lzf 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 4e0c58aad17afd1248a64a10f0be8331b2dd8746
+  data.tar.gz: 041ecfa49d2475edba77b8895a10cddd490ea897
+SHA512:
+  metadata.gz: d5dce1978fbb60097806f8ba0bcad5227468dd9003746f54bf85f22db8dc0eb878caae3081df9a9a7577f206662a7eb65764fdf217525dce0b26b10dbde8f09f
+  data.tar.gz: 5d6997fdb1886e5f790326bc2e24a4502c0c4efd55044f17a0eab8c11fd7e60af2452a4bfd7ad09eb70b35c5802774ec0437fc66d115f07e074b5dab0e74b49f

data/.gitignore

@@ -0,0 +1,19 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+test_data
+

data/.ruby-gemset

@@ -0,0 +1 @@
+lzf

data/.ruby-version

@@ -0,0 +1 @@
+2.0.0

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in lzf.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 glebtv
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,34 @@
+# Lzf
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'lzf'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install lzf
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request
+
+## Credits
+
+Loosely based on https://bitbucket.org/winebarrel/lzf-ruby/overview
+which won't compile for me.

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/ext/extconf.rb

@@ -0,0 +1,4 @@
+require 'mkmf'
+
+create_makefile('lzf')
+

data/ext/lib/lzfP.h

@@ -0,0 +1,185 @@
+/*
+ * Copyright (c) 2000-2007 Marc Alexander Lehmann <schmorp@schmorp.de>
+ * 
+ * Redistribution and use in source and binary forms, with or without modifica-
+ * tion, are permitted provided that the following conditions are met:
+ * 
+ *   1.  Redistributions of source code must retain the above copyright notice,
+ *       this list of conditions and the following disclaimer.
+ * 
+ *   2.  Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ * 
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MER-
+ * CHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO
+ * EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPE-
+ * CIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTH-
+ * ERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
+ * OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * Alternatively, the contents of this file may be used under the terms of
+ * the GNU General Public License ("GPL") version 2 or any later version,
+ * in which case the provisions of the GPL are applicable instead of
+ * the above. If you wish to allow the use of your version of this file
+ * only under the terms of the GPL and not to allow others to use your
+ * version of this file under the BSD license, indicate your decision
+ * by deleting the provisions above and replace them with the notice
+ * and other provisions required by the GPL. If you do not delete the
+ * provisions above, a recipient may use your version of this file under
+ * either the BSD or the GPL.
+ */
+
+#ifndef LZFP_h
+#define LZFP_h
+
+#define STANDALONE 1 /* at the moment, this is ok. */
+
+#ifndef STANDALONE
+# include "lzf.h"
+#endif
+
+/*
+ * Size of hashtable is (1 << HLOG) * sizeof (char *)
+ * decompression is independent of the hash table size
+ * the difference between 15 and 14 is very small
+ * for small blocks (and 14 is usually a bit faster).
+ * For a low-memory/faster configuration, use HLOG == 13;
+ * For best compression, use 15 or 16 (or more, up to 22).
+ */
+#ifndef HLOG
+# define HLOG 16
+#endif
+
+/*
+ * Sacrifice very little compression quality in favour of compression speed.
