This is an automated email from the ASF dual-hosted git repository.
lzljs3620320 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/paimon.git
commit a8c1c26c8887dd2a43241b5dbf2c3ce1134ece1a
Author: JingsongLi <jingsongl...@gmail.com>
AuthorDate: Wed Sep 10 15:45:39 2025 +0800
[python] Rename binary row to generic row
---
.../pypaimon/manifest/manifest_file_manager.py | 40 +++++++++++-----------
.../pypaimon/manifest/manifest_list_manager.py | 12 +++----
.../pypaimon/manifest/schema/data_file_meta.py | 8 ++---
.../pypaimon/manifest/schema/manifest_entry.py | 4 +--
.../pypaimon/manifest/schema/simple_stats.py | 6 ++--
paimon-python/pypaimon/read/interval_partition.py | 6 ++--
paimon-python/pypaimon/read/partition_info.py | 4 +--
paimon-python/pypaimon/read/split.py | 4 +--
.../table/row/{binary_row.py => generic_row.py} | 14 ++++----
.../pypaimon/tests/py36/ao_read_write_test.py | 8 ++---
paimon-python/pypaimon/tests/reader_basic_test.py | 8 ++---
.../pypaimon/tests/test_file_store_commit.py | 4 +--
paimon-python/pypaimon/write/file_store_commit.py | 10 +++---
paimon-python/pypaimon/write/writer/data_writer.py | 14 ++++----
14 files changed, 71 insertions(+), 71 deletions(-)
diff --git a/paimon-python/pypaimon/manifest/manifest_file_manager.py
b/paimon-python/pypaimon/manifest/manifest_file_manager.py
index 15d880356c..cedc27f284 100644
--- a/paimon-python/pypaimon/manifest/manifest_file_manager.py
+++ b/paimon-python/pypaimon/manifest/manifest_file_manager.py
@@ -24,8 +24,8 @@ from pypaimon.manifest.schema.data_file_meta import
DataFileMeta
from pypaimon.manifest.schema.manifest_entry import (MANIFEST_ENTRY_SCHEMA,
ManifestEntry)
from pypaimon.manifest.schema.simple_stats import SimpleStats
-from pypaimon.table.row.binary_row import (BinaryRowDeserializer,
- BinaryRowSerializer)
+from pypaimon.table.row.generic_row import (GenericRowDeserializer,
+ GenericRowSerializer)
class ManifestFileManager:
@@ -54,26 +54,26 @@ class ManifestFileManager:
file_dict = dict(record['_FILE'])
key_dict = dict(file_dict['_KEY_STATS'])
key_stats = SimpleStats(
-
min_values=BinaryRowDeserializer.from_bytes(key_dict['_MIN_VALUES'],
-
self.trimmed_primary_key_fields),
-
max_values=BinaryRowDeserializer.from_bytes(key_dict['_MAX_VALUES'],
-
self.trimmed_primary_key_fields),
+
min_values=GenericRowDeserializer.from_bytes(key_dict['_MIN_VALUES'],
+
self.trimmed_primary_key_fields),
+
max_values=GenericRowDeserializer.from_bytes(key_dict['_MAX_VALUES'],
+
self.trimmed_primary_key_fields),
null_counts=key_dict['_NULL_COUNTS'],
)
value_dict = dict(file_dict['_VALUE_STATS'])
value_stats = SimpleStats(
-
min_values=BinaryRowDeserializer.from_bytes(value_dict['_MIN_VALUES'],
-
self.table.table_schema.fields),
-
max_values=BinaryRowDeserializer.from_bytes(value_dict['_MAX_VALUES'],
-
self.table.table_schema.fields),
+
min_values=GenericRowDeserializer.from_bytes(value_dict['_MIN_VALUES'],
+
self.table.table_schema.fields),
+
max_values=GenericRowDeserializer.from_bytes(value_dict['_MAX_VALUES'],
+
self.table.table_schema.fields),
null_counts=value_dict['_NULL_COUNTS'],
