otlmow-template 0.3__tar.gz → 0.4__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {otlmow_template-0.3 → otlmow_template-0.4}/PKG-INFO +2 -2
- {otlmow_template-0.3 → otlmow_template-0.4}/otlmow_template/CsvTemplateCreator.py +21 -25
- otlmow_template-0.4/otlmow_template/SubsetTemplateCreator.py +465 -0
- {otlmow_template-0.3 → otlmow_template-0.4}/otlmow_template.egg-info/PKG-INFO +3 -3
- {otlmow_template-0.3 → otlmow_template-0.4}/pyproject.toml +3 -2
- otlmow_template-0.3/otlmow_template/SubsetTemplateCreator.py +0 -122
- {otlmow_template-0.3 → otlmow_template-0.4}/LICENSE +0 -0
- {otlmow_template-0.3 → otlmow_template-0.4}/README.md +0 -0
- {otlmow_template-0.3 → otlmow_template-0.4}/otlmow_template/ExcelTemplateCreator.py +0 -0
- {otlmow_template-0.3 → otlmow_template-0.4}/otlmow_template/Exceptions/MissingTypeUriException.py +0 -0
- {otlmow_template-0.3 → otlmow_template-0.4}/otlmow_template/__init__.py +0 -0
- {otlmow_template-0.3 → otlmow_template-0.4}/otlmow_template.egg-info/SOURCES.txt +0 -0
- {otlmow_template-0.3 → otlmow_template-0.4}/otlmow_template.egg-info/dependency_links.txt +0 -0
- {otlmow_template-0.3 → otlmow_template-0.4}/otlmow_template.egg-info/requires.txt +0 -0
- {otlmow_template-0.3 → otlmow_template-0.4}/otlmow_template.egg-info/top_level.txt +0 -0
- {otlmow_template-0.3 → otlmow_template-0.4}/setup.cfg +0 -0
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: otlmow_template
|
|
3
|
-
Version: 0.
|
|
4
|
-
Author-email: David Vlaminck <david.vlaminck@mow.vlaanderen.be>
|
|
3
|
+
Version: 0.4
|
|
4
|
+
Author-email: David Vlaminck <david.vlaminck@mow.vlaanderen.be>, Jasper Berton <jasperberton1@telenet.be>
|
|
5
5
|
License: GNU GENERAL PUBLIC LICENSE
|
|
6
6
|
Version 3, 29 June 2007
|
|
7
7
|
|
|
@@ -3,6 +3,7 @@ import ntpath
|
|
|
3
3
|
import os
|
|
4
4
|
import tempfile
|
|
5
5
|
from pathlib import Path
|
|
6
|
+
from typing import List, Sequence, Optional
|
|
6
7
|
|
|
7
8
|
from otlmow_converter.DotnotationHelper import DotnotationHelper
|
|
8
9
|
from otlmow_converter.OtlmowConverter import OtlmowConverter
|
|
@@ -62,8 +63,8 @@ class CsvTemplateCreator:
|
|
|
62
63
|
if add_geo_artefact is False:
|
|
63
64
|
[header, data] = cls.remove_geo_artefact_csv(header=header, data=data)
|
|
64
65
|
if add_attribute_info:
|
|
65
|
-
|
|
66
|
-
|
|
66
|
+
info = cls.add_attribute_info_csv(header=header, data=data,
|
|
67
|
+
instantiated_objects=instantiated_attributes)
|
|
67
68
|
new_file.write(delimiter.join(info) + '\n')
|
|
68
69
|
data = cls.remove_mock_data_csv(data=data, rows_of_examples=amount_of_examples)
|
|
69
70
|
if highlight_deprecated_attributes:
|
|
@@ -75,30 +76,25 @@ class CsvTemplateCreator:
|
|
|
75
76
|
new_file.close()
|
|
76
77
|
|
|
77
78
|
@classmethod
|
|
78
|
-
def add_attribute_info_csv(cls, header, data,
|
|
79
|
+
def add_attribute_info_csv(cls, header: List[str], data: List[List[str]], instantiated_objects: List) -> List[str]:
|
|
79
80
|
info_data = []
|
|
80
81
|
info_data.extend(header)
|
|
81
|
-
|
|
82
|
+
|
|
82
83
|
dotnotation_module = DotnotationHelper()
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
for uri in
|
|
88
|
-
single_object = next(x for x in
|
|
89
|
-
for dotnototation_title in info_data:
|
|
84
|
+
|
|
85
|
+
uri_index = cls.get_type_uri_index_in_row(header)
|
|
86
|
+
found_uris = set(d[uri_index] for d in data)
|
|
87
|
+
|
|
88
|
+
for uri in found_uris:
|
|
89
|
+
single_object = next(x for x in instantiated_objects if x.typeURI == uri)
|
|
90
|
+
for index, dotnototation_title in enumerate(info_data):
|
|
90
91
|
if dotnototation_title == 'typeURI':
|
|
91
|
-
index = info_data.index(dotnototation_title)
|
|
92
92
|
info_data[index] = 'De URI van het object volgens https://www.w3.org/2001/XMLSchema#anyURI .'
|
|
93
93
|
else:
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
dotnotation_attribute = dotnotation_module.get_attribute_by_dotnotation(
|
|
97
|
-
single_object, dotnototation_title)
|
|
98
|
-
except AttributeError as e:
|
|
99
|
-
continue
|
|
94
|
+
dotnotation_attribute = dotnotation_module.get_attribute_by_dotnotation(
|
|
95
|
+
single_object, dotnototation_title)
|
|
100
96
|
info_data[index] = dotnotation_attribute.definition
|
|
101
|
-
return
|
|
97
|
+
return info_data
|
|
102
98
|
|
|
103
99
|
@classmethod
|
|
104
100
|
def remove_mock_data_csv(cls, data, rows_of_examples):
|
|
@@ -110,7 +106,7 @@ class CsvTemplateCreator:
|
|
|
110
106
|
def highlight_deprecated_attributes_csv(cls, header, data, instantiated_attributes):
|
|
111
107
|
found_uri = []
|
|
112
108
|
dotnotation_module = DotnotationHelper()
|
|
113
|
-
uri_index = cls.
