first case with txt works. this refs #5

notebooks/xrd_file_parser.py

@@ -30,25 +30,34 @@
                    }
 
 
+class XrdFileType:
+    ras = '.ras'
+    asc = '.asc'
+    txt = '.txt'
+
+
 def file_content(file_name):
     with open(file_name, 'r', errors='replace') as f:
         content = f.readlines()
 
     return content
 
 
-def xrd_file_parser(xrd_file_name):
-    if not os.path.exists(xrd_file_name):
+def xrd_file_parser(xrd_file_name=None, xrd_file_content=None, xrd_file_type=XrdFileType.ras):
+    if (not os.path.exists(xrd_file_name)) and (xrd_file_content is None):
         return None
 
-    name, extension = os.path.splitext(xrd_file_name)
+    if xrd_file_name:
+        name, extension = os.path.splitext(xrd_file_name)
+    else:
+        extension = xrd_file_type
 
-    if extension == '.ras':
-        return ras_file_parser(xrd_file_name)
-    elif extension == '.asc':
-        return asc_file_parser(xrd_file_name)
-    elif extension == '.txt':
-        return txt_file_parser(xrd_file_name)
+    if extension == XrdFileType.ras:
+        return ras_file_parser(xrd_file_name, xrd_file_content)
+    elif extension == XrdFileType.asc:
+        return asc_file_parser(xrd_file_name, xrd_file_content)
+    elif extension == XrdFileType.txt:
+        return txt_file_parser(xrd_file_name, xrd_file_content)
 
     return None
 
@@ -61,7 +70,7 @@ def _pattern_match(pattern=None, line_starts_with=None, line=None):
     return None
 
 
-def asc_file_parser(xrd_file_name):
+def asc_file_parser(xrd_file_name=None, xrd_file_content=None):
     """retrieve the following metadata from the ASC file"""
     metadata = {'alpha1': None,
                 'alpha2': None,
@@ -117,7 +126,7 @@ def asc_file_parser(xrd_file_name):
     return metadata
 
 
-def ras_file_parser(xrd_file_name):
+def ras_file_parser(xrd_file_name=None, xrd_file_content=None):
     """retrieve the following metadata from the RAS file"""
     metadata = {'alpha1': None,
                 'alpha2': None,
@@ -158,8 +167,16 @@ def ras_file_parser(xrd_file_name):
     return metadata
 
 
-def txt_file_parser(xrd_file_name):
-    data = pd.read_csv(xrd_file_name, names=['2theta', 'intensity'], skiprows=1, sep='\t')
+def txt_file_parser(xrd_file_name=None, xrd_file_content=None):
+    if xrd_file_name is None:
+        if xrd_file_content is None:
+            raise AttributeError("Provide either xrd_file_name or xrd_file_content")
+
+        data = pd.read_csv(xrd_file_content, names=['2theta', 'intensity'], skiprows=1, sep='\t')
+
+    else:
+        data = pd.read_csv(xrd_file_name, names=['2theta', 'intensity'], skiprows=1, sep='\t')
+
     return {'data': {'2theta': np.array(data['2theta']),
                      'intensity': np.array(data['intensity']),
                      },

tests/test_xrd_file_parser.py

@@ -2,6 +2,7 @@
 from unittest import TestCase
 import os
 import numpy as np
+from io import StringIO
 
 from notebooks.xrd_file_parser import file_content, _pattern_match, xrd_file_parser
 from notebooks.xrd_file_parser import txt_file_parser, ras_file_parser, asc_file_parser
@@ -207,3 +208,38 @@ def test_txt_file_parser(self):
 
         for _exp, _ret in zip(y_axis_expected, y_axis_returned):
             assert _exp == _ret
+
+
+class TestContentFileParser(TestCase):
+
+    ASC_FILE_NAME = "data/xrd_file.asc"
+    RAS_FILE_NAME = "data/xrd_file.ras"
+    TXT_FILE_NAME = "data/xrd_file.txt"
+
+    def setUp(self):
+        _file_path = os.path.dirname(__file__)
+        self.asc_file_name = os.path.abspath(os.path.join(_file_path, self.ASC_FILE_NAME))
+        self.ras_file_name = os.path.abspath(os.path.join(_file_path, self.RAS_FILE_NAME))
+        self.txt_file_name = os.path.abspath(os.path.join(_file_path, self.TXT_FILE_NAME))
+
+    def test_txt(self):
+
+        content_of_file = StringIO("".join(file_content(self.txt_file_name)))
+
+        with pytest.raises(AttributeError):
+            txt_file_parser()
+
+        metadata_returned = txt_file_parser(xrd_file_content=content_of_file)
+
+        x_axis_returned = metadata_returned['data']['2theta']
+        y_axis_returned = metadata_returned['data']['intensity']
+
+        x_axis_expected = np.array([7.0144, 7.0314, 7.0484, 7.0654, 7.0824])
+        y_axis_expected = np.array([24868.9923, 24723.026, 24776.6393, 24816.3415, 24855.5135])
+
+        for _exp, _ret in zip(x_axis_expected, x_axis_returned):
+            assert _exp == _ret
+
+        for _exp, _ret in zip(y_axis_expected, y_axis_returned):
+            assert _exp == _ret
+