perf: Use samtools collate in fastq separate wrapper (#2960)

<!-- 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
-->

<!-- Add a description of your PR here-->

### 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),
* the `environment.yaml` pinning has been updated by running
`snakedeploy pin-conda-envs environment.yaml` on a linux machine,
* 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).

Author: fxwiegand

bio/samtools/fastq/separate/test/Snakefile

@@ -7,7 +7,7 @@ rule samtools_fastq_separate:
     log:
         "{sample}.separate.log",
     params:
-        sort="-m 4G",
+        collate="",
         fastq="-n",
     # Remember, this is the number of samtools' additional threads. At least 2 threads have to be requested on cluster sumbission. This value - 2 will be sent to samtools sort -@ argument.
     threads: 3

bio/samtools/fastq/separate/wrapper.py

@@ -10,37 +10,29 @@
 from snakemake.shell import shell
 from snakemake_wrapper_utils.snakemake import get_mem
 
-params_sort = snakemake.params.get("sort", "")
+params_collate = snakemake.params.get("collate", "")
 params_fastq = snakemake.params.get("fastq", "")
 log = snakemake.log_fmt_shell(stdout=True, stderr=True)
 
 # Samtools takes additional threads through its option -@
-# One thread is used bu Samtools sort
+# One thread is used by Samtools collate
 # One thread is used by Samtools fastq
 # So snakemake.threads has to take them into account
 # before allowing additional threads through samtools sort -@
 threads = 0 if snakemake.threads <= 2 else snakemake.threads - 2
 
-mem = get_mem(snakemake, "MiB")
-mem = "-m {0:.0f}M".format(mem / threads) if mem and threads else ""
-
-with tempfile.TemporaryDirectory() as tmpdir:
-    tmp_prefix = Path(tmpdir) / "samtools_fastq.sort"
-
-    shell(
-        "(samtools sort -n"
-        " --threads {threads}"
-        " {mem}"
-        " -T {tmp_prefix}"
-        " {params_sort}"
-        " {snakemake.input[0]} | "
-        "samtools fastq"
-        " {params_fastq}"
-        " -1 {snakemake.output[0]}"
-        " -2 {snakemake.output[1]}"
-        " -0 /dev/null"
-        " -s /dev/null"
-        " -F 0x900"
-        " - "
-        ") {log}"
-    )
+shell(
+    "(samtools collate -u -O"
+    " --threads {threads}"
+    " {params_collate}"
+    " {snakemake.input[0]} | "
+    "samtools fastq"
+    " {params_fastq}"
+    " -1 {snakemake.output[0]}"
+    " -2 {snakemake.output[1]}"
+    " -0 /dev/null"
+    " -s /dev/null"
+    " -F 0x900"
+    " - "
+    ") {log}"
+)