Skip to content

Expose cell method parsing. #1981

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

Expose cell method parsing. #1981

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
58ccfda
Expose cell method parsing.
rhattersley Apr 21, 2016
7903c41
Update copyright header
rhattersley Apr 21, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
97 changes: 3 additions & 94 deletions lib/iris/fileformats/_pyke_rules/fc_rules_cf.krb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -764,7 +764,6 @@ fc_formula_terms
fc_extras
import six

import re
import warnings

import biggus
Expand All @@ -777,6 +776,7 @@ fc_extras
import iris.coords
import iris.coord_systems
import iris.fileformats.cf as cf
import iris.fileformats.netcdf
import iris.fileformats.pp as pp
import iris.exceptions
import iris.std_names
Expand Down Expand Up @@ -873,26 +873,6 @@ fc_extras
CF_VALUE_STD_NAME_GRID_LON = 'grid_longitude'
CF_VALUE_STD_NAME_PROJ_X = 'projection_x_coordinate'
CF_VALUE_STD_NAME_PROJ_Y = 'projection_y_coordinate'

# Cell methods.
CM_KNOWN_METHODS = ['point', 'sum', 'mean', 'maximum', 'minimum', 'mid_range',
'standard_deviation', 'variance', 'mode', 'median']

CM_COMMENT = 'comment'
CM_EXTRA = 'extra'
CM_INTERVAL = 'interval'
CM_METHOD = 'method'
CM_NAME = 'name'

CM_PARSE = re.compile( r'''
(?P<name>([\w_]+\s*?:\s+)+)
(?P<method>[\w_\s]+(?![\w_]*\s*?:))\s*
(?:
\(\s*
(?P<extra>[^\)]+)
\)\s*
)?
''', re.VERBOSE)


################################################################################
Expand Down Expand Up @@ -923,7 +903,8 @@ fc_extras

# Incorporate cell methods
nc_att_cell_methods = getattr(cf_var, CF_ATTR_CELL_METHODS, None)
cube.cell_methods = _parse_cell_methods(cf_var.cf_name, nc_att_cell_methods)
cube.cell_methods = iris.fileformats.netcdf.parse_cell_methods(
cf_var.cf_name, nc_att_cell_methods)

# Set the cube global attributes.
for attr_name, attr_value in six.iteritems(cf_var.cf_group.global_attributes):
Expand Down Expand Up @@ -1546,75 +1527,3 @@ fc_extras
def is_rotated_longitude(engine, cf_name):
"""Determine whether the CF coordinate variable is rotated longitude."""
return _is_rotated(engine, cf_name, CF_VALUE_STD_NAME_GRID_LON)


################################################################################
def _parse_cell_methods(cf_var_name, nc_cell_methods):
"""Parse the CF cell_methods attribute string."""

cell_methods = []
if nc_cell_methods is not None:
for m in CM_PARSE.finditer(nc_cell_methods):
d = m.groupdict()
method = d[CM_METHOD]
method = method.strip()
# Check validity of method, allowing for multi-part methods
# e.g. mean over years.
method_words = method.split()
if method_words[0].lower() not in CM_KNOWN_METHODS:
msg = 'NetCDF variable {!r} contains unknown cell ' \
'method {!r}'
warnings.warn(msg.format('{}'.format(cf_var_name),
'{}'.format(method_words[0])))
d[CM_METHOD] = method
name = d[CM_NAME]
name = name.replace(' ', '')
name = name.rstrip(':')
d[CM_NAME] = tuple([n for n in name.split(':')])
interval = []
comment = []
if d[CM_EXTRA] is not None:
#
# tokenise the key words and field colon marker
#
d[CM_EXTRA] = d[CM_EXTRA].replace('comment:', '<<comment>><<:>>')
d[CM_EXTRA] = d[CM_EXTRA].replace('interval:', '<<interval>><<:>>')
d[CM_EXTRA] = d[CM_EXTRA].split('<<:>>')
if len(d[CM_EXTRA]) == 1:
comment.extend(d[CM_EXTRA])
else:
next_field_type = comment
for field in d[CM_EXTRA]:
field_type = next_field_type
index = field.rfind('<<interval>>')
if index == 0:
next_field_type = interval
continue
elif index > 0:
next_field_type = interval
else:
index = field.rfind('<<comment>>')
if index == 0:
next_field_type = comment
continue
elif index > 0:
next_field_type = comment
if index != -1:
field = field[:index]
field_type.append(field.strip())
#
# cater for a shared interval over multiple axes
#
if len(interval):
if len(d[CM_NAME]) != len(interval) and len(interval) == 1:
interval = interval*len(d[CM_NAME])
#
# cater for a shared comment over multiple axes
#
if len(comment):
if len(d[CM_NAME]) != len(comment) and len(comment) == 1:
comment = comment*len(d[CM_NAME])
d[CM_INTERVAL] = tuple(interval)
d[CM_COMMENT] = tuple(comment)
cell_methods.append(iris.coords.CellMethod(d[CM_METHOD], coords=d[CM_NAME], intervals=d[CM_INTERVAL], comments=d[CM_COMMENT]))
return tuple(cell_methods)
111 changes: 111 additions & 0 deletions lib/iris/fileformats/netcdf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@
import collections
import os
import os.path
import re
import string
import warnings

