Moved icartt to own package.

README.md

+# ICARTT reader

icartt/__init__.py

+from icartt import *
\ No newline at end of file

icartt/icartt.py

+# based on http://www-air.larc.nasa.gov/missions/etc/ESDS-RFC-019-v1.1_0.pdf
+
+# sanitize function
+def sane_read_line(f, split_char=',', do_split=True):
+    dmp = f.readline().replace('\n', '').replace('\r','')
+    if do_split:
+        dmp = [word.strip(' ') for word in dmp.split(split_char)]
+    return dmp
+
+def read_header(ict_file):
+
+    f = open( ict_file, 'r' )
+
+    out= { 'filename' : ict_file }
+
+    # line 1 - Number of lines in header, file format index (most files use
+    # 1001) - comma delimited.
+    dmp = sane_read_line(f)
+    out['nheader'] = int(dmp[0])
+    out['fformat'] = int(dmp[1])
+
+    # line 2 - PI last name, first name/initial.
+    dmp = sane_read_line(f, do_split=False)
+    out['PI'] = dmp
+
+    # line 3 - Organization/affiliation of PI.
+    dmp = sane_read_line(f, do_split=False)
+    out['organization'] = dmp
+
+    # line 4 - Data source description (e.g., instrument name, platform name,
+    # model name, etc.).
+    dmp = sane_read_line(f, do_split=False)
+    out['instrument'] = dmp
+
+    # line 5 - Mission name (usually the mission acronym).
+    dmp = sane_read_line(f, do_split=False)
+    out['mission'] = dmp
+
+    # line 6 - File volume number, number of file volumes (these integer values
+    # are used when the data require more than one file per day; for data that
+    # require only one file these values are set to 1, 1) - comma delimited.
+    dmp = sane_read_line(f)
+    out['vol']  = int(dmp[0])
+    out['nvol'] = int(dmp[1])
+
+    # line 7 - UTC date when data begin, UTC date of data reduction or revision
+    # - comma delimited (yyyy, mm, dd, yyyy, mm, dd).
+    dmp = sane_read_line(f)
+    out['date']         = [ int(x) for x in dmp[0:3] ]
+    out['rev_date']     = [ int(x) for x in dmp[3:6] ]
+
+    # line 8 - Data Interval (This value describes the time spacing (in seconds)
+    # between consecutive data records. It is the (constant) interval between
+    # values of the independent variable. For 1 Hz data the data interval value
+    # is 1 and for 10 Hz data the value is 0.1. All intervals longer than 1
+    # second must be reported as Start and Stop times, and the Data Interval
+    # value is set to 0. The Mid-point time is required when it is not at the
+    # average of Start and Stop times. For additional information see Section
+    # 2.5 below.).
+    dmp = sane_read_line(f)
+    out['dt'] = int(dmp[0])
+
+    # line 9 - Description or name of independent variable (This is the name
+    # chosen for the start time. It always refers to the number of seconds UTC
+    # from the start of the day on which measurements began. It should be noted
+    # here that the independent variable should monotonically increase even when
+    # crossing over to a second day.
+    dmp = sane_read_line(f)
+    out['ivar'] = dmp[0]
+    out['ivar_units'] = dmp[1]
+
+    # line 10 - Number of variables (Integer value showing the number of
+    # dependent variables: the total number of columns of data is this value
+    # plus one.).
+    dmp = sane_read_line(f)
+    out['ndvar'] = int(dmp[0])
+
+    # line 11- Scale factors (1 for most cases, except where grossly
+    # inconvenient) - comma delimited.
+    dmp = sane_read_line(f)
+    out['dvscale'] = [ float(x) for x in dmp ]
+
+    # line 12 - Missing data indicators (This is -9999 (or -99999, etc.) for
+    # any missing data condition, except for the main time (independent)
+    # variable which is never missing) - comma delimited.
+    dmp = sane_read_line(f)
+    out['dvmiss'] = dmp
+
+    # line 13 - Variable names and units (Short variable name and units are
+    # required, and optional long descriptive name, in that order, and separated
+    # by commas. If the variable is unitless, enter the keyword "none" for its
+    # units. Each short variable name and units (and optional long name) are
