Merge pull request #47 from aollier/merger-gzip

Merger gzip

data/compare.py

@@ -8,7 +8,7 @@
 
 class Compare(object):
     """
-    An object for comparing a file with its reference version
+    A class for comparing a file with its reference version
     that is expected to be found in <filename>.ref
     """
 
@@ -17,15 +17,8 @@ class Compare(object):
         re.compile("<color>[0-9a-f]+</color>"),
     ]
 
-    def __init__(self, filename, ref_name=None):
-        """
-        create object from its filename
-        compute reference filename if not specified
-        """
-        self.filename = filename
-        self.ref_name = ref_name or f"{self.filename}.ref"
-
-    def _bool_compare(self):
+    @staticmethod
+    def _bool_compare(fn_fm, fnref_fm):
         """
         returns True if both files match - modulo ignored portions
         - and False otherwise
@@ -37,28 +30,37 @@ def _bool_compare(self):
         # contents[1] for the reference version
         contents = [None, None]
 
-        for i, name in enumerate((self.filename, self.ref_name)):
+        for i, (name, fm) in enumerate((fn_fm, fnref_fm)):
             try:
-                with open(name, "r", newline="\n") as input:
+                with fm.open(name, mode=fm.READ) as input:
                     full = input.read()
-                    # remove ignored portions
-                    for ignore in self.ignore_regexps:
-                        full = re.sub(ignore, '', full)
+                # remove ignored portions
+                for ignore in Compare.ignore_regexps:
+                    full = ignore.sub('', full)
                 contents[i] = full
             # if anything goes wrong we just return False
             except Exception as e:
                 print(f"Could not read output {name}")
                 return False
-            # result is True iff both contents match
+            # result is True if both contents match
         return contents[0] == contents[1]
 
-    def compare_and_print(self):
+    @staticmethod
+    def compare_and_print(fn_fm, fnref_fm):
         """
         Checks for equality and prints a one-liner
         returns a boolean that says if both files indeed are equal
+
+        Args:
+            fn_fm: tuple of filename to test and filemanager
+            fnref_fm: tuple of filename of reference and filemanager
         """
-        bool_result = self._bool_compare()
+        filename, _ = fn_fm
+        ref_name, fm = fnref_fm
+        # compute reference filename if not specified
+        ref_name = ref_name or f"{filename}.ref"
+        bool_result = Compare._bool_compare(fn_fm, (ref_name, fm))
         status = "OK" if bool_result else "KO"
-        message = f"Comparing {self.filename} and {self.ref_name} -> {status}"
+        message = f"Comparing {filename} and {ref_name} -> {status}"
         print(message)
         return bool_result

data/file_manager.py

@@ -0,0 +1,48 @@
+import abc
+import enum
+import gzip
+
+
+class AbstractFileManager(abc.ABC):
+
+    @classmethod
+    def open(cls, filename, mode):
+        return cls._open(filename,
+            **{"encoding": "UTF-8", "mode": mode, "newline": '\n'})
+
+    @staticmethod
+    @abc.abstractmethod
+    def _open(filename, **kwargs):
+        pass
+
+    @property
+    def READ(self):
+        return self.Mode.READ.value
+
+    @property
+    def WRITE(self):
+        return self.Mode.WRITE.value
+
+
+class GzipFileManager(AbstractFileManager):
+
+    @enum.unique
+    class Mode(enum.Enum):
+        READ = "rt"
+        WRITE = "wt"
+
+    @staticmethod
+    def _open(filename, **kwargs):
+        return gzip.open(filename=filename, **kwargs)
+
+
+class TextFileManager(AbstractFileManager):
+
+    @enum.unique
+    class Mode(enum.Enum):
+        READ = "r"
+        WRITE = "w"
+
+    @staticmethod
+    def _open(filename, **kwargs):
+        return open(file=filename, **kwargs)

data/merger.py

@@ -1,16 +1,14 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 
-# Version : 3.0
-
 # standard library imports
-import gzip
 import json
 import glob
 from argparse import ArgumentParser
 #
 
 # application imports
+import file_manager
 from shipdict import ShipDict
 from kml import KML
 from compare import Compare
@@ -50,6 +48,12 @@ def __init__(self):
 
         self.ship_dict = ShipDict()
 
+        # file manager
+        if self.args.gzip:
+            self.fm = file_manager.GzipFileManager()
+        else:
+            self.fm = file_manager.TextFileManager()
+
     def merge(self, json_filenames):
         """
         given a list of json filenames, decode the JSON content
@@ -95,7 +99,8 @@ def write_ships_summary(self, ships, out_name):
 
         print(f"Opening {filename} for listing ships")
 
-        with open(filename, 'w', newline="\n") as summary:
+        tfm = file_manager.TextFileManager()
+        with tfm.open(filename, tfm.WRITE) as summary:
             # one line to say how many ships we have seen
             summary.write(f"Found {len(ships)} ships\n")
             # ships are expected to be sorted already
@@ -131,8 +136,7 @@ def write_kml_output(self, ships, out_name):
         # message
         print(f"Opening {kml_filename} for ship {out_name}")
         # open a plain file or compressed file as requested
-        with gzip.open(kml_filename, 'w', newline="\n") if self.args.gzip \
-                else open(kml_filename, 'w', newline="\n") as out:
+        with self.fm.open(kml_filename, mode=self.fm.WRITE) as out:
             out.write(contents)
         # return filename
         return kml_filename
@@ -186,9 +190,7 @@ def main(self):
                 output_name = self.args.ship_name
 
             # sort ships once and for good
-            # we can't sort these objects inline as they are
-            # typically dict_values objects
-            ships = sorted(ships, key=lambda ship: ship.name)
+            ships.sort(key=lambda ship: ship.name)
 
             # create summary file
             summary_filename = self.write_ships_summary(ships, output_name)
@@ -201,8 +203,13 @@ def main(self):
             else:
                 # for each of the 2 files, compare contents with the reference
                 # that is expected to be in this directory with a .ref extension
-                ok_summary = Compare(summary_filename).compare_and_print()
-                ok_kml = Compare(kml_filename).compare_and_print()
+                tfm = file_manager.TextFileManager()
+                ok_summary = Compare.compare_and_print(
+                  (summary_filename, tfm),
+                  (None, tfm))
+                ok_kml = Compare.compare_and_print(
+                  (kml_filename, self.fm),
+                  ("ALL_SHIPS.kml.ref", tfm))
                 # is everything fine ?
                 ok = ok_summary and ok_kml
             # if so return 0 otherwise 1

data/shipdict.py

@@ -222,6 +222,6 @@ def all_ships(self):
         # we need to create an actual list because it
         # may need to be sorted later on, and so
         # a raw dict_values object won't be good enough
-        return self.values()
+        return list(self.values())
 
 # @END@