Expand Down Expand Up @@ -136,6 +137,116 @@
}


# Cell methods.
_CM_KNOWN_METHODS = ['point', 'sum', 'mean', 'maximum', 'minimum', 'mid_range',
'standard_deviation', 'variance', 'mode', 'median']

_CM_COMMENT = 'comment'
_CM_EXTRA = 'extra'
_CM_INTERVAL = 'interval'
_CM_METHOD = 'method'
_CM_NAME = 'name'
_CM_PARSE = re.compile(r'''
(?P<name>([\w_]+\s*?:\s+)+)
(?P<method>[\w_\s]+(?![\w_]*\s*?:))\s*
(?:
\(\s*
(?P<extra>[^\)]+)
\)\s*
)?
''', re.VERBOSE)


def parse_cell_methods(cf_var_name, nc_cell_methods):
"""
Parse a CF cell_methods attribute string into a tuple of zero or
more CellMethod instances.

Args:

* cf_var_name (str):
The name of the netCDF variable that contains this cell methods
attribute.

* nc_cell_methods (str):
The value of the cell methods attribute to be parsed.

"""

cell_methods = []
if nc_cell_methods is not None:
for m in _CM_PARSE.finditer(nc_cell_methods):
d = m.groupdict()
method = d[_CM_METHOD]
method = method.strip()
# Check validity of method, allowing for multi-part methods
# e.g. mean over years.
method_words = method.split()
if method_words[0].lower() not in _CM_KNOWN_METHODS:
msg = 'NetCDF variable {!r} contains unknown cell ' \
'method {!r}'
warnings.warn(msg.format('{}'.format(cf_var_name),
'{}'.format(method_words[0])))
d[_CM_METHOD] = method
name = d[_CM_NAME]
name = name.replace(' ', '')
name = name.rstrip(':')
d[_CM_NAME] = tuple([n for n in name.split(':')])
interval = []
comment = []
if d[_CM_EXTRA] is not None:
#
# tokenise the key words and field colon marker
#
d[_CM_EXTRA] = d[_CM_EXTRA].replace('comment:',
'<<comment>><<:>>')
d[_CM_EXTRA] = d[_CM_EXTRA].replace('interval:',
'<<interval>><<:>>')
d[_CM_EXTRA] = d[_CM_EXTRA].split('<<:>>')
if len(d[_CM_EXTRA]) == 1:
comment.extend(d[_CM_EXTRA])
else:
next_field_type = comment
for field in d[_CM_EXTRA]:
field_type = next_field_type
index = field.rfind('<<interval>>')
if index == 0:
next_field_type = interval
continue
elif index > 0:
next_field_type = interval
else:
index = field.rfind('<<comment>>')
if index == 0:
next_field_type = comment
continue
elif index > 0:
next_field_type = comment
if index != -1:
field = field[:index]
field_type.append(field.strip())
#
# cater for a shared interval over multiple axes
#
if len(interval):
if len(d[_CM_NAME]) != len(interval) and len(interval) == 1:
interval = interval*len(d[_CM_NAME])
#
# cater for a shared comment over multiple axes
#
if len(comment):
if len(d[_CM_NAME]) != len(comment) and len(comment) == 1:
comment = comment*len(d[_CM_NAME])
d[_CM_INTERVAL] = tuple(interval)
d[_CM_COMMENT] = tuple(comment)
cell_method = iris.coords.CellMethod(d[_CM_METHOD],
coords=d[_CM_NAME],
intervals=d[_CM_INTERVAL],
comments=d[_CM_COMMENT])
cell_methods.append(cell_method)
return tuple(cell_methods)


class CFNameCoordMap(object):
"""Provide a simple CF name to CF coordinate mapping."""

