def file_fuck():
# now = datetime.now().date()
# future = datetime.strptime('01122015', "%d%m%Y").date()
# dt = future-now
# dt = dt.days
#
# if dt <= 100:
# easygui_copath.msgbox('This software license has expired. Please download new program excecutalble from ', 'Title Goes Here')
#
#Input GUI - set initial vars
openfile, out_dir, choice_site, choice_spec, encryption = input_gui()
# clean headers
outtexttemp = cleaner(openfile)
# get chunks
caselist = mapper(outtexttemp, choice_site, choice_spec)
if len(caselist) == 0:
os.rmdir(out_dir)
quit()
else:
print '\nMAKING OUTPUT DIRECTORY: ' + out_dir
open_diff_os.openFolder(out_dir)
# reduce chunks
fin_data, json_mrn, json_cases = reducer(caselist, choice_site)
arr = [["JSON_CASES", json_cases], ["JSON_MRN", json_mrn], ["TABDELIM_CASES_OUT", fin_data], ["TEMP_CLEAN", outtexttemp]]
if encryption == 1:
crypt_dir = out_dir + "\\CRYPT"
os.mkdir(crypt_dir)
crypt_codes = ""
for e in arr:
fil = str(e[0]) + ".txt"
filename = os.path.join(out_dir, fil)
print 'filename: ' + filename
os.open(filename, os.O_RDWR | os.O_CREAT)
with open(filename, 'wb') as out:
out.write(str(e[1]))
if encryption == 1:
pubkey, privkey = rsa.newkeys(128, poolsize=1)
print str(e[0]) + " KEYS: " + str(pubkey), str(privkey)
crypt_codes = str(crypt_codes) + str(e[0]) + " KEYS: " + str(pubkey), str(privkey) + "\n"
filecrypt = crypt_dir + "/CRYPTO_" + e[0] + ".txt"
os.open(filecrypt, os.O_RDWR | os.O_CREAT)
with open(filename, 'rb') as infile, open(filecrypt, 'wb') as outfile:
rsa.bigfile.encrypt_bigfile(infile, outfile, pubkey)
if encryption == 1:
filecrypts = crypt_dir + "/CRYPT_KEYS.txt"
os.open(filecrypts, os.O_RDWR | os.O_CREAT)
with open(filecrypts, 'wb') as out:
out.write(str(crypt_codes))
def file_fuck(params):
# now = datetime.now().date()
# future = datetime.strptime('01122015', "%d%m%Y").date()
# dt = future-now
# dt = dt.days
#
# if dt <= 100:
# easygui_copath.msgbox('This software license has expired. Please download new program excecutalble from ', 'Title Goes Here')
#
#Input GUI - set initial vars
now = "".join([str(datetime.now())[0:4],str(datetime.now())[5:7],
str(datetime.now())[8:10],str(datetime.now())[11:13],
str(datetime.now())[14:16],str(datetime.now())[17:19],
str(datetime.now())[20:len(str(datetime.now()))-1]])
openfile = params['openfile']
out_dir = '_'.join([params['out_dir'],now])
choice_site = params['choice_site']
choice_spec = params['choice_spec']
# clean headers
outtexttemp = cleaner(openfile)
os.mkdir(out_dir)
# get chunks
caselist, case_counts = mapper(outtexttemp, choice_site, choice_spec)
if len(caselist) == 0:
os.rmdir(out_dir)
parsed_cases_counts = {'specimens':str(0), 'patients': str(0)}
excel_truncation = str(0)
# quit()
else:
print '\nMAKING OUTPUT DIRECTORY: ' + out_dir
open_diff_os.openFolder(out_dir)
