| 1 |
#!/usr/bin/python |
|---|
| 2 |
"""Classes to handle sodar data samples |
|---|
| 3 |
|
|---|
| 4 |
Sodar data samples are collected into daily files. Each sample consists of a |
|---|
| 5 |
header followed by an observation for each height. |
|---|
| 6 |
""" |
|---|
| 7 |
|
|---|
| 8 |
import re |
|---|
| 9 |
|
|---|
| 10 |
class Data(object): |
|---|
| 11 |
"""Daily sodar file data (a collection of samples)""" |
|---|
| 12 |
def __init__(self,data): |
|---|
| 13 |
object.__init__(self) |
|---|
| 14 |
# samples in file are terminated by $ |
|---|
| 15 |
self.samples = [Sample(sample) for sample in [sample.strip() for sample in data.split('$')] if sample] |
|---|
| 16 |
|
|---|
| 17 |
class Sample(object): |
|---|
| 18 |
"""A single sample from daily sodar file data (a header and a body)""" |
|---|
| 19 |
def __init__(self,sample): |
|---|
| 20 |
object.__init__(self) |
|---|
| 21 |
# first three groups of lines are the header; rest is body |
|---|
| 22 |
samplePattern = re.compile(r'''(?P<header>.*?\n\n.*?\n\n.*?\n\n) |
|---|
| 23 |
(?P<body>.*$) |
|---|
| 24 |
''',re.DOTALL | re.VERBOSE) |
|---|
| 25 |
self.__dict__.update(samplePattern.match(sample.strip()).groupdict()) |
|---|
| 26 |
# fix for missing keys |
|---|
| 27 |
self.header = Header(self.header) |
|---|
| 28 |
|
|---|
| 29 |
class Header(object): |
|---|
| 30 |
"""A sodar data sample header (a collection of sample-wide parameters)""" |
|---|
| 31 |
def __init__(self,header): |
|---|
| 32 |
object.__init__(self) |
|---|
| 33 |
headerLines = [headerLine.strip() for headerLine in header.split('\n') if headerLine] |
|---|
| 34 |
# every other line contains parameter names; every other line contains parameter values |
|---|
| 35 |
parametersPairs = [(headerLine,headerLines[headerLines.index(headerLine)+1]) for headerLine in headerLines[::2]] |
|---|
| 36 |
for parameterNames,parameterValues in parametersPairs: |
|---|
| 37 |
# parameter names must be valid Python identifiers for named groups matching |
|---|
| 38 |
parameterNames = [parameterName.strip('#') for parameterName in parameterNames.split()] |
|---|
| 39 |
parameterPattern = re.compile(r'(?P<'+'>\S+)\s+(?P<'.join(parameterNames)+'>.*$)') |
|---|
| 40 |
self.__dict__.update(parameterPattern.match(parameterValues).groupdict()) |
|---|
| 41 |
|
|---|
| 42 |
def __main(): |
|---|
| 43 |
"""Process as script from command line""" |
|---|
| 44 |
import urllib2 |
|---|
| 45 |
try: |
|---|
| 46 |
data = urllib2.urlopen('http://nemo.isis.unc.edu/data/nccoos/level0/dukeforest/sodar/store/2007-06/20070601.dat') |
|---|
| 47 |
data = data.read() |
|---|
| 48 |
except: |
|---|
| 49 |
print "Failure to read test data" |
|---|
| 50 |
data = Data(data) |
|---|
| 51 |
print ' --- Sample ---\n'.join(data.samples) |
|---|
| 52 |
|
|---|
| 53 |
if __name__ == "__main__": |
|---|
| 54 |
__main() |
|---|
