Merge branch 'crawler_dev' of gitlab.gwdg.de:bmp-caosdb/caosdb-advanced-user-tools into crawler_dev

src/caosadvancedtools/read_md_header.py

@@ -224,8 +224,14 @@ def reference_data_files(entity, header, prefix=""):
 
 
 def get_data_glob(header):
+    if "data" in header:
+        name = "data"
+    elif "results" in header:
+        name = "results"
+    else:
+        raise Exception("no suitable header fields")
     globs = []
-    for el in header["data"]:
+    for el in header[name]:
         if isinstance(el, dict) and "filename" in el:
             globs.append(el["filename"])
         else:

unittests/test_read_md_header.py

+#!/usr/bin/env python
+# encoding: utf-8
+#
+# ** header v3.0
+# This file is a part of the CaosDB Project.
+#
+# Copyright (C) 2019 Henrik tom Wörden
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as
+# published by the Free Software Foundation, either version 3 of the
+# License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <https://www.gnu.org/licenses/>.
+#
+# ** end header
+import os
+import unittest
+from copy import deepcopy
+from tempfile import NamedTemporaryFile
+
+import caosdb as db
+from caosadvancedtools.read_md_header import get_data_glob, get_header
+
+
+def to_file(string):
+    f = NamedTemporaryFile(mode="w", delete=False)
+    f.write(string)
+    f.close()
+
+    return f.name
+
+
+class ReadHeaderTest(unittest.TestCase):
+    def setUp(self):
+        pass
+
+    def tearDown(self):
+        pass
+
+    def test_hash(self):
+        file_content = """
+---
+data:
+    - results/**
+...
+"""
+        header = get_header(to_file(file_content))[2]
+        assert get_data_glob(header)[0] == "results/**"