Skip to content

Commit

Permalink
Merge pull request #122 from wmo-im/add-metadata-id-to-reports
Browse files Browse the repository at this point in the history 
align ETS and KPI report formats, add UUID and metadata to reports
  • Loading branch information
@tomkralidis
tomkralidis authored Aug 27, 2024
2 parents 5a70a09 + f118672 commit bfd2644
Show file tree
Hide file tree
Showing 4 changed files with 102 additions and 64 deletions.
4 changes: 2 additions & 2 deletions pywcmp/ets.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
# Authors: Tom Kralidis <[email protected]>
# Ján Osuský <[email protected]>
#
# Copyright (c) 2023 Tom Kralidis
# Copyright (c) 2024 Tom Kralidis
# Copyright (c) 2022 Government of Canada
# Copyright (c) 2020 IBL Software Engineering spol. s r. o.
#
Expand Down Expand Up @@ -81,7 +81,7 @@ def validate(ctx, file_or_url, logfile, verbosity,
ctx.exit(1)

click.echo(json.dumps(results, indent=4))
ctx.exit(results['ets-report']['summary']['FAILED'])
ctx.exit(results['summary']['FAILED'])


ets.add_command(validate)
11 changes: 6 additions & 5 deletions pywcmp/wcmp2/ets.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
import json
import logging
from pathlib import Path
import uuid

from jsonschema.validators import Draft202012Validator

Expand Down Expand Up @@ -67,7 +68,6 @@ def __init__(self, data: dict):

self.test_id = None
self.record = data
self.report = []

self.th = TopicHierarchy(tables=get_userdir())

Expand All @@ -77,8 +77,10 @@ def run_tests(self, fail_on_schema_validation=False):
results = []
tests = []
ets_report = {
'id': str(uuid.uuid4()),
'report_type': 'ets',
'summary': {},
'generated-by': f'pywcmp {pywcmp.__version__} (https://github.com/wmo-im/pywcmp)' # noqa
'generated_by': f'pywcmp {pywcmp.__version__} (https://github.com/wmo-im/pywcmp)' # noqa
}

for f in dir(WMOCoreMetadataProfileTestSuite2):
Expand Down Expand Up @@ -106,10 +108,9 @@ def run_tests(self, fail_on_schema_validation=False):

ets_report['tests'] = results
ets_report['datetime'] = get_current_datetime_rfc3339()
ets_report['metadata_id'] = self.record['id']

return {
'ets-report': ets_report
}
return ets_report

def test_requirement_validation(self):
"""
Expand Down
121 changes: 75 additions & 46 deletions pywcmp/wcmp2/kpi.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
#
# Authors: Tom Kralidis <[email protected]>
#
# Copyright (c) 2023 Tom Kralidis
# Copyright (c) 2024 Tom Kralidis
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
Expand All @@ -28,6 +28,7 @@
import logging
import mimetypes
import re
import uuid

from bs4 import BeautifulSoup

Expand All @@ -41,6 +42,18 @@
ROUND = 3


def gen_test_id(test_id: str) -> str:
"""
Convenience function to print test identifier as URI
:param test_id: test suite identifier
:returns: test identifier as URI
"""

return f'http://wis.wmo.int/spec/wcmp/2/kpi/core/{test_id}'


class WMOCoreMetadataProfileKeyPerformanceIndicators:
"""Key Performance Indicators for WMO Core Metadata Profile"""

Expand Down Expand Up @@ -70,18 +83,19 @@ def kpi_title(self) -> tuple:
"""
Implements KPI for Good quality title
:returns: `tuple` of KPI name, achieved score, total score,
:returns: `tuple` of KPI id, title, achieved score, total score,
and comments
"""

total = 8
score = 0
comments = []

name = 'KPI: Good quality title'
id_ = gen_test_id('good_quality_title')
title = 'Good quality title'
acronym_regex = r'\b([A-Z]{2,}\d*)\b'

LOGGER.info(f'Running {name}')
LOGGER.info(f'Running {title}')

title = self.data['properties']['title']

