snappy 0.0.10 → 0.0.11
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.gitmodules +3 -0
- data/Rakefile +12 -13
- data/ext/extconf.rb +22 -31
- data/lib/snappy/reader.rb +10 -7
- data/lib/snappy/version.rb +1 -1
- data/snappy.gemspec +24 -0
- data/test/test-snappy-reader.rb +16 -0
- data/vendor/snappy/AUTHORS +1 -0
- data/vendor/snappy/COPYING +54 -0
- data/vendor/snappy/ChangeLog +1916 -0
- data/vendor/snappy/Makefile.am +23 -0
- data/vendor/snappy/NEWS +128 -0
- data/vendor/snappy/README +135 -0
- data/vendor/snappy/autogen.sh +7 -0
- data/vendor/snappy/configure.ac +133 -0
- data/vendor/snappy/format_description.txt +110 -0
- data/vendor/snappy/framing_format.txt +135 -0
- data/vendor/snappy/m4/gtest.m4 +74 -0
- data/vendor/snappy/snappy-c.cc +90 -0
- data/vendor/snappy/snappy-c.h +138 -0
- data/vendor/snappy/snappy-internal.h +150 -0
- data/vendor/snappy/snappy-sinksource.cc +71 -0
- data/vendor/snappy/snappy-sinksource.h +137 -0
- data/vendor/snappy/snappy-stubs-internal.cc +42 -0
- data/vendor/snappy/snappy-stubs-internal.h +491 -0
- data/vendor/snappy/snappy-stubs-public.h.in +98 -0
- data/vendor/snappy/snappy-test.cc +606 -0
- data/vendor/snappy/snappy-test.h +582 -0
- data/vendor/snappy/snappy.cc +1306 -0
- data/vendor/snappy/snappy.h +184 -0
- data/vendor/snappy/snappy_unittest.cc +1355 -0
- data/vendor/snappy/testdata/alice29.txt +3609 -0
- data/vendor/snappy/testdata/asyoulik.txt +4122 -0
- data/vendor/snappy/testdata/baddata1.snappy +0 -0
- data/vendor/snappy/testdata/baddata2.snappy +0 -0
- data/vendor/snappy/testdata/baddata3.snappy +0 -0
- data/vendor/snappy/testdata/fireworks.jpeg +0 -0
- data/vendor/snappy/testdata/geo.protodata +0 -0
- data/vendor/snappy/testdata/html +1 -0
- data/vendor/snappy/testdata/html_x_4 +1 -0
- data/vendor/snappy/testdata/kppkn.gtb +0 -0
- data/vendor/snappy/testdata/lcet10.txt +7519 -0
- data/vendor/snappy/testdata/paper-100k.pdf +600 -2
- data/vendor/snappy/testdata/plrabn12.txt +10699 -0
- data/vendor/snappy/testdata/urls.10K +10000 -0
- metadata +51 -12
@@ -0,0 +1,74 @@
|
|
1
|
+
dnl GTEST_LIB_CHECK([minimum version [,
|
2
|
+
dnl action if found [,action if not found]]])
|
3
|
+
dnl
|
4
|
+
dnl Check for the presence of the Google Test library, optionally at a minimum
|
5
|
+
dnl version, and indicate a viable version with the HAVE_GTEST flag. It defines
|
6
|
+
dnl standard variables for substitution including GTEST_CPPFLAGS,
|
7
|
+
dnl GTEST_CXXFLAGS, GTEST_LDFLAGS, and GTEST_LIBS. It also defines
|
8
|
+
dnl GTEST_VERSION as the version of Google Test found. Finally, it provides
|
9
|
+
dnl optional custom action slots in the event GTEST is found or not.
|
10
|
+
AC_DEFUN([GTEST_LIB_CHECK],
|
11
|
+
[
|
12
|
+
dnl Provide a flag to enable or disable Google Test usage.
|
13
|
+
AC_ARG_ENABLE([gtest],
|
14
|
+
[AS_HELP_STRING([--enable-gtest],
|
15
|
+
[Enable tests using the Google C++ Testing Framework.
|
16
|
+
(Default is enabled.)])],
|
17
|
+
[],
|
18
|
+
[enable_gtest=])
|
19
|
+
AC_ARG_VAR([GTEST_CONFIG],
|
20
|
+
[The exact path of Google Test's 'gtest-config' script.])
|
21
|
+
AC_ARG_VAR([GTEST_CPPFLAGS],
|
22
|
+
[C-like preprocessor flags for Google Test.])
|
23
|
+
AC_ARG_VAR([GTEST_CXXFLAGS],
|
24
|
+
[C++ compile flags for Google Test.])
