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
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
|
%global _empty_manifest_terminate_build 0
Name: python-download-giab
Version: 0.7.0
Release: 1
Summary: Utility Python package to download Genome-in-a-Bottle data from their index files.
License: GPLv3
URL: https://github.com/davidlougheed/download_giab
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/9d/6e/0a6a14adce94cf988f3b7c80d7f5b98fce1bbe2dd9cc32a40751c9c46ff6/download_giab-0.7.0.tar.gz
BuildArch: noarch
Requires: python3-requests
%description
# download_giab
Utility Python package to download Genome-in-a-Bottle (GIAB) data from their
[index files](https://github.com/genome-in-a-bottle/giab_data_indexes/).
This requires Python 3.6 or later.
To install, run the following:
```bash
pip install download_giab
```
If you're installing on a cluster, this might be more like:
```bash
pip install --user download_giab
```
To use, run something like the following:
```bash
download_giab https://raw.githubusercontent.com/genome-in-a-bottle/giab_data_indexes/master/AshkenazimTrio/sequence.index.AJtrio_Illumina300X_wgs_07292015.HG002
```
This will download everything in the linked index to the directory the utility is run from.
It can also download from local index files.
If you want to download lots of data and not have the program hang up upon session disconnect,
you can use `nohup` and `&`:
```bash
nohup download_giab https://raw.githubusercontent.com/genome-in-a-bottle/giab_data_indexes/master/AshkenazimTrio/sequence.index.AJtrio_Illumina300X_wgs_07292015.HG002 &
```
If you are downloading paired-end reads and want to concatenate all FASTQ files into two files,
you can use the `--cat-paired` flag. This will generate two files per sample: `[sample]_1.fastq.gz`
and `[sample]_2.fastq.gz`. If a sample ID is not present, the literal text `paired` will be used.
This will not work for some tools (e.g. `bwa mem`) if the FASTQ files in a pair-set are of
different lengths.
If instead you want to store the read pairs + a suggested common name, use the `--store-paired-names`
flag. This will write to a file called `paired_names.txt`.
To filter what files are downloaded, the `--filter` flag can be provided with a case insensitive
string or regular expression (in Python syntax.)
%package -n python3-download-giab
Summary: Utility Python package to download Genome-in-a-Bottle data from their index files.
Provides: python-download-giab
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-download-giab
# download_giab
Utility Python package to download Genome-in-a-Bottle (GIAB) data from their
[index files](https://github.com/genome-in-a-bottle/giab_data_indexes/).
This requires Python 3.6 or later.
To install, run the following:
```bash
pip install download_giab
```
If you're installing on a cluster, this might be more like:
```bash
pip install --user download_giab
```
To use, run something like the following:
```bash
download_giab https://raw.githubusercontent.com/genome-in-a-bottle/giab_data_indexes/master/AshkenazimTrio/sequence.index.AJtrio_Illumina300X_wgs_07292015.HG002
```
This will download everything in the linked index to the directory the utility is run from.
It can also download from local index files.
If you want to download lots of data and not have the program hang up upon session disconnect,
you can use `nohup` and `&`:
```bash
nohup download_giab https://raw.githubusercontent.com/genome-in-a-bottle/giab_data_indexes/master/AshkenazimTrio/sequence.index.AJtrio_Illumina300X_wgs_07292015.HG002 &
```
If you are downloading paired-end reads and want to concatenate all FASTQ files into two files,
you can use the `--cat-paired` flag. This will generate two files per sample: `[sample]_1.fastq.gz`
and `[sample]_2.fastq.gz`. If a sample ID is not present, the literal text `paired` will be used.
This will not work for some tools (e.g. `bwa mem`) if the FASTQ files in a pair-set are of
different lengths.
If instead you want to store the read pairs + a suggested common name, use the `--store-paired-names`
flag. This will write to a file called `paired_names.txt`.
To filter what files are downloaded, the `--filter` flag can be provided with a case insensitive
string or regular expression (in Python syntax.)
%package help
Summary: Development documents and examples for download-giab
Provides: python3-download-giab-doc
%description help
# download_giab
Utility Python package to download Genome-in-a-Bottle (GIAB) data from their
[index files](https://github.com/genome-in-a-bottle/giab_data_indexes/).
This requires Python 3.6 or later.
To install, run the following:
```bash
pip install download_giab
```
If you're installing on a cluster, this might be more like:
```bash
pip install --user download_giab
```
To use, run something like the following:
```bash
download_giab https://raw.githubusercontent.com/genome-in-a-bottle/giab_data_indexes/master/AshkenazimTrio/sequence.index.AJtrio_Illumina300X_wgs_07292015.HG002
```
This will download everything in the linked index to the directory the utility is run from.
It can also download from local index files.
If you want to download lots of data and not have the program hang up upon session disconnect,
you can use `nohup` and `&`:
```bash
nohup download_giab https://raw.githubusercontent.com/genome-in-a-bottle/giab_data_indexes/master/AshkenazimTrio/sequence.index.AJtrio_Illumina300X_wgs_07292015.HG002 &
```
If you are downloading paired-end reads and want to concatenate all FASTQ files into two files,
you can use the `--cat-paired` flag. This will generate two files per sample: `[sample]_1.fastq.gz`
and `[sample]_2.fastq.gz`. If a sample ID is not present, the literal text `paired` will be used.
This will not work for some tools (e.g. `bwa mem`) if the FASTQ files in a pair-set are of
different lengths.
If instead you want to store the read pairs + a suggested common name, use the `--store-paired-names`
flag. This will write to a file called `paired_names.txt`.
To filter what files are downloaded, the `--filter` flag can be provided with a case insensitive
string or regular expression (in Python syntax.)
%prep
%autosetup -n download-giab-0.7.0
%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-download-giab -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Wed May 10 2023 Python_Bot <Python_Bot@openeuler.org> - 0.7.0-1
- Package Spec generated
|