)
file_meta = DataFileMeta(
file_name=file_dict['_FILE_NAME'],
file_size=file_dict['_FILE_SIZE'],
row_count=file_dict['_ROW_COUNT'],
-
min_key=BinaryRowDeserializer.from_bytes(file_dict['_MIN_KEY'],
self.trimmed_primary_key_fields),
-
max_key=BinaryRowDeserializer.from_bytes(file_dict['_MAX_KEY'],
self.trimmed_primary_key_fields),
+
min_key=GenericRowDeserializer.from_bytes(file_dict['_MIN_KEY'],
self.trimmed_primary_key_fields),
+
max_key=GenericRowDeserializer.from_bytes(file_dict['_MAX_KEY'],
self.trimmed_primary_key_fields),
key_stats=key_stats,
value_stats=value_stats,
min_sequence_number=file_dict['_MIN_SEQUENCE_NUMBER'],
@@ -88,7 +88,7 @@ class ManifestFileManager:
)
entry = ManifestEntry(
kind=record['_KIND'],
-
partition=BinaryRowDeserializer.from_bytes(record['_PARTITION'],
self.partition_key_fields),
+
partition=GenericRowDeserializer.from_bytes(record['_PARTITION'],
self.partition_key_fields),
bucket=record['_BUCKET'],
total_buckets=record['_TOTAL_BUCKETS'],
file=file_meta
@@ -104,23 +104,23 @@ class ManifestFileManager:
avro_record = {
"_VERSION": 2,
"_KIND": entry.kind,
- "_PARTITION": BinaryRowSerializer.to_bytes(entry.partition),
+ "_PARTITION": GenericRowSerializer.to_bytes(entry.partition),
"_BUCKET": entry.bucket,
"_TOTAL_BUCKETS": entry.total_buckets,
"_FILE": {
"_FILE_NAME": entry.file.file_name,
"_FILE_SIZE": entry.file.file_size,
"_ROW_COUNT": entry.file.row_count,
- "_MIN_KEY":
BinaryRowSerializer.to_bytes(entry.file.min_key),
- "_MAX_KEY":
BinaryRowSerializer.to_bytes(entry.file.max_key),
+ "_MIN_KEY":
GenericRowSerializer.to_bytes(entry.file.min_key),
+ "_MAX_KEY":
GenericRowSerializer.to_bytes(entry.file.max_key),
"_KEY_STATS": {
- "_MIN_VALUES":
BinaryRowSerializer.to_bytes(entry.file.key_stats.min_values),
- "_MAX_VALUES":
BinaryRowSerializer.to_bytes(entry.file.key_stats.max_values),
+ "_MIN_VALUES":
GenericRowSerializer.to_bytes(entry.file.key_stats.min_values),
+ "_MAX_VALUES":
GenericRowSerializer.to_bytes(entry.file.key_stats.max_values),
"_NULL_COUNTS": entry.file.key_stats.null_counts,
},
"_VALUE_STATS": {
- "_MIN_VALUES":
BinaryRowSerializer.to_bytes(entry.file.value_stats.min_values),
- "_MAX_VALUES":
BinaryRowSerializer.to_bytes(entry.file.value_stats.max_values),
+ "_MIN_VALUES":
GenericRowSerializer.to_bytes(entry.file.value_stats.min_values),
+ "_MAX_VALUES":
GenericRowSerializer.to_bytes(entry.file.value_stats.max_values),
"_NULL_COUNTS": entry.file.value_stats.null_counts,
},
"_MIN_SEQUENCE_NUMBER": entry.file.min_sequence_number,
diff --git a/paimon-python/pypaimon/manifest/manifest_list_manager.py
b/paimon-python/pypaimon/manifest/manifest_list_manager.py
index dc9d5db44d..2fc1eea011 100644
--- a/paimon-python/pypaimon/manifest/manifest_list_manager.py
+++ b/paimon-python/pypaimon/manifest/manifest_list_manager.py
@@ -25,8 +25,8 @@ from pypaimon.manifest.schema.manifest_file_meta import (
MANIFEST_FILE_META_SCHEMA, ManifestFileMeta)
from pypaimon.manifest.schema.simple_stats import SimpleStats
from pypaimon.snapshot.snapshot import Snapshot
-from pypaimon.table.row.binary_row import (BinaryRowDeserializer,
