Skip to content

graflo.architecture.contract.bindings.connectors

Resource connector types (file, SQL table, SPARQL).

FileConnector

Bases: ResourceConnector

Connector for matching files.

Attributes:

Name Type Description
regex str | None

Regular expression pattern for matching filenames
sub_path Path

Path to search for matching files (default: "./")
date_field str | None

Name of the date field to filter on (for date-based filtering)
date_filter str | None

SQL-style date filter condition (e.g., "> '2020-10-10'")
date_range_start str | None

Start date for range filtering (e.g., "2015-11-11")
date_range_days int | None

Number of days after start date (used with date_range_start)
Source code in graflo/architecture/contract/bindings/connectors.py 
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
class FileConnector(ResourceConnector):
    """Connector for matching files.

    Attributes:
        regex: Regular expression pattern for matching filenames
        sub_path: Path to search for matching files (default: "./")
        date_field: Name of the date field to filter on (for date-based filtering)
        date_filter: SQL-style date filter condition (e.g., "> '2020-10-10'")
        date_range_start: Start date for range filtering (e.g., "2015-11-11")
        date_range_days: Number of days after start date (used with date_range_start)
    """

    regex: str | None = None
    sub_path: pathlib.Path = Field(default_factory=lambda: pathlib.Path("./"))
    date_field: str | None = None
    date_filter: str | None = None
    date_range_start: str | None = None
    date_range_days: int | None = None

    @model_validator(mode="after")
    def _validate_file_connector(self) -> Self:
        """Ensure sub_path is a Path and validate date filtering parameters."""
        if not isinstance(self.sub_path, pathlib.Path):
            object.__setattr__(self, "sub_path", pathlib.Path(self.sub_path))
        if (self.date_filter or self.date_range_start) and not self.date_field:
            raise ValueError(
                "date_field is required when using date_filter or date_range_start"
            )
        if self.date_range_days is not None and not self.date_range_start:
            raise ValueError("date_range_start is required when using date_range_days")
        return self

    def matches(self, resource_identifier: str) -> bool:
        """Check if connector matches a filename.

        Args:
            resource_identifier: Filename to match

        Returns:
            bool: True if connector matches
        """
        if self.regex is None:
            return False
        return bool(re.match(self.regex, resource_identifier))

    def get_resource_type(self) -> ResourceType:
        """Get resource type.

        FileConnector always represents a FILE resource type.
        The specific file format (CSV, JSON, JSONL, Parquet, etc.) is
        automatically detected by the loader based on file extensions.
        """
        return ResourceType.FILE

get_resource_type()

Get resource type.

FileConnector always represents a FILE resource type. The specific file format (CSV, JSON, JSONL, Parquet, etc.) is automatically detected by the loader based on file extensions.

Source code in graflo/architecture/contract/bindings/connectors.py 
156
157
158
159
160
161
162
163
def get_resource_type(self) -> ResourceType:
    """Get resource type.

    FileConnector always represents a FILE resource type.
    The specific file format (CSV, JSON, JSONL, Parquet, etc.) is
    automatically detected by the loader based on file extensions.
    """
    return ResourceType.FILE

matches(resource_identifier)

Check if connector matches a filename.

Parameters:

Name Type Description Default
resource_identifier str

Filename to match

 required

Returns:

Name Type Description
bool bool

True if connector matches
Source code in graflo/architecture/contract/bindings/connectors.py 
143
144
145
146
147
148
149
150
151
152
153
154
def matches(self, resource_identifier: str) -> bool:
    """Check if connector matches a filename.

    Args:
        resource_identifier: Filename to match

    Returns:
        bool: True if connector matches
    """
    if self.regex is None:
        return False
    return bool(re.match(self.regex, resource_identifier))

JoinClause

Bases: ConfigBaseModel

Specification for a SQL JOIN operation.

Used by TableConnector to describe multi-table queries. Each JoinClause adds one JOIN to the generated SQL.

Attributes:

Name Type Description
table str

Table name to join (e.g. "all_classes").
schema_name str | None

Optional schema override for the joined table.
alias str | None

SQL alias for the joined table (e.g. "s", "t"). Required when the same table is joined more than once.
on_self str

Column on the base (left) table used in the ON condition.
on_other str

Column on the joined (right) table used in the ON condition.
join_type str

Type of join -- LEFT, INNER, etc. Defaults to LEFT.
select_fields list[str] | None

Explicit list of columns to SELECT from this join. When None every column of the joined table is included (aliased with the join alias prefix).
Source code in graflo/architecture/contract/bindings/connectors.py 
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
class JoinClause(ConfigBaseModel):
    """Specification for a SQL JOIN operation.

