93 lines
3.4 KiB
Python
93 lines
3.4 KiB
Python
"""Classificazione di column eligibility (principio trasversale Thoth).
|
|
|
|
Il testo ampio (lettere di dimissione, note, anamnesi) è ignorato ovunque; i dati
|
|
provengono solo da numerici, enum, temporali, booleani e testo breve.
|
|
"""
|
|
|
|
import re
|
|
|
|
from tht.config import EligibilityConfig
|
|
from tht.db.sampling import is_text_type
|
|
from tht.mschema.models import ColumnAnnotation, ColumnPhysical, PhysicalSchema
|
|
|
|
_NUMERIC_PREFIXES = (
|
|
"smallint", "integer", "bigint", "numeric", "decimal", "real", "double", "money",
|
|
)
|
|
_TEMPORAL_PREFIXES = ("date", "time", "timestamp", "interval")
|
|
_LEN_RE = re.compile(r"\((\d+)\)")
|
|
|
|
|
|
def _declared_len(pg_type: str) -> int | None:
|
|
m = _LEN_RE.search(pg_type)
|
|
return int(m.group(1)) if m else None
|
|
|
|
|
|
def classify_column(
|
|
pg_type: str,
|
|
is_enum: bool,
|
|
sampled_avg: float | None,
|
|
sampled_max: int | None,
|
|
cfg: EligibilityConfig,
|
|
) -> tuple[bool, str]:
|
|
"""Classifica una colonna come (eligible, reason). Funzione pura, senza I/O."""
|
|
t = pg_type.strip().lower()
|
|
if t.endswith("[]"):
|
|
return False, "wide_text"
|
|
if is_enum:
|
|
return True, "enum"
|
|
if t.startswith(_NUMERIC_PREFIXES):
|
|
return True, "numeric"
|
|
if t.startswith("boolean"):
|
|
return True, "boolean"
|
|
if t.startswith(_TEMPORAL_PREFIXES):
|
|
return True, "temporal"
|
|
if t.startswith("uuid"):
|
|
return True, "code"
|
|
if is_text_type(t):
|
|
declared = _declared_len(t)
|
|
if declared is not None and declared <= cfg.max_declared_len:
|
|
return True, "short_text"
|
|
# bound grande o text/varchar non vincolato: decide il dato campionato
|
|
if sampled_avg is None or sampled_max is None:
|
|
return False, "wide_text"
|
|
if sampled_avg <= cfg.max_avg_length and sampled_max <= cfg.max_sampled_len:
|
|
return True, "short_text"
|
|
return False, "wide_text"
|
|
return False, "wide_text"
|
|
|
|
|
|
def _sampled_stats(examples: list[str]) -> tuple[float | None, int | None]:
|
|
if not examples:
|
|
return None, None
|
|
lengths = [len(v) for v in examples]
|
|
return sum(lengths) / len(lengths), max(lengths)
|
|
|
|
|
|
def classify_all(physical: PhysicalSchema, cfg: EligibilityConfig) -> None:
|
|
"""Assegna eligible/eligibility_reason a ogni colonna (in-place) e azzera gli
|
|
examples delle colonne ignored. Da chiamare DOPO add_examples."""
|
|
ignore_by_name = {name.lower() for name in cfg.ignore_columns}
|
|
for table in physical.tables.values():
|
|
for column_name, column in table.columns.items():
|
|
if column_name.lower() in ignore_by_name:
|
|
# colonna di servizio (ETL/audit): ignorata a prescindere dal tipo
|
|
column.eligible = False
|
|
column.eligibility_reason = "ignored_by_name"
|
|
column.examples = []
|
|
continue
|
|
avg, mx = _sampled_stats(column.examples)
|
|
eligible, reason = classify_column(column.type, column.is_enum, avg, mx, cfg)
|
|
column.eligible = eligible
|
|
column.eligibility_reason = reason
|
|
if not eligible:
|
|
column.examples = []
|
|
|
|
|
|
def effective_eligibility(
|
|
column: ColumnPhysical, annotation: ColumnAnnotation | None
|
|
) -> tuple[bool, str]:
|
|
"""Eligibilità effettiva: l'override in annotations.yaml vince sul fisico."""
|
|
if annotation is not None and annotation.eligible is not None:
|
|
return annotation.eligible, "override"
|
|
return column.eligible, column.eligibility_reason
|