python-table-converter 0.1.2__tar.gz → 0.2.1__tar.gz

{python_table_converter-0.1.2 → python_table_converter-0.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: python-table-converter
-Version: 0.1.2
+Version: 0.2.1
 Summary: A table data converter
 Home-page: https://github.com/akivajp/python-table-converter
 License: MIT
@@ -16,6 +16,7 @@ Requires-Dist: icecream (>=2.1.3,<3.0.0)
 Requires-Dist: logzero (>=1.7.0,<2.0.0)
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: pandas (>=2.2.3,<3.0.0)
+Requires-Dist: pyyaml (>=6.0.2,<7.0.0)
 Requires-Dist: tqdm (>=4.67.0,<5.0.0)
 Project-URL: Repository, https://github.com/akivajp/python-table-converter
 Description-Content-Type: text/markdown

{python_table_converter-0.1.2 → python_table_converter-0.2.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-table-converter"
-version = "0.1.2"
+version = "0.2.1"
 description = "A table data converter"
 authors = ["Akiva Miura <akiva.miura@gmail.com>"]
 license = "MIT"
@@ -25,6 +25,7 @@ logzero = "^1.7.0"
 tqdm = "^4.67.0"
 pandas = "^2.2.3"
 openpyxl = "^3.1.5"
+pyyaml = "^6.0.2"
 
 
 [build-system]

python_table_converter-0.2.1/table_converter/__init__.py

@@ -0,0 +1,2 @@
+__version__ = "0.2.1"
+__version_tuple__ = (0, 2, 1)

{python_table_converter-0.1.2 → python_table_converter-0.2.1}/table_converter/cli.py

@@ -2,6 +2,7 @@
 # -*- coding: utf-8 -*-
 
 import argparse
+import os
 import sys
 
 from icecream import ic
@@ -9,9 +10,14 @@ from icecream import ic
 def parse_and_run(
     parser: argparse.ArgumentParser,
 ):
-    ic.disable()
+    if os.environ.get('DEBUG', '').lower() in ['1', 'true', 'yes', 'on']:
+        pass
+    else:
+        ic.disable()
     ic()
     args = parser.parse_args()
+    if args.verbose:
+        ic.enable()
     ic(args)
     if args.handler:
         args.handler(args)
@@ -28,10 +34,10 @@ def command_convert_tables(
         )
     else:
         command_parser = parser
-    from . commands.convert_tables import setup_parser
+    from table_converter.commands.convert_tables import setup_parser
     setup_parser(command_parser)
     if parser is None:
-        parse_and_run(parser)
+        parse_and_run(command_parser)
 
 def main():
     parser = argparse.ArgumentParser(description='Table Data Converter')

{python_table_converter-0.1.2 → python_table_converter-0.2.1}/table_converter/commands/convert_tables.py

@@ -12,6 +12,7 @@ def run(
     convert(
         input_files = args.input_files,
         output_file = args.output_file,
+        config_path = args.config,
         assign_constants = args.assign_constants,
         assign_formats = args.assign_formats,
         pickup_columns= args.pickup_columns,
@@ -23,6 +24,10 @@ def run(
 def setup_parser(
     parser: argparse.ArgumentParser,
 ):
+    parser.add_argument(
+        '--verbose', '-v',
+        action='store_true',
+    )
     parser.add_argument(
         'input_files',
         metavar='INPUT_FILE',
@@ -30,11 +35,16 @@ def setup_parser(
         help='Path to the input file.'
     )
     parser.add_argument(
-        '-o', '--output-file',
+        '--output-file', '-o',
         metavar='OUTPUT_FILE',
         required=True,
         help='Path to the output file.'
     )
+    parser.add_argument(
+        '--config', '-c',
+        type=str,
+        help='Path to the configuration file.',
+    )
     parser.add_argument(
         '--pickup-columns',
         type=str,

python_table_converter-0.2.1/table_converter/core/config.py

@@ -0,0 +1,59 @@
+# -*- coding: utf-8 -*-
+
+from collections import OrderedDict
+import dataclasses
+from typing import Mapping
+
+from icecream import ic
+import yaml
+
+type FlatFieldMap = Mapping[str, str]
+type FieldMap = Mapping[str, str|FieldMap]
+
+@dataclasses.dataclass
+class ProcessConfig:
+    split_by_newline: FlatFieldMap = dataclasses.field(default_factory=OrderedDict)
+
+@dataclasses.dataclass
+class Config:
+    map: FieldMap = dataclasses.field(default_factory=OrderedDict)
+    process: ProcessConfig = dataclasses.field(default_factory=ProcessConfig)
+
+def flatten(
+    mapping: FieldMap,
+    parent_key: str = '',
+    new_mapping: FlatFieldMap | None = None,
+) -> FlatFieldMap:
+    if new_mapping is None:
+        new_mapping = OrderedDict()
+    for key, mapped in mapping.items():
+        new_key = f'{parent_key}.{key}' if parent_key else key
+        if isinstance(mapped, Mapping):
+            flatten(mapped, new_key, new_mapping)
+        else:
+            new_mapping[new_key] = mapped
+    return new_mapping
+
+def setup_config(
+    config_path: str | None = None,
+):
+    config = Config()
+    if config_path:
+        if config_path.endswith('.yaml'):
+            yaml.add_constructor(
+                yaml.resolver.BaseResolver.DEFAULT_MAPPING_TAG,
+                lambda loader, node: OrderedDict(loader.construct_pairs(node)),
+            )
+            with open(config_path, 'r') as f:
+                loaded = yaml.load(f, yaml.Loader)
+        else:
+            raise ValueError(
+                'Only YAML configuration files are supported.'
+            )
+        ic(loaded)
+        if 'map' in loaded:
+            config.map = flatten(loaded['map'])
+        if 'process' in loaded:
+            if 'split_by_newline' in loaded['process']:
+                config.process.split_by_newline = flatten(loaded['process']['split_by_newline'])
+    return config