    Used by TableConnector to describe multi-table queries. Each JoinClause
    adds one JOIN to the generated SQL.

    Attributes:
        table: Table name to join (e.g. "all_classes").
        schema_name: Optional schema override for the joined table.
        alias: SQL alias for the joined table (e.g. "s", "t"). Required when
            the same table is joined more than once.
        on_self: Column on the base (left) table used in the ON condition.
        on_other: Column on the joined (right) table used in the ON condition.
        join_type: Type of join -- LEFT, INNER, etc. Defaults to LEFT.
        select_fields: Explicit list of columns to SELECT from this join.
            When None every column of the joined table is included (aliased
            with the join alias prefix).
    """

    table: str = Field(..., description="Table name to join.")
    schema_name: str | None = Field(
        default=None, description="Schema override for the joined table."
    )
    alias: str | None = Field(
        default=None, description="SQL alias for the joined table."
    )
    on_self: str = Field(
        ..., description="Column on the base table for the ON condition."
    )
    on_other: str = Field(
        ..., description="Column on the joined table for the ON condition."
    )
    join_type: str = Field(default="LEFT", description="JOIN type (LEFT, INNER, etc.).")
    select_fields: list[str] | None = Field(
        default=None,
        description="Columns to SELECT from this join (None = all columns).",
    )

ResourceConnector

Bases: ConfigBaseModel, ABC

Abstract base class for resource connectors (files or tables).

Provides common API for connector matching and resource identification. All concrete connector types inherit from this class.

Connectors only describe source-side matching/query behavior. Resource-to- connector linkage is handled by Bindings.

Source code in graflo/architecture/contract/bindings/connectors.py 
 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
class ResourceConnector(ConfigBaseModel, abc.ABC):
    """Abstract base class for resource connectors (files or tables).

    Provides common API for connector matching and resource identification.
    All concrete connector types inherit from this class.

    Connectors only describe source-side matching/query behavior. Resource-to-
    connector linkage is handled by ``Bindings``.
    """

    name: str | None = Field(
        default=None,
        description="Optional connector name used by top-level resource_connector mapping.",
    )
    resource_name: str | None = Field(
        default=None,
        description="Optional direct resource binding declared on the connector itself.",
    )
    hash: str = Field(
        default="",
        exclude=True,
        description="Deterministic internal connector id derived from defining fields.",
    )

    def _hash_payload(self) -> dict[str, Any]:
        payload = self.model_dump(
            mode="json",
            by_alias=True,
            exclude={"hash", "name", "resource_name"},
        )
        payload["_connector_type"] = type(self).__name__
        return payload

    @model_validator(mode="after")
    def _compute_hash(self) -> Self:
        canonical = json.dumps(
            self._hash_payload(), sort_keys=True, separators=(",", ":")
        )
        object.__setattr__(
            self,
            "hash",
            hashlib.sha256(canonical.encode("utf-8")).hexdigest(),
        )
        return self

    @abc.abstractmethod
    def matches(self, resource_identifier: str) -> bool:
        """Check if connector matches a resource identifier.

        Args:
            resource_identifier: Identifier to match (filename or table name)

        Returns:
            bool: True if connector matches
        """
        pass

    @abc.abstractmethod
    def get_resource_type(self) -> ResourceType:
        """Get the type of resource this connector matches.

        Returns:
            ResourceType: Resource type enum value
        """
        pass

get_resource_type() abstractmethod

Get the type of resource this connector matches.

Returns:

Name Type Description
ResourceType ResourceType

Resource type enum value
Source code in graflo/architecture/contract/bindings/connectors.py 
101
102
103
104
105
106
107
108
@abc.abstractmethod
def get_resource_type(self) -> ResourceType:
    """Get the type of resource this connector matches.

    Returns:
        ResourceType: Resource type enum value
    """
    pass

matches(resource_identifier) abstractmethod

Check if connector matches a resource identifier.

