input_data listなど：出力されたCSVでsystem_metadataなどネストされたオブジェクトは`system_…

…metadata._type`などの列に格納されるようにしました。 (#1221) * 修正 * update docs
kurusugawa-computer · Jun 12, 2024 · eab8c72 · eab8c72
1 parent 8f040e4
commit eab8c72
Show file tree

Hide file tree

Showing 5 changed files with 41 additions and 17 deletions.
diff --git a/annofabcli/input_data/list_all_input_data.py b/annofabcli/input_data/list_all_input_data.py
@@ -7,11 +7,12 @@
 from typing import Any, Dict, List, Optional, Set, Tuple
 
 import annofabapi
+import pandas
 from annofabapi.dataclass.input import InputData
 from annofabapi.models import ProjectMemberRole
 
 import annofabcli
-from annofabcli.common.cli import ArgumentParser, CommandLine, build_annofabapi_resource_and_login
+from annofabcli.common.cli import ArgumentParser, CommandLine, build_annofabapi_resource_and_login, print_according_to_format, print_csv
 from annofabcli.common.download import DownloadingFile
 from annofabcli.common.enums import FormatArgument
 from annofabcli.common.facade import AnnofabApiFacade, InputDataQuery, match_input_data_with_query
@@ -98,7 +99,15 @@ def main(self) -> None:
         logger.debug(f"入力データ一覧の件数: {len(input_data_list)}")
 
         if len(input_data_list) > 0:
-            self.print_according_to_format(input_data_list)
+            output_format = FormatArgument(args.format)
+            if output_format == FormatArgument.CSV:
+                # panadas.DataFramdでなくpandas.json_normalizeを使う理由:
+                # ネストしたオブジェクトを`system_metadata.input_daration`のような列名でアクセスできるようにするため
+                df = pandas.json_normalize(input_data_list)
+                print_csv(df, output=args.output)
+            else:
+                print_according_to_format(input_data_list, format=output_format, output=args.output)
+
         else:
             logger.info("入力データ一覧の件数が0件のため、出力しません。")
 

diff --git a/annofabcli/input_data/list_input_data.py b/annofabcli/input_data/list_input_data.py
@@ -1,13 +1,15 @@
 import argparse
 import logging
 import urllib.parse
+from pathlib import Path
 from typing import Any, Dict, List, Optional
 
 import annofabapi
+import pandas
 from annofabapi.models import InputData, Task
 
 import annofabcli
-from annofabcli.common.cli import ArgumentParser, CommandLine, build_annofabapi_resource_and_login
+from annofabcli.common.cli import ArgumentParser, CommandLine, build_annofabapi_resource_and_login, print_according_to_format, print_csv
 from annofabcli.common.enums import FormatArgument
 from annofabcli.common.facade import AnnofabApiFacade
 from annofabcli.common.visualize import AddProps
@@ -131,13 +133,15 @@ def get_input_data_list(
 
         return input_data_list
 
-    def print_input_data(  # noqa: ANN201
+    def print_input_data(
         self,
         project_id: str,
+        output_file: Optional[Path],
+        output_format: FormatArgument,
         input_data_query: Optional[Dict[str, Any]] = None,
         input_data_id_list: Optional[List[str]] = None,
         add_details: bool = False,  # noqa: FBT001, FBT002
-    ):
+    ) -> None:
         """
         入力データ一覧を出力する
 
@@ -162,7 +166,13 @@ def print_input_data(  # noqa: ANN201
             logger.warning("入力データ一覧は10,000件で打ち切られている可能性があります。")
 
         if len(input_data_list) > 0:
-            self.print_according_to_format(input_data_list)
+            if output_format == FormatArgument.CSV:
+                # panadas.DataFramdでなくpandas.json_normalizeを使う理由:
+                # ネストしたオブジェクトを`system_metadata.input_daration`のような列名でアクセスできるようにするため
+                df = pandas.json_normalize(input_data_list)
+                print_csv(df, output=output_file)
+            else:
+                print_according_to_format(input_data_list, format=output_format, output=output_file)
         else:
             logger.info("入力データの件数が0件のため、出力しません。")
 
@@ -173,6 +183,8 @@ def main(self) -> None:
         input_data_query = annofabcli.common.cli.get_json_from_args(args.input_data_query)
         self.print_input_data(
             args.project_id,
+            output_file=Path(args.output),
+            output_format=FormatArgument(args.format),
             input_data_id_list=input_data_id_list,
             input_data_query=input_data_query,
             add_details=args.add_details,

diff --git a/annofabcli/input_data/list_input_data_merged_task.py b/annofabcli/input_data/list_input_data_merged_task.py
@@ -70,16 +70,19 @@ def _filter_input_data(
             )
         return df
 
-    def create_input_data_merged_task(  # noqa: ANN201
+    def create_input_data_merged_task(
         self,
         input_data_list: List[Dict[str, Any]],
         task_list: List[Dict[str, Any]],
-        is_not_used_by_task: bool = False,  # noqa: FBT001, FBT002
-        is_used_by_multiple_task: bool = False,  # noqa: FBT001, FBT002
-    ):
+        *,
+        is_not_used_by_task: bool = False,
+        is_used_by_multiple_task: bool = False,
+    ) -> pandas.DataFrame:
         new_task_list = self._to_task_list_based_input_data(task_list)
 