|
25
|
+
AC_ARG_VAR([GTEST_LDFLAGS],
|
26
|
+
[Linker path and option flags for Google Test.])
|
27
|
+
AC_ARG_VAR([GTEST_LIBS],
|
28
|
+
[Library linking flags for Google Test.])
|
29
|
+
AC_ARG_VAR([GTEST_VERSION],
|
30
|
+
[The version of Google Test available.])
|
31
|
+
HAVE_GTEST="no"
|
32
|
+
AS_IF([test "x${enable_gtest}" != "xno"],
|
33
|
+
[AC_MSG_CHECKING([for 'gtest-config'])
|
34
|
+
AS_IF([test "x${enable_gtest}" = "xyes"],
|
35
|
+
[AS_IF([test -x "${enable_gtest}/scripts/gtest-config"],
|
36
|
+
[GTEST_CONFIG="${enable_gtest}/scripts/gtest-config"],
|
37
|
+
[GTEST_CONFIG="${enable_gtest}/bin/gtest-config"])
|
38
|
+
AS_IF([test -x "${GTEST_CONFIG}"], [],
|
39
|
+
[AC_MSG_RESULT([no])
|
40
|
+
AC_MSG_ERROR([dnl
|
41
|
+
Unable to locate either a built or installed Google Test.
|
42
|
+
The specific location '${enable_gtest}' was provided for a built or installed
|
43
|
+
Google Test, but no 'gtest-config' script could be found at this location.])
|
44
|
+
])],
|
45
|
+
[AC_PATH_PROG([GTEST_CONFIG], [gtest-config])])
|
46
|
+
AS_IF([test -x "${GTEST_CONFIG}"],
|
47
|
+
[AC_MSG_RESULT([${GTEST_CONFIG}])
|
48
|
+
m4_ifval([$1],
|
49
|
+
[_gtest_min_version="--min-version=$1"
|
50
|
+
AC_MSG_CHECKING([for Google Test at least version >= $1])],
|
51
|
+
[_gtest_min_version="--min-version=0"
|
52
|
+
AC_MSG_CHECKING([for Google Test])])
|
53
|
+
AS_IF([${GTEST_CONFIG} ${_gtest_min_version}],
|
54
|
+
[AC_MSG_RESULT([yes])
|
55
|
+
HAVE_GTEST='yes'],
|
56
|
+
[AC_MSG_RESULT([no])])],
|
57
|
+
[AC_MSG_RESULT([no])])
|
58
|
+
AS_IF([test "x${HAVE_GTEST}" = "xyes"],
|
59
|
+
[GTEST_CPPFLAGS=`${GTEST_CONFIG} --cppflags`
|
60
|
+
GTEST_CXXFLAGS=`${GTEST_CONFIG} --cxxflags`
|
61
|
+
GTEST_LDFLAGS=`${GTEST_CONFIG} --ldflags`
|
62
|
+
GTEST_LIBS=`${GTEST_CONFIG} --libs`
|
63
|
+
GTEST_VERSION=`${GTEST_CONFIG} --version`
|
64
|
+
AC_DEFINE([HAVE_GTEST],[1],[Defined when Google Test is available.])],
|
65
|
+
[AS_IF([test "x${enable_gtest}" = "xyes"],
|
66
|
+
[AC_MSG_ERROR([dnl
|
67
|
+
Google Test was enabled, but no viable version could be found.])
|
68
|
+
])])])
|
69
|
+
AC_SUBST([HAVE_GTEST])
|
70
|
+
AM_CONDITIONAL([HAVE_GTEST],[test "x$HAVE_GTEST" = "xyes"])
|
71
|
+
AS_IF([test "x$HAVE_GTEST" = "xyes"],
|
72
|
+
[m4_ifval([$2], [$2])],
|
73
|
+
[m4_ifval([$3], [$3])])
|
74
|
+
])
|
@@ -0,0 +1,90 @@
|
|
1
|
+
// Copyright 2011 Martin Gieseking <martin.gieseking@uos.de>.
|
2
|
+
//
|
3
|
+
// Redistribution and use in source and binary forms, with or without
|
4
|
+
// modification, are permitted provided that the following conditions are
|
5
|
+
// met:
|
6
|
+
//
|
7
|
+
// * Redistributions of source code must retain the above copyright
|
8
|
+
// notice, this list of conditions and the following disclaimer.
|
9
|
+
// * Redistributions in binary form must reproduce the above
|
10
|
+
// copyright notice, this list of conditions and the following disclaimer
|
11
|
+
// in the documentation and/or other materials provided with the
|
12
|
+
// distribution.
