diff --git a/pyglance/glance/compare.py b/pyglance/glance/compare.py
index 533e2d0e2bfa60f2077e38e6f534d30277e2f1dc..59a9d3ffceca82eb1cf5e543a1c1d7da0dc4debd 100644
--- a/pyglance/glance/compare.py
+++ b/pyglance/glance/compare.py
@@ -11,7 +11,7 @@ Copyright (c) 2009 University of Wisconsin SSEC. All rights reserved.
#from pprint import pprint, pformat
-import os, sys, logging, re, datetime
+import os, sys, logging, re, datetime, glob
from numpy import *
import numpy
from urllib.parse import quote
@@ -48,6 +48,56 @@ from glance.gui_constants import A_CONST, B_CONST
LOG = logging.getLogger(__name__)
+def _get_possible_files_from_dir (dir_path) :
+ """given a path to a directory, return all the paths to files we think we can open in that directory
+
+ """
+
+ # find all the appropriate files in a_path
+ possible_extensions = io.get_acceptable_file_extensions()
+ found_files = set()
+ for filepath in glob.iglob(os.path.join(dir_path, "**"), recursive=True, ):
+ ext_txt = filepath.split(".")[-1]
+
+ if ext_txt in possible_extensions:
+ found_files.add(filepath)
+
+ return found_files
+
+def _match_files_from_dirs (a_path, b_path, ) :
+ """given two paths to directories, try to match up the files we can analyze in them
+
+ """
+
+ # find all the files in the a path we might be able to open
+ found_a_files = _get_possible_files_from_dir(a_path)
+
+ LOG.debug("Found " + str(len(found_a_files)) + " possible files in the A directory: ")
+ for filepath in found_a_files :
+ LOG.debug(filepath)
+
+ # TODO, when we get to python 3.9, we can use str.removeprefix but until then
+ def _remove_prefix(text, prefix):
+ if text.startswith(prefix):
+ return text[len(prefix):]
+ return None
+
+ # test to see if there is a matching file in the b_path for each a_path file
+ file_pairs = set()
+ for a_filepath in found_a_files :
+ inner_path = _remove_prefix(a_filepath, a_path)
+ b_filepath = os.path.join(b_path, inner_path)
+ if os.path.exists(b_filepath) :
+ file_pairs.add((a_filepath, b_filepath,))
+
+ # print out info on each resulting pair
+ #print ("Found " + str(len(file_pairs)) + " file pair(s): ")
+ #for a, b in file_pairs :
+ # print ("A: " + a)
+ # print ("B: " + b)
+
+ return file_pairs
+
# TODO, I'd like to move this into a different file at some point
def _get_name_info_for_variable(original_display_name, variable_run_info) :
"""
@@ -1520,7 +1570,117 @@ def main():
if len(args) >= 2:
temp_controller.newFileSelected(B_CONST, args[1])
temp_controller.launch_gui()
-
+
+ def report (*args) :
+ """generate reports of various types depending on your input
+
+ Depending on how many input file paths you give this command it will either generate comparison or
+ inspection reports. If you give it a directory instead of a file path it will search the underlying file
+ structure to find any appropriately typed files and attempt to create reports for each of them in the
+ output directory. If you include two directory paths it will attempt to automatically match files in the
+ same part of the sub-hierarchy with the same names and create comparison reports for them.
+
+ If latitude and longitude data are present in the file(s) and specified in the call options, the
+ plots will be drawn on a map. The longitude and latitude variable names may be specified with
+ --longitude and --latitude command line options. If no longitude or latitude names are specified Glance
+ will attempt to use pixel_longitude and pixel_latitude.
+
+ If you would rather plot the data without trying to place it on a map, use the --nolonlat option.
+
+ The created reports and images will be saved at the provided output path in subdirectories named for
+ each variable analyzed. If no output path is provided, output will be saved in the current directory.
+ Created images will be embedded in the report or visible as separate .png files.
+
+ Note: if you provided one or two directory paths and those paths included more than one set of files
+ that Glance is able to generate reports for, those reports will be placed in the output path in
+ separate temporarily directories. These directories are only labeled numerically at the current
+ time. In future we hope to have a summary report available for the run, but this does not currently
+ exist.
+
+ If you would prefer to generate reports without images, use the --reportonly option. This option will
+ generate the html report but omit the images. This may be significantly faster, depending on your system,
+ but the differences between the files may be more difficult to interpret.
+
+ Examples:
+
+ glance inspect_report A.hdf variable_name_1:: variable_name_2 variable_name_3::missing3 variable_name_4::missing4
+ glance --outputpath=/path/where/output/will/be/placed/ inspect_report C.nc
+ glance inspect_report --longitude=lon_variable_name --latitude=lat_variable_name D.h5 variable_name
+ glance inspect_report --reportonly A.hdf
+ """
+
+ # examine the args and see how many valid file paths we have
+ files = [ ]
+ variables = [ ]
+ for argument_val in args :
+ if os.path.exists(argument_val) :
+ LOG.debug("argument value is a file path: " + argument_val)
+ files.append(clean_path(argument_val))
+ else :
+ LOG.debug("argument value is not an existing file path, it will be treated as a variable name: " + argument_val)
+ variables.append(argument_val)
+
+ # if we have no file paths, just stop now
+ if len(files) < 1 :
+ LOG.warn("Expected at least one file path to input data. " +
+ "Unable to generate a report without a file path.")
