECK: This can be returned only if using
+ *                the LZMA_TELL_NO_CHECK flag.
+ *              - LZMA_UNSUPPORTED_CHECK: This can be returned only if using
+ *                the LZMA_TELL_UNSUPPORTED_CHECK flag.
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_MEMLIMIT_ERROR: Memory usage limit was reached.
+ *                The minimum required memlimit value was stored to *memlimit.
+ *              - LZMA_BUF_ERROR: Output buffer was too small.
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_stream_buffer_decode(
+		ulong *memlimit, uint flags, lzma_allocator *allocator,
+		const (ubyte)* in_, size_t *in_pos, size_t in_size,
+		ubyte* out_, size_t *out_pos, size_t out_size);

deimos/lzma_/delta.d

@@ -0,0 +1,79 @@
+/**
+ * \file        lzma/delta.h
+ * \brief       Delta filter
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.delta;
+import deimos.lzma;
+
+extern(C):
+
+/**
+ * \brief       Filter ID
+ *
+ * Filter ID of the Delta filter. This is used as lzma_filter.id.
+ */
+enum LZMA_FILTER_DELTA = 0x03UL;
+
+
+/**
+ * \brief       Type of the delta calculation
+ *
+ * Currently only byte-wise delta is supported. Other possible types could
+ * be, for example, delta of 16/32/64-bit little/big endian integers, but
+ * these are not currently planned since byte-wise delta is almost as good.
+ */
+enum lzma_delta_type
+{
+	LZMA_DELTA_TYPE_BYTE
+}
+
+
+/**
+ * \brief       Options for the Delta filter
+ *
+ * These options are needed by both encoder and decoder.
+ */
+struct lzma_options_delta
+{
+	/** For now, this must always be LZMA_DELTA_TYPE_BYTE. */
+	lzma_delta_type type;
+
+	/**
+	 * \brief       Delta distance
+	 *
+	 * With the only currently supported type, LZMA_DELTA_TYPE_BYTE,
+	 * the distance is as bytes.
+	 *
+	 * Examples:
+	 *  - 16-bit stereo audio: distance = 4 bytes
+	 *  - 24-bit RGB image data: distance = 3 bytes
+	 */
+	uint dist;
+	enum LZMA_DELTA_DIST_MIN = 1;
+	enum LZMA_DELTA_DIST_MAX = 256;
+
+	/*
+	 * Reserved space to allow possible future extensions without
+	 * breaking the ABI. You should not touch these, because the names
+	 * of these variables may change. These are and will never be used
+	 * when type is LZMA_DELTA_TYPE_BYTE, so it is safe to leave these
+	 * uninitialized.
+	 */
+	uint reserved_int1;
+	uint reserved_int2;
+	uint reserved_int3;
+	uint reserved_int4;
+	void *reserved_ptr1;
+	void *reserved_ptr2;
+
+}

deimos/lzma_/filter.d

@@ -0,0 +1,416 @@
+/**
+ * \file        lzma/filter.h
+ * \brief       Common filter related types and functions
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.filter;
+import deimos.lzma;
+
+extern(C):
+
+/**
+ * \brief       Maximum number of filters in a chain
+ *
+ * A filter chain can have 1-4 filters, of which three are allowed to change
+ * the size of the data. Usually only one or two filters are needed.
+ */
+enum LZMA_FILTERS_MAX = 4;
+
+
+/**
+ * \brief       Filter options
+ *
+ * This structure is used to pass Filter ID and a pointer filter's
+ * options to liblzma. A few functions work with a single lzma_filter
+ * structure, while most functions expect a filter chain.
+ *
+ * A filter chain is indicated with an array of lzma_filter structures.
+ * The array is terminated with .id = LZMA_VLI_UNKNOWN. Thus, the filter
+ * array must have LZMA_FILTERS_MAX + 1 elements (that is, five) to
+ * be able to hold any arbitrary filter chain. This is important when
+ * using lzma_block_header_decode() from block.h, because too small
+ * array would make liblzma write past the end of the filters array.
+ */
+struct lzma_filter
+{
+	/**
+	 * \brief       Filter ID
+	 *
+	 * Use constants whose name begin with `LZMA_FILTER_' to specify
+	 * different filters. In an array of lzma_filter structures, use
+	 * LZMA_VLI_UNKNOWN to indicate end of filters.
+	 *
+	 * \note        This is not an enum, because on some systems enums
+	 *              cannot be 64-bit.
+	 */
+	lzma_vli id;
+
+	/**
+	 * \brief       Pointer to filter-specific options structure
+	 *
+	 * If the filter doesn't need options, set this to NULL. If id is
+	 * set to LZMA_VLI_UNKNOWN, options is ignored, and thus
+	 * doesn't need be initialized.
+	 */
+	void *options;
+
+}
+
+
+/**
+ * \brief       Test if the given Filter ID is supported for encoding
+ *
+ * Return true if the give Filter ID is supported for encoding by this
+ * liblzma build. Otherwise false is returned.
+ *
+ * There is no way to list which filters are available in this particular
+ * liblzma version and build. It would be useless, because the application
+ * couldn't know what kind of options the filter would need.
+ */
+nothrow lzma_bool lzma_filter_encoder_is_supported(lzma_vli id);
+
+
+/**
+ * \brief       Test if the given Filter ID is supported for decoding
+ *
+ * Return true if the give Filter ID is supported for decoding by this
+ * liblzma build. Otherwise false is returned.
+ */
+nothrow lzma_bool lzma_filter_decoder_is_supported(lzma_vli id);
+
+
+/**
+ * \brief       Copy the filters array
+ *
+ * Copy the Filter IDs and filter-specific options from src to dest.
+ * Up to LZMA_FILTERS_MAX filters are copied, plus the terminating
+ * .id == LZMA_VLI_UNKNOWN. Thus, dest should have at least
+ * LZMA_FILTERS_MAX + 1 elements space unless the caller knows that
+ * src is smaller than that.
+ *
+ * Unless the filter-specific options is NULL, the Filter ID has to be
+ * supported by liblzma, because liblzma needs to know the size of every
+ * filter-specific options structure. The filter-specific options are not
+ * validated. If options is NULL, any unsupported Filter IDs are copied
+ * without returning an error.
+ *
+ * Old filter-specific options in dest are not freed, so dest doesn't
+ * need to be initialized by the caller in any way.
+ *
+ * If an error occurs, memory possibly already allocated by this function
+ * is always freed.
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_OPTIONS_ERROR: Unsupported Filter ID and its options
+ *                is not NULL.
+ *              - LZMA_PROG_ERROR: src or dest is NULL.
+ */
+nothrow lzma_ret lzma_filters_copy(const lzma_filter*src,
+		lzma_filter *dest, lzma_allocator *allocator);
+
+
+/**
+ * \brief       Calculate approximate memory requirements for raw encoder
+ *
+ * This function can be used to calculate the memory requirements for
+ * Block and Stream encoders too because Block and Stream encoders don't
+ * need significantly more memory than raw encoder.
+ *
+ * \param       filters     Array of filters terminated with
+ *                          .id == LZMA_VLI_UNKNOWN.
+ *
+ * \return      Number of bytes of memory required for the given
+ *              filter chain when encoding. If an error occurs,
+ *              for example due to unsupported filter chain,
+ *              UINT64_MAX is returned.
+ */
+pure nothrow ulong lzma_raw_encoder_memusage(const lzma_filter *filters);
+
+
+/**
+ * \brief       Calculate approximate memory requirements for raw decoder
+ *
+ * This function can be used to calculate the memory requirements for
+ * Block and Stream decoders too because Block and Stream decoders don't
+ * need significantly more memory than raw decoder.
+ *
+ * \param       filters     Array of filters terminated with
+ *                          .id == LZMA_VLI_UNKNOWN.
+ *
+ * \return      Number of bytes of memory required for the given
+ *              filter chain when decoding. If an error occurs,
+ *              for example due to unsupported filter chain,
+ *              UINT64_MAX is returned.
+ */
+nothrow pure ulong lzma_raw_decoder_memusage(const lzma_filter *filters);
+
+
+/**
+ * \brief       Initialize raw encoder
+ *
+ * This function may be useful when implementing custom file formats.
+ *
+ * \param       strm    Pointer to properly prepared lzma_stream
+ * \param       filters Array of lzma_filter structures. The end of the
+ *                      array must be marked with .id = LZMA_VLI_UNKNOWN.
+ *
+ * The `action' with lzma_code() can be LZMA_RUN, LZMA_SYNC_FLUSH (if the
+ * filter chain supports it), or LZMA_FINISH.
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_raw_encoder(
+		lzma_stream *strm, const lzma_filter *filters);
+
+
+/**
+ * \brief       Initialize raw decoder
+ *
+ * The initialization of raw decoder goes similarly to raw encoder.
+ *
+ * The `action' with lzma_code() can be LZMA_RUN or LZMA_FINISH. Using
+ * LZMA_FINISH is not required, it is supported just for convenience.
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_raw_decoder(
+		lzma_stream *strm, const lzma_filter *filters);
+
+
+/**
+ * \brief       Update the filter chain in the encoder
+ *
+ * This function is for advanced users only. This function has two slightly
+ * different purposes:
+ *
+ *  - After LZMA_FULL_FLUSH when using Stream encoder: Set a new filter
+ *    chain, which will be used starting from the next Block.
+ *
+ *  - After LZMA_SYNC_FLUSH using Raw, Block, or Stream encoder: Change
+ *    the filter-specific options in the middle of encoding. The actual
+ *    filters in the chain (Filter IDs) cannot be changed. In the future,
+ *    it might become possible to change the filter options without
+ *    using LZMA_SYNC_FLUSH.
+ *
+ * While rarely useful, this function may be called also when no data has
+ * been compressed yet. In that case, this function will behave as if
+ * LZMA_FULL_FLUSH (Stream encoder) or LZMA_SYNC_FLUSH (Raw or Block
+ * encoder) had been used right before calling this function.
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_MEMLIMIT_ERROR
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_filters_update(
+		lzma_stream *strm, const lzma_filter *filters);
+
+
+/**
+ * \brief       Single-call raw encoder
+ *
+ * \param       filters     Array of lzma_filter structures. The end of the
+ *                          array must be marked with .id = LZMA_VLI_UNKNOWN.
+ * \param       allocator   lzma_allocator for custom allocator functions.
+ *                          Set to NULL to use malloc() and free().
+ * \param       in          Beginning of the input buffer
+ * \param       in_size     Size of the input buffer
+ * \param       out         Beginning of the output buffer
+ * \param       out_pos     The next byte will be written to out[*out_pos].
+ *                          *out_pos is updated only if encoding succeeds.
+ * \param       out_size    Size of the out buffer; the first byte into
+ *                          which no data is written to is out[out_size].
+ *
+ * \return      - LZMA_OK: Encoding was successful.
+ *              - LZMA_BUF_ERROR: Not enough output buffer space.
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_DATA_ERROR
+ *              - LZMA_PROG_ERROR
+ *
+ * \note        There is no function to calculate how big output buffer
+ *              would surely be big enough. (lzma_stream_buffer_bound()
+ *              works only for lzma_stream_buffer_encode(); raw encoder
+ *              won't necessarily meet that bound.)
+ */
+nothrow lzma_ret lzma_raw_buffer_encode(
+		const lzma_filter *filters, lzma_allocator *allocator,
+		const(ubyte) *in_, size_t in_size, ubyte *out_,
+		size_t *out_pos, size_t out_size);
+
+
+/**
+ * \brief       Single-call raw decoder
+ *
+ * \param       filters     Array of lzma_filter structures. The end of the
+ *                          array must be marked with .id = LZMA_VLI_UNKNOWN.
+ * \param       allocator   lzma_allocator for custom allocator functions.
+ *                          Set to NULL to use malloc() and free().
+ * \param       in          Beginning of the input buffer
+ * \param       in_pos      The next byte will be read from in[*in_pos].
+ *                          *in_pos is updated only if decoding succeeds.
+ * \param       in_size     Size of the input buffer; the first byte that
+ *                          won't be read is in[in_size].
+ * \param       out         Beginning of the output buffer
+ * \param       out_pos     The next byte will be written to out[*out_pos].
+ *                          *out_pos is updated only if encoding succeeds.
+ * \param       out_size    Size of the out buffer; the first byte into
+ *                          which no data is written to is out[out_size].
+ */
+nothrow lzma_ret lzma_raw_buffer_decode(const lzma_filter *filters,
+		lzma_allocator *allocator,
+		const(ubyte) *in_, size_t *in_pos, size_t in_size,
+		ubyte *out_, size_t *out_pos, size_t out_size);
+
+
+/**
+ * \brief       Get the size of the Filter Properties field
+ *
+ * This function may be useful when implementing custom file formats
+ * using the raw encoder and decoder.
+ *
+ * \param       size    Pointer to uint32_t to hold the size of the properties
+ * \param       filter  Filter ID and options (the size of the properties may
+ *                      vary depending on the options)
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_PROG_ERROR
+ *
+ * \note        This function validates the Filter ID, but does not
+ *              necessarily validate the options. Thus, it is possible
+ *              that this returns LZMA_OK while the following call to
+ *              lzma_properties_encode() returns LZMA_OPTIONS_ERROR.
+ */
+nothrow lzma_ret lzma_properties_size(
+		uint *size, const lzma_filter *filter);
+
+
+/**
+ * \brief       Encode the Filter Properties field
+ *
+ * \param       filter  Filter ID and options
+ * \param       props   Buffer to hold the encoded options. The size of
+ *                      buffer must have been already determined with
+ *                      lzma_properties_size().
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_PROG_ERROR
+ *
+ * \note        Even this function won't validate more options than actually
+ *              necessary. Thus, it is possible that encoding the properties
+ *              succeeds but using the same options to initialize the encoder
+ *              will fail.
+ *
+ * \note        If lzma_properties_size() indicated that the size
+ *              of the Filter Properties field is zero, calling
+ *              lzma_properties_encode() is not required, but it
+ *              won't do any harm either.
+ */
+nothrow lzma_ret lzma_properties_encode(
+		const lzma_filter *filter, ubyte *props);
+
+
+/**
+ * \brief       Decode the Filter Properties field
+ *
+ * \param       filter      filter->id must have been set to the correct
+ *                          Filter ID. filter->options doesn't need to be
+ *                          initialized (it's not freed by this function). The
+ *                          decoded options will be stored to filter->options.
+ *                          filter->options is set to NULL if there are no
+ *                          properties or if an error occurs.
+ * \param       allocator   Custom memory allocator used to allocate the
+ *                          options. Set to NULL to use the default malloc(),
+ *                          and in case of an error, also free().
+ * \param       props       Input buffer containing the properties.
+ * \param       props_size  Size of the properties. This must be the exact
+ *                          size; giving too much or too little input will
+ *                          return LZMA_OPTIONS_ERROR.
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_MEM_ERROR
+ */
+nothrow lzma_ret lzma_properties_decode(
+		lzma_filter *filter, lzma_allocator *allocator,
+		const ubyte *props, size_t props_size);
+
+
+/**
+ * \brief       Calculate encoded size of a Filter Flags field
+ *
+ * Knowing the size of Filter Flags is useful to know when allocating
+ * memory to hold the encoded Filter Flags.
+ *
+ * \param       size    Pointer to integer to hold the calculated size
+ * \param       filter  Filter ID and associated options whose encoded
+ *                      size is to be calculated
+ *
+ * \return      - LZMA_OK: *size set successfully. Note that this doesn't
+ *                guarantee that filter->options is valid, thus
+ *                lzma_filter_flags_encode() may still fail.
+ *              - LZMA_OPTIONS_ERROR: Unknown Filter ID or unsupported options.
+ *              - LZMA_PROG_ERROR: Invalid options
+ *
+ * \note        If you need to calculate size of List of Filter Flags,
+ *              you need to loop over every lzma_filter entry.
+ */
+nothrow lzma_ret lzma_filter_flags_size(
+		uint *size, const lzma_filter *filter);
+
+
+/**
+ * \brief       Encode Filter Flags into given buffer
+ *
+ * In contrast to some functions, this doesn't allocate the needed buffer.
+ * This is due to how this function is used internally by liblzma.
+ *
+ * \param       filter      Filter ID and options to be encoded
+ * \param       out         Beginning of the output buffer
+ * \param       out_pos     out[*out_pos] is the next write position. This
+ *                          is updated by the encoder.
+ * \param       out_size    out[out_size] is the first byte to not write.
+ *
+ * \return      - LZMA_OK: Encoding was successful.
+ *              - LZMA_OPTIONS_ERROR: Invalid or unsupported options.
+ *              - LZMA_PROG_ERROR: Invalid options or not enough output
+ *                buffer space (you should have checked it with
+ *                lzma_filter_flags_size()).
+ */
+nothrow lzma_ret lzma_filter_flags_encode(const lzma_filter *filter,
+		ubyte *out_, size_t *out_pos, size_t out_size);
+
+
+/**
+ * \brief       Decode Filter Flags from given buffer
+ *
+ * The decoded result is stored into *filter. The old value of
+ * filter->options is not free()d.
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_OPTIONS_ERROR
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_filter_flags_decode(
+		lzma_filter *filter, lzma_allocator *allocator,
+		const ubyte *in_, size_t *in_pos, size_t in_size);