Parameters:

Name Type Description Default
resource_identifier str

Identifier to match (filename or table name)

 required

Returns:

Name Type Description
bool bool

True if connector matches
Source code in graflo/architecture/contract/bindings/connectors.py 
89
90
91
92
93
94
95
96
97
98
99
@abc.abstractmethod
def matches(self, resource_identifier: str) -> bool:
    """Check if connector matches a resource identifier.

    Args:
        resource_identifier: Identifier to match (filename or table name)

    Returns:
        bool: True if connector matches
    """
    pass

ResourceType

Bases: BaseEnum

Resource types for data sources.

Resource types distinguish between different data source categories. File type detection (CSV, JSON, JSONL, Parquet, etc.) is handled automatically by the loader based on file extensions.

Attributes:

Name Type Description
FILE

File-based data source (any format: CSV, JSON, JSONL, Parquet, etc.)
SQL_TABLE

SQL database table (e.g., PostgreSQL table)
SPARQL

SPARQL / RDF data source (endpoint or .ttl/.rdf files via rdflib)
Source code in graflo/architecture/contract/bindings/connectors.py 
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
class ResourceType(BaseEnum):
    """Resource types for data sources.

    Resource types distinguish between different data source categories.
    File type detection (CSV, JSON, JSONL, Parquet, etc.) is handled
    automatically by the loader based on file extensions.

    Attributes:
        FILE: File-based data source (any format: CSV, JSON, JSONL, Parquet, etc.)
        SQL_TABLE: SQL database table (e.g., PostgreSQL table)
        SPARQL: SPARQL / RDF data source (endpoint or .ttl/.rdf files via rdflib)
    """

    FILE = "file"
    SQL_TABLE = "sql_table"
    SPARQL = "sparql"

SparqlConnector

Bases: ResourceConnector

Connector for matching SPARQL / RDF data sources.

Each SparqlConnector targets instances of a single rdf:Class. It can be backed either by a remote SPARQL endpoint (Fuseki, Blazegraph, ...) or by a local RDF file parsed with rdflib.

Attributes:

Name Type Description
rdf_class str

Full URI of the rdf:Class whose instances this connector fetches (e.g. "http://example.org/Person").
endpoint_url str | None

SPARQL query endpoint URL. When set, instances are fetched via HTTP. When None the connector is for local file mode.
graph_uri str | None

Named-graph URI to restrict the query to (optional).
sparql_query str | None

Custom SPARQL SELECT query override. When provided the auto-generated per-class query is skipped.
rdf_file Path | None

Path to a local RDF file (.ttl, .rdf, .n3, .jsonld). Mutually exclusive with endpoint_url.
Source code in graflo/architecture/contract/bindings/connectors.py 
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
class SparqlConnector(ResourceConnector):
    """Connector for matching SPARQL / RDF data sources.

    Each ``SparqlConnector`` targets instances of a single ``rdf:Class``.
    It can be backed either by a remote SPARQL endpoint (Fuseki, Blazegraph, ...)
    or by a local RDF file parsed with *rdflib*.

    Attributes:
        rdf_class: Full URI of the ``rdf:Class`` whose instances this connector
            fetches (e.g. ``"http://example.org/Person"``).
        endpoint_url: SPARQL query endpoint URL.  When set, instances are
            fetched via HTTP.  When ``None`` the connector is for local file mode.
        graph_uri: Named-graph URI to restrict the query to (optional).
        sparql_query: Custom SPARQL ``SELECT`` query override.  When provided
            the auto-generated per-class query is skipped.
        rdf_file: Path to a local RDF file (``.ttl``, ``.rdf``, ``.n3``,
            ``.jsonld``).  Mutually exclusive with *endpoint_url*.
    """

    rdf_class: str = Field(
        ..., description="URI of the rdf:Class to fetch instances of"
    )
    endpoint_url: str | None = Field(
        default=None, description="SPARQL query endpoint URL"
    )
    graph_uri: str | None = Field(
        default=None, description="Named graph URI (optional)"
    )
    sparql_query: str | None = Field(
        default=None, description="Custom SPARQL query override"
    )
    rdf_file: pathlib.Path | None = Field(
        default=None, description="Path to a local RDF file"
    )

    def matches(self, resource_identifier: str) -> bool:
        """Match by the local name (fragment) of the rdf:Class URI.

