procdigs

#!/usr/bin/env python
from os import path
import sys
# import argparse
import glob
import re
import wave
import time
import csv
import sox
import subprocess
import hashlib

def main():

	paths = ['./']
	if len(sys.argv) > 1:
		paths = sys.argv[1:]

	fieldnames = [
		'path',
		'id',
		'side',
		'dig',
		'take',
		'notes',	
		'channels',
		'sample_rate',
		'bitrate',
		'num_samples',
		'encoding',
		'precision',
		'duration',		
		'size',
		'md5',
		'updated at (UTC)',

	]

	csv_writer = csv.DictWriter(sys.stdout, fieldnames = fieldnames, quoting=csv.QUOTE_MINIMAL)
	csv_writer.writeheader()
	file_pattern = re.compile('^(?:.+/)(.+?)-([ab])-(d\d+)-(t\d+)(?:-(.+))?.wav$')
	for this_path in paths:
		file_paths = glob.glob(this_path + '/*')
		for file_path in file_paths:			
			m = file_pattern.match(file_path)
			if m:				
				file_entry = get_file_information(file_path, m)
				csv_writer.writerow(file_entry)

def get_soxi_line(reg, input):
	return re.sub(reg, '', input) 

def get_file_intrinsic_information(file_path):
	info_line = re.compile('(.*?):(.+)')
	output = subprocess.check_output(['soxi', file_path]).split("\n")
	replace_header = re.compile('.*?: ')

	result = {
		'channels': get_soxi_line(replace_header, output[2]), #channels
		'sample_rate': get_soxi_line(replace_header, output[3]), #sample rate
		'precision': get_soxi_line(replace_header, output[4]), #precision
		'duration': re.sub('\s=.+$', '', get_soxi_line(replace_header, output[5])), #duration
		'bitrate': get_soxi_line(replace_header, output[7]), #bit rate
		'encoding': get_soxi_line(replace_header, output[8]) #encoding
	}
	return result


def get_file_extrinsic_information(file_path, m):
	file_entry = {
		'path': path.abspath(file_path),
		'id': m.group(1),
		'side': m.group(2),
		'dig': m.group(3),
		'take': m.group(4),
		'notes': m.group(5),	
		'updated at (UTC)': time.strftime("%d %b %Y %H:%M:%S", time.gmtime(path.getmtime(file_path))),
		'size': get_size(path.getsize(file_path)),
		'md5': md5(file_path)
	}

	return file_entry


# from https://stackoverflow.com/questions/3431825/generating-an-md5-checksum-of-a-file
def md5(fname):
	hash_md5 = hashlib.md5()
	with open(fname, "rb") as f:
		for chunk in iter(lambda: f.read(4096), b""):
			hash_md5.update(chunk)
	return hash_md5.hexdigest()

def get_file_information(file_path, m):
	# test = sox.file_info.info(file_path)
	
	file_file_extrinsic_information = get_file_extrinsic_information(file_path, m)
	file_intrinsic_information = get_file_intrinsic_information(file_path)

	result = dict(file_intrinsic_information, **file_file_extrinsic_information)

	return result

# from https://stackoverflow.com/questions/1094841/reusable-library-to-get-human-readable-version-of-file-size
def get_size(num, suffix='B'):
	for unit in ['','K','M','G','T','P','E','Z']:
		if abs(num) < 1024.0:
			return "%3.2f%s%s" % (num, unit, suffix)
		num /= 1024.0
	return "%.1f%s%s" % (num, 'Yi', suffix)

if __name__ == "__main__":
	main()