From 2d04c40c9e434d9233607bead20b5818c797cf71 Mon Sep 17 00:00:00 2001 From: CoprDistGit Date: Mon, 10 Apr 2023 18:43:08 +0000 Subject: automatic import of python-mgzip --- .gitignore | 1 + python-mgzip.spec | 192 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ sources | 1 + 3 files changed, 194 insertions(+) create mode 100644 python-mgzip.spec create mode 100644 sources diff --git a/.gitignore b/.gitignore index e69de29..4a8cb78 100644 --- a/.gitignore +++ b/.gitignore @@ -0,0 +1 @@ +/mgzip-0.2.1.tar.gz diff --git a/python-mgzip.spec b/python-mgzip.spec new file mode 100644 index 0000000..4e9e31b --- /dev/null +++ b/python-mgzip.spec @@ -0,0 +1,192 @@ +%global _empty_manifest_terminate_build 0 +Name: python-mgzip +Version: 0.2.1 +Release: 1 +Summary: A multi-threading implementation of Python gzip module +License: MIT +URL: https://github.com/vinlyx/mgzip +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/80/31/0f83d46a92aae1a39d6b78c22def34c6791de2a300f019695d6aee3e4e5a/mgzip-0.2.1.tar.gz +BuildArch: noarch + + +%description +# mgzip +A multi-threading implement of Python gzip module + +Using a block indexed GZIP file format to enable compress and decompress in parallel. This implement use 'FEXTRA' to record the index of compressed member, which is defined in offical GZIP file format specification version 4.3, so it is fully compatible with normal GZIP implement. + +This module is **~25X** faster for compression and **~7X** faster for decompression (limited by IO and Python implementation) with a *24 CPUs* computer. + +***In theoretical, compression and decompression acceleration should be linear according to the CPU cores. In fact, the performance is limited by IO and program language implementation.*** + +## Usage +Use same method as gzip module +```python +import mgzip + +s = "a big string..." + +## Use 8 threads to compress. +## None or 0 means using all CPUs (default) +## Compression block size is set to 200MB +with mgzip.open("test.txt.gz", "wt", thread=8, blocksize=2*10**8) as fw: + fw.write(s) + +with mgzip.open("test.txt.gz", "rt", thread=8) as fr: + assert fr.read(len(s)) == s +``` + +## Performance +### Compression: +![Compression Performance](https://raw.githubusercontent.com/vinlyx/mgzip/master/CompressionBenchmark.png) + +### Decompression: +![Decompression Performance](https://raw.githubusercontent.com/vinlyx/mgzip/master/DecompressionBenchmark.png) + +*Brenchmarked on a 24 cores, 48 threads server (Xeon(R) CPU E5-2650 v4 @ 2.20GHz) with 8.0GB FASTQ text file.* + +*Using parameters thread=42 and blocksize=200000000* + +## Warning +**This package only replace the 'GzipFile' class and 'open', 'compress', 'decompress' functions of standard gzip module. It is not well tested for other class and function.** + +**As the first release version, some features are not yet supported, such as seek() and tell(). Any contribution or improvement is appreciated.** + +%package -n python3-mgzip +Summary: A multi-threading implementation of Python gzip module +Provides: python-mgzip +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-mgzip +# mgzip +A multi-threading implement of Python gzip module + +Using a block indexed GZIP file format to enable compress and decompress in parallel. This implement use 'FEXTRA' to record the index of compressed member, which is defined in offical GZIP file format specification version 4.3, so it is fully compatible with normal GZIP implement. + +This module is **~25X** faster for compression and **~7X** faster for decompression (limited by IO and Python implementation) with a *24 CPUs* computer. + +***In theoretical, compression and decompression acceleration should be linear according to the CPU cores. In fact, the performance is limited by IO and program language implementation.