ENH+BF: Format species names consistently in species_map, make matching more stringent for common names, improved testing by Copilot · Pull Request #1866 · dandi/dandi-cli

Copilot · 2026-05-28T22:49:59Z

Thanks for the feedback on #1865. I've created this new PR, which merges into #1865, to address your comment. I will work on the changes and keep this PR's description up to date as I make progress.

Original PR: #1865
Triggering review: #1865 (comment)

I think this version is better than just
        "Macaca radiata",
as we did for "Macaca nemestrina" above . I think we should expand all others into similar

{current name} - {Genbank common name} form which seems they all follow.

@copilot -- prepare a PR where all other entries follow the same format for their "name" and also expand description above on the expected format of the "name" field

Adds NCBI taxon 9548 (Macaca radiata, common name "bonnet macaque") to the species lookup table so the species can be recognized by common name, "radiata", or its NCBITaxon URL. Requested by a user via email. Co-Authored-By: Claude Code 2.1.154 / Claude Opus 4.7 <noreply@anthropic.com>

…fall back + more thorough testing of mapping itself Added by copilot test revealed a problem of matching 'rat' potentially to multiple (thus order dependent) entries since we have multiple 'rat's but only one of them is commonly named 'rat'. So I decided to split out that other test for common names out. Also extended with a dedicated test for that. Made it potentially gain multiple matches and then explicitly fail/raise exception so we do not proceed with some oddly matched item

…taining Otherwise we would be matching partial names etc. Better fail than to do wrong match!

yarikoptic · 2026-05-29T13:16:18Z

@copilot I force pushed my changes over yours, improved matching and testing. Now

Address type-check fails
Adjust overall PR description to reflect carried out changes fuller (I already adjusted the title)

yarikoptic · 2026-05-29T13:17:09Z

@copilot also please review my changes as well!

codecov · 2026-05-29T13:17:39Z

Codecov Report

❌ Patch coverage is 94.28571% with 2 lines in your changes missing coverage. Please review.
✅ Project coverage is 76.73%. Comparing base (813fb8e) to head (e85ef07).

Files with missing lines	Patch %	Lines
dandi/metadata/util.py	85.71%	2 Missing ⚠️

Additional details and impacted files

@@                  Coverage Diff                   @@
##           enh-macaca-radiata    #1866      +/-   ##
======================================================
- Coverage               76.74%   76.73%   -0.01%     
======================================================
  Files                      87       87              
  Lines                   12769    12788      +19     
======================================================
+ Hits                     9799     9813      +14     
- Misses                   2970     2975       +5

Flag	Coverage Δ
unittests	`76.73% <94.28%> (-0.01%)`	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Copilot · 2026-05-29T13:25:23Z

@copilot I force pushed my changes over yours, improved matching and testing. Now

Address type-check fails

Adjust overall PR description to reflect carried out changes fuller (I already adjuste...

Addressed in a8834c2. The type-check failure was the value_matches annotation not allowing the URI fallback's optional name; widening it to str | None makes tox -e typing pass again. I also updated the summary text to reflect the current scope more fully.

Copilot · 2026-05-29T13:46:29Z

@copilot also please review my changes as well!

Reviewed the current force-pushed changes and I don’t see a blocking follow-up from my side. I also rechecked the relevant validations locally: python -m pytest -q dandi/tests/test_metadata.py passed, and python -m tox -e typing passed. Recent completed Linters and Type-check runs on this branch are successful as well.

…ormat-species-names-consiste

CodyCBakerPhD · 2026-05-29T15:15:09Z


-# common_names, prefix, uri, name
+# common_names, prefix, uri, name ({current name} - {GenBank common name})
 species_map = [


Do you think, as this list grows and becomes more complicated, it might be better as a formal model, or a data class, or at the very least a namedtuple? Instead of just loosely structured a list of tuples

good idea, filed an issue , feel welcome to put your claude to it after we are done with this PR

Sure, sure; out of credits for this month so maybe when back from break

CodyCBakerPhD · 2026-05-29T15:18:55Z

+                    value_matches.append((uri, name))
+            # only if no matches -- try to match by common names within common names
+            if not value_matches:
+                for common_names, prefix, uri, name in species_map:


Towards consistency (+/- future class-based representation) the line above marked such fields as private in the scope, (not must sense to me) so might want to adjust that to match; https://github.com/dandi/dandi-cli/pull/1866/changes#diff-f1fffc52a57ec0f6b12d707f48d19c51f4dd81a4606d3535935d38e10e710bbdL470

Interesting though, https://github.com/dandi/dandi-cli/pull/1866/changes#diff-f1fffc52a57ec0f6b12d707f48d19c51f4dd81a4606d3535935d38e10e710bbdR498 didn't

CodyCBakerPhD · 2026-05-29T15:22:39Z

+                    if any(key == lower_value for key in common_names):
+                        value_matches.append((uri, name))


Plus if this were a class unto itself you could define such equivalency logic as a method within it to make a little more sense from the outside looking in, such as .match(...), possible arguments exact or loose

CodyCBakerPhD · 2026-05-29T15:23:12Z

+                f"Got multiple ({len(value_matches)}) species matched for "
+                f"{value_orig}: {value_matches}.  Should not happen. "
+                "Either you need to be more specific or our code needs "
+                "fixing - contact help@dandiarchive.org."


I do like including such info in error since it gives the user something Actionable~(A) at least

CodyCBakerPhD · 2026-05-29T15:24:10Z

Minor comments, nothing blocking

yarikoptic and others added 2 commits May 28, 2026 17:42

Initial plan

5a9d473

Copilot AI assigned Copilot and yarikoptic May 28, 2026

Copilot AI mentioned this pull request May 28, 2026

enh: add Macaca radiata (bonnet macaque) to species_map #1865

Open

Copilot started work on behalf of yarikoptic May 28, 2026 22:50 View session

fix: normalize species_map name formatting

e98375c

Copilot finished work on behalf of yarikoptic May 28, 2026 23:00

Copilot AI requested a review from yarikoptic May 28, 2026 23:00

yarikoptic reviewed May 29, 2026

View reviewed changes

Comment thread dandi/metadata/util.py Outdated

Copilot started work on behalf of yarikoptic May 29, 2026 03:31 View session

Copilot AI added 2 commits May 29, 2026 03:39

Fix species_map exact part matching

1177640

Guard species common-name matching

2eadb00

Copilot finished work on behalf of yarikoptic May 29, 2026 03:41

Copilot AI requested a review from yarikoptic May 29, 2026 03:41

yarikoptic reviewed May 29, 2026

View reviewed changes

Comment thread dandi/metadata/util.py Outdated

Copilot started work on behalf of yarikoptic May 29, 2026 12:12 View session

yarikoptic force-pushed the enh-macaca-radiata branch from 1a2d7a9 to 813fb8e Compare May 29, 2026 12:14

Copilot finished work on behalf of yarikoptic May 29, 2026 12:22

Copilot AI requested a review from yarikoptic May 29, 2026 12:22

yarikoptic added 2 commits May 29, 2026 09:06

Make matching for common names more stringent - euqality not just con…

db81fa7

…taining Otherwise we would be matching partial names etc. Better fail than to do wrong match!

yarikoptic force-pushed the copilot/wip-address-feedback-format-species-names-consiste branch from 4f2e7f4 to db81fa7 Compare May 29, 2026 13:13

yarikoptic added the patch Increment the patch version when merged label May 29, 2026

yarikoptic changed the title ~~[WIP] [WIP] Address feedback: format species names consistently in species_map~~ ENH+BF: Format species names consistently in species_map, make matching more stringent for common names, improved testing May 29, 2026

Copilot started work on behalf of yarikoptic May 29, 2026 13:16 View session

Fix species typing annotation

a8834c2

Copilot finished work on behalf of yarikoptic May 29, 2026 13:25

Copilot started work on behalf of yarikoptic May 29, 2026 13:25 View session

Copilot finished work on behalf of yarikoptic May 29, 2026 13:46

yarikoptic approved these changes May 29, 2026

View reviewed changes

yarikoptic marked this pull request as ready for review May 29, 2026 14:25

yarikoptic requested review from CodyCBakerPhD and bendichter May 29, 2026 14:25

Merge branch 'enh-macaca-radiata' into copilot/wip-address-feedback-f…

e85ef07

…ormat-species-names-consiste

CodyCBakerPhD reviewed May 29, 2026

View reviewed changes

CodyCBakerPhD approved these changes May 29, 2026

View reviewed changes

yarikoptic mentioned this pull request May 29, 2026

Make dataclass for species_map records #1867

Open

		if any(key == lower_value for key in common_names):
		value_matches.append((uri, name))

Conversation

Copilot AI commented May 28, 2026

Uh oh!

Uh oh!

Uh oh!

yarikoptic commented May 29, 2026

Uh oh!

yarikoptic commented May 29, 2026

Uh oh!

codecov Bot commented May 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

Copilot AI commented May 29, 2026

Uh oh!

Copilot AI commented May 29, 2026

Uh oh!

CodyCBakerPhD May 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

yarikoptic May 29, 2026

Choose a reason for hiding this comment

Uh oh!

CodyCBakerPhD May 29, 2026

Choose a reason for hiding this comment

Uh oh!

CodyCBakerPhD May 29, 2026

Choose a reason for hiding this comment

Uh oh!

CodyCBakerPhD May 29, 2026

Choose a reason for hiding this comment

Uh oh!

CodyCBakerPhD May 29, 2026

Choose a reason for hiding this comment

Uh oh!

CodyCBakerPhD commented May 29, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

codecov Bot commented May 29, 2026 •

edited

Loading

CodyCBakerPhD May 29, 2026 •

edited

Loading