|
|
109
|
+
uri_index = cls.get_type_uri_index_in_row(header)
|
|
114
110
|
for d in data:
|
|
115
111
|
if d[uri_index] not in found_uri:
|
|
116
112
|
found_uri.append(d[uri_index])
|
|
@@ -142,11 +138,11 @@ class CsvTemplateCreator:
|
|
|
142
138
|
return header
|
|
143
139
|
|
|
144
140
|
@classmethod
|
|
145
|
-
def
|
|
146
|
-
|
|
147
|
-
|
|
148
|
-
|
|
149
|
-
|
|
141
|
+
def get_type_uri_index_in_row(cls, header: Sequence[str]) -> Optional[int]:
|
|
142
|
+
try:
|
|
143
|
+
return header.index('typeURI')
|
|
144
|
+
except ValueError:
|
|
145
|
+
return None
|
|
150
146
|
|
|
151
147
|
@classmethod
|
|
152
148
|
def remove_geo_artefact_csv(cls, header, data):
|
|
@@ -0,0 +1,465 @@
|
|
|
1
|
+
import ntpath
|
|
2
|
+
import os
|
|
3
|
+
import csv
|
|
4
|
+
import site
|
|
5
|
+
import tempfile
|
|
6
|
+
from pathlib import Path
|
|
7
|
+
from typing import List
|
|
8
|
+
from openpyxl.reader.excel import load_workbook
|
|
9
|
+
from openpyxl.styles import PatternFill
|
|
10
|
+
from openpyxl.utils import get_column_letter
|
|
11
|
+
from openpyxl.worksheet.datavalidation import DataValidation
|
|
12
|
+
from openpyxl.worksheet.dimensions import DimensionHolder, ColumnDimension
|
|
13
|
+
from otlmow_converter.DotnotationHelper import DotnotationHelper
|
|
14
|
+
from otlmow_converter.OtlmowConverter import OtlmowConverter
|
|
15
|
+
from otlmow_model.OtlmowModel.BaseClasses.BooleanField import BooleanField
|
|
16
|
+
from otlmow_model.OtlmowModel.BaseClasses.KeuzelijstField import KeuzelijstField
|
|
17
|
+
from otlmow_model.OtlmowModel.BaseClasses.OTLObject import dynamic_create_instance_from_uri
|
|
18
|
+
from otlmow_modelbuilder.OSLOCollector import OSLOCollector
|
|
19
|
+
|
|
20
|
+
ROOT_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
|
|
21
|
+
|
|
22
|
+
enumeration_validation_rules = {
|
|
23
|
+
"valid_uri_and_types": {},
|
|
24
|
+
"valid_regexes": [
|
|
25
|
+
"^https://wegenenverkeer.data.vlaanderen.be/ns/.+"]
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
class SubsetTemplateCreator:
|
|
30
|
+
def __init__(self):
|
|
31
|
+
pass
|
|
32
|
+
|
|
33
|
+
@staticmethod
|
|
34
|
+
def _load_collector_from_subset_path(path_to_subset: Path) -> OSLOCollector:
|
|
35
|
+
collector = OSLOCollector(path_to_subset)
|
|
36
|
+
collector.collect_all(include_abstract=True)
|
|
37
|
+
return collector
|
|
38
|
+
|
|
39
|
+
def generate_template_from_subset(self, path_to_subset: Path, path_to_template_file_and_extension: Path,
|
|
40
|
+
**kwargs):
|
|
41
|
+
tempdir = Path(tempfile.gettempdir()) / 'temp-otlmow'
|
|
42
|
+
if not tempdir.exists():
|
|
43
|
+
os.makedirs(tempdir)
|
|
44
|
+
test = ntpath.basename(path_to_template_file_and_extension)
|
|
45
|
+
temporary_path = Path(tempdir) / test
|
|
46
|
+
instantiated_attributes = self.generate_basic_template(path_to_subset=path_to_subset,
|
|
47
|
+
temporary_path=temporary_path,
|
|
48
|
+
path_to_template_file_and_extension=path_to_template_file_and_extension,
|
|
49
|
+
**kwargs)
|
|
50
|
+
extension = os.path.splitext(path_to_template_file_and_extension)[-1].lower()
|
|
51
|
+
if extension == '.xlsx':
|
|
52
|
+
self.alter_excel_template(path_to_template_file_and_extension=path_to_template_file_and_extension,
|
|
53
|
+
temporary_path=temporary_path,
|
|
54
|
+
path_to_subset=path_to_subset, instantiated_attributes=instantiated_attributes,
|
|
55
|
+
**kwargs)
|
|
56
|
+
elif extension == '.csv':
|
|
57
|
+
self.determine_multiplicity_csv(path_to_template_file_and_extension=path_to_template_file_and_extension,
|
|
58
|
+
path_to_subset=path_to_subset,
|
|
59
|
+
instantiated_attributes=instantiated_attributes,
|
|
60
|
+
temporary_path=temporary_path,
|
|
61
|
+
**kwargs)
|
|
62
|
+
|
|
63
|
+
def generate_basic_template(self, path_to_subset: Path, path_to_template_file_and_extension: Path,
|
|
64
|
+
temporary_path: Path, **kwargs):
|
|
65
|
+
collector = self._load_collector_from_subset_path(path_to_subset=path_to_subset)
|
|
66
|
+
otl_objects = []
|
|
67
|
+
amount_of_examples = kwargs.get('amount_of_examples', 0)
|
|
68
|
+
|
|
69
|
+
for class_object in list(filter(lambda cl: cl.abstract == 0, collector.classes)):
|
|
70
|
+
model_directory = None
|
|
