/usr/lib/python2.7/dist-packages/pbcommand-0.2.17.egg-info/PKG-INFO is in python-pbcommand 0.2.17-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | Metadata-Version: 1.1
Name: pbcommand
Version: 0.2.17
Summary: Library and Tools for interfacing to PacBio pbsmrtpipe workflow engine.
Home-page: https://github.com/PacificBiosciences/pbcommand
Author: mpkocher
Author-email: mkocher@pacificbiosciences.com
License: BSD
Download-URL: https://github.com/PacificBiosciences/pbcommand/tarball/0.2.17
Description: pbcommand High Level Overview
=============================
[Full Docs](http://pbcommand.readthedocs.org/en/latest/)
Note the APIs are still in flux. WIP.
[](https://circleci.com/gh/PacificBiosciences/pbcommand)
PacBio library for common utils, models, and tools to interface with pbsmrtpipe workflow engine.
To integrate with the pbsmrtpipe workflow engine you must to be able to generate a **Tool Contract** and to be able to run from a **Resolved Tool Contract**.
A **Tool Contract** contains the metadata of the exe, such as the file types of inputs, outputs and options.
Example [Tool Contract Json](https://github.com/PacificBiosciences/pbcommand/blob/master/tests/data/dev_example_dev_txt_app_tool_contract.json) (and [Avro Schema](https://github.com/PacificBiosciences/pbcommand/blob/master/pbcommand/schemas/tool_contract.avsc))
Example [Resolved Tool Contract Json](https://github.com/PacificBiosciences/pbcommand/blob/master/tests/data/resolved_tool_contract_dev_app.json) (and [Avro Schema](https://github.com/PacificBiosciences/pbcommand/blob/master/pbcommand/schemas/resolved_tool_contract.avsc))
There are two principle use cases, first wrapping/calling python functions that have been defined in external python packages, or scripts. Second, creating a CLI tool that supports emitting tool contracts, running resolved tool contracts and complete argparse style CLI.
Example from **pbcommand.cli.examples**
```python
import sys
import logging
from pbcommand.models import FileTypes
from pbcommand.cli import registry_builder, registry_runner
log = logging.getLogger(__name__)
registry = registry_builder("pbcommand", "python -m pbcommand.cli.examples.dev_quick_hello_world ")
def _example_main(input_files, output_files, **kwargs):
# Simple Function that should imported from your library code
# write mock output files for testing purposes, otherwise the End-to-End test will fail
xs = output_files if isinstance(output_files, (list, tuple)) else [output_files]
for x in xs:
with open(x, 'w') as writer:
writer.write("Mock data\n")
return 0
@registry("dev_qhello_world", "0.2.1", FileTypes.FASTA, FileTypes.FASTA, nproc=1, options=dict(alpha=1234))
def run_rtc(rtc):
return _example_main(rtc.task.input_files[0], rtc.task.output_files[0], nproc=rtc.task.nproc)
@registry("dev_fastq2fasta", "0.1.0", FileTypes.FASTQ, FileTypes.FASTA)
def run_rtc(rtc):
return _example_main(rtc.task.input_files[0], rtc.task.output_files[0])
if __name__ == '__main__':
sys.exit(registry_runner(registry, sys.argv[1:]))
```
A driver is the commandline interface that the workflow engine will call.
The driver will be called with "${exe} /path/to/resolved_tool_contract.json"
The tool contracts can be emitted to a directory and used in [pbsmrtpipe](https://github.com/PacificBiosciences/pbsmrtpipe).
```bash
$> python -m pbcommand.cli.examples.dev_quick_hello_world -o /path/to/my-tool-contracts
```
Creating a Full Commandline Tool with TC/RTC and argparse support
-----------------------------------------------------------------
Three Steps
- define Parser
- add running from argparse and running from Resolved ToolContract funcs to call your main
- add call to driver
Import or define your main function.
```python
def run_my_main(fasta_in, fasta_out, min_length):
# do stuff. Main should return an int exit code
return 0
```
Define a function that will add inputs, outputs and options to your parser.
