import_data.py 17.6 KB
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550
#-*- coding:utf-8 -*-

import sqlite3
import datetime
from django.db import connection, transaction
from django.core.management.base import BaseCommand, CommandError
from django.contrib.auth.models import User

from common.util import no_history
from dictionary.models import *

DEFAULT_DATABASE = 'data/sgjp.db'
MINI_LEXEME_COUNT = 500
mini = False
sql = True
cursor = connection.cursor()
db = None
cur = None
no_history()

class Command(BaseCommand):
  args = '<input db filename>'
  help = 'Imports initial data'

  #TODO opcja -mini (?)
  def handle(self, db_name=DEFAULT_DATABASE, **options):
    global db
    db = db_name
    delete_and_import()

def get_cursor(db):
  conn = sqlite3.connect(db)
  conn.row_factory = sqlite3.Row
  return conn.cursor()


def import_lexical_classes():
  lc = LexicalClass(symbol='inne')
  lc.save()
  for row in cur.execute('select distinct pos from wzory'):
    if not sql:
      lc = LexicalClass(symbol=row['pos'])
      lc.save()
    else:
      cursor.execute("INSERT INTO czescimowy (czm) VALUES (%s)",
                     [row['pos']])


def import_parts_of_speech():
  cur2 = get_cursor(db)
  other = 'inne'
  lcs = {}
  for row in cur.execute('select distinct wzory.pos, leksemy.pos from wzory '
                         'natural join odmieniasie join leksemy on '
                         'leksemy.nr = odmieniasie.nr'):
    lcs[row[1]] = row[0]
    print row
  for row in cur.execute('SELECT pos FROM klasygramatyczne'):
    lc = lcs.get(row['pos'], other)
    if not sql:
      pos = PartOfSpeech(symbol=row['pos'])
      pos.lexical_class = LexicalClass.objects.get(symbol=lc)
      pos.save()
    else:
      cursor.execute("INSERT INTO klasygramatyczne (pos, czm) VALUES (%s, %s)",
                     [row['pos'], lc])


def import_base_form_labels():
  query_result = cur.execute("""
    SELECT efobaz FROM paradygmaty
    UNION
    SELECT efobaz FROM zakonczenia
    """)
  for row in query_result:
    if not sql:
      bfl = BaseFormLabel(entry=row[0])
      bfl.save()
    else:
      cursor.execute("INSERT INTO efobazy (efobaz) VALUES (%s)", [row[0]])

# tymczasowa tabelka - powinna przychodzić z bazą
# (albo zrobić w kodzie wyjątek na p123... jak już i tak są wyjątki)
basic_form_labels = {
  '0-': '1',
  '3+': '1',
  'f':  'sg:nom',
  'm1': 'sg:nom',
  'm2': 'sg:nom',
  'm3': 'sg:nom',
  'n1': 'sg:nom',
  'n2': 'sg:nom',
  'p1': 'pl:nom:mo',
  'p2': 'pl:nom',
  'p3': 'pl:nom',
  'pri': 'sg:nom', # albo pl. teraz już naprawdę się nie da.
  'sec': 'sg:nom',
}

# to chyba nie jest najlepsze rozwiązanie...
basic_form_labels_pos = {
  'v': '5',
  'ger': '11',
  'pact': '3',
  'ppas': '10',
  'appas': '10',
  'pred': '5',
}

ics = {}

def import_inflection_characteristics():
  for row in cur.execute('SELECT DISTINCT charfl, pos FROM paradygmaty'):
    if row['charfl'] == '':
      bfl_entry = '1' if row['pos'] in ('adj', 'adjcom') else ''
    else:
      bfl_entry = basic_form_labels.get(row['charfl'], '')
    if row['pos'] in basic_form_labels_pos:
      bfl_entry = basic_form_labels_pos[row['pos']]
    bfl = BaseFormLabel.objects.get(entry=bfl_entry)
    if not sql:
      ic = InflectionCharacteristic(
        entry=row['charfl'], basic_form_label=bfl,
        part_of_speech=PartOfSpeech.objects.get(pk=row['pos']))
      ic.save()
    else:
      cursor.execute("INSERT INTO charfle (charfl, pos, efobaz) "
                     "VALUES (%s, %s, %s)", [row['charfl'], row['pos'], bfl.pk])
  for ic in InflectionCharacteristic.objects.all():
    ics[(ic.entry, ic.part_of_speech.symbol)] = ic


