-
Notifications
You must be signed in to change notification settings - Fork 1
/
file_handling.py
154 lines (135 loc) · 6.56 KB
/
file_handling.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
import pandas as pd
from tkinter.filedialog import askopenfilename, asksaveasfilename
import os
def open_unknown_csv(file_in, delimination):
encode_index = 0
encoders = ['utf_8', 'latin1', 'utf_16',
'ascii', 'big5', 'big5hkscs', 'cp037', 'cp424',
'cp437', 'cp500', 'cp720', 'cp737', 'cp775',
'cp850', 'cp852', 'cp855', 'cp856', 'cp857',
'cp858', 'cp860', 'cp861', 'cp862', 'cp863',
'cp864', 'cp865', 'cp866', 'cp869', 'cp874',
'cp875', 'cp932', 'cp949', 'cp950', 'cp1006',
'cp1026', 'cp1140', 'cp1250', 'cp1251', 'cp1252',
'cp1253', 'cp1254', 'cp1255', 'cp1256', 'cp1257',
'cp1258', 'euc_jp', 'euc_jis_2004', 'euc_jisx0213', 'euc_kr',
'gb2312', 'gbk', 'gb18030', 'hz', 'iso2022_jp',
'iso2022_jp_1', 'iso2022_jp_2', 'iso2022_jp_2004', 'iso2022_jp_3', 'iso2022_jp_ext',
'iso2022_kr', 'latin_1', 'iso8859_2', 'iso8859_3', 'iso8859_4',
'iso8859_5', 'iso8859_6', 'iso8859_7', 'iso8859_8', 'iso8859_9',
'iso8859_10', 'iso8859_11', 'iso8859_13', 'iso8859_14', 'iso8859_15',
'iso8859_16', 'johab', 'koi8_r', 'koi8_u', 'mac_cyrillic',
'mac_greek', 'mac_iceland', 'mac_latin2', 'mac_roman', 'mac_turkish',
'ptcp154', 'shift_jis', 'shift_jis_2004', 'shift_jisx0213', 'utf_32',
'utf_32_be', 'utf_32_le', 'utf_16', 'utf_16_be', 'utf_16_le',
'utf_7', 'utf_8', 'utf_8_sig']
data = open_file(file_in, encoders[encode_index], delimination)
encoder = encoders[encode_index]
while type(data) == str:
print("Encoder error: " + encoders[encode_index])
if encode_index < len(encoders) - 1:
encode_index = encode_index + 1
try:
print("Trying encoder: " + encoders[encode_index])
data = open_file(file_in, encoders[encode_index], delimination)
except:
continue
print("")
encoder = encoders[encode_index]
else:
print("Can't find appropriate encoder")
input("Program Terminated. Press Enter to continue...")
exit()
return data
def encoding_selection(statement):
basic_encoders = ['utf_8', 'latin1', 'utf_16', 'See All Encoders']
advanced_encoders = ['ascii', 'big5', 'big5hkscs', 'cp037', 'cp424',
'cp437', 'cp500', 'cp720', 'cp737', 'cp775',
'cp850', 'cp852', 'cp855', 'cp856', 'cp857',
'cp858', 'cp860', 'cp861', 'cp862', 'cp863',
'cp864', 'cp865', 'cp866', 'cp869', 'cp874',
'cp875', 'cp932', 'cp949', 'cp950', 'cp1006',
'cp1026', 'cp1140', 'cp1250', 'cp1251', 'cp1252',
'cp1253', 'cp1254', 'cp1255', 'cp1256', 'cp1257',
'cp1258', 'euc_jp', 'euc_jis_2004', 'euc_jisx0213', 'euc_kr',
'gb2312', 'gbk', 'gb18030', 'hz', 'iso2022_jp',
'iso2022_jp_1', 'iso2022_jp_2', 'iso2022_jp_2004', 'iso2022_jp_3', 'iso2022_jp_ext',
'iso2022_kr', 'latin_1', 'iso8859_2', 'iso8859_3', 'iso8859_4',
'iso8859_5', 'iso8859_6', 'iso8859_7', 'iso8859_8', 'iso8859_9',
'iso8859_10', 'iso8859_11', 'iso8859_13', 'iso8859_14', 'iso8859_15',
'iso8859_16', 'johab', 'koi8_r', 'koi8_u', 'mac_cyrillic',
'mac_greek', 'mac_iceland', 'mac_latin2', 'mac_roman', 'mac_turkish',
'ptcp154', 'shift_jis', 'shift_jis_2004', 'shift_jisx0213', 'utf_32',
'utf_32_be', 'utf_32_le', 'utf_16', 'utf_16_be', 'utf_16_le',
'utf_7', 'utf_8', 'utf_8_sig']
while True:
try:
print()
print(statement)
for j, i in enumerate(basic_encoders):
if j != len(basic_encoders) - 1:
print(str(j) + ": to use " + str(i) + "")
else:
print(str(j) + ": to see all possible encoders.")
encoder = basic_encoders[int(input("Enter Selection: "))]
except ValueError:
print("Input must be integer between 0 and " + str(len(basic_encoders)))
continue
else:
break
if encoder == 'See All Encoders':
while True:
try:
print()
print(statement)
for j, i in enumerate(advanced_encoders):
print(str(j) + ": to use " + str(i) + "")
encoder = advanced_encoders[int(input("Enter Selection: "))]
except ValueError:
print("Input must be integer between 0 and " + str(len(advanced_encoders)))
continue
else:
break
print()
return encoder
def open_file(file_in, encoder, delimination):
try:
data = pd.read_csv(file_in, low_memory=False, encoding=encoder, delimiter=delimination)
print("Opened file using encoder: " + encoder)
except UnicodeDecodeError:
print("Encoder Error for: " + encoder)
return "Encode Error"
return data
def select_file_in():
file_in = askopenfilename(initialdir="../", title="Select file",
filetypes=(("Comma Separated Values", "*.csv"), ("all files", "*.*")))
if not file_in:
input("Program Terminated. Press Enter to continue...")
exit()
return file_in
def select_file_out_kml(file_in):
file_out = asksaveasfilename(initialdir=file_in, title="Select file",
filetypes=(("Keyhole Markup Language", "*.kml"), ("all files", "*.*")))
if not file_out:
input("Program Terminated. Press Enter to continue...")
exit()
# If file doesn't include .kml, add it
if file_out[-4:].lower() != ".kml":
file_out = file_out + ".kml"
else:
# Replace the extension with all lower case
file_out = file_out[:-4] + ".kml"
# Create an empty output file
open(file_out, 'a').close()
return file_out
def delete_file(file_path):
if os.path.exists(file_path):
try:
os.remove(file_path)
return True
except:
print("File could not be deleted. This may be a permission issue or the file is currently open!")
return False
else:
print("The file does not exist, thus could not be deleted!")
return True