+    # entered on one line. The short variable name must correspond exactly to
+    # the name used for that variable as a column header, i.e., the last header
+    # line prior to start of data.).
+    dmp = sane_read_line(f)
+    out['dvar']          = [ dmp[0] ]
+    out['dvar_units']    = [ dmp[1] ]
+
+    for i in range(1, out['ndvar']):
+        dmp = sane_read_line(f)
+        out['dvar']          += [ dmp[0] ]
+        out['dvar_units']    += [ dmp[1] ]
+
+    # add-on: create list including the independent variable
+    out['nvar']         = 1                     + out['ndvar']
+    out['var']          = [ out['ivar'] ]       + out['dvar']
+    out['var_units']    = [ out['ivar_units'] ] + out['dvar_units']
+    out['vscale']       = [ 1.0 ]               + out['dvscale']
+    out['vmiss']        = [ 'DONOTREPLACE' ]    + out['dvmiss']
+
+    # line 14 + nvar - Number of SPECIAL comment lines (Integer value
+    # indicating the number of lines of special comments, NOT including this
+    # line.).
+    dmp = sane_read_line(f)
+    out['nscom'] = int(dmp[0])
+
+    # line 15 + nvar - Special comments (Notes of problems or special
+    # circumstances unique to this file. An example would be comments/problems
+    # associated with a particular flight.).
+    if out['nscom'] > 0:
+        dmp = sane_read_line(f, do_split=False)
+        out['scom']          = [ dmp ]
+        for i in range(1, out['nscom']):
+            dmp = sane_read_line(f, do_split=False)
+            out['scom']          += [ dmp ]
+
+    # line 16 + nvar + nscom - Number of Normal comments (i.e., number of
+    # additional lines of SUPPORTING information: Integer value indicating the
+    # number of lines of additional information, NOT including this line.).
+    dmp = sane_read_line(f)
+    out['ncom'] = int(dmp[0])
+
+    # line 17 + nvar + nscom - Normal comments (SUPPORTING information: This is
+    # the place for investigators to more completely describe the data and
+    # measurement parameters. The supporting information structure is described
+    # below as a list of key word: value pairs. Specifically include here
+    # information on the platform used, the geo-location of data, measurement
+    # technique, and data revision comments. Note the non-optional information
+    # regarding uncertainty, the upper limit of detection (ULOD) and the lower
+    # limit of detection (LLOD) for each measured variable. The ULOD and LLOD
+    # are the values, in the same units as the measurements that correspond to
+    # the flags -7777's and -8888's within the data, respectively. The last line
+    # of this section should contain all the "short" variable names on one line.
+    # The key words in this section are written in BOLD below and must appear in
+    # this section of the header along with the relevant data listed after the
+    # colon. For key words where information is not needed or applicable, simply
+    # enter N/A.).
+    if out['ncom'] > 0:
+        dmp = sane_read_line(f, do_split=False)
+        out['com']          = [ dmp ]
+        for i in range(1, out['ncom']):
+            dmp = sane_read_line(f, do_split=False)
+            out['com']          += [ dmp ]
+
+    f.close()
+
+    return(out)
+
+def read(ict_file):
+
+    out = read_header(ict_file)
+
+    f = open( ict_file, 'r' )
+
+    nul = [f.readline() for i in xrange(out['nheader'])]
+
+    def nan_miss_float(raw, vmiss):
+        return [ float(x.replace(vmiss[i], 'NaN')) for i, x in enumerate(raw) ]
+
+    out['data'] = [ nan_miss_float(line.split(','), out['vmiss']) for line in f ]
+
+    f.close()
+
+    return(out)
+
+
+
+
+
+
+

setup.py

+from setuptools import setup
+
+setup(name='icartt',
+      version='0.1',
+      description='ICARTT reader',
+      url='http://christoph.knote.net',
+      author='Christoph Knote',
+      author_email='christoph.knote@lmu.de',
+      license='MIT',
+      packages=['icartt'],
+      zip_safe=False)