71
|
+
if kwargs is not None:
|
|
72
|
+
model_directory = kwargs.get('model_directory', None)
|
|
73
|
+
if amount_of_examples != 0:
|
|
74
|
+
for i in range(amount_of_examples):
|
|
75
|
+
instance = dynamic_create_instance_from_uri(class_object.objectUri, model_directory=model_directory)
|
|
76
|
+
if instance is None:
|
|
77
|
+
continue
|
|
78
|
+
instance.fill_with_dummy_data()
|
|
79
|
+
otl_objects.append(instance)
|
|
80
|
+
else:
|
|
81
|
+
instance = dynamic_create_instance_from_uri(class_object.objectUri, model_directory=model_directory)
|
|
82
|
+
if instance is None:
|
|
83
|
+
continue
|
|
84
|
+
instance.fill_with_dummy_data()
|
|
85
|
+
otl_objects.append(instance)
|
|
86
|
+
|
|
87
|
+
# TODO: check if this is needed, as the above line should cover this
|
|
88
|
+
attributen = collector.find_attributes_by_class(class_object)
|
|
89
|
+
for attribute_object in attributen:
|
|
90
|
+
attr = getattr(instance, '_' + attribute_object.name)
|
|
91
|
+
attr.fill_with_dummy_data()
|
|
92
|
+
converter = OtlmowConverter()
|
|
93
|
+
converter.from_objects_to_file(file_path=temporary_path,
|
|
94
|
+
sequence_of_objects=otl_objects, **kwargs)
|
|
95
|
+
path_is_split = kwargs.get('split_per_type', True)
|
|
96
|
+
extension = os.path.splitext(path_to_template_file_and_extension)[-1].lower()
|
|
97
|
+
instantiated_attributes = []
|
|
98
|
+
if path_is_split is False or extension == '.xlsx':
|
|
99
|
+
instantiated_attributes = converter.from_file_to_objects(file_path=temporary_path,
|
|
100
|
+
path_to_subset=path_to_subset)
|
|
101
|
+
return instantiated_attributes
|
|
102
|
+
|
|
103
|
+
@classmethod
|
|
104
|
+
def alter_excel_template(cls, path_to_template_file_and_extension: Path, path_to_subset: Path,
|
|
105
|
+
instantiated_attributes: List, temporary_path, **kwargs):
|
|
106
|
+
generate_choice_list = kwargs.get('generate_choice_list', False)
|
|
107
|
+
add_geo_artefact = kwargs.get('add_geo_artefact', False)
|
|
108
|
+
add_attribute_info = kwargs.get('add_attribute_info', False)
|
|
109
|
+
highlight_deprecated_attributes = kwargs.get('highlight_deprecated_attributes', False)
|
|
110
|
+
amount_of_examples = kwargs.get('amount_of_examples', 0)
|
|
111
|
+
wb = load_workbook(temporary_path)
|
|
112
|
+
wb.create_sheet('Keuzelijsten')
|
|
113
|
+
# Volgorde is belangrijk! Eerst rijen verwijderen indien nodig dan choice list toevoegen,
|
|
114
|
+
# staat namelijk vast op de kolom en niet het attribuut in die kolom
|
|
115
|
+
if add_geo_artefact is False:
|
|
116
|
+
cls.remove_geo_artefact_excel(workbook=wb)
|
|
117
|
+
if generate_choice_list:
|
|
118
|
+
cls.add_choice_list_excel(workbook=wb, instantiated_attributes=instantiated_attributes,
|
|
119
|
+
path_to_subset=path_to_subset)
|
|
120
|
+
cls.add_mock_data_excel(workbook=wb, rows_of_examples=amount_of_examples)
|
|
121
|
+
if highlight_deprecated_attributes:
|
|
122
|
+
cls.check_for_deprecated_attributes(workbook=wb, instantiated_attributes=instantiated_attributes)
|
|
123
|
+
if add_attribute_info:
|
|
124
|
+
cls.add_attribute_info_excel(workbook=wb, instantiated_attributes=instantiated_attributes)
|
|
125
|
+
cls.design_workbook_excel(workbook=wb)
|
|
126
|
+
wb.save(path_to_template_file_and_extension)
|
|
127
|
+
file_location = os.path.dirname(temporary_path)
|
|
128
|
+
[f.unlink() for f in Path(file_location).glob("*") if f.is_file()]
|
|
129
|
+
|
|
130
|
+
def determine_multiplicity_csv(self, path_to_template_file_and_extension: Path, path_to_subset: Path,
|
|
131
|
+
instantiated_attributes: List, temporary_path: Path, **kwargs):
|
|
132
|
+
path_is_split = kwargs.get('split_per_type', True)
|
|
133
|
+
if path_is_split is False:
|
|
134
|
+
self.alter_csv_template(path_to_template_file_and_extension=path_to_template_file_and_extension,
|
|
135
|
+
temporary_path=temporary_path, path_to_subset=path_to_subset, **kwargs)
|
|
136
|
+
else:
|
|
137
|
+
self.multiple_csv_template(path_to_template_file_and_extension=path_to_template_file_and_extension,
|
|
138
|
+
temporary_path=temporary_path,
|
|
139
|
+
path_to_subset=path_to_subset, instantiated_attributes=instantiated_attributes,
|
|
140
|
+
**kwargs)
|
|
141
|
+
file_location = os.path.dirname(temporary_path)
