rnsrk/goodByeHida
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

new commit

Browse source
This commit is contained in:
rnsrk 2025-09-09 10:16:31 +02:00
parent da296f8a64
commit e46a9fd4ec
69 changed files with 4199 additions and 4805 deletions
Download patch file Download diff file Expand all files Collapse all files

118
09_importInspectionMarkRelation.py
View file

@ -5,80 +5,66 @@ import os # For environment variable loading
from dotenv import load_dotenv # For environment variable loading
import pandas as pd # For dataframe handling
# Initialize the database
print('Initializing the database...')
engine, metadata, Session = initDb(True, './schemas/')
if engine == False:
print('Database initialization failed.')
exit()
def importInspectionMarkRelation(api, engine):
print('Importing inspection mark relations...')
# Load the environment variables
load_dotenv()
tableName = 'c__67b7_beziehung'
bundleId = 'bd9b0ff8dc3a6d9284e1798531389bf1'
# Initialize the WissKI API
print('Initializing the WissKI API...')
api_url = os.getenv('API_URL')
auth = (os.getenv('API_USERNAME'), os.getenv('API_PASSWORD'))
headers = {"Cache-Control": "no-cache"}
api = Api(api_url, auth, headers)
api.pathbuilder = api.get_pathbuilder('default')
try:
processedRows = pd.read_csv(f'./logs/{tableName}.csv')
except FileNotFoundError:
processedRows = pd.DataFrame(columns=['id', 'uuid', 'uri'])
try:
processedRows = pd.read_csv(f'./logs/processedInspectionMarkRelation.csv')
except FileNotFoundError:
processedRows = pd.DataFrame(columns=[ 'uuid', 'uri'])
# Load sources table
inspectionMarkRelationsTable = pd.read_sql_table(tableName, con=engine)
# Load sources table
inspectionMarkRelationsTable = pd.read_sql_table('c__67b7_beziehung', con=engine)
inspectionMarkRelationValues = {}
# Create inspectionMarkRelations
for index, row in inspectionMarkRelationsTable.iterrows():
# For every row in table...
if index < len(processedRows) and inspectionMarkRelationsTable.iloc[index, 0] == processedRows.iloc[index, 0]:
# skip if already processed
print(f'Skipping already processed inspectionMarkRelation {inspectionMarkRelationsTable.iloc[index, 0]}')
continue
# Create Entity property dicts
inspectionMarkRelationValues = {}
for key, value in row.items():
# For every column in row...
if (value is None) or (value == ''):
# skip if cell has no value
# Create inspectionMarkRelations
for index, row in inspectionMarkRelationsTable.iterrows():
# For every row in table...
if index < len(processedRows) and inspectionMarkRelationsTable.loc[index, 'id'] == processedRows.loc[index, 'id']:
# skip if already processed
print(f'Skipping already processed inspectionMarkRelation {inspectionMarkRelationsTable.loc[index, "id"]}')
continue
# Properties of an entity have to be an array, so...
if '###{{new_line}}###' in str(value):
print('replaced curly braces')
value = str(value).replace('###{{new_line}}###', '')
if '&' in str(value):
# ...Explode "&"-separated values to array items
value = [x.strip() for x in str(value).split('&')]
else:
# ...Or parse to array
value = [value]
# Map columns to fields. We use assignments for reification.
match key:
case 'id':
# Create Entity property dicts
inspectionMarkRelationValues = {}
for key, value in row.items():
# For every column in row...
if (value is None) or (value == ''):
# skip if cell has no value
continue
case 'f__uuid':
inspectionMarkRelationValues['ffd502413c286815811ae5546f73935b'] = value # UUID
case 'f__67b8_bez_bz_nr':
inspectionMarkRelationValues['ff3f6dd331ed27515f6721ac8312706c'] = value # Inspection Mark Identifier
case 'f__67b7_beziehung':
inspectionMarkRelationValues['f1cb8db7e1c26a5b5fe0c9d8fca60de2'] = value # Relation
# Properties of an entity have to be an array, so...
value = str(value).replace('&###{{new_line}}###'.format(), '&')
value = str(value).replace('###{{new_line}}###', '&')
value = str(value).replace(' & ', '&')
if '&' in str(value):
# ...Explode "&"-separated values to array items
value = [x.strip() for x in str(value).split('&')]
else:
# ...Or parse to array
value = [value]
# Map columns to fields. We use assignments for reification.
match key:
case 'id':
continue
case 'f__uuid':
inspectionMarkRelationValues['ffd502413c286815811ae5546f73935b'] = value # UUID
case 'f__67b8_bez_bz_nr':
inspectionMarkRelationValues['ff3f6dd331ed27515f6721ac8312706c'] = value # Inspection Mark Identifier
case 'f__67b7_beziehung':
inspectionMarkRelationValues['f1cb8db7e1c26a5b5fe0c9d8fca60de2'] = value # Relation
case _:
print(f'{key} is not a valid field, skipping.')
case _:
print(f'{key} is not a valid field, skipping.')
# Create Material
inspectionMarkRelation = Entity(api=api, fields=inspectionMarkRelationValues, bundle_id='bd9b0ff8dc3a6d9284e1798531389bf1')
api.save(inspectionMarkRelation)
# Create Material
inspectionMarkRelation = Entity(api=api, fields=inspectionMarkRelationValues, bundle_id='bd9b0ff8dc3a6d9284e1798531389bf1')
api.save(inspectionMarkRelation)
print(f'Created inspectionMarkRelation {index}: {inspectionMarkRelation.uri}')
print(f'Created inspection mark relation {index}: {inspectionMarkRelation.uri}')
# Write log
processedRows = processedRows._append({'uuid': inspectionMarkRelationValues['ffd502413c286815811ae5546f73935b'][0], 'uri': inspectionMarkRelation.uri}, ignore_index=True)
processedRows.to_csv(f'./logs/processedInspectionMarkRelation.csv', index=False)
# Write log
processedRows = processedRows._append({'id': row['id'], 'uuid': inspectionMarkRelationValues['ffd502413c286815811ae5546f73935b'][0], 'uri': inspectionMarkRelation.uri}, ignore_index=True)
processedRows.to_csv(f'./logs/{tableName}.csv', index=False)
print('finish')
print('finish')