- BinaryRowSerializer)
+from pypaimon.table.row.generic_row import (GenericRowDeserializer,
+ GenericRowSerializer)
class ManifestListManager:
@@ -58,11 +58,11 @@ class ManifestListManager:
for record in reader:
stats_dict = dict(record['_PARTITION_STATS'])
partition_stats = SimpleStats(
- min_values=BinaryRowDeserializer.from_bytes(
+ min_values=GenericRowDeserializer.from_bytes(
stats_dict['_MIN_VALUES'],
self.table.table_schema.get_partition_key_fields()
),
- max_values=BinaryRowDeserializer.from_bytes(
+ max_values=GenericRowDeserializer.from_bytes(
stats_dict['_MAX_VALUES'],
self.table.table_schema.get_partition_key_fields()
),
@@ -90,8 +90,8 @@ class ManifestListManager:
"_NUM_ADDED_FILES": meta.num_added_files,
"_NUM_DELETED_FILES": meta.num_deleted_files,
"_PARTITION_STATS": {
- "_MIN_VALUES":
BinaryRowSerializer.to_bytes(meta.partition_stats.min_values),
- "_MAX_VALUES":
BinaryRowSerializer.to_bytes(meta.partition_stats.max_values),
+ "_MIN_VALUES":
GenericRowSerializer.to_bytes(meta.partition_stats.min_values),
+ "_MAX_VALUES":
GenericRowSerializer.to_bytes(meta.partition_stats.max_values),
"_NULL_COUNTS": meta.partition_stats.null_counts,
},
"_SCHEMA_ID": meta.schema_id,
diff --git a/paimon-python/pypaimon/manifest/schema/data_file_meta.py
b/paimon-python/pypaimon/manifest/schema/data_file_meta.py
index cd1034ead9..a4eddabc55 100644
--- a/paimon-python/pypaimon/manifest/schema/data_file_meta.py
+++ b/paimon-python/pypaimon/manifest/schema/data_file_meta.py
@@ -23,7 +23,7 @@ from typing import List, Optional
from pypaimon.manifest.schema.simple_stats import (SIMPLE_STATS_SCHEMA,
SimpleStats)
-from pypaimon.table.row.binary_row import BinaryRow
+from pypaimon.table.row.generic_row import GenericRow
@dataclass
@@ -31,8 +31,8 @@ class DataFileMeta:
file_name: str
file_size: int
row_count: int
- min_key: BinaryRow
- max_key: BinaryRow
+ min_key: GenericRow
+ max_key: GenericRow
key_stats: SimpleStats
value_stats: SimpleStats
min_sequence_number: int
@@ -51,7 +51,7 @@ class DataFileMeta:
# not a schema field, just for internal usage
file_path: str = None
- def set_file_path(self, table_path: Path, partition: BinaryRow, bucket:
int):
+ def set_file_path(self, table_path: Path, partition: GenericRow, bucket:
int):
path_builder = table_path
partition_dict = partition.to_dict()
for field_name, field_value in partition_dict.items():
diff --git a/paimon-python/pypaimon/manifest/schema/manifest_entry.py
b/paimon-python/pypaimon/manifest/schema/manifest_entry.py
index 75a51f30c5..9a02341175 100644
--- a/paimon-python/pypaimon/manifest/schema/manifest_entry.py
+++ b/paimon-python/pypaimon/manifest/schema/manifest_entry.py
@@ -20,13 +20,13 @@ from dataclasses import dataclass
from pypaimon.manifest.schema.data_file_meta import (DATA_FILE_META_SCHEMA,
DataFileMeta)
-from pypaimon.table.row.binary_row import BinaryRow
+from pypaimon.table.row.generic_row import GenericRow
@dataclass
class ManifestEntry:
kind: int
- partition: BinaryRow
+ partition: GenericRow
bucket: int
total_buckets: int
file: DataFileMeta
