Skip to content

fix: Correctly parse CSV where multiple results include multiple tables #64

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 28, 2020
Merged

fix: Correctly parse CSV where multiple results include multiple tables #64

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,9 @@
### Features
1. [#59](https://github.com/influxdata/influxdb-client-python/issues/59): Set User-Agent to influxdb-client-python/VERSION for all requests

### Bugs
1. [#61](https://github.com/influxdata/influxdb-client-python/issues/61): Correctly parse CSV where multiple results include multiple tables

## 1.4.0 [2020-02-14]

### Features
Expand Down
11 changes: 8 additions & 3 deletions influxdb_client/client/flux_csv_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,7 @@ def generator(self):

def _parse_flux_response(self):
table_index = 0
table_id = -1
start_new_table = False
table = None
parsing_state_error = False
Expand Down Expand Up @@ -83,6 +84,7 @@ def _parse_flux_response(self):
table = FluxTable()
self._insert_table(table, table_index)
table_index = table_index + 1
table_id = -1
elif table is None:
raise FluxCsvParserException("Unable to parse CSV response. FluxTable definition was not found.")

Expand Down Expand Up @@ -111,15 +113,18 @@ def _parse_flux_response(self):
continue

# to int converions todo
current_index = int(csv[2])
current_id = int(csv[2])
if table_id == -1:
table_id = current_id

if current_index > (table_index - 1):
if table_id != current_id:
# create new table with previous column headers settings
flux_columns = table.columns
table = FluxTable()
table.columns.extend(flux_columns)
self._insert_table(table, table_index)
table_index = table_index + 1
table_id = current_id

flux_record = self.parse_record(table_index - 1, table, csv)

Expand Down Expand Up @@ -217,4 +222,4 @@ def add_column_names_and_tags(table, csv):

def _insert_table(self, table, table_index):
if self._serialization_mode is FluxSerializationMode.tables:
self.tables.insert(table_index, table)
self.tables.insert(table_index, table)
128 changes: 128 additions & 0 deletions tests/test_FluxCSVParser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,128 @@
from io import BytesIO

from urllib3 import HTTPResponse

from influxdb_client.client.flux_csv_parser import FluxCsvParser, FluxSerializationMode
from tests.base_test import BaseTest


class FluxCsvParserTest(BaseTest):

def test_one_table(self):
data = "#datatype,string,long,dateTime:RFC3339,dateTime:RFC3339,string,string,string,string,long,long,string\n" \
"#group,false,false,true,true,true,true,true,true,false,false,false\n" \
"#default,_result,,,,,,,,,,\n" \
",result,table,_start,_stop,_field,_measurement,host,region,_value2,value1,value_str\n" \
",,0,1677-09-21T00:12:43.145224192Z,2018-07-16T11:21:02.547596934Z,free,mem,A,west,121,11,test\n"

tables = self._parse_to_tables(data=data)
self.assertEqual(1, tables.__len__())
self.assertEqual(11, tables[0].columns.__len__())
self.assertEqual(1, tables[0].records.__len__())

def test_more_tables(self):
data = "#datatype,string,long,dateTime:RFC3339,dateTime:RFC3339,string,string,string,string,long,long,string\n" \
"#group,false,false,true,true,true,true,true,true,false,false,false\n" \
"#default,_result,,,,,,,,,,\n" \
",result,table,_start,_stop,_field,_measurement,host,region,_value2,value1,value_str\n" \
",,0,1677-09-21T00:12:43.145224192Z,2018-07-16T11:21:02.547596934Z,free,mem,A,west,121,11,test\n" \
",,1,1677-09-21T00:12:43.145224192Z,2018-07-16T11:21:02.547596934Z,free,mem,B,west,484,22,test\n" \
",,2,1677-09-21T00:12:43.145224192Z,2018-07-16T11:21:02.547596934Z,usage_system,cpu,A,west,1444,38,test\n" \
",,3,1677-09-21T00:12:43.145224192Z,2018-07-16T11:21:02.547596934Z,user_usage,cpu,A,west,2401,49,test"

