biopipen 0.21.0__py3-none-any.whl → 0.34.26__py3-none-any.whl

biopipen/scripts/vcf/BcftoolsSort.py

@@ -0,0 +1,113 @@
+from typing import Literal
+from pathlib import Path, PosixPath  # noqa: F401
+
+from biopipen.utils.misc import run_command, logger
+from biopipen.scripts.vcf.bcftools_utils import run_bcftools
+
+infile: str = {{in.infile | quote}}  # pyright: ignore # noqa: E999
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
+envs: dict = {{envs | dict | repr}}  # pyright: ignore
+
+outdir = Path(outfile).parent
+bcftools = envs.pop("bcftools")
+tabix = envs.pop("tabix")
+ncores = envs.pop("ncores")
+gz = envs.pop("gz")
+index = envs.pop("index")
+chrsize = envs.pop("chrsize")
+notfound = envs.pop("notfound")
+
+if chrsize:
+    class Contig:
+        def __init__(self, name: str, length: str):
+            self.name = name
+            self.length = length
+
+        def __str__(self) -> str:
+            return f"##contig=<ID={self.name},length={self.length}>"
+
+    def parse_header(header_file: Path) -> tuple[list[str], dict[str, Contig]]:
+        hlines = []
+        ctgs = {}
+        with open(header_file) as fh:
+            for line in fh:
+                if line.startswith("##contig"):
+                    ctg = line.strip().split("##contig=<ID=")[1].split(",length=")
+                    ctgs[ctg[0]] = Contig(ctg[0], ctg[1].replace(">", ""))
+                else:
+                    hlines.append(line.strip())
+        return hlines, ctgs
+
+    def match_contigs(
+        ctgs: dict[str, Contig],
+        chroms: list[str],
+        notfound: Literal["error", "remove", "start", "end"],
+    ) -> list[str]:
+        if (
+            ctgs
+            and chroms
+            and all(chrom.startswith("chr") for chrom in chroms)
+            and not any(chrom.startswith("chr") for chrom in ctgs)
+        ):
+            logger.warning(
+                "Removing 'chr' prefix from chromosomes in envs.chrsize file, "
+                "because the input VCF file does not have 'chr' prefix."
+            )
+            chroms = [chrom[3:] for chrom in chroms]
+
+        new_ctgs = []
+        for chrom in chroms:
+            if chrom in ctgs:
+                new_ctgs.append(str(ctgs[chrom]))
+                del ctgs[chrom]
+
+        if ctgs:
+            if notfound == "error":
+                raise ValueError(
+                    "Chromosomes not found in envs.chrsize file: "
+                    f"{', '.join(ctgs.keys())}"
+                )
+            elif notfound == "start":
+                new_ctgs = [str(ctg) for ctg in ctgs.values()] + new_ctgs
+            elif notfound == "end":
+                new_ctgs = new_ctgs + [str(ctg) for ctg in ctgs.values()]
+
+        return new_ctgs
+
+    chroms = []
+    with Path(chrsize).expanduser().open() as fh:
+        for line in fh:
+            chrom = line.strip().split()[0]
+            chroms.append(chrom)
+
+    header_file = outdir / "header.txt"
+    run_command(f'{bcftools} view -h {infile} > {header_file}', fg=True)
+    header_lines, contigs = parse_header(header_file)
+    new_contigs = match_contigs(contigs, chroms, notfound=notfound)
+    header_lines = [header_lines[0], *new_contigs, *header_lines[1:]]
+    reheader_file = outdir / "reheader.txt"
+    with open(reheader_file, "w") as fh:
+        fh.writelines([f"{line}\n" for line in header_lines])
+
+    reheader_vcf = outdir / f"{Path(infile).stem}_reheader.vcf"
+    run_command([
+        bcftools, "reheader",
+        "--header", reheader_file,
+        "-o", reheader_vcf,
+        infile
+    ], fg=True)
+
+    infile = str(reheader_vcf)
+
+envs[""] = [bcftools, "sort"]
+envs["_"] = infile
+envs["o"] = outfile
+
+if index and not gz:
+    logger.warning("Forcing envs.gz to True because envs.index is True.")
+    gz = True
+
+if "O" not in envs and "output-type" not in envs and "output_type" not in envs:
+    envs["O"] = "z" if gz else "v"
+
+run_bcftools(envs, bcftools=bcftools, index=index, tabix=tabix)

