mirror of
https://github.com/lz4/lz4.git
synced 2024-11-23 18:04:05 +08:00
Remove whitespace from ends of lines
I'm trying to import LZ4 code into a project with strict linting requirements. This will make that easier. Signed-off-by: Julius Werner <jwerner@chromium.org>
This commit is contained in:
Julius Werner
parent
ad564c8720
commit
4fcb2e17fb
10
Makefile
10
Makefile
@ -2,18 +2,18 @@
|
||||
# LZ4 - Makefile
|
||||
# Copyright (C) Yann Collet 2011-2015
|
||||
# All rights reserved.
|
||||
#
|
||||
#
|
||||
# BSD license
|
||||
# Redistribution and use in source and binary forms, with or without modification,
|
||||
# are permitted provided that the following conditions are met:
|
||||
#
|
||||
#
|
||||
# * Redistributions of source code must retain the above copyright notice, this
|
||||
# list of conditions and the following disclaimer.
|
||||
#
|
||||
#
|
||||
# * 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 COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
||||
# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
||||
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
@ -24,7 +24,7 @@
|
||||
# ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
||||
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
#
|
||||
#
|
||||
# You can contact the author at :
|
||||
# - LZ4 source repository : https://github.com/Cyan4973/lz4
|
||||
# - LZ4 forum froup : https://groups.google.com/forum/#!forum/lz4c
|
||||
|
||||
12
README.md
12
README.md
@ -1,11 +1,11 @@
|
||||
LZ4 - Extremely fast compression
|
||||
================================
|
||||
|
||||
LZ4 is lossless compression algorithm,
|
||||
providing compression speed at 400 MB/s per core,
|
||||
scalable with multi-cores CPU.
|
||||
It features an extremely fast decoder,
|
||||
with speed in multiple GB/s per core,
|
||||
LZ4 is lossless compression algorithm,
|
||||
providing compression speed at 400 MB/s per core,
|
||||
scalable with multi-cores CPU.
|
||||
It features an extremely fast decoder,
|
||||
with speed in multiple GB/s per core,
|
||||
typically reaching RAM speed limits on multi-core systems.
|
||||
|
||||
Speed can be tuned dynamically, selecting an "acceleration" factor
|
||||
@ -77,7 +77,7 @@ Interoperable versions of LZ4 must respect this frame format.
|
||||
Other source versions
|
||||
-------------------------
|
||||
|
||||
Beyond the C reference source,
|
||||
Beyond the C reference source,
|
||||
many contributors have created versions of lz4 in multiple languages
|
||||
(Java, C#, Python, Perl, Ruby, etc.).
|
||||
A list of known source ports is maintained on the [LZ4 Homepage].
|
||||
|
||||
@ -42,9 +42,9 @@ if(BUILD_TOOLS)
|
||||
install(TARGETS lz4 RUNTIME DESTINATION "bin/")
|
||||
endif()
|
||||
|
||||
if(BUILD_LIBS)
|
||||
|
||||
|
||||
if(BUILD_LIBS)
|
||||
|
||||
|
||||
SET(LIBS_TARGETS "")
|
||||
IF(NOT WIN32)
|
||||
add_library(liblz4 SHARED ${LZ4_SRCS_LIB})
|
||||
@ -55,12 +55,12 @@ if(BUILD_LIBS)
|
||||
add_library(liblz4 STATIC ${LZ4_SRCS_LIB})
|
||||
SET(LIBS_TARGETS liblz4)
|
||||
ENDIF(NOT WIN32)
|
||||
|
||||
|
||||
set_target_properties(liblz4 PROPERTIES
|
||||
OUTPUT_NAME lz4
|
||||
SOVERSION "${CPACK_PACKAGE_VERSION_MAJOR}.${CPACK_PACKAGE_VERSION_MINOR}"
|
||||
)
|
||||
|
||||
|
||||
install(TARGETS ${LIBS_TARGETS}
|
||||
RUNTIME DESTINATION lib #on Windows: cmake considers dlls as runtime component
|
||||
LIBRARY DESTINATION lib
|
||||
@ -73,7 +73,7 @@ if(BUILD_LIBS)
|
||||
${LZ4_DIR}/lz4frame.h
|
||||
DESTINATION include
|
||||
)
|
||||
|
||||
|
||||
if(BUILD_TOOLS)
|
||||
target_link_libraries(lz4 liblz4)
|
||||
endif()
|
||||
|
||||
@ -43,7 +43,7 @@ void test_compress(FILE* outFp, FILE* inpFp)
|
||||
|
||||
char inpBuf[2][BLOCK_BYTES];
|
||||
int inpBufIndex = 0;
|
||||
|
||||
|
||||
LZ4_resetStream(lz4Stream);
|
||||
|
||||
for(;;) {
|
||||
|
||||
@ -39,7 +39,7 @@ Example (1) : Block API, 4KiB Block
|
||||
+---------------+---------------+----+----+----+
|
||||
| Block #1 | Block #2 | #3 | #4 |... |
|
||||
+---------------+---------------+----+----+----+
|
||||
|
||||
|
||||
(No Dependency)
