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
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
|
%global _empty_manifest_terminate_build 0
Name: python-dictionaryutils
Version: 3.4.5
Release: 1
Summary: Python wrapper and metaschema for datadictionary.
License: Apache-2.0
URL: https://github.com/uc-cdis/dictionaryutils
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/0d/f3/b613db7a4b680ba9718b2e6776a0fbc5b9b8f2c4ff321127b0dbadfb179e/dictionaryutils-3.4.5.tar.gz
BuildArch: noarch
Requires: python3-PyYAML
Requires: python3-jsonschema
Requires: python3-cdislogging
Requires: python3-requests
%description
# dictionaryutils
python wrapper and metaschema for datadictionary.
It can be used to:
- load a local dictionary to a python object.
- dump schemas to a file that can be uploaded to s3 as an artifact.
- load schema file from an url to a python object that can be used by services
## Test for dictionary validity with Docker
Say you have a dictionary you are building locally and you want to see if it will pass the tests.
You can add a simple alias to your `.bash_profile` to enable a quick test command:
```
testdict() { docker run --rm -v $(pwd):/dictionary quay.io/cdis/dictionaryutils:master; }
```
Then from the directory containing the `gdcdictionary` directory run `testdict`.
## Generate simulated data with Docker
If you wish to generate fake simulated data you can also do that with dictionaryutils and the data-simulator.
```
simdata() { docker run --rm -v $(pwd):/dictionary -v $(pwd)/simdata:/simdata quay.io/cdis/dictionaryutils:master /bin/sh -c "cd /dictionary && python setup.py install --force; python /src/datasimulator/bin/data-simulator simulate --path /simdata/ $*; export SUCCESS=$?; rm -rf build dictionaryutils dist gdcdictionary.egg-info; chmod -R a+rwX /simdata; exit $SUCCESS"; }
simdataurl() { docker run --rm -v $(pwd):/dictionary -v $(pwd)/simdata:/simdata quay.io/cdis/dictionaryutils:master /bin/sh -c "python /src/datasimulator/bin/data-simulator simulate --path /simdata/ $*; chmod -R a+rwX /simdata"; }
```
Then from the directory containing the `gdcdictionary` directory run `simdata` and a folder will be created called `simdata` with the results of the simulator run. You can also pass in additional arguments to the data-simulator script such as `simdata --max_samples 10`.
The `--max_samples` argument will define a default number of nodes to simulate, but you can override it using the `--node_num_instances_file` argument. For example, if you create the following `instances.json`:
```
{
"case": 100,
"demographic": 100
}
```
Then run the following:
```
docker run --rm -v $(pwd):/dictionary -v $(pwd)/simdata:/simdata quay.io/cdis/dictionaryutils:master /bin/sh -c "cd /dictionary && python setup.py install --force; python /src/datasimulator/bin/data-simulator simulate --path /simdata/ --program workshop --project project1 --max_samples 10 --node_num_instances_file instances.json; export SUCCESS=$?; rm -rf build dictionaryutils dist gdcdictionary.egg-info; chmod -R a+rwX /simdata; exit $SUCCESS";
```
Then you'll get 100 each of `case` and `demographic` nodes and 10 each of everything else. Note that the above example also defines `program` and `project` names.
You can also run the simulator for an arbitrary json url by using `simdataurl --url https://datacommons.example.com/schema.json`.
## Use dictionaryutils to load a dictionary
```
from dictionaryutils import DataDictionary
dict_fetch_from_remote = DataDictionary(url=URL_FOR_THE_JSON)
dict_loaded_locally = DataDictionary(root_dir=PATH_TO_SCHEMA_DIR)
```
## Use dictionaryutils to dump a dictionary
```
import json
from dictionaryutils import dump_schemas_from_dir
with open('dump.json', 'w') as f:
json.dump(dump_schemas_from_dir('../datadictionary/gdcdictionary/schemas/'), f)
```
%package -n python3-dictionaryutils
Summary: Python wrapper and metaschema for datadictionary.
Provides: python-dictionaryutils
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-dictionaryutils
# dictionaryutils
python wrapper and metaschema for datadictionary.
It can be used to:
- load a local dictionary to a python object.
- dump schemas to a file that can be uploaded to s3 as an artifact.
- load schema file from an url to a python object that can be used by services
## Test for dictionary validity with Docker
Say you have a dictionary you are building locally and you want to see if it will pass the tests.
You can add a simple alias to your `.bash_profile` to enable a quick test command:
```
testdict() { docker run --rm -v $(pwd):/dictionary quay.io/cdis/dictionaryutils:master; }
```
Then from the directory containing the `gdcdictionary` directory run `testdict`.
## Generate simulated data with Docker
If you wish to generate fake simulated data you can also do that with dictionaryutils and the data-simulator.
```
simdata() { docker run --rm -v $(pwd):/dictionary -v $(pwd)/simdata:/simdata quay.io/cdis/dictionaryutils:master /bin/sh -c "cd /dictionary && python setup.py install --force; python /src/datasimulator/bin/data-simulator simulate --path /simdata/ $*; export SUCCESS=$?; rm -rf build dictionaryutils dist gdcdictionary.egg-info; chmod -R a+rwX /simdata; exit $SUCCESS"; }
simdataurl() { docker run --rm -v $(pwd):/dictionary -v $(pwd)/simdata:/simdata quay.io/cdis/dictionaryutils:master /bin/sh -c "python /src/datasimulator/bin/data-simulator simulate --path /simdata/ $*; chmod -R a+rwX /simdata"; }
```
Then from the directory containing the `gdcdictionary` directory run `simdata` and a folder will be created called `simdata` with the results of the simulator run. You can also pass in additional arguments to the data-simulator script such as `simdata --max_samples 10`.