biopipen/scripts/vcf/BcftoolsView.py

@@ -0,0 +1,73 @@
+from contextlib import suppress
+# In case there are paths passed to envs
+from pathlib import PosixPath  # noqa: F401
+
+from biopipen.utils.misc import logger
+from biopipen.utils.reference import tabix_index
+from biopipen.scripts.vcf.bcftools_utils import run_bcftools
+
+infile: str = {{in.infile | quote}}  # pyright: ignore # noqa: #999
+regions_file: str = {{in.regions_file | quote}}  # pyright: ignore
+samples_file: str = {{in.samples_file | quote}}  # pyright: ignore
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
+envs: dict = {{envs | dict | repr}}  # pyright: ignore
+
+bcftools = envs.pop("bcftools")
+tabix = envs.pop("tabix")
+ncores = envs.pop("ncores")
+gz = envs.pop("gz")
+index = envs.pop("index")
+
+if regions_file:
+    if "R" in envs or "regions_file" in envs or "regions-file" in envs:
+        logger.warning(
+            r"Ignoring envs\[regions_file/regions-file/R] "
+            "because in.regionsfile is provided."
+        )
+        with suppress(KeyError):
+            del envs["regions_file"]
+        with suppress(KeyError):
+            del envs["regions-file"]
+        with suppress(KeyError):
+            del envs["R"]
+elif "R" in envs or "regions_file" in envs or "regions-file" in envs:
+    regions_file = (
+        envs.pop("regions_file", None)
+        or envs.pop("regions-file", None)
+        or envs.pop("R", None)
+    )
+
+if samples_file:
+    if "S" in envs or "samples_file" in envs or "samples-file" in envs:
+        logger.warning(
+            "Ignoring envs[samples_file/samples-file/S] "
+            "because in.samples_file is provided."
+        )
+        with suppress(KeyError):
+            del envs["samples_file"]
+        with suppress(KeyError):
+            del envs["samples-file"]
+        with suppress(KeyError):
+            del envs["S"]
+elif "S" in envs or "samples_file" in envs or "samples-file" in envs:
+    samples_file = (
+        envs.pop("samples_file", None)
+        or envs.pop("samples-file", None)
+        or envs.pop("S", None)
+    )
+
+if index and not gz:
+    logger.warning("Forcing envs.gz to True because envs.index is True.")
+    gz = True
+
+if "O" not in envs and "output-type" not in envs and "output_type" not in envs:
+    envs["O"] = "z" if gz else "v"
+
+envs[""] = [bcftools, "view"]
+envs["_"] = tabix_index(infile, "vcf", tabix=tabix)
+envs["o"] = outfile
+envs["threads"] = ncores
+envs["regions_file"] = regions_file
+envs["samples_file"] = samples_file
+
+run_bcftools(envs, bcftools=bcftools, index=index, tabix=tabix)

biopipen/scripts/vcf/TruvariBench.sh

@@ -1,13 +1,15 @@
+# shellcheck disable=SC1083
 compvcf={{in.compvcf | quote}}
 basevcf={{in.basevcf | quote}}
 outdir={{out.outdir | quote}}
 truvari={{envs.truvari | quote}}
 ref={{envs.ref | quote}}
 refdist={{envs.refdist | quote}}
-pctsim={{envs.pctsim | quote}}
+pctseq={{envs.pctseq | quote}}
 pctsize={{envs.pctsize | quote}}
 pctovl={{envs.pctovl | quote}}
 sizemax={{envs.sizemax | default: 50000 | quote}}
+# shellcheck disable=SC1054
 {% if envs.typeignore %}
 typeignore="--typeignore"
 {% else %}
@@ -15,20 +17,25 @@ typeignore=""
 {% endif %}
 {% if envs.multimatch %}
 multimatch="--multimatch"
+# shellcheck disable=SC1009
 {% else %}
 multimatch=""
+# shellcheck disable=SC1073
 {% endif %}
 
 rm -rf $outdir
-$truvari bench \
-    -c "$compvcf" \
-    -b "$basevcf" \
-    -f "$ref" \
+cmd="$truvari bench \
+    -c '$compvcf' \
+    -b '$basevcf' \
+    -f '$ref' \
     --refdist $refdist \
-    --pctsim $pctsim \
+    --pctseq $pctseq \
     --pctsize $pctsize \
     --pctovl $pctovl \
     --sizemax $sizemax \
     $typeignore \
     $multimatch \
-    -o $outdir
+    -o $outdir"
+
+echo "$cmd"
+eval "$cmd"

