Increase max size of CSV to system's max int (#53)

* Increase max size of CSV to system's max int

* Pylint fixes

* Fix syntax error

* More pylint

* Pylint

.circleci/config.yml

@@ -12,7 +12,7 @@ jobs:
             source ~/.virtualenvs/tap-salesforce/bin/activate
             pip install .
             pip install pylint
-            pylint tap_salesforce -d missing-docstring,invalid-name,line-too-long,too-many-locals,too-few-public-methods,fixme,stop-iteration-return
+            pylint tap_salesforce -d missing-docstring,invalid-name,line-too-long,too-many-locals,too-few-public-methods,fixme,stop-iteration-return,no-else-return
       - run:
           name: 'Unit Tests'
           command: |

tap_salesforce/__init__.py

@@ -2,9 +2,8 @@
 import json
 import sys
 import singer
-import singer.metrics as metrics
 import singer.utils as singer_utils
-from singer import metadata
+from singer import metadata, metrics
 
 import tap_salesforce.salesforce
 from tap_salesforce.sync import (sync_stream, resume_syncing_bulk_query, get_stream_version)
@@ -102,8 +101,7 @@ def do_discover(sf):
     """Describes a Salesforce instance's objects and generates a JSON schema for each field."""
     global_description = sf.describe()
 
-    objects_to_discover = set([o['name']
-                               for o in global_description['sobjects']])
+    objects_to_discover = {o['name'] for o in global_description['sobjects']}
     key_properties = ['Id']
 
     sf_custom_setting_objects = []
@@ -177,7 +175,7 @@ def do_discover(sf):
 
         # There are cases where compound fields are referenced by the associated
         # subfields but are not actually present in the field list
-        field_name_set = set([f['name'] for f in fields])
+        field_name_set = {f['name'] for f in fields}
         filtered_unsupported_fields = [f for f in unsupported_fields if f[0] in field_name_set]
         missing_unsupported_field_names = [f[0] for f in unsupported_fields if f[0] not in field_name_set]
 
@@ -245,7 +243,7 @@ def do_discover(sf):
     unsupported_tag_objects = [object_to_tag_references[f]
                                for f in sf_custom_setting_objects if f in object_to_tag_references]
     if unsupported_tag_objects:
-        LOGGER.info(
+        LOGGER.info( #pylint:disable=logging-not-lazy
             "Skipping the following Tag objects, Tags on Custom Settings Salesforce objects " +
             "are not supported by the Bulk API:")
         LOGGER.info(unsupported_tag_objects)

tap_salesforce/salesforce/__init__.py

@@ -5,9 +5,8 @@
 import requests
 from requests.exceptions import RequestException
 import singer
-import singer.metrics as metrics
 import singer.utils as singer_utils
-from singer import metadata
+from singer import metadata, metrics
 
 from tap_salesforce.salesforce.bulk import Bulk
 from tap_salesforce.salesforce.rest import Rest
@@ -185,7 +184,7 @@ def field_to_property_schema(field, mdata):
 
     return property_schema, mdata
 
-class Salesforce(object):
+class Salesforce():
     # pylint: disable=too-many-instance-attributes,too-many-arguments
     def __init__(self,
                  refresh_token=None,

tap_salesforce/salesforce/bulk.py

@@ -1,10 +1,11 @@
 # pylint: disable=protected-access
 import csv
 import json
+import sys
 import time
 import tempfile
 import singer
-import singer.metrics as metrics
+from singer import metrics
 
 import xmltodict
 
@@ -35,11 +36,13 @@ def find_parent(stream):
     return parent_stream
 
 
-class Bulk(object):
+class Bulk():
 
     bulk_url = "{}/services/async/41.0/{}"
 
     def __init__(self, sf):
+        # Set csv max reading size to the platform's max size available.
+        csv.field_size_limit(sys.maxsize)
         self.sf = sf
 
     def query(self, catalog_entry, state):

tap_salesforce/salesforce/rest.py

@@ -8,7 +8,7 @@
 
 MAX_RETRIES = 4
 
-class Rest(object):
+class Rest():
 
     def __init__(self, sf):
         self.sf = sf

tap_salesforce/sync.py

@@ -1,8 +1,7 @@
 import time
 import singer
-import singer.metrics as metrics
 import singer.utils as singer_utils
-from singer import Transformer, metadata
+from singer import Transformer, metadata, metrics
 from requests.exceptions import RequestException
 from tap_salesforce.salesforce.bulk import Bulk