[7512] | 1 | ## $Id: fix_import_file.py 7518 2012-01-27 06:54:13Z henrik $ |
---|
| 2 | ## |
---|
[7518] | 3 | ## Copyright (C) 2012 Uli Fouquet & Henrik Bettermann |
---|
[7512] | 4 | ## This program is free software; you can redistribute it and/or modify |
---|
| 5 | ## it under the terms of the GNU General Public License as published by |
---|
| 6 | ## the Free Software Foundation; either version 2 of the License, or |
---|
| 7 | ## (at your option) any later version. |
---|
| 8 | ## |
---|
| 9 | ## This program is distributed in the hope that it will be useful, |
---|
| 10 | ## but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
| 11 | ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
---|
| 12 | ## GNU General Public License for more details. |
---|
| 13 | ## |
---|
| 14 | ## You should have received a copy of the GNU General Public License |
---|
| 15 | ## along with this program; if not, write to the Free Software |
---|
| 16 | ## Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA |
---|
| 17 | ## |
---|
| 18 | """ |
---|
[7518] | 19 | Fix exports from old SRP portal to make them importable by current portal. |
---|
[7512] | 20 | |
---|
| 21 | Usage: |
---|
| 22 | |
---|
| 23 | Change into this directory, set the options below (files are assumed |
---|
| 24 | to be in the same directory) and then run |
---|
| 25 | |
---|
[7518] | 26 | python fix_import_file.py <filename> |
---|
[7512] | 27 | |
---|
| 28 | Errors/warnings will be displayed on the shell, the output will be put |
---|
| 29 | into the specified output file. |
---|
| 30 | """ |
---|
| 31 | |
---|
[7518] | 32 | import sys |
---|
| 33 | |
---|
| 34 | |
---|
| 35 | if len(sys.argv) != 2: |
---|
| 36 | print 'Usage: python fix_import_file.py <filename>' |
---|
| 37 | sys.exit(1) |
---|
| 38 | |
---|
[7512] | 39 | ## |
---|
| 40 | ## CONFIGURATION SECTION |
---|
| 41 | ## |
---|
| 42 | # file with input data |
---|
[7518] | 43 | INPUT_FILE = '%s' % sys.argv[1] |
---|
[7512] | 44 | |
---|
| 45 | # file written with modified output |
---|
[7518] | 46 | OUTPUT_FILE = '%s_edited.csv' % sys.argv[1].split('.')[0] |
---|
[7512] | 47 | |
---|
| 48 | # keys are fieldnames in input file, values are methods of class |
---|
| 49 | # Converter (see below) |
---|
| 50 | OPTIONS = { |
---|
| 51 | 'sex': 'gender', |
---|
| 52 | 'birthday': 'date', |
---|
| 53 | 'request_date': 'datetime', |
---|
[7514] | 54 | 'marit_stat': 'marit_stat', |
---|
| 55 | 'entry_session': 'session', |
---|
| 56 | 'current_session': 'session', |
---|
[7512] | 57 | } |
---|
[7516] | 58 | |
---|
| 59 | # Mapping input file colnames --> output file colnames |
---|
| 60 | COLNAME_MAPPING = { |
---|
[7518] | 61 | 'jamb_reg_no': 'reg_number', |
---|
[7516] | 62 | 'birthday': 'date_of_birth', |
---|
| 63 | } |
---|
[7512] | 64 | ## |
---|
| 65 | ## END OF CONFIG |
---|
| 66 | ## |
---|
| 67 | |
---|
| 68 | import csv |
---|
| 69 | import datetime |
---|
| 70 | import sys |
---|
| 71 | |
---|
[7516] | 72 | def convert_fieldnames(fieldnames): |
---|
| 73 | """Replace input fieldnames by fieldnames of COLNAME_MAPPING. |
---|
| 74 | """ |
---|
| 75 | header = dict([(name, name) for name in fieldnames]) |
---|
| 76 | for in_name, out_name in COLNAME_MAPPING.items(): |
---|
| 77 | if in_name not in header: |
---|
| 78 | continue |
---|
| 79 | header[in_name] = out_name |
---|
[7514] | 80 | return header |
---|
| 81 | |
---|