+ * This gives almost the same compression as the default code, and is
+ * (very roughly) 15% faster. This is the preferred mode of operation.
+ */
+#ifndef VERY_FAST
+# define VERY_FAST 1
+#endif
+
+/*
+ * Sacrifice some more compression quality in favour of compression speed.
+ * (roughly 1-2% worse compression for large blocks and
+ * 9-10% for small, redundant, blocks and >>20% better speed in both cases)
+ * In short: when in need for speed, enable this for binary data,
+ * possibly disable this for text data.
+ */
+#ifndef ULTRA_FAST
+# define ULTRA_FAST 0
+#endif
+
+/*
+ * Unconditionally aligning does not cost very much, so do it if unsure
+ */
+#ifndef STRICT_ALIGN
+# define STRICT_ALIGN !(defined(__i386) || defined (__amd64))
+#endif
+
+/*
+ * You may choose to pre-set the hash table (might be faster on some
+ * modern cpus and large (>>64k) blocks, and also makes compression
+ * deterministic/repeatable when the configuration otherwise is the same).
+ */
+#ifndef INIT_HTAB
+# define INIT_HTAB 0
+#endif
+
+/*
+ * Avoid assigning values to errno variable? for some embedding purposes
+ * (linux kernel for example), this is necessary. NOTE: this breaks
+ * the documentation in lzf.h. Avoiding errno has no speed impact.
+ */
+#ifndef AVOID_ERRNO
+# define AVOID_ERRNO 0
+#endif
+
+/*
+ * Whether to pass the LZF_STATE variable as argument, or allocate it
+ * on the stack. For small-stack environments, define this to 1.
+ * NOTE: this breaks the prototype in lzf.h.
+ */
+#ifndef LZF_STATE_ARG
+# define LZF_STATE_ARG 0
+#endif
+
+/*
+ * Whether to add extra checks for input validity in lzf_decompress
+ * and return EINVAL if the input stream has been corrupted. This
+ * only shields against overflowing the input buffer and will not
+ * detect most corrupted streams.
+ * This check is not normally noticeable on modern hardware
+ * (<1% slowdown), but might slow down older cpus considerably.
+ */
+#ifndef CHECK_INPUT
+# define CHECK_INPUT 1
+#endif
+
+/*
+ * Whether to store pointers or offsets inside the hash table. On
+ * 64 bit architetcures, pointers take up twice as much space,
+ * and might also be slower. Default is to autodetect.
+ */
+/*#define LZF_USER_OFFSETS autodetect */
+
+/*****************************************************************************/
+/* nothing should be changed below */
+
+#ifdef __cplusplus
+# include <cstring>
+# include <climits>
+using namespace std;
+#else
+# include <string.h>
+# include <limits.h>
+#endif
+
+#ifndef LZF_USE_OFFSETS
+# if defined (WIN32)
+#  define LZF_USE_OFFSETS defined(_M_X64)
+# else
+#  if __cplusplus > 199711L
+#   include <cstdint>
+#  else
+#   include <stdint.h>
+#  endif
+#  define LZF_USE_OFFSETS (UINTPTR_MAX > 0xffffffffU)
+# endif
+#endif
+
+typedef unsigned char u8;
+
+#if LZF_USE_OFFSETS
+# define LZF_HSLOT_BIAS ((const u8 *)in_data)
+  typedef unsigned int LZF_HSLOT;
+#else
+# define LZF_HSLOT_BIAS 0
+  typedef const u8 *LZF_HSLOT;
+#endif
+
+typedef LZF_HSLOT LZF_STATE[1 << (HLOG)];
+
+#if !STRICT_ALIGN
+/* for unaligned accesses we need a 16 bit datatype. */
+# if USHRT_MAX == 65535
+    typedef unsigned short u16;
+# elif UINT_MAX == 65535
+    typedef unsigned int u16;
+# else
+#  undef STRICT_ALIGN
+#  define STRICT_ALIGN 1
+# endif
+#endif
+
+#if ULTRA_FAST
+# undef VERY_FAST
+#endif
+
+#endif
+

