[#130] Add command line option to default configuration options.

Author: kindly

examples/help/unflatten/expected.txt

@@ -9,6 +9,7 @@ usage: flatten-tool unflatten [-h] -f INPUT_FORMAT [--xml] [--id-name ID_NAME]
                               [--metatab-schema METATAB_SCHEMA]
                               [--metatab-only]
                               [--metatab-vertical-orientation]
+                              [--default-configuration DEFAULT_CONFIGURATION]
                               input_name
 
 positional arguments:
@@ -60,4 +61,7 @@ optional arguments:
   --metatab-vertical-orientation
                         Read metatab so that headings are in the first column
                         and data is read vertically. Only for XLSX not CSV
+  --default-configuration DEFAULT_CONFIGURATION
+                        Comma seperated list of default parsing commands for
+                        all sheets. Only for XLSX not CSV
 

flattentool/__init__.py

@@ -4,6 +4,7 @@
 from flattentool.output import FORMATS_SUFFIX
 from flattentool.input import FORMATS as INPUT_FORMATS
 from flattentool.xml_output import toxml
+from flattentool.lib import parse_sheet_configuration
 import sys
 import json
 import codecs
@@ -112,6 +113,7 @@ def unflatten(input_name, base_json=None, input_format=None, output_name=None,
               vertical_orientation=False,
               metatab_name=None, metatab_only=False, metatab_schema='',
               metatab_vertical_orientation=False,
+              default_configuration='',
               **_):
     """
     Unflatten a flat structure (spreadsheet - csv or xlsx) into a nested structure (JSON).
@@ -130,7 +132,10 @@ def unflatten(input_name, base_json=None, input_format=None, output_name=None,
     else:
         base = OrderedDict()
 
-    base_configuration = {}
+
+    base_configuration = parse_sheet_configuration(
+        [item.strip() for item in default_configuration.split(",")]
+    )
 
     cell_source_map_data = OrderedDict()
     heading_source_map_data = OrderedDict()

flattentool/cli.py

@@ -155,6 +155,9 @@ def create_parser():
         "--metatab-vertical-orientation",
         action='store_true',
         help="Read metatab so that headings are in the first column and data is read vertically. Only for XLSX not CSV")
+    parser_unflatten.add_argument(
+        "--default-configuration",
+        help="Comma seperated list of default parsing commands for all sheets. Only for XLSX not CSV")
 
     return parser
 

flattentool/tests/fixtures/xlsx/commands_defaulted.xlsx

@@ -1169,3 +1169,32 @@ def test_commands_metatab(tmpdir):
 
     assert unflattened == {'main': [{'actual': 'actual', 'headings': 'data', 'some': 'some'}, {'actual': 'actual', 'headings': 'Other data', 'some': 'some'}],
                            'some': 'data'}
+
+def test_commands_single_sheet_default(tmpdir):
+
+    unflatten(
+        'flattentool/tests/fixtures/xlsx/commands_defaulted.xlsx',
+        input_format='xlsx',
+        output_name=tmpdir.join('command_single_unflattened.json').strpath,
+        cell_source_map=tmpdir.join('command_single_source_map.json').strpath,
+        heading_source_map=tmpdir.join('command_single_heading_source_map.json').strpath,
+        default_configuration="SkipRows 1, headerrows 2",
+        )
+
+    unflattened = json.load(tmpdir.join('command_single_unflattened.json'))
+
+    assert unflattened == {'main': [{'actual': 'actual', 'headings': 'data', 'some': 'some'}]}
+
+
+    unflatten(
+        'flattentool/tests/fixtures/xlsx/commands_defaulted.xlsx',
+        input_format='xlsx',
+        output_name=tmpdir.join('command_single_unflattened.json').strpath,
+        cell_source_map=tmpdir.join('command_single_source_map.json').strpath,
+        heading_source_map=tmpdir.join('command_single_heading_source_map.json').strpath,
+        default_configuration="SkipRows 1",
+        )
+
+    unflattened = json.load(tmpdir.join('command_single_unflattened.json'))
+
+    assert unflattened == {'main': [{'actual': 'other', 'headings': 'headings', 'some': 'some'}, {'actual': 'actual', 'headings': 'data', 'some': 'some'}]}