*** + +## Usage +Use same method as gzip module +```python +import mgzip + +s = "a big string..." + +## Use 8 threads to compress. +## None or 0 means using all CPUs (default) +## Compression block size is set to 200MB +with mgzip.open("test.txt.gz", "wt", thread=8, blocksize=2*10**8) as fw: + fw.write(s) + +with mgzip.open("test.txt.gz", "rt", thread=8) as fr: + assert fr.read(len(s)) == s +``` + +## Performance +### Compression: +![Compression Performance](https://raw.githubusercontent.com/vinlyx/mgzip/master/CompressionBenchmark.png) + +### Decompression: +![Decompression Performance](https://raw.githubusercontent.com/vinlyx/mgzip/master/DecompressionBenchmark.png) + +*Brenchmarked on a 24 cores, 48 threads server (Xeon(R) CPU E5-2650 v4 @ 2.20GHz) with 8.0GB FASTQ text file.* + +*Using parameters thread=42 and blocksize=200000000* + +## Warning +**This package only replace the 'GzipFile' class and 'open', 'compress', 'decompress' functions of standard gzip module. It is not well tested for other class and function.** + +**As the first release version, some features are not yet supported, such as seek() and tell(). Any contribution or improvement is appreciated.** + +%package help +Summary: Development documents and examples for mgzip +Provides: python3-mgzip-doc +%description help +# mgzip +A multi-threading implement of Python gzip module + +Using a block indexed GZIP file format to enable compress and decompress in parallel. This implement use 'FEXTRA' to record the index of compressed member, which is defined in offical GZIP file format specification version 4.3, so it is fully compatible with normal GZIP implement. + +This module is **~25X** faster for compression and **~7X** faster for decompression (limited by IO and Python implementation) with a *24 CPUs* computer. + +***In theoretical, compression and decompression acceleration should be linear according to the CPU cores. In fact, the performance is limited by IO and program language implementation.*** + +## Usage +Use same method as gzip module +```python +import mgzip + +s = "a big string..." + +## Use 8 threads to compress. +## None or 0 means using all CPUs (default) +## Compression block size is set to 200MB +with mgzip.open("test.txt.gz", "wt", thread=8, blocksize=2*10**8) as fw: + fw.write(s) + +with mgzip.open("test.txt.gz", "rt", thread=8) as fr: + assert fr.read(len(s)) == s +``` + +## Performance +### Compression: +![Compression Performance](https://raw.githubusercontent.com/vinlyx/mgzip/master/CompressionBenchmark.png) + +### Decompression: +![Decompression Performance](https://raw.githubusercontent.com/vinlyx/mgzip/master/DecompressionBenchmark.png) + +*Brenchmarked on a 24 cores, 48 threads server (Xeon(R) CPU E5-2650 v4 @ 2.20GHz) with 8.0GB FASTQ text file.* + +*Using parameters thread=42 and blocksize=200000000* + +## Warning +**This package only replace the 'GzipFile' class and 'open', 'compress', 'decompress' functions of standard gzip module. It is not well tested for other class and function.** + +**As the first release version, some features are not yet supported, such as seek() and tell(). Any contribution or improvement is appreciated.** + +%prep +%autosetup -n mgzip-0.2.1 + +%build +%py3_build + +%install +%py3_install +install -d -m755 %{buildroot}/%{_pkgdocdir} +if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi +if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi +if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi +if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi +pushd %{buildroot} +if [ -d usr/lib ]; then + find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/lib64 ]; then + find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/bin ]; then + find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/sbin ]; then + find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst +fi +touch doclist.lst +if [ -d usr/share/man ]; then + find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst +fi +popd +mv %{buildroot}/filelist.lst . +mv %{buildroot}/doclist.lst . + +%files -n python3-mgzip -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Mon Apr 10 2023 Python_Bot - 0.2.1-1 +- Package Spec generated diff --git a/sources b/sources new file mode 100644 index 0000000..dce8f50 --- /dev/null +++ b/sources @@ -0,0 +1 @@ +00f034d30400ac47cc1e68c100f48520 mgzip-0.2.1.tar.gz -- cgit v1.2.3