|
||||
|
||||
|
||||
|
||||
10
lib/Makefile
10
lib/Makefile
@ -2,18 +2,18 @@
|
||||
# LZ4 library - Makefile
|
||||
# Copyright (C) Yann Collet 2011-2015
|
||||
# All rights reserved.
|
||||
#
|
||||
#
|
||||
# BSD license
|
||||
# Redistribution and use in source and binary forms, with or without modification,
|
||||
# are permitted provided that the following conditions are met:
|
||||
#
|
||||
#
|
||||
# * Redistributions of source code must retain the above copyright notice, this
|
||||
# list of conditions and the following disclaimer.
|
||||
#
|
||||
#
|
||||
# * 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 COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
||||
# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
||||
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
@ -24,7 +24,7 @@
|
||||
# ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
||||
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
#
|
||||
#
|
||||
# You can contact the author at :
|
||||
# - LZ4 source repository : https://github.com/Cyan4973/lz4
|
||||
# - LZ4 forum froup : https://groups.google.com/forum/#!forum/lz4c
|
||||
|
||||
@ -258,7 +258,7 @@ size_t LZ4F_getFrameInfo(LZ4F_decompressionContext_t dctx,
|
||||
/* LZ4F_getFrameInfo()
|
||||
* This function decodes frame header information (such as max blockSize, frame checksum, etc.).
|
||||
* Its usage is optional. The objective is to extract frame header information, typically for allocation purposes.
|
||||
* A header size is variable and can be from 7 to 15 bytes. It's also possible to input more bytes than that.
|
||||
* A header size is variable and can be from 7 to 15 bytes. It's also possible to input more bytes than that.
|
||||
* The number of bytes read from srcBuffer will be updated within *srcSizePtr (necessarily <= original value).
|
||||
* (note that LZ4F_getFrameInfo() can also be used anytime *after* starting decompression, in this case 0 input byte is enough)
|
||||
* Frame header info is *copied into* an already allocated LZ4F_frameInfo_t structure.
|
||||
|
||||
@ -75,15 +75,15 @@ This is a 2 bytes value, in little endian format
|
||||
The offset represents the position of the match to be copied from.
|
||||
1 means "current position - 1 byte".
|
||||
The maximum offset value is 65535, 65536 cannot be coded.
|
||||
Note that 0 is an invalid value, not used.
|
||||
Note that 0 is an invalid value, not used.
|
||||
|
||||
Then we need to extract the match length.
|
||||
For this, we use the second token field, the low 4-bits.
|
||||
Value, obviously, ranges from 0 to 15.
|
||||
However here, 0 means that the copy operation will be minimal.
|
||||
The minimum length of a match, called minmatch, is 4.
|
||||
The minimum length of a match, called minmatch, is 4.
|
||||
As a consequence, a 0 value means 4 bytes, and a value of 15 means 19+ bytes.
|
||||
Similar to literal length, on reaching the highest possible value (15),
|
||||
Similar to literal length, on reaching the highest possible value (15),
|
||||
we output additional bytes, one at a time, with values ranging from 0 to 255.
|
||||
They are added to total to provide the final match length.
|
||||
A 255 value means there is another byte to read and add.
|
||||
@ -102,7 +102,7 @@ There are specific parsing rules to respect in order to remain compatible
|
||||
with assumptions made by the decoder :
|
||||
|
||||
1. The last 5 bytes are always literals
|
||||
2. The last match must start at least 12 bytes before end of block.
|
||||
2. The last match must start at least 12 bytes before end of block.
|
||||
Consequently, a block with less than 13 bytes cannot be compressed.
