__init__.py 18.4 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
# Copyright 2018 Markus Scheidgen
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an"AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
16
The *parsing* module is an interface for the existing NOMAD-coe parsers.
17
18
This module redefines some of the old NOMAD-coe python-common functionality to create a
more coherent interface to the parsers.
19
20
21
22
23
24
25
26

Assumption about parsers
------------------------
For now, we make a few assumption about parsers
- they always work on the same *meta-info* version
- they have no conflicting python requirments
- they can be loaded at the same time and can be used within the same python process
- they are uniquely identified by a GIT URL and publicly accessible
27
- their version is uniquely identified by a GIT commit SHA
28
29
30
31
32
33

Each parser is defined via an instance of :class:`Parser`.

.. autoclass:: nomad.parsing.Parser
    :members:

Markus Scheidgen's avatar
Markus Scheidgen committed
34
35
36
37
The implementation :class:`LegacyParser` is used for most NOMAD-coe parsers.

.. autoclass:: nomad.parsing.LegacyParser

38
39
40
41
42
The parser definitions are available via the following two variables.

.. autodata:: nomad.parsing.parsers
.. autodata:: nomad.parsing.parser_dict

Markus Scheidgen's avatar
Markus Scheidgen committed
43
44
Parsers are reused for multiple caclulations.

45
46
Parsers and calculation files are matched via regular expressions.

Markus Scheidgen's avatar
Markus Scheidgen committed
47
.. autofunction:: nomad.parsing.match_parser
48

Markus Scheidgen's avatar
Markus Scheidgen committed
49
Parsers in NOMAD-coe use a *backend* to create output. There are different NOMAD-coe
Markus Scheidgen's avatar
Markus Scheidgen committed
50
basends. In nomad@FAIRDI, we only currently only use a single backed. A version of
Markus Scheidgen's avatar
Markus Scheidgen committed
51
52
53
NOMAD-coe's *LocalBackend*. It stores all parser results in memory. The following
classes provide a interface definition for *backends* as an ABC and a concrete implementation
based on NOMAD-coe's *python-common* module.
54
55
56
57
58

.. autoclass:: nomad.parsing.AbstractParserBackend
    :members:
.. autoclass:: nomad.parsing.LocalBackend
    :members:
Markus Scheidgen's avatar
Markus Scheidgen committed
59

60
"""
61
from typing import Callable, IO, Union
62
import magic
63
64
import gzip
import bz2
65
import os.path
66

67
from nomad import files, config
68
69

from nomad.parsing.backend import AbstractParserBackend, LocalBackend, LegacyLocalBackend, JSONStreamWriter, BadContextURI, WrongContextState
70
from nomad.parsing.parser import Parser, LegacyParser, VaspOutcarParser, BrokenParser, MissingParser
71
from nomad.parsing.artificial import TemplateParser, GenerateRandomParser, ChaosParser
72

73

74
75
76
77
78
79
_compressions = {
    b'\x1f\x8b\x08': ('gz', gzip.open),
    b'\x42\x5a\x68': ('bz2', bz2.open)
}


80
def match_parser(mainfile: str, upload_files: Union[str, files.StagingUploadFiles]) -> 'Parser':
81
82
83
84
85
86
87
88
89
90
    """
    Performs parser matching. This means it take the given mainfile and potentially
    opens it with the given callback and tries to identify a parser that can parse
    the file.

    This is determined by filename (e.g. *.out), mime type (e.g. text/*, application/xml),
    and beginning file contents.

    Arguments:
        mainfile: The upload relative path to the mainfile
91
92
        upload_files: Either a :class:`files.StagingUploadFiles` object or a directory name.
            Directory name + mainfile needs to point to the file.
93
94
95

    Returns: The parser, or None if no parser could be matched.
    """
96
97
98
99
100
101
    if isinstance(upload_files, str):
        mainfile_path = os.path.join(upload_files, mainfile)
    else:
        mainfile_path = upload_files.raw_file_object(mainfile).os_path

    with open(mainfile_path, 'rb') as f:
102
        compression, open_compressed = _compressions.get(f.read(3), (None, open))
103
104
105

    with open_compressed(mainfile_path, 'rb') as cf:
        buffer = cf.read(2048)
106
107
108

    mime_type = magic.from_buffer(buffer, mime=True)
    for parser in parsers:
109
110
111
112
        if parser.domain == config.domain:
            if parser.is_mainfile(mainfile_path, mime_type, buffer, compression):
                # TODO: deal with multiple possible parser specs
                return parser
113
114
115
116