|
|
142
|
+
[f.unlink() for f in Path(file_location).glob("*") if f.is_file()]
|
|
143
|
+
|
|
144
|
+
@classmethod
|
|
145
|
+
def filters_assets_by_subset(cls, path_to_subset: Path, list_of_otl_objectUri: [str] = None):
|
|
146
|
+
if list_of_otl_objectUri is None:
|
|
147
|
+
list_of_otl_objectUri = []
|
|
148
|
+
|
|
149
|
+
collector = cls._load_collector_from_subset_path(path_to_subset=path_to_subset)
|
|
150
|
+
if list_of_otl_objectUri == []:
|
|
151
|
+
return [x for x in collector.classes]
|
|
152
|
+
return [x for x in collector.classes if x.objectUri in list_of_otl_objectUri]
|
|
153
|
+
|
|
154
|
+
@staticmethod
|
|
155
|
+
def _try_getting_settings_of_converter() -> Path:
|
|
156
|
+
converter_path = Path(site.getsitepackages()[0]) / 'otlmow_converter'
|
|
157
|
+
return converter_path / 'settings_otlmow_converter.json'
|
|
158
|
+
|
|
159
|
+
@classmethod
|
|
160
|
+
def design_workbook_excel(cls, workbook):
|
|
161
|
+
for sheet in workbook:
|
|
162
|
+
dim_holder = DimensionHolder(worksheet=sheet)
|
|
163
|
+
for col in range(sheet.min_column, sheet.max_column + 1):
|
|
164
|
+
dim_holder[get_column_letter(col)] = ColumnDimension(sheet, min=col, max=col, width=20)
|
|
165
|
+
sheet.column_dimensions = dim_holder
|
|
166
|
+
|
|
167
|
+
@classmethod
|
|
168
|
+
def add_attribute_info_excel(cls, workbook, instantiated_attributes: List):
|
|
169
|
+
dotnotation_module = DotnotationHelper()
|
|
170
|
+
for sheet in workbook:
|
|
171
|
+
if sheet == workbook['Keuzelijsten']:
|
|
172
|
+
break
|
|
173
|
+
filter_uri = SubsetTemplateCreator.find_uri_in_sheet(sheet)
|
|
174
|
+
single_attribute = next(x for x in instantiated_attributes if x.typeURI == filter_uri)
|
|
175
|
+
sheet.insert_rows(1)
|
|
176
|
+
for rows in sheet.iter_rows(min_row=2, max_row=2, min_col=1):
|
|
177
|
+
for cell in rows:
|
|
178
|
+
if cell.value == 'typeURI':
|
|
179
|
+
value = 'De URI van het object volgens https://www.w3.org/2001/XMLSchema#anyURI .'
|
|
180
|
+
elif cell.value.find('[DEPRECATED]') != -1:
|
|
181
|
+
strip = cell.value.split(' ')
|
|
182
|
+
dotnotation_attribute = dotnotation_module.get_attribute_by_dotnotation(single_attribute,
|
|
183
|
+
strip[1])
|
|
184
|
+
value = dotnotation_attribute.definition
|
|
185
|
+
else:
|
|
186
|
+
dotnotation_attribute = dotnotation_module.get_attribute_by_dotnotation(single_attribute,
|
|
187
|
+
cell.value)
|
|
188
|
+
value = dotnotation_attribute.definition
|
|
189
|
+
|
|
190
|
+
sheet.cell(row=1, column=cell.column, value=value)
|
|
191
|
+
sheet.cell(row=1, column=cell.column).fill = PatternFill(start_color="808080", end_color="808080",
|
|
192
|
+
fill_type="solid")
|
|
193
|
+
|
|
194
|
+
@classmethod
|
|
195
|
+
def check_for_deprecated_attributes(cls, workbook, instantiated_attributes: List):
|
|
196
|
+
dotnotation_module = DotnotationHelper()
|
|
197
|
+
for sheet in workbook:
|
|
198
|
+
if sheet == workbook['Keuzelijsten']:
|
|
199
|
+
break
|
|
200
|
+
filter_uri = SubsetTemplateCreator.find_uri_in_sheet(sheet)
|
|
201
|
+
single_attribute = next(x for x in instantiated_attributes if x.typeURI == filter_uri)
|
|
202
|
+
for rows in sheet.iter_rows(min_row=1, max_row=1, min_col=2):
|
|
203
|
+
for cell in rows:
|
|
204
|
+
is_deprecated = False
|
|
205
|
+
if cell.value.count('.') == 1:
|
|
206
|
+
dot_split = cell.value.split('.')
|
|
207
|
+
attribute = dotnotation_module.get_attribute_by_dotnotation(single_attribute,
|
|
208
|
+
dot_split[0])
|
|
209
|
+
|
|
210
|
+
if len(attribute.deprecated_version) > 0:
|
|
211
|
+
is_deprecated = True
|
|
212
|
+
dotnotation_attribute = dotnotation_module.get_attribute_by_dotnotation(single_attribute,
|
|
213
|
+
cell.value)
|
|
214
|
+
if len(dotnotation_attribute.deprecated_version) > 0:
|
|
215
|
+
is_deprecated = True
|
|
216
|
+
|
|
217
|
+
if is_deprecated:
|
|
218
|
+
cell.value = '[DEPRECATED] ' + cell.value
|
|
219
|
+
|
|
220
|
+
@classmethod
|
|
221
|
+
def find_uri_in_sheet(cls, sheet):
|
|
222
|
+
filter_uri = None
|
|
223
|
+
for row in sheet.iter_rows(min_row=1, max_row=1):
|
|
224
|
+
for cell in row:
|
|
225
|
+
if cell.value == 'typeURI':
|
|
226
|
+
row_index = cell.row
|
|
227
|
+
column_index = cell.column
