Skip to content

feat: add optional do_not_paginate parameter - option 1 (stream) #225

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

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

feat: add optional do_not_paginate parameter - option 1 (stream) #225

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f3cebf6
add optional do_not_paginate parameter
ericboucher Jul 25, 2023
5790c6d
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Jul 25, 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
27 changes: 25 additions & 2 deletions tap_github/repository_streams.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2191,6 +2191,7 @@ class DependenciesStream(GitHubGraphqlStream):
parent_stream_type = RepositoryStream
state_partitioning_keys = ["repo_id"]
ignore_parent_replication_key = True
do_not_paginate = False

@property
def http_headers(self) -> dict:
Expand Down Expand Up @@ -2220,7 +2221,7 @@ def query(self) -> str:
"""Return dynamic GraphQL query."""
# Graphql id is equivalent to REST node_id. To keep the tap consistent, we rename "id" to "node_id".
# Due to GrapQl nested-pagination limitations, we loop through the top level dependencyGraphManifests one by one.
return """
initial_query = """
query repositoryDependencies($repo: String! $org: String! $nextPageCursor_0: String $nextPageCursor_1: String) {
repository(name: $repo owner: $org) {
dependencyGraphManifests (first: 1 withDependencies: true after: $nextPageCursor_0) {
Expand Down Expand Up @@ -2263,9 +2264,25 @@ def query(self) -> str:
cost
}
}

"""

if self.do_not_paginate:
no_pagination_query = initial_query.replace(
" $nextPageCursor_0: String $nextPageCursor_1: String", ""
)
no_pagination_query = no_pagination_query.replace(
"after: $nextPageCursor_0", ""
)
no_pagination_query = no_pagination_query.replace(
"after: $nextPageCursor_1", ""
)
no_pagination_query = no_pagination_query.replace("first: 1", "first: 10")
no_pagination_query = no_pagination_query.replace("first: 50", "first: 100")

return no_pagination_query

return initial_query

schema = th.PropertiesList(
# Parent Keys
th.Property("repo", th.StringType),
Expand Down Expand Up @@ -2296,6 +2313,12 @@ def query(self) -> str:
).to_dict()


class DependenciesStreamIncomplete(DependenciesStream):
"""Defines 'DependenciesStreamDirty' stream to limit pagination."""

do_not_paginate = True


class TrafficRestStream(GitHubRestStream):
"""Base class for Traffic Streams"""

Expand Down
2 changes: 2 additions & 0 deletions tap_github/streams.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
CommunityProfileStream,
ContributorsStream,
DependenciesStream,
DependenciesStreamIncomplete,
DependentsStream,
EventsStream,
ExtraMetricsStream,
Expand Down Expand Up @@ -75,6 +76,7 @@ def __init__(self, valid_queries: Set[str], streams: List[Type[Stream]]):
CommunityProfileStream,
ContributorsStream,
DependenciesStream,
DependenciesStreamIncomplete,
DependentsStream,
EventsStream,
IssueCommentsStream,
Expand Down