    return None


117
parsers = [
118
    GenerateRandomParser(),
119
    TemplateParser(),
120
    ChaosParser(),
Daniel Speckhard's avatar
Daniel Speckhard committed
121
    LegacyParser(
122
        name='parsers/phonopy', code_name='Phonopy',
Daniel Speckhard's avatar
Daniel Speckhard committed
123
        parser_class_name='phonopyparser.PhonopyParserWrapper',
Daniel Speckhard's avatar
Daniel Speckhard committed
124
        # mainfile_contents_re=r'',  # Empty regex since this code calls other DFT codes.
Daniel Speckhard's avatar
Daniel Speckhard committed
125
126
        mainfile_name_re=(r'.*/phonopy-FHI-aims-displacement-0*1/control.in$')
    ),
127
    LegacyParser(
128
        name='parsers/vasp', code_name='VASP',
129
        parser_class_name='vaspparser.VASPRunParserInterface',
130
131
        mainfile_mime_re=r'(application/xml)|(text/.*)',
        mainfile_contents_re=(
132
133
134
135
            r'^\s*<\?xml version="1\.0" encoding="ISO-8859-1"\?>\s*'
            r'?\s*<modeling>'
            r'?\s*<generator>'
            r'?\s*<i name="program" type="string">\s*vasp\s*</i>'
136
137
            r'?'),
        supported_compressions=['gz', 'bz2']
138
    ),
139
    VaspOutcarParser(
140
        name='parsers/vasp-outcar', code_name='VASP',
141
        parser_class_name='vaspparser.VaspOutcarParser',
142
143
        mainfile_name_re=r'(.*/)?OUTCAR(\.[^\.]*)?',
        mainfile_contents_re=(r'^\svasp\.')
144
    ),
145
    LegacyParser(
146
        name='parsers/exciting', code_name='exciting',
147
        parser_class_name='excitingparser.ExcitingParser',
148
149
        mainfile_name_re=r'^.*.OUT?',
        mainfile_contents_re=(r'EXCITING.*started')
150
151
    ),
    LegacyParser(
152
        name='parsers/fhi-aims', code_name='FHI-aims',
153
        parser_class_name='fhiaimsparser.FHIaimsParser',
154
        mainfile_contents_re=(
155
156
            r'^(.*\n)*'
            r'?\s*Invoking FHI-aims \.\.\.'
157
            r'?\s*Version')
158
159
    ),
    LegacyParser(
160
        name='parsers/cp2k', code_name='CP2K',
161
        parser_class_name='cp2kparser.CP2KParser',
162
        mainfile_contents_re=(
163
164
165
166
            r'\*\*\*\* \*\*\*\* \*\*\*\*\*\*  \*\*  PROGRAM STARTED AT\s.*\n'
            r' \*\*\*\*\* \*\* \*\*\*  \*\*\* \*\*   PROGRAM STARTED ON\s*.*\n'
            r' \*\*    \*\*\*\*   \*\*\*\*\*\*    PROGRAM STARTED BY .*\n'
            r' \*\*\*\*\* \*\*    \*\* \*\* \*\*   PROGRAM PROCESS ID .*\n'
speckhard's avatar
speckhard committed
167
168
            r'  \*\*\*\* \*\*  \*\*\*\*\*\*\*  \*\*  PROGRAM STARTED IN .*\n'
        )
169
    ),
170
    LegacyParser(
171
        name='parsers/crystal', code_name='Crystal',
172
        parser_class_name='crystalparser.CrystalParser',
173
        mainfile_contents_re=(
174
            r'(CRYSTAL\s*\n0 0 0)|('
speckhard's avatar
speckhard committed
175
            r'\s*\*\s{10,}CRYSTAL(?P<majorVersion>[\d]+)\s{10,}\*'
176
            r'\s*\*\s{10,}public \: (?P<minorVersion>[\d\.]+) \- .*\*)'
speckhard's avatar
speckhard committed
177
        )
178
    ),
179
180
181
    # The main contents regex of CPMD was causing a catostrophic backtracking issue
    # when searching through the first 500 bytes of main files. We decided
    # to use only a portion of the regex to avoid that issue.
182
    LegacyParser(
183
        name='parsers/cpmd', code_name='CPMD',
184
        parser_class_name='cpmdparser.CPMDParser',
185
        mainfile_contents_re=(
186
187
188
189
190
191
192
193
            # r'\s+\*\*\*\*\*\*  \*\*\*\*\*\*    \*\*\*\*  \*\*\*\*  \*\*\*\*\*\*\s*'
