Name validation only two periods (#393)

* add validation for more than two periods in file name

* make ._period_strings public

* pre-commit ran?

* check for three periods in tests

Author: aecorn

src/dapla_metadata/datasets/dapla_dataset_path_info.py

@@ -340,7 +340,7 @@ def __init__(self, dataset_path: ReadablePathLike) -> None:
         self.dataset_string = str(dataset_path)
         self.dataset_path = UPath(self.dataset_string)
         self.dataset_name_sections = self.dataset_path.stem.split("_")
-        self._period_strings = self._extract_period_strings(self.dataset_name_sections)
+        self.period_strings = self._extract_period_strings(self.dataset_name_sections)
 
         # Since UPath as a trailing slash after the bucket name we remove that so that we are able to find the bucket name in the path parts later
         self.dataset_path_parts = [p.strip("/") for p in self.dataset_path.parent.parts]
@@ -446,7 +446,7 @@ def _extract_period_string_from_index(self, index: int) -> str | None:
             The extracted period string if it exists, otherwise None.
         """
         try:
-            return self._period_strings[index]
+            return self.period_strings[index]
         except IndexError:
             return None
 
@@ -574,7 +574,7 @@ def contains_data_from(self) -> datetime.date | None:
         """
         period_string = self._extract_period_string_from_index(0)
         if not period_string or (
-            len(self._period_strings) > 1 and period_string > self._period_strings[1]
+            len(self.period_strings) > 1 and period_string > self.period_strings[1]
         ):
             return None
         date_format = categorize_period_string(period_string)

src/dapla_metadata/standards/name_validator.py

@@ -8,18 +8,19 @@
 
 from dapla_metadata.datasets.dapla_dataset_path_info import DaplaDatasetPathInfo
 from dapla_metadata.datasets.dataset_parser import SUPPORTED_DATASET_FILE_SUFFIXES
-from dapla_metadata.standards.utils.constants import DESCRIPTION_OTHER_THAN_DASHES
 from dapla_metadata.standards.utils.constants import FILE_DOES_NOT_EXIST
 from dapla_metadata.standards.utils.constants import FILE_IGNORED
 from dapla_metadata.standards.utils.constants import IGNORED_FOLDERS
 from dapla_metadata.standards.utils.constants import INVALID_SYMBOLS
+from dapla_metadata.standards.utils.constants import MAX_TWO_PERIODS
 from dapla_metadata.standards.utils.constants import MISSING_DATA_STATE
 from dapla_metadata.standards.utils.constants import MISSING_DATASET_SHORT_NAME
 from dapla_metadata.standards.utils.constants import MISSING_PERIOD
 from dapla_metadata.standards.utils.constants import MISSING_SHORT_NAME
 from dapla_metadata.standards.utils.constants import NAME_STANDARD_SUCCESS
 from dapla_metadata.standards.utils.constants import NAME_STANDARD_VIOLATION
 from dapla_metadata.standards.utils.constants import PATH_IGNORED
+from dapla_metadata.standards.utils.constants import SHORT_NAME_OTHER_THAN_DASHES
 from dapla_metadata.standards.utils.constants import SSB_NAMING_STANDARD_REPORT
 from dapla_metadata.standards.utils.constants import SSB_NAMING_STANDARD_REPORT_FILES
 from dapla_metadata.standards.utils.constants import (
@@ -194,9 +195,10 @@ def _check_violations(
         MISSING_SHORT_NAME: path_info.statistic_short_name,
         MISSING_DATA_STATE: path_info.dataset_state,
         MISSING_PERIOD: path_info.contains_data_from,
+        MAX_TWO_PERIODS: len(path_info.period_strings) <= 2,
         MISSING_DATASET_SHORT_NAME: path_info.dataset_short_name,
         INVALID_SYMBOLS: not _has_invalid_symbols(file),
-        DESCRIPTION_OTHER_THAN_DASHES: not _short_name_has_illegal_chars(
+        SHORT_NAME_OTHER_THAN_DASHES: not _short_name_has_illegal_chars(
             path_info.dataset_short_name
         ),
     }

src/dapla_metadata/standards/utils/constants.py

@@ -7,7 +7,7 @@
 NAME_STANDARD_SUCCESS = "Filene dine er i samsvar med SSB-navnestandarden"
 
 NAME_STANDARD_VIOLATION = "Det er oppdaget brudd på SSB-navnestandard:"
-
+MAX_TWO_PERIODS = "Det er mer enn to perioder i filnavnet, navnestandarden åpner kun for to: https://manual.dapla.ssb.no/statistikkere/navnestandard.html#tbl-filename"
 MISSING_BUCKET_NAME = "Filnavn mangler bøttenavn ref: https://manual.dapla.ssb.no/statistikkere/navnestandard.html#obligatoriske-mapper"
 MISSING_VERSION = "Filnavn mangler versjon, hvis ikke filen er nyeste versjon kan dette være brudd på navnestandarden ref: https://manual.dapla.ssb.no/statistikkere/navnestandard.html#versjonering-av-datasett"
 MISSING_PERIOD = "Filnavn mangler gyldighetsperiode ref: https://manual.dapla.ssb.no/statistikkere/navnestandard.html#filnavn"
@@ -16,7 +16,7 @@
 MISSING_DATASET_SHORT_NAME = "Filnavn mangler datasett kortnavn ref: https://manual.dapla.ssb.no/statistikkere/navnestandard.html#filnavn"
 
 INVALID_SYMBOLS = "Filnavn inneholder ulovlige tegn ref: https://manual.dapla.ssb.no/statistikkere/navnestandard.html#filnavn"
-DESCRIPTION_OTHER_THAN_DASHES = "Datasett kortnavn inneholder ulovlige tegn ref: https://manual.dapla.ssb.no/statistikkere/navnestandard.html#filnavn"
+SHORT_NAME_OTHER_THAN_DASHES = "Datasett kortnavn inneholder ulovlige tegn ref: https://manual.dapla.ssb.no/statistikkere/navnestandard.html#filnavn"
 
 PATH_IGNORED = "Ignorert, mappen er ikke underlagt krav til navnestandard."
 FILE_IGNORED = f"Ignorert, kun datasett med {', '.join(SUPPORTED_DATASET_FILE_SUFFIXES.keys())} filendelser valideres foreløpig."

tests/standards/test_check_naming_standard.py

@@ -351,6 +351,7 @@ async def test_generate_naming_standard_report(tmp_path):
         "buckets/ssb-dapla-example-data-produkt-prod/klargjorte_data/_p2021-12-31_p2021-12-31_v1.parquet",
         "buckets/ssb-dapla-example-data-produkt-prod/ledstill/klargjorte_data/park_p2021-12-31_p2021-12-31_v1.parquet",
         "buckets/ssb-dapla-example-data-produkt-prod/ledstill/park_wrongunderscore_v1.parquet",
+        "buckets/ssb-dapla-example-data-produkt-prod/ledstill/klargjorte_data/three-periods_p2020-12-31_p2021-12-31_p2022-12-31_v1.parquet",
     ]
     for file_path in file_paths:
         full_path = tmp_path / file_path
@@ -363,8 +364,8 @@ async def test_generate_naming_standard_report(tmp_path):
 
     if isinstance(results, list):
         report = generate_validation_report(validation_results=results)
-        assert report.num_failures == 4
-        assert report.num_files_validated == 6
+        assert report.num_failures == 5
+        assert report.num_files_validated == 7
         assert report.num_success == 2