utility functions / classes done

src/icartt/dataset.py

@@ -498,25 +498,10 @@ class Dataset:
         :param delimiter: field delimiter character(s), defaults to DEFAULT_FIELD_DELIM
         :type delimiter: str, optional
         """
-
-        class FilehandleWithLinecounter:  # TODO: this could be a 'utils' class
-            def __init__(self, f, delimiter):
-                self.f = f
-                self.line = 0
-                self.delimiter = delimiter
-
-            def readline(self, doSplit=True):
-                self.line += 1
-                dmp = self.f.readline().replace("\n", "").replace("\r", "")
-                if doSplit:
-                    dmp = [word.strip(" ") for word in dmp.split(self.delimiter)]
-                return dmp
-
         if self.inputFhandle:
             if self.inputFhandle.closed:
                 self.inputFhandle = open(self.inputFhandle.name, encoding="utf-8")
-
-            f = FilehandleWithLinecounter(self.inputFhandle, delimiter)
+            f = utl.FilehandleWithLinecounter(self.inputFhandle, delimiter)
             self._readHeader(f)
             self.inputFhandle.close()
 
@@ -579,18 +564,9 @@ class Dataset:
         # here that the independent variable should monotonically increase even when
         # crossing over to a second day.
 
-        def extractVardesc(dmp):  # TODO: could be a 'utils' function or one line,
-            shortname = dmp[
-                0
-            ]  # shortname, units, standardname, longname, *_ = dmp + [None] * 3
-            units = dmp[1]
-            standardname = dmp[2] if len(dmp) > 2 else None
-            longname = dmp[3] if len(dmp) > 3 else None
-            return shortname, units, standardname, longname
-
         if self.format == Formats.FFI2110:
             dmp = f.readline()
-            shortname, units, standardname, longname = extractVardesc(dmp)
+            shortname, units, standardname, longname = utl.extractVardesc(dmp)
             self.independentBoundedVariable = Variable(
                 shortname,
                 units,
@@ -600,7 +576,7 @@ class Dataset:
             )
 
         dmp = f.readline()
-        shortname, units, standardname, longname = extractVardesc(dmp)
+        shortname, units, standardname, longname = utl.extractVardesc(dmp)
         self.independentVariable = Variable(
             shortname,
             units,
@@ -633,7 +609,7 @@ class Dataset:
             # the name used for that variable as a column header, i.e., the last header
             # line prior to start of data.).
             dmp = f.readline()
-            shortname, units, standardname, longname = extractVardesc(dmp)
+            shortname, units, standardname, longname = utl.extractVardesc(dmp)
             vshortname = [shortname]
             vunits = [units]
             vstandardname = [standardname]
@@ -641,7 +617,7 @@ class Dataset:
 
             for _ in range(1, nvar):
                 dmp = f.readline()
-                shortname, units, standardname, longname = extractVardesc(dmp)
+                shortname, units, standardname, longname = utl.extractVardesc(dmp)
                 vshortname += [shortname]
                 vunits += [units]
                 vstandardname += [standardname]
@@ -768,7 +744,7 @@ class Dataset:
 
         return fn + ".ict"
 
-    def isValidFileName(self, name):  # TODO: this could be a 'utils' function
+    def isValidFileName(self, name):
         """test whether file name complies with ICARTT standard:
 
         ICARTT standard v2 2.1.1 3)
@@ -781,11 +757,7 @@ class Dataset:
         :return: is file name valid according to ICARTT standard?
         :rtype: bool
         """
-
-        def isAsciiAlpha(x):  # TODO: this could be a 'utils' function
-            return re.match("[a-zA-Z0-9-_.]", x)
-
-        allAsciiAlpha = all(isAsciiAlpha(x) for x in name)
+        allAsciiAlpha = utl.isAsciiAlpha(name)
         lessThan128Characters = len(name) < 128
 
         return allAsciiAlpha and lessThan128Characters and name.endswith(".ict")

src/icartt/ictutils.py

@@ -3,6 +3,33 @@
 import re
 
 
-def isAsciiAlphaOrUnderscore(x: str, _only="[a-zA-Z0-9_]") -> bool:
+class FilehandleWithLinecounter:
+    """a file handle that counts the number of files that were read"""
+
+    def __init__(self, f, delimiter):
+        self.f = f
+        self.line = 0
+        self.delimiter = delimiter
+
+    def readline(self, doSplit=True):
+        self.line += 1
+        dmp = self.f.readline().replace("\n", "").replace("\r", "")
+        if doSplit:
+            dmp = [word.strip(" ") for word in dmp.split(self.delimiter)]
+        return dmp
+
+
+def isAsciiAlphaOrUnderscore(x: str) -> bool:
     """check if string x contains only characters from [a-zA-Z0-9_] regex"""
-    return re.match(_only, x)
+    return re.match("[a-zA-Z0-9_]", x)
+
+
+def isAsciiAlpha(x):
+    """check if string x contains only characters from [a-zA-Z0-9-_.] regex"""
+    return re.match("[a-zA-Z0-9-_.]", x)
+
+
+def extractVardesc(line_parts: list) -> str:
+    """extract variable description from ict header line parts (splitted line)"""
+    shortname, units, standardname, longname, *_ = line_parts + [None] * 3
+    return shortname, units, standardname, longname