[7512] | 1 | ## $Id: fix_import_file.py 8522 2012-05-25 20:45:24Z 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 | """ |
---|
[7573] | 31 | import csv |
---|
| 32 | import datetime |
---|
[7575] | 33 | import re |
---|
[7573] | 34 | import sys |
---|
[7512] | 35 | |
---|
| 36 | ## |
---|
| 37 | ## CONFIGURATION SECTION |
---|
| 38 | ## |
---|
| 39 | # keys are fieldnames in input file, values are methods of class |
---|
| 40 | # Converter (see below) |
---|
| 41 | OPTIONS = { |
---|
[8478] | 42 | 'student_id': 'student_id', |
---|
[7512] | 43 | 'sex': 'gender', |
---|
| 44 | 'birthday': 'date', |
---|
| 45 | 'request_date': 'datetime', |
---|
[7514] | 46 | 'marit_stat': 'marit_stat', |
---|
[7537] | 47 | 'session': 'session', |
---|
[7514] | 48 | 'entry_session': 'session', |
---|
| 49 | 'current_session': 'session', |
---|
[7602] | 50 | 'session_id': 'session', |
---|
[7632] | 51 | 'entry_mode': 'mode', |
---|
[7526] | 52 | 'reg_state': 'reg_state', |
---|
| 53 | 'password': 'password', |
---|
[7575] | 54 | 'phone': 'phone', |
---|
[8478] | 55 | 'nationality': 'nationality', |
---|
[7602] | 56 | 'level': 'level', |
---|
| 57 | 'start_level': 'level', |
---|
| 58 | 'end_level': 'level', |
---|
| 59 | 'level_id': 'level', |
---|
| 60 | 'current_level': 'level', |
---|
| 61 | 'semester': 'semester', |
---|
| 62 | 'application_category': 'application_category', |
---|
[7610] | 63 | 'lga': 'lga', |
---|
[7628] | 64 | 'order_id': 'no_int', |
---|
[7512] | 65 | } |
---|
[7516] | 66 | |
---|
| 67 | # Mapping input file colnames --> output file colnames |
---|
| 68 | COLNAME_MAPPING = { |
---|
[7666] | 69 | # base data |
---|
[8478] | 70 | 'reg_state': 'state', |
---|
[7518] | 71 | 'jamb_reg_no': 'reg_number', |
---|
[7645] | 72 | 'matric_no': 'matric_number', |
---|
[7516] | 73 | 'birthday': 'date_of_birth', |
---|
[7526] | 74 | 'clr_ac_pin': 'clr_code', |
---|
[7550] | 75 | # study course |
---|
[7530] | 76 | 'study_course': 'certificate', |
---|
[7550] | 77 | # study level |
---|
[7537] | 78 | 'session': 'level_session', |
---|
| 79 | 'verdict': 'level_verdict', |
---|
[7550] | 80 | # course ticket |
---|
| 81 | 'level_id': 'level', |
---|
[7666] | 82 | 'core_or_elective': 'mandatory', |
---|
[7628] | 83 | # payment ticket |
---|
| 84 | 'order_id': 'p_id', |
---|
| 85 | 'status': 'p_state', |
---|
| 86 | 'category': 'p_category', |
---|
| 87 | 'resp_pay_reference': 'r_pay_reference', |
---|
| 88 | 'resp_desc': 'r_desc', |
---|
| 89 | 'resp_approved_amount': 'r_amount_approved', |
---|
| 90 | 'item': 'p_item', |
---|
| 91 | 'amount': 'amount_auth', |
---|
| 92 | 'resp_card_num': 'r_card_num', |
---|
| 93 | 'resp_code': 'r_code', |
---|
| 94 | 'date': 'creation_date', |
---|
| 95 | 'surcharge': 'surcharge_1', |
---|
| 96 | 'session_id': 'p_session', |
---|
[7516] | 97 | } |
---|
[7526] | 98 | |
---|
[8478] | 99 | # Mapping input state --> output state |
---|
[7526] | 100 | REGSTATE_MAPPING = { |
---|
| 101 | 'student_created': 'created', |
---|
| 102 | 'admitted': 'admitted', |
