From fa1de1d92473e17f30cf2432925d033c684a4d44 Mon Sep 17 00:00:00 2001
From: Amir Golparvar <amir.golparvar@physik.hu-berlin.de>
Date: Wed, 19 Apr 2023 14:40:37 +0000
Subject: [PATCH] Changed the behavior of the row mode in tabular parser
Changelog: Fixed
---
nomad/parsing/tabular.py | 10 +--------
tests/parsing/test_tabular.py | 41 ++++-------------------------------
2 files changed, 5 insertions(+), 46 deletions(-)
diff --git a/nomad/parsing/tabular.py b/nomad/parsing/tabular.py
index 7e7033184c..cb80c5dfa0 100644
--- a/nomad/parsing/tabular.py
+++ b/nomad/parsing/tabular.py
@@ -65,14 +65,6 @@ def traverse_to_target_data_file(section, path_list: List[str]):
raise MetainfoError(f'The path {temp} in path_to_data_file does not exist')
-def to_camel_case(snake_str: str):
- '''Take as input a snake case variable and return a camel case one'''
-
- components = snake_str.split('_')
-
- return ''.join(f'{x[0].upper()}{x[1:].lower()}' for x in components)
-
-
def extract_tabular_parser_annotation(archive):
for quantity_def in archive.m_def.all_quantities.values():
annotation = quantity_def.m_get_annotations('tabular_parser')
@@ -181,7 +173,7 @@ class TableData(ArchiveSection):
for section_name in section_names:
section_name_list = section_name.split('/')
section_name_str = section_name_list[0]
- section_def = getattr(self, to_camel_case(section_name_str)).m_def
+ section_def = self.m_def.all_properties[section_name_str].sub_section
if not list_of_visited_sections.count(section_name_str):
list_of_visited_sections.append(section_name_str)
diff --git a/tests/parsing/test_tabular.py b/tests/parsing/test_tabular.py
index dc1a7905a9..129513b4fd 100644
--- a/tests/parsing/test_tabular.py
+++ b/tests/parsing/test_tabular.py
@@ -632,11 +632,10 @@ data:
Main_Class:
base_sections:
- nomad.parsing.tabular.TableData
- - nomad.datamodel.data.EntryData
quantities:
csv_file:
type: str
- default: 'asghar'
+ default: 'placeholder'
m_annotations:
tabular_parser:
mode: row
@@ -645,20 +644,10 @@ data:
sub_sections:
subsection_1:
repeats: True
- section: '#/Base_Class'
+ section: '#/Class_1'
Class_1:
base_sections:
- '#/Base_Class'
- - nomad.parsing.tabular.TableData
- quantities:
- data_file_1:
- type: str
- default: '#data/csv_file'
- m_annotations:
- tabular_parser:
- mode: row
- target_sub_section:
- - subsection_1
sub_sections:
subsection_1:
repeats: true
@@ -669,32 +658,11 @@ data:
m_annotations:
tabular:
name: header_0
- Class_2:
- base_sections:
- - nomad.parsing.tabular.TableData
- quantities:
- data_file_2:
- type: str
- default: '#data/csv_file'
- m_annotations:
- tabular_parser:
- mode: column
- sub_sections:
- subsection_1:
- section:
- quantities:
- header_1:
- type: str
- shape: ['*']
- m_annotations:
- tabular:
- name: header_1
data:
m_def: Main_Class
csv_file: test.my_schema.archive.csv
subsection_1:
- m_def: Class_1
- - m_def: Class_2
'''),
strip('''
header_0,header_1
@@ -725,10 +693,9 @@ def test_tabular_csv(raw_files, monkeypatch, schema, content):
assert isinstance(main_archive.data.MySubsection[instance].header_0, datetime.datetime)
elif re.search('data file as reference', schema):
assert len(main_archive.data.subsection_1) == 2
- assert len(main_archive.data.subsection_1[0].subsection_1) == 2
+ assert len(main_archive.data.subsection_1[0].subsection_1) == 1
assert main_archive.data.subsection_1[0].subsection_1[0].header_0 == '0_0'
- assert main_archive.data.subsection_1[0].subsection_1[1].header_0 == '1_0'
- assert main_archive.data.subsection_1[1].subsection_1.header_1 == ['0_1', '1_1']
+ assert main_archive.data.subsection_1[1].subsection_1[0].header_0 == '1_0'
@pytest.mark.parametrize('schema,content,missing', [
--
GitLab