1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
|
%global _empty_manifest_terminate_build 0
Name: python-mrjob
Version: 0.7.4
Release: 1
Summary: Python MapReduce framework
License: Apache
URL: http://github.com/Yelp/mrjob
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/2c/ed/207853d1ebc6b549551d12db35e471289d26cac2cdae363419357294d3c5/mrjob-0.7.4.tar.gz
BuildArch: noarch
Requires: python3-PyYAML
Requires: python3-boto3
Requires: python3-botocore
Requires: python3-google-cloud-dataproc
Requires: python3-google-cloud-logging
Requires: python3-google-cloud-storage
Requires: python3-rapidjson
Requires: python3-simplejson
Requires: python3-ujson
%description
mrjob is a Python 2.7/3.4+ package that helps you write and run Hadoop
Streaming jobs.
`Stable version (v0.7.4) documentation <http://mrjob.readthedocs.org/en/stable/>`_
`Development version documentation <http://mrjob.readthedocs.org/en/latest/>`_
mrjob fully supports Amazon's Elastic MapReduce (EMR) service, which allows you
to buy time on a Hadoop cluster on an hourly basis. mrjob has basic support for Google Cloud Dataproc (Dataproc)
which allows you to buy time on a Hadoop cluster on a minute-by-minute basis. It also works with your own
Hadoop cluster.
Some important features:
* Run jobs on EMR, Google Cloud Dataproc, your own Hadoop cluster, or locally (for testing).
* Write multi-step jobs (one map-reduce step feeds into the next)
* Easily launch Spark jobs on EMR or your own Hadoop cluster
* Duplicate your production environment inside Hadoop
* Upload your source tree and put it in your job's ``$PYTHONPATH``
* Run make and other setup scripts
* Set environment variables (e.g. ``$TZ``)
* Easily install python packages from tarballs (EMR only)
* Setup handled transparently by ``mrjob.conf`` config file
* Automatically interpret error logs
* SSH tunnel to hadoop job tracker (EMR only)
* Minimal setup
* To run on EMR, set ``$AWS_ACCESS_KEY_ID`` and ``$AWS_SECRET_ACCESS_KEY``
* To run on Dataproc, set ``$GOOGLE_APPLICATION_CREDENTIALS``
* No setup needed to use mrjob on your own Hadoop cluster
%package -n python3-mrjob
Summary: Python MapReduce framework
Provides: python-mrjob
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-mrjob
mrjob is a Python 2.7/3.4+ package that helps you write and run Hadoop
Streaming jobs.
`Stable version (v0.7.4) documentation <http://mrjob.readthedocs.org/en/stable/>`_
`Development version documentation <http://mrjob.readthedocs.org/en/latest/>`_
mrjob fully supports Amazon's Elastic MapReduce (EMR) service, which allows you
to buy time on a Hadoop cluster on an hourly basis. mrjob has basic support for Google Cloud Dataproc (Dataproc)
which allows you to buy time on a Hadoop cluster on a minute-by-minute basis. It also works with your own
Hadoop cluster.
Some important features:
* Run jobs on EMR, Google Cloud Dataproc, your own Hadoop cluster, or locally (for testing).
* Write multi-step jobs (one map-reduce step feeds into the next)
* Easily launch Spark jobs on EMR or your own Hadoop cluster
* Duplicate your production environment inside Hadoop
* Upload your source tree and put it in your job's ``$PYTHONPATH``
* Run make and other setup scripts
* Set environment variables (e.g. ``$TZ``)
* Easily install python packages from tarballs (EMR only)
* Setup handled transparently by ``mrjob.conf`` config file
* Automatically interpret error logs
* SSH tunnel to hadoop job tracker (EMR only)
* Minimal setup
* To run on EMR, set ``$AWS_ACCESS_KEY_ID`` and ``$AWS_SECRET_ACCESS_KEY``
* To run on Dataproc, set ``$GOOGLE_APPLICATION_CREDENTIALS``
* No setup needed to use mrjob on your own Hadoop cluster
%package help
Summary: Development documents and examples for mrjob
Provides: python3-mrjob-doc
%description help
mrjob is a Python 2.7/3.4+ package that helps you write and run Hadoop
Streaming jobs.
`Stable version (v0.7.4) documentation <http://mrjob.readthedocs.org/en/stable/>`_
`Development version documentation <http://mrjob.readthedocs.org/en/latest/>`_
mrjob fully supports Amazon's Elastic MapReduce (EMR) service, which allows you
to buy time on a Hadoop cluster on an hourly basis. mrjob has basic support for Google Cloud Dataproc (Dataproc)
which allows you to buy time on a Hadoop cluster on a minute-by-minute basis. It also works with your own
Hadoop cluster.
Some important features:
* Run jobs on EMR, Google Cloud Dataproc, your own Hadoop cluster, or locally (for testing).
* Write multi-step jobs (one map-reduce step feeds into the next)
* Easily launch Spark jobs on EMR or your own Hadoop cluster
* Duplicate your production environment inside Hadoop
* Upload your source tree and put it in your job's ``$PYTHONPATH``
* Run make and other setup scripts
* Set environment variables (e.g. ``$TZ``)
* Easily install python packages from tarballs (EMR only)
* Setup handled transparently by ``mrjob.conf`` config file
* Automatically interpret error logs
* SSH tunnel to hadoop job tracker (EMR only)
* Minimal setup
* To run on EMR, set ``$AWS_ACCESS_KEY_ID`` and ``$AWS_SECRET_ACCESS_KEY``
* To run on Dataproc, set ``$GOOGLE_APPLICATION_CREDENTIALS``
* No setup needed to use mrjob on your own Hadoop cluster
%prep
%autosetup -n mrjob-0.7.4
%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-mrjob -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Sun Apr 23 2023 Python_Bot <Python_Bot@openeuler.org> - 0.7.4-1
- Package Spec generated
|
