ENH: add table importer implementations for csv

There are actually two classes TSVImporter and CSVImporter.

src/caosadvancedtools/table_importer.py

@@ -145,12 +145,7 @@ def win_path_converter(val):
     return path.as_posix()
 
 
-class TSVImporter(object):
-    def __init__(self, converters, obligatory_columns=[], unique_columns=[]):
-        raise NotImplementedError()
-
-
-class XLSImporter(object):
+class TableImporter(object):
     def __init__(self, converters, obligatory_columns=None, unique_keys=None):
         """
         converters: dict with column names as keys and converter functions as
@@ -168,50 +163,14 @@ class XLSImporter(object):
         """
         self.sup = SuppressKnown()
         self.required_columns = list(converters.keys())
-        self.obligatory_columns = [] if obligatory_columns is None else obligatory_columns
+        self.obligatory_columns = ([]
+                                   if obligatory_columns is None
+                                   else obligatory_columns)
         self.unique_keys = [] if unique_keys is None else unique_keys
         self.converters = converters
 
-    def read_xls(self, filename, **kwargs):
-        """
-        converts an xls file into a Pandas DataFrame.
-
-        The converters of the XLSImporter object are used.
-
-        Raises: DataInconsistencyError
-        """
-        try:
-            xls_file = pd.io.excel.ExcelFile(filename)
-        except (XLRDError, ValueError) as e:
-            logger.warning(
-                "Cannot read \n{}.\nError:{}".format(filename,
-                                                     str(e)),
-                extra={'identifier': str(filename),
-                       'category': "inconsistency"})
-            raise DataInconsistencyError(*e.args)
-
-        if len(xls_file.sheet_names) > 1:
-            # Multiple sheets is the default now. Only show in debug
-            logger.debug(
-                "Excel file {} contains multiple sheets. "
-                "All but the first are being ignored.".format(filename))
-
-        try:
-            df = xls_file.parse(converters=self.converters, **kwargs)
-        except Exception as e:
-            logger.warning(
-                "Cannot parse {}.".format(filename),
-                extra={'identifier': str(filename),
-                       'category': "inconsistency"})
-            raise DataInconsistencyError(*e.args)
-
-        self.check_columns(df, filename=filename)
-        df = self.check_missing(df, filename=filename)
-
-        if len(self.unique_keys) > 0:
-            df = self.check_unique(df, filename=filename)
-
-        return df
+    def read_file(self, filename, **kwargs):
+        raise NotImplementedError()
 
     def check_columns(self, df, filename=None):
         """
@@ -306,3 +265,70 @@ class XLSImporter(object):
                     okay = False
 
         return df
+
+    def check_dataframe(self, df, filename):
+        self.check_columns(df, filename=filename)
+        df = self.check_missing(df, filename=filename)
+
+        if len(self.unique_keys) > 0:
+            df = self.check_unique(df, filename=filename)
+
+
+class XLSImporter(TableImporter):
+    def read_file(self, filename, **kwargs):
+        return self.read_xls(filename=filename, **kwargs)
+
+    def read_xls(self, filename, **kwargs):
+        """
+        converts an xls file into a Pandas DataFrame.
+
+        The converters of the XLSImporter object are used.
+
+        Raises: DataInconsistencyError
+        """
+        try:
+            xls_file = pd.io.excel.ExcelFile(filename)
+        except (XLRDError, ValueError) as e:
+            logger.warning(
+                "Cannot read \n{}.\nError:{}".format(filename,
+                                                     str(e)),
+                extra={'identifier': str(filename),
+                       'category': "inconsistency"})
+            raise DataInconsistencyError(*e.args)
+
+        if len(xls_file.sheet_names) > 1:
+            # Multiple sheets is the default now. Only show in debug
+            logger.debug(
+                "Excel file {} contains multiple sheets. "
+                "All but the first are being ignored.".format(filename))
+
+        try:
+            df = xls_file.parse(converters=self.converters, **kwargs)
+        except Exception as e:
+            logger.warning(
+                "Cannot parse {}.".format(filename),
+                extra={'identifier': str(filename),
+                       'category': "inconsistency"})
+            raise DataInconsistencyError(*e.args)
+
+        self.check_dataframe(df, filename)
+
+        return df
+
+
+class CSVImporter(TableImporter):
+    def read_file(self, filename, **kwargs):
+        df = pd.read_csv(filename, sep=";", converters=self.converters,
+                         **kwargs)
+        self.check_dataframe(df, filename)
+
+        return df
+
+
+class TSVImporter(TableImporter):
+    def read_file(self, filename, **kwargs):
+        df = pd.read_csv(filename, sep="\t", converters=self.converters,
+                         **kwargs)
+        self.check_dataframe(df, filename)
+
+        return df