|
13
|
+
// * Neither the name of Google Inc. nor the names of its
|
14
|
+
// contributors may be used to endorse or promote products derived from
|
15
|
+
// this software without specific prior written permission.
|
16
|
+
//
|
17
|
+
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
18
|
+
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
19
|
+
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
20
|
+
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
21
|
+
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
22
|
+
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
23
|
+
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
24
|
+
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
25
|
+
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
26
|
+
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
27
|
+
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
28
|
+
|
29
|
+
#include "snappy.h"
|
30
|
+
#include "snappy-c.h"
|
31
|
+
|
32
|
+
extern "C" {
|
33
|
+
|
34
|
+
snappy_status snappy_compress(const char* input,
|
35
|
+
size_t input_length,
|
36
|
+
char* compressed,
|
37
|
+
size_t *compressed_length) {
|
38
|
+
if (*compressed_length < snappy_max_compressed_length(input_length)) {
|
39
|
+
return SNAPPY_BUFFER_TOO_SMALL;
|
40
|
+
}
|
41
|
+
snappy::RawCompress(input, input_length, compressed, compressed_length);
|
42
|
+
return SNAPPY_OK;
|
43
|
+
}
|
44
|
+
|
45
|
+
snappy_status snappy_uncompress(const char* compressed,
|
46
|
+
size_t compressed_length,
|
47
|
+
char* uncompressed,
|
48
|
+
size_t* uncompressed_length) {
|
49
|
+
size_t real_uncompressed_length;
|
50
|
+
if (!snappy::GetUncompressedLength(compressed,
|
51
|
+
compressed_length,
|
52
|
+
&real_uncompressed_length)) {
|
53
|
+
return SNAPPY_INVALID_INPUT;
|
54
|
+
}
|
55
|
+
if (*uncompressed_length < real_uncompressed_length) {
|
56
|
+
return SNAPPY_BUFFER_TOO_SMALL;
|
57
|
+
}
|
58
|
+
if (!snappy::RawUncompress(compressed, compressed_length, uncompressed)) {
|
59
|
+
return SNAPPY_INVALID_INPUT;
|
60
|
+
}
|
61
|
+
*uncompressed_length = real_uncompressed_length;
|
62
|
+
return SNAPPY_OK;
|
63
|
+
}
|
64
|
+
|
65
|
+
size_t snappy_max_compressed_length(size_t source_length) {
|
66
|
+
return snappy::MaxCompressedLength(source_length);
|
67
|
+
}
|
68
|
+
|
69
|
+
snappy_status snappy_uncompressed_length(const char *compressed,
|
70
|
+
size_t compressed_length,
|
71
|
+
size_t *result) {
|
72
|
+
if (snappy::GetUncompressedLength(compressed,
|
73
|
+
compressed_length,
|
74
|
+
result)) {
|
75
|
+
return SNAPPY_OK;
|
76
|
+
} else {
|
77
|
+
return SNAPPY_INVALID_INPUT;
|
78
|
+
}
|
79
|
+
}
|
80
|
+
|
81
|
+
snappy_status snappy_validate_compressed_buffer(const char *compressed,
|
82
|
+
size_t compressed_length) {
|
83
|
+
if (snappy::IsValidCompressedBuffer(compressed, compressed_length)) {
|
84
|
+
return SNAPPY_OK;
|
85
|
+
} else {
|
86
|
+
return SNAPPY_INVALID_INPUT;
|
87
|
+
}
|
88
|
+
}
|
89
|
+
|
90
|
+
} // extern "C"
|
@@ -0,0 +1,138 @@
|
|
1
|
+
/*
|
2
|
+
* Copyright 2011 Martin Gieseking <martin.gieseking@uos.de>.
|
3
|
+
*
|
4
|
+
* Redistribution and use in source and binary forms, with or without
|
5
|
+
* modification, are permitted provided that the following conditions are
|
6
|
+
* met:
|
7
|
+
*
|
8
|
+
* * Redistributions of source code must retain the above copyright
|
9
|
+
* notice, this list of conditions and the following disclaimer.
|
10
|
+
* * Redistributions in binary form must reproduce the above
|
11
|
+
* copyright notice, this list of conditions and the following disclaimer
|
12
|
+
* in the documentation and/or other materials provided with the
|
13
|
+
* distribution.
|
14
|
+
* * Neither the name of Google Inc. nor the names of its
|
15
|
+
* contributors may be used to endorse or promote products derived from
|
16
|
+
* this software without specific prior written permission.
|
17
|
+
*
|
18
|
+
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
19
|
+
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
20
|
+
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
21
|
+
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
22
|
+
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
23
|
+
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
24
|
+
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
25
|
+
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
26
|
+
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
27
|
+
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
28
|
+
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
29
|
+
*
|
30
|
+
* Plain C interface (a wrapper around the C++ implementation).
