Merge branch 'wien2k-fixes' into 'v0.9.8'

Wien2k fixes #445

See merge request !230

wien2k @ 0bfb17da

-Subproject commit cf6abfe712ff2d0052947f46bdb27131ac6fbaf8
+Subproject commit 0bfb17daec156d26110d55cd0918d8fb584f7fac

nomad/parsing/parser.py

@@ -19,6 +19,9 @@
 from typing import List
 from abc import ABCMeta, abstractmethod
 import re
+import os
+import os.path
+from functools import lru_cache
 
 from nomad import config
 from nomad.datamodel import EntryArchive, UserProvidableMetadata, EntryMetadata
@@ -105,6 +108,8 @@ class MatchingParser(Parser):
         mainfile_contents_re: A regexp that is used to match the first 1024 bytes of a
             potential mainfile.
         mainfile_name_re: A regexp that is used to match the paths of potential mainfiles
+        mainfile_alternative: If True files are mainfile if no mainfile_name_re matching file
+            is present in the same directory.
         domain: The domain that this parser should be used for. Default is 'dft'.
         supported_compressions: A list of [gz, bz2], if the parser supports compressed files
     '''
@@ -114,6 +119,7 @@ class MatchingParser(Parser):
             mainfile_binary_header: bytes = None,
             mainfile_mime_re: str = r'text/.*',
             mainfile_name_re: str = r'.*',
+            mainfile_alternative: bool = False,
             domain='dft',
             supported_compressions: List[str] = []) -> None:
 
@@ -125,6 +131,7 @@ class MatchingParser(Parser):
         self._mainfile_binary_header = mainfile_binary_header
         self._mainfile_mime_re = re.compile(mainfile_mime_re)
         self._mainfile_name_re = re.compile(mainfile_name_re)
+        self._mainfile_alternative = mainfile_alternative
         # Assign private variable this way to avoid static check issue.
         if mainfile_contents_re is not None:
             self._mainfile_contents_re = re.compile(mainfile_contents_re)
@@ -132,6 +139,8 @@ class MatchingParser(Parser):
             self._mainfile_contents_re = None
         self._supported_compressions = supported_compressions
 
+        self._ls = lru_cache(maxsize=16)(lambda directory: os.listdir(directory))
+
     def is_mainfile(
             self, filename: str, mime: str, buffer: bytes, decoded_buffer: str,
             compression: str = None) -> bool:
@@ -139,15 +148,34 @@ class MatchingParser(Parser):
         if self._mainfile_binary_header is not None:
             if self._mainfile_binary_header not in buffer:
                 return False
+
         if self._mainfile_contents_re is not None:
             if decoded_buffer is not None:
                 if self._mainfile_contents_re.search(decoded_buffer) is None:
                     return False
             else:
                 return False
-        return self._mainfile_mime_re.match(mime) is not None and \
-            self._mainfile_name_re.fullmatch(filename) is not None and \
-            (compression is None or compression in self._supported_compressions)
+
+        if self._mainfile_mime_re.match(mime) is None:
+            return False
+
+        if compression is not None and compression not in self._supported_compressions:
+            return False
+
+        if self._mainfile_name_re.fullmatch(filename) is None:
+            if not self._mainfile_alternative:
+                return False
+
+            directory = os.path.dirname(filename)
+            for sibling in self._ls(directory):
+                sibling = os.path.join(directory, sibling)
+                sibling_is_mainfile = sibling != filename and \
+                    self._mainfile_name_re.fullmatch(sibling) is not None and \
+                    os.path.isfile(sibling)
+                if sibling_is_mainfile:
+                    return False
+
+        return True
 
     def __repr__(self):
         return self.name

nomad/parsing/parsers.py

@@ -217,6 +217,8 @@ parsers = [
     LegacyParser(
         name='parsers/wien2k', code_name='WIEN2k', code_homepage='http://www.wien2k.at/',
         parser_class_name='wien2kparser.Wien2kParser',
+        mainfile_name_re=r'.*\.scf$',
+        mainfile_alternative=True,
         mainfile_contents_re=r'\s*---------\s*:ITE[0-9]+:\s*[0-9]+\.\s*ITERATION\s*---------'
     ),
     LegacyParser(