deimos/lzma_/hardware.d

@@ -0,0 +1,50 @@
+/**
+ * \file        lzma/hardware.h
+ * \brief       Hardware information
+ *
+ * Since liblzma can consume a lot of system resources, it also provides
+ * ways to limit the resource usage. Applications linking against liblzma
+ * need to do the actual decisions how much resources to let liblzma to use.
+ * To ease making these decisions, liblzma provides functions to find out
+ * the relevant capabilities of the underlaying hardware. Currently there
+ * is only a function to find out the amount of RAM, but in the future there
+ * will be also a function to detect how many concurrent threads the system
+ * can run.
+ *
+ * \note        On some operating systems, these function may temporarily
+ *              load a shared library or open file descriptor(s) to find out
+ *              the requested hardware information. Unless the application
+ *              assumes that specific file descriptors are not touched by
+ *              other threads, this should have no effect on thread safety.
+ *              Possible operations involving file descriptors will restart
+ *              the syscalls if they return EINTR.
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.hardware;
+import deimos.lzma;
+
+extern(C):
+
+/**
+ * \brief       Get the total amount of physical memory (RAM) in bytes
+ *
+ * This function may be useful when determining a reasonable memory
+ * usage limit for decompressing or how much memory it is OK to use
+ * for compressing.
+ *
+ * \return      On success, the total amount of physical memory in bytes
+ *              is returned. If the amount of RAM cannot be determined,
+ *              zero is returned. This can happen if an error occurs
+ *              or if there is no code in liblzma to detect the amount
+ *              of RAM on the specific operating system.
+ */
+nothrow ulong lzma_physmem();