|
31
|
+
*/
|
32
|
+
|
33
|
+
#ifndef UTIL_SNAPPY_OPENSOURCE_SNAPPY_C_H_
|
34
|
+
#define UTIL_SNAPPY_OPENSOURCE_SNAPPY_C_H_
|
35
|
+
|
36
|
+
#ifdef __cplusplus
|
37
|
+
extern "C" {
|
38
|
+
#endif
|
39
|
+
|
40
|
+
#include <stddef.h>
|
41
|
+
|
42
|
+
/*
|
43
|
+
* Return values; see the documentation for each function to know
|
44
|
+
* what each can return.
|
45
|
+
*/
|
46
|
+
typedef enum {
|
47
|
+
SNAPPY_OK = 0,
|
48
|
+
SNAPPY_INVALID_INPUT = 1,
|
49
|
+
SNAPPY_BUFFER_TOO_SMALL = 2
|
50
|
+
} snappy_status;
|
51
|
+
|
52
|
+
/*
|
53
|
+
* Takes the data stored in "input[0..input_length-1]" and stores
|
54
|
+
* it in the array pointed to by "compressed".
|
55
|
+
*
|
56
|
+
* <compressed_length> signals the space available in "compressed".
|
57
|
+
* If it is not at least equal to "snappy_max_compressed_length(input_length)",
|
58
|
+
* SNAPPY_BUFFER_TOO_SMALL is returned. After successful compression,
|
59
|
+
* <compressed_length> contains the true length of the compressed output,
|
60
|
+
* and SNAPPY_OK is returned.
|
61
|
+
*
|
62
|
+
* Example:
|
63
|
+
* size_t output_length = snappy_max_compressed_length(input_length);
|
64
|
+
* char* output = (char*)malloc(output_length);
|
65
|
+
* if (snappy_compress(input, input_length, output, &output_length)
|
66
|
+
* == SNAPPY_OK) {
|
67
|
+
* ... Process(output, output_length) ...
|
68
|
+
* }
|
69
|
+
* free(output);
|
70
|
+
*/
|
71
|
+
snappy_status snappy_compress(const char* input,
|
72
|
+
size_t input_length,
|
73
|
+
char* compressed,
|
74
|
+
size_t* compressed_length);
|
75
|
+
|
76
|
+
/*
|
77
|
+
* Given data in "compressed[0..compressed_length-1]" generated by
|
78
|
+
* calling the snappy_compress routine, this routine stores
|
79
|
+
* the uncompressed data to
|
80
|
+
* uncompressed[0..uncompressed_length-1].
|
81
|
+
* Returns failure (a value not equal to SNAPPY_OK) if the message
|
82
|
+
* is corrupted and could not be decrypted.
|
83
|
+
*
|
84
|
+
* <uncompressed_length> signals the space available in "uncompressed".
|
85
|
+
* If it is not at least equal to the value returned by
|
86
|
+
* snappy_uncompressed_length for this stream, SNAPPY_BUFFER_TOO_SMALL
|
87
|
+
* is returned. After successful decompression, <uncompressed_length>
|
88
|
+
* contains the true length of the decompressed output.
|
89
|
+
*
|
90
|
+
* Example:
|
91
|
+
* size_t output_length;
|
92
|
+
* if (snappy_uncompressed_length(input, input_length, &output_length)
|
93
|
+
* != SNAPPY_OK) {
|
94
|
+
* ... fail ...
|
95
|
+
* }
|
96
|
+
* char* output = (char*)malloc(output_length);
|
97
|
+
* if (snappy_uncompress(input, input_length, output, &output_length)
|
98
|
+
* == SNAPPY_OK) {
|
99
|
+
* ... Process(output, output_length) ...
|
100
|
+
* }
|
101
|
+
* free(output);
|
102
|
+
*/
|
103
|
+
snappy_status snappy_uncompress(const char* compressed,
|
104
|
+
size_t compressed_length,
|
105
|
+
char* uncompressed,
|
106
|
+
size_t* uncompressed_length);
|
107
|
+
|
108
|
+
/*
|
109
|
+
* Returns the maximal size of the compressed representation of
|
110
|
+
* input data that is "source_length" bytes in length.
|
111
|
+
*/
|
112
|
+
size_t snappy_max_compressed_length(size_t source_length);
|
113
|
+
|
114
|
+
/*
|
115
|
+
* REQUIRES: "compressed[]" was produced by snappy_compress()
|
116
|
+
* Returns SNAPPY_OK and stores the length of the uncompressed data in
|
117
|
+
* *result normally. Returns SNAPPY_INVALID_INPUT on parsing error.