biopipen/scripts/vcf/TruvariBenchSummary.R

@@ -1,11 +1,7 @@
-source("{{biopipen_dir}}/utils/misc.R")
-source("{{biopipen_dir}}/utils/plot.R")
-
-library(ggprism)
 library(rjson)
+library(rlang)
 library(dplyr)
-
-theme_set(theme_prism(axis_text_angle = 90))
+library(plotthis)
 
 indirs = {{in.indirs | r}}
 outdir = {{out.outdir | r}}
@@ -17,7 +13,7 @@ read_summary = function() {
 
     summaries = NULL
     for (indir in indirs) {
-        summary = fromJSON(file=file.path(indir, "summary.txt"))
+        summary = fromJSON(file=file.path(indir, "summary.json"))
         summary$gt_matrix = NULL
         summary$Sample = sub(".truvari_bench", "", basename(indir), fixed=T)
         summaries = bind_rows(summaries, summary)
@@ -39,14 +35,21 @@ get_devpars = function() {
 
 plot_summary = function(col) {
     outfile = file.path(outdir, paste0(col, ".png"))
-    plotGG(
+    p <- plotthis::BarPlot(
         summaries,
-        "col",
-        list(mapping = aes_string(x = "Sample", y = bQuote(col), fill = "Sample")),
-
-        devpars = get_devpars(),
-        outfile = outfile
+        x = "Sample",
+        y = col,
+        x_text_angle = 90
+    )
+    devpars <- get_devpars()
+    png(
+        filename = outfile,
+        width = devpars$width,
+        height = devpars$height,
+        res = devpars$res
     )
+    print(p)
+    dev.off()
 }
 
 main = function() {

biopipen/scripts/vcf/TruvariConsistency.R

@@ -1,4 +1,4 @@
-source("{{biopipen_dir}}/utils/plot.R")
+{{ biopipen_dir | joinpaths: "utils", "plot.R" | source_r }}
 # to compile the expressions
 library(ComplexHeatmap)
 

biopipen/scripts/vcf/Vcf2Bed.py

@@ -1,7 +1,7 @@
 from cyvcf2 import VCF, Variant
 
-infile = {{in.infile | quote}}  # pyright: ignore
-outfile = {{out.outfile | quote}}  # pyright: ignore
+infile: str = {{in.infile | quote}}  # pyright: ignore  # noqa: E999
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
 # vcf, default 1
 inbase = {{envs.inbase | int}}  # pyright: ignore
 # bed, default 0

biopipen/scripts/vcf/VcfAnno.py

@@ -2,22 +2,22 @@ from os import path
 
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
-infile = {{in.infile | quote}}  # pyright: ignore
-outfile = {{out.outfile | quote}}  # pyright: ignore
-joboutdir = {{job.outdir | quote}}  # pyright: ignore
+infile: str = {{in.infile | quote}}  # pyright: ignore  # noqa
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
+joboutdir: str = {{job.outdir | quote}}  # pyright: ignore
 vcfanno = {{envs.vcfanno | quote}}  # pyright: ignore
-ncores = {{envs.ncores | repr}}  # pyright: ignore
-args = {{envs.args | repr}}  # pyright: ignore
+ncores: int = {{envs.ncores | repr}}  # pyright: ignore
+args: dict = {{envs.args | dict}}  # pyright: ignore
 
-{% set conf = envs.conffile or in.conffile %}
-{% if conf | isinstance: dict %}
+{% set conf = envs.conffile or in.conffile %}  # pyright: ignore  # noqa
+{% if conf | isinstance: dict %}  # pyright: ignore  # noqa
 conffile = path.join(joboutdir, "config.toml")
-conf = {{ conf | toml | quote }}
+conf: str = {{ conf | toml | quote }}  # pyright: ignore  # noqa
 with open(conffile, "w") as f:
     f.write(conf)
-{% else %}
-conffile = {{conf | quote}}
-{% endif %}
+{% else %}  # pyright: ignore  # noqa
+conffile = {{conf | quote}}  # pyright: ignore  # noqa
+{% endif %}  # pyright: ignore  # noqa
 
 args["p"] = ncores
 args["_"] = [conffile, infile]

biopipen/scripts/vcf/VcfDownSample.sh

@@ -1,25 +1,37 @@
+# shellcheck disable=SC2148
+# shellcheck disable=SC2036
+# shellcheck disable=SC2030
+# shellcheck disable=SC1083
+# shellcheck disable=SC2288
 infile={{in.infile | quote}}
 outfile={{out.outfile | quote}}
 n={{envs.n}}
 