|
||||
|
||||
These rules are in place to ensure that the decoder
|
||||
|
||||
@ -5,12 +5,12 @@ LZ4 Frame Format Description
|
||||
|
||||
Copyright (c) 2013-2015 Yann Collet
|
||||
|
||||
Permission is granted to copy and distribute this document
|
||||
for any purpose and without charge,
|
||||
including translations into other languages
|
||||
and incorporation into compilations,
|
||||
provided that the copyright notice and this notice are preserved,
|
||||
and that any substantive changes or deletions from the original
|
||||
Permission is granted to copy and distribute this document
|
||||
for any purpose and without charge,
|
||||
including translations into other languages
|
||||
and incorporation into compilations,
|
||||
provided that the copyright notice and this notice are preserved,
|
||||
and that any substantive changes or deletions from the original
|
||||
are clearly marked.
|
||||
Distribution of this document is unlimited.
|
||||
|
||||
@ -22,13 +22,13 @@ Distribution of this document is unlimited.
|
||||
Introduction
|
||||
------------
|
||||
|
||||
The purpose of this document is to define a lossless compressed data format,
|
||||
that is independent of CPU type, operating system,
|
||||
file system and character set, suitable for
|
||||
File compression, Pipe and streaming compression
|
||||
The purpose of this document is to define a lossless compressed data format,
|
||||
that is independent of CPU type, operating system,
|
||||
file system and character set, suitable for
|
||||
File compression, Pipe and streaming compression
|
||||
using the [LZ4 algorithm](http://www.lz4.org).
|
||||
|
||||
The data can be produced or consumed,
|
||||
The data can be produced or consumed,
|
||||
even for an arbitrarily long sequentially presented input data stream,
|
||||
using only an a priori bounded amount of intermediate storage,
|
||||
and hence can be used in data communications.
|
||||
@ -36,7 +36,7 @@ The format uses the LZ4 compression method,
|
||||
and optional [xxHash-32 checksum method](https://github.com/Cyan4973/xxHash),
|
||||
for detection of data corruption.
|
||||
|
||||
The data format defined by this specification
|
||||
The data format defined by this specification
|
||||
does not attempt to allow random access to compressed data.
|
||||
|
||||
This specification is intended for use by implementers of software
|
||||
@ -63,7 +63,7 @@ General Structure of LZ4 Frame format
|
||||
|
||||
| MagicNb | F. Descriptor | Block | (...) | EndMark | C. Checksum |
|
||||
|:-------:|:-------------:| ----- | ----- | ------- | ----------- |
|
||||
| 4 bytes | 3-11 bytes | | | 4 bytes | 0-4 bytes |
|
||||
| 4 bytes | 3-11 bytes | | | 4 bytes | 0-4 bytes |
|
||||
|
||||
__Magic Number__
|
||||
|
||||
@ -88,11 +88,11 @@ The size is expressed as a 32-bits value.
|
||||
__Content Checksum__
|
||||
|
||||
Content Checksum verify that the full content has been decoded correctly.
|
||||
The content checksum is the result
|
||||
The content checksum is the result
|
||||
of [xxh32() hash function](https://github.com/Cyan4973/xxHash)
|
||||
digesting the original (decoded) data as input, and a seed of zero.
|
||||
Content checksum is only present when its associated flag
|
||||
is set in the frame descriptor.
|
||||
is set in the frame descriptor.
|
||||
Content Checksum validates the result,
|
||||
that all blocks were fully transmitted in the correct order and without error,
|
||||
and also that the encoding/decoding process itself generated no distortion.
|
||||
@ -108,19 +108,19 @@ In such case, each frame has its own set of descriptor flags.
|
||||
Each frame is considered independent.
|
||||
The only relation between frames is their sequential order.
|
||||
|
||||
The ability to decode multiple concatenated frames
|
||||
The ability to decode multiple concatenated frames
|
||||
within a single stream or file
|
||||
is left outside of this specification.
|
||||
is left outside of this specification.
|
||||
As an example, the reference lz4 command line utility behavior is
|
||||
to decode all concatenated frames in their sequential order.
|
||||
|
||||
|
||||
|
||||
Frame Descriptor
|
||||
----------------
|
||||
|
||||
| FLG | BD | (Content Size) | HC |
|
||||
| ------- | ------- |:--------------:| ------- |
|
||||
| 1 byte | 1 byte | 0 - 8 bytes | 1 byte |
|
||||
| 1 byte | 1 byte | 0 - 8 bytes | 1 byte |
|
||||
|
||||
The descriptor uses a minimum of 3 bytes,
|
||||
and up to 11 bytes depending on optional parameters.