---|
[7610] | 103 | 'objection_raised': 'clearance started', |
---|
[7526] | 104 | 'clearance_pin_entered': 'clearance started', |
---|
| 105 | 'clearance_requested': 'clearance requested', |
---|
| 106 | 'cleared_and_validated': 'cleared', |
---|
| 107 | 'school_fee_paid': 'school fee paid', |
---|
| 108 | 'returning': 'returning', |
---|
| 109 | 'courses_registered': 'courses registered', |
---|
| 110 | 'courses_validated': 'courses validated', |
---|
| 111 | } |
---|
| 112 | |
---|
[7512] | 113 | ## |
---|
| 114 | ## END OF CONFIG |
---|
| 115 | ## |
---|
| 116 | |
---|
[7575] | 117 | # Look for the first sequence of numbers |
---|
| 118 | RE_PHONE = re.compile('[^\d]*(\d*)[^\d]*') |
---|
| 119 | |
---|
[7516] | 120 | def convert_fieldnames(fieldnames): |
---|
| 121 | """Replace input fieldnames by fieldnames of COLNAME_MAPPING. |
---|
| 122 | """ |
---|
| 123 | header = dict([(name, name) for name in fieldnames]) |
---|
| 124 | for in_name, out_name in COLNAME_MAPPING.items(): |
---|
| 125 | if in_name not in header: |
---|
| 126 | continue |
---|
| 127 | header[in_name] = out_name |
---|
[7514] | 128 | return header |
---|
| 129 | |
---|
[7512] | 130 | class Converters(): |
---|
| 131 | """Converters to turn old-style values into new ones. |
---|
| 132 | """ |
---|
[8478] | 133 | |
---|
[7512] | 134 | @classmethod |
---|
[8478] | 135 | def student_id(self, value): |
---|
| 136 | """ 'A123456' --> 'EA123456' |
---|
| 137 | """ |
---|
| 138 | if len(value) == 7: |
---|
| 139 | return 'E' + value |
---|
| 140 | return value |
---|
| 141 | |
---|
| 142 | @classmethod |
---|
[7526] | 143 | def reg_state(self, value): |
---|
| 144 | """ 'courses_validated' --> 'courses validated' |
---|
| 145 | """ |
---|
| 146 | return REGSTATE_MAPPING.get(value,value) |
---|
| 147 | |
---|
| 148 | @classmethod |
---|
[7602] | 149 | def level(self, value): |
---|
| 150 | """ '000' --> '10' |
---|
| 151 | """ |
---|
| 152 | try: |
---|
| 153 | number = int(value) |
---|
| 154 | except ValueError: |
---|
| 155 | return 9999 |
---|
| 156 | if number == 0: |
---|
| 157 | return 10 |
---|
| 158 | return number |
---|
| 159 | |
---|
| 160 | @classmethod |
---|
| 161 | def semester(self, value): |
---|
| 162 | """ '0' --> '9' |
---|
| 163 | """ |
---|
| 164 | try: |
---|
| 165 | number = int(value) |
---|
| 166 | except ValueError: |
---|
| 167 | return 9999 |
---|
| 168 | if number == 0: |
---|
| 169 | return 9 |
---|
| 170 | return number |
---|
| 171 | |
---|
| 172 | @classmethod |
---|
| 173 | def application_category(self, value): |
---|
| 174 | """ '' --> 'no' |
---|
| 175 | """ |
---|
| 176 | if value == '': |
---|
| 177 | return 'no' |
---|
| 178 | return value |
---|
| 179 | |
---|
[7610] | 180 | @classmethod |
---|
| 181 | def lga(self, value): |
---|
| 182 | """ Remove apostrophe |
---|
| 183 | """ |
---|
| 184 | if value == 'akwa_ibom_uru_offong_oruko': |
---|
| 185 | return 'akwa_ibom_urue-offong-oruko' |
---|
| 186 | try: |
---|
| 187 | value = value.replace("'","") |
---|