{python_table_converter-0.1.2 → python_table_converter-0.2.1}/table_converter/core/convert.py

@@ -5,9 +5,15 @@ import os
 
 from collections import OrderedDict
 
+# 3-rd party modules
+
+from icecream import ic
 import numpy as np
 import pandas as pd
-from icecream import ic
+
+# local
+
+from . config import setup_config
 
 dict_loaders: dict[str, callable] = {}
 def register_loader(
@@ -227,6 +233,7 @@ def assign_id(
 def convert(
     input_files: list[str],
     output_file: str | None = None,
+    config_path: str | None = None,
     assign_constants: str | None = None,
     assign_formats: str | None = None,
     pickup_columns: str | None = None,
@@ -234,16 +241,16 @@ def convert(
     fields_to_assign_ids: str | None = None,
     output_debug: bool = False,
 ):
+    ic.enable()
     ic()
     ic(input_files)
     df_list = []
     dict_constants: OrderedDict | None = None
-    dict_columns: OrderedDict | None = None
     dict_formats: OrderedDict | None = None
-    #list_fields_to_split_by_newline = None
-    dict_split_by_newline: OrderedDict | None = None
     dict_assign_ids= None
     root_id_stat = create_id_stat_node()
+    config = setup_config(config_path)
+    ic(config)
     if assign_constants:
         dict_constants = OrderedDict()
         fields = assign_constants.split(',')
@@ -263,22 +270,19 @@ def convert(
             else:
                 raise ValueError(f'Invalid template assignment: {field}')
     if pickup_columns:
-        dict_columns = OrderedDict()
         fields = pickup_columns.split(',')
         for field in fields:
             if '=' in field:
                 dst, value = field.split('=')
-                dict_columns[dst] = value
+                config.map[dst] = value
             else:
-                dict_columns[field] = field
+                config.map[field] = field
     if fields_to_split_by_newline:
-        #list_fields_to_split_by_newline = fields_to_split_by_newline.split(',')
-        dict_split_by_newline = OrderedDict()
         fields = fields_to_split_by_newline.split(',')
         for field in fields:
             if '=' in field:
                 dst, src = field.split('=')
-                dict_split_by_newline[dst] = src
+                config.process.split_by_newline[dst] = src
             else:
                 raise ValueError(f'Invalid split by newline: {field}')
     if fields_to_assign_ids:
@@ -295,6 +299,7 @@ def convert(
         if ext not in dict_savers:
             raise ValueError(f'Unsupported file type: {ext}')
         saver = dict_savers[ext]
+    ic(config)
     for input_file in input_files:
         ic(input_file)
         if not os.path.exists(input_file):
@@ -318,18 +323,16 @@ def convert(
             set_field_value(new_row, '__debug__.__file__', input_file)
             if dict_constants:
                 new_row = map_constants(new_row, dict_constants)
-            if dict_columns:
-                new_row = remap_columns(new_row, dict_columns)
-            #if list_fields_to_split_by_newline:
-            #    new_row = apply_fields_split_by_newline(new_row, list_fields_to_split_by_newline)
-            if dict_split_by_newline:
-                new_row = apply_fields_split_by_newline(new_row, dict_split_by_newline)
+            if config.map:
+                new_row = remap_columns(new_row, config.map)
+            if config.process.split_by_newline:
+                new_row = apply_fields_split_by_newline(new_row, config.process.split_by_newline)
             if dict_assign_ids:
                 new_row = assign_id(new_row, dict_assign_ids, root_id_stat)
             if dict_formats:
                 new_row = map_formats(new_row, dict_formats)
-            if dict_columns:
-                new_row = remap_columns(new_row, dict_columns)
+            if config.map:
+                new_row = remap_columns(new_row, config.map)
             if not output_debug:
                 new_row.pop('__debug__', None)
             new_rows.append(new_row)

python_table_converter-0.1.2/table_converter/__init__.py

@@ -1,2 +0,0 @@
-__version__ = "0.1.2"
-__version_tuple__ = (0, 1, 2)