|
|
228
|
+
filter_uri = sheet.cell(row=row_index + 1, column=column_index).value
|
|
229
|
+
return filter_uri
|
|
230
|
+
|
|
231
|
+
@classmethod
|
|
232
|
+
def remove_geo_artefact_excel(cls, workbook):
|
|
233
|
+
for sheet in workbook:
|
|
234
|
+
for row in sheet.iter_rows(min_row=1, max_row=1):
|
|
235
|
+
for cell in row:
|
|
236
|
+
if cell.value == 'geometry':
|
|
237
|
+
sheet.delete_cols(cell.column)
|
|
238
|
+
|
|
239
|
+
@classmethod
|
|
240
|
+
def add_choice_list_excel(cls, workbook, instantiated_attributes: List, path_to_subset: Path):
|
|
241
|
+
choice_list_dict = {}
|
|
242
|
+
dotnotation_module = DotnotationHelper()
|
|
243
|
+
for sheet in workbook:
|
|
244
|
+
if sheet == workbook['Keuzelijsten']:
|
|
245
|
+
break
|
|
246
|
+
filter_uri = SubsetTemplateCreator.find_uri_in_sheet(sheet)
|
|
247
|
+
single_attribute = next(x for x in instantiated_attributes if x.typeURI == filter_uri)
|
|
248
|
+
for rows in sheet.iter_rows(min_row=1, max_row=1, min_col=2):
|
|
249
|
+
for cell in rows:
|
|
250
|
+
if cell.value.find('[DEPRECATED]') != -1:
|
|
251
|
+
strip = cell.value.split(' ')
|
|
252
|
+
dotnotation_attribute = dotnotation_module.get_attribute_by_dotnotation(single_attribute,
|
|
253
|
+
strip[1])
|
|
254
|
+
else:
|
|
255
|
+
dotnotation_attribute = dotnotation_module.get_attribute_by_dotnotation(single_attribute,
|
|
256
|
+
cell.value)
|
|
257
|
+
|
|
258
|
+
if issubclass(dotnotation_attribute.field, KeuzelijstField):
|
|
259
|
+
name = dotnotation_attribute.field.naam
|
|
260
|
+
valid_options = [v.invulwaarde for k, v in dotnotation_attribute.field.options.items()
|
|
261
|
+
if v.status != 'verwijderd']
|
|
262
|
+
if dotnotation_attribute.field.naam in choice_list_dict:
|
|
263
|
+
column = choice_list_dict[dotnotation_attribute.field.naam]
|
|
264
|
+
else:
|
|
265
|
+
choice_list_dict = cls.add_choice_list_to_sheet(workbook=workbook, name=name,
|
|
266
|
+
options=valid_options,
|
|
267
|
+
choice_list_dict=choice_list_dict)
|
|
268
|
+
column = choice_list_dict[dotnotation_attribute.field.naam]
|
|
269
|
+
print(column)
|
|
270
|
+
option_list = []
|
|
271
|
+
for option in valid_options:
|
|
272
|
+
option_list.append(option)
|
|
273
|
+
start_range = f"${column}$2"
|
|
274
|
+
end_range = f"${column}${len(valid_options) + 1}"
|
|
275
|
+
data_val = DataValidation(type="list", formula1=f"Keuzelijsten!{start_range}:{end_range}",
|
|
276
|
+
allowBlank=True)
|
|
277
|
+
sheet.add_data_validation(data_val)
|
|
278
|
+
data_val.add(f'{get_column_letter(cell.column)}2:{get_column_letter(cell.column)}1000')
|
|
279
|
+
if issubclass(dotnotation_attribute.field, BooleanField):
|
|
280
|
+
data_validation = DataValidation(type="list", formula1='"TRUE,FALSE,-"', allow_blank=True)
|
|
281
|
+
column = cell.column
|
|
282
|
+
sheet.add_data_validation(data_validation)
|
|
283
|
+
data_validation.add(f'{get_column_letter(column)}2:{get_column_letter(column)}1000')
|
|
284
|
+
sheet.add_data_validation(data_validation)
|
|
285
|
+
|
|
286
|
+
@classmethod
|
|
287
|
+
def add_mock_data_excel(cls, workbook, rows_of_examples: int):
|
|
288
|
+
for sheet in workbook:
|
|
289
|
+
if sheet == workbook["Keuzelijsten"]:
|
|
290
|
+
break
|
|
291
|
+
if rows_of_examples == 0:
|
|
292
|
+
for rows in sheet.iter_rows(min_row=2, max_row=2):
|
|
293
|
+
for cell in rows:
|
|
294
|
+
cell.value = ''
|
|
295
|
+
|
|
296
|
+
@classmethod
|
|
297
|
+
def remove_geo_artefact_csv(cls, header, data):
|
|
298
|
+
if 'geometry' in header:
|
|
299
|
+
deletion_index = header.index('geometry')
|
|
300
|
+
header.remove('geometry')
|
|
301
|
+
for d in data:
|
|
302
|
+
d.pop(deletion_index)
|
|
303
|
+
return [header, data]
|
|
304
|
+
|
|
305
|
+
@classmethod
|
|
306
|
+
def multiple_csv_template(cls, path_to_template_file_and_extension, path_to_subset, temporary_path,
|
|
307
|
+
instantiated_attributes, **kwargs):
|
|
308
|
+
file_location = os.path.dirname(path_to_template_file_and_extension)
|
|
309
|
+
tempdir = Path(tempfile.gettempdir()) / 'temp-otlmow'
|
|
310
|
+
print(file_location)
|
|
311
|
+
file_name = ntpath.basename(path_to_template_file_and_extension)
|
|
312
|
+
split_file_name = file_name.split('.')
