__init__.py 10.2 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
47
48
Parsers and calculation files are matched via regular expressions.

.. autofunc:: nomad.parsing.match_parser

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
62
from typing import Callable, IO
import magic
63
64
65
66
import gzip
import bz2

from nomad import files
67
68

from nomad.parsing.backend import AbstractParserBackend, LocalBackend, LegacyLocalBackend, JSONStreamWriter, BadContextURI, WrongContextState
69
from nomad.parsing.parser import Parser, LegacyParser, VaspOutcarParser
70
from nomad.parsing.artificial import TemplateParser, GenerateRandomParser, ChaosParser
71

72

73
74
75
76
77
78
79
_compressions = {
    b'\x1f\x8b\x08': ('gz', gzip.open),
    b'\x42\x5a\x68': ('bz2', bz2.open)
}


def match_parser(mainfile: str, upload_files: files.StagingUploadFiles) -> 'Parser':
80
81
82
83
84
85
86
87
88
89
90
91
92
93
    """
    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
        open: A function that allows to open a stream to the file

    Returns: The parser, or None if no parser could be matched.
    """
94
95
96
97
    with upload_files.raw_file(mainfile, 'rb') as f:
        compression, open_compressed = _compressions.get(f.read(3), (None, open))

    with open_compressed(upload_files.raw_file_object(mainfile).os_path, 'rb') as f:
98
99
100
101
102
103
104
        buffer = f.read(2048)

    mime_type = magic.from_buffer(buffer, mime=True)
    if mime_type.startswith('application') and not mime_type.endswith('xml'):
        return None

    for parser in parsers:
105
        if parser.is_mainfile(mainfile, mime_type, buffer.decode('utf-8'), compression):
106
107
108
109
110
            return parser

    return None


111
parsers = [
112
    GenerateRandomParser(),
113
    TemplateParser(),
114
    ChaosParser(),
115
    LegacyParser(
116
        name='parsers/vasp',
117
        parser_class_name='vaspparser.VASPRunParserInterface',
118
119
        mainfile_mime_re=r'(application/xml)|(text/.*)',
        mainfile_contents_re=(
120
121
122
123
            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>'
124
125
            r'?'),
        supported_compressions=['gz', 'bz2']
126
    ),
127
    VaspOutcarParser(
128
        name='parsers/vasp',
129
        parser_class_name='vaspparser.VaspOutcarParser',
130
131
        mainfile_name_re=r'(.*/)?OUTCAR(\.[^\.]*)?',
        mainfile_contents_re=(r'^\svasp\.')
132
    ),
133
    LegacyParser(
134
        name='parsers/exciting',
135
        parser_class_name='excitingparser.ExcitingParser',
136
137
        mainfile_name_re=r'^.*/INFO\.OUT?',
        mainfile_contents_re=(
138
139
140
141
142
            r'^\s*=================================================+\s*'
            r'\s*\|\s*EXCITING\s+\S+\s+started\s*='
            r'\s*\|\s*version hash id:\s*\S*\s*=')
    ),
    LegacyParser(
143
        name='parsers/fhi-aims',
144
        parser_class_name='fhiaimsparser.FHIaimsParser',
145
        mainfile_contents_re=(
146
147
148
            r'^(.*\n)*'
            r'?\s*Invoking FHI-aims \.\.\.'
            r'?\s*Version')
149
150
    ),
    LegacyParser(
151
        name='parsers/cp2k',
152
        parser_class_name='cp2kparser.CP2KParser',
153
        mainfile_contents_re=(
154
155
156
157
            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
158
159
            r'  \*\*\*\* \*\*  \*\*\*\*\*\*\*  \*\*  PROGRAM STARTED IN .*\n'
        )
160
    ),
161
    LegacyParser(
162
        name='parsers/crystal',
163
        parser_class_name='crystalparser.CrystalParser',
164
        mainfile_contents_re=(
speckhard's avatar
speckhard committed
165
166
167
168
169
            r'\s*[\*]{22,}'  # Looks for '*' 22 times or more in a row.
            r'\s*\*\s{20,}\*'  # Looks for a '*' sandwhiched by whitespace.
            r'\s*\*\s{10,}CRYSTAL(?P<majorVersion>[\d]+)\s{10,}\*'
            r'\s*\*\s{10,}public \: (?P<minorVersion>[\d\.]+) \- .*\*'
        )
170
    ),
171
172
173
    # 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.
174
    LegacyParser(
175
        name='parsers/cpmd',
176
        parser_class_name='cpmdparser.CPMDParser',
177
        mainfile_contents_re=(
178
179
180
181
182
183
184
185
            # 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
186
        )
187
    ),
speckhard's avatar
speckhard committed
188
    LegacyParser(
189
        name='parsers/nwchem',
speckhard's avatar
speckhard committed
190
        parser_class_name='nwchemparser.NWChemParser',
191
        mainfile_contents_re=(
192
193
194
195
196
            r'\s+Northwest Computational Chemistry Package \(NWChem\) \d+\.\d+'
            r'\s+------------------------------------------------------'
            r'\s+Environmental Molecular Sciences Laboratory'
            r'\s+Pacific Northwest National Laboratory'
            r'\s+Richland, WA 99352'
speckhard's avatar
speckhard committed
197
198
199
        )
    ),
    LegacyParser(
200
        name='parsers/bigdft',
speckhard's avatar
speckhard committed
201
        parser_class_name='bigdftparser.BigDFTParser',
202
        mainfile_contents_re=(
speckhard's avatar
speckhard committed
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
            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*'
            r'\|_____\|__:__\|__:__\|_____\|_____\|___ BBBBB          i     g         g\s*'
            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
228
        )
229
230
    ),
    LegacyParser(
231
        name='parsers/wien2k',
232
        parser_class_name='wien2kparser.Wien2kParser',
233
        mainfile_contents_re=r':LABEL\d+: using WIEN2k_\d+\.\d+'
speckhard's avatar
speckhard committed
234
    )
235
]
236

237
238
""" Instanciation and constructor based config of all parsers. """

Markus Scheidgen's avatar
Markus Scheidgen committed
239
parser_dict = {parser.name: parser for parser in parsers}  # type: ignore
240
""" A dict to access parsers by name. Usually 'parsers/<...>', e.g. 'parsers/vasp'. """