            # r'\s+\*\*\*\*\*\*\*  \*\*\*\*\*\*\*   \*\*\*\*\*\*\*\*\*\*  \*\*\*\*\*\*\*\s+'
            r'\*\*\*       \*\*   \*\*\*  \*\* \*\*\*\* \*\*  \*\*   \*\*\*'
            # r'\s+\*\*        \*\*   \*\*\*  \*\*  \*\*  \*\*  \*\*    \*\*\s+'
            # r'\s+\*\*        \*\*\*\*\*\*\*   \*\*      \*\*  \*\*    \*\*\s+'
            # r'\s+\*\*\*       \*\*\*\*\*\*    \*\*      \*\*  \*\*   \*\*\*\s+'
            # r'\s+\*\*\*\*\*\*\*  \*\*        \*\*      \*\*  \*\*\*\*\*\*\*\s+'
            # r'\s+\*\*\*\*\*\*  \*\*        \*\*      \*\*  \*\*\*\*\*\*\s+'
speckhard's avatar
speckhard committed
194
        )
195
    ),
speckhard's avatar
speckhard committed
196
    LegacyParser(
197
        name='parsers/nwchem', code_name='NWChem',
speckhard's avatar
speckhard committed
198
        parser_class_name='nwchemparser.NWChemParser',
199
        mainfile_contents_re=(
200
            r'Northwest Computational Chemistry Package \(NWChem\) (\d+\.)+\d+'
speckhard's avatar
speckhard committed
201
202
203
        )
    ),
    LegacyParser(
204
        name='parsers/bigdft', code_name='BigDFT',
speckhard's avatar
speckhard committed
205
        parser_class_name='bigdftparser.BigDFTParser',
206
        mainfile_contents_re=(
Markus Scheidgen's avatar
Markus Scheidgen committed
207
208
209
210
211
212
            # r'__________________________________ A fast and precise DFT wavelet code\s*'
            # r'\|     \|     \|     \|     \|     \|\s*'
            # r'\|     \|     \|     \|     \|     \|      BBBB         i       gggggg\s*'
            # r'\|_____\|_____\|_____\|_____\|_____\|     B    B               g\s*'
            # r'\|     \|  :  \|  :  \|     \|     \|    B     B        i     g\s*'
            # r'\|     \|-0\+--\|-0\+--\|     \|     \|    B    B         i     g        g\s*'
speckhard's avatar
speckhard committed
213
            r'\|_____\|__:__\|__:__\|_____\|_____\|___ BBBBB          i     g         g\s*'
Markus Scheidgen's avatar
Markus Scheidgen committed
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
            # r'\|  :  \|     \|     \|  :  \|     \|    B    B         i     g         g\s*'
            # r'\|--\+0-\|     \|     \|-0\+--\|     \|    B     B     iiii     g         g\s*'
            # r'\|__:__\|_____\|_____\|__:__\|_____\|    B     B        i      g        g\s*'
            # r'\|     \|  :  \|  :  \|     \|     \|    B BBBB        i        g      g\s*'
            # r'\|     \|-0\+--\|-0\+--\|     \|     \|    B        iiiii          gggggg\s*'
            # r'\|_____\|__:__\|__:__\|_____\|_____\|__BBBBB\s*'
            # r'\|     \|     \|     \|  :  \|     \|                           TTTTTTTTT\s*'
            # r'\|     \|     \|     \|--\+0-\|     \|  DDDDDD          FFFFF        T\s*'
            # r'\|_____\|_____\|_____\|__:__\|_____\| D      D        F        TTTT T\s*'
            # r'\|     \|     \|     \|  :  \|     \|D        D      F        T     T\s*'
            # r'\|     \|     \|     \|--\+0-\|     \|D         D     FFFF     T     T\s*'
            # r'\|_____\|_____\|_____\|__:__\|_____\|D___      D     F         T    T\s*'
            # r'\|     \|     \|  :  \|     \|     \|D         D     F          TTTTT\s*'
            # r'\|     \|     \|--\+0-\|     \|     \| D        D     F         T    T\s*'
            # r'\|_____\|_____\|__:__\|_____\|_____\|          D     F        T     T\s*'
            # r'\|     \|     \|     \|     \|     \|         D               T    T\s*'
            # r'\|     \|     \|     \|     \|     \|   DDDDDD       F         TTTT\s*'
            # r'\|_____\|_____\|_____\|_____\|_____\|______                    www\.bigdft\.org'