deimos/lzma_/index.d

@@ -0,0 +1,663 @@
+/**
+ * \file        lzma/index.h
+ * \brief       Handling of .xz Index and related information
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.index;
+import deimos.lzma;
+
+extern(C):
+
+/**
+ * \brief       Opaque data type to hold the Index(es) and other information
+ *
+ * lzma_index often holds just one .xz Index and possibly the Stream Flags
+ * of the same Stream and size of the Stream Padding field. However,
+ * multiple lzma_indexes can be concatenated with lzma_index_cat() and then
+ * there may be information about multiple Streams in the same lzma_index.
+ *
+ * Notes about thread safety: Only one thread may modify lzma_index at
+ * a time. All functions that take non-const pointer to lzma_index
+ * modify it. As long as no thread is modifying the lzma_index, getting
+ * information from the same lzma_index can be done from multiple threads
+ * at the same time with functions that take a const pointer to
+ * lzma_index or use lzma_index_iter. The same iterator must be used
+ * only by one thread at a time, of course, but there can be as many
+ * iterators for the same lzma_index as needed.
+ */
+struct lzma_index {};
+
+
+/**
+ * \brief       Iterator to get information about Blocks and Streams
+ */
+struct lzma_index_iter
+{
+	struct StreamStruct
+	{
+		/**
+		 * \brief       Pointer to Stream Flags
+		 *
+		 * This is NULL if Stream Flags have not been set for
+		 * this Stream with lzma_index_stream_flags().
+		 */
+		const lzma_stream_flags *flags;
+
+		const void *reserved_ptr1;
+		const void *reserved_ptr2;
+		const void *reserved_ptr3;
+
+		/**
+		 * \brief       Stream number in the lzma_index
+		 *
+		 * The first Stream is 1.
+		 */
+		lzma_vli number;
+
+		/**
+		 * \brief       Number of Blocks in the Stream
+		 *
+		 * If this is zero, the block structure below has
+		 * undefined values.
+		 */
+		lzma_vli block_count;
+
+		/**
+		 * \brief       Compressed start offset of this Stream
+		 *
+		 * The offset is relative to the beginning of the lzma_index
+		 * (i.e. usually the beginning of the .xz file).
+		 */
+		lzma_vli compressed_offset;
+
+		/**
+		 * \brief       Uncompressed start offset of this Stream
+		 *
+		 * The offset is relative to the beginning of the lzma_index
+		 * (i.e. usually the beginning of the .xz file).
+		 */
+		lzma_vli uncompressed_offset;
+
+		/**
+		 * \brief       Compressed size of this Stream
+		 *
+		 * This includes all headers except the possible
+		 * Stream Padding after this Stream.
+		 */
+		lzma_vli compressed_size;
+
+		/**
+		 * \brief       Uncompressed size of this Stream
+		 */
+		lzma_vli uncompressed_size;
+
+		/**
+		 * \brief       Size of Stream Padding after this Stream
+		 *
+		 * If it hasn't been set with lzma_index_stream_padding(),
+		 * this defaults to zero. Stream Padding is always
+		 * a multiple of four bytes.
+		 */
+		lzma_vli padding;
+
+		lzma_vli reserved_vli1;
+		lzma_vli reserved_vli2;
+		lzma_vli reserved_vli3;
+		lzma_vli reserved_vli4;
+	}
+	StreamStruct stream;
+
+	struct BlockStruct
+	{
+		/**
+		 * \brief       Block number in the file
+		 *
+		 * The first Block is 1.
+		 */
+		lzma_vli number_in_file;
+
+		/**
+		 * \brief       Compressed start offset of this Block
+		 *
+		 * This offset is relative to the beginning of the
+		 * lzma_index (i.e. usually the beginning of the .xz file).
+		 * Normally this is where you should seek in the .xz file
+		 * to start decompressing this Block.
+		 */
+		lzma_vli compressed_file_offset;
+
+		/**
+		 * \brief       Uncompressed start offset of this Block
+		 *
+		 * This offset is relative to the beginning of the lzma_index
+		 * (i.e. usually the beginning of the .xz file).
+		 *
+		 * When doing random-access reading, it is possible that
+		 * the target offset is not exactly at Block boundary. One
+		 * will need to compare the target offset against
+		 * uncompressed_file_offset or uncompressed_stream_offset,
+		 * and possibly decode and throw away some amount of data
+		 * before reaching the target offset.
+		 */
+		lzma_vli uncompressed_file_offset;
+
+		/**
+		 * \brief       Block number in this Stream
+		 *
+		 * The first Block is 1.
+		 */
+		lzma_vli number_in_stream;
+
+		/**
+		 * \brief       Compressed start offset of this Block
+		 *
+		 * This offset is relative to the beginning of the Stream
+		 * containing this Block.
+		 */
+		lzma_vli compressed_stream_offset;
+
+		/**
+		 * \brief       Uncompressed start offset of this Block
+		 *
+		 * This offset is relative to the beginning of the Stream
+		 * containing this Block.
+		 */
+		lzma_vli uncompressed_stream_offset;
+
+		/**
+		 * \brief       Uncompressed size of this Block
+		 *
+		 * You should pass this to the Block decoder if you will
+		 * decode this Block. It will allow the Block decoder to
+		 * validate the uncompressed size.
+		 */
+		lzma_vli uncompressed_size;
+
+		/**
+		 * \brief       Unpadded size of this Block
+		 *
+		 * You should pass this to the Block decoder if you will
+		 * decode this Block. It will allow the Block decoder to
+		 * validate the unpadded size.
+		 */
+		lzma_vli unpadded_size;
+
+		/**
+		 * \brief       Total compressed size
+		 *
+		 * This includes all headers and padding in this Block.
+		 * This is useful if you need to know how many bytes
+		 * the Block decoder will actually read.
+		 */
+		lzma_vli total_size;
+
+		lzma_vli reserved_vli1;
+		lzma_vli reserved_vli2;
+		lzma_vli reserved_vli3;
+		lzma_vli reserved_vli4;
+
+		const void *reserved_ptr1;
+		const void *reserved_ptr2;
+		const void *reserved_ptr3;
+		const void *reserved_ptr4;
+	}
+	BlockStruct block;
+
+	/*
+	 * Internal data which is used to store the state of the iterator.
+	 * The exact format may vary between liblzma versions, so don't
+	 * touch these in any way.
+	 */
+	union InternalData
+	{
+		const void *p;
+		size_t s;
+		lzma_vli v;
+	}
+	InternalData internal[6];
+}
+
+
+/**
+ * Operation mode for lzma_index_iter_next()
+ */
+enum lzma_index_iter_mode
+{
+	LZMA_INDEX_ITER_ANY             = 0,
+		/**<
+		 * \brief       Get the next Block or Stream
+		 *
+		 * Go to the next Block if the current Stream has at least
+		 * one Block left. Otherwise go to the next Stream even if
+		 * it has no Blocks. If the Stream has no Blocks
+		 * (lzma_index_iter.stream.block_count == 0),
+		 * lzma_index_iter.block will have undefined values.
+		 */
+
+	LZMA_INDEX_ITER_STREAM          = 1,
+		/**<
+		 * \brief       Get the next Stream
+		 *
+		 * Go to the next Stream even if the current Stream has
+		 * unread Blocks left. If the next Stream has at least one
+		 * Block, the iterator will point to the first Block.
+		 * If there are no Blocks, lzma_index_iter.block will have
+		 * undefined values.
+		 */
+
+	LZMA_INDEX_ITER_BLOCK           = 2,
+		/**<
+		 * \brief       Get the next Block
+		 *
+		 * Go to the next Block if the current Stream has at least
+		 * one Block left. If the current Stream has no Blocks left,
+		 * the next Stream with at least one Block is located and
+		 * the iterator will be made to point to the first Block of
+		 * that Stream.
+		 */
+
+	LZMA_INDEX_ITER_NONEMPTY_BLOCK  = 3
+
+}
+
+
+/**
+ * \brief       Calculate memory usage of lzma_index
+ *
+ * On disk, the size of the Index field depends on both the number of Records
+ * stored and how big values the Records store (due to variable-length integer
+ * encoding). When the Index is kept in lzma_index structure, the memory usage
+ * depends only on the number of Records/Blocks stored in the Index(es), and
+ * in case of concatenated lzma_indexes, the number of Streams. The size in
+ * RAM is almost always significantly bigger than in the encoded form on disk.
+ *
+ * This function calculates an approximate amount of memory needed hold
+ * the given number of Streams and Blocks in lzma_index structure. This
+ * value may vary between CPU architectures and also between liblzma versions
+ * if the internal implementation is modified.
+ */
+nothrow ulong lzma_index_memusage(
+		lzma_vli streams, lzma_vli blocks);
+
+
+/**
+ * \brief       Calculate the memory usage of an existing lzma_index
+ *
+ * This is a shorthand for lzma_index_memusage(lzma_index_stream_count(i),
+ * lzma_index_block_count(i)).
+ */
+nothrow ulong lzma_index_memused(const lzma_index *i);
+
+
+/**
+ * \brief       Allocate and initialize a new lzma_index structure
+ *
+ * \return      On success, a pointer to an empty initialized lzma_index is
+ *              returned. If allocation fails, NULL is returned.
+ */
+nothrow lzma_index* lzma_index_init(lzma_allocator *allocator);
+
+
+/**
+ * \brief       Deallocate lzma_index
+ *
+ * If i is NULL, this does nothing.
+ */
+nothrow void lzma_index_end(lzma_index *i, lzma_allocator *allocator);
+
+
+/**
+ * \brief       Add a new Block to lzma_index
+ *
+ * \param       i                 Pointer to a lzma_index structure
+ * \param       allocator         Pointer to lzma_allocator, or NULL to
+ *                                use malloc()
+ * \param       unpadded_size     Unpadded Size of a Block. This can be
+ *                                calculated with lzma_block_unpadded_size()
+ *                                after encoding or decoding the Block.
+ * \param       uncompressed_size Uncompressed Size of a Block. This can be
+ *                                taken directly from lzma_block structure
+ *                                after encoding or decoding the Block.
+ *
+ * Appending a new Block does not invalidate iterators. For example,
+ * if an iterator was pointing to the end of the lzma_index, after
+ * lzma_index_append() it is possible to read the next Block with
+ * an existing iterator.
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_DATA_ERROR: Compressed or uncompressed size of the
+ *                Stream or size of the Index field would grow too big.
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_index_append(
+		lzma_index *i, lzma_allocator *allocator,
+		lzma_vli unpadded_size, lzma_vli uncompressed_size);
+
+
+/**
+ * \brief       Set the Stream Flags
+ *
+ * Set the Stream Flags of the last (and typically the only) Stream
+ * in lzma_index. This can be useful when reading information from the
+ * lzma_index, because to decode Blocks, knowing the integrity check type
+ * is needed.
+ *
+ * The given Stream Flags are copied into internal preallocated structure
+ * in the lzma_index, thus the caller doesn't need to keep the *stream_flags
+ * available after calling this function.
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_OPTIONS_ERROR: Unsupported stream_flags->version.
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_index_stream_flags(
+		lzma_index *i, const lzma_stream_flags *stream_flags);
+
+
+/**
+ * \brief       Get the types of integrity Checks
+ *
+ * If lzma_index_stream_flags() is used to set the Stream Flags for
+ * every Stream, lzma_index_checks() can be used to get a bitmask to
+ * indicate which Check types have been used. It can be useful e.g. if
+ * showing the Check types to the user.
+ *
+ * The bitmask is 1 << check_id, e.g. CRC32 is 1 << 1 and SHA-256 is 1 << 10.
+ */
+nothrow pure uint lzma_index_checks(const lzma_index *i);
+
+
+/**
+ * \brief       Set the amount of Stream Padding
+ *
+ * Set the amount of Stream Padding of the last (and typically the only)
+ * Stream in the lzma_index. This is needed when planning to do random-access
+ * reading within multiple concatenated Streams.
+ *
+ * By default, the amount of Stream Padding is assumed to be zero bytes.
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_DATA_ERROR: The file size would grow too big.
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_index_stream_padding(
+		lzma_index *i, lzma_vli stream_padding);
+
+
+/**
+ * \brief       Get the number of Streams
+ */
+nothrow pure lzma_vli lzma_index_stream_count(const lzma_index *i);
+
+
+/**
+ * \brief       Get the number of Blocks
+ *
+ * This returns the total number of Blocks in lzma_index. To get number
+ * of Blocks in individual Streams, use lzma_index_iter.
+ */
+nothrow pure lzma_vli lzma_index_block_count(const lzma_index *i);
+
+
+/**
+ * \brief       Get the size of the Index field as bytes
+ *
+ * This is needed to verify the Backward Size field in the Stream Footer.
+ */
+nothrow pure lzma_vli lzma_index_size(const lzma_index *i);
+
+
+/**
+ * \brief       Get the total size of the Stream
+ *
+ * If multiple lzma_indexes have been combined, this works as if the Blocks
+ * were in a single Stream. This is useful if you are going to combine
+ * Blocks from multiple Streams into a single new Stream.
+ */
+nothrow pure lzma_vli lzma_index_stream_size(const lzma_index *i);
+
+
+/**
+ * \brief       Get the total size of the Blocks
+ *
+ * This doesn't include the Stream Header, Stream Footer, Stream Padding,
+ * or Index fields.
+ */
+nothrow pure lzma_vli lzma_index_total_size(const lzma_index *i);
+
+
+/**
+ * \brief       Get the total size of the file
+ *
+ * When no lzma_indexes have been combined with lzma_index_cat() and there is
+ * no Stream Padding, this function is identical to lzma_index_stream_size().
+ * If multiple lzma_indexes have been combined, this includes also the headers
+ * of each separate Stream and the possible Stream Padding fields.
+ */
+nothrow pure lzma_vli lzma_index_file_size(const lzma_index *i);
+
+
+/**
+ * \brief       Get the uncompressed size of the file
+ */
+nothrow pure lzma_vli lzma_index_uncompressed_size(const lzma_index *i);
+
+
+/**
+ * \brief       Initialize an iterator
+ *
+ * \param       iter    Pointer to a lzma_index_iter structure
+ * \param       i       lzma_index to which the iterator will be associated
+ *
+ * This function associates the iterator with the given lzma_index, and calls
+ * lzma_index_iter_rewind() on the iterator.
+ *
+ * This function doesn't allocate any memory, thus there is no
+ * lzma_index_iter_end(). The iterator is valid as long as the
+ * associated lzma_index is valid, that is, until lzma_index_end() or
+ * using it as source in lzma_index_cat(). Specifically, lzma_index doesn't
+ * become invalid if new Blocks are added to it with lzma_index_append() or
+ * if it is used as the destination in lzma_index_cat().
+ *
+ * It is safe to make copies of an initialized lzma_index_iter, for example,
+ * to easily restart reading at some particular position.
+ */
+nothrow void lzma_index_iter_init(
+		lzma_index_iter *iter, const lzma_index *i);
+
+
+/**
+ * \brief       Rewind the iterator
+ *
+ * Rewind the iterator so that next call to lzma_index_iter_next() will
+ * return the first Block or Stream.
+ */
+nothrow void lzma_index_iter_rewind(lzma_index_iter *iter);
+
+
+/**
+ * \brief       Get the next Block or Stream
+ *
+ * \param       iter    Iterator initialized with lzma_index_iter_init()
+ * \param       mode    Specify what kind of information the caller wants
+ *                      to get. See lzma_index_iter_mode for details.
+ *
+ * \return      If next Block or Stream matching the mode was found, *iter
+ *              is updated and this function returns false. If no Block or
+ *              Stream matching the mode is found, *iter is not modified
+ *              and this function returns true. If mode is set to an unknown
+ *              value, *iter is not modified and this function returns true.
+ */
+nothrow lzma_bool lzma_index_iter_next(
+		lzma_index_iter *iter, lzma_index_iter_mode mode);
+
+
+/**
+ * \brief       Locate a Block
+ *
+ * If it is possible to seek in the .xz file, it is possible to parse
+ * the Index field(s) and use lzma_index_iter_locate() to do random-access
+ * reading with granularity of Block size.
+ *
+ * \param       iter    Iterator that was earlier initialized with
+ *                      lzma_index_iter_init().
+ * \param       target  Uncompressed target offset which the caller would
+ *                      like to locate from the Stream
+ *
+ * If the target is smaller than the uncompressed size of the Stream (can be
+ * checked with lzma_index_uncompressed_size()):
+ *  - Information about the Stream and Block containing the requested
+ *    uncompressed offset is stored into *iter.
+ *  - Internal state of the iterator is adjusted so that
+ *    lzma_index_iter_next() can be used to read subsequent Blocks or Streams.
+ *  - This function returns false.
+ *
+ * If target is greater than the uncompressed size of the Stream, *iter
+ * is not modified, and this function returns true.
+ */
+nothrow lzma_bool lzma_index_iter_locate(
+		lzma_index_iter *iter, lzma_vli target);
+
+
+/**
+ * \brief       Concatenate lzma_indexes
+ *
+ * Concatenating lzma_indexes is useful when doing random-access reading in
+ * multi-Stream .xz file, or when combining multiple Streams into single
+ * Stream.
+ *
+ * \param       dest      lzma_index after which src is appended
+ * \param       src       lzma_index to be appended after dest. If this
+ *                        function succeeds, the memory allocated for src
+ *                        is freed or moved to be part of dest, and all
+ *                        iterators pointing to src will become invalid.
+ * \param       allocator Custom memory allocator; can be NULL to use
+ *                        malloc() and free().
+ *
+ * \return      - LZMA_OK: lzma_indexes were concatenated successfully.
+ *                src is now a dangling pointer.
+ *              - LZMA_DATA_ERROR: *dest would grow too big.
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_index_cat(
+		lzma_index *dest, lzma_index *src, lzma_allocator *allocator);
+
+
+/**
+ * \brief       Duplicate lzma_index
+ *
+ * \return      A copy of the lzma_index, or NULL if memory allocation failed.
+ */
+nothrow lzma_index * lzma_index_dup(
+		const lzma_index *i, lzma_allocator *allocator);
+
+
+/**
+ * \brief       Initialize .xz Index encoder
+ *
+ * \param       strm        Pointer to properly prepared lzma_stream
+ * \param       i           Pointer to lzma_index which should be encoded.
+ *
+ * The valid `action' values for lzma_code() are LZMA_RUN and LZMA_FINISH.
+ * It is enough to use only one of them (you can choose freely; use LZMA_RUN
+ * to support liblzma versions older than 5.0.0).
+ *
+ * \return      - LZMA_OK: Initialization succeeded, continue with lzma_code().
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_index_encoder(
+		lzma_stream *strm, const lzma_index *i);
+
+
+/**
+ * \brief       Initialize .xz Index decoder
+ *
+ * \param       strm        Pointer to properly prepared lzma_stream
+ * \param       i           The decoded Index will be made available via
+ *                          this pointer. Initially this function will
+ *                          set *i to NULL (the old value is ignored). If
+ *                          decoding succeeds (lzma_code() returns
+ *                          LZMA_STREAM_END), *i will be set to point
+ *                          to a new lzma_index, which the application
+ *                          has to later free with lzma_index_end().
+ * \param       memlimit    How much memory the resulting lzma_index is
+ *                          allowed to require.
+ *
+ * The valid `action' values for lzma_code() are LZMA_RUN and LZMA_FINISH.
+ * It is enough to use only one of them (you can choose freely; use LZMA_RUN
+ * to support liblzma versions older than 5.0.0).
+ *
+ * \return      - LZMA_OK: Initialization succeeded, continue with lzma_code().
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_MEMLIMIT_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_index_decoder(
+		lzma_stream *strm, lzma_index **i, ulong memlimit);
+
+
+/**
+ * \brief       Single-call .xz Index encoder
+ *
+ * \param       i         lzma_index to be encoded
+ * \param       out       Beginning of the output buffer
+ * \param       out_pos   The next byte will be written to out[*out_pos].
+ *                        *out_pos is updated only if encoding succeeds.
+ * \param       out_size  Size of the out buffer; the first byte into
+ *                        which no data is written to is out[out_size].
+ *
+ * \return      - LZMA_OK: Encoding was successful.
+ *              - LZMA_BUF_ERROR: Output buffer is too small. Use
+ *                lzma_index_size() to find out how much output
+ *                space is needed.
+ *              - LZMA_PROG_ERROR
+ *
+ * \note        This function doesn't take allocator argument since all
+ *              the internal data is allocated on stack.
+ */
+nothrow lzma_ret lzma_index_buffer_encode(const lzma_index *i,
+		ubyte *out_, size_t *out_pos, size_t out_size);
+
+
+/**
+ * \brief       Single-call .xz Index decoder
+ *
+ * \param       i           If decoding succeeds, *i will point to a new
+ *                          lzma_index, which the application has to
+ *                          later free with lzma_index_end(). If an error
+ *                          occurs, *i will be NULL. The old value of *i
+ *                          is always ignored and thus doesn't need to be
+ *                          initialized by the caller.
+ * \param       memlimit    Pointer to how much memory the resulting
+ *                          lzma_index is allowed to require. The value
+ *                          pointed by this pointer is modified if and only
+ *                          if LZMA_MEMLIMIT_ERROR is returned.
+ * \param       allocator   Pointer to lzma_allocator, or NULL to use malloc()
+ * \param       in          Beginning of the input buffer
+ * \param       in_pos      The next byte will be read from in[*in_pos].
+ *                          *in_pos is updated only if decoding succeeds.
+ * \param       in_size     Size of the input buffer; the first byte that
+ *                          won't be read is in[in_size].
+ *
+ * \return      - LZMA_OK: Decoding was successful.
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_MEMLIMIT_ERROR: Memory usage limit was reached.
+ *                The minimum required memlimit value was stored to *memlimit.
+ *              - LZMA_DATA_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_index_buffer_decode(lzma_index **i,
+		ulong *memlimit, lzma_allocator *allocator,
+		const ubyte *in_, size_t *in_pos, size_t in_size);