The `--max_samples` argument will define a default number of nodes to simulate, but you can override it using the `--node_num_instances_file` argument. For example, if you create the following `instances.json`:
```
{
"case": 100,
"demographic": 100
}
```
Then run the following:
```
docker run --rm -v $(pwd):/dictionary -v $(pwd)/simdata:/simdata quay.io/cdis/dictionaryutils:master /bin/sh -c "cd /dictionary && python setup.py install --force; python /src/datasimulator/bin/data-simulator simulate --path /simdata/ --program workshop --project project1 --max_samples 10 --node_num_instances_file instances.json; export SUCCESS=$?; rm -rf build dictionaryutils dist gdcdictionary.egg-info; chmod -R a+rwX /simdata; exit $SUCCESS";
```
Then you'll get 100 each of `case` and `demographic` nodes and 10 each of everything else. Note that the above example also defines `program` and `project` names.
You can also run the simulator for an arbitrary json url by using `simdataurl --url https://datacommons.example.com/schema.json`.
## Use dictionaryutils to load a dictionary
```
from dictionaryutils import DataDictionary
dict_fetch_from_remote = DataDictionary(url=URL_FOR_THE_JSON)
dict_loaded_locally = DataDictionary(root_dir=PATH_TO_SCHEMA_DIR)
```
## Use dictionaryutils to dump a dictionary
```
import json
from dictionaryutils import dump_schemas_from_dir
with open('dump.json', 'w') as f:
json.dump(dump_schemas_from_dir('../datadictionary/gdcdictionary/schemas/'), f)
```
%package help
Summary: Development documents and examples for dictionaryutils
Provides: python3-dictionaryutils-doc
%description help
# dictionaryutils
python wrapper and metaschema for datadictionary.
It can be used to:
- load a local dictionary to a python object.
- dump schemas to a file that can be uploaded to s3 as an artifact.
- load schema file from an url to a python object that can be used by services
## Test for dictionary validity with Docker
Say you have a dictionary you are building locally and you want to see if it will pass the tests.
You can add a simple alias to your `.bash_profile` to enable a quick test command:
```
testdict() { docker run --rm -v $(pwd):/dictionary quay.io/cdis/dictionaryutils:master; }
```
Then from the directory containing the `gdcdictionary` directory run `testdict`.
## Generate simulated data with Docker
If you wish to generate fake simulated data you can also do that with dictionaryutils and the data-simulator.
```
simdata() { docker run --rm -v $(pwd):/dictionary -v $(pwd)/simdata:/simdata quay.io/cdis/dictionaryutils:master /bin/sh -c "cd /dictionary && python setup.py install --force; python /src/datasimulator/bin/data-simulator simulate --path /simdata/ $*; export SUCCESS=$?; rm -rf build dictionaryutils dist gdcdictionary.egg-info; chmod -R a+rwX /simdata; exit $SUCCESS"; }
simdataurl() { docker run --rm -v $(pwd):/dictionary -v $(pwd)/simdata:/simdata quay.io/cdis/dictionaryutils:master /bin/sh -c "python /src/datasimulator/bin/data-simulator simulate --path /simdata/ $*; chmod -R a+rwX /simdata"; }
```
Then from the directory containing the `gdcdictionary` directory run `simdata` and a folder will be created called `simdata` with the results of the simulator run. You can also pass in additional arguments to the data-simulator script such as `simdata --max_samples 10`.
The `--max_samples` argument will define a default number of nodes to simulate, but you can override it using the `--node_num_instances_file` argument. For example, if you create the following `instances.json`:
```
{
"case": 100,
"demographic": 100
}
```
Then run the following:
```
docker run --rm -v $(pwd):/dictionary -v $(pwd)/simdata:/simdata quay.io/cdis/dictionaryutils:master /bin/sh -c "cd /dictionary && python setup.py install --force; python /src/datasimulator/bin/data-simulator simulate --path /simdata/ --program workshop --project project1 --max_samples 10 --node_num_instances_file instances.json; export SUCCESS=$?; rm -rf build dictionaryutils dist gdcdictionary.egg-info; chmod -R a+rwX /simdata; exit $SUCCESS";
```
Then you'll get 100 each of `case` and `demographic` nodes and 10 each of everything else. Note that the above example also defines `program` and `project` names.
You can also run the simulator for an arbitrary json url by using `simdataurl --url https://datacommons.example.com/schema.json`.
## Use dictionaryutils to load a dictionary
```
from dictionaryutils import DataDictionary
dict_fetch_from_remote = DataDictionary(url=URL_FOR_THE_JSON)
dict_loaded_locally = DataDictionary(root_dir=PATH_TO_SCHEMA_DIR)
```
## Use dictionaryutils to dump a dictionary
```
import json
from dictionaryutils import dump_schemas_from_dir
with open('dump.json', 'w') as f:
json.dump(dump_schemas_from_dir('../datadictionary/gdcdictionary/schemas/'), f)
```
%prep
%autosetup -n dictionaryutils-3.4.5
%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-dictionaryutils -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Wed Apr 12 2023 Python_Bot <Python_Bot@openeuler.org> - 3.4.5-1
- Package Spec generated
|