speckhard's avatar
speckhard committed
232
        )
233
234
    ),
    LegacyParser(
235
        name='parsers/wien2k', code_name='WIEN2k',
236
        parser_class_name='wien2kparser.Wien2kParser',
237
        mainfile_contents_re=r':LABEL\d+: using WIEN2k_\d+\.\d+'
Markus Scheidgen's avatar
Markus Scheidgen committed
238
239
    ),
    LegacyParser(
240
        name='parsers/band', code_name=config.services.not_processed_value,
241
        parser_class_name='bandparser.BANDParser',
Markus Scheidgen's avatar
Markus Scheidgen committed
242
        mainfile_contents_re=r' +\* +Amsterdam Density Functional +\(ADF\)'),
Daniel Speckhard's avatar
Daniel Speckhard committed
243
    LegacyParser(
244
        name='parsers/gaussian', code_name='Gaussian',
Daniel Speckhard's avatar
Daniel Speckhard committed
245
        parser_class_name='gaussianparser.GaussianParser',
Daniel Speckhard's avatar
Daniel Speckhard committed
246
247
248
249
250
251
252
        # This previous file matching string was too far down the line.
        # r'\s*Cite this work as:'
        # r'\s*Gaussian [0-9]+, Revision [A-Za-z0-9.]*,'
        # r'\s\*\*\*\*\*\*\*\*\*\*\*\**'
        # r'\s*Gaussian\s*([0-9]+):\s*([A-Za-z0-9-.]+)\s*([0-9][0-9]?\-[A-Z][a-z][a-z]\-[0-9]+)'
        # r'\s*([0-9][0-9]?\-[A-Z][a-z][a-z]\-[0-9]+)')
        mainfile_contents_re=r'Gaussian, Inc'),
253
    LegacyParser(
254
        name='parsers/quantumespresso', code_name='Quantum Espresso',
255
        parser_class_name='quantumespressoparser.QuantumEspressoParserPWSCF',
256
257
258
259
260
        mainfile_contents_re=r'(Program PWSCF)|(This program is part of the open-source Quantum)'
        #    r'^(.*\n)*'
        #    r'\s*Program (\S+)\s+v\.(\S+)(?:\s+\(svn\s+rev\.\s+'
        #    r'(\d+)\s*\))?\s+starts[^\n]+'
        #    r'(?:\s*\n?)*This program is part of the open-source Quantum')
Daniel Speckhard's avatar
Daniel Speckhard committed
261
262
    ),
    LegacyParser(
263
        name='parsers/abinit', code_name='ABINIT',
Daniel Speckhard's avatar
Daniel Speckhard committed
264
        parser_class_name='abinitparser.AbinitParser',
265
        mainfile_contents_re=(r'^\n*\.Version\s*[0-9.]*\s*of ABINIT\s*')
Daniel Speckhard's avatar
Daniel Speckhard committed
266
267
    ),
    LegacyParser(
268
        name='parsers/orca', code_name='ORCA',
Daniel Speckhard's avatar
Daniel Speckhard committed
269
270
271
272
273
274
275
        parser_class_name='orcaparser.OrcaParser',
        mainfile_contents_re=(
            r'\s+\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\**\s*'
            r'\s+\* O   R   C   A \*\s*'
            r'\s+\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\**\s*'
            r'\s*'
            r'\s*--- An Ab Initio, DFT and Semiempirical electronic structure package ---\s*')
276
277
    ),
    LegacyParser(
278
        name='parsers/castep', code_name='CASTEP',
279
280
        parser_class_name='castepparser.CastepParser',
        mainfile_contents_re=(r'\s\|\s*CCC\s*AA\s*SSS\s*TTTTT\s*EEEEE\s*PPPP\s*\|\s*')
Daniel Speckhard's avatar
Daniel Speckhard committed
281
282
    ),
    LegacyParser(
283
        name='parsers/dl-poly', code_name='DL_POLY',
Daniel Speckhard's avatar
Daniel Speckhard committed
284
285
        parser_class_name='dlpolyparser.DlPolyParserWrapper',
        mainfile_contents_re=(r'\*\* DL_POLY \*\*')
Daniel Speckhard's avatar
Daniel Speckhard committed
286
287
    ),
    LegacyParser(
288
        name='parsers/lib-atoms', code_name='libAtoms',
Daniel Speckhard's avatar
Daniel Speckhard committed
289
290
        parser_class_name='libatomsparser.LibAtomsParserWrapper',