Expand Down Expand Up @@ -146,23 +160,24 @@ def kpi_title(self) -> tuple:
else:
comments.append(f'Title contains spelling errors {misspelled}')

return name, total, score, comments
return id_, title, total, score, comments

def kpi_description(self) -> tuple:
"""
Implements KPI for Good quality description
:returns: `tuple` of KPI name, achieved score, total score,
:returns: `tuple` of KPI id, title, achieved score, total score,
and comments
"""

total = 4
score = 0
comments = []

name = 'KPI: Good quality description'
id_ = gen_test_id('good_quality_description')
title = ': Good quality description'

LOGGER.info(f'Running {name}')
LOGGER.info(f'Running {title}')

description = self.data['properties']['description']

Expand Down Expand Up @@ -198,13 +213,13 @@ def kpi_description(self) -> tuple:
else:
comments.append(f'Description contains spelling errors {misspelled}') # noqa

return name, total, score, comments
return id_, title, total, score, comments

def kpi_time_intervals(self) -> tuple:
"""
Implements KPI for Time intervals
:returns: `tuple` of KPI name, achieved score, total score,
:returns: `tuple` of KPI id, title, achieved score, total score,
and comments
"""

Expand All @@ -214,15 +229,16 @@ def kpi_time_intervals(self) -> tuple:
score = 0
comments = []

name = 'KPI: Time intervals'
id_ = gen_test_id('time_intervals')
title = 'Time intervals'

LOGGER.info(f'Running {name}')
LOGGER.info(f'Running {title}')

time_ = self.data.get('time')
if time_ is None:
msg = 'time is null; no KPI check'
LOGGER.debug(msg)
return name, 0, 0, [msg]
return id_, title, 0, 0, [msg]

interval = self.data['time'].get('interval')

Expand Down Expand Up @@ -258,13 +274,13 @@ def kpi_time_intervals(self) -> tuple:
else:
comments.append('No temporal resolution found')

return name, total, score, comments
return id_, title, total, score, comments

def kpi_graphic_overview(self) -> tuple:
"""
Implements KPI for Graphic overview for metadata records
:returns: `tuple` of KPI name, achieved score, total score,
:returns: `tuple` of KPI id, title, achieved score, total score,
and comments
"""

Expand All @@ -282,9 +298,10 @@ def kpi_graphic_overview(self) -> tuple:
'image/webp'
]

name = 'KPI: Graphic overview for metadata records'
id_ = gen_test_id('graphic_overview_for_metadata_records')
title = 'Graphic overview for metadata records'

LOGGER.info(f'Running {name}')
LOGGER.info(f'Running {title}')

for link in self.data['links']:
if link.get('rel') == 'preview':
Expand All @@ -308,13 +325,13 @@ def kpi_graphic_overview(self) -> tuple:
else:
comments.append(f"URL not accessible: {link['href']}")

return name, total, score, comments
return id_, title, total, score, comments

def kpi_links_health(self) -> tuple:
"""
Implements KPI for Links health
:returns: `tuple` of KPI name, achieved score, total score,
:returns: `tuple` of KPI id, title, achieved score, total score,
and comments
"""

Expand All @@ -324,7 +341,8 @@ def kpi_links_health(self) -> tuple:
score = 0
comments = []

name = 'KPI: Links health'
id_ = gen_test_id('links_health')
title = 'Links health'

valid_link_mime_types = list(mimetypes.types_map.values())
valid_link_mime_types.extend([
Expand All @@ -333,7 +351,7 @@ def kpi_links_health(self) -> tuple:
'text/turtle'
])

LOGGER.info(f'Running {name}')
LOGGER.info(f'Running {title}')

LOGGER.debug('Assembling all links')

Expand Down Expand Up @@ -384,13 +402,13 @@ def kpi_links_health(self) -> tuple:
else:
comments.append(f"invalid link type {link_type}")

return name, total, score, comments
return id_, title, total, score, comments

def kpi_contacts(self) -> tuple:
"""
Implements KPI for Contacts
:returns: `tuple` of KPI name, achieved score, total score,
:returns: `tuple` of KPI id, title, achieved score, total score,
and comments
"""