|
||||
@ -148,7 +148,7 @@ Other version numbers will use different flag layouts.
|
||||
|
||||
__Block Independence flag__
|
||||
|
||||
If this flag is set to “1”, blocks are independent.
|
||||
If this flag is set to “1”, blocks are independent.
|
||||
If this flag is set to “0”, each block depends on previous ones
|
||||
(up to LZ4 window size, which is 64 KB).
|
||||
In such case, it’s necessary to decode all blocks in sequence.
|
||||
@ -160,13 +160,13 @@ __Block checksum flag__
|
||||
|
||||
If this flag is set, each data block will be followed by a 4-bytes checksum,
|
||||
calculated by using the xxHash-32 algorithm on the raw (compressed) data block.
|
||||
The intention is to detect data corruption (storage or transmission errors)
|
||||
The intention is to detect data corruption (storage or transmission errors)
|
||||
immediately, before decoding.
|
||||
Block checksum usage is optional.
|
||||
|
||||
__Content Size flag__
|
||||
|
||||
If this flag is set, the uncompressed size of data included within the frame
|
||||
If this flag is set, the uncompressed size of data included within the frame
|
||||
will be present as an 8 bytes unsigned little endian value, after the flags.
|
||||
Content Size usage is optional.
|
||||
|
||||
@ -182,9 +182,9 @@ This information is intended to help the decoder allocate memory.
|
||||
Size here refers to the original (uncompressed) data size.
|
||||
Block Maximum Size is one value among the following table :
|
||||
|
||||
| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
|
||||
| --- | --- | --- | --- | ----- | ------ | ---- | ---- |
|
||||
| N/A | N/A | N/A | N/A | 64 KB | 256 KB | 1 MB | 4 MB |
|
||||
| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
|
||||
| --- | --- | --- | --- | ----- | ------ | ---- | ---- |
|
||||
| N/A | N/A | N/A | N/A | 64 KB | 256 KB | 1 MB | 4 MB |
|
||||
|
||||
The decoder may refuse to allocate block sizes above a (system-specific) size.
|
||||
Unused values may be used in a future revision of the spec.
|
||||
@ -224,7 +224,7 @@ Data Blocks
|
||||
|
||||
| Block Size | data | (Block Checksum) |
|
||||
|:----------:| ------ |:----------------:|
|
||||
| 4 bytes | | 0 - 4 bytes |
|
||||
| 4 bytes | | 0 - 4 bytes |
|
||||
|
||||
|
||||
__Block Size__
|
||||
@ -239,7 +239,7 @@ All other bits give the size, in bytes, of the following data block
|
||||
(the size does not include the block checksum if present).
|
||||
|
||||
Block Size shall never be larger than Block Maximum Size.
|
||||
Such a thing could happen for incompressible source data.
|
||||
Such a thing could happen for incompressible source data.
|
||||
In such case, such a data block shall be passed in uncompressed format.
|
||||
|
||||
__Data__
|
||||
@ -247,7 +247,7 @@ __Data__
|
||||
Where the actual data to decode stands.
|
||||
It might be compressed or not, depending on previous field indications.
|
||||
Uncompressed size of Data can be any size, up to “block maximum size”.
|
||||
Note that data block is not necessarily full :
|
||||
Note that data block is not necessarily full :
|
||||
an arbitrary “flush” may happen anytime. Any block can be “partially filled”.
|
||||
|
||||
__Block checksum__
|
||||
@ -256,7 +256,7 @@ Only present if the associated flag is set.
|
||||
This is a 4-bytes checksum value, in little endian format,
|
||||
calculated by using the xxHash-32 algorithm on the raw (undecoded) data block,
|
||||
and a seed of zero.
|
||||
The intention is to detect data corruption (storage or transmission errors)
|
||||
The intention is to detect data corruption (storage or transmission errors)
|
||||
before decoding.
|
||||
|
||||
Block checksum is cumulative with Content checksum.
|
||||
@ -267,12 +267,12 @@ Skippable Frames
|
||||
|
||||
| Magic Number | Frame Size | User Data |
|
||||
|:------------:|:----------:| --------- |
|
||||
| 4 bytes | 4 bytes | |
|
||||
| 4 bytes | 4 bytes | |
|
||||
|
||||
Skippable frames allow the integration of user-defined data
|
||||
into a flow of concatenated frames.
|
||||
Its design is pretty straightforward,
|
||||
with the sole objective to allow the decoder to quickly skip
|
||||
with the sole objective to allow the decoder to quickly skip
|
||||
over user-defined data and continue decoding.