        mainfile_contents_re=(r'\s*<GAP_params\s')
Daniel Speckhard's avatar
Daniel Speckhard committed
291
292
    ),
    LegacyParser(
293
        name='parsers/octopus', code_name='Octopus',
Daniel Speckhard's avatar
Daniel Speckhard committed
294
        parser_class_name='octopusparser.OctopusParserWrapper',
Daniel Speckhard's avatar
Daniel Speckhard committed
295
296
297
        mainfile_contents_re=(r'\|0\) ~ \(0\) \|')
        # We decided to use the octopus eyes instead of
        # r'\*{32} Grid \*{32}Simulation Box:' since it was so far down in the file.
Daniel Speckhard's avatar
Daniel Speckhard committed
298
299
    ),
    LegacyParser(
300
        name='parsers/gpaw', code_name='GPAW',
Daniel Speckhard's avatar
Daniel Speckhard committed
301
302
303
304
305
        parser_class_name='gpawparser.GPAWParserWrapper',
        mainfile_name_re=(r'^.*\.gpw$'),
        mainfile_mime_re=r'application/x-tar'
    ),
    LegacyParser(
306
        name='parsers/gpaw2', code_name='GPAW',
Daniel Speckhard's avatar
Daniel Speckhard committed
307
308
309
310
311
312
        parser_class_name='gpawparser.GPAWParser2Wrapper',
        # mainfile_contents_re=r'',  # We can't read .gpw2 to match AFFormatGPAW'
        mainfile_name_re=(r'^.*\.gpw2$'),
        mainfile_mime_re=r'application/x-tar'
    ),
    LegacyParser(
313
        name='parsers/atk', code_name='ATK',
Daniel Speckhard's avatar
Daniel Speckhard committed
314
315
316
317
318
        parser_class_name='atkparser.ATKParserWrapper',
        # mainfile_contents_re=r'',  # We can't read .gpw as txt - of UlmGPAW|AFFormatGPAW'
        mainfile_name_re=r'^.*\.nc',
        # The previously used mime type r'application/x-netcdf' wasn't found by magic library.
        mainfile_mime_re=r'application/octet-stream'
Daniel Speckhard's avatar
Daniel Speckhard committed
319
320
    ),
    LegacyParser(
321
        name='parsers/gulp', code_name='gulp',
Daniel Speckhard's avatar
Daniel Speckhard committed
322
323
324
325
326
327
328
        parser_class_name='gulpparser.GULPParser',
        mainfile_contents_re=(
            r'\s*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*'
            r'\*\*\*\*\*\*\*\*\*\*\*\*\*\s*'
            r'\s*\*\s*GENERAL UTILITY LATTICE PROGRAM\s*\*\s*')
    ),
    LegacyParser(
329
        name='parsers/siesta', code_name='Siesta',
Daniel Speckhard's avatar
Daniel Speckhard committed
330
331
332
333
334
        parser_class_name='siestaparser.SiestaParser',
        mainfile_contents_re=(
            r'(Siesta Version: siesta-|SIESTA [0-9]\.[0-9]\.[0-9])')
    ),
    LegacyParser(
335
        name='parsers/elk', code_name='elk',
Daniel Speckhard's avatar
Daniel Speckhard committed
336
        parser_class_name='elkparser.ElkParser',
337
        mainfile_contents_re=r'\| Elk version [0-9.a-zA-Z]+ started \|'
Daniel Speckhard's avatar
Daniel Speckhard committed
338
339
    ),
    LegacyParser(
340
        name='parsers/elastic', code_name='elastic',
Daniel Speckhard's avatar
Daniel Speckhard committed
341
342
        parser_class_name='elasticparser.ElasticParser',
        mainfile_contents_re=r'\s*Order of elastic constants\s*=\s*[0-9]+\s*'
Daniel Speckhard's avatar
Daniel Speckhard committed
343
344
    ),
    LegacyParser(
345
        name='parsers/gamess', code_name='GAMESS',
Daniel Speckhard's avatar
Daniel Speckhard committed
346
347
348
349
350
        parser_class_name='gamessparser.GamessParser',
        mainfile_contents_re=(
            r'\s*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\**\s*'
            r'\s*\*\s*GAMESS VERSION =\s*(.*)\*\s*'
