add config and csv tools

3 files changed, 82 insertions, 0 deletions

diff --git a/datastore_reader/utils/__init__.py b/datastore_reader/utils/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/datastore_reader/utils/__init__.py
diff --git a/datastore_reader/utils/config.py b/datastore_reader/utils/config.py
new file mode 100644
index 0000000..76caed6
--- /dev/null
+++ b/datastore_reader/utils/config.py
@@ -0,0 +1,16 @@
+# config obj
+from ConfigObject import config_module
+
+def _init_config_obj():
+    # init config obj
+    config_module(__name__, __file__, 'config.ini')
+
+# singleton flag
+__initialized__ = False
+
+# do init
+if __initialized__ is False:
+    # init config
+    _init_config_obj()
+    # update flag
+    __initialized__ = True
diff --git a/datastore_reader/utils/csv.py b/datastore_reader/utils/csv.py
new file mode 100644
index 0000000..c31eafb
--- /dev/null
+++ b/datastore_reader/utils/csv.py
@@ -0,0 +1,66 @@
+import csv, codecs, cStringIO
+
+class UTF8Recoder:
+    """
+    Iterator that reads an encoded stream and reencodes the input to UTF-8
+    """
+    def __init__(self, f, encoding):
+        self.reader = codecs.getreader(encoding)(f)
+
+    def __iter__(self):
+        return self
+
+    def next(self):
+        return self.reader.next().encode("utf-8")
+
+class Reader:
+    """
+    A CSV reader which will iterate over lines in the CSV file "f",
+    which is encoded in the given encoding.
+    """
+
+    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
+        f = UTF8Recoder(f, encoding)
+        self.reader = csv.reader(f, dialect=dialect, **kwds)
+
+    def next(self):
+        row = self.reader.next()
+        return [unicode(s, "utf-8") for s in row]
+
+    def __iter__(self):
+        return self
+
+class Writer:
+    """
+    A CSV writer which will write rows to CSV file "f",
+    which is encoded in the given encoding.
+    """
+
+    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
+        # Redirect output to a queue
+        self.queue = cStringIO.StringIO()
+        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
+        self.stream = f
+        self.encoder = codecs.getincrementalencoder(encoding)()
+
+    def writerow(self, row):
+        for i, s in enumerate(row):
+            # ensure string for encoding
+            if not isinstance(s, str)\
+            and not isinstance(s, unicode):
+                s = str(s)
+            row[i] = s.encode("utf-8")
+        self.writer.writerow(row)
+        # Fetch UTF-8 output from the queue ...
+        data = self.queue.getvalue()
+        data = data.decode("utf-8")
+        # ... and reencode it into the target encoding
+        data = self.encoder.encode(data)
+        # write to the target stream
+        self.stream.write(data)
+        # empty queue
+        self.queue.truncate(0)
+
+    def writerows(self, rows):
+        for row in rows:
+            self.writerow(row)