-        df_input_data = pandas.DataFrame(input_data_list)
+        # panadas.DataFramdでなくpandas.json_normalizeを使う理由:
+        # ネストしたオブジェクトを`system_metadata.input_daration`のような列名でアクセスできるようにするため
+        df_input_data = pandas.json_normalize(input_data_list)
 
         df_task = pandas.DataFrame(new_task_list)
 

diff --git a/docs/command_reference/input_data/list/out.csv b/docs/command_reference/input_data/list/out.csv
@@ -1,3 +1,3 @@
-input_data_id,project_id,organization_id,input_data_set_id,input_data_name,input_data_path,url,etag,updated_datetime,original_input_data_path,sign_required,metadata,system_metadata
-input1,prj1,org1,12345678-abcd-1234-abcd-1234abcd5678,test-input1,s3://af-production-input/organizations/…,https://annofab.com/organizations/…,…,2021-01-04T21:21:28.169+09:00,s3://af-production-input/organizations/…,False,{},"{'resized_resolution': None, 'original_resolution': {'width': 128, 'height': 128}, '_type': 'Image'}"
-input2,prj1,org1,12345678-abcd-1234-abcd-1234abcd5678,test-input2,s3://af-production-input/organizations/…,https://annofab.com/organizations/…,…,2021-01-04T21:21:28.169+09:00,s3://af-production-input/organizations/…,False,{},"{'resized_resolution': None, 'original_resolution': {'width': 128, 'height': 128}, '_type': 'Image'}"
+input_data_id,project_id,organization_id,input_data_set_id,input_data_name,input_data_path,url,etag,updated_datetime,original_input_data_path,sign_required,metadata,system_metadata.original_resolution.width,system_metadata.original_resolution.height,system_metadata._type,system_metadata.resized_resolution.width,system_metadata.resized_resolution.height,system_metadata.original_resolution
+input1,prj1,org1,12345678-abcd-1234-abcd-1234abcd5678,test-input1,s3://af-production-input/organizations/…,https://annofab.com/organizations/…,…,2021-01-04T21:21:28.169+09:00,s3://af-production-input/organizations/…,False,,1280,720,Image,,,
+input2,prj1,org1,12345678-abcd-1234-abcd-1234abcd5678,test-input2,s3://af-production-input/organizations/…,https://annofab.com/organizations/…,…,2021-01-04T21:21:28.169+09:00,s3://af-production-input/organizations/…,False,,975,435,Image,640,285,
diff --git a/docs/command_reference/input_data/list_merged_task/out.csv b/docs/command_reference/input_data/list_merged_task/out.csv
@@ -1,3 +1,3 @@
-input_data_id,project_id,organization_id,input_data_set_id,input_data_name,input_data_path,url,etag,updated_datetime,original_input_data_path,sign_required,metadata,system_metadata,task_id,task_status,task_phase,worktime_hour
-input1,prj1,org1,12345678-abcd-1234-abcd-1234abcd5678,test-input1,s3://af-production-input/organizations/…,https://annofab.com/organizations/…,…,2021-01-04T21:21:28.169+09:00,s3://af-production-input/organizations/…,False,{},"{'resized_resolution': None, 'original_resolution': {'width': 128, 'height': 128}, '_type': 'Image'}",task1,not_started,annotation,0
-input2,prj1,org1,12345678-abcd-1234-abcd-1234abcd5678,test-input2,s3://af-production-input/organizations/…,https://annofab.com/organizations/…,…,2021-01-04T21:21:28.169+09:00,s3://af-production-input/organizations/…,False,{},"{'resized_resolution': None, 'original_resolution': {'width': 128, 'height': 128}, '_type': 'Image'}",task2,not_started,annotation,0
+input_data_id,project_id,organization_id,input_data_set_id,input_data_name,input_data_path,url,etag,updated_datetime,original_input_data_path,sign_required,metadata,system_metadata.resized_resolution,system_metadata.original_resolution.width,system_metadata.original_resolution.height,system_metadata._type,system_metadata.resized_resolution.width,system_metadata.resized_resolution.height,system_metadata.original_resolution,task_id,task_status,task_phase,worktime_hour
+input1,prj1,org1,12345678-abcd-1234-abcd-1234abcd5678,test-input1,s3://af-production-input/organizations/…,https://annofab.com/organizations/…,…,2021-01-04T21:21:28.169+09:00,s3://af-production-input/organizations/…,False,,,1280,720,Image,,,,task1,not_started,annotation,0
+input2,prj1,org1,12345678-abcd-1234-abcd-1234abcd5678,test-input2,s3://af-production-input/organizations/…,https://annofab.com/organizations/…,…,2021-01-04T21:21:28.169+09:00,s3://af-production-input/organizations/…,False,,,975,435,Image,640,285,,task2,not_started,annotation,0