mirror of
https://github.com/cyclotruc/gitingest.git
synced 2026-05-01 07:29:36 +00:00
dd8f1e0aac
* feat: make parser domain-agnostic to support multiple Git hosts - added list of known domains/Git hosts in `query_parser.py` - fixed bug from [#115](https://github.com/cyclotruc/gitingest/pull/115): corrected case handling for URL components—scheme, domain, username, and repository are case-insensitive, but paths beyond (e.g., file names, branches) are case-sensitive - implemented `try_domains_for_user_and_repo` in `query_parser.py` to iteratively guess the correct domain until success or supported hosts are exhausted - added helper functions `_get_user_and_repo_from_path`, `_validate_host`, and `_validate_scheme` in `query_parser.py` - extended `_parse_repo_source` in `query_parser.py` to be Git host agnostic by using `try_domains_for_user_and_repo` - added tests `test_parse_url_unsupported_host` and `test_parse_query_with_branch` in `test_query_parser.py` - created new file `test_git_host_agnostic.py` to verify domain/Git host agnostic behavior
81 lines
2.4 KiB
Python
81 lines
2.4 KiB
Python
""" Tests to verify that the query parser is Git host agnostic. """
|
|
|
|
import pytest
|
|
|
|
from gitingest.query_parser import parse_query
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"urls, expected_user, expected_repo, expected_url",
|
|
[
|
|
(
|
|
[
|
|
"https://github.com/tiangolo/fastapi",
|
|
"github.com/tiangolo/fastapi",
|
|
"tiangolo/fastapi",
|
|
],
|
|
"tiangolo",
|
|
"fastapi",
|
|
"https://github.com/tiangolo/fastapi",
|
|
),
|
|
(
|
|
[
|
|
"https://gitlab.com/gitlab-org/gitlab-runner",
|
|
"gitlab.com/gitlab-org/gitlab-runner",
|
|
"gitlab-org/gitlab-runner",
|
|
],
|
|
"gitlab-org",
|
|
"gitlab-runner",
|
|
"https://gitlab.com/gitlab-org/gitlab-runner",
|
|
),
|
|
(
|
|
[
|
|
"https://bitbucket.org/na-dna/llm-knowledge-share",
|
|
"bitbucket.org/na-dna/llm-knowledge-share",
|
|
"na-dna/llm-knowledge-share",
|
|
],
|
|
"na-dna",
|
|
"llm-knowledge-share",
|
|
"https://bitbucket.org/na-dna/llm-knowledge-share",
|
|
),
|
|
(
|
|
[
|
|
"https://gitea.com/xorm/xorm",
|
|
"gitea.com/xorm/xorm",
|
|
"xorm/xorm",
|
|
],
|
|
"xorm",
|
|
"xorm",
|
|
"https://gitea.com/xorm/xorm",
|
|
),
|
|
(
|
|
[
|
|
"https://codeberg.org/forgejo/forgejo",
|
|
"codeberg.org/forgejo/forgejo",
|
|
"forgejo/forgejo",
|
|
],
|
|
"forgejo",
|
|
"forgejo",
|
|
"https://codeberg.org/forgejo/forgejo",
|
|
),
|
|
],
|
|
)
|
|
@pytest.mark.asyncio
|
|
async def test_parse_query_without_host(
|
|
urls: list[str],
|
|
expected_user: str,
|
|
expected_repo: str,
|
|
expected_url: str,
|
|
) -> None:
|
|
for url in urls:
|
|
result = await parse_query(url, max_file_size=50, from_web=True)
|
|
# Common assertions for all cases
|
|
assert result["user_name"] == expected_user
|
|
assert result["repo_name"] == expected_repo
|
|
assert result["url"] == expected_url
|
|
assert result["slug"] == f"{expected_user}-{expected_repo}"
|
|
assert result["id"] is not None
|
|
assert result["subpath"] == "/"
|
|
assert result["branch"] is None
|
|
assert result["commit"] is None
|
|
assert result["type"] is None
|