diff --git a/paimon-python/pypaimon/manifest/schema/simple_stats.py
b/paimon-python/pypaimon/manifest/schema/simple_stats.py
index 55b2163e76..45982491b9 100644
--- a/paimon-python/pypaimon/manifest/schema/simple_stats.py
+++ b/paimon-python/pypaimon/manifest/schema/simple_stats.py
@@ -19,13 +19,13 @@
from dataclasses import dataclass
from typing import List, Optional
-from pypaimon.table.row.binary_row import BinaryRow
+from pypaimon.table.row.generic_row import GenericRow
@dataclass
class SimpleStats:
- min_values: BinaryRow
- max_values: BinaryRow
+ min_values: GenericRow
+ max_values: GenericRow
null_counts: Optional[List[int]]
diff --git a/paimon-python/pypaimon/read/interval_partition.py
b/paimon-python/pypaimon/read/interval_partition.py
index 3e0c637cd3..130e937f8b 100644
--- a/paimon-python/pypaimon/read/interval_partition.py
+++ b/paimon-python/pypaimon/read/interval_partition.py
@@ -22,7 +22,7 @@ from functools import cmp_to_key
from typing import Callable, List
from pypaimon.manifest.schema.data_file_meta import DataFileMeta
-from pypaimon.table.row.binary_row import BinaryRow
+from pypaimon.table.row.generic_row import GenericRow
@dataclass
@@ -91,7 +91,7 @@ class IntervalPartition:
@dataclass
class HeapRun:
run: List[DataFileMeta]
- comparator: Callable[[BinaryRow, BinaryRow], int]
+ comparator: Callable[[GenericRow, GenericRow], int]
def __lt__(self, other) -> bool:
my_last_max = self.run[-1].max_key
@@ -99,7 +99,7 @@ class HeapRun:
return self.comparator(my_last_max, other_last_max) < 0
-def default_key_comparator(key1: BinaryRow, key2: BinaryRow) -> int:
+def default_key_comparator(key1: GenericRow, key2: GenericRow) -> int:
if not key1 or not key1.values:
if not key2 or not key2.values:
return 0
diff --git a/paimon-python/pypaimon/read/partition_info.py
b/paimon-python/pypaimon/read/partition_info.py
index e07b37a619..08ba231c6c 100644
--- a/paimon-python/pypaimon/read/partition_info.py
+++ b/paimon-python/pypaimon/read/partition_info.py
@@ -19,7 +19,7 @@
from typing import Any, List
from pypaimon.schema.data_types import DataField
-from pypaimon.table.row.binary_row import BinaryRow
+from pypaimon.table.row.generic_row import GenericRow
class PartitionInfo:
@@ -27,7 +27,7 @@ class PartitionInfo:
Partition information about how the row mapping of outer row.
"""
- def __init__(self, mapping: List[int], partition: BinaryRow):
+ def __init__(self, mapping: List[int], partition: GenericRow):
self.mapping = mapping
self.partition_values = partition.values
self.partition_fields = partition.fields
diff --git a/paimon-python/pypaimon/read/split.py
b/paimon-python/pypaimon/read/split.py
index f3bfdbab6b..9b802d9880 100644
--- a/paimon-python/pypaimon/read/split.py
+++ b/paimon-python/pypaimon/read/split.py
@@ -20,14 +20,14 @@ from dataclasses import dataclass
from typing import List
from pypaimon.manifest.schema.data_file_meta import DataFileMeta
-from pypaimon.table.row.binary_row import BinaryRow
+from pypaimon.table.row.generic_row import GenericRow
@dataclass
class Split:
"""Implementation of Split for native Python reading."""
