Skip to content

fastflowtransform.contracts.runtime.bigquery

BigQueryRuntimeContracts

Bases: BaseRuntimeContracts

Runtime schema contracts for BigQuery.

Notes: - executor._execute_sql returns a job-like object; we force execution via .result() when present. - CAST mode uses BigQuery's src.* EXCEPT(col1, col2, ...) to retain extra columns.

Source code in src/fastflowtransform/contracts/runtime/bigquery.py
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 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
class BigQueryRuntimeContracts(BaseRuntimeContracts):
    """
    Runtime schema contracts for BigQuery.

    Notes:
    - executor._execute_sql returns a job-like object; we force execution via .result()
      when present.
    - CAST mode uses BigQuery's `src.* EXCEPT(col1, col2, ...)` to retain extra columns.
    """

    def __init__(self, executor: ContractExecutor):
        super().__init__(executor)

    # --- helpers ---------------------------------------------------------

    def _exec(self, sql: str) -> Any:
        res = self.executor._execute_sql(sql)
        # BigQuery QueryJob / our _TrackedQueryJob: execute via .result()
        result_fn = getattr(res, "result", None)
        if callable(result_fn):
            return result_fn()
        # Spark-like fallbacks (harmless here, but keeps this helper generic)
        collect_fn = getattr(res, "collect", None)
        if callable(collect_fn):
            return collect_fn()
        return res

    def _verify(
        self,
        *,
        table: str,
        expected: Mapping[str, str],
        cfg: RuntimeContractConfig,
    ) -> None:
        if not expected:
            return

        actual = self.executor.introspect_table_physical_schema(table)  # {lower_name: TYPE}
        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 str(got).lower() != str(expected_type).lower():
                problems.append(f"- column {col!r}: expected type {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] BigQuery schema enforcement failed for {table}:\n"
                + "\n".join(problems)
            )

    def _ctas_raw(self, target: str, select_body: str) -> None:
        # BigQuery supports CREATE OR REPLACE TABLE ... AS <select>
        self._exec(f"create or replace table {target} as {select_body}")

    def _ctas_cast_via_subquery(
        self,
        *,
        ctx: RuntimeContractContext,
        select_body: str,
        expected: Mapping[str, str],
    ) -> None:
        """
        Cast mode for SQL models:

          CREATE OR REPLACE TABLE target AS
          SELECT
            CAST(src.col AS TYPE) AS col,
            ...
            [, src.* EXCEPT(col, ...)]   -- if allow_extra_columns
          FROM ( <user select_body> ) AS src
        """
        if not expected:
            self._ctas_raw(ctx.physical_table, select_body)
            return

        casts = [f"cast(src.{col} as {typ}) as {col}" for col, typ in expected.items()]

        if ctx.config.allow_extra_columns:
            # Keep extras without duplicating expected columns
            except_list = ", ".join(expected.keys())
            casts.append(f"src.* except ({except_list})")

        proj_sql = ", ".join(casts)
        wrapped = f"select {proj_sql} from ({select_body}) as src"
        self._ctas_raw(ctx.physical_table, wrapped)

    # --- 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

        if mode == "off" or not expected:
            self._ctas_raw(ctx.physical_table, select_body)
            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."
                )
            self._ctas_cast_via_subquery(ctx=ctx, select_body=select_body, expected=expected)
            self._verify(table=ctx.physical_table, expected=expected, cfg=ctx.config)
            return

        if mode == "verify":
            self._ctas_raw(ctx.physical_table, select_body)
            self._verify(table=ctx.physical_table, expected=expected, cfg=ctx.config)
            return

        # unknown mode -> behave like off
        self._ctas_raw(ctx.physical_table, select_body)

    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)

build_context

build_context(*, node, relation, physical_table, contract, project_contracts, is_incremental=False)

Build a RuntimeContractContext with the correct RuntimeContractConfig.

The caller (run-engine) decides which contract applies and passes: - node: the fft Node being built - relation: logical name (typically node.name) - physical_table: fully-qualified identifier used in SQL - contract: per-table ContractsFileModel, or None - project_contracts: parsed project-level contracts.yml, or None

Source code in src/fastflowtransform/contracts/runtime/base.py
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
def build_context(
    self,
    *,
    node: Node,
    relation: str,
    physical_table: str,
    contract: ContractsFileModel | None,
    project_contracts: ProjectContractsModel | None,
    is_incremental: bool = False,
) -> RuntimeContractContext:
    """
    Build a RuntimeContractContext with the correct RuntimeContractConfig.

    The caller (run-engine) decides which contract applies and passes:
      - node:          the fft Node being built
      - relation:      logical name (typically node.name)
      - physical_table: fully-qualified identifier used in SQL
      - contract:      per-table ContractsFileModel, or None
      - project_contracts: parsed project-level contracts.yml, or None
    """
    # Use the contract's declared table name if present, otherwise fall
    # back to the logical relation name for project-level overrides.
    table_key = contract.table if contract is not None else relation

    cfg = resolve_runtime_contract_config(
        table_name=table_key,
        contract=contract,
        project_contracts=project_contracts,
    )

    return RuntimeContractContext(
        node=node,
        relation=relation,
        physical_table=physical_table,
        contract=contract,
        project_contracts=project_contracts,
        config=cfg,
        is_incremental=is_incremental,
    )

coerce_frame_schema

coerce_frame_schema(df, ctx)

Optional hook for Python models: given a DataFrame-like object and the RuntimeContractContext, return a new frame whose column types have been coerced to match the expected physical schema (where reasonable).

Default implementation is a no-op. Engine-specific subclasses may override this (e.g. DuckDB + pandas).

Source code in src/fastflowtransform/contracts/runtime/base.py
244
245
246
247
248
249
250
251
252
253
def coerce_frame_schema(self, df: Any, ctx: RuntimeContractContext) -> Any:
    """
    Optional hook for Python models: given a DataFrame-like object and the
    RuntimeContractContext, return a new frame whose column types have been
    coerced to match the expected physical schema (where reasonable).

    Default implementation is a no-op. Engine-specific subclasses may
    override this (e.g. DuckDB + pandas).
    """
    return df

materialize_python

materialize_python(*, ctx, df)

Optional hook for Python models.

Engines override this to take over materialization for Python models (e.g. to enforce contracts via explicit CASTs).

Return True if you fully materialized ctx.physical_table yourself. Return False to let the executor use its normal path (_materialize_relation / _materialize_incremental).

Source code in src/fastflowtransform/contracts/runtime/base.py
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
def materialize_python(
    self,
    *,
    ctx: RuntimeContractContext,
    df: Any,
) -> bool:
    """
    Optional hook for Python models.

    Engines override this to take over materialization for Python
    models (e.g. to enforce contracts via explicit CASTs).

    Return True if you fully materialized ctx.physical_table yourself.
    Return False to let the executor use its normal path
    (_materialize_relation / _materialize_incremental).
    """
    return False