Expand All @@ -401,9 +419,10 @@ def kpi_contacts(self) -> tuple:
score = 0
comments = []

name = 'KPI: Contacts'
id_ = gen_test_id('contacts')
title = 'Contacts'

LOGGER.info(f'Running {name}')
LOGGER.info(f'Running {title}')

for contact in self.data['properties']['contacts']:
if 'host' in contact['roles']:
Expand All @@ -429,13 +448,13 @@ def kpi_contacts(self) -> tuple:
else:
comments.append('No host contact email found')

return name, total, score, comments
return id_, title, total, score, comments

def kpi_pids(self) -> tuple:
"""
Implements KPI for Persistent identifiers
:returns: `tuple` of KPI name, achieved score, total score,
:returns: `tuple` of KPI id, title, achieved score, total score,
and comments
"""

Expand All @@ -445,9 +464,10 @@ def kpi_pids(self) -> tuple:
score = 0
comments = []

name = 'KPI: Persistent identifiers'
id_ = gen_test_id('persistent_identifiers')
title = 'Persistent identifiers'

LOGGER.info(f'Running {name}')
LOGGER.info(f'Running {title}')

if 'externalIds' in self.data['properties']:
total = 3
Expand All @@ -467,7 +487,7 @@ def kpi_pids(self) -> tuple:
score += 1
break

return name, total, score, comments
return id_, title, total, score, comments

def evaluate(self, kpi: str = None) -> dict:
"""
Expand Down Expand Up @@ -498,38 +518,42 @@ def evaluate(self, kpi: str = None) -> dict:

LOGGER.info(f'Evaluating KPIs: {kpis_to_run}')

results = {}
results = {
'id': str(uuid.uuid4()),
'report_type': 'kpi',
'metadata_id': self.identifier,
'datetime': get_current_datetime_rfc3339(),
'generated_by': f'pywcmp {pywcmp.__version__} (https://github.com/wmo-im/pywcmp)', # noqa
'tests': []
}

for kpi in kpis_to_run:
LOGGER.debug(f'Running {kpi}')
result = getattr(self, kpi)()
LOGGER.debug(f'Raw result: {result}')
LOGGER.debug('Calculating result')
try:
percentage = round(float((result[2] / result[1]) * 100), ROUND)
percentage = round(float((result[3] / result[2]) * 100), ROUND)
except ZeroDivisionError:
percentage = None

results[kpi] = {
'name': result[0],
'total': result[1],
'score': result[2],
'comments': result[3],
results['tests'].append({
'id': result[0],
'title': result[1],
'total': result[2],
'score': result[3],
'comments': result[4],
'percentage': percentage
}
LOGGER.debug(f'{kpi}: {result[1]} / {result[2]} = {percentage}')
})
LOGGER.debug(f'{kpi}: {result[2]} / {result[3]} = {percentage}')

LOGGER.debug('Calculating total results')
results['summary'] = generate_summary(results)
# this total summary needs extra elements
results['summary']['identifier'] = self.identifier
overall_grade = 'F'
overall_grade = calculate_grade(results['summary']['percentage'])
results['summary']['grade'] = overall_grade

results['datetime'] = get_current_datetime_rfc3339()
results['generated-by'] = f'pywcmp {pywcmp.__version__} (https://github.com/wmo-im/pywcmp)' # noqa

return results


Expand All @@ -542,9 +566,14 @@ def generate_summary(results: dict) -> dict:
:returns: `dict` of summary report
"""

sum_total = sum(v['total'] for v in results.values())
sum_score = sum(v['score'] for v in results.values())
comments = {k: v['comments'] for k, v in results.items() if v['comments']}
sum_total = sum(v['total'] for v in results['tests'])
sum_score = sum(v['score'] for v in results['tests'])
comments = {}

for test in results['tests']:
if test['comments']:
for k, v in test.items():
comments[k] = v

try:
sum_percentage = round(float((sum_score / sum_total) * 100), ROUND)
Expand Down
Loading

0 comments on commit bfd2644

Please sign in to comment.