data/ext/lib/lzf_c.c

@@ -0,0 +1,291 @@
+/*
+ * Copyright (c) 2000-2010 Marc Alexander Lehmann <schmorp@schmorp.de>
+ * 
+ * Redistribution and use in source and binary forms, with or without modifica-
+ * tion, are permitted provided that the following conditions are met:
+ * 
+ *   1.  Redistributions of source code must retain the above copyright notice,
+ *       this list of conditions and the following disclaimer.
+ * 
+ *   2.  Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ * 
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MER-
+ * CHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO
+ * EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPE-
+ * CIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTH-
+ * ERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
+ * OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * Alternatively, the contents of this file may be used under the terms of
+ * the GNU General Public License ("GPL") version 2 or any later version,
+ * in which case the provisions of the GPL are applicable instead of
+ * the above. If you wish to allow the use of your version of this file
+ * only under the terms of the GPL and not to allow others to use your
+ * version of this file under the BSD license, indicate your decision
+ * by deleting the provisions above and replace them with the notice
+ * and other provisions required by the GPL. If you do not delete the
+ * provisions above, a recipient may use your version of this file under
+ * either the BSD or the GPL.
+ */
+
+#include "lzfP.h"
+
+#define HSIZE (1 << (HLOG))
+
+/*
+ * don't play with this unless you benchmark!
+ * the data format is not dependent on the hash function.
+ * the hash function might seem strange, just believe me,
+ * it works ;)
+ */
+#ifndef FRST
+# define FRST(p) (((p[0]) << 8) | p[1])
+# define NEXT(v,p) (((v) << 8) | p[2])
+# if ULTRA_FAST
+#  define IDX(h) ((( h             >> (3*8 - HLOG)) - h  ) & (HSIZE - 1))
+# elif VERY_FAST
+#  define IDX(h) ((( h             >> (3*8 - HLOG)) - h*5) & (HSIZE - 1))
+# else
+#  define IDX(h) ((((h ^ (h << 5)) >> (3*8 - HLOG)) - h*5) & (HSIZE - 1))
+# endif
+#endif
+/*
+ * IDX works because it is very similar to a multiplicative hash, e.g.
+ * ((h * 57321 >> (3*8 - HLOG)) & (HSIZE - 1))
+ * the latter is also quite fast on newer CPUs, and compresses similarly.
+ *
+ * the next one is also quite good, albeit slow ;)
+ * (int)(cos(h & 0xffffff) * 1e6)
+ */
+
+#if 0
+/* original lzv-like hash function, much worse and thus slower */
+# define FRST(p) (p[0] << 5) ^ p[1]
+# define NEXT(v,p) ((v) << 5) ^ p[2]
+# define IDX(h) ((h) & (HSIZE - 1))
+#endif
+
+#define        MAX_LIT        (1 <<  5)
+#define        MAX_OFF        (1 << 13)
+#define        MAX_REF        ((1 << 8) + (1 << 3))
+
+#if __GNUC__ >= 3
+# define expect(expr,value)         __builtin_expect ((expr),(value))
+# define inline                     inline
+#else
+# define expect(expr,value)         (expr)
+# define inline                     static
+#endif
+
+#define expect_false(expr) expect ((expr) != 0, 0)
+#define expect_true(expr)  expect ((expr) != 0, 1)
+
+/*
+ * compressed format
+ *
+ * 000LLLLL <L+1>    ; literal, L+1=1..33 octets
+ * LLLooooo oooooooo ; backref L+1=1..7 octets, o+1=1..4096 offset
+ * 111ooooo LLLLLLLL oooooooo ; backref L+8 octets, o+1=1..4096 offset
+ *
+ */
+
+unsigned int
+lzf_compress (const void *const in_data, unsigned int in_len,
+	      void *out_data, unsigned int out_len
+#if LZF_STATE_ARG
+              , LZF_STATE htab
+#endif
+              )
+{
+#if !LZF_STATE_ARG
+  LZF_STATE htab;
+#endif
+  const u8 *ip = (const u8 *)in_data;
+        u8 *op = (u8 *)out_data;
+  const u8 *in_end  = ip + in_len;
+        u8 *out_end = op + out_len;
+  const u8 *ref;
+
+  /* off requires a type wide enough to hold a general pointer difference.
+   * ISO C doesn't have that (size_t might not be enough and ptrdiff_t only
