Added xz compression

vasp @ 7d850bd7

-Subproject commit dc59aff14e69a6818fbefeb7b1d504348438e26b
+Subproject commit 7d850bd76e878b1429d6974f5daac456099f6e4f

nomad/parsing/__init__.py

@@ -75,6 +75,7 @@ from typing import Callable, IO, Union
 import magic
 import gzip
 import bz2
+import lzma
 import os.path
 
 from nomad import files, config
@@ -87,7 +88,8 @@ from nomad.parsing.artificial import TemplateParser, GenerateRandomParser, Chaos
 
 _compressions = {
     b'\x1f\x8b\x08': ('gz', gzip.open),
-    b'\x42\x5a\x68': ('bz2', bz2.open)
+    b'\x42\x5a\x68': ('bz2', bz2.open),
+    b'\xfd\x37\x7a': ('xz', lzma.open)
 }
 
 
@@ -147,14 +149,14 @@ parsers = [
     LegacyParser(
         name='parsers/vasp', code_name='VASP',
         parser_class_name='vaspparser.VASPRunParserInterface',
-        mainfile_mime_re=r'(application/xml)|(text/.*)',
+        mainfile_mime_re=r'(application/.*)|(text/.*)',
         mainfile_contents_re=(
             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>'
             r'?'),
-        supported_compressions=['gz', 'bz2']
+        supported_compressions=['gz', 'bz2', 'xz']
     ),
     VaspOutcarParser(
         name='parsers/vasp-outcar', code_name='VASP',

nomad/parsing/parser.py

@@ -139,7 +139,8 @@ class MatchingParser(Parser):
         if self._mainfile_contents_re is not None:
             try:  # Try to open the file as a string for regex matching.
                 decoded_buffer = buffer.decode('utf-8')
-            except UnicodeDecodeError:
+                print('DECODED',decoded_buffer)
+            except UnicodeDecodeError as e:
                 return False  # We're looking for a string match in a file that can't be converted to string.
             if self._mainfile_contents_re.search(decoded_buffer) is None:
                 return False