```python
from pbcommand.models import FileTypes
def add_args_and_options(p):
# FileType, label, name, description
p.add_input_file_type(FileTypes.FASTA, "fasta_in", "Fasta File", "PacBio Spec'ed fasta file")
# File Type, label, name, description, default file name
p.add_output_file_type(FileTypes.FASTA, "fasta_out", "Filtered Fasta file", "Filtered Fasta file", "filter.fasta")
# Option id, label, default value, name, description
# for the argparse, the read-length will be translated to --read-length and (accessible via args.read_length)
p.add_int("pbcommand.task_options.dev_read_length", "read-length", 25, "Length filter", "Min Sequence Length filter")
return p
```
Define Parser
```python
from pbcommand.models import TaskTypes, SymbolTypes, get_pbparser
def get_contract_parser():
tool_id = "example_namespace.tasks.my_id"
version = "0.1.0" # or reuse __version__
display_name = "My Example Tool"
# Number of processors to use, can also be SymbolTypes.MAX_NPROC
nproc = 1
# Log file, tmp dir, tmp file. See ResourceTypes in models, ResourceTypes.TMP_DIR
resource_types = ()
# Commandline exe to call "{exe}" /path/to/resolved-tool-contract.json
driver_exe = "python -m pbcommand.cli.example.dev_app --resolved-tool-contract "
desc = "Dev app for Testing that supports emitting tool contracts"
is_distributed = False
# set to True if you want your task to be submitted to the cluster manager (e.g., SGE) if
# one is provided to the workflow engine.
p = get_pbparser(tool_id, version, display_name, desc, driver_exe, is_distributed=is_distributed, nproc=nproc, resource_types=resource_types)
add_args_and_options(p)
return p
```
Define a Wrapping layer to call your main from both the tool contract and raw argparse IO layer
```python
def _args_runner(args):
# this is the args from parser.parse_args()
# the properties of args are defined as "labels" in the add_args_and_options func.
return run_my_main(args.fasta_in, args.fasta_out, args.read_length)
def _resolved_tool_contract_runner(resolved_tool_contract):
"""
:type resolved_tool_contract: pbcommand.models.ResolvedToolContract"""
rtc = resolved_tool_contract
# all options are referenced by globally namespaced id. This allows tools to use other tools options
# e.g., pbalign to use blasr defined options.
return run_my_main(rtc.task.input_files[0], rtc.task.outputs[0], rtc.task.options["pbcommand.task_options.dev_read_length"])
```
Add running layer
```python
import sys
import logging
from pbcommand.utils import setup_log
from pbcommand.cli import pbparser_runner
log = logging.getLogger(__name__)
def main(argv=sys.argv):
# New interface that supports running resolved tool contracts
log.info("Starting {f} version {v} pbcommand example dev app".format(f=__file__, v="0.1.0"))
return pbparser_runner(argv[1:],
get_contract_parser(),
_args_runner, # argparse runner func
_resolved_tool_contract_runner, # tool contract runner func
log, # log instance
setup_log # setup log func
)
if __name__ == '__main__':
sys.exit(main())
```
Now you can run your tool via the argparse standard interface as well as emitting a **Tool Contract** to stdout from the commandline interface.
```sh
> python -m 'pbcommand.cli.examples.dev_app' --emit-tool-contract
```
And you can run the tool from a **Resolved Tool Contract**
```sh
> python -m pbcommand.cli.example.dev_app --resolved-tool-contract /path/to/resolved_contract.json
```
See the dev apps in ["pbcommand.cli.examples"](https://github.com/PacificBiosciences/pbcommand/blob/master/pbcommand/cli/examples/dev_app.py) for a complete application (They require pbcore to be installed).
In addition to TC/RTC support, there's a complete argparse support for the task options. An example of **help** is shown below.
```sh
(pbcommand_test)pbcommand $> python -m 'pbcommand.cli.examples.dev_app' --help
usage: dev_app.py [-h] [-v] [--versions] [--emit-tool-contract]
[--resolved-tool-contract RESOLVED_TOOL_CONTRACT]
[--log-level LOG_LEVEL] [--debug]
[--read-length READ_LENGTH]
fasta_in fasta_out
Dev app for Testing that supports emitting tool contracts
positional arguments:
fasta_in PacBio Spec'ed fasta file
fasta_out Filtered Fasta file
optional arguments:
-h, --help show this help message and exit
-v, --version show program's version number and exit
--versions Show versions of individual components (default: None)
--emit-tool-contract Emit Tool Contract to stdout (default: False)
--resolved-tool-contract RESOLVED_TOOL_CONTRACT
Run Tool directly from a PacBio Resolved tool contract
(default: None)
--log-level LOG_LEVEL
Set log level (default: 10)
--debug Debug to stdout (default: False)
--read-length READ_LENGTH
Min Sequence Length filter (default: 25)
```
Keywords: workflow,pacbio
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Topic :: Software Development :: Bug Tracking
|