tudor/school_compare
1
0
Fork 0
Code Issues 2 Pull Requests Actions Packages Projects Releases Wiki Activity

fix(api): fall back to legacy name-column query when marts predate code migration

Browse Source 
Closes the deploy window flagged by CI review — the backend now works
against both the old (name) and new (code) mart schemas.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Tudor
2026-07-09 14:44:27 +01:00
co-authored by Claude Fable 5
parent c26755750d
commit b44fca902f
2 changed files with 104 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/data_loader.py
+52 -11
View File
@@ -262,25 +262,66 @@ assert "NULL AS has_sixth_form" in str(_MAIN_QUERY_NO_SIXTH_FORM), (
"expected replacement of 's.has_sixth_form,' to have taken effect"
)
# Fallback used when marts.dim_school predates the GIAS code-dictionary
# migration (i.e. the nightly dbt pipeline hasn't rebuilt the mart yet on
# this DB, so it still has the old name columns instead of *_code columns).
_MAIN_QUERY_LEGACY_NAMES = str(_MAIN_QUERY)
_LEGACY_NAME_REPLACEMENTS = [
("s.phase_code,", "s.phase,"),
("s.school_type_code,", "s.school_type,"),
(
"s.religious_character_code,",
"s.religious_character AS religious_denomination,",
),
("s.status_code,", "s.status,"),
("s.admissions_policy_code,", "s.admissions_policy,"),
]
for _old, _new in _LEGACY_NAME_REPLACEMENTS:
assert _old in _MAIN_QUERY_LEGACY_NAMES, (
f"expected {_old!r} to be present in _MAIN_QUERY before replacement"
)
_MAIN_QUERY_LEGACY_NAMES = _MAIN_QUERY_LEGACY_NAMES.replace(_old, _new)
_MAIN_QUERY_LEGACY_NAMES = text(_MAIN_QUERY_LEGACY_NAMES)
_GIAS_CODE_COLUMN_NAMES = (
"phase_code",
"school_type_code",
"religious_character_code",
"status_code",
"admissions_policy_code",
)
def load_school_data_as_dataframe() -> pd.DataFrame:
"""Load all school + KS2 data as a pandas DataFrame."""
try:
df = pd.read_sql(_MAIN_QUERY, engine)
except sqlalchemy.exc.ProgrammingError as exc:
if "has_sixth_form" not in str(exc):
if any(col in str(exc) for col in _GIAS_CODE_COLUMN_NAMES):
logging.getLogger(__name__).warning(
"marts predate the GIAS code migration — falling back to "
"legacy name-column query: %s",
exc,
)
try:
df = pd.read_sql(_MAIN_QUERY_LEGACY_NAMES, engine)
except Exception as exc2:
print(f"Warning: Could not load school data from marts: {exc2}")
return pd.DataFrame()
elif "has_sixth_form" in str(exc):
logging.getLogger(__name__).warning(
"marts.dim_school is missing has_sixth_form (pipeline hasn't "
"rebuilt the mart yet on this DB) — retrying without it: %s",
exc,
)
try:
df = pd.read_sql(_MAIN_QUERY_NO_SIXTH_FORM, engine)
except Exception as exc2:
print(f"Warning: Could not load school data from marts: {exc2}")
return pd.DataFrame()
else:
print(f"Warning: Could not load school data from marts: {exc}")
return pd.DataFrame()
logging.getLogger(__name__).warning(
"marts.dim_school is missing has_sixth_form (pipeline hasn't "
"rebuilt the mart yet on this DB) — retrying without it: %s",
exc,
)
try:
df = pd.read_sql(_MAIN_QUERY_NO_SIXTH_FORM, engine)
except Exception as exc2:
print(f"Warning: Could not load school data from marts: {exc2}")
return pd.DataFrame()
except Exception as exc:
print(f"Warning: Could not load school data from marts: {exc}")
return pd.DataFrame()