amogh-jahagirdar commented on code in PR #614:
URL: https://github.com/apache/iceberg-python/pull/614#discussion_r1619789557
##########
pyiceberg/table/__init__.py:
##########
@@ -3537,6 +3537,106 @@ def update_partitions_map(
schema=table_schema,
)
+ def files(self, snapshot_id: Optional[int] = None) -> "pa.Table":
+ import pyarrow as pa
+
+ from pyiceberg.io.pyarrow import schema_to_pyarrow
+
+ schema = self.tbl.metadata.schema()
+ readable_metrics_struct = []
+
+ def _readable_metrics_struct(bound_type: PrimitiveType) ->
pa.StructType:
+ pa_bound_type = schema_to_pyarrow(bound_type)
+ return pa.struct([
+ pa.field("column_size", pa.int64(), nullable=True),
+ pa.field("value_count", pa.int64(), nullable=True),
+ pa.field("null_value_count", pa.int64(), nullable=True),
+ pa.field("nan_value_count", pa.int64(), nullable=True),
+ pa.field("lower_bound", pa_bound_type, nullable=True),
+ pa.field("upper_bound", pa_bound_type, nullable=True),
+ ])
+
+ for field in self.tbl.metadata.schema().fields:
+ readable_metrics_struct.append(
+ pa.field(schema.find_column_name(field.field_id),
_readable_metrics_struct(field.field_type), nullable=False)
+ )
+
+ files_schema = pa.schema([
+ pa.field('content', pa.int8(), nullable=False),
+ pa.field('file_path', pa.string(), nullable=False),
+ pa.field('file_format', pa.dictionary(pa.int32(), pa.string()),
nullable=False),
+ pa.field('spec_id', pa.int32(), nullable=False),
+ pa.field('record_count', pa.int64(), nullable=False),
+ pa.field('file_size_in_bytes', pa.int64(), nullable=False),
+ pa.field('column_sizes', pa.map_(pa.int32(), pa.int64()),
nullable=True),
+ pa.field('value_counts', pa.map_(pa.int32(), pa.int64()),
nullable=True),
+ pa.field('null_value_counts', pa.map_(pa.int32(), pa.int64()),
nullable=True),
+ pa.field('nan_value_counts', pa.map_(pa.int32(), pa.int64()),
nullable=True),
+ pa.field('lower_bounds', pa.map_(pa.int32(), pa.binary()),
nullable=True),
+ pa.field('upper_bounds', pa.map_(pa.int32(), pa.binary()),
nullable=True),
+ pa.field('key_metadata', pa.binary(), nullable=True),
+ pa.field('split_offsets', pa.list_(pa.int64()), nullable=True),
+ pa.field('equality_ids', pa.list_(pa.int32()), nullable=True),
+ pa.field('sort_order_id', pa.int32(), nullable=True),
+ pa.field('readable_metrics', pa.struct(readable_metrics_struct),
nullable=True),
+ ])
+
+ files = []
+
+ snapshot = self._get_snapshot(snapshot_id)
Review Comment:
Opening this up again for discussion. Actually, I think I agree with @geruh
that we actually do *not* want to fail if there's no current snapshot, and
rather return an empty list of files. If the explicitly specified snapshot ID
is invalid, it makes sense to fail.
That seems more correct to me from an API perspective.
"What are the files in this empty table? There are no files.
"What are the files in this table at snapshot some_invalid_snapshot? The
specified snapshot does not exist.".
It also is the same as what's done in the Java metadata table
implementations, which may be a useful semantic to preserve for people who want
to migrate some Spark metadata table queries to PyIceberg.
cc @Fokko @Gowthami03B what do you think?
--
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
