70
71
72
73
74
75
76
77
78
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267 | class DatabricksSparkRuntimeContracts(BaseRuntimeContracts):
"""
Runtime schema contracts for Spark / DatabricksSparkExecutor.
- verify: write output table, then compare contract vs actual Spark schema
- cast: apply Spark casts before writing, then verify
"""
def __init__(self, executor: ContractExecutor):
super().__init__(executor)
# --- helpers ---------------------------------------------------------
def _save_df_as_table(self, *, ctx: RuntimeContractContext, df: Any) -> None:
"""
Delegate to DatabricksSparkExecutor._save_df_as_table (format handler aware).
"""
save = getattr(self.executor, "_save_df_as_table", None)
if not callable(save):
raise RuntimeError(
"[contracts] Spark runtime contracts require executor._save_df_as_table(...)"
)
# Preserve existing storage behavior if available
storage_meta = {}
storage_fn = getattr(self.executor, "_storage_meta", None)
if callable(storage_fn):
try:
storage_meta = storage_fn(ctx.node, ctx.physical_table)
except Exception:
storage_meta = {}
save(ctx.physical_table, df, storage=storage_meta)
def _verify(
self,
*,
table: str,
expected: Mapping[str, str],
cfg: RuntimeContractConfig,
) -> None:
if not expected:
return
actual = self.executor.introspect_table_physical_schema(table)
exp_lower = {k.lower(): v for k, v in expected.items()}
problems: list[str] = []
for col, expected_type in expected.items():
key = col.lower()
if key not in actual:
problems.append(f"- missing column {col!r}")
continue
got = actual[key]
if not _types_match(expected_type, got):
problems.append(f"- column {col!r}: expected {expected_type!r}, got {got!r}")
if not cfg.allow_extra_columns:
extras = [c for c in actual if c not in exp_lower]
if extras:
problems.append(f"- extra columns present: {sorted(extras)}")
if problems:
raise RuntimeError(
f"[contracts] Spark schema enforcement failed for {table}:\n" + "\n".join(problems)
)
def _cast_df(
self,
*,
df: Any,
expected: Mapping[str, str],
allow_extra: bool,
) -> Any:
"""
Return a projected DataFrame:
- expected cols casted to expected Spark SQL types
- optionally keep extra cols
"""
# Use your lazy import helper to avoid hard pyspark deps at import time
from fastflowtransform.executors._spark_imports import get_spark_functions # noqa: PLC0415
F = get_spark_functions()
if not expected:
return df
cols = list(getattr(df, "columns", []) or [])
col_map = {c.lower(): c for c in cols} # actual name by lower key
exp_lower = {k.lower(): v for k, v in expected.items()}
# Ensure expected columns exist
missing = [c for c in exp_lower if c not in col_map]
if missing:
raise RuntimeError(f"[contracts] missing expected columns: {sorted(missing)}")
projections: list[Any] = []
for low_name, typ in exp_lower.items():
real = col_map[low_name]
projections.append(F.col(real).cast(str(typ)).alias(real))
if allow_extra:
for c in cols:
if c.lower() not in exp_lower:
projections.append(F.col(c))
return df.select(*projections)
# --- BaseRuntimeContracts hooks -------------------------------------
def apply_sql_contracts(
self,
*,
ctx: RuntimeContractContext,
select_body: str,
) -> None:
expected = expected_physical_schema(executor=self.executor, contract=ctx.contract)
mode = ctx.config.mode
# Spark executor doesn't do CTAS SQL; it materializes via DF + _save_df_as_table
df = self.executor._execute_sql(select_body)
if mode == "off" or not expected:
self._save_df_as_table(ctx=ctx, df=df)
return
if mode == "cast":
if not expected:
raise RuntimeError(
f"[contracts] cast mode enabled for {ctx.relation!r} "
"but no physical schema could be resolved."
)
df2 = self._cast_df(
df=df, expected=expected, allow_extra=ctx.config.allow_extra_columns
)
self._save_df_as_table(ctx=ctx, df=df2)
self._verify(table=ctx.physical_table, expected=expected, cfg=ctx.config)
return
if mode == "verify":
self._save_df_as_table(ctx=ctx, df=df)
self._verify(table=ctx.physical_table, expected=expected, cfg=ctx.config)
return
# unknown mode -> behave like off
self._save_df_as_table(ctx=ctx, df=df)
def materialize_python(
self,
*,
ctx: RuntimeContractContext,
df: Any,
) -> bool:
"""
Spark Python models return a Spark DataFrame. Enforce contracts here
so we can CAST before writing.
"""
mode = ctx.config.mode
if mode == "off":
return False
expected = expected_physical_schema(executor=self.executor, contract=ctx.contract)
if mode == "cast" and not expected:
raise RuntimeError(
f"[contracts] cast mode enabled for {ctx.relation!r} "
"but no physical schema could be resolved."
)
# basic Spark DF shape check (avoid importing pyspark types)
if not hasattr(df, "schema") or not hasattr(df, "columns") or not hasattr(df, "select"):
return False
if mode == "cast":
df2 = self._cast_df(
df=df, expected=expected, allow_extra=ctx.config.allow_extra_columns
)
self._save_df_as_table(ctx=ctx, df=df2)
self._verify(table=ctx.physical_table, expected=expected, cfg=ctx.config)
return True
if mode == "verify":
self._save_df_as_table(ctx=ctx, df=df)
if expected:
self._verify(table=ctx.physical_table, expected=expected, cfg=ctx.config)
return True
return False
def verify_after_materialization(self, *, ctx: RuntimeContractContext) -> None:
expected = expected_physical_schema(executor=self.executor, contract=ctx.contract)
if not expected:
return
if ctx.config.mode not in {"verify", "cast"}:
return
self._verify(table=ctx.physical_table, expected=expected, cfg=ctx.config)
|