# reduce chunks
fin_data, json_mrn, json_cases, parsed_cases_counts, excel_truncation = reducer(caselist, choice_site)
arr = [["JSON_CASES", json_cases], ["JSON_MRN", json_mrn], ["TABDELIM_CASES_OUT", fin_data], ["TEMP_CLEAN", outtexttemp]]
for e in arr:
fil = str(e[0]) + ".txt"
filename = os.path.join(out_dir, fil)
print 'filename: ' + filename
os.open(filename, os.O_RDWR | os.O_CREAT)
with open(filename, 'wb') as out:
out.write(str(e[1]))
return case_counts, parsed_cases_counts, excel_truncation
def copath_parse(params):
# Input GUI - set initial vars
now = ''.join([
str(datetime.now())[0:4],
str(datetime.now())[5:7],
str(datetime.now())[8:10],
str(datetime.now())[11:13],
str(datetime.now())[14:16],
str(datetime.now())[17:19],
str(datetime.now())[20:len(str(datetime.now())) - 1]
])
openfile = params['openfile']
out_dir = '_'.join([params['out_dir'], now])
choice_site = params['choice_site']
choice_spec = params['choice_spec']
# clean headers
outtexttemp = cleaner(openfile)
os.mkdir(out_dir)
# get chunks
caselist, case_counts = mapper(outtexttemp, choice_site, choice_spec)
if len(caselist) == 0:
os.rmdir(out_dir)
parsed_cases_counts = {'specimens': str(0), 'patients': str(0)}
excel_truncation = str(0)
else:
print('\nMAKING OUTPUT DIRECTORY: ' + out_dir)
open_diff_os.openFolder(out_dir)
# reduce chunks
fin_data, json_mrn, json_cases, parsed_cases_counts, excel_truncation = reducer(
caselist, choice_site)
arr = [['JSON_CASES', json_cases], ['JSON_MRN', json_mrn],
['TABDELIM_CASES_OUT', fin_data], ['TEMP_CLEAN', outtexttemp]]
for e in arr:
fil = str(e[0]) + '.txt'
filename = os.path.join(out_dir, fil)
print('filename: ' + filename)
os.open(filename, os.O_RDWR | os.O_CREAT)
with open(filename, 'w') as out:
out.write(str(e[1]))
return case_counts, parsed_cases_counts, excel_truncation
def meditech_parse(params):
openfile = params['openfile']
out_dir = params['out_dir']
choice_site = params['choice_site']
choice_spec = params['choice_spec']
outtext_temp = os.path.join(out_dir, 'CLEANEDTEMP')
os.mkdir(outtext_temp)
outtext = os.path.join(out_dir, 'CLEANED')
os.mkdir(outtext)
# clean headers
outtexttemp = cleaner(openfile)
# get chunks
caselist, case_counts = mapper(outtexttemp, choice_spec)
print(caselist)
print(case_counts)
if len(caselist) == 0:
shutil.rmtree(out_dir)
parsed_cases_counts = {'specimens': str(0), 'patients': str(0)}
excel_truncation = str(0)
else:
print('\nMAKING OUTPUT DIRECTORY: ' + out_dir)
open_diff_os.openFolder(out_dir)
# reduce chunks
fin_data, json_mrn, json_cases, parsed_cases_counts, excel_truncation = reducer(
caselist, choice_site)
arr = [["JSON_CASES", json_cases], ["JSON_MRN", json_mrn],
["TABDELIM_CASES_OUT", fin_data], ["TEMP_CLEAN", outtexttemp]]
for e in arr:
fil = str(e[0]) + ".txt"
filename = os.path.join(out_dir, fil)
print('filename: ' + filename)
os.open(filename, os.O_RDWR | os.O_CREAT)