        Args:
            resource_identifier: Identifier to match against

        Returns:
            True when *resource_identifier* equals the class local name
        """
        local_name = self.rdf_class.rsplit("#", 1)[-1].rsplit("/", 1)[-1]
        return resource_identifier == local_name

    def get_resource_type(self) -> ResourceType:
        """Return ``ResourceType.SPARQL``."""
        return ResourceType.SPARQL

    def build_select_query(self) -> str:
        """Build a SPARQL SELECT query for instances of ``rdf_class``.

        If *sparql_query* is set it is returned as-is.  Otherwise a simple
        per-class query is generated::

            SELECT ?s ?p ?o WHERE {
              ?s a <rdf_class> .
              ?s ?p ?o .
            }

        Returns:
            SPARQL query string
        """
        if self.sparql_query:
            return self.sparql_query

        graph_open = f"GRAPH <{self.graph_uri}> {{" if self.graph_uri else ""
        graph_close = "}" if self.graph_uri else ""

        return (
            "SELECT ?s ?p ?o WHERE { "
            f"{graph_open} "
            f"?s a <{self.rdf_class}> . "
            f"?s ?p ?o . "
            f"{graph_close} "
            "}"
        )

build_select_query()

Build a SPARQL SELECT query for instances of rdf_class.

If sparql_query is set it is returned as-is. Otherwise a simple per-class query is generated::

SELECT ?s ?p ?o WHERE {
  ?s a <rdf_class> .
  ?s ?p ?o .
}

Returns:

Type Description
str

SPARQL query string
Source code in graflo/architecture/contract/bindings/connectors.py 
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
def build_select_query(self) -> str:
    """Build a SPARQL SELECT query for instances of ``rdf_class``.

    If *sparql_query* is set it is returned as-is.  Otherwise a simple
    per-class query is generated::

        SELECT ?s ?p ?o WHERE {
          ?s a <rdf_class> .
          ?s ?p ?o .
        }

    Returns:
        SPARQL query string
    """
    if self.sparql_query:
        return self.sparql_query

    graph_open = f"GRAPH <{self.graph_uri}> {{" if self.graph_uri else ""
    graph_close = "}" if self.graph_uri else ""

    return (
        "SELECT ?s ?p ?o WHERE { "
        f"{graph_open} "
        f"?s a <{self.rdf_class}> . "
        f"?s ?p ?o . "
        f"{graph_close} "
        "}"
    )

get_resource_type()

Return ResourceType.SPARQL.

Source code in graflo/architecture/contract/bindings/connectors.py 
471
472
473
def get_resource_type(self) -> ResourceType:
    """Return ``ResourceType.SPARQL``."""
    return ResourceType.SPARQL

matches(resource_identifier)

Match by the local name (fragment) of the rdf:Class URI.

Parameters:

Name Type Description Default
resource_identifier str

Identifier to match against

 required

Returns:

Type Description
bool

True when resource_identifier equals the class local name
Source code in graflo/architecture/contract/bindings/connectors.py 
459
460
461
462
463
464
465
466
467
468
469
def matches(self, resource_identifier: str) -> bool:
    """Match by the local name (fragment) of the rdf:Class URI.

    Args:
        resource_identifier: Identifier to match against

    Returns:
        True when *resource_identifier* equals the class local name
    """
    local_name = self.rdf_class.rsplit("#", 1)[-1].rsplit("/", 1)[-1]
    return resource_identifier == local_name

TableConnector

Bases: ResourceConnector

Connector for matching database tables.

Supports simple single-table queries as well as multi-table JOINs and pushdown filters via FilterExpression.

Attributes:

Name Type Description
table_name str

Exact table name or regex pattern
schema_name str | None

Schema name (optional, defaults to public)
database str | None

Database name (optional)
date_field str | None

Name of the date field to filter on (for date-based filtering)
date_filter str | None

SQL-style date filter condition (e.g., "> '2020-10-10'")
date_range_start str | None

Start date for range filtering (e.g., "2015-11-11")
date_range_days int | None

Number of days after start date (used with date_range_start)
filters list[Any]

General-purpose pushdown filters rendered as SQL WHERE fragments.
joins list[JoinClause]

Multi-table JOIN specifications (auto-generated or explicit).
select_columns list[str] | None

Explicit SELECT column list. None means * for the base table (plus aliased columns from joins).
Source code in graflo/architecture/contract/bindings/connectors.py 
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
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
class TableConnector(ResourceConnector):
    """Connector for matching database tables.