requirements.txt

@@ -23,6 +23,7 @@ elasticsearch-dsl==6.4.0
 jmespath
 
 # [parsing]
+netCDF4==1.5.4
 pandas
 h5py
 hjson

tests/data/parsers/wien2k/alternative_without_mainfile/AlN_ZB.struct

+AlN_ZB                                                                         
+F   LATTICE,NONEQUIV.ATOMS:  2                                                 
+MODE OF CALC=RELA unit=bohr                                                    
+  8.277004  8.277004  8.277004 90.000000 90.000000 90.000000                   
+ATOM   1: X=0.00000000 Y=0.00000000 Z=0.00000000
+          MULT= 1          ISPLIT= 2
+Al         NPT=  781  R0=0.00010000 RMT= 1.75000     Z: 13.0                   
+LOCAL ROT MATRIX:    1.0000000 0.0000000 0.0000000
+                     0.0000000 1.0000000 0.0000000
+                     0.0000000 0.0000000 1.0000000
+ATOM   2: X=0.25000000 Y=0.25000000 Z=0.25000000
+          MULT= 1          ISPLIT= 2
+N          NPT=  781  R0=0.00010000 RMT= 1.49000     Z:  7.0                   
+LOCAL ROT MATRIX:    1.0000000 0.0000000 0.0000000
+                     0.0000000 1.0000000 0.0000000
+                     0.0000000 0.0000000 1.0000000
+  24      NUMBER OF SYMMETRY OPERATIONS
+ 1 0 0 0.00000000
+ 0-1 0 0.00000000
+ 0 0-1 0.00000000
+       1
+ 1 0 0 0.00000000
+ 0 0-1 0.00000000
+ 0-1 0 0.00000000
+       2
+ 0 1 0 0.00000000
+-1 0 0 0.00000000
+ 0 0-1 0.00000000
+       3
+ 0 0 1 0.00000000
+-1 0 0 0.00000000
+ 0-1 0 0.00000000
+       4
+ 0 1 0 0.00000000
+ 0 0-1 0.00000000
+-1 0 0 0.00000000
+       5
+ 0 0 1 0.00000000
+ 0-1 0 0.00000000
+-1 0 0 0.00000000
+       6
+ 0-1 0 0.00000000
+ 1 0 0 0.00000000
+ 0 0-1 0.00000000
+       7
+ 0 0-1 0.00000000
+ 1 0 0 0.00000000
+ 0-1 0 0.00000000
+       8
+-1 0 0 0.00000000
+ 0 1 0 0.00000000
+ 0 0-1 0.00000000
+       9
+-1 0 0 0.00000000
+ 0 0 1 0.00000000
+ 0-1 0 0.00000000
+      10
+ 0-1 0 0.00000000
+ 0 0-1 0.00000000
+ 1 0 0 0.00000000
+      11
+ 0 0-1 0.00000000
+ 0-1 0 0.00000000
+ 1 0 0 0.00000000
+      12
+ 0 0 1 0.00000000
+ 0 1 0 0.00000000
+ 1 0 0 0.00000000
+      13
+ 0 1 0 0.00000000
+ 0 0 1 0.00000000
+ 1 0 0 0.00000000
+      14
+-1 0 0 0.00000000
+ 0 0-1 0.00000000
+ 0 1 0 0.00000000
+      15
+-1 0 0 0.00000000
+ 0-1 0 0.00000000
+ 0 0 1 0.00000000
+      16
+ 0 0 1 0.00000000
+ 1 0 0 0.00000000
+ 0 1 0 0.00000000
+      17
+ 0 1 0 0.00000000
+ 1 0 0 0.00000000
+ 0 0 1 0.00000000
+      18
+ 0 0-1 0.00000000
+ 0 1 0 0.00000000
+-1 0 0 0.00000000
+      19
+ 0-1 0 0.00000000
+ 0 0 1 0.00000000
+-1 0 0 0.00000000
+      20
+ 0 0-1 0.00000000
+-1 0 0 0.00000000
+ 0 1 0 0.00000000
+      21
+ 0-1 0 0.00000000
+-1 0 0 0.00000000
+ 0 0 1 0.00000000
+      22
+ 1 0 0 0.00000000
+ 0 0 1 0.00000000
+ 0 1 0 0.00000000
+      23
+ 1 0 0 0.00000000
+ 0 1 0 0.00000000
+ 0 0 1 0.00000000
+      24

tests/parsing/test_parsing.py

@@ -85,7 +85,7 @@ for parser, mainfile in parser_examples:
 parser_examples = fixed_parser_examples
 
 
-correct_num_output_files = 114
+correct_num_output_files = 115
 
 
 class TestBackend(object):