+ return 1
+
+ # organize our command line options
+ tempOptions = config_organizer.convert_options_to_dict(options)
+
+ # if we have one file path, do either one or many inspect reports
+ if len(files) <= 1 :
+ a_file_path = files[0]
+ # check to see if the file is a dir
+ if os.path.isdir(a_file_path) :
+ a_files_list = _get_possible_files_from_dir(a_file_path)
+ temp_offset = 0
+ to_return = 0
+ # run each of the reports, putting them in inner temp dirs
+ for file_path in a_files_list :
+ ops_copy = tempOptions.copy()
+ if len(a_files_list) > 1 :
+ ops_copy[OPTIONS_OUTPUT_PATH_KEY] = os.path.join(ops_copy[OPTIONS_OUTPUT_PATH_KEY], "tmp" + str(temp_offset))
+ temp_offset += 1
+ to_return += inspect_library_call(file_path, variables, ops_copy, )
+ return to_return
+ else : # in this case we just have a regular file, so run one inspect report
+ return inspect_library_call(a_file_path, variables, tempOptions, )
+
+ # this doesn't seem super likely, but just in case, let's at least give a warning so the user has some idea why we ignored some paths
+ if len(files) > 2:
+ LOG.warn("More than two file paths were found in your command line input. "
+ "Only the first two will be used. The rest will be discarded.")
+
+ # if we have two file paths, do either one or many comparison reports
+ if len(files) >= 2 :
+ a_file_path = files[0]
+ b_file_path = files[1]
+ # check to see if the paths are dirs
+ if os.path.isdir(a_file_path) and os.path.isdir(b_file_path) :
+ file_pairs = _match_files_from_dirs(a_file_path, b_file_path)
+ temp_offset = 0
+ to_return = 0
+ # run each of the reports, putting them in inner temp dirs
+ for single_a_file, single_b_file in file_pairs :
+ ops_copy = tempOptions.copy()
+ if len(file_pairs) > 1 :
+ ops_copy[OPTIONS_OUTPUT_PATH_KEY] = os.path.join(ops_copy[OPTIONS_OUTPUT_PATH_KEY], "tmp" + str(temp_offset))
+ temp_offset += 1
+ to_return += reportGen_library_call(single_a_file, single_b_file, variables, ops_copy, )
+ return to_return
+ # if both the paths are regular files, just run one report
+ elif os.path.isfile(a_file_path) and os.path.isfile(b_file_path) :
+ return reportGen_library_call(a_file_path, b_file_path, variables, tempOptions, )
+ else :
+ LOG.error("You have provided one directory path and one file path. "
+ "Please input two directories or two files, not a mixture.")
+ return 1
+
+ # if we got to here, something has gone terribly wrong
+ return 1
+
def help(command=None):
"""print help for a specific command or list of commands
e.g. help stats
diff --git a/pyglance/glance/io.py b/pyglance/glance/io.py
index cbdbeed6891a90196fa107b6b111df7961ef0b21..eed4437ca727495a6f51ea264bfb12275b9caa9d 100644
--- a/pyglance/glance/io.py
+++ b/pyglance/glance/io.py
@@ -13,9 +13,12 @@ from functools import reduce
LOG = logging.getLogger(__name__)
+Loadable_Types = set()
+
try:
import pyhdf
from pyhdf.SD import SD,SDC, SDS, HDF4Error
+ Loadable_Types.add("hdf")
except:
LOG.info('no pyhdf module available for HDF4')
pyhdf = None
@@ -25,6 +28,7 @@ except:
try:
import h5py
from h5py import h5d
+ Loadable_Types.add("h5")
except ImportError:
LOG.info('no h5py module available for reading HDF5')
h5py = None
@@ -32,6 +36,7 @@ except ImportError:
# the newer netCDF library that replaced pycdf
try:
import netCDF4
+ Loadable_Types.update(["nc", "nc4", "cdf", ])
except:
LOG.info("unable to import netcdf4 library")
netCDF4 = None
@@ -39,6 +44,7 @@ except:
try:
import dmv as dmvlib
LOG.info('loaded dmv module for AERI data file access')
+ Loadable_Types.update(["cxs", "rnc", "cxv", "csv", "spc", "sum", "uvs", "aeri", ])
except ImportError:
LOG.info('no AERI dmv data file format module')
dmvlib = None
@@ -46,6 +52,7 @@ except ImportError:
try:
import adl_blob
LOG.info('adl_blob module found for JPSS ADL data file access')
+ # TODO, what is the loadable file extension?
except ImportError:
LOG.info('no adl_blob format handler available')
adl_blob = None
@@ -53,6 +60,7 @@ except ImportError:
try :
from osgeo import gdal
LOG.info('loading osgeo module for GeoTIFF data file access')
+ Loadable_Types.update(["tiff", "tif", "tifa", ])
except :
LOG.info('no osgeo available for reading GeoTIFF data files')
gdal = None
@@ -1429,6 +1437,12 @@ def open(pathname, allowWrite=False):
cls = globals()[suffix]
return cls(pathname, allowWrite=allowWrite)
+def get_acceptable_file_extensions ( ) :
+ """
+ Get a list of file extensions this module thinks it can open with the currently installed libraries
+ """
+ return Loadable_Types.copy()
+
if __name__=='__main__':
import doctest
doctest.testmod()