Skip to content
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

fix: handle all whitespaces in column names #17

Merged
merged 7 commits into from
Jan 17, 2024
Merged

fix: handle all whitespaces in column names #17

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
3829542
fix: handle whitespaces in column names
srpwnd Jan 17, 2024
47c54df
chore: update test to assert multiple whitespace cases
srpwnd Jan 17, 2024
107d7b5
chore: formatting
srpwnd Jan 17, 2024
ce92cf8
Merge branch 'master' into fix/column-whitespace
ReubenFrankel Jan 17, 2024
343ff50
chore: fix formatting
srpwnd Jan 17, 2024
a993398
chore: sort imports
srpwnd Jan 17, 2024
fdaf267
chore: make regex string raw
srpwnd Jan 17, 2024
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: 2 additions & 1 deletion tap_google_sheets/streams.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
"""Stream type classes for tap-google-sheets."""

import re
from itertools import zip_longest
from pathlib import Path
from typing import Iterable
Expand Down Expand Up @@ -37,7 +38,7 @@ def parse_response(self, response: requests.Response) -> Iterable[dict]:
data_rows.append(
dict(
[
(h.replace(" ", "_"), v or "")
(re.sub(r"\s+", "_", h.strip()), v or "")
for m, h, v in zip_longest(mask, headings, values)
if m
]
Expand Down
5 changes: 4 additions & 1 deletion tap_google_sheets/tap.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
"""google_sheets tap class."""

import re
from typing import List

import requests
Expand Down Expand Up @@ -102,7 +103,9 @@ def get_schema(self, google_sheet_data: requests.Response):
schema = th.PropertiesList()
for column in headings:
if column:
schema.append(th.Property(column.replace(" ", "_"), th.StringType))
schema.append(
th.Property(re.sub(r"\s+", "_", column.strip()), th.StringType)
)

return schema.to_dict()

Expand Down
30 changes: 27 additions & 3 deletions tap_google_sheets/tests/test_underscoring_column_names.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,21 @@ def setUp(self):

@responses.activate()
def test_underscoring_column_names(self):
self.column_response = {"values": [["Column One", "Column Two"], ["1", "1"]]}
self.column_response = {
"values": [
[
"Column One",
" Column Two",
" Column Three ",
"Column\nFour",
"Column \n\tFive\n\n\t ",
"Multi Column One",
" Multi Column Two ",
"\tMulti \r\nColumn\f\vThree",
],
["1"] * 8,
]
}

responses.add(
responses.POST,
Expand All @@ -39,7 +53,7 @@ def test_underscoring_column_names(self):
responses.add(
responses.GET,
"https://sheets.googleapis.com/v4/spreadsheets/12345/values/!1:1",
json={"range": "Sheet1!1:1", "values": [["Column_One", "Column_Two"]]},
json={"range": "Sheet1!1:1", "values": [self.column_response["values"][0]]},
status=200,
),
responses.add(
Expand All @@ -61,5 +75,15 @@ def test_underscoring_column_names(self):

# Assert that column names have been underscored
self.assertEquals(
test_utils.SINGER_MESSAGES[2].record, {"Column_One": "1", "Column_Two": "1"}
test_utils.SINGER_MESSAGES[2].record,
{
"Column_One": "1",
"Column_Two": "1",
"Column_Three": "1",
"Column_Four": "1",
"Column_Five": "1",
"Multi_Column_One": "1",
"Multi_Column_Two": "1",
"Multi_Column_Three": "1",
},
)
Loading