|
|
313
|
+
things_in_there = os.listdir(tempdir)
|
|
314
|
+
csv_templates = [x for x in things_in_there if x.startswith(split_file_name[0] + '_')]
|
|
315
|
+
print(csv_templates)
|
|
316
|
+
for file in csv_templates:
|
|
317
|
+
test_template_loc = Path(os.path.dirname(path_to_template_file_and_extension)) / file
|
|
318
|
+
temp_loc = Path(tempdir) / file
|
|
319
|
+
cls.alter_csv_template(path_to_template_file_and_extension=test_template_loc, temporary_path=temp_loc,
|
|
320
|
+
path_to_subset=path_to_subset, **kwargs)
|
|
321
|
+
|
|
322
|
+
@classmethod
|
|
323
|
+
def alter_csv_template(cls, path_to_template_file_and_extension, path_to_subset, temporary_path,
|
|
324
|
+
**kwargs):
|
|
325
|
+
converter = OtlmowConverter()
|
|
326
|
+
instantiated_attributes = converter.from_file_to_objects(file_path=temporary_path,
|
|
327
|
+
path_to_subset=path_to_subset)
|
|
328
|
+
header = []
|
|
329
|
+
data = []
|
|
330
|
+
delimiter = ';'
|
|
331
|
+
add_geo_artefact = kwargs.get('add_geo_artefact', False)
|
|
332
|
+
add_attribute_info = kwargs.get('add_attribute_info', False)
|
|
333
|
+
highlight_deprecated_attributes = kwargs.get('highlight_deprecated_attributes', False)
|
|
334
|
+
amount_of_examples = kwargs.get('amount_of_examples', 0)
|
|
335
|
+
quote_char = '"'
|
|
336
|
+
with open(temporary_path, 'r+', encoding='utf-8') as csvfile:
|
|
337
|
+
new_file = open(path_to_template_file_and_extension, 'w', encoding='utf-8')
|
|
338
|
+
reader = csv.reader(csvfile, delimiter=delimiter, quotechar=quote_char)
|
|
339
|
+
for row_nr, row in enumerate(reader):
|
|
340
|
+
if row_nr == 0:
|
|
341
|
+
header = row
|
|
342
|
+
else:
|
|
343
|
+
data.append(row)
|
|
344
|
+
if add_geo_artefact is False:
|
|
345
|
+
[header, data] = cls.remove_geo_artefact_csv(header=header, data=data)
|
|
346
|
+
if add_attribute_info:
|
|
347
|
+
[info, header] = cls.add_attribute_info_csv(header=header, data=data,
|
|
348
|
+
instantiated_attributes=instantiated_attributes)
|
|
349
|
+
new_file.write(delimiter.join(info) + '\n')
|
|
350
|
+
data = cls.add_mock_data_csv(header=header, data=data, rows_of_examples=amount_of_examples)
|
|
351
|
+
if highlight_deprecated_attributes:
|
|
352
|
+
header = cls.highlight_deprecated_attributes_csv(header=header, data=data,
|
|
353
|
+
instantiated_attributes=instantiated_attributes)
|
|
354
|
+
new_file.write(delimiter.join(header) + '\n')
|
|
355
|
+
for d in data:
|
|
356
|
+
new_file.write(delimiter.join(d) + '\n')
|
|
357
|
+
new_file.close()
|
|
358
|
+
|
|
359
|
+
@classmethod
|
|
360
|
+
def add_attribute_info_csv(cls, header, data, instantiated_attributes):
|
|
361
|
+
info_data = []
|
|
362
|
+
info_data.extend(header)
|
|
363
|
+
found_uri = []
|
|
364
|
+
dotnotation_module = DotnotationHelper()
|
|
365
|
+
uri_index = cls.find_uri_in_csv(header)
|
|
366
|
+
for d in data:
|
|
367
|
+
if d[uri_index] not in found_uri:
|
|
368
|
+
found_uri.append(d[uri_index])
|
|
369
|
+
for uri in found_uri:
|
|
370
|
+
single_object = next(x for x in instantiated_attributes if x.typeURI == uri)
|
|
371
|
+
for dotnototation_title in info_data:
|
|
372
|
+
if dotnototation_title == 'typeURI':
|
|
373
|
+
index = info_data.index(dotnototation_title)
|
|
374
|
+
info_data[index] = 'De URI van het object volgens https://www.w3.org/2001/XMLSchema#anyURI .'
|
|
375
|
+
else:
|
|
376
|
+
index = info_data.index(dotnototation_title)
|
|
377
|
+
try:
|
|
378
|
+
dotnotation_attribute = dotnotation_module.get_attribute_by_dotnotation(
|
|
379
|
+
single_object, dotnototation_title)
|
|
380
|
+
except AttributeError as e:
|
|
381
|
+
continue
|
|
382
|
+
info_data[index] = dotnotation_attribute.definition
|
|
383
|
+
return [info_data, header]
|
|
384
|
+
|
|
385
|
+
@classmethod
|
|
386
|
+
def add_mock_data_csv(cls, header, data, rows_of_examples):
|
|
387
|
+
if rows_of_examples == 0:
|
|
388
|
+
data = []
|
|
389
|
+
return data
|
|
390
|
+
|
|
391
|
+
@classmethod
|
|
392
|
+
def highlight_deprecated_attributes_csv(cls, header, data, instantiated_attributes):
|
|
393
|
+
found_uri = []
|
|
394
|
+
dotnotation_module = DotnotationHelper()
|
|
395
|
+
uri_index = cls.find_uri_in_csv(header)
|
|
396
|
+
for d in data:
|
|
397
|
+
if d[uri_index] not in found_uri:
|
|
398
|
+
found_uri.append(d[uri_index])
|
|
399
|
+
for uri in found_uri:
|
|
400
|
+
single_object = next(x for x in instantiated_attributes if x.typeURI == uri)
|
|
401
|
+
for dotnototation_title in header:
|
|
402
|
+
if dotnototation_title == 'typeURI':
|
|
403
|
+
continue
|
|
404
|
+
else:
|
|
405
|
+
index = header.index(dotnototation_title)
|
|
406
|
+
value = header[index]
|
|
407
|
+
try:
|
|
408
|
+
is_deprecated = False
|
|
409
|
+
if dotnototation_title.count('.') == 1:
|
|
410
|
+
dot_split = dotnototation_title.split('.')