sgjp_domain = ('SGJP', 'WSJP', 'SJPDor', 'zmiotki')


def import_vocabularies():
  try:
    sgjp = User.objects.get(username='sgjp')
  except:
    sgjp = None
  result = cur.execute("""
    SELECT slownik FROM leksemy
    UNION
    SELECT slownik_uz FROM slowniki_uzywajace
  """)
  for row in result:
    v = Vocabulary()
    v.id = row[0]
    v.save()
    if sgjp and v.id in sgjp_domain:
      v.managers.add(sgjp) #add


def import_qualifiers():
  sgjp = Vocabulary.objects.get(id='SGJP')
  query_result = cur.execute("""
    SELECT okwal FROM odmieniasie
    UNION
    SELECT zkwal FROM zakonczenia
    UNION
    SELECT lkwal FROM leksemy
    """)
  added = set()
  for row in query_result:
    if row[0]:
      for qualifier in row[0].split('|'):
        if qualifier not in added:
          added.add(qualifier)
          if not sql:
            q = Qualifier(label=qualifier, vocabulary=sgjp)
            q.save()
          else:
            cursor.execute("INSERT INTO kwalifikatory (kwal, slownik) "
                           "VALUES (%s, %s)", [qualifier, sgjp.pk])


mini_lexeme_query = 'SELECT %s FROM leksemy LIMIT ?'

def import_lexemes():
  if mini:
    result = cur.execute(mini_lexeme_query % '*', (MINI_LEXEME_COUNT,))
  else:
    result = cur.execute('SELECT * FROM leksemy')
  date = datetime.datetime.now()
  cv_table = dict(ClassificationValue.objects.values_list('label', 'pk'))
  for row in result:
    slownik = row['slownik']
    status = 'conf' if slownik != 'zmiotki' else 'cand'
    if not sql:
      l = Lexeme()
      l.id = row['nr']
      l.entry = row['haslo']
      l.part_of_speech = PartOfSpeech.objects.get(pk=row['pos'])
      l.comment = row['komentarz']
      l.source = 'SGJP' # potrzebne to w ogóle?
      l.status = status
      l.gloss = row['glosa'] or ''
      l.entry_suffix = row['haslosuf'] or ''
      cv = ClassificationValue.objects.get(label=row['pospolitosc'])
      cv.lexemes.add(l) #add
      l.fix_homonym_number()

      l.owner_vocabulary = Vocabulary.objects.get(pk=slownik)
      l.save()
      LexemeAssociation.objects.create(
        vocabulary=Vocabulary.objects.get(pk=slownik),
        lexeme=l)
      # brak kwalifikatorów - nieauktualne
    else:
      cv_pk = cv_table[row['pospolitosc']]
      cursor.execute(
        "INSERT INTO leksemy (id, haslo, haslosuf, glosa, hom, pos, zrodlo, "
        "status, komentarz, data_modyfikacji, slownik) VALUES (%s, %s, %s, %s, "
        "%s, %s, %s, %s, %s, %s, %s)", [row['nr'], row['haslo'],
        row['haslosuf'] or '', row['glosa'] or '', 1, row['pos'], 'SGJP',
        status, row['komentarz'], date, row['slownik']])
      cursor.execute(
        "INSERT INTO leksemy_w_slownikach (l_id, slownik) "
        "VALUES (%s, %s)", [row['nr'], slownik])
      cursor.execute(
        "INSERT INTO wartosci_klasyfikacji_lexemes (classificationvalue_id, "
        "lexeme_id) VALUES (%s, %s)", [cv_pk, row['nr']])
      if row['lkwal']:
        for qual in row['lkwal'].split('|'):
          q_id = Qualifier.objects.get(label=qual).pk
          cursor.execute(
            "INSERT INTO kwalifikatory_leksemow (lexeme_id, "
            "qualifier_id) VALUES (%s, %s)", [row['nr'], q_id])