deimos/lzma_/index_hash.d

@@ -0,0 +1,103 @@
+/**
+ * \file        lzma/index_hash.h
+ * \brief       Validate Index by using a hash function
+ *
+ * Hashing makes it possible to use constant amount of memory to validate
+ * Index of arbitrary size.
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.index_hash;
+import deimos.lzma;
+
+extern(C):
+
+/**
+ * \brief       Opaque data type to hold the Index hash
+ */
+struct lzma_index_hash {};
+
+
+/**
+ * \brief       Allocate and initialize a new lzma_index_hash structure
+ *
+ * If index_hash is NULL, a new lzma_index_hash structure is allocated,
+ * initialized, and a pointer to it returned. If allocation fails, NULL
+ * is returned.
+ *
+ * If index_hash is non-NULL, it is reinitialized and the same pointer
+ * returned. In this case, return value cannot be NULL or a different
+ * pointer than the index_hash that was given as an argument.
+ */
+nothrow lzma_index_hash * lzma_index_hash_init(
+		lzma_index_hash *index_hash, lzma_allocator *allocator);
+
+
+/**
+ * \brief       Deallocate lzma_index_hash structure
+ */
+nothrow void lzma_index_hash_end(
+		lzma_index_hash *index_hash, lzma_allocator *allocator);
+
+
+/**
+ * \brief       Add a new Record to an Index hash
+ *
+ * \param       index             Pointer to a lzma_index_hash structure
+ * \param       unpadded_size     Unpadded Size of a Block
+ * \param       uncompressed_size Uncompressed Size of a Block
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_DATA_ERROR: Compressed or uncompressed size of the
+ *                Stream or size of the Index field would grow too big.
+ *              - LZMA_PROG_ERROR: Invalid arguments or this function is being
+ *                used when lzma_index_hash_decode() has already been used.
+ */
+nothrow lzma_ret lzma_index_hash_append(lzma_index_hash *index_hash,
+		lzma_vli unpadded_size, lzma_vli uncompressed_size);
+
+
+/**
+ * \brief       Decode and validate the Index field
+ *
+ * After telling the sizes of all Blocks with lzma_index_hash_append(),
+ * the actual Index field is decoded with this function. Specifically,
+ * once decoding of the Index field has been started, no more Records
+ * can be added using lzma_index_hash_append().
+ *
+ * This function doesn't use lzma_stream structure to pass the input data.
+ * Instead, the input buffer is specified using three arguments. This is
+ * because it matches better the internal APIs of liblzma.
+ *
+ * \param       index_hash      Pointer to a lzma_index_hash structure
+ * \param       in              Pointer to the beginning of the input buffer
+ * \param       in_pos          in[*in_pos] is the next byte to process
+ * \param       in_size         in[in_size] is the first byte not to process
+ *
+ * \return      - LZMA_OK: So far good, but more input is needed.
+ *              - LZMA_STREAM_END: Index decoded successfully and it matches
+ *                the Records given with lzma_index_hash_append().
+ *              - LZMA_DATA_ERROR: Index is corrupt or doesn't match the
+ *                information given with lzma_index_hash_append().
+ *              - LZMA_BUF_ERROR: Cannot progress because *in_pos >= in_size.
+ *              - LZMA_PROG_ERROR
+ */
+nothrow lzma_ret lzma_index_hash_decode(lzma_index_hash *index_hash,
+		const ubyte *in_, size_t *in_pos, size_t in_size);
+
+
+/**
+ * \brief       Get the size of the Index field as bytes
+ *
+ * This is needed to verify the Backward Size field in the Stream Footer.
+ */
+nothrow pure lzma_vli lzma_index_hash_size(
+		const lzma_index_hash *index_hash);