|
|
411
|
+
attribute = dotnotation_module.get_attribute_by_dotnotation(single_object,
|
|
412
|
+
dot_split[0])
|
|
413
|
+
|
|
414
|
+
if len(attribute.deprecated_version) > 0:
|
|
415
|
+
is_deprecated = True
|
|
416
|
+
dotnotation_attribute = dotnotation_module.get_attribute_by_dotnotation(single_object,
|
|
417
|
+
dotnototation_title)
|
|
418
|
+
if len(dotnotation_attribute.deprecated_version) > 0:
|
|
419
|
+
is_deprecated = True
|
|
420
|
+
except AttributeError:
|
|
421
|
+
continue
|
|
422
|
+
if is_deprecated:
|
|
423
|
+
header[index] = "[DEPRECATED] " + value
|
|
424
|
+
return header
|
|
425
|
+
|
|
426
|
+
@classmethod
|
|
427
|
+
def find_uri_in_csv(cls, header):
|
|
428
|
+
filter_uri = None
|
|
429
|
+
if 'typeURI' in header:
|
|
430
|
+
filter_uri = header.index('typeURI')
|
|
431
|
+
return filter_uri
|
|
432
|
+
|
|
433
|
+
@classmethod
|
|
434
|
+
def add_choice_list_to_sheet(cls, workbook, name, options, choice_list_dict):
|
|
435
|
+
active_sheet = workbook['Keuzelijsten']
|
|
436
|
+
print(options)
|
|
437
|
+
row_nr = 2
|
|
438
|
+
for rows in active_sheet.iter_rows(min_row=1, max_row=1, min_col=1, max_col=700):
|
|
439
|
+
for cell in rows:
|
|
440
|
+
if cell.value is None:
|
|
441
|
+
cell.value = name
|
|
442
|
+
column_nr = cell.column
|
|
443
|
+
for option in options:
|
|
444
|
+
print(option)
|
|
445
|
+
active_sheet.cell(row=row_nr, column=column_nr, value=option)
|
|
446
|
+
row_nr += 1
|
|
447
|
+
print(row_nr)
|
|
448
|
+
choice_list_dict[name] = get_column_letter(column_nr)
|
|
449
|
+
break
|
|
450
|
+
return choice_list_dict
|
|
451
|
+
|
|
452
|
+
|
|
453
|
+
if __name__ == '__main__':
|
|
454
|
+
subset_tool = SubsetTemplateCreator()
|
|
455
|
+
subset_location = Path(ROOT_DIR) / 'UnitTests' / 'Subset' / 'Flitspaal_noAgent3.0.db'
|
|
456
|
+
# directory = Path(ROOT_DIR) / 'UnitTests' / 'TestClasses'
|
|
457
|
+
# Slash op het einde toevoegen verandert weinig of niks aan het resultaat
|
|
458
|
+
# directory = os.path.join(directory, '')
|
|
459
|
+
xls_location = Path(ROOT_DIR) / 'UnitTests' / 'Subset' / 'testFileStorage' / 'template_file.csv'
|
|
460
|
+
subset_tool.generate_template_from_subset(path_to_subset=subset_location,
|
|
461
|
+
path_to_template_file_and_extension=xls_location, add_attribute_info=True,
|
|
462
|
+
highlight_deprecated_attributes=True,
|
|
463
|
+
amount_of_examples=5,
|
|
464
|
+
generate_choice_list=True,
|
|
465
|
+
split_per_type=False)
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
|
-
Name:
|
|
3
|
-
Version: 0.
|
|
4
|
-
Author-email: David Vlaminck <david.vlaminck@mow.vlaanderen.be>
|
|
2
|
+
Name: otlmow_template
|
|
3
|
+
Version: 0.4
|
|
4
|
+
Author-email: David Vlaminck <david.vlaminck@mow.vlaanderen.be>, Jasper Berton <jasperberton1@telenet.be>
|
|
5
5
|
License: GNU GENERAL PUBLIC LICENSE
|
|
6
6
|
Version 3, 29 June 2007
|
|
7
7
|
|
|
@@ -4,8 +4,9 @@ build-backend = "setuptools.build_meta"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "otlmow_template"
|
|
7
|
-
version = "0.
|
|
8
|
-
authors = [{name = "David Vlaminck", email = "david.vlaminck@mow.vlaanderen.be"}
|
|
7
|
+
version = "0.4"
|
|
8
|
+
authors = [{name = "David Vlaminck", email = "david.vlaminck@mow.vlaanderen.be"},
|
|
9
|
+
{name = "Jasper Berton", email = "jasperberton1@telenet.be"}]
|
|
9
10
|
readme = "README.md"
|
|
10
11
|
license = {file = "LICENSE"}
|
|
11
12
|
classifiers = [
|
|
@@ -1,122 +0,0 @@
|
|
|
1
|
-
import ntpath
|
|
2
|
-
import os
|
|
3
|
-
import site
|
|
4
|
-
import tempfile
|
|
5
|
-
from pathlib import Path
|
|
6
|
-
from otlmow_converter.OtlmowConverter import OtlmowConverter
|
|
7
|
-
from otlmow_model.OtlmowModel.Helpers.AssetCreator import dynamic_create_instance_from_uri
|
|
8
|
-
from otlmow_modelbuilder.OSLOCollector import OSLOCollector
|
|
9
|
-
|
|
10
|
-
from otlmow_template.CsvTemplateCreator import CsvTemplateCreator
|
|
11
|
-
from otlmow_template.ExcelTemplateCreator import ExcelTemplateCreator
|
|
12
|
-
|
|
13
|
-
ROOT_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
|
|
14
|
-
|
|
15
|
-
enumeration_validation_rules = {
|
|
16
|
-
"valid_uri_and_types": {},
|
|
17
|
-
"valid_regexes": [
|
|
18
|
-
"^https://wegenenverkeer.data.vlaanderen.be/ns/.+"]
|
|
19
|
-
}
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
class SubsetTemplateCreator:
|
|
23
|
-
def __init__(self):
|
|
24
|
-
pass
|
|
25
|
-
|
|
26
|
-
@staticmethod
|
|
27
|
-
def _load_collector_from_subset_path(path_to_subset: Path) -> OSLOCollector:
|
|
28
|
-
collector = OSLOCollector(path_to_subset)
|
|
29
|
-
collector.collect_all(include_abstract=True)
|
|
30
|
-
return collector
|
|
31
|
-
|
|
32
|
-
def generate_template_from_subset(self, path_to_subset: Path, path_to_template_file_and_extension: Path,
|
|
33
|
-
**kwargs):
|
|
34
|
-
temporary_path = self.return_temp_path(path_to_template_file_and_extension=path_to_template_file_and_extension)
