tscottcoombes1 commented on code in PR #1534: URL: https://github.com/apache/iceberg-python/pull/1534#discussion_r1947257232
########## pyiceberg/table/upsert_util.py: ########## @@ -0,0 +1,153 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +from pyarrow import Table as pyarrow_table +import pyarrow as pa +from pyarrow import compute as pc +from pyiceberg import table as pyiceberg_table + +from pyiceberg.expressions import ( + BooleanExpression, + And, + EqualTo, + Or, + In, +) + +def create_match_filter(df: pyarrow_table, join_cols: list) -> BooleanExpression: + + unique_keys = df.select(join_cols).group_by(join_cols).aggregate([]) + + if len(join_cols) == 1: + return In(join_cols[0], unique_keys[0].to_pylist()) + else: + return Or(*[ + And(*[ + EqualTo(col, row[col]) + for col in join_cols + ]) + for row in unique_keys.to_pylist() + ]) + +def has_duplicate_rows(df: pyarrow_table, join_cols: list) -> bool: + """ + This function checks if there are duplicate rows in the source table based on the join columns. + It returns True if there are duplicate rows in the source table, otherwise it returns False. + """ + + source_dup_count = len( + df.select(join_cols) + .group_by(join_cols) + .aggregate([([], "count_all")]) + .filter(pc.field("count_all") > 1) + ) + + return source_dup_count > 0 + +def get_rows_to_update(source_table: pa.Table, target_table: pa.Table, join_cols: list) -> pa.Table: + + """ + This function takes the source_table, trims it down to rows that match in both source and target. + It then does a scan for the non-key columns to see if any are mis-aligned before returning the final row set to update + """ + + all_columns = set(source_table.column_names) + join_cols_set = set(join_cols) + + non_key_cols = list(all_columns - join_cols_set) + + + match_expr = None + + for col in join_cols: + target_values = target_table.column(col).to_pylist() + expr = pc.field(col).isin(target_values) + + if match_expr is None: + match_expr = expr + else: + match_expr = match_expr & expr + + + matching_source_rows = source_table.filter(match_expr) + + rows_to_update = [] + + for index in range(matching_source_rows.num_rows): Review Comment: it's potentially more efficient to do tablewise operations. with the aim of doing ``` select * from tbl1 except select * from tbl2 ``` you could do something like: * concat the two tables * count(*) over (partition by (all columns)), having count(*) > 1 * then exclude these rows from the update. you could reuse your code for deduping the source table. -- 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