            r'\s*\*\s*FROM IOWA STATE UNIVERSITY\s*\*\s*')
351
352
    ),
    LegacyParser(
353
        name='parsers/turbomole', code_name='turbomole',
354
355
        parser_class_name='turbomoleparser.TurbomoleParser',
        mainfile_contents_re=(
356
            r'Copyright \(C\) [0-9]+ TURBOMOLE GmbH, Karlsruhe')
357
358
359
360
361
362
    ),
    LegacyParser(
        name='parsers/skeleton', code_name='skeleton', domain='EMS',
        parser_class_name='skeletonparser.SkeletonParserInterface',
        mainfile_mime_re=r'(application/json)|(text/.*)',
        mainfile_contents_re=(r'skeleton experimental metadata format')
Markus Scheidgen's avatar
Markus Scheidgen committed
363
364
365
366
367
    ),
    LegacyParser(
        name='parsers/mpes', code_name='mpes', domain='EMS',
        parser_class_name='mpesparser.MPESParserInterface',
        mainfile_mime_re=r'(application/json)|(text/.*)',
368
        mainfile_name_re=(r'.*.meta'),
369
        mainfile_contents_re=(r'"data_repository_name": "zenodo.org"')
370
371
372
373
374
375
    ),
    LegacyParser(
        name='parsers/aptfim', code_name='mpes', domain='EMS',
        parser_class_name='aptfimparser.APTFIMParserInterface',
        mainfile_mime_re=r'(application/json)|(text/.*)',
        mainfile_name_re=(r'.*.aptfim')
376
377
378
379
    ),
    MissingParser(
        name='parsers/qbox', code_name='qbox', domain='DFT',
        mainfile_contents_re=(r'http://qboxcode.org')
380
    ),
381
382
383
384
385
386
387
388
389
390
391
392
393
    MissingParser(
        name='parsers/dmol', code_name='DMol3', domain='DFT',
        mainfile_name_re=r'.*\.outmol'
    ),
    MissingParser(
        name='parser/fleur', code_name='fleur', domain='DFT',
        mainfile_contents_re=r'This output is generated by fleur.'
    ),
    MissingParser(
        name='parser/molcas', code_name='MOLCAS', domain='DFT',
        mainfile_contents_re=r'M O L C A S'
    ),
    MissingParser(
Markus Scheidgen's avatar
Markus Scheidgen committed
394
        name='parser/onetep', code_name='ONETEP', domain='DFT',
395
396
397
398
399
400
401
402
403
404
405
        mainfile_contents_re=r'####### #     # ####### ####### ####### ######'
    ),
    # These are supposedly octopus files, but they do not look like octopus files at all
    MissingParser(
        name='parser/octopus', code_name='Octopus', domain='DFT',
        mainfile_name_re=r'(inp)|(.*/inp)'
    ),
    # We already have crystal with mainfile_contents_re, but this one does not always properly match
    LegacyParser(
        name='parsers/crystal', code_name='Crystal',
        parser_class_name='crystalparser.CrystalParser',
406
        mainfile_name_re=r'.*\.cryst\.out'
407
408
409
410
411
    ),
    # We already have wien2k with mainfile_contents_re, but this one does not always properly match
    LegacyParser(
        name='parsers/wien2k', code_name='WIEN2k',
        parser_class_name='wien2kparser.Wien2kParser',
412
        mainfile_name_re=r'.*\.scf'
413
414
415
416
417
    ),
    # We already have fhi-aims with mainfile_contents_re, but this one does not always properly match
    LegacyParser(
        name='parsers/fhi-aims', code_name='FHI-aims',
        parser_class_name='fhiaimsparser.FHIaimsParser',
418
        mainfile_name_re=r'.*\.fhiaims'
419
420
    ),
    BrokenParser()
421
]
422

423
""" Instantiation and constructor based config of all parsers. """
424

Markus Scheidgen's avatar
Markus Scheidgen committed
425
parser_dict = {parser.name: parser for parser in parsers}  # type: ignore
426
""" A dict to access parsers by name. Usually 'parsers/<...>', e.g. 'parsers/vasp'. """