files: List[DataFileMeta]
- partition: BinaryRow
+ partition: GenericRow
bucket: int
_file_paths: List[str]
_row_count: int
diff --git a/paimon-python/pypaimon/table/row/binary_row.py
b/paimon-python/pypaimon/table/row/generic_row.py
similarity index 98%
rename from paimon-python/pypaimon/table/row/binary_row.py
rename to paimon-python/pypaimon/table/row/generic_row.py
index d52e38cf11..2f6d3d86ae 100644
--- a/paimon-python/pypaimon/table/row/binary_row.py
+++ b/paimon-python/pypaimon/table/row/generic_row.py
@@ -27,7 +27,7 @@ from pypaimon.table.row.row_kind import RowKind
@dataclass
-class BinaryRow:
+class GenericRow:
values: List[Any]
fields: List[DataField]
row_kind: RowKind = RowKind.INSERT
@@ -36,7 +36,7 @@ class BinaryRow:
return {self.fields[i].name: self.values[i] for i in
range(len(self.fields))}
-class BinaryRowDeserializer:
+class GenericRowDeserializer:
HEADER_SIZE_IN_BITS = 8
MAX_FIX_PART_DATA_SIZE = 7
HIGHEST_FIRST_BIT = 0x80 << 56
@@ -47,9 +47,9 @@ class BinaryRowDeserializer:
cls,
bytes_data: bytes,
data_fields: List[DataField]
- ) -> BinaryRow:
+ ) -> GenericRow:
if not bytes_data:
- return BinaryRow([], data_fields)
+ return GenericRow([], data_fields)
arity = len(data_fields)
actual_data = bytes_data
@@ -66,7 +66,7 @@ class BinaryRowDeserializer:
value = cls._parse_field_value(actual_data, 0,
null_bits_size_in_bytes, i, data_field.type)
fields.append(value)
- return BinaryRow(fields, data_fields, RowKind(actual_data[0]))
+ return GenericRow(fields, data_fields, RowKind(actual_data[0]))
@classmethod
def _calculate_bit_set_width_in_bytes(cls, arity: int) -> int:
@@ -235,12 +235,12 @@ class BinaryRowDeserializer:
)
-class BinaryRowSerializer:
+class GenericRowSerializer:
HEADER_SIZE_IN_BITS = 8
MAX_FIX_PART_DATA_SIZE = 7
@classmethod
- def to_bytes(cls, binary_row: BinaryRow) -> bytes:
+ def to_bytes(cls, binary_row: GenericRow) -> bytes:
arity = len(binary_row.fields)
null_bits_size_in_bytes = cls._calculate_bit_set_width_in_bytes(arity)
fixed_part_size = null_bits_size_in_bytes + arity * 8
diff --git a/paimon-python/pypaimon/tests/py36/ao_read_write_test.py
b/paimon-python/pypaimon/tests/py36/ao_read_write_test.py
index de174e6413..01a635b548 100644
--- a/paimon-python/pypaimon/tests/py36/ao_read_write_test.py
+++ b/paimon-python/pypaimon/tests/py36/ao_read_write_test.py
@@ -23,7 +23,7 @@ from pypaimon.schema.data_types import DataField, AtomicType
from pypaimon.table.row.row_kind import RowKind
-from pypaimon.table.row.binary_row import BinaryRow, BinaryRowSerializer,
BinaryRowDeserializer
+from pypaimon.table.row.generic_row import GenericRow, GenericRowSerializer,
GenericRowDeserializer
from pypaimon.api.options import Options
from pypaimon.catalog.catalog_context import CatalogContext
@@ -381,8 +381,8 @@ class RESTTableReadWritePy36Test(RESTCatalogBaseTest):
long_string = "This is a long string that exceeds 7 bytes"
values = [long_string]
- binary_row = BinaryRow(values, fields, RowKind.INSERT)
- serialized_bytes = BinaryRowSerializer.to_bytes(binary_row)
+ binary_row = GenericRow(values, fields, RowKind.INSERT)
+ serialized_bytes = GenericRowSerializer.to_bytes(binary_row)
# Verify the last 6 bytes are 0
# This is because the variable part data is rounded to the nearest
word (8 bytes)
@@ -390,7 +390,7 @@ class RESTTableReadWritePy36Test(RESTCatalogBaseTest):