+# shellcheck disable=SC2031
 if [[ $infile == *.gz ]]; then
-    outfile=$(echo $outfile | sed -r "s/\.gz$//")
-    nheader=$(zcat $infile | head -n 9999 | grep "^#" | wc -l | cut -d' ' -f1)
+    outfile=$(echo "$outfile" | sed -r "s/\.gz$//")
+    # shellcheck disable=SC2126
+    nheader=$(zcat "$infile" | head -n 9999 | grep "^#" | wc -l | cut -d' ' -f1)
     if [[ ! $n -gt 1 ]]; then
-        nrows=$(zcat $infile | wc -l | cut -d' ' -f1)
+        nrows=$(zcat "$infile" | wc -l | cut -d' ' -f1)
+        # shellcheck disable=SC2004
         nvars=$(($nrows - $nheader))
         n=$(echo "$nvars * $n" | bc)
     fi
-    zcat $infile | head -n $nheader > $outfile
-    zcat $infile | tail -n +$(($nheader + 1)) | shuf -n $n | LC_ALL=C sort -k1,1V -k2,2n >> $outfile
-    bgzip $outfile
+    zcat "$infile" | head -n "$nheader" > "$outfile"
+    # shellcheck disable=SC2004
+    zcat "$infile" | tail -n +$(($nheader + 1)) | shuf -n "$n" | LC_ALL=C sort -k1,1V -k2,2n >> "$outfile"
+    bgzip "$outfile"
 else
-    nheader=$(head -n 9999 $infile | grep "^#" | wc -l | cut -d' ' -f1)
+    # shellcheck disable=SC2126
+    nheader=$(head -n 9999 "$infile" | grep "^#" | wc -l | cut -d' ' -f1)
     if [[ ! $n -gt 1 ]]; then
-        nrows=$(wc -l $infile | cut -d' ' -f1)
+        nrows=$(wc -l "$infile" | cut -d' ' -f1)
+        # shellcheck disable=SC2004
         nvars=$(($nrows - $nheader))
         n=$(echo "$nvars * $n" | bc)
     fi
-    head -n $nheader $infile > $outfile
-    tail -n +$(($nheader + 1)) $infile | shuf -n $n | LC_ALL=C sort -k1,1V -k2,2n >> $outfile
+    head -n "$nheader" "$infile" > "$outfile"
+    # shellcheck disable=SC2004
+    tail -n +$(($nheader + 1)) "$infile" | shuf -n "$n" | LC_ALL=C sort -k1,1V -k2,2n >> "$outfile"
 fi

biopipen/scripts/vcf/VcfFilter.py

@@ -1,13 +1,13 @@
 from cyvcf2 import VCF, Writer, Variant
 
-infile = {{in.invcf | repr}}  # pyright: ignore
-outfile = {{out.outfile | repr}}  # pyright: ignore
+infile: str = {{in.invcf | quote}}  # pyright: ignore  # noqa: E999
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
 
-{{envs.helper}}
+{{envs.helper}}  # pyright: ignore  # noqa: E999
 
 keep = {{envs.keep | repr}}  # pyright: ignore
-filters = {{envs.filters | repr}}  # pyright: ignore
-filter_descs = {{envs.filter_descs | repr}}  # pyright: ignore
+filters: dict = {{envs.filters | repr}}  # pyright: ignore
+filter_descs: dict = {{envs.filter_descs | repr}}  # pyright: ignore
 
 # builtin filters
 BUILTIN_FILTERS = {}

biopipen/scripts/vcf/VcfFix.py

@@ -7,17 +7,17 @@ from biopipen.scripts.vcf.VcfFix_utils import (  # noqa: F401
     HeaderContig,
     HeaderGeneral,
     Fields,
-    Info,
-    Format,
-    Alt,
-    Filter,
-    Sample,
-    Samples,
+    # Info,
+    # Format,
+    # Alt,
+    # Filter,
+    # Sample,
+    # Samples,
     Variant,
 )
 from biopipen.scripts.vcf.VcfFix_utils import fix_vcffile
 