def import_lexeme_associations():
  if mini:
    result = cur.execute('SELECT * FROM slowniki_uzywajace WHERE nr in (%s)' %
                         (mini_lexeme_query % 'nr'), [MINI_LEXEME_COUNT])
  else:
    result = cur.execute('SELECT * FROM slowniki_uzywajace')
  for row in result:
    if not sql:
      v = Vocabulary.objects.get(pk=row['slownik_uz'])
      l = Lexeme.objects.get(pk=row['nr'])
      LexemeAssociation.objects.create(vocabulary=v, lexeme=l)
    else:
      cursor.execute(
        "INSERT INTO leksemy_w_slownikach (l_id, slownik) "
        "VALUES (%s, %s)", [row['nr'], row['slownik_uz']])


def import_cross_reference_types():
  result = cur.execute('select distinct l1.pos pos1, l2.pos pos2, t.* '
                       'from odsylacze o join leksemy l1 on nrod=l1.nr '
                       'join leksemy l2 on nrdo=l2.nr '
                       'join typyodsylaczy t on t.typods=o.typods')
  for row in result:
    t = CrossReferenceType()
    t.symbol = row['typods']
    t.desc = row['naglowek']
    t.index = row['kolejnosc']
    t.from_pos = PartOfSpeech.objects.get(symbol=row['pos1'])
    t.to_pos = PartOfSpeech.objects.get(symbol=row['pos2'])
    t.save()


def import_cross_references():
  if mini:
    result = cur.execute('SELECT * FROM odsylacze WHERE '
                         'nrod in (%(subq)s) and nrdo in (%(subq)s)' %
                         {'subq': mini_lexeme_query % 'nr'},
                         [MINI_LEXEME_COUNT, MINI_LEXEME_COUNT])
  else:
    result = cur.execute('SELECT * FROM odsylacze')
  for row in result:
    if row['nrod'] and row['nrdo']: # no bo nie wiem jak to interpretować
      l_from = Lexeme.objects.get(pk=row['nrod'])
      l_to = Lexeme.objects.get(pk=row['nrdo'])
      cr_type = CrossReferenceType(
        symbol=row['typods'], from_pos=l_from.part_of_speech,
        to_pos=l_to.part_of_speech)
      if not sql:
        CrossReference.objects.create(
          from_lexeme=l_from, to_lexeme=to_lexeme, type=cr_type)
      else:
        cursor.execute(
          "INSERT INTO odsylacze (l_id_od, l_id_do, typods_id) "
          "VALUES (%s, %s, %s)", [row['nrod'], row['nrdo'], cr_type.pk])


def import_pattern_types():
  for row in cur.execute('SELECT DISTINCT typr, pos FROM paradygmaty'):
    lc = PartOfSpeech.objects.get(symbol=row['pos']).lexical_class
    PatternType.objects.get_or_create(lexical_class=lc, entry=row['typr'])
  # prowizorka z powodu pustej klasy 'skr'
  for row in cur.execute('SELECT DISTINCT typr, pos FROM wzory'):
    lc = LexicalClass.objects.get(symbol=row['pos'])
    PatternType.objects.get_or_create(lexical_class=lc, entry=row['typr'])


def import_patterns():
  for row in cur.execute('SELECT * FROM wzory'):
    pt = PatternType.objects.get(
      lexical_class__symbol=row['pos'], entry=row['typr'])
    status = 'temp'
    example = '-'
    if not sql:
      p = Pattern()
      p.name = row['wzor']
      p.type = pt
      p.basic_form_ending = row['zakp']

      p.example = example
      p.status = status
      p.save()
    else:
      cursor.execute(
        "INSERT INTO wzory (w_id, typ, przyklad, zakp, status, komentarz) "
        "VALUES (%s, %s, %s, %s, %s, %s)",
        [row['wzor'], pt.pk, example, row['zakp'], status, ''])