|
118
|
+
* This operation takes O(1) time.
|
119
|
+
*/
|
120
|
+
snappy_status snappy_uncompressed_length(const char* compressed,
|
121
|
+
size_t compressed_length,
|
122
|
+
size_t* result);
|
123
|
+
|
124
|
+
/*
|
125
|
+
* Check if the contents of "compressed[]" can be uncompressed successfully.
|
126
|
+
* Does not return the uncompressed data; if so, returns SNAPPY_OK,
|
127
|
+
* or if not, returns SNAPPY_INVALID_INPUT.
|
128
|
+
* Takes time proportional to compressed_length, but is usually at least a
|
129
|
+
* factor of four faster than actual decompression.
|
130
|
+
*/
|
131
|
+
snappy_status snappy_validate_compressed_buffer(const char* compressed,
|
132
|
+
size_t compressed_length);
|
133
|
+
|
134
|
+
#ifdef __cplusplus
|
135
|
+
} // extern "C"
|
136
|
+
#endif
|
137
|
+
|
138
|
+
#endif /* UTIL_SNAPPY_OPENSOURCE_SNAPPY_C_H_ */
|
@@ -0,0 +1,150 @@
|
|
1
|
+
// Copyright 2008 Google Inc. All Rights Reserved.
|
2
|
+
//
|
3
|
+
// Redistribution and use in source and binary forms, with or without
|
4
|
+
// modification, are permitted provided that the following conditions are
|
5
|
+
// met:
|
6
|
+
//
|
7
|
+
// * Redistributions of source code must retain the above copyright
|
8
|
+
// notice, this list of conditions and the following disclaimer.
|
9
|
+
// * Redistributions in binary form must reproduce the above
|
10
|
+
// copyright notice, this list of conditions and the following disclaimer
|
11
|
+
// in the documentation and/or other materials provided with the
|
12
|
+
// distribution.
|
13
|
+
// * Neither the name of Google Inc. nor the names of its
|
14
|
+
// contributors may be used to endorse or promote products derived from
|
15
|
+
// this software without specific prior written permission.
|
16
|
+
//
|
17
|
+
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
18
|
+
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
19
|
+
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
20
|
+
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
21
|
+
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
22
|
+
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
23
|
+
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
24
|
+
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
25
|
+
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
26
|
+
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
27
|
+
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
28
|
+
//
|
29
|
+
// Internals shared between the Snappy implementation and its unittest.
|
30
|
+
|
31
|
+
#ifndef UTIL_SNAPPY_SNAPPY_INTERNAL_H_
|
32
|
+
#define UTIL_SNAPPY_SNAPPY_INTERNAL_H_
|
33
|
+
|
34
|
+
#include "snappy-stubs-internal.h"
|
35
|
+
|
36
|
+
namespace snappy {
|
37
|
+
namespace internal {
|
38
|
+
|
39
|
+
class WorkingMemory {
|
40
|
+
public:
|
41
|
+
WorkingMemory() : large_table_(NULL) { }
|
42
|
+
~WorkingMemory() { delete[] large_table_; }
|
43
|
+
|
44
|
+
// Allocates and clears a hash table using memory in "*this",
|
45
|
+
// stores the number of buckets in "*table_size" and returns a pointer to
|
46
|
+
// the base of the hash table.
|
47
|
+
uint16* GetHashTable(size_t input_size, int* table_size);
|
48
|
+
|
49
|
+
private:
|
50
|
+
uint16 small_table_[1<<10]; // 2KB
|
51
|
+
uint16* large_table_; // Allocated only when needed
|
52
|
+
|
53
|
+
DISALLOW_COPY_AND_ASSIGN(WorkingMemory);
|
54
|
+
};
|
55
|
+
|
56
|
+
// Flat array compression that does not emit the "uncompressed length"
|
57
|
+
// prefix. Compresses "input" string to the "*op" buffer.
|
58
|
+
//
|
59
|
+
// REQUIRES: "input_length <= kBlockSize"
|
60
|
+
// REQUIRES: "op" points to an array of memory that is at least
|
61
|
+
// "MaxCompressedLength(input_length)" in size.
|
62
|
+
// REQUIRES: All elements in "table[0..table_size-1]" are initialized to zero.
|
63
|
+
// REQUIRES: "table_size" is a power of two
|
64
|
+
//
|
65
|
+
// Returns an "end" pointer into "op" buffer.
|
66
|
+
// "end - op" is the compressed size of "input".