|
||||
|
||||
For the purpose of facilitating identification,
|
||||
@ -283,14 +283,14 @@ it’s recommended to start with a zero-byte LZ4 frame
|
||||
followed by a skippable frame.
|
||||
This will make it easier for file type identifiers.
|
||||
|
||||
|
||||
|
||||
__Magic Number__
|
||||
|
||||
4 Bytes, Little endian format.
|
||||
Value : 0x184D2A5X, which means any value from 0x184D2A50 to 0x184D2A5F.
|
||||
All 16 values are valid to identify a skippable frame.
|
||||
|
||||
__Frame Size__
|
||||
__Frame Size__
|
||||
|
||||
This is the size, in bytes, of the following User Data
|
||||
(without including the magic number nor the size field itself).
|
||||
@ -313,7 +313,7 @@ Main characteristics of the legacy format :
|
||||
- Fixed block size : 8 MB.
|
||||
- All blocks must be completely filled, except the last one.
|
||||
- All blocks are always compressed, even when compression is detrimental.
|
||||
- The last block is detected either because
|
||||
- The last block is detected either because
|
||||
it is followed by the “EOF” (End of File) mark,
|
||||
or because it is followed by a known Frame Magic Number.
|
||||
- No checksum
|
||||
|
||||
@ -18,11 +18,11 @@
|
||||
.PP
|
||||
.B unlz4
|
||||
is equivalent to
|
||||
.BR "lz4 \-d"
|
||||
.BR "lz4 \-d"
|
||||
.br
|
||||
.B lz4cat
|
||||
is equivalent to
|
||||
.BR "lz4 \-dc"
|
||||
.BR "lz4 \-dc"
|
||||
.br
|
||||
.PP
|
||||
When writing scripts that need to decompress files,
|
||||
@ -42,17 +42,17 @@ and
|
||||
.PP
|
||||
\fBlz4\fR is an extremely fast lossless compression algorithm,
|
||||
based on \fBbyte-aligned LZ77\fR family of compression scheme.
|
||||
\fBlz4\fR offers compression speeds of 400 MB/s per core, linearly scalable with multi-core CPUs.
|
||||
\fBlz4\fR offers compression speeds of 400 MB/s per core, linearly scalable with multi-core CPUs.
|
||||
It features an extremely fast decoder, with speed in multiple GB/s per core,
|
||||
typically reaching RAM speed limit on multi-core systems.
|
||||
typically reaching RAM speed limit on multi-core systems.
|
||||
The native file format is the
|
||||
.B .lz4
|
||||
format.
|
||||
|
||||
.B lz4
|
||||
supports a command line syntax similar but not identical to
|
||||
.BR gzip (1).
|
||||
Differences are :
|
||||
.B lz4
|
||||
supports a command line syntax similar but not identical to
|
||||
.BR gzip (1).
|
||||
Differences are :
|
||||
\fBlz4\fR preserve original files ;
|
||||
\fBlz4 file1 file2\fR means : compress file1 \fIinto\fR file2 ;
|
||||
\fBlz4 file\fR shows real-time statistics during compression .
|
||||
@ -98,9 +98,9 @@ only the latest one will be applied.
|
||||
.TP
|
||||
.BR \-z ", " \-\-compress
|
||||
Compress.
|
||||
This is the default operation mode
|
||||
This is the default operation mode
|
||||
when no operation mode option is specified ,
|
||||
no other operation mode is implied from the command name
|
||||
no other operation mode is implied from the command name
|
||||
(for example,
|
||||
.B unlz4
|
||||
implies
|
||||
@ -192,7 +192,7 @@ independently, and the resulting name of each compressed file will be
|
||||
Note : this option can only be activated when the original size can be determined,
|
||||
hence for a file. It won't work with unknown source size, such as stdin or pipe.
|
||||
.TP
|
||||
.B \--[no-]sparse
|
||||
.B \--[no-]sparse
|
||||
sparse mode support (default:enabled on file, disabled on stdout)
|
||||
.TP
|
||||
.B \-l
|
||||
|
||||
@ -21,7 +21,7 @@ def proc(cmd_args, pipe=True, dummy=False):
|
||||
return
|
||||
if pipe:
|
||||
subproc = subprocess.Popen(cmd_args,
|
||||
stdout=subprocess.PIPE,
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.PIPE)
|
||||
else:
|
||||
subproc = subprocess.Popen(cmd_args)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user