python-table-processor 0.3.4__py3-none-any.whl → 0.3.6__py3-none-any.whl

{python_table_processor-0.3.4.dist-info → python_table_processor-0.3.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: python-table-processor
-Version: 0.3.4
+Version: 0.3.6
 Summary: A table data processor
 Home-page: https://github.com/akivajp/python-table-processor
 License: MIT

{python_table_processor-0.3.4.dist-info → python_table_processor-0.3.6.dist-info}/RECORD

@@ -1,23 +1,23 @@
-table_processor/__init__.py,sha256=7OSG5h81lLUUtcYTKQ2mDbsjJLsWCC6uFVXVJlfe8FE,52
+table_processor/__init__.py,sha256=NnfhwEniUS8sdLDZO-0YfiWrkT_whyk4dJmhf1LDoHs,52
 table_processor/cli.py,sha256=uluf_VsBzq3Ldxh3ePGseSrv8--lI7huu-6RjDaHPPg,2170
-table_processor/commands/convert_tables.py,sha256=j25KL0zRl5ikrBk73jAkKn4rPmDq7SecChZxecDpILQ,2123
-table_processor/commands/merge_tables.py,sha256=Uu-hjfPh69Of0_OZrY8sY0oscpLSdK4jwJ_t1qgfPMg,1485
+table_processor/commands/convert_tables.py,sha256=w4IZftSlrbt-BMPjldULT_616LSiNE3h7GmrFF7K5OM,2276
+table_processor/commands/merge_tables.py,sha256=jryGU3gUx2TlGrI6FozGS_aJQvJQFco2LKwun6Uo9KY,1719
 table_processor/core/actions.py,sha256=GKUKzoPxUEuWSeuY-HsqFoS5Bdm99bjkRhuBgG1s_uk,23658
 table_processor/core/config.py,sha256=Z1s2r3y4oQXdbDCwIY_hYzoq6VRv7Sb3oUlfBCu13Lc,11646
 table_processor/core/constants.py,sha256=w-1TxtpXywb6Qh8M4YWuzcCHUvCjy5zJYxaXC3RQS6A,158
-table_processor/core/convert.py,sha256=cibzqJ5hHsfX_7qUz4kE2Gi-WH4UMqecBl3kSb4IVsY,11140
+table_processor/core/convert.py,sha256=dzGcpBwJ5omiE8Pw-VmHnGoOqDyh1Rip6BiLdvdf3V8,11561
 table_processor/core/functions/assign_id.py,sha256=dA-wgZA7E01gbx8qGvo1PeMd3aq9PhMdyITzr3BKXIE,4204
 table_processor/core/functions/flatten_row.py,sha256=2l-s4YXgBM58IthpfVzd7L4EGUCekSi7ss5CaM_3MUU,686
-table_processor/core/functions/get_nested_field_value.py,sha256=vF4pH6nxR3-2bDfAvrMfHcPFNiS4MnGkXL8FdcScdIw,685
+table_processor/core/functions/get_nested_field_value.py,sha256=ZEJi8XtDONoYmhPoqYpVZRGtEWvsfAksV4FXtkMAaq8,946
 table_processor/core/functions/nest_row.py,sha256=b5AKfxE39g-NOLranQRy0dfTZq-27Or8ZlgCB8N5kFs,640
 table_processor/core/functions/search_column_value.py,sha256=GscwLaMTORHFDhdCdjzdoy46UGyFHrGwDQA2b_tZhsQ,740
 table_processor/core/functions/set_flat_field_value.py,sha256=7-BgD2yEUGyBaFaIJ18bYv82Qdy0CN8NiC5ZtsAdv44,531
 table_processor/core/functions/set_nested_field_value.py,sha256=csO0v_nW94q-M9bNL91xR-TLHPXDDxnLK8gN-0LLd6k,595
 table_processor/core/functions/set_row_value.py,sha256=wlF_nVGZY74XCzd6pBJJyti62m6y0s1kc5Q6uq9jn8o,641
-table_processor/core/merge.py,sha256=Yc5OV9n1xV9QtgY4srl6Susd5cOKbuYseEtYuBampDw,4672
+table_processor/core/merge.py,sha256=Sqnr-d7XCkRHvypExsHLboJBKxemPWnLNhKB0CuCPN8,5157
 table_processor/core/types.py,sha256=xNvy1vL1ei87kt-MgSfRJSllYrNKRo23pHtJA15DyLQ,2895
-python_table_processor-0.3.4.dist-info/LICENSE,sha256=1_Gn0I1neLPxDLfLiHEyxjDg-pbAra1p2iHEqutGS_c,1068
-python_table_processor-0.3.4.dist-info/METADATA,sha256=c9BCBmEomxvkfcU2FpuhGvFT2TM183wdYiCcDy4yQQA,1098
-python_table_processor-0.3.4.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-python_table_processor-0.3.4.dist-info/entry_points.txt,sha256=lq97F6m51yZ93qmVIqkUHJfbILZuYLxrMWXSqrP4JpM,118
-python_table_processor-0.3.4.dist-info/RECORD,,
+python_table_processor-0.3.6.dist-info/LICENSE,sha256=1_Gn0I1neLPxDLfLiHEyxjDg-pbAra1p2iHEqutGS_c,1068
+python_table_processor-0.3.6.dist-info/METADATA,sha256=TgRGjK9lb7EFMdnyoZMffMiOz16SR2HEzc7w442DtvE,1098
+python_table_processor-0.3.6.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+python_table_processor-0.3.6.dist-info/entry_points.txt,sha256=lq97F6m51yZ93qmVIqkUHJfbILZuYLxrMWXSqrP4JpM,118
+python_table_processor-0.3.6.dist-info/RECORD,,