self.assertEqual(serialized_bytes[-6:], b'\x00\x00\x00\x00\x00\x00')
self.assertEqual(serialized_bytes[20:62].decode('utf-8'), long_string)
# Deserialize to verify
- deserialized_row = BinaryRowDeserializer.from_bytes(serialized_bytes,
fields)
+ deserialized_row = GenericRowDeserializer.from_bytes(serialized_bytes,
fields)
self.assertEqual(deserialized_row.values[0], long_string)
self.assertEqual(deserialized_row.row_kind, RowKind.INSERT)
diff --git a/paimon-python/pypaimon/tests/reader_basic_test.py
b/paimon-python/pypaimon/tests/reader_basic_test.py
index 9402ae93f7..8b4ed05dd6 100644
--- a/paimon-python/pypaimon/tests/reader_basic_test.py
+++ b/paimon-python/pypaimon/tests/reader_basic_test.py
@@ -25,7 +25,7 @@ import pandas as pd
import pyarrow as pa
from pypaimon.table.row.row_kind import RowKind
-from pypaimon.table.row.binary_row import BinaryRow, BinaryRowSerializer,
BinaryRowDeserializer
+from pypaimon.table.row.generic_row import GenericRow, GenericRowSerializer,
GenericRowDeserializer
from pypaimon.schema.data_types import DataField, AtomicType
@@ -209,8 +209,8 @@ class ReaderBasicTest(unittest.TestCase):
long_string = "This is a long string that exceeds 7 bytes"
values = [long_string]
- binary_row = BinaryRow(values, fields, RowKind.INSERT)
- serialized_bytes = BinaryRowSerializer.to_bytes(binary_row)
+ binary_row = GenericRow(values, fields, RowKind.INSERT)
+ serialized_bytes = GenericRowSerializer.to_bytes(binary_row)
# Verify the last 6 bytes are 0
# This is because the variable part data is rounded to the nearest
word (8 bytes)
@@ -218,7 +218,7 @@ class ReaderBasicTest(unittest.TestCase):
self.assertEqual(serialized_bytes[-6:], b'\x00\x00\x00\x00\x00\x00')
self.assertEqual(serialized_bytes[20:62].decode('utf-8'), long_string)
# Deserialize to verify
- deserialized_row = BinaryRowDeserializer.from_bytes(serialized_bytes,
fields)
+ deserialized_row = GenericRowDeserializer.from_bytes(serialized_bytes,
fields)
self.assertEqual(deserialized_row.values[0], long_string)
self.assertEqual(deserialized_row.row_kind, RowKind.INSERT)
diff --git a/paimon-python/pypaimon/tests/test_file_store_commit.py
b/paimon-python/pypaimon/tests/test_file_store_commit.py
index 5110bc0f80..ac7ce95094 100644
--- a/paimon-python/pypaimon/tests/test_file_store_commit.py
+++ b/paimon-python/pypaimon/tests/test_file_store_commit.py
@@ -24,7 +24,7 @@ from unittest.mock import Mock, patch
from pypaimon.manifest.schema.data_file_meta import DataFileMeta
from pypaimon.manifest.schema.manifest_entry import ManifestEntry
from pypaimon.snapshot.snapshot_commit import PartitionStatistics
-from pypaimon.table.row.binary_row import BinaryRow
+from pypaimon.table.row.generic_row import GenericRow
from pypaimon.write.commit_message import CommitMessage
from pypaimon.write.file_store_commit import FileStoreCommit
@@ -379,7 +379,7 @@ class TestFileStoreCommit(unittest.TestCase):
def _to_entries(commit_messages):
commit_entries = []
for msg in commit_messages:
- partition = BinaryRow(list(msg.partition), None)
+ partition = GenericRow(list(msg.partition), None)
for file in msg.new_files:
commit_entries.append(ManifestEntry(
kind=0,
diff --git a/paimon-python/pypaimon/write/file_store_commit.py
b/paimon-python/pypaimon/write/file_store_commit.py
index ed9f5d16fc..8136117092 100644