|
67
|
+
char* CompressFragment(const char* input,
|
68
|
+
size_t input_length,
|
69
|
+
char* op,
|
70
|
+
uint16* table,
|
71
|
+
const int table_size);
|
72
|
+
|
73
|
+
// Return the largest n such that
|
74
|
+
//
|
75
|
+
// s1[0,n-1] == s2[0,n-1]
|
76
|
+
// and n <= (s2_limit - s2).
|
77
|
+
//
|
78
|
+
// Does not read *s2_limit or beyond.
|
79
|
+
// Does not read *(s1 + (s2_limit - s2)) or beyond.
|
80
|
+
// Requires that s2_limit >= s2.
|
81
|
+
//
|
82
|
+
// Separate implementation for x86_64, for speed. Uses the fact that
|
83
|
+
// x86_64 is little endian.
|
84
|
+
#if defined(ARCH_K8)
|
85
|
+
static inline int FindMatchLength(const char* s1,
|
86
|
+
const char* s2,
|
87
|
+
const char* s2_limit) {
|
88
|
+
assert(s2_limit >= s2);
|
89
|
+
int matched = 0;
|
90
|
+
|
91
|
+
// Find out how long the match is. We loop over the data 64 bits at a
|
92
|
+
// time until we find a 64-bit block that doesn't match; then we find
|
93
|
+
// the first non-matching bit and use that to calculate the total
|
94
|
+
// length of the match.
|
95
|
+
while (PREDICT_TRUE(s2 <= s2_limit - 8)) {
|
96
|
+
if (PREDICT_FALSE(UNALIGNED_LOAD64(s2) == UNALIGNED_LOAD64(s1 + matched))) {
|
97
|
+
s2 += 8;
|
98
|
+
matched += 8;
|
99
|
+
} else {
|
100
|
+
// On current (mid-2008) Opteron models there is a 3% more
|
101
|
+
// efficient code sequence to find the first non-matching byte.
|
102
|
+
// However, what follows is ~10% better on Intel Core 2 and newer,
|
103
|
+
// and we expect AMD's bsf instruction to improve.
|
104
|
+
uint64 x = UNALIGNED_LOAD64(s2) ^ UNALIGNED_LOAD64(s1 + matched);
|
105
|
+
int matching_bits = Bits::FindLSBSetNonZero64(x);
|
106
|
+
matched += matching_bits >> 3;
|
107
|
+
return matched;
|
108
|
+
}
|
109
|
+
}
|
110
|
+
while (PREDICT_TRUE(s2 < s2_limit)) {
|
111
|
+
if (PREDICT_TRUE(s1[matched] == *s2)) {
|
112
|
+
++s2;
|
113
|
+
++matched;
|
114
|
+
} else {
|
115
|
+
return matched;
|
116
|
+
}
|
117
|
+
}
|
118
|
+
return matched;
|
119
|
+
}
|
120
|
+
#else
|
121
|
+
static inline int FindMatchLength(const char* s1,
|
122
|
+
const char* s2,
|
123
|
+
const char* s2_limit) {
|
124
|
+
// Implementation based on the x86-64 version, above.
|
125
|
+
assert(s2_limit >= s2);
|
126
|
+
int matched = 0;
|
127
|
+
|
128
|
+
while (s2 <= s2_limit - 4 &&
|
129
|
+
UNALIGNED_LOAD32(s2) == UNALIGNED_LOAD32(s1 + matched)) {
|
130
|
+
s2 += 4;
|
131
|
+
matched += 4;
|
132
|
+
}
|
133
|
+
if (LittleEndian::IsLittleEndian() && s2 <= s2_limit - 4) {
|
134
|
+
uint32 x = UNALIGNED_LOAD32(s2) ^ UNALIGNED_LOAD32(s1 + matched);
|
135
|
+
int matching_bits = Bits::FindLSBSetNonZero(x);
|
136
|
+
matched += matching_bits >> 3;
|
137
|
+
} else {
|
138
|
+
while ((s2 < s2_limit) && (s1[matched] == *s2)) {
|
139
|
+
++s2;
|
140
|
+
++matched;
|
141
|
+
}
|
142
|
+
}
|
143
|
+
return matched;
|
144
|
+
}
|
145
|
+
#endif
|
146
|
+
|
147
|
+
} // end namespace internal
|
148
|
+
} // end namespace snappy
|
149
|
+
|
150
|
+
#endif // UTIL_SNAPPY_SNAPPY_INTERNAL_H_
|
@@ -0,0 +1,71 @@
|
|
1
|
+
// Copyright 2011 Google Inc. All Rights Reserved.
