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

Jump to bottom

Migrate CLX parsers #894

Merged
merged 16 commits into from
May 5, 2023
Merged

Migrate CLX parsers #894

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
1f23c52
migrate clx parsers
efajardo-nv Apr 14, 2023
e0f4cc5
parser updates
efajardo-nv Apr 19, 2023
6a51aed
update docstring
efajardo-nv Apr 19, 2023
5337257
Merge branch 'branch-23.07' of https://github.com/nv-morpheus/Morpheu…
efajardo-nv Apr 19, 2023
618410b
add __init__.py to parsers
efajardo-nv Apr 19, 2023
21c99a0
update regex yaml filepaths
efajardo-nv Apr 19, 2023
bfd80cf
move regex yamls to morpheus.DATA_DIR
efajardo-nv Apr 19, 2023
5b15221
Merge branch 'branch-23.07' of https://github.com/nv-morpheus/Morpheu…
efajardo-nv Apr 20, 2023
1c62433
Merge branch 'branch-23.07' into migrate-clx-parsers
efajardo-nv Apr 24, 2023
ed9b984
add clx url parser
efajardo-nv Apr 27, 2023
fb113a8
Merge branch 'migrate-clx-parsers' of https://github.com/efajardo-nv/…
efajardo-nv Apr 27, 2023
03256b4
style fixes
efajardo-nv Apr 27, 2023
7822dc1
Merge branch 'branch-23.07' of https://github.com/nv-morpheus/Morpheu…
efajardo-nv Apr 27, 2023
6464362
add clx ip tool
efajardo-nv May 1, 2023
a9ca88e
update docstring
efajardo-nv May 1, 2023
cbc9d80
Merge branch 'branch-23.07' into migrate-clx-parsers
efajardo-nv May 1, 2023
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
Prev Previous commit
Next Next commit
style fixes
  • Loading branch information
@efajardo-nv
efajardo-nv committed Apr 27, 2023
commit 03256b4fac6759f1cf1906ad1e897c711ef11b71
2 changes: 1 addition & 1 deletion morpheus/parsers/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Copyright (c) 2023, NVIDIA CORPORATION.
# Copyright (c) 2022-2023, NVIDIA CORPORATION.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
Expand Down
250 changes: 122 additions & 128 deletions tests/test_url_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,155 +13,149 @@
# limitations under the License.

import pytest

from cudf import DataFrame

from morpheus.parsers import url_parser

input_df = DataFrame(
{
"url": [
"http://www.google.com",
"gmail.com",
"github.com",
"https://pandas.pydata.org",
"http://www.worldbank.org.kg/",
"waiterrant.blogspot.com",
"http://forums.news.cnn.com.ac/",
"http://forums.news.cnn.ac/",
"ftp://b.cnn.com/",
"a.news.uk",
"a.news.co.uk",
"https://a.news.co.uk",
"107-193-100-2.lightspeed.cicril.sbcglobal.net",
"a23-44-13-2.deploy.static.akamaitechnologies.com",
]
}
)
input_df = DataFrame({
"url": [
"http://www.google.com",
"gmail.com",
"github.com",
"https://pandas.pydata.org",
"http://www.worldbank.org.kg/",
"waiterrant.blogspot.com",
"http://forums.news.cnn.com.ac/",
"http://forums.news.cnn.ac/",
"ftp://b.cnn.com/",
"a.news.uk",
"a.news.co.uk",
"https://a.news.co.uk",
"107-193-100-2.lightspeed.cicril.sbcglobal.net",
"a23-44-13-2.deploy.static.akamaitechnologies.com",
]
})