tables = self._parse_to_tables(data=data)
self.assertEqual(4, tables.__len__())
self.assertEqual(11, tables[0].columns.__len__())
self.assertEqual(1, tables[0].records.__len__())
self.assertEqual(11, tables[1].columns.__len__())
self.assertEqual(1, tables[1].records.__len__())
self.assertEqual(11, tables[2].columns.__len__())
self.assertEqual(1, tables[2].records.__len__())
self.assertEqual(11, tables[3].columns.__len__())
self.assertEqual(1, tables[3].records.__len__())

def test_multiple_queries(self):
data = "#datatype,string,long,string,string,dateTime:RFC3339,dateTime:RFC3339,dateTime:RFC3339,double,string\n" \
"#group,false,false,true,true,true,true,false,false,true\n" \
"#default,t1,,,,,,,,\n" \
",result,table,_field,_measurement,_start,_stop,_time,_value,tag\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:20:00Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:21:40Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:23:20Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:25:00Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:26:40Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:28:20Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:30:00Z,2,test1\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:20:00Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:21:40Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:23:20Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:25:00Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:26:40Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:28:20Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:30:00Z,2,test2\n" \
"\n" \
"#datatype,string,long,string,string,dateTime:RFC3339,dateTime:RFC3339,dateTime:RFC3339,double,string\n" \
"#group,false,false,true,true,true,true,false,false,true\n" \
"#default,t2,,,,,,,,\n" \
",result,table,_field,_measurement,_start,_stop,_time,_value,tag\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:20:00Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:21:40Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:23:20Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:25:00Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:26:40Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:28:20Z,2,test1\n" \
",,0,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:30:00Z,2,test1\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:20:00Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:21:40Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:23:20Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:25:00Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:26:40Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:28:20Z,2,test2\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:30:00Z,2,test2"

tables = self._parse_to_tables(data=data)
self.assertEqual(4, tables.__len__())
self.assertEqual(9, tables[0].columns.__len__())
self.assertEqual(7, tables[0].records.__len__())
self.assertEqual(9, tables[1].columns.__len__())
self.assertEqual(7, tables[1].records.__len__())
self.assertEqual(9, tables[2].columns.__len__())
self.assertEqual(7, tables[2].records.__len__())
self.assertEqual(9, tables[3].columns.__len__())
self.assertEqual(7, tables[3].records.__len__())

def test_table_index_not_start_at_zero(self):
data = "#datatype,string,long,string,string,dateTime:RFC3339,dateTime:RFC3339,dateTime:RFC3339,double,string\n" \
"#group,false,false,true,true,true,true,false,false,true\n" \
"#default,t1,,,,,,,,\n" \
",result,table,_field,_measurement,_start,_stop,_time,_value,tag\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:20:00Z,2,test1\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:21:40Z,2,test1\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:23:20Z,2,test1\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:25:00Z,2,test1\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:26:40Z,2,test1\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:28:20Z,2,test1\n" \
",,1,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:30:00Z,2,test1\n" \
",,2,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:20:00Z,2,test2\n" \
",,2,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:21:40Z,2,test2\n" \
",,2,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:23:20Z,2,test2\n" \
",,2,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:25:00Z,2,test2\n" \
",,2,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:26:40Z,2,test2\n" \
",,2,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:28:20Z,2,test2\n" \
",,2,value,python_client_test,2010-02-27T04:48:32.752600083Z,2020-02-27T16:48:32.752600083Z,2020-02-27T16:30:00Z,2,test2\n"

tables = self._parse_to_tables(data=data)
self.assertEqual(2, tables.__len__())
self.assertEqual(9, tables[0].columns.__len__())
self.assertEqual(7, tables[0].records.__len__())
self.assertEqual(9, tables[1].columns.__len__())
self.assertEqual(7, tables[1].records.__len__())

@staticmethod
def _parse_to_tables(data: str):
fp = BytesIO(str.encode(data))
_parser = FluxCsvParser(response=HTTPResponse(fp, preload_content=False),
serialization_mode=FluxSerializationMode.tables)
list(_parser.generator())
tables = _parser.tables
return tables
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy