Conversation
akirak
force-pushed
the
fix-empty-cells
branch
from
fdbd5d3 to
a624d2d
Compare
akirak
force-pushed
the
fix-empty-cells
branch
from
a624d2d to
4782cee
Compare
|
@codex review |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 4782ceef45
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
lib/xlsxir/parse_worksheet.ex
Outdated
| empty_cells = | ||
| cond do | ||
| is_nil(previous) && String.first(ref) != "A" -> | ||
| is_nil(previous) && Regex.match?(~r/^A\d/, ref) -> |
There was a problem hiding this comment.
The new guard in fill_nil/1 now calls fill_empty_cells/4 only when the first reference matches A\d, which is the opposite of what this branch needs. For rows whose first populated cell is B1, C1, or AA1, previous is nil and this condition is false, so no leading nil cells are inserted and row values shift left in get_list/1/get_mda/1. This both fails to fix the AA1 case and regresses previously working non-A columns.
Useful? React with 👍 / 👎.
akirak
force-pushed
the
fix-empty-cells
branch
from
4782cee to
b88bcda
Compare
2 participants
There are situations where the first non-empty cell on a row is like
AA1, which has not been handled previously. This PR fixes that.There is currently no test case for this. Can I modify the test data to add a test case for this PR?