+   * works for differences within a single object). We also assume that no
+   * no bit pattern traps. Since the only platform that is both non-POSIX
+   * and fails to support both assumptions is windows 64 bit, we make a
+   * special workaround for it.
+   */
+#if defined (WIN32) && defined (_M_X64)
+  unsigned _int64 off; /* workaround for missing POSIX compliance */
+#else
+  unsigned long off;
+#endif
+  unsigned int hval;
+  int lit;
+
+  if (!in_len || !out_len)
+    return 0;
+
+#if INIT_HTAB
+  memset (htab, 0, sizeof (htab));
+#endif
+
+  lit = 0; op++; /* start run */
+
+  hval = FRST (ip);
+  while (ip < in_end - 2)
+    {
+      LZF_HSLOT *hslot;
+
+      hval = NEXT (hval, ip);
+      hslot = htab + IDX (hval);
+      ref = *hslot + LZF_HSLOT_BIAS; *hslot = ip - LZF_HSLOT_BIAS;
+
+      if (1
+#if INIT_HTAB
+          && ref < ip /* the next test will actually take care of this, but this is faster */
+#endif
+          && (off = ip - ref - 1) < MAX_OFF
+          && ref > (u8 *)in_data
+          && ref[2] == ip[2]
+#if STRICT_ALIGN
+          && ((ref[1] << 8) | ref[0]) == ((ip[1] << 8) | ip[0])
+#else
+          && *(u16 *)ref == *(u16 *)ip
+#endif
+        )
+        {
+          /* match found at *ref++ */
+          unsigned int len = 2;
+          unsigned int maxlen = in_end - ip - len;
+          maxlen = maxlen > MAX_REF ? MAX_REF : maxlen;
+
+          if (expect_false (op + 3 + 1 >= out_end)) /* first a faster conservative test */
+            if (op - !lit + 3 + 1 >= out_end) /* second the exact but rare test */
+              return 0;
+
+          op [- lit - 1] = lit - 1; /* stop run */
+          op -= !lit; /* undo run if length is zero */
+
+          for (;;)
+            {
+              if (expect_true (maxlen > 16))
+                {
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+                  len++; if (ref [len] != ip [len]) break;
+                }
+
+              do
+                len++;
+              while (len < maxlen && ref[len] == ip[len]);
+
+              break;
+            }
+
+          len -= 2; /* len is now #octets - 1 */
+          ip++;
+
+          if (len < 7)
+            {
+              *op++ = (off >> 8) + (len << 5);
+            }
+          else
+            {
+              *op++ = (off >> 8) + (  7 << 5);
+              *op++ = len - 7;
+            }
+
+          *op++ = off;
+
+          lit = 0; op++; /* start run */
+
+          ip += len + 1;
+
+          if (expect_false (ip >= in_end - 2))
+            break;
+
+#if ULTRA_FAST || VERY_FAST
+          --ip;
+# if VERY_FAST && !ULTRA_FAST
+          --ip;
+# endif
+          hval = FRST (ip);
+
+          hval = NEXT (hval, ip);
+          htab[IDX (hval)] = ip - LZF_HSLOT_BIAS;
+          ip++;
+
+# if VERY_FAST && !ULTRA_FAST
+          hval = NEXT (hval, ip);
+          htab[IDX (hval)] = ip - LZF_HSLOT_BIAS;
+          ip++;
+# endif
+#else
+          ip -= len + 1;
+
+          do
+            {
+              hval = NEXT (hval, ip);
+              htab[IDX (hval)] = ip - LZF_HSLOT_BIAS;
+              ip++;
+            }
+          while (len--);
+#endif
+        }
+      else
+        {
+          /* one more literal byte we must copy */
+          if (expect_false (op >= out_end))
+            return 0;
+
+          lit++; *op++ = *ip++;
+
+          if (expect_false (lit == MAX_LIT))
+            {
+              op [- lit - 1] = lit - 1; /* stop run */
+              lit = 0; op++; /* start run */
+            }
+        }
+    }
+
+  if (op + 3 > out_end) /* at most 3 bytes can be missing here */
+    return 0;
+
+  while (ip < in_end)
+    {
+      lit++; *op++ = *ip++;
+
+      if (expect_false (lit == MAX_LIT))
+        {
+          op [- lit - 1] = lit - 1; /* stop run */
+          lit = 0; op++; /* start run */
+        }
+    }
+
+  op [- lit - 1] = lit - 1; /* end run */
+  op -= !lit; /* undo run if length is zero */
+
+  return op - (u8 *)out_data;
+}
+