| 188 | value = value.lower() |
---|
| 189 | except: |
---|
| 190 | return '' |
---|
| 191 | return value |
---|
[7602] | 192 | |
---|
[7610] | 193 | |
---|
[7602] | 194 | @classmethod |
---|
[7514] | 195 | def session(self, value): |
---|
| 196 | """ '08' --> '2008' |
---|
[8478] | 197 | '2008/2009' --> '2008' |
---|
[7514] | 198 | """ |
---|
[8478] | 199 | if '/' in value: |
---|
| 200 | numbers = value.split('/') |
---|
| 201 | number = int(numbers[0]) |
---|
| 202 | if number in range(2000,2015): |
---|
| 203 | return number |
---|
| 204 | else: |
---|
| 205 | return 9999 |
---|
[7514] | 206 | try: |
---|
| 207 | number = int(value) |
---|
| 208 | except ValueError: |
---|
[7602] | 209 | #import pdb; pdb.set_trace() |
---|
[7514] | 210 | return 9999 |
---|
| 211 | if number < 14: |
---|
| 212 | return number + 2000 |
---|
| 213 | elif number in range(2000,2015): |
---|
| 214 | return number |
---|
| 215 | else: |
---|
| 216 | return 9999 |
---|
| 217 | |
---|
| 218 | @classmethod |
---|
| 219 | def marit_stat(self, value): |
---|
| 220 | """ 'True'/'False' --> 'married'/'unmarried' |
---|
| 221 | """ |
---|
[7610] | 222 | if value in ('True','married'): |
---|
[7514] | 223 | value = 'married' |
---|
[7610] | 224 | elif value in ('False','unmarried'): |
---|
[7514] | 225 | value = 'unmarried' |
---|
| 226 | else: |
---|
| 227 | value = '' |
---|
| 228 | return value |
---|
| 229 | |
---|
| 230 | @classmethod |
---|
| 231 | def gender(self, value): |
---|
[7526] | 232 | """ 'True'/'False' --> 'f'/'m' |
---|
[7514] | 233 | """ |
---|
[7610] | 234 | if value in ('True','f'): |
---|
[7526] | 235 | value = 'f' |
---|
[7610] | 236 | elif value in ('False','m'): |
---|
[7526] | 237 | value = 'm' |
---|
[7514] | 238 | else: |
---|
| 239 | value = '' |
---|
| 240 | return value |
---|
| 241 | |
---|
| 242 | @classmethod |
---|
[7512] | 243 | def date(self, value): |
---|
| 244 | """ 'yyyy/mm/dd' --> 'yyyy-mm-dd' |
---|
| 245 | """ |
---|
| 246 | if value == "None": |
---|
| 247 | value = "" |
---|
| 248 | elif value == "": |
---|
| 249 | value = "" |
---|
| 250 | else: |
---|
| 251 | value = value.replace('/', '-') |
---|
[7514] | 252 | # We add the hash symbol to avoid automatic date transformation |
---|
| 253 | # in Excel and Calc for further processing |
---|
| 254 | value += '#' |
---|
[7512] | 255 | return value |
---|
| 256 | |
---|
| 257 | @classmethod |
---|
[7628] | 258 | def no_int(self, value): |
---|
| 259 | """ Add hash. |
---|
| 260 | """ |
---|
| 261 | # We add the hash symbol to avoid automatic number transformation |
---|
| 262 | # in Excel and Calc for further processing |
---|
| 263 | value += '#' |
---|
| 264 | return value |
---|
| 265 | |
---|
| 266 | |
---|
| 267 | @classmethod |
---|
[7512] | 268 | def datetime(self, value): |
---|
| 269 | """ 'yyyy/mm/dd' --> 'yyyy-mm-dd' |
---|
| 270 | """ |
---|
| 271 | #print "IN: ", value |
---|
| 272 | if value == "None": |
---|
| 273 | value = "" |
---|
| 274 | elif value == "": |
---|
| 275 | value = "" |
