chore(deps): bump snakefmt from 1.1.0 to 2.0.1 in /ingest (#6550)

Bumps snakefmt from 1.1.0 to 2.0.1.


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=snakefmt&package-manager=conda&previous-version=1.1.0&new-version=2.0.1)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

🚀 Preview: Add `preview` label to enable

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: anna-parker <50943381+anna-parker@users.noreply.github.com>

Author: dependabot[bot]

ingest/Snakefile

@@ -143,9 +143,9 @@ rule fetch_inflate_ncbi_dataset_package:
                 --filename {params.compressed_package_zip} \
                 {params.api_key} \
                 {params.gateway} \
-            && {params.unzip} \
-                -o {params.compressed_package_zip} \
-                -d results
+                && {params.unzip} \
+                    -o {params.compressed_package_zip} \
+                    -d results
         fi
         """
 
@@ -163,7 +163,7 @@ rule format_ncbi_dataset_report:
             --config-file {input.config} \
             --input {input.dataset_report} \
             --output {output.ncbi_dataset_tsv}
-        echo "Processed metadata file lines: $(wc -l < {output.ncbi_dataset_tsv})"
+        echo "Processed metadata file lines: $(wc -l <{output.ncbi_dataset_tsv})"
         echo "Hash of output: $(md5sum {output.ncbi_dataset_tsv})"
         echo "Hash of sorted output: $(md5sum <(sort {output.ncbi_dataset_tsv}))"
         """
@@ -178,7 +178,7 @@ rule format_ncbi_dataset_sequences:
         """
         seqkit seq -w0 -i \
             {input.dataset_sequences} \
-            > {output.ncbi_dataset_sequences}
+            >{output.ncbi_dataset_sequences}
         echo "Stats of NCBI dataset sequences: $(seqkit stats {output.ncbi_dataset_sequences})"
         echo "seqkit hash of NCBI dataset sequences: $(seqkit sum -a -s {output.ncbi_dataset_sequences})"
         echo "Plain hash of NCBI dataset sequences: $(md5sum {output.ncbi_dataset_sequences})"
@@ -198,9 +198,9 @@ if CHECK_ENA_DEPOSITION:
         shell:
             """
             python {input.script} \
-            --output-insdc-accessions {output.exclude_insdc_accessions} \
-            --log-level {params.log_level} \
-            --config-file {input.config} \
+                --output-insdc-accessions {output.exclude_insdc_accessions} \
+                --log-level {params.log_level} \
+                --config-file {input.config}
             """
 
     rule filter_out_loculus_depositions:
@@ -216,11 +216,11 @@ if CHECK_ENA_DEPOSITION:
         shell:
             """
             python {input.script} \
-            --input-metadata-tsv {input.ncbi_dataset_tsv} \
-            --exclude-insdc-accessions {input.exclude_insdc_accessions} \
-            --log-level {params.log_level} \
-            --config-file {input.config} \
-            --output-metadata-tsv {output.metadata_tsv} \
+                --input-metadata-tsv {input.ncbi_dataset_tsv} \
+                --exclude-insdc-accessions {input.exclude_insdc_accessions} \
+                --log-level {params.log_level} \
+                --config-file {input.config} \
+                --output-metadata-tsv {output.metadata_tsv}
             """
 
 
@@ -260,7 +260,7 @@ if SEGMENTED and segment_detection_method == SegmentDetectionMethod.ALIGN:
                 {input.sequences} \
                 --output-tsv {output.results} \
                 --server {params.dataset_server} \
-                --dataset-name {params.dataset_name} \
+                --dataset-name {params.dataset_name}
             """
 
     rule process_alignments:
@@ -281,10 +281,10 @@ if SEGMENTED and segment_detection_method == SegmentDetectionMethod.ALIGN:
             ),
         shell:
             """
-        python {input.script} \
-            {params.segment_paths} \
-            --output {output.merged}
-        """
+            python {input.script} \
+                {params.segment_paths} \
+                --output {output.merged}
+            """
 
 
 if APPLY_MINIMIZER:
@@ -312,8 +312,8 @@ if APPLY_MINIMIZER:
         shell:
             """
             nextclade sort -m {input.minimizer} \
-            -r {output.results}  {input.sequences} \
-            --max-score-gap 0.3 --min-score 0.05 --min-hits 2  --all-matches
+                -r {output.results} {input.sequences} \
+                --max-score-gap 0.3 --min-score 0.05 --min-hits 2 --all-matches
             """
 
     rule parse_sort:
@@ -328,10 +328,10 @@ if APPLY_MINIMIZER:
         shell:
             """
             python {input.script} \
-            --config-file {input.config} \
-            --sort-results {input.sorted} \
-            --output {output.merged} \
-            --log-level {params.log_level} \
+                --config-file {input.config} \
+                --sort-results {input.sorted} \
+                --output {output.merged} \
+                --log-level {params.log_level}
             """
 
 
@@ -369,7 +369,7 @@ rule prepare_metadata:
             --sequence-hashes-file {input.sequence_hashes} \
             {params.segments} \
             --output {output.metadata} \
-            --log-level {params.log_level} \
+            --log-level {params.log_level}
         """
 