    Supports simple single-table queries as well as multi-table JOINs and
    pushdown filters via ``FilterExpression``.

    Attributes:
        table_name: Exact table name or regex pattern
        schema_name: Schema name (optional, defaults to public)
        database: Database name (optional)
        date_field: Name of the date field to filter on (for date-based filtering)
        date_filter: SQL-style date filter condition (e.g., "> '2020-10-10'")
        date_range_start: Start date for range filtering (e.g., "2015-11-11")
        date_range_days: Number of days after start date (used with date_range_start)
        filters: General-purpose pushdown filters rendered as SQL WHERE fragments.
        joins: Multi-table JOIN specifications (auto-generated or explicit).
        select_columns: Explicit SELECT column list. None means ``*`` for the
            base table (plus aliased columns from joins).
    """

    table_name: str = Field(
        default="", validation_alias=AliasChoices("table_name", "table")
    )
    schema_name: str | None = Field(
        default=None, validation_alias=AliasChoices("schema_name", "schema")
    )
    database: str | None = None
    date_field: str | None = None
    date_filter: str | None = None
    date_range_start: str | None = None
    date_range_days: int | None = None
    filters: list[Any] = Field(
        default_factory=list,
        description="Pushdown FilterExpression filters (rendered to SQL WHERE).",
    )
    joins: list[JoinClause] = Field(
        default_factory=list,
        description="JOIN clauses for multi-table queries.",
    )
    select_columns: list[str] | None = Field(
        default=None,
        description="Explicit SELECT columns. None = SELECT * (plus join aliases).",
    )
    view: Any = Field(
        default=None,
        description="SelectSpec or dict for declarative view (alternative to table+joins+filters).",
    )

    @field_validator("view", mode="before")
    @classmethod
    def _coerce_view(cls, v: Any) -> Any:
        if v is None:
            return None
        if isinstance(v, dict):
            from graflo.filter.select import SelectSpec

            return SelectSpec.from_dict(v)
        return v

    @model_validator(mode="after")
    def _validate_table_connector(self) -> Self:
        """Validate table_name and date filtering parameters."""
        if not self.table_name:
            raise ValueError("table_name is required for TableConnector")
        if (self.date_filter or self.date_range_start) and not self.date_field:
            raise ValueError(
                "date_field is required when using date_filter or date_range_start"
            )
        if self.date_range_days is not None and not self.date_range_start:
            raise ValueError("date_range_start is required when using date_range_days")
        return self

    def matches(self, resource_identifier: str) -> bool:
        """Check if connector matches a table name.

        Args:
            resource_identifier: Table name to match (format: schema.table or just table)

        Returns:
            bool: True if connector matches
        """
        if not self.table_name:
            return False

        # Compile regex expression
        if self.table_name.startswith("^") or self.table_name.endswith("$"):
            # Already a regex expression
            compiled_regex = re.compile(self.table_name)
        else:
            # Exact match expression
            compiled_regex = re.compile(f"^{re.escape(self.table_name)}$")

        # Check if resource_identifier matches
        if compiled_regex.match(resource_identifier):
            return True

        # If schema_name is specified, also check schema.table format
        if self.schema_name:
            full_name = f"{self.schema_name}.{resource_identifier}"
            if compiled_regex.match(full_name):
                return True

        return False

    def get_resource_type(self) -> ResourceType:
        """Get resource type."""
        return ResourceType.SQL_TABLE

    def build_where_clause(self) -> str:
        """Build SQL WHERE clause from date filtering parameters **and** general filters.

        Returns:
            WHERE clause string (without the WHERE keyword) or empty string if no filters
        """
        from graflo.filter.onto import FilterExpression
        from graflo.onto import ExpressionFlavor

        conditions: list[str] = []

        # Date-specific conditions (legacy fields)
        if self.date_field:
            if self.date_range_start and self.date_range_days is not None:
                conditions.append(
                    f"\"{self.date_field}\" >= '{self.date_range_start}'::date"
                )
                conditions.append(
                    f"\"{self.date_field}\" < '{self.date_range_start}'::date + INTERVAL '{self.date_range_days} days'"
                )
            elif self.date_filter:
                filter_parts = self.date_filter.strip().split(None, 1)
                if len(filter_parts) == 2:
                    operator, value = filter_parts
                    if not (value.startswith("'") and value.endswith("'")):
                        if len(value) == 10 and value.count("-") == 2:
                            value = f"'{value}'"
                    conditions.append(f'"{self.date_field}" {operator} {value}')
                else:
                    conditions.append(f'"{self.date_field}" {self.date_filter}')