data/ext/lib/lzf_d.c

@@ -0,0 +1,185 @@
+/*
+ * Copyright (c) 2000-2010 Marc Alexander Lehmann <schmorp@schmorp.de>
+ * 
+ * Redistribution and use in source and binary forms, with or without modifica-
+ * tion, are permitted provided that the following conditions are met:
+ * 
+ *   1.  Redistributions of source code must retain the above copyright notice,
+ *       this list of conditions and the following disclaimer.
+ * 
+ *   2.  Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ * 
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MER-
+ * CHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO
+ * EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPE-
+ * CIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTH-
+ * ERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
+ * OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * Alternatively, the contents of this file may be used under the terms of
+ * the GNU General Public License ("GPL") version 2 or any later version,
+ * in which case the provisions of the GPL are applicable instead of
+ * the above. If you wish to allow the use of your version of this file
+ * only under the terms of the GPL and not to allow others to use your
+ * version of this file under the BSD license, indicate your decision
+ * by deleting the provisions above and replace them with the notice
+ * and other provisions required by the GPL. If you do not delete the
+ * provisions above, a recipient may use your version of this file under
+ * either the BSD or the GPL.
+ */
+
+#include "lzfP.h"
+
+#if AVOID_ERRNO
+# define SET_ERRNO(n)
+#else
+# include <errno.h>
+# define SET_ERRNO(n) errno = (n)
+#endif
+
+#if USE_REP_MOVSB /* small win on amd, big loss on intel */
+#if (__i386 || __amd64) && __GNUC__ >= 3
+# define lzf_movsb(dst, src, len)                \
+   asm ("rep movsb"                              \
+        : "=D" (dst), "=S" (src), "=c" (len)     \
+        :  "0" (dst),  "1" (src),  "2" (len));
+#endif
+#endif
+
+unsigned int 
+lzf_decompress (const void *const in_data,  unsigned int in_len,
+                void             *out_data, unsigned int out_len)
+{
+  u8 const *ip = (const u8 *)in_data;
+  u8       *op = (u8 *)out_data;
+  u8 const *const in_end  = ip + in_len;
+  u8       *const out_end = op + out_len;
+
+  do
+    {
+      unsigned int ctrl = *ip++;
+
+      if (ctrl < (1 << 5)) /* literal run */
+        {
+          ctrl++;
+
+          if (op + ctrl > out_end)
+            {
+              SET_ERRNO (E2BIG);
+              return 0;
+            }
+
+#if CHECK_INPUT
+          if (ip + ctrl > in_end)
+            {
+              SET_ERRNO (EINVAL);
+              return 0;
+            }
+#endif
+
+#ifdef lzf_movsb
+          lzf_movsb (op, ip, ctrl);
+#else
+          switch (ctrl)
+            {
+              case 32: *op++ = *ip++; case 31: *op++ = *ip++; case 30: *op++ = *ip++; case 29: *op++ = *ip++;
+              case 28: *op++ = *ip++; case 27: *op++ = *ip++; case 26: *op++ = *ip++; case 25: *op++ = *ip++;
+              case 24: *op++ = *ip++; case 23: *op++ = *ip++; case 22: *op++ = *ip++; case 21: *op++ = *ip++;
+              case 20: *op++ = *ip++; case 19: *op++ = *ip++; case 18: *op++ = *ip++; case 17: *op++ = *ip++;
+              case 16: *op++ = *ip++; case 15: *op++ = *ip++; case 14: *op++ = *ip++; case 13: *op++ = *ip++;
+              case 12: *op++ = *ip++; case 11: *op++ = *ip++; case 10: *op++ = *ip++; case  9: *op++ = *ip++;
+              case  8: *op++ = *ip++; case  7: *op++ = *ip++; case  6: *op++ = *ip++; case  5: *op++ = *ip++;
+              case  4: *op++ = *ip++; case  3: *op++ = *ip++; case  2: *op++ = *ip++; case  1: *op++ = *ip++;
+            }
+#endif
+        }
+      else /* back reference */
+        {
+          unsigned int len = ctrl >> 5;
+
+          u8 *ref = op - ((ctrl & 0x1f) << 8) - 1;
+
+#if CHECK_INPUT
+          if (ip >= in_end)
+            {
+              SET_ERRNO (EINVAL);
+              return 0;
+            }
+#endif
+          if (len == 7)
+            {
+              len += *ip++;
+#if CHECK_INPUT
+              if (ip >= in_end)
+                {
+                  SET_ERRNO (EINVAL);
+                  return 0;
+                }
+#endif
+            }
+
+          ref -= *ip++;
+
+          if (op + len + 2 > out_end)
+            {
+              SET_ERRNO (E2BIG);
+              return 0;
+            }
+
+          if (ref < (u8 *)out_data)
+            {
+              SET_ERRNO (EINVAL);
+              return 0;
+            }
+
+#ifdef lzf_movsb
+          len += 2;
+          lzf_movsb (op, ref, len);
+#else
+          switch (len)
+            {
+              default:
+                len += 2;
+
+                if (op >= ref + len)
+                  {
+                    /* disjunct areas */
+                    memcpy (op, ref, len);
+                    op += len;
+                  }
+                else
+                  {
+                    /* overlapping, use octte by octte copying */
+                    do
+                      *op++ = *ref++;
+                    while (--len);
+                  }
+
+                break;
+
+              case 9: *op++ = *ref++;
+              case 8: *op++ = *ref++;
+              case 7: *op++ = *ref++;
+              case 6: *op++ = *ref++;
+              case 5: *op++ = *ref++;
+              case 4: *op++ = *ref++;
+              case 3: *op++ = *ref++;
+              case 2: *op++ = *ref++;
+              case 1: *op++ = *ref++;
+              case 0: *op++ = *ref++; /* two octets more */
+                      *op++ = *ref++;
+            }
+#endif
+        }
+    }
+  while (ip < in_end);
+
+  return op - (u8 *)out_data;
+}
+

