Fokko commented on code in PR #6437:
URL: https://github.com/apache/iceberg/pull/6437#discussion_r1059518886
##########
python/pyiceberg/io/pyarrow.py:
##########
@@ -437,3 +468,170 @@ def visit_or(self, left_result: pc.Expression,
right_result: pc.Expression) -> p
def expression_to_pyarrow(expr: BooleanExpression) -> pc.Expression:
return boolean_expression_visit(expr, _ConvertToArrowExpression())
+
+
+def project_table(
+ files: Iterable[FileScanTask], table: Table, row_filter:
BooleanExpression, projected_schema: Schema, case_sensitive: bool
+) -> pa.Table:
+ """Resolves the right columns based on the identifier
+
+ Args:
+ files(Iterable[FileScanTask]): A URI or a path to a local file
+ table(Table): The table that's being queried
+ row_filter(BooleanExpression): The expression for filtering rows
+ projected_schema(Schema): The output schema
+ case_sensitive(bool): Case sensitivity when looking up column names
+
+ Raises:
+ ResolveException: When an incompatible query is done
+ """
+
+ if isinstance(table.io, PyArrowFileIO):
+ scheme, path = PyArrowFileIO.parse_location(table.location())
+ fs = table.io.get_fs(scheme)
+ else:
+ raise ValueError(f"Expected PyArrowFileIO, got: {table.io}")
+
+ bound_row_filter = bind(table.schema(), row_filter,
case_sensitive=case_sensitive)
+
+ projected_field_ids = {
+ id for id in projected_schema.field_ids if not
isinstance(projected_schema.find_type(id), (MapType, ListType))
+ }.union(extract_field_ids(bound_row_filter))
+
+ tables = []
+ for task in files:
+ _, path = PyArrowFileIO.parse_location(task.file.file_path)
+
+ # Get the schema
+ with fs.open_input_file(path) as fout:
+ parquet_schema = pq.read_schema(fout)
+ schema_raw = parquet_schema.metadata.get(ICEBERG_SCHEMA)
+ file_schema = Schema.parse_raw(schema_raw)
+
+ pyarrow_filter = None
+ if row_filter is not AlwaysTrue():
+ translated_row_filter = translate_column_names(bound_row_filter,
file_schema, case_sensitive=case_sensitive)
+ bound_row_filter = bind(file_schema, translated_row_filter,
case_sensitive=case_sensitive)
+ pyarrow_filter = expression_to_pyarrow(bound_row_filter)
+
+ file_project_schema = prune_columns(file_schema, projected_field_ids,
select_full_types=False)
+
+ if file_schema is None:
+ raise ValueError(f"Missing Iceberg schema in Metadata for file:
{path}")
+
+ # Prune the stuff that we don't need anyway
+ file_project_schema_arrow = schema_to_pyarrow(file_project_schema)
+
+ arrow_table = ds.dataset(
+ source=[path], schema=file_project_schema_arrow,
format=ds.ParquetFileFormat(), filesystem=fs
+ ).to_table(filter=pyarrow_filter)
+
+ tables.append(to_requested_schema(projected_schema,
file_project_schema, arrow_table))
+
+ if len(tables) > 1:
+ return pa.concat_tables(tables)
+ else:
+ return tables[0]
+
+
+def to_requested_schema(requested_schema: Schema, file_schema: Schema, table:
pa.Table) -> pa.Table:
+ struct_array = visit_with_partner(
+ requested_schema, table, ArrowProjectionVisitor(file_schema,
len(table)), ArrowAccessor(file_schema)
+ )
+
+ arrays = []
+ fields = []
+ for pos, field in enumerate(requested_schema.fields):
+ array = struct_array.field(pos)
+ arrays.append(array)
+ fields.append(pa.field(field.name, array.type, field.optional))
+ return pa.Table.from_arrays(arrays, schema=pa.schema(fields))
+
+
+class ArrowProjectionVisitor(SchemaWithPartnerVisitor[pa.Array,
Optional[pa.Array]]):
+ file_schema: Schema
+ table_length: int
+
+ def __init__(self, file_schema: Schema, table_length: int):
+ self.file_schema = file_schema
+ self.table_length = table_length
+
+ def cast_if_needed(self, field: NestedField, values: pa.Array) -> pa.Array:
+ file_field = self.file_schema.find_field(field.field_id)
+ if field.field_type != file_field.field_type:
Review Comment:
Ah I see, this also allows us to remove the struct from the promotion.
Thanks!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
