Newer
Older
# encoding: utf-8
#
# This file is a part of the LinkAhead Project.
#
# Copyright (C) 2024 Indiscale GmbH <info@indiscale.com>
# Copyright (C) 2024 Henrik tom Wörden <h.tomwoerden@indiscale.com>
# Copyright (C) 2024 Daniel Hornung <d.hornung@indiscale.com>
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as
# published by the Free Software Foundation, either version 3 of the
# License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
import os
import tempfile
import jsonschema.exceptions as schema_exc
import pytest
from openpyxl import load_workbook
from caosadvancedtools.table_json_conversion import xlsx_utils
from caosadvancedtools.table_json_conversion.fill_xlsx import fill_template
from caosadvancedtools.table_json_conversion.xlsx_utils import (
get_row_type_column_index,
get_path_rows,
)
def rfp(*pathcomponents):
"""
Return full path.
Shorthand convenience function.
"""
return os.path.join(os.path.dirname(__file__), *pathcomponents)
def fill_and_compare(json_file: str, template_file: str, known_good: str,
schema: str = None, custom_output: str = None):
"""Fill the data into a template and compare to a known good.
Parameters:
-----------
schema: str, optional,
Json schema to validate against.
custom_output: str, optional
If given, write to this file and drop into an IPython shell. For development only.
"""
with tempfile.TemporaryDirectory() as tmpdir:
outfile = os.path.join(tmpdir, 'test.xlsx')
assert not os.path.exists(outfile)
if custom_output is not None:
outfile = custom_output
fill_template(data=json_file, template=template_file, result=outfile,
validation_schema=schema)
assert os.path.exists(outfile)
generated = load_workbook(outfile) # workbook can be read
known_good_wb = load_workbook(known_good)
compare_workbooks(generated, known_good_wb)
def test_detect():
example = load_workbook(rfp("data/simple_template.xlsx"))
assert 0 == get_row_type_column_index(example['Person'])
assert [1, 2] == get_path_rows(example['Person'])
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
def test_temporary():
# TODO: remove the following after manual testing
di = '/home/henrik/CaosDB/management/external/dimr/eingabemaske/crawler/schemas'
dd = '/home/henrik/CaosDB/management/external/dimr/eingabemaske/django/laforms/persistent/'
allreadydone = [
"Präventionsmaßnahmen",
"Beratungsstellen",
"Schutzeinrichtungen",
"Einzelfallversorgung",
"Strategiedokumente",
"Kooperationsvereinbarungen",
"Gremien",
"Verwaltungsvorschriften",
"Gewaltschutzkonzepte und -maßnahmen",
"Polizeilicher Opferschutz",
"Feedback",
]
for prefix, _, files in os.walk(dd):
for fi in files:
match = re.match(r"(?P<teilb>.*)_2024-.*\.json", fi)
if match:
print(match.group('teilb'))
tb = match.group('teilb')
if tb in allreadydone:
continue
# allreadydone.append(tb)
template = os.path.join(di, "template_"+tb+".xlsx")
schema = os.path.join(di, "schema_"+tb+".json")
if not os.path.exists(template):
print(template)
assert False
jfi = os.path.join(prefix, fi)
print(jfi)
if not fi.startswith("Art"):
continue
# if jfi != "/home/henrik/CaosDB/management/external/dimr/eingabemaske/django/laforms/persistent/data/datenhalterin_gg/he_gg_2/Art__13_Bewusstseinsbildung_2024-01-11T10:22:26.json":
# continue
with open(jfi, encoding="utf-8") as infile:
data = json.load(infile)
data = data["form_data"]
if "__version__" in data:
del data["__version__"]
with tempfile.TemporaryDirectory() as tmpdir:
outfile = os.path.join(tmpdir, 'test.xlsx')
fill_template(data=data, template=template, result=outfile,
validation_schema=schema)
os.system(f'libreoffice {outfile}')
def test_fill_xlsx():
fill_and_compare(json_file=rfp("data/simple_data.json"),
template_file=rfp("data/simple_template.xlsx"),
known_good=rfp("data/simple_data.xlsx"),
schema=rfp("data/simple_schema.json"))
fill_and_compare(json_file=rfp("data/multiple_refs_data.json"),
template_file=rfp("data/multiple_refs_template.xlsx"),
known_good=rfp("data/multiple_refs_data.xlsx"),
schema=rfp("data/multiple_refs_schema.json"))
fill_and_compare(json_file=rfp("data/indirect_data.json"),
template_file=rfp("data/indirect_template.xlsx"),
known_good=rfp("data/indirect_data.xlsx"),
schema=rfp("data/indirect_schema.json"))
fill_and_compare(json_file=rfp("data/simple_data_ascii_chars.json"),
template_file=rfp("data/simple_template.xlsx"),
known_good=rfp("data/simple_data_ascii_chars.xlsx"),
schema=rfp("data/simple_schema.json"))
fill_and_compare(json_file=rfp("data/multiple_choice_data.json"),
template_file=rfp("data/multiple_choice_template.xlsx"),
known_good=rfp("data/multiple_choice_data.xlsx"),
schema=rfp("data/multiple_choice_schema.json"))
def test_errors():
with pytest.raises(AssertionError) as exc:
fill_and_compare(json_file=rfp("data/error_simple_data.json"),
template_file=rfp("data/simple_template.xlsx"),
known_good=rfp("data/simple_data.xlsx"))
assert "Auric\nSteve" in str(exc.value)
with pytest.raises(schema_exc.ValidationError) as exc:
fill_and_compare(json_file=rfp("data/error_simple_data.json"),
template_file=rfp("data/simple_template.xlsx"),
known_good=rfp("data/simple_data.xlsx"),
schema=rfp("data/simple_schema.json"))
assert exc.value.message == "0.5 is not of type 'integer'"
def test_data_schema_generation():
model_schema = xlsx_utils.read_or_dict(rfp("data/simple_schema.json"))
array_schema = xlsx_utils.array_schema_from_model_schema(model_schema)
expected = xlsx_utils.read_or_dict(rfp("data/simple_data_schema.json"))
assert array_schema == expected