data/ext/lzf.c

@@ -0,0 +1,70 @@
+#include <ruby.h>
+
+#include "lib/lzf_c.c"
+#include "lib/lzf_d.c"
+
+static VALUE rb_mLZF;
+static VALUE rb_eLZF;
+
+static VALUE lzfruby_compress(int argc, VALUE *argv, VALUE self) {
+  VALUE src, dst;
+  unsigned int output_length, result;
+
+  rb_scan_args(argc, argv, "1", &src);
+
+  StringValue(src);
+
+  output_length = (unsigned int) (RSTRING_LEN(src) * 1.05);
+
+  dst = rb_str_new(NULL, output_length);
+
+  result = lzf_compress(RSTRING_PTR(src), RSTRING_LEN(src), RSTRING_PTR(dst), &output_length);
+  if (result == 0) {
+    rb_raise(rb_eLZF, "ERROR");
+    return Qnil;
+  } else {
+    StringValue(dst);
+    rb_str_resize(dst, result);
+    return dst;
+  }
+}
+
+static VALUE lzfruby_decompress(int argc, VALUE *argv, VALUE self) {
+  VALUE src, dst;
+  rb_scan_args(argc, argv, "1", &src);
+  StringValue(src);
+  unsigned int result, i = 1, buffer_size = 1024;
+
+  dst = rb_str_new(NULL, buffer_size);
+
+  // Pretty inefficient for large data, but PHP does it the same way
+  do {
+    buffer_size *= i++;
+    rb_str_resize(dst, buffer_size);
+    result = lzf_decompress(RSTRING_PTR(src), RSTRING_LEN(src), RSTRING_PTR(dst), buffer_size);
+  } while (result == 0 && errno == E2BIG);
+
+  if (result == 0) {
+    if (errno == EINVAL) {
+      rb_raise(rb_eLZF, "LZF error: compressed data corrupted");
+      return Qnil;
+    } else {
+      rb_raise(rb_eLZF, printf("LZF error %d", errno));
+      return Qnil;
+    }
+  } else {
+    StringValue(dst);
+    rb_str_resize(dst, result);
+    return dst;
+  }
+}
+
+
+void Init_lzf(void) {
+  rb_mLZF = rb_define_module("LZF");
+  rb_eLZF = rb_define_class_under(rb_mLZF, "Error", rb_eStandardError);
+
+  rb_define_singleton_method(rb_mLZF, "compress", lzfruby_compress, -1);
+  rb_define_singleton_method(rb_mLZF, "decompress", lzfruby_decompress, -1);
+}
+

data/lib/lzf/version.rb

@@ -0,0 +1,3 @@
+module Lzf
+  VERSION = "0.0.1"
+end

data/lzf.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'lzf/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "lzf"
+  spec.version       = Lzf::VERSION
+  spec.authors       = ["glebtv"]
+  spec.email         = ["glebtv@gmail.com"]
+  spec.description   = %q{LZF compression with liblzf for ruby}
+  spec.summary       = %q{LZF compression with liblzf for ruby}
+  spec.homepage      = "https://github.com/glebtv/lzf"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  
+  spec.extensions    = ['ext/extconf.rb']
+  
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+end

data/test.rb

@@ -0,0 +1,20 @@
+require 'lzf'
+require 'zlib'
+
+Dir.glob('./test_data/*.lzf').each do |f|
+  hash = File.basename(f, '.lzf')
+  # puts hash
+  compressed = File.read(f)
+  decompressed = LZF.decompress(compressed)
+  # p decompressed
+  if Zlib.adler32(decompressed) != hash.to_f
+    puts "crc error: #{Zlib.adler32(decompressed)} != #{hash}"
+    puts decompressed
+  end
+
+  if LZF.decompress(LZF.compress(decompressed)) != decompressed
+    puts "#{hash} compressed != decompressed"
+  end
+end
+
+puts "all ok"

metadata

@@ -0,0 +1,88 @@
+--- !ruby/object:Gem::Specification
+name: lzf
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- glebtv
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-06-01 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: LZF compression with liblzf for ruby
+email:
+- glebtv@gmail.com
+executables: []
+extensions:
+- ext/extconf.rb
+extra_rdoc_files: []
+files:
+- .gitignore
+- .ruby-gemset
+- .ruby-version
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- ext/extconf.rb
+- ext/lib/lzfP.h
+- ext/lib/lzf_c.c
+- ext/lib/lzf_d.c
+- ext/lzf.c
+- lib/lzf/version.rb
+- lzf.gemspec
+- test.rb
+homepage: https://github.com/glebtv/lzf
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.3
+signing_key: 
+specification_version: 4
+summary: LZF compression with liblzf for ruby
+test_files: []