def import_lexeme_inflection_patterns():
  if mini:
    result = cur.execute(
      'SELECT * FROM odmieniasie WHERE nr IN (%s)' % (mini_lexeme_query % 'nr'),
      (MINI_LEXEME_COUNT,))
  else:
    result = cur.execute('SELECT * FROM odmieniasie')
  pos_table = dict(Lexeme.objects.values_list('pk', 'part_of_speech'))
  pattern_pk_table = dict(Pattern.objects.values_list('name', 'pk'))
  for row in result:
    if not sql:
      lip = LexemeInflectionPattern()
      lip.lexeme = Lexeme.objects.get(id=row['nr'])
      lip.index = row['oskl']
      lip.pattern = Pattern.objects.get(name=row['wzor'])
      lip.inflection_characteristic = ics[(row['charfl'],
                                           lip.lexeme.part_of_speech)]
      lip.root = row['rdzen']
      lip.save()
      # nieaktualne
      if row['okwal']:
        lip.qualifiers.add(Qualifier.objects.get(label=row['okwal'])) #add
    else:
      pos = pos_table[row['nr']]
      pattern_pk = pattern_pk_table[row['wzor']]
      charfl_id = ics[(row['charfl'], pos)].pk
      cursor.execute(
        "INSERT INTO odmieniasie (l_id, oind, w_id, charfl, rdzen) "
        "VALUES (%s, %s, %s, %s, %s) ", [row['nr'], row['oskl'], pattern_pk,
        charfl_id, row['rdzen']])
      if row['okwal']:
        cursor.execute("select currval('odmieniasie_id_seq')")
        last_id = cursor.fetchone()[0]
        for qual in row['okwal'].split('|'):
          q_id = Qualifier.objects.get(label=qual).pk
          cursor.execute(
            "INSERT INTO kwalifikatory_odmieniasiow (lexemeinflectionpattern_id, "
            "qualifier_id) VALUES (%s, %s)", [last_id, q_id])

def import_endings():
  if sql:
    pattern_pk_table = dict(Pattern.objects.values_list('name', 'pk'))
    bfl_table = dict(BaseFormLabel.objects.values_list('entry', 'pk'))
  for row in cur.execute('SELECT * FROM zakonczenia'):
    if row['zak'] is not None:
      if not sql:
        e = Ending()
        e.pattern = Pattern.objects.get(name=row['wzor'])
        e.base_form_label = BaseFormLabel.objects.get(entry=row['efobaz'])
        e.string = row['zak']
        e.index = row['nrskl']
        e.save()
        for qual in row['zkwal'].split('|'):
          e.qualifiers.add(Qualifier.objects.get(label=qual)) #add
      else:
        pattern_pk = pattern_pk_table[row['wzor']]
        if pattern_pk:
          efobaz_id = bfl_table[row['efobaz']]
          cursor.execute(
            "INSERT INTO zakonczenia (w_id, efobaz, zind, zak) VALUES "
            "(%s, %s, %s, %s)",
            [pattern_pk, efobaz_id, row['nrskl'], row['zak']])
          if row['zkwal']:
            cursor.execute("select currval('zakonczenia_id_seq')")
            last_id = cursor.fetchone()[0]
            for qual in row['zkwal'].split('|'):
              q_id = Qualifier.objects.get(label=qual).pk
              cursor.execute(
                "INSERT INTO kwalifikatory_zakonczen (ending_id, qualifier_id) "
                "VALUES (%s, %s)", [last_id, q_id])


def import_tables():
  bfl_table = dict(BaseFormLabel.objects.values_list('entry', 'pk'))
  for row in cur.execute('SELECT * FROM paradygmaty'):
    lc = PartOfSpeech.objects.get(symbol=row['pos']).lexical_class
    variant, _created = Variant.objects.get_or_create(id=row['wariant'])
    tt_data = {
      'variant': variant,
      'pattern_type': PatternType.objects.get(
        entry=row['typr'], lexical_class=lc),
      'inflection_characteristic': InflectionCharacteristic.objects.get(
        entry=row['charfl'], part_of_speech__symbol=row['pos']),
    }
    tt, _created = TableTemplate.objects.get_or_create(**tt_data)
    if not sql:
      c = Cell()
      c.table_template = tt
      c.base_form_label = BaseFormLabel.objects.get(entry=row['efobaz'])
      c.tag = row['morf']
      c.prefix = row['pref']
      c.suffix = row['suf']
      c.index = row['kskl']
      c.save()
      if row['row']:
        tc = TableCell()
        tc.cell = c
        tc.row = row['row']
        tc.col = row['col']
        tc.rowspan = row['rowspan']
        tc.colspan = row['colspan']
        tc.save()
    else:
      efobaz_id = bfl_table[row['efobaz']]
      cursor.execute(
        "INSERT INTO klatki (st_id, efobaz, tag, prefiks, sufiks, kind) "
        "VALUES (%s, %s, %s, %s, %s, %s)", [tt.pk, efobaz_id, row['morf'],
        row['pref'], row['suf'], row['kskl']])
      if row['row']:
        cursor.execute("select currval('klatki_id_seq')")
        last_id = cursor.fetchone()[0]
        cursor.execute(
          "INSERT INTO komorki_tabel (k_id, row, col, rowspan, colspan) "
          "VALUES (%s, %s, %s, %s, %s)", [last_id, row['row'],
          row['col'], row['rowspan'], row['colspan']])


