python-table-processor 0.3.5__tar.gz → 0.3.7__tar.gz

{python_table_processor-0.3.5 → python_table_processor-0.3.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: python-table-processor
-Version: 0.3.5
+Version: 0.3.7
 Summary: A table data processor
 Home-page: https://github.com/akivajp/python-table-processor
 License: MIT

{python_table_processor-0.3.5 → python_table_processor-0.3.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-table-processor"
-version = "0.3.5"
+version = "0.3.7"
 description = "A table data processor"
 authors = ["Akiva Miura <akiva.miura@gmail.com>"]
 license = "MIT"

python_table_processor-0.3.7/table_processor/__init__.py

@@ -0,0 +1,2 @@
+__version__ = "0.3.7"
+__version_tuple__ = (0, 3, 7)

{python_table_processor-0.3.5 → python_table_processor-0.3.7}/table_processor/commands/merge_tables.py

@@ -15,7 +15,8 @@ def run(
         keys=args.keys,
         allow_duplicate_keys=args.allow_duplicate_keys,
         ignore_not_found=args.ignore_not_found,
-        output_file=args.output_file,
+        output_base_data_file=args.output_base_data_file,
+        output_modified_data_file=args.output_modified_data_file,
     )
 
 def setup_parser(
@@ -50,9 +51,13 @@ def setup_parser(
         help='Ignore not found',
     )
     parser.add_argument(
-        '--output-file', '--output', '-o',
-        metavar='OUTPUT_FILE',
+        '--output-base-data-file', '--output-base',
         required=False,
-        help='Path to the output file.',
+        help='Path to output base data file',
+    )
+    parser.add_argument(
+        '--output-modified-data-file', '--output-modified',
+        required=False,
+        help='Path to output modified data file',
     )
     parser.set_defaults(handler=run)

python_table_processor-0.3.7/table_processor/core/functions/set_nested_field_value.py

@@ -0,0 +1,41 @@
+'''
+Set the value of a field in a nested dictionary.
+'''
+
+from collections import OrderedDict
+from icecream import ic
+
+def set_nested_field_value(
+    data: OrderedDict | list,
+    field: str,
+    value: any,
+):
+    if isinstance(field, str) and  '.' in field:
+        field, rest = field.split('.', 1)
+        if isinstance(data, dict):
+            sub_data = data.get(field)
+        elif isinstance(data, list):
+            field = int(field)
+            if field < len(data):
+                sub_data = data[field]
+            else:
+                sub_data = None
+        if not isinstance(sub_data, dict):
+            do_create_dict = True
+            if isinstance(sub_data, list):
+                # NOTE: 続くフィールド文字列が数字の場合は、リストの要素として扱う
+                field2 = rest.split('.', 1)[0]
+                if field2.isdigit():
+                    do_create_dict = False
+            if do_create_dict:
+                data[field] = OrderedDict()
+        set_nested_field_value(data[field], rest, value)
+    else:
+        try:
+            if isinstance(data, dict):
+                data[field] = value
+            elif isinstance(data, list):
+                data[int(field)] = value
+        except:
+            ic(data, field, value)
+            raise

{python_table_processor-0.3.5 → python_table_processor-0.3.7}/table_processor/core/merge.py

@@ -45,7 +45,8 @@ def merge(
     keys: list[str],
     allow_duplicate_keys: bool = False,
     ignore_not_found: bool = False,
-    output_file: str | None = None,
+    output_base_data_file: str | None = None,
+    output_modified_data_file: str | None = None,
 ):
     ic.enable()
     ic()
@@ -53,7 +54,8 @@ def merge(
     ic(modification_files)
     ic(keys)
     dict_key_to_row = {}
-    all_rows = []
+    all_base_rows = []
+    all_modified_rows = []
     list_ignored_keys = []
     num_modified = 0
     for previous_file in previous_files:
@@ -83,9 +85,9 @@ def merge(
             if not allow_duplicate_keys:
                 if primary_key in dict_key_to_row:
                     ic(index)
-                    raise ValueError(f'Duplicate key: {key}')
+                    raise ValueError(f'Duplicate key: {primary_key}')
             dict_key_to_row[primary_key] = row
-            all_rows.append(row)
+            all_base_rows.append(row)
     for modification_file in modification_files:
         if not os.path.exists(modification_file):
             raise FileNotFoundError(f'File not found: {modification_file}')
@@ -123,6 +125,7 @@ def merge(
                 ic(index)
                 raise ValueError(f'Key not found: {primary_key}')
             previous_row = dict_key_to_row[primary_key]
+            all_modified_rows.append(previous_row)
             #ic(previous_row)
             #ic(previous_row.flat)
             for key, value in row.flat.items():
@@ -131,8 +134,6 @@ def merge(
                 #ic(key)
                 #ic(key, value)
                 set_row_value(previous_row, key, value)
-                #set_row_value(previous_row, '指示追従性？', 'test')
-                #set_row_value(previous_row, 'modified', True)
             #ic(previous_row)
             #ic(previous_row.flat)
             #raise
@@ -141,8 +142,11 @@ def merge(
     if ignore_not_found:
         ic(len(list_ignored_keys))
         ic(list_ignored_keys)
-    if output_file:
-        #all_df = pd.DataFrame(all_rows)
-        all_df = pd.DataFrame([row.flat for row in all_rows])
-        ic('Saving to: ', output_file)
-        save(all_df, output_file)
+    if output_base_data_file:
+        all_df = pd.DataFrame([row.flat for row in all_base_rows])
+        ic('Saving to: ', output_base_data_file)
+        save(all_df, output_base_data_file)
+    if output_modified_data_file:
+        all_df = pd.DataFrame([row.flat for row in all_modified_rows])
+        ic('Saving to: ', output_modified_data_file)
+        save(all_df, output_modified_data_file)

python_table_processor-0.3.5/table_processor/__init__.py

@@ -1,2 +0,0 @@
-__version__ = "0.3.5"
-__version_tuple__ = (0, 3, 5)

python_table_processor-0.3.5/table_processor/core/functions/set_nested_field_value.py

@@ -1,24 +0,0 @@
-'''
-Set the value of a field in a nested dictionary.
-'''
-
-from collections import OrderedDict
-from icecream import ic
-
-def set_nested_field_value(
-    data: OrderedDict,
-    field: str,
-    value: any,
-):
-    if isinstance(field, str) and  '.' in field:
-        field, rest = field.split('.', 1)
-        sub_data = data.get(field)
-        if not isinstance(sub_data, dict):
-            data[field] = OrderedDict()
-        set_nested_field_value(data[field], rest, value)
-    else:
-        try:
-            data[field] = value
-        except:
-            ic(data, field, value)
-            raise