@pytest.mark.parametrize("input_df", [input_df])
def test_parse_1(input_df):
expected_output_df = DataFrame(
{
"domain": [
"google",
"gmail",
"github",
"pydata",
"worldbank",
"waiterrant",
"cnn",
"cnn",
"cnn",
"news",
"news",
"news",
"sbcglobal",
"akamaitechnologies",
],
"suffix": [
"com",
"com",
"com",
"org",
"org.kg",
"blogspot.com",
"com.ac",
"ac",
"com",
"uk",
"co.uk",
"co.uk",
"net",
"com",
],
}
)
expected_output_df = DataFrame({
"domain": [
"google",
"gmail",
"github",
"pydata",
"worldbank",
"waiterrant",
"cnn",
"cnn",
"cnn",
"news",
"news",
"news",
"sbcglobal",
"akamaitechnologies",
],
"suffix": [
"com",
"com",
"com",
"org",
"org.kg",
"blogspot.com",
"com.ac",
"ac",
"com",
"uk",
"co.uk",
"co.uk",
"net",
"com",
],
})
output_df = url_parser.parse(input_df["url"], req_cols={"domain", "suffix"})

assert expected_output_df.equals(output_df)


@pytest.mark.parametrize("input_df", [input_df])
def test_parse_2(input_df):
expected_output_df = DataFrame(
{
"hostname": [
"www.google.com",
"gmail.com",
"github.com",
"pandas.pydata.org",
"www.worldbank.org.kg",
"waiterrant.blogspot.com",
"forums.news.cnn.com.ac",
"forums.news.cnn.ac",
"b.cnn.com",
"a.news.uk",
"a.news.co.uk",
"a.news.co.uk",
"107-193-100-2.lightspeed.cicril.sbcglobal.net",
"a23-44-13-2.deploy.static.akamaitechnologies.com",
],
"subdomain": [
"www",
"",
"",
"pandas",
"www",
"",
"forums.news",
"forums.news",
"b",
"a",
"a",
"a",
"107-193-100-2.lightspeed.cicril",
"a23-44-13-2.deploy.static",
],
"domain": [
"google",
"gmail",
"github",
"pydata",
"worldbank",
"waiterrant",
"cnn",
"cnn",
"cnn",
"news",
"news",
"news",
"sbcglobal",
"akamaitechnologies",
],
"suffix": [
"com",
"com",
"com",
"org",
"org.kg",
"blogspot.com",
"com.ac",
"ac",
"com",
"uk",
"co.uk",
"co.uk",
"net",
"com",
],
}
)
expected_output_df = DataFrame({
"hostname": [
"www.google.com",
"gmail.com",
"github.com",
"pandas.pydata.org",
"www.worldbank.org.kg",
"waiterrant.blogspot.com",
"forums.news.cnn.com.ac",
"forums.news.cnn.ac",
"b.cnn.com",
"a.news.uk",
"a.news.co.uk",
"a.news.co.uk",
"107-193-100-2.lightspeed.cicril.sbcglobal.net",
"a23-44-13-2.deploy.static.akamaitechnologies.com",
],
"subdomain": [
"www",
"",
"",
"pandas",
"www",
"",
"forums.news",
"forums.news",
"b",
"a",
"a",
"a",
"107-193-100-2.lightspeed.cicril",
"a23-44-13-2.deploy.static",
],
"domain": [
"google",
"gmail",
"github",
"pydata",
"worldbank",
"waiterrant",
"cnn",
"cnn",
"cnn",
"news",
"news",
"news",
"sbcglobal",
"akamaitechnologies",
],
"suffix": [
"com",
"com",
"com",
"org",
"org.kg",
"blogspot.com",
"com.ac",
"ac",
"com",
"uk",
"co.uk",
"co.uk",
"net",
"com",
],
})
output_df = url_parser.parse(input_df["url"])

assert expected_output_df.equals(output_df)


@pytest.mark.parametrize("input_df", [input_df])
def test_parse_invalid_req_cols(input_df):
expected_error = ValueError(
"Given req_cols must be subset of %s"
% ('["hostname", "subdomain", "domain", "suffix"]')
)
expected_error = ValueError("Given req_cols must be subset of %s" %
('["hostname", "subdomain", "domain", "suffix"]'))
with pytest.raises(ValueError) as actual_error:
url_parser.parse(input_df["url"], req_cols={"test"})
assert actual_error == expected_error