def import_table_headers():
  for row in cur.execute('SELECT * FROM naglowkiwierszy'):
    if row['styl'] != 'b' and row['nagl']:
      tts = TableTemplate.objects.filter(
        variant__id=row['wariant'], pattern_type__entry=row['typr'],
        inflection_characteristic__entry=row['charfl'],
        inflection_characteristic__part_of_speech__symbol=row['pos'])
      if tts:
        tt = tts[0]
        if not sql:
          th = TableHeader()
          th.table_template = tt
          th.row = row['row']
          th.col = row['col']
          th.rowspan = row['rowspan']
          th.colspan = row['colspan']
          th.label = row['nagl']
          th.horizontal = row['styl'] == 'h'
          th.save()
        else:
          cursor.execute(
            "INSERT INTO naglowki_tabel (st_id, row, col, rowspan, colspan, "
            "nagl, wierszowy) VALUES (%s, %s, %s, %s, %s, %s, %s)",
            [tt.pk, row['row'], row['col'], row['rowspan'], row['colspan'],
            row['nagl'], row['styl'] == 'h'])


def single_import(fun, db):
  global cur, cursor
  transaction.commit_unless_managed()
  transaction.enter_transaction_management()
  transaction.managed(True)
  cur = get_cursor(db)
  cursor = connection.cursor()
  fun()
  cur.close()
  cursor.close()
  transaction.commit()
  transaction.leave_transaction_management()


def delete_and_import():
  transaction.commit_unless_managed()
  transaction.enter_transaction_management()
  transaction.managed(True)
  models = (
    Qualifier,
    LexicalClass,
    PartOfSpeech,
    BaseFormLabel,
    InflectionCharacteristic,
    Lexeme,
    PatternType,
    Pattern,
    LexemeInflectionPattern,
    Ending,
    TableTemplate,
    Cell,
    TableCell,
    Vocabulary,
    LexemeAssociation,
  )
  print 'deleting old data...'
  for model in models:
    model.objects.all().delete()

  global cur
  cur = get_cursor(db)
  print 'importing lexical classes...'
  import_lexical_classes()
  print 'importing parts of speech'
  import_parts_of_speech()
  print 'importing base form labels'
  import_base_form_labels()
  print 'importing inflection characteristics'
  import_inflection_characteristics()
  print 'importing vocabularies...'
  import_vocabularies()
  print 'importing qualifiers...'
  import_qualifiers()
  print 'importing lexemes...'
  import_lexemes()
  print 'importing lexeme associations...'
  import_lexeme_associations()
  print 'importing cross-reference types...'
  import_cross_reference_types()
  print 'importing cross-references...'
  import_cross_references()
  print 'importing pattern types...'
  import_pattern_types()
  print 'importing patterns...'
  import_patterns()
  print 'importing lexeme inflection patterns...'
  import_lexeme_inflection_patterns()
  print 'importing endings...'
  import_endings()
  print 'importing table templates...'
  import_tables()
  print 'importing table headers...'
  import_table_headers()
  cur.close()
  cursor.close()
  transaction.commit()
  transaction.leave_transaction_management()

import sys
if __name__ == '__main__':
  if sys.argv[-1] == '-mini':
    mini = True
    del sys.argv[-1]
  if len(sys.argv) > 1:
    db = sys.argv[1]
  else:
    db = DEFAULT_DATABASE
  delete_and_import()