feat: added wrapper for loglog (#1154)

<!-- Ensure that the PR title follows conventional commit style (<type>:
<description>)-->
<!-- Possible types are here:
https://github.com/commitizen/conventional-commit-types/blob/master/index.json
-->

### Description

<!-- Add a description of your PR here-->
Adding wrapper for `loglog` from the package `BBtools`.

### QC
<!-- Make sure that you can tick the boxes below. -->

* [x] I confirm that:

For all wrappers added by this PR, 

* there is a test case which covers any introduced changes,
* `input:` and `output:` file paths in the resulting rule can be changed
arbitrarily,
* either the wrapper can only use a single core, or the example rule
contains a `threads: x` statement with `x` being a reasonable default,
* rule names in the test case are in
[snake_case](https://en.wikipedia.org/wiki/Snake_case) and somehow tell
what the rule is about or match the tools purpose or name (e.g.,
`map_reads` for a step that maps reads),
* all `environment.yaml` specifications follow [the respective best
practices](https://stackoverflow.com/a/64594513/2352071),
* wherever possible, command line arguments are inferred and set
automatically (e.g. based on file extensions in `input:` or `output:`),
* all fields of the example rules in the `Snakefile`s and their entries
are explained via comments (`input:`/`output:`/`params:` etc.),
* `stderr` and/or `stdout` are logged correctly (`log:`), depending on
the wrapped tool,
* temporary files are either written to a unique hidden folder in the
working directory, or (better) stored where the Python function
`tempfile.gettempdir()` points to (see
[here](https://docs.python.org/3/library/tempfile.html#tempfile.gettempdir);
this also means that using any Python `tempfile` default behavior
works),
* the `meta.yaml` contains a link to the documentation of the respective
tool or command,
* `Snakefile`s pass the linting (`snakemake --lint`),
* `Snakefile`s are formatted with
[snakefmt](https://github.com/snakemake/snakefmt),
* Python wrapper scripts are formatted with
[black](https://black.readthedocs.io).
* Conda environments use a minimal amount of channels, in recommended
ordering. E.g. for bioconda, use (conda-forge, bioconda, nodefaults, as
conda-forge should have highest priority and defaults channels are
usually not needed because most packages are in conda-forge nowadays).

bio/bbtools/loglog/environment.yaml

@@ -0,0 +1,8 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - bbmap =39.01
+  - python =3.11.0
+  - snakemake-wrapper-utils =0.5.2

bio/bbtools/loglog/meta.yaml

@@ -0,0 +1,12 @@
+name: LogLog
+url: https://jgi.doe.gov/data-and-tools/software-tools/bbtools/bb-tools-user-guide/bbnorm-guide/
+description: |
+  Run LogLog to estimate memory requirements.
+authors:
+  - Filipe G. Vieira
+input:
+  - sample: list of R1 and (if PE) R2 fastq file(s)
+params:
+  - extra: additional program arguments
+notes: |
+  * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. `-XX:ParallelGCThreads=10` (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically).

bio/bbtools/loglog/test/Snakefile

@@ -0,0 +1,26 @@
+rule loglog_se:
+    input:
+        sample=["reads/se/{sample}.fastq"],
+    log:
+        "logs/se/{sample}.log",
+    params:
+        extra="buckets=2048 seed=1234",
+    threads: 2
+    resources:
+        mem_mb=1024,
+    wrapper:
+        "master/bio/bbtools/loglog"
+
+
+rule loglog_pe:
+    input:
+        sample=["reads/pe/{sample}.1.fastq", "reads/pe/{sample}.2.fastq"],
+    log:
+        "logs/pe/{sample}.log",
+    params:
+        extra="buckets=2048 seed=1234",
+    threads: 2
+    resources:
+        mem_mb=1024,
+    wrapper:
+        "master/bio/bbtools/loglog"

bio/bbtools/loglog/test/reads/pe/a.1.fastq

@@ -0,0 +1,4 @@
+@1
+ACGGCAT
++
+!!!!!!!

