UTF-8 characters from marketo are improperly decoded singer-io#74

tap_marketo/sync.py

@@ -134,16 +134,17 @@ def wait_for_export(client, state, stream, export_id):
 # This function has an issue with UTF-8 data most likely caused by decode_unicode=True
 # See https://github.com/singer-io/tap-marketo/pull/51/files
 def stream_rows(client, stream_type, export_id):
-    with tempfile.NamedTemporaryFile(mode="w+", encoding="utf8") as csv_file:
+    with tempfile.NamedTemporaryFile(mode="w+", encoding="utf8", delete=False) as csv_file:
         singer.log_info("Download starting.")
         resp = client.stream_export(stream_type, export_id)
+        resp.encoding = 'utf-8'
         for chunk in resp.iter_content(chunk_size=CHUNK_SIZE_BYTES, decode_unicode=True):
             if chunk:
                 # Replace CR
                 chunk = chunk.replace('\r', '')
                 csv_file.write(chunk)
 
-        singer.log_info("Download completed. Begin streaming rows.")
+        singer.log_info("Download completed. Begin streaming rows to file: " + csv_file.name)
         csv_file.seek(0)
 
         reader = csv.reader((line.replace('\0', '') for line in csv_file), delimiter=',', quotechar='"')