with open(filename, 'w') as out:
out.write(str(e[1]))
return case_counts, parsed_cases_counts, excel_truncation
def cyto_tissue_extract(params):
now = "".join([str(datetime.now())[0:4],str(datetime.now())[5:7],
str(datetime.now())[8:10],str(datetime.now())[11:13],
str(datetime.now())[14:16],str(datetime.now())[17:19],
str(datetime.now())[20:len(str(datetime.now()))-1]])
openfile = params['openfile']
out_dir = '_'.join([params['out_dir'],now])
choice_site = params['choice_site']
with open(openfile, "r") as txt_body:
txt_body = txt_body.read()
os.mkdir(out_dir)
print txt_body[:1000]
if choice_site == 'UM':
allcases = re.findall(r'([A-Z]+(?:-\w+)*,\s[A-Z\s]+)\nSpecimen\sNumber\sAccession\sDate\sTarget\sor\sRelated\sFinal\sDiagnosis\n'
'DOB:\s\d+\/\d+\/\d{4}\sMRN:\s\w+\n([A-Z]{1,2}\d{2}-\d+\s\d+\/\d+\/\d{4}\s\d+:\d{2}\s'
'(Target|Related).+?\n)(?=[A-Z]+(?:-\w+)*,\s[A-Z\s]+\nSpecimen\sNumber\sAccession\sDate\sTarget\sor\s'
'Related\sFinal\sDiagnosis\nDOB:\s\d+\/\d+\/\d{4}\sMRN:\s\w+\n)', txt_body, re.S)
elif choice_site == 'JHS':
allcases = re.findall(r'([A-Z]+(?:-\w+)*,[A-Z\s]+)\nSpecimen\sNumber\sAccession\sDate\sTarget\sor\sRelated\sFinal\sDiagnosis\n([A-Z]{1,2}\d{2}-\d+\s'
'\d+\/\d+\/\d{4}\s\d+:\d{2}\s(Target|Related).+?\n)(?=[A-Z]+(?:-\w+)*,[A-Z\s]+\nSpecimen\sNumber\sAccession\sDate\sTarget\sor\s'
'Related\sFinal\sDiagnosis\n)', txt_body, re.S)
#print allcases
#exit
case_dict = {}
for case in allcases:
all_subcases = re.findall(r'([A-Z]{1,2}\d{2}-\d+)\s(\d+\/\d+\/\d{4})\s\d+:\d{2}\s(Target|Related)(.*?)\n'
'(?=$|[A-Z]{1,2}\d{2}-\d+\s\d+\/\d+\/\d{4}\s\d+:\d{2}\s(?:Target|Related).*\n)', case[1], re.S)
all_subcases = [{'accession_number':x[0], 'accession_date':x[1], 'case_type':x[2], 'diagnosis':encode_decode(x[3])} for x in all_subcases]
if case[0] in case_dict:
for c in all_subcases:
case_dict[case[0]].append(c)
else:
case_dict[case[0]] = all_subcases
case_dict = cleaner(case_dict, choice_site)
with open(os.path.join(out_dir,'out_multiple_row.csv'), 'wb') as out_file:
fileWriter = csv.writer(out_file)
row = ['NAME', 'ACCESSION_DATE', 'TYPE', 'ACCESSION_NUMBER', 'DIAGNOSIS', 'EVENT_FILTER_1','EVENT_FILTER_2']
fileWriter.writerow(row)
count = 0
for e in case_dict:
for c in case_dict[e]:
row = [e]+[c[x].strip() for x in c] + [''.join(["=IF(ISERROR(SEARCH(F$1,$E", str(count+2), ",1)),0,1)"]), ''.join(["=IF(ISERROR(SEARCH(G$1,$E", str(count+2), ",1)),0,1)"])]
fileWriter.writerow(row)
count += 1
with open(os.path.join(out_dir,'out_single_row.csv'), 'wb') as out_file:
fileWriter = csv.writer(out_file)
for e in case_dict:
row_blob = [e]
for c in case_dict[e]:
row_blob = row_blob + [c[x].strip() for x in c]
fileWriter.writerow(row_blob)
#print case_dict
with open(os.path.join(out_dir,'out_data_elastic.json'), 'wb') as out_file:
json_str = json.dumps(case_dict)
out_file.write(json_str)
open_diff_os.openFolder(out_dir)