|
2
|
+
//
|
3
|
+
// Redistribution and use in source and binary forms, with or without
|
4
|
+
// modification, are permitted provided that the following conditions are
|
5
|
+
// met:
|
6
|
+
//
|
7
|
+
// * Redistributions of source code must retain the above copyright
|
8
|
+
// notice, this list of conditions and the following disclaimer.
|
9
|
+
// * Redistributions in binary form must reproduce the above
|
10
|
+
// copyright notice, this list of conditions and the following disclaimer
|
11
|
+
// in the documentation and/or other materials provided with the
|
12
|
+
// distribution.
|
13
|
+
// * Neither the name of Google Inc. nor the names of its
|
14
|
+
// contributors may be used to endorse or promote products derived from
|
15
|
+
// this software without specific prior written permission.
|
16
|
+
//
|
17
|
+
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
18
|
+
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
19
|
+
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
20
|
+
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
21
|
+
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
22
|
+
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
23
|
+
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
24
|
+
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
25
|
+
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
26
|
+
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
27
|
+
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
28
|
+
|
29
|
+
#include <string.h>
|
30
|
+
|
31
|
+
#include "snappy-sinksource.h"
|
32
|
+
|
33
|
+
namespace snappy {
|
34
|
+
|
35
|
+
Source::~Source() { }
|
36
|
+
|
37
|
+
Sink::~Sink() { }
|
38
|
+
|
39
|
+
char* Sink::GetAppendBuffer(size_t length, char* scratch) {
|
40
|
+
return scratch;
|
41
|
+
}
|
42
|
+
|
43
|
+
ByteArraySource::~ByteArraySource() { }
|
44
|
+
|
45
|
+
size_t ByteArraySource::Available() const { return left_; }
|
46
|
+
|
47
|
+
const char* ByteArraySource::Peek(size_t* len) {
|
48
|
+
*len = left_;
|
49
|
+
return ptr_;
|
50
|
+
}
|
51
|
+
|
52
|
+
void ByteArraySource::Skip(size_t n) {
|
53
|
+
left_ -= n;
|
54
|
+
ptr_ += n;
|
55
|
+
}
|
56
|
+
|
57
|
+
UncheckedByteArraySink::~UncheckedByteArraySink() { }
|
58
|
+
|
59
|
+
void UncheckedByteArraySink::Append(const char* data, size_t n) {
|
60
|
+
// Do no copying if the caller filled in the result of GetAppendBuffer()
|
61
|
+
if (data != dest_) {
|
62
|
+
memcpy(dest_, data, n);
|
63
|
+
}
|
64
|
+
dest_ += n;
|
65
|
+
}
|
66
|
+
|
67
|
+
char* UncheckedByteArraySink::GetAppendBuffer(size_t len, char* scratch) {
|
68
|
+
return dest_;
|
69
|
+
}
|
70
|
+
|
71
|
+
}
|
@@ -0,0 +1,137 @@
|
|
1
|
+
// Copyright 2011 Google Inc. All Rights Reserved.
|
2
|
+
//
|
3
|
+
// Redistribution and use in source and binary forms, with or without
|
4
|
+
// modification, are permitted provided that the following conditions are
|
5
|
+
// met:
|
6
|
+
//
|
7
|
+
// * Redistributions of source code must retain the above copyright
|
8
|
+
// notice, this list of conditions and the following disclaimer.
|
9
|
+
// * Redistributions in binary form must reproduce the above
|
10
|
+
// copyright notice, this list of conditions and the following disclaimer
|
11
|
+
// in the documentation and/or other materials provided with the
|
12
|
+
// distribution.
|
13
|
+
// * Neither the name of Google Inc. nor the names of its
|
14
|
+
// contributors may be used to endorse or promote products derived from
|
15
|
+
// this software without specific prior written permission.
|
16
|
+
//
|
17
|
+
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
18
|
+
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
19
|
+
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
20
|
+
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
21
|
+
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
22
|
+
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
23
|
+
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
24
|
+
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
25
|
+
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
26
|
+
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
27
|
+
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
28
|
+
|
29
|
+
#ifndef UTIL_SNAPPY_SNAPPY_SINKSOURCE_H_
|
30
|
+
#define UTIL_SNAPPY_SNAPPY_SINKSOURCE_H_
|
31
|
+
|
32
|
+
#include <stddef.h>
|
33
|
+
|
34
|
+
|
35
|
+
namespace snappy {
|
36
|
+
|
37
|
+
// A Sink is an interface that consumes a sequence of bytes.
|
38
|
+
class Sink {
|
39
|
+
public:
|
40
|
+
Sink() { }
|
41
|
+
virtual ~Sink();
|
42
|
+
|
43
|
+
// Append "bytes[0,n-1]" to this.
