Convert to new augur curate commands; update ingest/vendored subrepo [#26]

ingest/defaults/config.yaml

@@ -61,6 +61,9 @@ curate:
     - "%Y-%m-%d"
     - "%Y-%m-%dT%H:%M:%SZ"
 
+  # Field containing location information
+  genbank_location_field: "location"
+
   titlecase:
     # Abbreviations not cast to titlecase, keeps uppercase
     abbreviations: ["USA"]

ingest/rules/curate.smk

@@ -77,6 +77,7 @@ rule curate:
         field_map=format_field_map(config["curate"]["field_map"]),
         date_fields=config["curate"]["date_fields"],
         expected_date_formats=config["curate"]["expected_date_formats"],
+        genbank_location_field=config["curate"]["genbank_location_field"],
         articles=config["curate"]["titlecase"]["articles"],
         abbreviations=config["curate"]["titlecase"]["abbreviations"],
         titlecase_fields=config["curate"]["titlecase"]["fields"],
@@ -91,32 +92,32 @@ rule curate:
         """
         (
           cat {input.sequences_ndjson:q} \
-            | ./vendored/transform-field-names \
+            | augur curate rename \
                 --field-map {params.field_map} \
             | augur curate normalize-strings \
             | augur curate format-dates \
                 --date-fields {params.date_fields:q} \
                 --expected-date-formats {params.expected_date_formats:q} \
-            | ./vendored/transform-genbank-location \
+            | augur curate parse-genbank-location \
+                --location-field {params.genbank_location_field:q} \
             | augur curate titlecase \
                 --titlecase-fields {params.titlecase_fields:q} \
                 --articles {params.articles:q} \
                 --abbreviations {params.abbreviations:q} \
-            | ./vendored/transform-authors \
+            | augur curate abbreviate-authors \
                 --authors-field {params.authors_field:q} \
                 --default-value {params.authors_default_value:q} \
                 --abbr-authors-field {params.abbr_authors_field:q} \
-            | ./vendored/apply-geolocation-rules \
+            | augur curate apply-geolocation-rules \
                 --geolocation-rules {input.all_geolocation_rules:q} \
-            | ./vendored/merge-user-metadata \
+            | augur curate apply-record-annotations \
                 --annotations {input.annotations:q} \
                 --id-field {params.annotations_id:q} \
-            | augur curate passthru \
                 --output-metadata {output.metadata:q} \
                 --output-fasta {output.sequences:q} \
                 --output-id-field {params.id_field:q} \
                 --output-seq-field {params.sequence_field}
-        ) 2>> {log:q}
+        ) 2> {log:q}
         """
 
 

ingest/vendored/.github/workflows/pre-commit.yaml

@@ -0,0 +1,14 @@
+name: pre-commit
+
+on:
+  - push
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - uses: pre-commit/[email protected]

ingest/vendored/.gitrepo

@@ -6,7 +6,7 @@
 [subrepo]
 	remote = https://github.com/nextstrain/ingest
 	branch = main
-	commit = c0b4c6bb5e6ccbba86374d2c09b42077768aac23
+	commit = 258ab8ce898a88089bc88caee336f8d683a0e79a
 	parent = d2728676b6fe0d74abf87e0cebf7ac9ec9a2917b
 	method = merge
-	cmdver = 0.4.6
+	cmdver = 0.4.7

ingest/vendored/.pre-commit-config.yaml

@@ -0,0 +1,40 @@
+default_language_version:
+  python: python3
+repos:
+  - repo: https://github.com/pre-commit/sync-pre-commit-deps
+    rev: v0.0.1
+    hooks:
+      - id: sync-pre-commit-deps
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.10.0.1
+    hooks:
+      - id: shellcheck
+  - repo: https://github.com/rhysd/actionlint
+    rev: v1.6.27
+    hooks:
+      - id: actionlint
+        entry: env SHELLCHECK_OPTS='--exclude=SC2027' actionlint
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: trailing-whitespace
+      - id: check-ast
+      - id: check-case-conflict
+      - id: check-docstring-first
+      - id: check-json
+      - id: check-executables-have-shebangs
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-symlinks
+      - id: check-toml
+      - id: check-yaml
+      - id: destroyed-symlinks
+      - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: fix-byte-order-marker
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.4.6
+    hooks:
+      # Run the linter.
+      - id: ruff

ingest/vendored/README.md

@@ -117,15 +117,6 @@ Potential Nextstrain CLI scripts
 - [download-from-s3](download-from-s3) - Download file from AWS S3 bucket with decompression based on file extension in S3 URL.
   Skips download if the local file already exists and has a hash identical to the S3 object's metadata `sha256sum`.
 
-Potential augur curate scripts
-
-- [apply-geolocation-rules](apply-geolocation-rules) - Applies user curated geolocation rules to NDJSON records
-- [merge-user-metadata](merge-user-metadata) - Merges user annotations with NDJSON records
-- [transform-authors](transform-authors) - Abbreviates full author lists to '<first author> et al.'
-- [transform-field-names](transform-field-names) - Rename fields of NDJSON records
-- [transform-genbank-location](transform-genbank-location) - Parses `location` field with the expected pattern `"<country_value>[:<region>][, <locality>]"` based on [GenBank's country field](https://www.ncbi.nlm.nih.gov/genbank/collab/country/)
-- [transform-strain-names](transform-strain-names) - Ordered search for strain names across several fields.
-
 ## Software requirements
 
 Some scripts may require Bash ≥4. If you are running these scripts on macOS, the builtin Bash (`/bin/bash`) does not meet this requirement. You can install [Homebrew's Bash](https://formulae.brew.sh/formula/bash) which is more up to date.
@@ -134,7 +125,24 @@ Some scripts may require Bash ≥4. If you are running these scripts on macOS, t
 
 Most scripts are untested within this repo, relying on "testing in production". That is the only practical testing option for some scripts such as the ones interacting with S3 and Slack.
 
-For more locally testable scripts, Cram-style functional tests live in `tests` and are run as part of CI. To run these locally,
+## Working on this repo
+
+This repo is configured to use [pre-commit](https://pre-commit.com),
+to help automatically catch common coding errors and syntax issues
+with changes before they are committed to the repo.
+
+If you will be writing new code or otherwise working within this repo,
+please do the following to get started:
+
+1. [install `pre-commit`](https://pre-commit.com/#install) by running
+   either `python -m pip install pre-commit` or `brew install
+   pre-commit`, depending on your preferred package management
+   solution
+2. install the local git hooks by running `pre-commit install` from
+   the root of the repo
+3. when problems are detected, correct them in your local working tree
+   before committing them.
 
-1. Download Cram: `pip install cram`
-2. Run the tests: `cram tests/`
+Note that these pre-commit checks are also run in a GitHub Action when
+changes are pushed to GitHub, so correcting issues locally will
+prevent extra cycles of correction.