---|
| 276 | else: |
---|
| 277 | #value = datetime.datetime.strptime(value, '%Y/%m/%d') |
---|
| 278 | #value = datetime.datetime.strftime(value, '%Y-%m-%d') |
---|
| 279 | pass |
---|
| 280 | #print "OUT: ", value |
---|
| 281 | return value |
---|
| 282 | |
---|
[7526] | 283 | @classmethod |
---|
[7632] | 284 | def mode(self, value): |
---|
| 285 | if value == "transfer_fulltime": |
---|
| 286 | return "transfer_ft" |
---|
[8522] | 287 | if value == "ume_ft": |
---|
| 288 | return "utme_ft" |
---|
[7632] | 289 | return value |
---|
| 290 | |
---|
| 291 | @classmethod |
---|
[7526] | 292 | def password(self, value): |
---|
| 293 | if value == "not set": |
---|
| 294 | return "" |
---|
| 295 | return value |
---|
| 296 | |
---|
[7575] | 297 | @classmethod |
---|
[8478] | 298 | def nationality(self, value): |
---|
| 299 | if value == "nigeria": |
---|
| 300 | return "NG" |
---|
| 301 | return value |
---|
| 302 | |
---|
| 303 | @classmethod |
---|
[7575] | 304 | def phone(self, value): |
---|
| 305 | """ '<num-seq1>-<num-seq2> asd' -> '--<num-seq1><num-seq2>' |
---|
[7526] | 306 | |
---|
[7575] | 307 | Dashes and slashes are removed before looking for sequences |
---|
| 308 | of numbers. |
---|
| 309 | """ |
---|
| 310 | value = value.replace('-', '') |
---|
| 311 | value = value.replace('/', '') |
---|
| 312 | match = RE_PHONE.match(value) |
---|
| 313 | phone = match.groups()[0] |
---|
[8478] | 314 | value = '-%s' % phone |
---|
[7575] | 315 | return value |
---|
| 316 | |
---|
| 317 | |
---|
[7572] | 318 | def main(): |
---|
[7573] | 319 | input_file = '%s' % sys.argv[1] |
---|
| 320 | output_file = '%s_edited.csv' % sys.argv[1].split('.')[0] |
---|
| 321 | reader = csv.DictReader(open(input_file, 'rb')) |
---|
[7572] | 322 | writer = None |
---|
[7512] | 323 | |
---|
[7572] | 324 | for num, row in enumerate(reader): |
---|
| 325 | if num == 0: |
---|
[7573] | 326 | writer = csv.DictWriter(open(output_file, 'wb'), reader.fieldnames) |
---|
[7572] | 327 | print "FIELDS: " |
---|
| 328 | for x, y in enumerate(reader.fieldnames): |
---|
| 329 | print x, y |
---|
| 330 | header = convert_fieldnames(reader.fieldnames) |
---|
| 331 | writer.writerow(header) |
---|
| 332 | for key, value in row.items(): |
---|
| 333 | if not key in OPTIONS.keys(): |
---|
| 334 | continue |
---|
| 335 | conv_name = OPTIONS[key] |
---|
| 336 | converter = getattr(Converters, conv_name, None) |
---|
| 337 | if converter is None: |
---|
| 338 | print "WARNING: cannot find converter %s" % conv_name |
---|
| 339 | continue |
---|
| 340 | row[key] = converter(row[key]) |
---|
[7602] | 341 | try: |
---|
| 342 | writer.writerow(row) |
---|
| 343 | except: |
---|
| 344 | print row['student_id'] |
---|
[7512] | 345 | |
---|
[7573] | 346 | print "Output written to %s" % output_file |
---|
[7572] | 347 | |
---|
| 348 | |
---|
| 349 | if __name__ == '__main__': |
---|
| 350 | if len(sys.argv) != 2: |
---|
| 351 | print 'Usage: %s <filename>' % __file__ |
---|
| 352 | sys.exit(1) |
---|
| 353 | main() |
---|