From c0fef89da9538c9a2d9eb10201b59798bdf9cffa Mon Sep 17 00:00:00 2001
From: Alvin Noe Ladines <ladinesalvinnoe@gmail.com>
Date: Thu, 20 Apr 2023 21:19:38 +0000
Subject: [PATCH] Resolve "Extend text parser"
Implement functionality to write file parser results to archive.
Changelog: Added
---
nomad/parsing/file_parser/file_parser.py | 26 ++++++++++
tests/parsing/test_file_parser.py | 63 +++++++++++++++++++++++-
2 files changed, 87 insertions(+), 2 deletions(-)
diff --git a/nomad/parsing/file_parser/file_parser.py b/nomad/parsing/file_parser/file_parser.py
index 14bd2ad89b..08fd87ee6a 100644
--- a/nomad/parsing/file_parser/file_parser.py
+++ b/nomad/parsing/file_parser/file_parser.py
@@ -22,6 +22,8 @@ import bz2
import lzma
import tarfile
+from nomad.metainfo import MSection
+
class FileParser:
'''
@@ -32,6 +34,7 @@ class FileParser:
Arguments:
mainfile: the file to be parsed
logger: optional logger
+ open: function to open file
'''
def __init__(self, mainfile=None, logger=None, open=None):
self._mainfile: Any = None
@@ -152,8 +155,31 @@ class FileParser:
def __getattr__(self, key):
if self._results is None:
self._results = dict()
+ self.parse()
return self._results.get(key, None)
+ def to_dict(self):
+ '''
+ Recursively converts the the parser results into a dictionary.
+ '''
+ results = {}
+ for key, val in self.results.items():
+ if isinstance(val, FileParser):
+ val = val.to_dict()
+ elif isinstance(val, list) and val and isinstance(val[0], FileParser):
+ for n, val_n in enumerate(val):
+ val[n] = val_n.to_dict()
+
+ results[key] = val
+ return results
+
+ def write_to_archive(self, section: MSection):
+ '''
+ Wrapper for the m_from_dict functionality of msection to write the parser
+ results to an archive section.
+ '''
+ return section.m_from_dict(self.to_dict())
+
def parse(self, quantity_key: str = None, **kwargs):
pass
diff --git a/tests/parsing/test_file_parser.py b/tests/parsing/test_file_parser.py
index d89572e5e9..bf5569f49a 100644
--- a/tests/parsing/test_file_parser.py
+++ b/tests/parsing/test_file_parser.py
@@ -2,11 +2,70 @@ import pytest
import numpy as np
import pint
from nomad.units import ureg
-
from nomad.parsing.file_parser import TextParser, Quantity, ParsePattern,\
- XMLParser, BasicParser
+ XMLParser, BasicParser, FileParser
from nomad.datamodel.metainfo.simulation.system import Atoms
from nomad.datamodel import EntryArchive
+from nomad.datamodel.metainfo.simulation.run import Run
+from nomad.datamodel.metainfo.simulation.calculation import Calculation
+
+
+class TestFileParser:
+
+ @pytest.fixture(scope='class')
+ def calculation_parser(self):
+ class Parser(FileParser):
+ def parse(self, key):
+ self._results = {'time_calculation': 2.0}
+
+ return Parser()
+
+ @pytest.fixture(scope='class')
+ def run_parser(self, calculation_parser):
+ class Parser(FileParser):
+ def parse(self, key):
+ self._results = {'clean_end': True, 'calculation': [calculation_parser]}
+
+ return Parser()
+
+ @pytest.fixture(scope='function')
+ def text_parser(self):
+ return TextParser()
+
+ @pytest.fixture(scope='class')
+ def parser(self, run_parser):
+ class Parser(FileParser):
+ def parse(self, key):
+ self._results = {'run': [run_parser]}
+
+ return Parser()
+
+ @pytest.mark.parametrize('mainfile', [
+ 'tests/data/parsers/vasp/vasp.xml',
+ 'tests/data/parsers/vasp_compressed/vasp.xml.gz'])
+ def test_open(self, text_parser, mainfile):
+ text_parser.quantities = [
+ Quantity('program', r'name="program" type="string">(.+?) *<')
+ ]
+ text_parser.mainfile = mainfile
+ assert text_parser.program == 'vasp'
+
+ def test_get(self, text_parser):
+ text_parser.quantities = [
+ Quantity('energy', r'free +energy +TOTEN += +(\S+) +eV', dtype=np.float64, repeats=True),
+ ]
+ text_parser.mainfile = 'tests/data/parsers/vasp_outcar/OUTCAR'
+ assert text_parser.energy[1] == 1.70437998
+ assert text_parser.get('energy', unit='eV')[1].magnitude == 1.70437998
+
+ def test_write_to_archive(self, parser):
+ for create_section in [True, False]:
+ archive = EntryArchive()
+ if create_section:
+ archive.m_create(Run).m_create(Calculation)
+ archive = parser.write_to_archive(archive)
+ assert archive.run[0].clean_end
+ assert archive.run[0].calculation[0].time_calculation.magnitude == 2.0
class TestTextParser:
--
GitLab