deimos/lzma_/lzma.d

@@ -0,0 +1,422 @@
+/**
+ * \file        lzma/lzma.h
+ * \brief       LZMA1 and LZMA2 filters
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.lzma;
+import deimos.lzma;
+
+extern(C):
+
+
+/**
+ * \brief       LZMA1 Filter ID
+ *
+ * LZMA1 is the very same thing as what was called just LZMA in LZMA Utils,
+ * 7-Zip, and LZMA SDK. It's called LZMA1 here to prevent developers from
+ * accidentally using LZMA when they actually want LZMA2.
+ *
+ * LZMA1 shouldn't be used for new applications unless you _really_ know
+ * what you are doing. LZMA2 is almost always a better choice.
+ */
+enum LZMA_FILTER_LZMA1 = 0x4000000000000001UL;
+
+/**
+ * \brief       LZMA2 Filter ID
+ *
+ * Usually you want this instead of LZMA1. Compared to LZMA1, LZMA2 adds
+ * support for LZMA_SYNC_FLUSH, uncompressed chunks (smaller expansion
+ * when trying to compress uncompressible data), possibility to change
+ * lc/lp/pb in the middle of encoding, and some other internal improvements.
+ */
+enum LZMA_FILTER_LZMA2 = 0x21UL;
+
+
+/**
+ * \brief       Match finders
+ *
+ * Match finder has major effect on both speed and compression ratio.
+ * Usually hash chains are faster than binary trees.
+ *
+ * If you will use LZMA_SYNC_FLUSH often, the hash chains may be a better
+ * choice, because binary trees get much higher compression ratio penalty
+ * with LZMA_SYNC_FLUSH.
+ *
+ * The memory usage formulas are only rough estimates, which are closest to
+ * reality when dict_size is a power of two. The formulas are  more complex
+ * in reality, and can also change a little between liblzma versions. Use
+ * lzma_raw_encoder_memusage() to get more accurate estimate of memory usage.
+ */
+enum lzma_match_finder
+{
+	LZMA_MF_HC3     = 0x03,
+		/**<
+		 * \brief       Hash Chain with 2- and 3-byte hashing
+		 *
+		 * Minimum nice_len: 3
+		 *
+		 * Memory usage:
+		 *  - dict_size <= 16 MiB: dict_size * 7.5
+		 *  - dict_size > 16 MiB: dict_size * 5.5 + 64 MiB
+		 */
+
+	LZMA_MF_HC4     = 0x04,
+		/**<
+		 * \brief       Hash Chain with 2-, 3-, and 4-byte hashing
+		 *
+		 * Minimum nice_len: 4
+		 *
+		 * Memory usage:
+		 *  - dict_size <= 32 MiB: dict_size * 7.5
+		 *  - dict_size > 32 MiB: dict_size * 6.5
+		 */
+
+	LZMA_MF_BT2     = 0x12,
+		/**<
+		 * \brief       Binary Tree with 2-byte hashing
+		 *
+		 * Minimum nice_len: 2
+		 *
+		 * Memory usage: dict_size * 9.5
+		 */
+
+	LZMA_MF_BT3     = 0x13,
+		/**<
+		 * \brief       Binary Tree with 2- and 3-byte hashing
+		 *
+		 * Minimum nice_len: 3
+		 *
+		 * Memory usage:
+		 *  - dict_size <= 16 MiB: dict_size * 11.5
+		 *  - dict_size > 16 MiB: dict_size * 9.5 + 64 MiB
+		 */
+
+	LZMA_MF_BT4     = 0x14
+		/**<
+		 * \brief       Binary Tree with 2-, 3-, and 4-byte hashing
+		 *
+		 * Minimum nice_len: 4
+		 *
+		 * Memory usage:
+		 *  - dict_size <= 32 MiB: dict_size * 11.5
+		 *  - dict_size > 32 MiB: dict_size * 10.5
+		 */
+}
+
+
+/**
+ * \brief       Test if given match finder is supported
+ *
+ * Return true if the given match finder is supported by this liblzma build.
+ * Otherwise false is returned. It is safe to call this with a value that
+ * isn't listed in lzma_match_finder enumeration; the return value will be
+ * false.
+ *
+ * There is no way to list which match finders are available in this
+ * particular liblzma version and build. It would be useless, because
+ * a new match finder, which the application developer wasn't aware,
+ * could require giving additional options to the encoder that the older
+ * match finders don't need.
+ */
+nothrow lzma_bool lzma_mf_is_supported(lzma_match_finder match_finder);
+
+
+/**
+ * \brief       Compression modes
+ *
+ * This selects the function used to analyze the data produced by the match
+ * finder.
+ */
+enum lzma_mode
+{
+	LZMA_MODE_FAST = 1,
+		/**<
+		 * \brief       Fast compression
+		 *
+		 * Fast mode is usually at its best when combined with
+		 * a hash chain match finder.
+		 */
+
+	LZMA_MODE_NORMAL = 2
+		/**<
+		 * \brief       Normal compression
+		 *
+		 * This is usually notably slower than fast mode. Use this
+		 * together with binary tree match finders to expose the
+		 * full potential of the LZMA1 or LZMA2 encoder.
+		 */
+}
+
+
+/**
+ * \brief       Test if given compression mode is supported
+ *
+ * Return true if the given compression mode is supported by this liblzma
+ * build. Otherwise false is returned. It is safe to call this with a value
+ * that isn't listed in lzma_mode enumeration; the return value will be false.
+ *
+ * There is no way to list which modes are available in this particular
+ * liblzma version and build. It would be useless, because a new compression
+ * mode, which the application developer wasn't aware, could require giving
+ * additional options to the encoder that the older modes don't need.
+ */
+nothrow lzma_bool lzma_mode_is_supported(lzma_mode mode);
+
+
+/**
+ * \brief       Options specific to the LZMA1 and LZMA2 filters
+ *
+ * Since LZMA1 and LZMA2 share most of the code, it's simplest to share
+ * the options structure too. For encoding, all but the reserved variables
+ * need to be initialized unless specifically mentioned otherwise.
+ * lzma_lzma_preset() can be used to get a good starting point.
+ *
+ * For raw decoding, both LZMA1 and LZMA2 need dict_size, preset_dict, and
+ * preset_dict_size (if preset_dict != NULL). LZMA1 needs also lc, lp, and pb.
+ */
+struct lzma_options_lzma
+{
+	/**
+	 * \brief       Dictionary size in bytes
+	 *
+	 * Dictionary size indicates how many bytes of the recently processed
+	 * uncompressed data is kept in memory. One method to reduce size of
+	 * the uncompressed data is to store distance-length pairs, which
+	 * indicate what data to repeat from the dictionary buffer. Thus,
+	 * the bigger the dictionary, the better the compression ratio
+	 * usually is.
+	 *
+	 * Maximum size of the dictionary depends on multiple things:
+	 *  - Memory usage limit
+	 *  - Available address space (not a problem on 64-bit systems)
+	 *  - Selected match finder (encoder only)
+	 *
+	 * Currently the maximum dictionary size for encoding is 1.5 GiB
+	 * (i.e. (UINT32_C(1) << 30) + (UINT32_C(1) << 29)) even on 64-bit
+	 * systems for certain match finder implementation reasons. In the
+	 * future, there may be match finders that support bigger
+	 * dictionaries.
+	 *
+	 * Decoder already supports dictionaries up to 4 GiB - 1 B (i.e.
+	 * UINT32_MAX), so increasing the maximum dictionary size of the
+	 * encoder won't cause problems for old decoders.
+	 *
+	 * Because extremely small dictionaries sizes would have unneeded
+	 * overhead in the decoder, the minimum dictionary size is 4096 bytes.
+	 *
+	 * \note        When decoding, too big dictionary does no other harm
+	 *              than wasting memory.
+	 */
+	uint dict_size;
+	enum LZMA_DICT_SIZE_MIN     =  4096U;
+	enum LZMA_DICT_SIZE_DEFAULT =  (1U << 23);
+
+	/**
+	 * \brief       Pointer to an initial dictionary
+	 *
+	 * It is possible to initialize the LZ77 history window using
+	 * a preset dictionary. It is useful when compressing many
+	 * similar, relatively small chunks of data independently from
+	 * each other. The preset dictionary should contain typical
+	 * strings that occur in the files being compressed. The most
+	 * probable strings should be near the end of the preset dictionary.
+	 *
+	 * This feature should be used only in special situations. For
+	 * now, it works correctly only with raw encoding and decoding.
+	 * Currently none of the container formats supported by
+	 * liblzma allow preset dictionary when decoding, thus if
+	 * you create a .xz or .lzma file with preset dictionary, it
+	 * cannot be decoded with the regular decoder functions. In the
+	 * future, the .xz format will likely get support for preset
+	 * dictionary though.
+	 */
+	const ubyte *preset_dict;
+
+	/**
+	 * \brief       Size of the preset dictionary
+	 *
+	 * Specifies the size of the preset dictionary. If the size is
+	 * bigger than dict_size, only the last dict_size bytes are
+	 * processed.
+	 *
+	 * This variable is read only when preset_dict is not NULL.
+	 * If preset_dict is not NULL but preset_dict_size is zero,
+	 * no preset dictionary is used (identical to only setting
+	 * preset_dict to NULL).
+	 */
+	uint preset_dict_size;
+
+	/**
+	 * \brief       Number of literal context bits
+	 *
+	 * How many of the highest bits of the previous uncompressed
+	 * eight-bit byte (also known as `literal') are taken into
+	 * account when predicting the bits of the next literal.
+	 *
+	 * E.g. in typical English text, an upper-case letter is
+	 * often followed by a lower-case letter, and a lower-case
+	 * letter is usually followed by another lower-case letter.
+	 * In the US-ASCII character set, the highest three bits are 010
+	 * for upper-case letters and 011 for lower-case letters.
+	 * When lc is at least 3, the literal coding can take advantage of
+	 * this property in the uncompressed data.
+	 *
+	 * There is a limit that applies to literal context bits and literal
+	 * position bits together: lc + lp <= 4. Without this limit the
+	 * decoding could become very slow, which could have security related
+	 * results in some cases like email servers doing virus scanning.
+	 * This limit also simplifies the internal implementation in liblzma.
+	 *
+	 * There may be LZMA1 streams that have lc + lp > 4 (maximum possible
+	 * lc would be 8). It is not possible to decode such streams with
+	 * liblzma.
+	 */
+	uint lc;
+	enum LZMA_LCLP_MIN   = 0;
+	enum LZMA_LCLP_MAX   = 4;
+	enum LZMA_LC_DEFAULT = 3;
+
+	/**
+	 * \brief       Number of literal position bits
+	 *
+	 * lp affects what kind of alignment in the uncompressed data is
+	 * assumed when encoding literals. A literal is a single 8-bit byte.
+	 * See pb below for more information about alignment.
+	 */
+	uint lp;
+	enum LZMA_LP_DEFAULT = 0;
+
+	/**
+	 * \brief       Number of position bits
+	 *
+	 * pb affects what kind of alignment in the uncompressed data is
+	 * assumed in general. The default means four-byte alignment
+	 * (2^ pb =2^2=4), which is often a good choice when there's
+	 * no better guess.
+	 *
+	 * When the aligment is known, setting pb accordingly may reduce
+	 * the file size a little. E.g. with text files having one-byte
+	 * alignment (US-ASCII, ISO-8859-*, UTF-8), setting pb=0 can
+	 * improve compression slightly. For UTF-16 text, pb=1 is a good
+	 * choice. If the alignment is an odd number like 3 bytes, pb=0
+	 * might be the best choice.
+	 *
+	 * Even though the assumed alignment can be adjusted with pb and
+	 * lp, LZMA1 and LZMA2 still slightly favor 16-byte alignment.
+	 * It might be worth taking into account when designing file formats
+	 * that are likely to be often compressed with LZMA1 or LZMA2.
+	 */
+	uint pb;
+	enum LZMA_PB_MIN     = 0;
+	enum LZMA_PB_MAX     = 4;
+	enum LZMA_PB_DEFAULT = 2;
+
+	/** Compression mode */
+	lzma_mode mode;
+
+	/**
+	 * \brief       Nice length of a match
+	 *
+	 * This determines how many bytes the encoder compares from the match
+	 * candidates when looking for the best match. Once a match of at
+	 * least nice_len bytes long is found, the encoder stops looking for
+	 * better candidates and encodes the match. (Naturally, if the found
+	 * match is actually longer than nice_len, the actual length is
+	 * encoded; it's not truncated to nice_len.)
+	 *
+	 * Bigger values usually increase the compression ratio and
+	 * compression time. For most files, 32 to 128 is a good value,
+	 * which gives very good compression ratio at good speed.
+	 *
+	 * The exact minimum value depends on the match finder. The maximum
+	 * is 273, which is the maximum length of a match that LZMA1 and
+	 * LZMA2 can encode.
+	 */
+	uint nice_len;
+
+	/** Match finder ID */
+	lzma_match_finder mf;
+
+	/**
+	 * \brief       Maximum search depth in the match finder
+	 *
+	 * For every input byte, match finder searches through the hash chain
+	 * or binary tree in a loop, each iteration going one step deeper in
+	 * the chain or tree. The searching stops if
+	 *  - a match of at least nice_len bytes long is found;
+	 *  - all match candidates from the hash chain or binary tree have
+	 *    been checked; or
+	 *  - maximum search depth is reached.
+	 *
+	 * Maximum search depth is needed to prevent the match finder from
+	 * wasting too much time in case there are lots of short match
+	 * candidates. On the other hand, stopping the search before all
+	 * candidates have been checked can reduce compression ratio.
+	 *
+	 * Setting depth to zero tells liblzma to use an automatic default
+	 * value, that depends on the selected match finder and nice_len.
+	 * The default is in the range [4, 200] or so (it may vary between
+	 * liblzma versions).
+	 *
+	 * Using a bigger depth value than the default can increase
+	 * compression ratio in some cases. There is no strict maximum value,
+	 * but high values (thousands or millions) should be used with care:
+	 * the encoder could remain fast enough with typical input, but
+	 * malicious input could cause the match finder to slow down
+	 * dramatically, possibly creating a denial of service attack.
+	 */
+	uint depth;
+
+	/*
+	 * Reserved space to allow possible future extensions without
+	 * breaking the ABI. You should not touch these, because the names
+	 * of these variables may change. These are and will never be used
+	 * with the currently supported options, so it is safe to leave these
+	 * uninitialized.
+	 */
+	uint reserved_int1;
+	uint reserved_int2;
+	uint reserved_int3;
+	uint reserved_int4;
+	uint reserved_int5;
+	uint reserved_int6;
+	uint reserved_int7;
+	uint reserved_int8;
+	lzma_reserved_enum reserved_enum1;
+	lzma_reserved_enum reserved_enum2;
+	lzma_reserved_enum reserved_enum3;
+	lzma_reserved_enum reserved_enum4;
+	void *reserved_ptr1;
+	void *reserved_ptr2;
+
+}
+
+
+/**
+ * \brief       Set a compression preset to lzma_options_lzma structure
+ *
+ * 0 is the fastest and 9 is the slowest. These match the switches -0 .. -9
+ * of the xz command line tool. In addition, it is possible to bitwise-or
+ * flags to the preset. Currently only LZMA_PRESET_EXTREME is supported.
+ * The flags are defined in container.h, because the flags are used also
+ * with lzma_easy_encoder().
+ *
+ * The preset values are subject to changes between liblzma versions.
+ *
+ * This function is available only if LZMA1 or LZMA2 encoder has been enabled
+ * when building liblzma.
+ *
+ * \return      On success, false is returned. If the preset is not
+ *              supported, true is returned.
+ */
+nothrow lzma_bool lzma_lzma_preset(
+		lzma_options_lzma *options, uint preset);

deimos/lzma_/stream_flags.d

@@ -0,0 +1,219 @@
+/**
+ * \file        lzma/stream_flags.h
+ * \brief       .xz Stream Header and Stream Footer encoder and decoder
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.stream_flags;
+import deimos.lzma;
+
+extern(C):
+
+
+/**
+ * \brief       Size of Stream Header and Stream Footer
+ *
+ * Stream Header and Stream Footer have the same size and they are not
+ * going to change even if a newer version of the .xz file format is
+ * developed in future.
+ */
+enum LZMA_STREAM_HEADER_SIZE = 12;
+
+
+/**
+ * \brief       Options for encoding/decoding Stream Header and Stream Footer
+ */
+struct lzma_stream_flags
+{
+	/**
+	 * \brief       Stream Flags format version
+	 *
+	 * To prevent API and ABI breakages if new features are needed in
+	 * Stream Header or Stream Footer, a version number is used to
+	 * indicate which fields in this structure are in use. For now,
+	 * version must always be zero. With non-zero version, the
+	 * lzma_stream_header_encode() and lzma_stream_footer_encode()
+	 * will return LZMA_OPTIONS_ERROR.
+	 *
+	 * lzma_stream_header_decode() and lzma_stream_footer_decode()
+	 * will always set this to the lowest value that supports all the
+	 * features indicated by the Stream Flags field. The application
+	 * must check that the version number set by the decoding functions
+	 * is supported by the application. Otherwise it is possible that
+	 * the application will decode the Stream incorrectly.
+	 */
+	uint version_;
+
+	/**
+	 * \brief       Backward Size
+	 *
+	 * Backward Size must be a multiple of four bytes. In this Stream
+	 * format version, Backward Size is the size of the Index field.
+	 *
+	 * Backward Size isn't actually part of the Stream Flags field, but
+	 * it is convenient to include in this structure anyway. Backward
+	 * Size is present only in the Stream Footer. There is no need to
+	 * initialize backward_size when encoding Stream Header.
+	 *
+	 * lzma_stream_header_decode() always sets backward_size to
+	 * LZMA_VLI_UNKNOWN so that it is convenient to use
+	 * lzma_stream_flags_compare() when both Stream Header and Stream
+	 * Footer have been decoded.
+	 */
+	lzma_vli backward_size;
+	enum LZMA_BACKWARD_SIZE_MIN = 4;
+	enum LZMA_BACKWARD_SIZE_MAX = (1UL << 34);
+
+	/**
+	 * \brief       Check ID
+	 *
+	 * This indicates the type of the integrity check calculated from
+	 * uncompressed data.
+	 */
+	lzma_check check;
+
+	/*
+	 * Reserved space to allow possible future extensions without
+	 * breaking the ABI. You should not touch these, because the
+	 * names of these variables may change.
+	 *
+	 * (We will never be able to use all of these since Stream Flags
+	 * is just two bytes plus Backward Size of four bytes. But it's
+	 * nice to have the proper types when they are needed.)
+	 */
+	lzma_reserved_enum reserved_enum1;
+	lzma_reserved_enum reserved_enum2;
+	lzma_reserved_enum reserved_enum3;
+	lzma_reserved_enum reserved_enum4;
+	lzma_bool reserved_bool1;
+	lzma_bool reserved_bool2;
+	lzma_bool reserved_bool3;
+	lzma_bool reserved_bool4;
+	lzma_bool reserved_bool5;
+	lzma_bool reserved_bool6;
+	lzma_bool reserved_bool7;
+	lzma_bool reserved_bool8;
+	uint reserved_int1;
+	uint reserved_int2;
+}
+
+
+/**
+ * \brief       Encode Stream Header
+ *
+ * \param       options     Stream Header options to be encoded.
+ *                          options->backward_size is ignored and doesn't
+ *                          need to be initialized.
+ * \param       out         Beginning of the output buffer of
+ *                          LZMA_STREAM_HEADER_SIZE bytes.
+ *
+ * \return      - LZMA_OK: Encoding was successful.
+ *              - LZMA_OPTIONS_ERROR: options->version is not supported by
+ *                this liblzma version.
+ *              - LZMA_PROG_ERROR: Invalid options.
+ */
+nothrow lzma_ret lzma_stream_header_encode(
+		const lzma_stream_flags *options, ubyte *out_);
+
+
+/**
+ * \brief       Encode Stream Footer
+ *
+ * \param       options     Stream Footer options to be encoded.
+ * \param       out         Beginning of the output buffer of
+ *                          LZMA_STREAM_HEADER_SIZE bytes.
+ *
+ * \return      - LZMA_OK: Encoding was successful.
+ *              - LZMA_OPTIONS_ERROR: options->version is not supported by
+ *                this liblzma version.
+ *              - LZMA_PROG_ERROR: Invalid options.
+ */
+nothrow lzma_ret lzma_stream_footer_encode(
+		const lzma_stream_flags *options, ubyte *out_);
+
+
+/**
+ * \brief       Decode Stream Header
+ *
+ * \param       options     Target for the decoded Stream Header options.
+ * \param       in          Beginning of the input buffer of
+ *                          LZMA_STREAM_HEADER_SIZE bytes.
+ *
+ * options->backward_size is always set to LZMA_VLI_UNKNOWN. This is to
+ * help comparing Stream Flags from Stream Header and Stream Footer with
+ * lzma_stream_flags_compare().
+ *
+ * \return      - LZMA_OK: Decoding was successful.
+ *              - LZMA_FORMAT_ERROR: Magic bytes don't match, thus the given
+ *                buffer cannot be Stream Header.
+ *              - LZMA_DATA_ERROR: CRC32 doesn't match, thus the header
+ *                is corrupt.
+ *              - LZMA_OPTIONS_ERROR: Unsupported options are present
+ *                in the header.
+ *
+ * \note        When decoding .xz files that contain multiple Streams, it may
+ *              make sense to print "file format not recognized" only if
+ *              decoding of the Stream Header of the _first_ Stream gives
+ *              LZMA_FORMAT_ERROR. If non-first Stream Header gives
+ *              LZMA_FORMAT_ERROR, the message used for LZMA_DATA_ERROR is
+ *              probably more appropriate.
+ *
+ *              For example, Stream decoder in liblzma uses LZMA_DATA_ERROR if
+ *              LZMA_FORMAT_ERROR is returned by lzma_stream_header_decode()
+ *              when decoding non-first Stream.
+ */
+nothrow lzma_ret lzma_stream_header_decode(
+		lzma_stream_flags *options, const ubyte *in_);
+
+
+/**
+ * \brief       Decode Stream Footer
+ *
+ * \param       options     Target for the decoded Stream Header options.
+ * \param       in          Beginning of the input buffer of
+ *                          LZMA_STREAM_HEADER_SIZE bytes.
+ *
+ * \return      - LZMA_OK: Decoding was successful.
+ *              - LZMA_FORMAT_ERROR: Magic bytes don't match, thus the given
+ *                buffer cannot be Stream Footer.
+ *              - LZMA_DATA_ERROR: CRC32 doesn't match, thus the Stream Footer
+ *                is corrupt.
+ *              - LZMA_OPTIONS_ERROR: Unsupported options are present
+ *                in Stream Footer.
+ *
+ * \note        If Stream Header was already decoded successfully, but
+ *              decoding Stream Footer returns LZMA_FORMAT_ERROR, the
+ *              application should probably report some other error message
+ *              than "file format not recognized", since the file more likely
+ *              is corrupt (possibly truncated). Stream decoder in liblzma
+ *              uses LZMA_DATA_ERROR in this situation.
+ */
+nothrow lzma_ret lzma_stream_footer_decode(
+		lzma_stream_flags *options, const ubyte *in_);
+
+
+/**
+ * \brief       Compare two lzma_stream_flags structures
+ *
+ * backward_size values are compared only if both are not
+ * LZMA_VLI_UNKNOWN.
+ *
+ * \return      - LZMA_OK: Both are equal. If either had backward_size set
+ *                to LZMA_VLI_UNKNOWN, backward_size values were not
+ *                compared or validated.
+ *              - LZMA_DATA_ERROR: The structures differ.
+ *              - LZMA_OPTIONS_ERROR: version in either structure is greater
+ *                than the maximum supported version (currently zero).
+ *              - LZMA_PROG_ERROR: Invalid value, e.g. invalid check or
+ *                backward_size.
+ */
+nothrow pure lzma_ret lzma_stream_flags_compare(
+		const lzma_stream_flags *a, const lzma_stream_flags *b);