        # General-purpose FilterExpression filters
        for filt in self.filters:
            if isinstance(filt, FilterExpression):
                rendered = filt(kind=ExpressionFlavor.SQL)
                if rendered:
                    conditions.append(str(rendered))

        if conditions:
            return " AND ".join(conditions)
        return ""

    def build_query(self, effective_schema: str | None = None) -> str:
        """Build a complete SQL SELECT query.

        When ``view`` is set, delegates to ``view.build_sql()``. Otherwise
        incorporates the base table, any JoinClauses, explicit select_columns,
        date filters, and FilterExpression filters.

        Args:
            effective_schema: Schema to use if ``self.schema_name`` is None.

        Returns:
            Complete SQL query string.
        """
        schema = self.schema_name or effective_schema or "public"
        if self.view is not None:
            from graflo.filter.select import SelectSpec

            if isinstance(self.view, SelectSpec):
                return self.view.build_sql(schema=schema, base_table=self.table_name)
        base_alias = "r" if self.joins else None
        base_ref = f'"{schema}"."{self.table_name}"'
        if base_alias:
            base_ref_aliased = f"{base_ref} {base_alias}"
        else:
            base_ref_aliased = base_ref

        # --- SELECT ---
        select_parts: list[str] = []
        if self.select_columns is not None:
            select_parts = list(self.select_columns)
        elif self.joins:
            select_parts.append(f"{base_alias}.*")
            for jc in self.joins:
                alias = jc.alias or jc.table
                jc_schema = jc.schema_name or schema
                if jc.select_fields is not None:
                    for col in jc.select_fields:
                        select_parts.append(f'{alias}."{col}" AS "{alias}__{col}"')
                else:
                    select_parts.append(f"{alias}.*")
        else:
            select_parts.append("*")

        select_clause = ", ".join(select_parts)

        # --- FROM + JOINs ---
        from_clause = base_ref_aliased
        for jc in self.joins:
            jc_schema = jc.schema_name or schema
            alias = jc.alias or jc.table
            join_ref = f'"{jc_schema}"."{jc.table}"'
            left_col = (
                f'{base_alias}."{jc.on_self}"' if base_alias else f'"{jc.on_self}"'
            )
            right_col = f'{alias}."{jc.on_other}"'
            from_clause += (
                f" {jc.join_type} JOIN {join_ref} {alias} ON {left_col} = {right_col}"
            )

        query = f"SELECT {select_clause} FROM {from_clause}"

        # --- WHERE ---
        where = self.build_where_clause()
        if where:
            query += f" WHERE {where}"

        return query

build_query(effective_schema=None)

Build a complete SQL SELECT query.

When view is set, delegates to view.build_sql(). Otherwise incorporates the base table, any JoinClauses, explicit select_columns, date filters, and FilterExpression filters.

Parameters:

Name Type Description Default
effective_schema str | None

Schema to use if self.schema_name is None.

 None

Returns:

Type Description
str

Complete SQL query string.
Source code in graflo/architecture/contract/bindings/connectors.py 
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
def build_query(self, effective_schema: str | None = None) -> str:
    """Build a complete SQL SELECT query.

    When ``view`` is set, delegates to ``view.build_sql()``. Otherwise
    incorporates the base table, any JoinClauses, explicit select_columns,
    date filters, and FilterExpression filters.

    Args:
        effective_schema: Schema to use if ``self.schema_name`` is None.