[7512] | 82 | class Converters(): |
---|
| 83 | """Converters to turn old-style values into new ones. |
---|
| 84 | """ |
---|
| 85 | @classmethod |
---|
[7514] | 86 | def session(self, value): |
---|
| 87 | """ '08' --> '2008' |
---|
| 88 | """ |
---|
| 89 | try: |
---|
| 90 | number = int(value) |
---|
| 91 | except ValueError: |
---|
| 92 | return 9999 |
---|
| 93 | if number < 14: |
---|
| 94 | return number + 2000 |
---|
| 95 | elif number in range(2000,2015): |
---|
| 96 | return number |
---|
| 97 | else: |
---|
| 98 | return 9999 |
---|
| 99 | |
---|
| 100 | @classmethod |
---|
| 101 | def marit_stat(self, value): |
---|
| 102 | """ 'True'/'False' --> 'married'/'unmarried' |
---|
| 103 | """ |
---|
| 104 | if value == 'True': |
---|
| 105 | value = 'married' |
---|
| 106 | elif value == 'False': |
---|
| 107 | value = 'unmarried' |
---|
| 108 | else: |
---|
| 109 | value = '' |
---|
| 110 | return value |
---|
| 111 | |
---|
| 112 | @classmethod |
---|
| 113 | def gender(self, value): |
---|
| 114 | """ 'True'/'False' --> 'female'/'male' |
---|
| 115 | """ |
---|
| 116 | if value == 'True': |
---|
| 117 | value = 'female' |
---|
| 118 | elif value == 'False': |
---|
| 119 | value = 'male' |
---|
| 120 | else: |
---|
| 121 | value = '' |
---|
| 122 | return value |
---|
| 123 | |
---|
| 124 | @classmethod |
---|
[7512] | 125 | def date(self, value): |
---|
| 126 | """ 'yyyy/mm/dd' --> 'yyyy-mm-dd' |
---|
| 127 | """ |
---|
| 128 | if value == "None": |
---|
| 129 | value = "" |
---|
| 130 | elif value == "": |
---|
| 131 | value = "" |
---|
| 132 | else: |
---|
| 133 | value = value.replace('/', '-') |
---|
[7514] | 134 | # We add the hash symbol to avoid automatic date transformation |
---|
| 135 | # in Excel and Calc for further processing |
---|
| 136 | value += '#' |
---|
[7512] | 137 | return value |
---|
| 138 | |
---|
| 139 | @classmethod |
---|
| 140 | def datetime(self, value): |
---|
| 141 | """ 'yyyy/mm/dd' --> 'yyyy-mm-dd' |
---|
| 142 | """ |
---|
| 143 | #print "IN: ", value |
---|
| 144 | if value == "None": |
---|
| 145 | value = "" |
---|
| 146 | elif value == "": |
---|
| 147 | value = "" |
---|
| 148 | else: |
---|
| 149 | #value = datetime.datetime.strptime(value, '%Y/%m/%d') |
---|
| 150 | #value = datetime.datetime.strftime(value, '%Y-%m-%d') |
---|
| 151 | pass |
---|
| 152 | #print "OUT: ", value |
---|
| 153 | return value |
---|
| 154 | |
---|
| 155 | reader = csv.DictReader(open(INPUT_FILE, 'rb')) |
---|
| 156 | writer = None |
---|
| 157 | |
---|
| 158 | for num, row in enumerate(reader): |
---|
| 159 | if num == 0: |
---|
| 160 | writer = csv.DictWriter(open(OUTPUT_FILE, 'wb'), reader.fieldnames) |
---|
| 161 | print "FIELDS: " |
---|
| 162 | for x, y in enumerate(reader.fieldnames): |
---|
| 163 | print x, y |
---|
[7516] | 164 | header = convert_fieldnames(reader.fieldnames) |
---|
[7512] | 165 | writer.writerow(header) |
---|
| 166 | for key, value in row.items(): |
---|
| 167 | if not key in OPTIONS.keys(): |
---|
| 168 | continue |
---|
| 169 | conv_name = OPTIONS[key] |
---|
| 170 | converter = getattr(Converters, conv_name, None) |
---|
| 171 | if converter is None: |
---|
| 172 | print "WARNING: cannot find converter %s" % conv_name |
---|
| 173 | continue |
---|
| 174 | row[key] = converter(row[key]) |
---|
| 175 | writer.writerow(row) |
---|
| 176 | |
---|
[7518] | 177 | print "Output written to %s" % OUTPUT_FILE |
---|