deimos/lzma_/version_.d

@@ -0,0 +1,108 @@
+/**
+ * \file        lzma/version.h
+ * \brief       Version number
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.version_;
+import deimos.lzma;
+import std.conv;
+
+extern(C):
+
+/*
+ * Version number split into components
+ */
+enum LZMA_VERSION_MAJOR = 5;
+enum LZMA_VERSION_MINOR = 0;
+enum LZMA_VERSION_PATCH = 3;
+enum LZMA_VERSION_STABILITY = LZMA_VERSION_STABILITY_STABLE;
+
+/*
+#ifndef LZMA_VERSION_COMMIT
+#	define LZMA_VERSION_COMMIT ""
+#endif*/
+enum LZMA_VERSION_COMMIT = "";
+
+/*
+ * Map symbolic stability levels to integers.
+ */
+enum LZMA_VERSION_STABILITY_ALPHA = 0;
+enum LZMA_VERSION_STABILITY_BETA = 1;
+enum LZMA_VERSION_STABILITY_STABLE = 2;
+
+
+/**
+ * \brief       Compile-time version number
+ *
+ * The version number is of format xyyyzzzs where
+ *  - x = major
+ *  - yyy = minor
+ *  - zzz = revision
+ *  - s indicates stability: 0 = alpha, 1 = beta, 2 = stable
+ *
+ * The same xyyyzzz triplet is never reused with different stability levels.
+ * For example, if 5.1.0alpha has been released, there will never be 5.1.0beta
+ * or 5.1.0 stable.
+ *
+ * \note        The version number of liblzma has nothing to with
+ *              the version number of Igor Pavlov's LZMA SDK.
+ */
+enum LZMA_VERSION = (LZMA_VERSION_MAJOR * 10000000U 
+		+ LZMA_VERSION_MINOR * 10000U
+		+ LZMA_VERSION_PATCH * 10U
+		+ LZMA_VERSION_STABILITY);
+
+
+/*
+ * Macros to construct the compile-time version string
+ */
+static if(LZMA_VERSION_STABILITY == LZMA_VERSION_STABILITY_ALPHA)
+	enum LZMA_VERSION_STABILITY_STRING = "alpha";
+else static if(LZMA_VERSION_STABILITY == LZMA_VERSION_STABILITY_BETA)
+	enum LZMA_VERSION_STABILITY_STRING = "beta";
+else static if(LZMA_VERSION_STABILITY == LZMA_VERSION_STABILITY_STABLE)
+	enum LZMA_VERSION_STABILITY_STRING = "";
+else
+	static assert(false, "Incorrect LZMA_VERSION_STABILITY");
+
+/**
+ * \brief       Compile-time version as a string
+ *
+ * This can be for example "4.999.5alpha", "4.999.8beta", or "5.0.0" (stable
+ * versions don't have any "stable" suffix). In future, a snapshot built
+ * from source code repository may include an additional suffix, for example
+ * "4.999.8beta-21-g1d92". The commit ID won't be available in numeric form
+ * in LZMA_VERSION macro.
+ */
+enum LZMA_VERSION_STRING = 
+		to!string(LZMA_VERSION_MAJOR) ~ "." ~ to!string(LZMA_VERSION_MINOR) ~
+		"." ~ to!string(LZMA_VERSION_PATCH) ~ LZMA_VERSION_STABILITY_STRING ~
+		LZMA_VERSION_COMMIT;
+
+
+/**
+ * \brief       Run-time version number as an integer
+ *
+ * Return the value of LZMA_VERSION macro at the compile time of liblzma.
+ * This allows the application to compare if it was built against the same,
+ * older, or newer version of liblzma that is currently running.
+ */
+nothrow uint lzma_version_number();
+
+
+/**
+ * \brief       Run-time version as a string
+ *
+ * This function may be useful if you want to display which version of
+ * liblzma your application is currently using.
+ */
+nothrow immutable(char)* lzma_version_string();

deimos/lzma_/vli.d

@@ -0,0 +1,167 @@
+/**
+ * \file        lzma/vli.h
+ * \brief       Variable-length integer handling
+ *
+ * In the .xz format, most integers are encoded in a variable-length
+ * representation, which is sometimes called little endian base-128 encoding.
+ * This saves space when smaller values are more likely than bigger values.
+ *
+ * The encoding scheme encodes seven bits to every byte, using minimum
+ * number of bytes required to represent the given value. Encodings that use
+ * non-minimum number of bytes are invalid, thus every integer has exactly
+ * one encoded representation. The maximum number of bits in a VLI is 63,
+ * thus the vli argument must be less than or equal to UINT64_MAX / 2. You
+ * should use LZMA_VLI_MAX for clarity.
+ */
+
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ *
+ * See ../lzma.h for information about liblzma as a whole.
+ */
+
+module deimos.lzma_.vli;
+import deimos.lzma;
+
+extern(C):
+
+
+/**
+ * \brief       Maximum supported value of a variable-length integer
+ */
+enum LZMA_VLI_MAX = (ulong.max / 2);
+
+/**
+ * \brief       VLI value to denote that the value is unknown
+ */
+enum LZMA_VLI_UNKNOWN = ulong.max;
+
+/**
+ * \brief       Maximum supported encoded length of variable length integers
+ */
+enum LZMA_VLI_BYTES_MAX = 9;
+
+/**
+ * \brief       VLI constant suffix
+ */
+//#define LZMA_VLI_C(n) UINT64_C(n)
+
+
+/**
+ * \brief       Variable-length integer type
+ *
+ * Valid VLI values are in the range [0, LZMA_VLI_MAX]. Unknown value is
+ * indicated with LZMA_VLI_UNKNOWN, which is the maximum value of the
+ * underlaying integer type.
+ *
+ * lzma_vli will be uint64_t for the foreseeable future. If a bigger size
+ * is needed in the future, it is guaranteed that 2 * LZMA_VLI_MAX will
+ * not overflow lzma_vli. This simplifies integer overflow detection.
+ */
+alias ulong lzma_vli;
+
+
+/**
+ * \brief       Validate a variable-length integer
+ *
+ * This is useful to test that application has given acceptable values
+ * for example in the uncompressed_size and compressed_size variables.
+ *
+ * \return      True if the integer is representable as VLI or if it
+ *              indicates unknown value.
+ */
+bool lzma_vli_is_valid(lzma_vli vli)
+{
+    return vli <= LZMA_VLI_MAX || (vli) == LZMA_VLI_UNKNOWN;
+}
+
+
+/**
+ * \brief       Encode a variable-length integer
+ *
+ * This function has two modes: single-call and multi-call. Single-call mode
+ * encodes the whole integer at once; it is an error if the output buffer is
+ * too small. Multi-call mode saves the position in *vli_pos, and thus it is
+ * possible to continue encoding if the buffer becomes full before the whole
+ * integer has been encoded.
+ *
+ * \param       vli       Integer to be encoded
+ * \param       vli_pos   How many VLI-encoded bytes have already been written
+ *                        out. When starting to encode a new integer in
+ *                        multi-call mode, *vli_pos must be set to zero.
+ *                        To use single-call encoding, set vli_pos to NULL.
+ * \param       out       Beginning of the output buffer
+ * \param       out_pos   The next byte will be written to out[*out_pos].
+ * \param       out_size  Size of the out buffer; the first byte into
+ *                        which no data is written to is out[out_size].
+ *
+ * \return      Slightly different return values are used in multi-call and
+ *              single-call modes.
+ *
+ *              Single-call (vli_pos == NULL):
+ *              - LZMA_OK: Integer successfully encoded.
+ *              - LZMA_PROG_ERROR: Arguments are not sane. This can be due
+ *                to too little output space; single-call mode doesn't use
+ *                LZMA_BUF_ERROR, since the application should have checked
+ *                the encoded size with lzma_vli_size().
+ *
+ *              Multi-call (vli_pos != NULL):
+ *              - LZMA_OK: So far all OK, but the integer is not
+ *                completely written out yet.
+ *              - LZMA_STREAM_END: Integer successfully encoded.
+ *              - LZMA_BUF_ERROR: No output space was provided.
+ *              - LZMA_PROG_ERROR: Arguments are not sane.
+ */
+nothrow lzma_ret lzma_vli_encode(lzma_vli vli, size_t *vli_pos,
+		ubyte* out_, size_t *out_pos, size_t out_size);
+
+
+/**
+ * \brief       Decode a variable-length integer
+ *
+ * Like lzma_vli_encode(), this function has single-call and multi-call modes.
+ *
+ * \param       vli       Pointer to decoded integer. The decoder will
+ *                        initialize it to zero when *vli_pos == 0, so
+ *                        application isn't required to initialize *vli.
+ * \param       vli_pos   How many bytes have already been decoded. When
+ *                        starting to decode a new integer in multi-call
+ *                        mode, *vli_pos must be initialized to zero. To
+ *                        use single-call decoding, set vli_pos to NULL.
+ * \param       in        Beginning of the input buffer
+ * \param       in_pos    The next byte will be read from in[*in_pos].
+ * \param       in_size   Size of the input buffer; the first byte that
+ *                        won't be read is in[in_size].
+ *
+ * \return      Slightly different return values are used in multi-call and
+ *              single-call modes.
+ *
+ *              Single-call (vli_pos == NULL):
+ *              - LZMA_OK: Integer successfully decoded.
+ *              - LZMA_DATA_ERROR: Integer is corrupt. This includes hitting
+ *                the end of the input buffer before the whole integer was
+ *                decoded; providing no input at all will use LZMA_DATA_ERROR.
+ *              - LZMA_PROG_ERROR: Arguments are not sane.
+ *
+ *              Multi-call (vli_pos != NULL):
+ *              - LZMA_OK: So far all OK, but the integer is not
+ *                completely decoded yet.
+ *              - LZMA_STREAM_END: Integer successfully decoded.
+ *              - LZMA_DATA_ERROR: Integer is corrupt.
+ *              - LZMA_BUF_ERROR: No input was provided.
+ *              - LZMA_PROG_ERROR: Arguments are not sane.
+ */
+nothrow lzma_ret lzma_vli_decode(lzma_vli *vli, size_t *vli_pos,
+		const(ubyte)* in_, size_t *in_pos, size_t in_size);
+
+
+/**
+ * \brief       Get the number of bytes required to encode a VLI
+ *
+ * \return      Number of bytes on success (1-9). If vli isn't valid,
+ *              zero is returned.
+ */
+nothrow pure uint lzma_vli_size(lzma_vli vli);