    Returns:
        Complete SQL query string.
    """
    schema = self.schema_name or effective_schema or "public"
    if self.view is not None:
        from graflo.filter.select import SelectSpec

        if isinstance(self.view, SelectSpec):
            return self.view.build_sql(schema=schema, base_table=self.table_name)
    base_alias = "r" if self.joins else None
    base_ref = f'"{schema}"."{self.table_name}"'
    if base_alias:
        base_ref_aliased = f"{base_ref} {base_alias}"
    else:
        base_ref_aliased = base_ref

    # --- SELECT ---
    select_parts: list[str] = []
    if self.select_columns is not None:
        select_parts = list(self.select_columns)
    elif self.joins:
        select_parts.append(f"{base_alias}.*")
        for jc in self.joins:
            alias = jc.alias or jc.table
            jc_schema = jc.schema_name or schema
            if jc.select_fields is not None:
                for col in jc.select_fields:
                    select_parts.append(f'{alias}."{col}" AS "{alias}__{col}"')
            else:
                select_parts.append(f"{alias}.*")
    else:
        select_parts.append("*")

    select_clause = ", ".join(select_parts)

    # --- FROM + JOINs ---
    from_clause = base_ref_aliased
    for jc in self.joins:
        jc_schema = jc.schema_name or schema
        alias = jc.alias or jc.table
        join_ref = f'"{jc_schema}"."{jc.table}"'
        left_col = (
            f'{base_alias}."{jc.on_self}"' if base_alias else f'"{jc.on_self}"'
        )
        right_col = f'{alias}."{jc.on_other}"'
        from_clause += (
            f" {jc.join_type} JOIN {join_ref} {alias} ON {left_col} = {right_col}"
        )

    query = f"SELECT {select_clause} FROM {from_clause}"

    # --- WHERE ---
    where = self.build_where_clause()
    if where:
        query += f" WHERE {where}"

    return query

build_where_clause()

Build SQL WHERE clause from date filtering parameters and general filters.

Returns:

Type Description
str

WHERE clause string (without the WHERE keyword) or empty string if no filters
Source code in graflo/architecture/contract/bindings/connectors.py 
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
def build_where_clause(self) -> str:
    """Build SQL WHERE clause from date filtering parameters **and** general filters.

    Returns:
        WHERE clause string (without the WHERE keyword) or empty string if no filters
    """
    from graflo.filter.onto import FilterExpression
    from graflo.onto import ExpressionFlavor

    conditions: list[str] = []

    # Date-specific conditions (legacy fields)
    if self.date_field:
        if self.date_range_start and self.date_range_days is not None:
            conditions.append(
                f"\"{self.date_field}\" >= '{self.date_range_start}'::date"
            )
            conditions.append(
                f"\"{self.date_field}\" < '{self.date_range_start}'::date + INTERVAL '{self.date_range_days} days'"
            )
        elif self.date_filter:
            filter_parts = self.date_filter.strip().split(None, 1)
            if len(filter_parts) == 2:
                operator, value = filter_parts
                if not (value.startswith("'") and value.endswith("'")):
                    if len(value) == 10 and value.count("-") == 2:
                        value = f"'{value}'"
                conditions.append(f'"{self.date_field}" {operator} {value}')
            else:
                conditions.append(f'"{self.date_field}" {self.date_filter}')

    # General-purpose FilterExpression filters
    for filt in self.filters:
        if isinstance(filt, FilterExpression):
            rendered = filt(kind=ExpressionFlavor.SQL)
            if rendered:
                conditions.append(str(rendered))

    if conditions:
        return " AND ".join(conditions)
    return ""

get_resource_type()

Get resource type.

Source code in graflo/architecture/contract/bindings/connectors.py 
309
310
311
def get_resource_type(self) -> ResourceType:
    """Get resource type."""
    return ResourceType.SQL_TABLE

matches(resource_identifier)

Check if connector matches a table name.

Parameters:

Name Type Description Default
resource_identifier str

Table name to match (format: schema.table or just table)

 required

Returns:

Name Type Description
bool bool

True if connector matches
Source code in graflo/architecture/contract/bindings/connectors.py 
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
def matches(self, resource_identifier: str) -> bool:
    """Check if connector matches a table name.

    Args:
        resource_identifier: Table name to match (format: schema.table or just table)

    Returns:
        bool: True if connector matches
    """
    if not self.table_name:
        return False

    # Compile regex expression
    if self.table_name.startswith("^") or self.table_name.endswith("$"):
        # Already a regex expression
        compiled_regex = re.compile(self.table_name)
    else:
        # Exact match expression
        compiled_regex = re.compile(f"^{re.escape(self.table_name)}$")

    # Check if resource_identifier matches
    if compiled_regex.match(resource_identifier):
        return True

    # If schema_name is specified, also check schema.table format
    if self.schema_name:
        full_name = f"{self.schema_name}.{resource_identifier}"
        if compiled_regex.match(full_name):
            return True

    return False