--- a/paimon-python/pypaimon/write/file_store_commit.py
+++ b/paimon-python/pypaimon/write/file_store_commit.py
@@ -32,7 +32,7 @@ from pypaimon.snapshot.snapshot import Snapshot
from pypaimon.snapshot.snapshot_commit import (PartitionStatistics,
SnapshotCommit)
from pypaimon.snapshot.snapshot_manager import SnapshotManager
-from pypaimon.table.row.binary_row import BinaryRow
+from pypaimon.table.row.generic_row import GenericRow
from pypaimon.table.row.offset_row import OffsetRow
from pypaimon.write.commit_message import CommitMessage
@@ -66,7 +66,7 @@ class FileStoreCommit:
commit_entries = []
for msg in commit_messages:
- partition = BinaryRow(list(msg.partition),
self.table.table_schema.get_partition_key_fields())
+ partition = GenericRow(list(msg.partition),
self.table.table_schema.get_partition_key_fields())
for file in msg.new_files:
commit_entries.append(ManifestEntry(
kind=0,
@@ -106,7 +106,7 @@ class FileStoreCommit:
entry.kind = 1
commit_entries.append(entry)
for msg in commit_messages:
- partition = BinaryRow(list(msg.partition),
self.table.table_schema.get_partition_key_fields())
+ partition = GenericRow(list(msg.partition),
self.table.table_schema.get_partition_key_fields())
for file in msg.new_files:
commit_entries.append(ManifestEntry(
kind=0,
@@ -153,11 +153,11 @@ class FileStoreCommit:
num_added_files=added_file_count,
num_deleted_files=deleted_file_count,
partition_stats=SimpleStats(
- min_values=BinaryRow(
+ min_values=GenericRow(
values=partition_min_stats,
fields=self.table.table_schema.get_partition_key_fields(),
),
- max_values=BinaryRow(
+ max_values=GenericRow(
values=partition_max_stats,
fields=self.table.table_schema.get_partition_key_fields(),
),
diff --git a/paimon-python/pypaimon/write/writer/data_writer.py
b/paimon-python/pypaimon/write/writer/data_writer.py
index 4a197c6919..a7eb9cb2b8 100644
--- a/paimon-python/pypaimon/write/writer/data_writer.py
+++ b/paimon-python/pypaimon/write/writer/data_writer.py
@@ -28,7 +28,7 @@ from pypaimon.common.core_options import CoreOptions
from pypaimon.manifest.schema.data_file_meta import DataFileMeta
from pypaimon.manifest.schema.simple_stats import SimpleStats
from pypaimon.table.bucket_mode import BucketMode
-from pypaimon.table.row.binary_row import BinaryRow
+from pypaimon.table.row.generic_row import GenericRow
class DataWriter(ABC):
@@ -147,16 +147,16 @@ class DataWriter(ABC):
file_name=file_name,
file_size=self.file_io.get_file_size(file_path),
row_count=data.num_rows,
- min_key=BinaryRow(min_key, self.trimmed_primary_key_fields),
- max_key=BinaryRow(max_key, self.trimmed_primary_key_fields),
+ min_key=GenericRow(min_key, self.trimmed_primary_key_fields),
+ max_key=GenericRow(max_key, self.trimmed_primary_key_fields),
key_stats=SimpleStats(
- BinaryRow(min_key_stats, self.trimmed_primary_key_fields),
- BinaryRow(max_key_stats, self.trimmed_primary_key_fields),
+ GenericRow(min_key_stats, self.trimmed_primary_key_fields),
+ GenericRow(max_key_stats, self.trimmed_primary_key_fields),
key_null_counts,
),
value_stats=SimpleStats(
- BinaryRow(min_value_stats, self.table.table_schema.fields),
- BinaryRow(max_value_stats, self.table.table_schema.fields),
+ GenericRow(min_value_stats, self.table.table_schema.fields),
+ GenericRow(max_value_stats, self.table.table_schema.fields),
value_null_counts,
),
min_sequence_number=min_seq,