lzma.d

@@ -0,0 +1,116 @@
+/*
+ *  Copyright 2012, 2013, 2014 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  This file is part of RABCDAsm.
+ *
+ *  RABCDAsm is free software: you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation, either version 3 of the License, or
+ *  (at your option) any later version.
+ *
+ *  RABCDAsm is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with RABCDAsm.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+module lzma;
+
+version(HAVE_LZMA) {} else static assert(0, "LZMA is not available (HAVE_LZMA version is not defined)");
+
+import deimos.lzma;
+import std.conv;
+import std.exception;
+
+version (Windows)
+	{ pragma(lib, "liblzma"); }
+else
+	{ pragma(lib, "lzma"); }
+
+align(1) struct LZMAHeader
+{
+align(1):
+	ubyte compressionParameters;
+	uint dictionarySize;
+	long decompressedSize = -1;
+}
+static assert(LZMAHeader.sizeof == 13);
+
+ubyte[] lzmaDecompress(LZMAHeader header, in ubyte[] compressedData)
+{
+	enforce(header.decompressedSize > 0, "Decompression with unknown size is unsupported");
+
+	lzma_stream strm;
+	lzmaEnforce(lzma_alone_decoder(&strm, ulong.max), "lzma_alone_decoder");
+	scope(exit) lzma_end(&strm);
+
+	auto outBuf = new ubyte[to!size_t(header.decompressedSize)];
+	strm.next_out  = outBuf.ptr;
+	strm.avail_out = outBuf.length;
+
+	void decompress(in ubyte[] chunk)
+	{
+		strm.next_in  = chunk.ptr;
+		strm.avail_in = chunk.length;
+		lzmaEnforce!true(lzma_code(&strm, lzma_action.LZMA_RUN), "lzma_code (LZMA_RUN)");
+		enforce(strm.avail_in == 0, "Not all data was read");
+	}
+
+	header.decompressedSize = -1; // Required as Flash uses End-of-Stream marker
+	fixDictSize(header.dictionarySize);
+	decompress(cast(ubyte[])(&header)[0..1]);
+	decompress(compressedData);
+
+	lzmaEnforce!true(lzma_code(&strm, lzma_action.LZMA_FINISH), "lzma_code (LZMA_FINISH)");
+
+	enforce(strm.avail_out == 0, "Decompressed size mismatch");
+
+	return outBuf;
+}
+
+ubyte[] lzmaCompress(in ubyte[] decompressedData, LZMAHeader* header)
+{
+	lzma_options_lzma opts;
+	enforce(lzma_lzma_preset(&opts, 9 | LZMA_PRESET_EXTREME) == false, "lzma_lzma_preset error");
+
+	lzma_stream strm;
+	lzmaEnforce(lzma_alone_encoder(&strm, &opts), "lzma_alone_encoder");
+	scope(exit) lzma_end(&strm);
+
+	auto outBuf = new ubyte[decompressedData.length * 11 / 10 + 1024];
+	strm.next_out  = outBuf.ptr;
+	strm.avail_out = outBuf.length;
+	strm.next_in   = decompressedData.ptr;
+	strm.avail_in  = decompressedData.length;
+	lzmaEnforce(lzma_code(&strm, lzma_action.LZMA_RUN), "lzma_code (LZMA_RUN)");
+	enforce(strm.avail_in == 0, "Not all data was read");
+	enforce(strm.avail_out != 0, "Ran out of compression space");
+
+	lzmaEnforce!true(lzma_code(&strm, lzma_action.LZMA_FINISH), "lzma_code (LZMA_FINISH)");
+
+	*header = *cast(LZMAHeader*)outBuf.ptr;
+	return outBuf[LZMAHeader.sizeof..to!size_t(strm.total_out)];
+}
+
+private void lzmaEnforce(bool STREAM_END_OK=false)(lzma_ret v, string f)
+{
+	if (v != lzma_ret.LZMA_OK && (!STREAM_END_OK || v != lzma_ret.LZMA_STREAM_END))
+		throw new Exception(text(f, " error: ", v));
+}
+
+/// Work around an artificial lzma_alone_decoder limitation in liblzma
+/// which prevents it from accepting any streams with a dictionary size
+/// that is not 2^n or 2^n + 2^(n-1).
+/// See xz\src\liblzma\common\alone_decoder.c (git commit e7b424d267), line 87
+private void fixDictSize(ref uint d)
+{
+	--d;
+	d |= d >> 2;
+	d |= d >> 3;
+	d |= d >> 4;
+	d |= d >> 8;
+	d |= d >> 16;
+	++d;
+}

murmurhash2a.d

@@ -16,6 +16,8 @@
 
 module murmurhash2a;
 
+import std.conv;
+
 struct MurmurHash2A
 {
 	private static string mmix(string h, string k) { return "{ "~k~" *= m; "~k~" ^= "~k~" >> r; "~k~" *= m; "~h~" *= m; "~h~" ^= "~k~"; }"; }
@@ -31,7 +33,7 @@ public:
 		m_size  = 0;
 	}
 
-	void Add ( void * vdata, int len )
+	void Add ( const(void) * vdata, int len )
 	{
 		ubyte * data = cast(ubyte*)vdata;
 		m_size += len;
@@ -67,8 +69,8 @@ public:
 	void Add(ref ubyte v) { Add(&v, v.sizeof); }
 	void Add(ref int v) { Add(&v, v.sizeof); }
 	void Add(ref uint v) { Add(&v, v.sizeof); }
-	void Add(string s) { Add(s.ptr, s.length); }
-	void Add(ubyte[] s) { Add(s.ptr, s.length); }
+	void Add(string s) { Add(s.ptr, to!uint(s.length)); }
+	void Add(ubyte[] s) { Add(s.ptr, to!uint(s.length)); }
 
 private:
 

rabcasm.d

@@ -1,5 +1,5 @@
 /*
- *  Copyright (C) 2010 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  Copyright 2010, 2011 Vladimir Panteleev <vladimir@thecybershadow.net>
  *  This file is part of RABCDAsm.
  *
  *  RABCDAsm is free software: you can redistribute it and/or modify
@@ -35,5 +35,5 @@ void main(string[] args)
 		assembler.assemble(arg);
 	}
 	auto abc = as.toABC();
-	write(getName(args[1]) ~ ".abc", abc.write());
+	write(setExtension(args[1], "abc"), abc.write());
 }

rabcdasm.d

@@ -1,5 +1,5 @@
 /*
- *  Copyright (C) 2010 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  Copyright 2010, 2011 Vladimir Panteleev <vladimir@thecybershadow.net>
  *  This file is part of RABCDAsm.
  *
  *  RABCDAsm is free software: you can redistribute it and/or modify
@@ -32,7 +32,7 @@ void main(string[] args)
 	{
 		scope abc = ABCFile.read(cast(ubyte[])read(arg));
 		scope as = ASProgram.fromABC(abc);
-		scope disassembler = new Disassembler(as, getName(getBaseName(arg)));
+		scope disassembler = new Disassembler(as, stripExtension(arg), stripExtension(baseName(arg)));
 		disassembler.disassemble();
 	}
 }

swf7zcompress.d

@@ -1,5 +1,5 @@
 /*
- *  Copyright (C) 2010 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  Copyright 2010, 2011 Vladimir Panteleev <vladimir@thecybershadow.net>
  *  This file is part of RABCDAsm.
  *
  *  RABCDAsm is free software: you can redistribute it and/or modify

swfbinexport.d

@@ -0,0 +1,50 @@
+/*
+ *  Copyright 2010, 2011 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  This file is part of RABCDAsm.
+ *
+ *  RABCDAsm is free software: you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation, either version 3 of the License, or
+ *  (at your option) any later version.
+ *
+ *  RABCDAsm is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with RABCDAsm.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+module swfbinexport;
+
+import std.file;
+import std.path;
+import std.string;
+import std.stdio;
+import std.exception;
+import swffile;
+
+void main(string[] args)
+{
+	if (args.length == 1)
+		throw new Exception("No file specified");
+	foreach (arg; args[1..$])
+		try
+		{
+			scope swf = SWFFile.read(cast(ubyte[])read(arg));
+			bool found;
+			foreach (ref tag; swf.tags)
+				if (tag.type == TagType.DefineBinaryData)
+				{
+					found = true;
+					enforce(tag.data.length >= 6);
+					ushort id = *cast(short*)tag.data.ptr;
+					ubyte[] bin = tag.data[6..$];
+					std.file.write(format("%s-%d.bin", stripExtension(arg), id), bin);
+				}
+			enforce(found, "No DefineBinaryData tags found");
+		}
+		catch (Exception e)
+			writefln("Error while processing %s: %s", arg, e);
+}

swfbinreplace.d

@@ -0,0 +1,41 @@
+/*
+ *  Copyright 2010, 2011, 2012 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  This file is part of RABCDAsm.
+ *
+ *  RABCDAsm is free software: you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation, either version 3 of the License, or
+ *  (at your option) any later version.
+ *
+ *  RABCDAsm is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with RABCDAsm.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+module swfbinreplace;
+
+import std.file;
+import std.conv;
+import swffile;
+
+void main(string[] args)
+{
+	if (args.length != 4)
+		throw new Exception("Bad arguments. Usage: swfbinreplace file.swf id data.bin");
+	auto swf = SWFFile.read(cast(ubyte[])read(args[1]));
+	auto id = to!ushort(args[2]);
+	foreach (ref tag; swf.tags)
+		if (tag.type == TagType.DefineBinaryData && tag.data.length >= 6 && *cast(short*)tag.data.ptr == id)
+		{
+			auto bin = cast(ubyte[])read(args[3]);
+			tag.data = tag.data[0..6] ~ bin;
+			tag.length = cast(uint)tag.data.length;
+			write(args[1], swf.write());
+			return;
+		}
+	throw new Exception("DefineBinaryData tag with specified ID not found in file");
+}

swfdecompress.d

@@ -1,5 +1,5 @@
 /*
- *  Copyright (C) 2010 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  Copyright 2010, 2011, 2012 Vladimir Panteleev <vladimir@thecybershadow.net>
  *  This file is part of RABCDAsm.
  *
  *  RABCDAsm is free software: you can redistribute it and/or modify
@@ -19,8 +19,6 @@
 module swfdecompress;
 
 import std.file;
-import std.zlib;
-import zlibx;
 import swffile;
 
 void main(string[] args)
@@ -29,13 +27,10 @@ void main(string[] args)
 		throw new Exception("No file specified");
 	foreach (arg; args[1..$])
 	{
-		auto swf = cast(ubyte[])read(arg);
-		auto header = cast(SWFFile.Header*)swf.ptr;
-		if (header.signature[0] == cast(ubyte)'F')
+		auto swf = SWFFile.read(cast(ubyte[])read(arg));
+		if (swf.header.signature[0] == cast(ubyte)'F')
 			throw new Exception("Already uncompressed");
-		if (header.signature[0] != cast(ubyte)'C')
-			throw new Exception("Unknown format");
-		header.signature[0] = cast(ubyte)'F'; // uncompressed
-		write(arg, swf[0..8] ~ exactUncompress(swf[8..$], header.fileLength-8));
+		swf.header.signature[0] = cast(ubyte)'F'; // uncompressed
+		write(arg, swf.write());
 	}
 }

swffile.d

@@ -1,5 +1,5 @@
 /*
- *  Copyright (C) 2010 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  Copyright 2010, 2011, 2012 Vladimir Panteleev <vladimir@thecybershadow.net>
  *  This file is part of RABCDAsm.
  *
  *  RABCDAsm is free software: you can redistribute it and/or modify
@@ -18,11 +18,14 @@
 
 module swffile;
 
+import std.conv;
+import std.exception;
 import std.zlib;
 import zlibx;
+version (HAVE_LZMA) import lzma;
 
-/** 
- * Implements a shallow representation of a .swf file. 
+/**
+ * Implements a shallow representation of a .swf file.
  * Loading and saving a .swf file using this class should produce
  * output identical to the input (aside zlib compression differences).
  */
@@ -36,12 +39,22 @@ final class SWFFile
 
 	align(1) struct Header
 	{
+	align(1):
 		char[3] signature;
 		ubyte ver;
 		uint fileLength;
 		static assert(Header.sizeof == 8);
 	}
 