 
@@ -418,22 +418,22 @@ if CALCULATE_GROUPS_OVERRIDE_JSON:
         shell:
             """
             if [[ "{params.use_mirror}" == "True" ]]; then
-                curl {params.mirror_url} -o {params.compressed_package_tzst} && \
-                mkdir -p {params.package} && \
-                tar xf {params.compressed_package_tzst} -C {params.package}
+                curl {params.mirror_url} -o {params.compressed_package_tzst} \
+                    && mkdir -p {params.package} \
+                    && tar xf {params.compressed_package_tzst} -C {params.package}
             else
                 datasets download genome taxon {params.taxon_id} \
                     --assembly-source {wildcards.source} \
                     --no-progressbar --dehydrated \
                     --filename {params.compressed_package_zip} \
                     {params.api_key} \
                     {params.gateway} \
-                && {params.unzip} \
-                    -o {params.compressed_package_zip} \
-                    -d {params.package} \
-                && datasets rehydrate \
-                    --directory {params.package} \
-                    --no-progressbar
+                    && {params.unzip} \
+                        -o {params.compressed_package_zip} \
+                        -d {params.package} \
+                    && datasets rehydrate \
+                        --directory {params.package} \
+                        --no-progressbar
             fi
             touch {output.marker}
             """
@@ -453,11 +453,11 @@ if CALCULATE_GROUPS_OVERRIDE_JSON:
         shell:
             """
             python {input.script} \
-            --dataset-dir {params.genbank_dir} \
-            --dataset-dir {params.refseq_dir} \
-            --output-file {output.groups_json} \
-            --ignore-list {input.ignore_list} \
-            --config-file {input.config_file}
+                --dataset-dir {params.genbank_dir} \
+                --dataset-dir {params.refseq_dir} \
+                --output-file {output.groups_json} \
+                --ignore-list {input.ignore_list} \
+                --config-file {input.config_file}
             """
 
 
@@ -474,10 +474,10 @@ if GROUPING_OVERRIDE_URL and CALCULATE_GROUPS_OVERRIDE_JSON:
         shell:
             """
             python {input.script} \
-            --groups {input.calculated} \
-            --groups {input.downloaded} \
-            --config-file {input.config} \
-            --output-file {output.groups_json}
+                --groups {input.calculated} \
+                --groups {input.downloaded} \
+                --config-file {input.config} \
+                --output-file {output.groups_json}
             """
 
 
@@ -560,8 +560,8 @@ rule heuristic_group_segments:
             --output-seq {output.sequences} \
             --log-level {params.log_level}
         if [ "{params.GROUPS_OVERRIDE_JSON}" = "true" ]; then
-            cat {input.metadata_grouped} >> {output.metadata}
-            cat {input.sequences_grouped} >> {output.sequences}
+            cat {input.metadata_grouped} >>{output.metadata}
+            cat {input.sequences_grouped} >>{output.sequences}
         fi
         """
 
@@ -594,12 +594,12 @@ if FILTER:
         shell:
             """
             python {input.script} \
-            --input-seq {input.sequences} \
-            --output-seq {output.sequences} \
-            --input-metadata {input.metadata} \
-            --output-metadata {output.metadata} \
-            --log-level {params.log_level} \
-            --config-file {input.config} \
+                --input-seq {input.sequences} \
+                --output-seq {output.sequences} \
+                --input-metadata {input.metadata} \
+                --output-metadata {output.metadata} \
+                --log-level {params.log_level} \
+                --config-file {input.config}
             """
 
 
@@ -669,7 +669,7 @@ rule compare_hashes:
             --output-blocked {output.blocked} \
             --sampled-out-file {output.sampled_out} \
             --log-level {params.log_level} \
-            --subsample-fraction {params.subsample_fraction} \
+            --subsample-fraction {params.subsample_fraction}
         """
 
 
@@ -711,7 +711,7 @@ rule prepare_files:
             --metadata-submit-prior-to-revoke-path {output.metadata_revoke} \
             --sequences-submit-path {output.sequences_submit} \
             --sequences-revise-path {output.sequences_revise} \
-            --sequences-submit-prior-to-revoke-path {output.sequences_revoke} \
+            --sequences-submit-prior-to-revoke-path {output.sequences_revoke}
         """
 
 
@@ -723,7 +723,7 @@ rule sort_fasta:
         sorted="results/{basename}_sorted.fasta",
     shell:
         """
-        seqkit sort -N --two-pass {input.sequences} | seqkit seq -w 0 > {output.sorted}
+        seqkit sort -N --two-pass {input.sequences} | seqkit seq -w 0 >{output.sorted}
         """
 
 
@@ -735,11 +735,11 @@ rule sort_metadata:
         sorted="results/{basename}_sorted.tsv",
     shell:
         """
-        columnNumber=$(awk -F'\\t' '{{for(i=1;i<=NF;i++) if($i=="id") print i}}' {input.metadata});
+        columnNumber=$(awk -F'\\t' '{{for(i=1;i<=NF;i++) if($i=="id") print i}}' {input.metadata})
         if [ ${{columnNumber}} ]; then
-        (head -n 1 {input.metadata} && tail -n +2 {input.metadata} | sort -t$'\t' -k${{columnNumber}},${{columnNumber}}) > {output.sorted}
+            (head -n 1 {input.metadata} && tail -n +2 {input.metadata} | sort -t$'\t' -k${{columnNumber}},${{columnNumber}}) >{output.sorted}
         else
-        cat {input.metadata} > {output.sorted}
+            cat {input.metadata} >{output.sorted}
         fi
         """
 

ingest/environment.yml

@@ -21,7 +21,7 @@ dependencies:
   - pyyaml=6.0.3
   - requests=2.33.1
   - seqkit=2.13.0
-  - snakefmt=1.1.0
+  - snakefmt=2.0.1
   - snakemake=9.20.0
   - unzip=6.0
   - pytest=9.0.3