table_processor/__init__.py

@@ -1,2 +1,2 @@
-__version__ = "0.3.4"
-__version_tuple__ = (0, 3, 4)
+__version__ = "0.3.6"
+__version_tuple__ = (0, 3, 6)

table_processor/commands/convert_tables.py

@@ -20,6 +20,7 @@ def run(
         output_debug = args.output_debug,
         verbose = args.verbose,
         ignore_file_rows = args.ignore_file_rows,
+        skip_header = args.skip_header,
     )
 
 def setup_parser(
@@ -77,4 +78,9 @@ def setup_parser(
         action='store_true',
         help='Output debug information',
     )
+    parser.add_argument(
+        '--skip-header',
+        action='store_true',
+        help='Skip header',
+    )
     parser.set_defaults(handler=run)

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)

table_processor/core/convert.py

@@ -64,12 +64,13 @@ def register_loader(
 
 def load(
     input_file: str,
+    **kwargs,
 ):
     ext = os.path.splitext(input_file)[1]
     if ext not in dict_loaders:
         raise ValueError(f'Unsupported file type: {ext}')
     loader = dict_loaders[ext]
-    return loader(input_file)
+    return loader(input_file, **kwargs)
 
 dict_savers: dict[str, callable] = {}
 def register_saver(
@@ -93,16 +94,34 @@ def save(
 @register_loader('.csv')
 def load_csv(
     input_file: str,
+    **kwargs,
 ):
+    skip_header = kwargs.get('skip_header', False)
     # utf-8
     #df = pd.read_csv(input_file)
     # UTF-8 with BOM
-    df = pd.read_csv(input_file, encoding='utf-8-sig')
+    if skip_header:
+        df = pd.read_csv(
+            input_file,
+            encoding='utf-8-sig',
+            header=None,
+        )
+        #new_column_names = [f'__values__.{i}' for i in df.columns]
+        new_column_names = [f'{i}' for i in df.columns]
+        df = df.rename(columns=dict(
+            zip(df.columns, new_column_names)
+        ))
+    else:
+        df = pd.read_csv(
+            input_file,
+            encoding='utf-8-sig',
+        )
     return df
 
 @register_loader('.xlsx')
 def load_excel(
     input_file: str,
+    **kwargs,
 ):
     #df = pd.read_excel(input_file)
     # NOTE: Excelで勝手に日時データなどに変換されてしまうことを防ぐため
@@ -123,6 +142,7 @@ def load_excel(
 @register_loader('.json')
 def load_json(
     input_file: str,
+    **kiwargs,
 ):
     with open(input_file, 'r') as f:
         data = json.load(f)
@@ -165,6 +185,7 @@ def save_json(
 @register_loader('.jsonl')
 def load_jsonl(
     input_file: str,
+    **kwargs,
 ):
     rows = []
     with open(input_file, 'r') as f:
@@ -274,6 +295,7 @@ def convert(
     action_delimiter: str = ':',
     verbose: bool = False,
     ignore_file_rows: list[str] | None = None,
+    skip_header: bool = False,
 ):
     ic.enable()
     ic()
@@ -306,11 +328,7 @@ def convert(
         if not os.path.exists(input_file):
             raise FileNotFoundError(f'File not found: {input_file}')
         base_name = os.path.basename(input_file)
-        ext = os.path.splitext(input_file)[1]
-        ic(ext)
-        if ext not in dict_loaders:
-            raise ValueError(f'Unsupported file type: {ext}')
-        df = dict_loaders[ext](input_file)
+        df = load(input_file, skip_header=skip_header)
         # NOTE: NaN を None に変換しておかないと厄介
         df = df.replace([np.nan], [None])
         #ic(df)

table_processor/core/functions/get_nested_field_value.py

@@ -15,11 +15,17 @@ def get_nested_field_value(
             if index < len(data):
                 return data[index], True
             return None, False
+        if '.' in field:
+            field, rest = field.split('.', 1)
+            if field.isdigit():
+                index = int(field)
+                if index < len(data):
+                    return get_nested_field_value(data[index], rest)
     if isinstance(data, dict):
         if field in data:
             return data[field], True
-    if '.' in field:
-        field, rest = field.split('.', 1)
-        if field in data:
-            return get_nested_field_value(data[field], rest)
+        if '.' in field:
+            field, rest = field.split('.', 1)
+            if field in data:
+                return get_nested_field_value(data[field], rest)
     return None, False

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:
@@ -85,7 +87,7 @@ def merge(
                     ic(index)
                     raise ValueError(f'Duplicate key: {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}')
@@ -116,17 +118,21 @@ def merge(
             #    dict_key_to_row[key].flat.update(row.flat)
             if primary_key not in dict_key_to_row:
                 if ignore_not_found:
+                    ic(primary_key)
+                    ic(row.flat['__staging__.__file_row_index__'])
                     list_ignored_keys.append(primary_key)
                     continue
                 ic(index)
-                raise ValueError(f'Key not found: {key}')
+                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():
                 if key.startswith('__staging__.'):
                     continue
-                ic(key, value)
+                #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)
@@ -138,8 +144,11 @@ 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)