+	align(1) struct LZMAHeader
+	{
+	align(1):
+		uint compressedLength;
+		ubyte compressionParameters;
+		uint dictionarySize;
+		static assert(LZMAHeader.sizeof == 9);
+	}
+
 	struct Rect
 	{
 		//int xMin, xMax, yMin, yMax;
@@ -52,6 +65,7 @@ final class SWFFile
 	{
 		ushort type;
 		ubyte[] data;
+		uint length; // may be >data.length if file is truncated
 		bool forceLongLength;
 	}
 
@@ -78,14 +92,30 @@ private final class SWFReader
 		swf = new SWFFile();
 
 		readRaw((&swf.header)[0..1]);
-		if ((swf.header.signature[0] != 'F' && swf.header.signature[0] != 'C') || swf.header.signature[1] != 'W' || swf.header.signature[2] != 'S')
-			throw new Exception("Invalid file signature");
+		enforce(swf.header.signature == "FWS" || swf.header.signature == "CWS" || swf.header.signature == "ZWS", "Invalid file signature");
 		if (swf.header.signature[0] == 'C')
+			buf = buf[0..swf.header.sizeof] ~ exactUncompress(buf[swf.header.sizeof..$], swf.header.fileLength-swf.header.sizeof);
+		else
+		if (swf.header.signature[0] == 'Z')
 		{
-			buf = buf[0..8] ~ exactUncompress(buf[8..$], swf.header.fileLength-8);
-			if (swf.header.fileLength != buf.length)
-				throw new Exception("Incorrect file length in file header");
+			version (HAVE_LZMA)
+			{
+				SWFFile.LZMAHeader lzHeader;
+				readRaw((&lzHeader)[0..1]);
+
+				lzma.LZMAHeader lzInfo;
+				lzInfo.compressionParameters = lzHeader.compressionParameters;
+				lzInfo.dictionarySize = lzHeader.dictionarySize;
+				lzInfo.decompressedSize = swf.header.fileLength - swf.header.sizeof;
+
+				enforce(swf.header.sizeof + lzHeader.sizeof + lzHeader.compressedLength == buf.length, "Trailing data in LZMA-compressed SWF file");
+				buf = buf[0..swf.header.sizeof] ~ lzmaDecompress(lzInfo, buf[swf.header.sizeof + lzHeader.sizeof .. $]);
+				pos = swf.header.sizeof;
+			}
+			else
+				enforce(false, "This version was built without LZMA support");
 		}
+		enforce(swf.header.fileLength == buf.length, "Incorrect file length in file header");
 		swf.frameSize = readRect();
 		swf.frameRate = readU16();
 		swf.frameCount = readU16();
@@ -100,10 +130,12 @@ private final class SWFReader
 		pos += raw.length;
 	}
 
+	/// May read less than len on EOF
 	void[] readRaw(size_t len)
 	{
-		auto data = buf[pos..pos+len];
-		pos += len;
+		auto end = pos+len;
+		auto data = buf[pos..end<$?end:$];
+		pos = end;
 		return data;
 	}
 
@@ -145,6 +177,7 @@ private final class SWFReader
 			if (length < 0x3F)
 				t.forceLongLength = true;
 		}
+		t.length = length;
 		t.data = cast(ubyte[])readRaw(length);
 		return t;
 	}
@@ -152,73 +185,73 @@ private final class SWFReader
 
 enum TagType
 {
-	End						= 0,
-	ShowFrame				= 1,
-	DefineShape				= 2,
-	FreeCharacter			= 3,
-	PlaceObject				= 4,
-	RemoveObject			= 5,
-	DefineBits				= 6,
-	DefineButton			= 7,
-	JPEGTables				= 8,
-	SetBackgroundColor		= 9,
-	DefineFont				= 10,
-	DefineText				= 11,
-	DoAction				= 12,
-	DefineFontInfo			= 13,
-	DefineSound				= 14,
-	StartSound				= 15,
-	DefineButtonSound		= 17,
-	SoundStreamHead			= 18,
-	SoundStreamBlock		= 19,
-	DefineBitsLossless		= 20,
-	DefineBitsJPEG2			= 21,
-	DefineShape2			= 22,
-	DefineButtonCxform		= 23,
-	Protect					= 24,
-	PathsArePostScript		= 25,
-	PlaceObject2			= 26,
-	RemoveObject2			= 28,
-	DefineShape3			= 32,
-	DefineText2				= 33,
-	DefineButton2			= 34,
-	DefineBitsJPEG3			= 35,
-	DefineBitsLossless2		= 36,
-	DefineSprite			= 39,
-	ProductInfo				= 41,
-	FrameLabel				= 43,
-	SoundStreamHead2		= 45,
-	DefineMorphShape		= 46,
-	DefineFont2				= 48,
-	DefineEditText			= 37,
-	ExportAssets			= 56,
-	ImportAssets			= 57,
-	EnableDebugger			= 58,
-	DoInitAction			= 59,
-	DefineVideoStream		= 60,
-	VideoFrame				= 61,
-	DefineFontInfo2			= 62,
-	DebugID					= 63,
-	EnableDebugger2			= 64,
-    ScriptLimits			= 65,
-    SetTabIndex				= 66,
-	FileAttributes			= 69,
-	PlaceObject3			= 70,
-	ImportAssets2			= 71,
-	DoABC					= 72,
-    DefineFontAlignZones	= 73,
-    CSMTextSettings     	= 74,
-    DefineFont3				= 75,
-	SymbolClass				= 76,
-    Metadata                = 77,
-    DefineScalingGrid       = 78,
-    DoABC2                  = 82,
-    DefineShape4            = 83,
-	DefineMorphShape2		= 84,
-    DefineSceneAndFrameLabelData = 86,
-    DefineBinaryData        = 87,
-	DefineFontName          = 88,
-	DefineFont4             = 91
+	End                          =  0,
+	ShowFrame                    =  1,
+	DefineShape                  =  2,
+	FreeCharacter                =  3,
+	PlaceObject                  =  4,
+	RemoveObject                 =  5,
+	DefineBits                   =  6,
+	DefineButton                 =  7,
+	JPEGTables                   =  8,
+	SetBackgroundColor           =  9,
+	DefineFont                   = 10,
+	DefineText                   = 11,
+	DoAction                     = 12,
+	DefineFontInfo               = 13,
+	DefineSound                  = 14,
+	StartSound                   = 15,
+	DefineButtonSound            = 17,
+	SoundStreamHead              = 18,
+	SoundStreamBlock             = 19,
+	DefineBitsLossless           = 20,
+	DefineBitsJPEG2              = 21,
+	DefineShape2                 = 22,
+	DefineButtonCxform           = 23,
+	Protect                      = 24,
+	PathsArePostScript           = 25,
+	PlaceObject2                 = 26,
+	RemoveObject2                = 28,
+	DefineShape3                 = 32,
+	DefineText2                  = 33,
+	DefineButton2                = 34,
+	DefineBitsJPEG3              = 35,
+	DefineBitsLossless2          = 36,
+	DefineSprite                 = 39,
+	ProductInfo                  = 41,
+	FrameLabel                   = 43,
+	SoundStreamHead2             = 45,
+	DefineMorphShape             = 46,
+	DefineFont2                  = 48,
+	DefineEditText               = 37,
+	ExportAssets                 = 56,
+	ImportAssets                 = 57,
+	EnableDebugger               = 58,
+	DoInitAction                 = 59,
+	DefineVideoStream            = 60,
+	VideoFrame                   = 61,
+	DefineFontInfo2              = 62,
+	DebugID                      = 63,
+	EnableDebugger2              = 64,
+	ScriptLimits                 = 65,
+	SetTabIndex                  = 66,
+	FileAttributes               = 69,
+	PlaceObject3                 = 70,
+	ImportAssets2                = 71,
+	DoABC                        = 72,
+	DefineFontAlignZones         = 73,
+	CSMTextSettings              = 74,
+	DefineFont3                  = 75,
+	SymbolClass                  = 76,
+	Metadata                     = 77,
+	DefineScalingGrid            = 78,
+	DoABC2                       = 82,
+	DefineShape4                 = 83,
+	DefineMorphShape2            = 84,
+	DefineSceneAndFrameLabelData = 86,
+	DefineBinaryData             = 87,
+	DefineFontName               = 88,
+	DefineFont4                  = 91
 }
 
 private final class SWFWriter
@@ -230,28 +263,46 @@ private final class SWFWriter
 		buf ~= swf.frameSize.bytes;
 		buf ~= toArray(swf.frameRate);
 		buf ~= toArray(swf.frameCount);
-		
+
 		foreach (ref tag; swf.tags)
 		{
 			ushort u = cast(ushort)(tag.type << 6);
-			if (tag.data.length < 0x3F && !tag.forceLongLength)
+			if (tag.length < 0x3F && !tag.forceLongLength)
 			{
-				u |= tag.data.length;
+				u |= tag.length;
 				buf ~= toArray(u);
 			}
 			else
 			{
 				u |= 0x3F;
 				buf ~= toArray(u);
-				uint l = tag.data.length;
+				uint l = to!uint(tag.length);
 				buf ~= toArray(l);
 			}
 			buf ~= tag.data;
 		}
 
-		swf.header.fileLength = 8 + buf.length;
+		swf.header.fileLength = to!uint(swf.header.sizeof + buf.length);
 		if (swf.header.signature[0] == 'C')
 			buf = cast(ubyte[])compress(buf, 9);
+		else
+		if (swf.header.signature[0] == 'Z')
+		{
+			version (HAVE_LZMA)
+			{
+				lzma.LZMAHeader lzInfo;
+				buf = lzmaCompress(buf, &lzInfo);
+
+				SWFFile.LZMAHeader lzHeader;
+				lzHeader.compressionParameters = lzInfo.compressionParameters;
+				lzHeader.dictionarySize = lzInfo.dictionarySize;
+				lzHeader.compressedLength = to!uint(buf.length);
+
+				buf = cast(ubyte[])(&lzHeader)[0..1] ~ buf;
+			}
+			else
+				enforce(false, "This version was built without LZMA support");
+		}
 		buf = toArray(swf.header) ~ buf;
 
 		return buf;

swflzmacompress.d

@@ -0,0 +1,68 @@
+/*
+ *  Copyright 2010, 2011, 2012, 2013 Vladimir Panteleev <vladimir@thecybershadow.net>
+ *  This file is part of RABCDAsm.
+ *
+ *  RABCDAsm is free software: you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation, either version 3 of the License, or
+ *  (at your option) any later version.
+ *
+ *  RABCDAsm is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with RABCDAsm.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+module swflzmacompress;
+
+import std.exception;
+import std.file;
+import std.getopt;
+import std.string;
+import swffile;
+
+void main(string[] args)
+{
+	bool force, updateVersion;
+	getopt(args,
+		"--force", &force,
+		"--update-version", &updateVersion,
+	);
+
+	if (args.length == 1)
+		throw new Exception("No file specified");
+	enum MIN_LZMA_VER = 13;
+	foreach (arg; args[1..$])
+	{
+		auto swf = SWFFile.read(cast(ubyte[])read(arg));
+		enforce(swf.header.signature[0] != cast(ubyte)'Z', "Already LZMA-compressed");
+		if (swf.header.ver < MIN_LZMA_VER)
+		{
+			if (updateVersion)
+			{
+				if (swf.header.ver < 8 && !force)
+					throw new Exception(format(
+						"SWF version %d has different file format than version %d, " ~
+						"required for LZMA. Resulting file may not work. " ~
+						"Use --force to override and update version anyway.",
+						swf.header.ver, MIN_LZMA_VER
+					));
+				swf.header.ver = MIN_LZMA_VER;
+			}
+			else
+			if (!force)
+				throw new Exception(format(
+					"SWF version %d is too old to support SWF LZMA compression, " ~
+					"which requires version %d. " ~
+					"Use --update-version to update the version number, " ~
+					"or --force to compress anyway without updating it.",
+					swf.header.ver, MIN_LZMA_VER
+				));
+		}
+		swf.header.signature[0] = cast(ubyte)'Z'; // LZMA
+		write(arg, swf.write());
+	}
+}

zlibx.d

@@ -2,7 +2,7 @@
 
 module zlibx;
 
-import std.zlib, etc.c.zlib;
+import std.zlib, etc.c.zlib, std.conv;
 static import etc.c.zlib;
 alias std.zlib.Z_SYNC_FLUSH Z_SYNC_FLUSH;
 
@@ -13,12 +13,12 @@ ubyte[] exactUncompress(ubyte[] srcbuf, size_t destlen)
 
 	auto destbuf = new ubyte[destlen];
 	uint err;
-		
+
 	zs.next_in = srcbuf.ptr;
-	zs.avail_in = srcbuf.length;
+	zs.avail_in = to!uint(srcbuf.length);
 
 	zs.next_out = destbuf.ptr;
-	zs.avail_out = destbuf.length;
+	zs.avail_out = to!uint(destbuf.length);
 
 	err = etc.c.zlib.inflateInit2(&zs, 15);
 	if (err)
@@ -37,7 +37,7 @@ ubyte[] exactUncompress(ubyte[] srcbuf, size_t destlen)
 	}
 	if (zs.avail_out != 0)
 		throw new Exception("Too little data in stream");
-	
+
 	err = etc.c.zlib.inflateEnd(&zs);
 	if (err != Z_OK)
 		goto Lerr;