Expand Down
22 changes: 10 additions & 12 deletions ...c_rules_cf_fc/test__parse_cell_methods.py → ...formats/netcdf/test_parse_cell_methods.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# (C) British Crown Copyright 2015, Met Office
# (C) British Crown Copyright 2015 - 2016, Met Office
#
# This file is part of Iris.
#
Expand All @@ -15,8 +15,7 @@
# You should have received a copy of the GNU Lesser General Public License
# along with Iris. If not, see <http://www.gnu.org/licenses/>.
"""
Test function :func:`iris.fileformats._pyke_rules.compiled_krb.\
fc_rules_cf_fc._parse_cell_methods`.
Unit tests for :func:`iris.fileformats.netcdf.parse_cell_methods`.

"""

Expand All @@ -28,8 +27,7 @@
import iris.tests as tests

from iris.coords import CellMethod
from iris.fileformats._pyke_rules.compiled_krb.fc_rules_cf_fc import \
_parse_cell_methods
from iris.fileformats.netcdf import parse_cell_methods
from iris.tests import mock


Expand All @@ -41,7 +39,7 @@ def test_simple(self):
]
expected = (CellMethod(method='mean', coords='time'),)
for cell_method_str in cell_method_strings:
res = _parse_cell_methods('test_var', cell_method_str)
res = parse_cell_methods('test_var', cell_method_str)
self.assertEqual(res, expected)

def test_with_interval(self):
Expand All @@ -52,7 +50,7 @@ def test_with_interval(self):
expected = (CellMethod(method='variance', coords='time',
intervals='1 hr'),)
for cell_method_str in cell_method_strings:
res = _parse_cell_methods('test_var', cell_method_str)
res = parse_cell_methods('test_var', cell_method_str)
self.assertEqual(res, expected)

def test_multiple(self):
Expand All @@ -67,7 +65,7 @@ def test_multiple(self):
CellMethod(method='mean', coords='time',
intervals='1 day'))
for cell_method_str in cell_method_strings:
res = _parse_cell_methods('test_var', cell_method_str)
res = parse_cell_methods('test_var', cell_method_str)
self.assertEqual(res, expected)

def test_comment(self):
Expand All @@ -86,7 +84,7 @@ def test_comment(self):
CellMethod(method='mean', coords='time',
intervals='1 day', comments='second bit'))
for cell_method_str in cell_method_strings:
res = _parse_cell_methods('test_var', cell_method_str)
res = parse_cell_methods('test_var', cell_method_str)
self.assertEqual(res, expected)

def test_portions_of_cells(self):
Expand All @@ -97,7 +95,7 @@ def test_portions_of_cells(self):
expected = (CellMethod(method='mean where sea_ice over sea',
coords='area'),)
for cell_method_str in cell_method_strings:
res = _parse_cell_methods('test_var', cell_method_str)
res = parse_cell_methods('test_var', cell_method_str)
self.assertEqual(res, expected)

def test_climatology(self):
Expand All @@ -110,7 +108,7 @@ def test_climatology(self):
expected = (CellMethod(method='minimum within days', coords='time'),
CellMethod(method='mean over days', coords='time'))
for cell_method_str in cell_method_strings:
res = _parse_cell_methods('test_var', cell_method_str)
res = parse_cell_methods('test_var', cell_method_str)
self.assertEqual(res, expected)

def test_climatology_with_unknown_method(self):
Expand All @@ -124,7 +122,7 @@ def test_climatology_with_unknown_method(self):
CellMethod(method='mean over days', coords='time'))
for cell_method_str in cell_method_strings:
with mock.patch('warnings.warn') as warn:
res = _parse_cell_methods('test_var', cell_method_str)
res = parse_cell_methods('test_var', cell_method_str)
self.assertIn("NetCDF variable 'test_var' contains unknown "
"cell method 'min'",
warn.call_args[0][0])
Expand Down