|
|
35
|
-
instantiated_attributes = self.generate_basic_template(path_to_subset=path_to_subset,
|
|
36
|
-
temporary_path=temporary_path,
|
|
37
|
-
path_to_template_file_and_extension=path_to_template_file_and_extension,
|
|
38
|
-
**kwargs)
|
|
39
|
-
extension = os.path.splitext(path_to_template_file_and_extension)[-1].lower()
|
|
40
|
-
if extension == '.xlsx':
|
|
41
|
-
ExcelTemplateCreator().alter_excel_template(
|
|
42
|
-
path_to_template_file_and_extension=path_to_template_file_and_extension,
|
|
43
|
-
temporary_path=temporary_path, instantiated_attributes=instantiated_attributes, **kwargs)
|
|
44
|
-
elif extension == '.csv':
|
|
45
|
-
CsvTemplateCreator().determine_multiplicity_csv(
|
|
46
|
-
path_to_template_file_and_extension=path_to_template_file_and_extension,
|
|
47
|
-
path_to_subset=path_to_subset,
|
|
48
|
-
temporary_path=temporary_path,
|
|
49
|
-
**kwargs)
|
|
50
|
-
|
|
51
|
-
def generate_basic_template(self, path_to_subset: Path, path_to_template_file_and_extension: Path,
|
|
52
|
-
temporary_path: Path, **kwargs):
|
|
53
|
-
collector = self._load_collector_from_subset_path(path_to_subset=path_to_subset)
|
|
54
|
-
otl_objects = []
|
|
55
|
-
amount_of_examples = kwargs.get('amount_of_examples', 0)
|
|
56
|
-
class_list = self.filters_assets_by_subset(path_to_subset=path_to_subset, **kwargs)
|
|
57
|
-
|
|
58
|
-
for class_object in list(class_list):
|
|
59
|
-
model_directory = None
|
|
60
|
-
if kwargs is not None:
|
|
61
|
-
model_directory = kwargs.get('model_directory', None)
|
|
62
|
-
if amount_of_examples != 0:
|
|
63
|
-
for i in range(amount_of_examples):
|
|
64
|
-
instance = dynamic_create_instance_from_uri(class_object.objectUri, model_directory=model_directory)
|
|
65
|
-
if instance is None:
|
|
66
|
-
continue
|
|
67
|
-
instance.fill_with_dummy_data()
|
|
68
|
-
otl_objects.append(instance)
|
|
69
|
-
else:
|
|
70
|
-
instance = dynamic_create_instance_from_uri(class_object.objectUri, model_directory=model_directory)
|
|
71
|
-
if instance is None:
|
|
72
|
-
continue
|
|
73
|
-
instance.fill_with_dummy_data()
|
|
74
|
-
otl_objects.append(instance)
|
|
75
|
-
|
|
76
|
-
converter = OtlmowConverter()
|
|
77
|
-
converter.create_file_from_assets(filepath=temporary_path,
|
|
78
|
-
list_of_objects=otl_objects, **kwargs)
|
|
79
|
-
path_is_split = kwargs.get('split_per_type', True)
|
|
80
|
-
extension = os.path.splitext(path_to_template_file_and_extension)[-1].lower()
|
|
81
|
-
instantiated_attributes = []
|
|
82
|
-
if path_is_split is False or extension == '.xlsx':
|
|
83
|
-
instantiated_attributes = converter.create_assets_from_file(filepath=temporary_path,
|
|
84
|
-
path_to_subset=path_to_subset)
|
|
85
|
-
return instantiated_attributes
|
|
86
|
-
|
|
87
|
-
@classmethod
|
|
88
|
-
def filters_assets_by_subset(cls, path_to_subset: Path, **kwargs):
|
|
89
|
-
list_of_otl_object_uri = kwargs.get('list_of_otl_objectUri', None)
|
|
90
|
-
collector = cls._load_collector_from_subset_path(path_to_subset=path_to_subset)
|
|
91
|
-
if list_of_otl_object_uri is None:
|
|
92
|
-
return [x for x in collector.classes if x.abstract == 0]
|
|
93
|
-
else:
|
|
94
|
-
collector = cls._load_collector_from_subset_path(path_to_subset=path_to_subset)
|
|
95
|
-
filtered_list = [x for x in collector.classes if x.objectUri in list_of_otl_object_uri]
|
|
96
|
-
return filtered_list
|
|
97
|
-
|
|
98
|
-
@staticmethod
|
|
99
|
-
def _try_getting_settings_of_converter() -> Path:
|
|
100
|
-
converter_path = Path(site.getsitepackages()[0]) / 'otlmow_converter'
|
|
101
|
-
return converter_path / 'settings_otlmow_converter.json'
|
|
102
|
-
|
|
103
|
-
@classmethod
|
|
104
|
-
def return_temp_path(cls, path_to_template_file_and_extension: Path):
|
|
105
|
-
tempdir = Path(tempfile.gettempdir()) / 'temp-otlmow'
|
|
106
|
-
if not tempdir.exists():
|
|
107
|
-
os.makedirs(tempdir)
|
|
108
|
-
test = ntpath.basename(path_to_template_file_and_extension)
|
|
109
|
-
temporary_path = Path(tempdir) / test
|
|
110
|
-
return temporary_path
|
|
111
|
-
|
|
112
|
-
|
|
113
|
-
if __name__ == '__main__':
|
|
114
|
-
subset_tool = SubsetTemplateCreator()
|
|
115
|
-
subset_location = Path(ROOT_DIR) / 'UnitTests' / 'Subset' / 'Flitspaal_noAgent3.0.db'
|
|
116
|
-
xls_location = Path(ROOT_DIR) / 'UnitTests' / 'Subset' / 'testFileStorage' / 'template_file.xlsx'
|
|
117
|
-
subset_tool.generate_template_from_subset(path_to_subset=subset_location,
|
|
118
|
-
path_to_template_file_and_extension=xls_location, add_attribute_info=True,
|
|
119
|
-
highlight_deprecated_attributes=True,
|
|
120
|
-
amount_of_examples=5,
|
|
121
|
-
generate_choice_list=True,
|
|
122
|
-
)
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{otlmow_template-0.3 → otlmow_template-0.4}/otlmow_template/Exceptions/MissingTypeUriException.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|