lsst.meas.algorithms  22.0.1-23-gc2439a9a+6551e58923
readTextCatalogTask.py
Go to the documentation of this file.
1 #
2 # LSST Data Management System
3 #
4 # Copyright 2008-2017 AURA/LSST.
5 #
6 # This product includes software developed by the
7 # LSST Project (http://www.lsst.org/).
8 #
9 # This program is free software: you can redistribute it and/or modify
10 # it under the terms of the GNU General Public License as published by
11 # the Free Software Foundation, either version 3 of the License, or
12 # (at your option) any later version.
13 #
14 # This program is distributed in the hope that it will be useful,
15 # but WITHOUT ANY WARRANTY; without even the implied warranty of
16 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17 # GNU General Public License for more details.
18 #
19 # You should have received a copy of the LSST License Statement and
20 # the GNU General Public License along with this program. If not,
21 # see <https://www.lsstcorp.org/LegalNotices/>.
22 #
23 
24 __all__ = ["ReadTextCatalogConfig", "ReadTextCatalogTask"]
25 
26 import numpy as np
27 from astropy.table import Table
28 
29 import lsst.pex.config as pexConfig
30 import lsst.pipe.base as pipeBase
31 
32 
33 class ReadTextCatalogConfig(pexConfig.Config):
34  header_lines = pexConfig.Field(
35  dtype=int,
36  default=0,
37  doc='Number of lines to skip when reading the text reference file.'
38  )
39  colnames = pexConfig.ListField(
40  dtype=str,
41  default=[],
42  doc="An ordered list of column names to use in ingesting the catalog. "
43  "With an empty list, column names will be discovered from the first line "
44  "after the skipped header lines."
45  )
46  delimiter = pexConfig.Field(
47  dtype=str,
48  default=',',
49  doc='Delimiter to use when reading text reference files. Comma is default.'
50  )
51  format = pexConfig.Field(
52  dtype=str,
53  default='csv',
54  doc=("Format of files to read, from the astropy.table I/O list here:"
55  "http://docs.astropy.org/en/stable/io/unified.html#built-in-table-readers-writers")
56  )
57 
58 
59 class ReadTextCatalogTask(pipeBase.Task):
60  """Read an object catalog from a text file
61  """
62  _DefaultName = 'readCatalog'
63  ConfigClass = ReadTextCatalogConfig
64 
65  def run(self, filename):
66  """Read an object catalog from the specified text file
67 
68  Parameters
69  ----------
70  filename : `string`
71  Path to specified text file
72 
73  Returns
74  -------
75  A numpy structured array containing the specified columns
76  """
77  kwargs = {}
78  if self.config.colnames:
79  kwargs['names'] = self.config.colnames
80  # if we specify the column names, then we need to just ignore the header lines.
81  kwargs['data_start'] = self.config.header_lines
82  else:
83  # if we don't specify column names, start the header at this line.
84  kwargs['header_start'] = self.config.header_lines
85 
86  # return a numpy array for backwards compatibility with other readers
87  return np.array(Table.read(filename, format=self.config.format,
88  delimiter=self.config.delimiter,
89  **kwargs).as_array())