bio/bbtools/loglog/test/reads/pe/a.2.fastq

@@ -0,0 +1,4 @@
+@1
+ACGGCAT
++
+!!!!!!!

bio/bbtools/loglog/test/reads/se/a.fastq

@@ -0,0 +1,4 @@
+@1
+ACGGCAT
++
+!!!!!!!

bio/bbtools/loglog/wrapper.py

@@ -0,0 +1,26 @@
+__author__ = "Filipe G. Vieira"
+__copyright__ = "Copyright 2023, Filipe G. Vieira"
+__license__ = "MIT"
+
+
+from snakemake.shell import shell
+from snakemake_wrapper_utils.java import get_java_opts
+
+
+java_opts = get_java_opts(snakemake)
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+
+n = len(snakemake.input.sample)
+assert (
+    n == 1 or n == 2
+), "input->sample must have 1 (single-end) or 2 (paired-end) elements."
+
+if n == 1:
+    reads = "in={}".format(snakemake.input.sample)
+else:
+    reads = "in={} in2={}".format(*snakemake.input.sample)
+
+
+shell("loglog.sh {java_opts} {reads} {extra} {log}")

bio/bbtools/tadpole/test/Snakefile

@@ -20,7 +20,7 @@ rule tadpole_correct_pe:
     input:
         sample=["reads/pe/{sample}.1.fastq", "reads/pe/{sample}.2.fastq"],
     output:
-        out=["out/correct_pe/{sample}.1.fastq", "out/correct/pe/{sample}.2.fastq"],
+        out=["out/correct_pe/{sample}.1.fastq", "out/correct_pe/{sample}.2.fastq"],
         discarded="out/correct_pe/{sample}.discarded.fastq",
     log:
         "logs/correct_pe/{sample}.log",
@@ -56,7 +56,7 @@ rule tadpole_extend_pe:
     input:
         sample=["reads/pe/{sample}.1.fastq", "reads/pe/{sample}.2.fastq"],
     output:
-        out=["out/extend_pe/{sample}.1.fastq", "out/extend/pe/{sample}.2.fastq"],
+        out=["out/extend_pe/{sample}.1.fastq", "out/extend_pe/{sample}.2.fastq"],
         discarded="out/extend_pe/{sample}.discarded.fastq",
     log:
         "logs/extend_pe/{sample}.log",

bio/bbtools/tadpole/wrapper.py

@@ -28,9 +28,9 @@
     out = "out={} out2={}".format(*snakemake.output.out)
 
 
-extra = snakemake.output.get("extra", "")
-if extra:
-    reads += f" extra={extra}"
+in_extra = snakemake.input.get("extra", "")
+if in_extra:
+    reads += f" extra={in_extra}"
 
 
 discarded = snakemake.output.get("discarded", "")

test.py

@@ -140,6 +140,21 @@ def run(wrapper, cmd, check_log=None):
 
 
 
+@skip_if_not_modified
+def test_loglog():
+    run(
+        "bio/bbtools/loglog",
+        [
+            "snakemake",
+            "--cores",
+            "2",
+            "--use-conda",
+            "-F",
+            "logs/se/a.log",
+            "logs/pe/a.log",
+        ],
+    )
+
 @skip_if_not_modified
 def test_tadpole():
     run(
@@ -151,9 +166,15 @@ def test_tadpole():
             "--use-conda",
             "-F",
             "out/correct_se/a.fastq.gz",
+            "out/correct_se/a.discarded.fastq.gz",
             "out/correct_pe/a.1.fastq",
+            "out/correct_pe/a.2.fastq",
+            "out/correct_pe/a.discarded.fastq",
             "out/extend_se/a.fastq.gz",
+            "out/extend_se/a.discarded.fastq.gz",
             "out/extend_pe/a.1.fastq",
+            "out/extend_pe/a.2.fastq",
+            "out/extend_pe/a.discarded.fastq",
         ],
     )