|
44
|
+
virtual void Append(const char* bytes, size_t n) = 0;
|
45
|
+
|
46
|
+
// Returns a writable buffer of the specified length for appending.
|
47
|
+
// May return a pointer to the caller-owned scratch buffer which
|
48
|
+
// must have at least the indicated length. The returned buffer is
|
49
|
+
// only valid until the next operation on this Sink.
|
50
|
+
//
|
51
|
+
// After writing at most "length" bytes, call Append() with the
|
52
|
+
// pointer returned from this function and the number of bytes
|
53
|
+
// written. Many Append() implementations will avoid copying
|
54
|
+
// bytes if this function returned an internal buffer.
|
55
|
+
//
|
56
|
+
// If a non-scratch buffer is returned, the caller may only pass a
|
57
|
+
// prefix of it to Append(). That is, it is not correct to pass an
|
58
|
+
// interior pointer of the returned array to Append().
|
59
|
+
//
|
60
|
+
// The default implementation always returns the scratch buffer.
|
61
|
+
virtual char* GetAppendBuffer(size_t length, char* scratch);
|
62
|
+
|
63
|
+
|
64
|
+
private:
|
65
|
+
// No copying
|
66
|
+
Sink(const Sink&);
|
67
|
+
void operator=(const Sink&);
|
68
|
+
};
|
69
|
+
|
70
|
+
// A Source is an interface that yields a sequence of bytes
|
71
|
+
class Source {
|
72
|
+
public:
|
73
|
+
Source() { }
|
74
|
+
virtual ~Source();
|
75
|
+
|
76
|
+
// Return the number of bytes left to read from the source
|
77
|
+
virtual size_t Available() const = 0;
|
78
|
+
|
79
|
+
// Peek at the next flat region of the source. Does not reposition
|
80
|
+
// the source. The returned region is empty iff Available()==0.
|
81
|
+
//
|
82
|
+
// Returns a pointer to the beginning of the region and store its
|
83
|
+
// length in *len.
|
84
|
+
//
|
85
|
+
// The returned region is valid until the next call to Skip() or
|
86
|
+
// until this object is destroyed, whichever occurs first.
|
87
|
+
//
|
88
|
+
// The returned region may be larger than Available() (for example
|
89
|
+
// if this ByteSource is a view on a substring of a larger source).
|
90
|
+
// The caller is responsible for ensuring that it only reads the
|
91
|
+
// Available() bytes.
|
92
|
+
virtual const char* Peek(size_t* len) = 0;
|
93
|
+
|
94
|
+
// Skip the next n bytes. Invalidates any buffer returned by
|
95
|
+
// a previous call to Peek().
|
96
|
+
// REQUIRES: Available() >= n
|
97
|
+
virtual void Skip(size_t n) = 0;
|
98
|
+
|
99
|
+
private:
|
100
|
+
// No copying
|
101
|
+
Source(const Source&);
|
102
|
+
void operator=(const Source&);
|
103
|
+
};
|
104
|
+
|
105
|
+
// A Source implementation that yields the contents of a flat array
|
106
|
+
class ByteArraySource : public Source {
|
107
|
+
public:
|
108
|
+
ByteArraySource(const char* p, size_t n) : ptr_(p), left_(n) { }
|
109
|
+
virtual ~ByteArraySource();
|
110
|
+
virtual size_t Available() const;
|
111
|
+
virtual const char* Peek(size_t* len);
|
112
|
+
virtual void Skip(size_t n);
|
113
|
+
private:
|
114
|
+
const char* ptr_;
|
115
|
+
size_t left_;
|
116
|
+
};
|
117
|
+
|
118
|
+
// A Sink implementation that writes to a flat array without any bound checks.
|
119
|
+
class UncheckedByteArraySink : public Sink {
|
120
|
+
public:
|
121
|
+
explicit UncheckedByteArraySink(char* dest) : dest_(dest) { }
|
122
|
+
virtual ~UncheckedByteArraySink();
|
123
|
+
virtual void Append(const char* data, size_t n);
|
124
|
+
virtual char* GetAppendBuffer(size_t len, char* scratch);
|
125
|
+
|
126
|
+
// Return the current output pointer so that a caller can see how
|
127
|
+
// many bytes were produced.
|
128
|
+
// Note: this is not a Sink method.
|
129
|
+
char* CurrentDestination() const { return dest_; }
|
130
|
+
private:
|
131
|
+
char* dest_;
|
132
|
+
};
|
133
|
+
|
134
|
+
|
135
|
+
}
|
136
|
+
|
137
|
+
#endif // UTIL_SNAPPY_SNAPPY_SINKSOURCE_H_
|