-infile = {{in.infile | quote}}  # pyright: ignore
+infile = {{in.infile | quote}}  # pyright: ignore  # noqa: E999
 instem = {{in.infile | stem | quote}}  # pyright: ignore
 outfile = {{out.outfile | quote}}  # pyright: ignore
 

biopipen/scripts/vcf/VcfFix_utils.py

@@ -1,6 +1,15 @@
 import re
 import gzip
-from biopipen.utils.vcf import *  # noqa: F401, F403
+from biopipen.utils.vcf import (
+    HeaderInfo,
+    HeaderFormat,
+    HeaderFilter,
+    HeaderContig,
+    HeaderGeneral,
+    Fields,
+    Variant,
+    HeaderItem,
+)
 
 
 def line_to_obj(line: str):
@@ -41,7 +50,7 @@ def handle_obj(obj, fixes: dict):
 
         regex = fix.get("regex")
         if regex:
-            if not re.search(regex, obj.raw):
+            if not re.search(regex, obj.raw):  # type: ignore
                 continue
 
             return fix["fix"](obj.raw if kind is None else obj)
@@ -63,11 +72,11 @@ def fix_vcffile(vcffile, outfile, fixes):
         else:
             modify_fixes.append(fix)
 
-    inopen = gzip.open if vcffile.endswith(".gz") else open
+    inopen = gzip.open if str(vcffile).endswith(".gz") else open
     with inopen(vcffile, "rt") as fin, open(outfile, "w") as fout:
         for line in fin:
             obj = line_to_obj(line)
-            out = handle_obj(obj, modify_fixes)
+            out = handle_obj(obj, modify_fixes)  # type: ignore
             if obj.kind == "fields":
                 for fix in header_append_fixes:
                     fout.write(str(fix["fix"](None)).rstrip("\n") + "\n")

biopipen/scripts/vcf/VcfIndex.py

@@ -4,10 +4,10 @@ from os import path
 from biopipen.utils.reference import tabix_index
 from biopipen.utils.misc import run_command
 
-infile = {{in.infile | repr}}  # pyright: ignore
-outfile = Path({{out.outfile | repr}})  # pyright: ignore
+infile: str = {{in.infile | quote}}  # pyright: ignore  # noqa
+outfile = Path({{out.outfile | quote}})  # pyright: ignore
 outidx = {{out.outidx | repr}}  # pyright: ignore
-tabix = {{envs.tabix | repr}}  # pyright: ignore
+tabix: str = {{envs.tabix | repr}}  # pyright: ignore
 ncores = {{envs.ncores | repr}}  # pyright: ignore
 
 outfile_with_index = tabix_index(infile, "vcf", outfile.parent, tabix)

biopipen/scripts/vcf/VcfIntersect.py

@@ -1,8 +1,8 @@
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
-infile1 = {{in.infile1 | repr}}  # pyright: ignore
-infile2 = {{in.infile2 | repr}}  # pyright: ignore
-outfile = {{out.outfile | repr}}  # pyright: ignore
+infile1: str = {{in.infile1 | quote}}  # pyright: ignore  # noqa
+infile2 = {{in.infile2 | quote}}  # pyright: ignore
+outfile = {{out.outfile | quote}}  # pyright: ignore
 bcftools = {{envs.bcftools | repr}}  # pyright: ignore
 gz = {{envs.gz | repr}}  # pyright: ignore
 index = {{envs.index | repr}}  # pyright: ignore

biopipen/scripts/vcf/VcfLiftOver.sh

@@ -1,3 +1,5 @@
+# shellcheck disable=SC2148
+# shellcheck disable=SC1083
 invcf={{ in.invcf | quote }}
 outvcf={{ out.outvcf | quote }}
 rejfile={{ job.outdir | joinpaths: "rejected.vcf" | quote }}
@@ -6,12 +8,15 @@ chain={{ envs.chain | quote }}
 reffa={{ envs.reffa | quote }}
 args={{ envs.args | dict_to_cli_args: join=True }}
 
+# shellcheck disable=SC2154
 refdict="${reffa%.fa}.dict"
 if [[ ! -e "$refdict" ]]; then
     echo "Sequence dictionary does not exist: $refdict" 1>&2
     exit 1
 fi
 
+# shellcheck disable=SC2154
+# shellcheck disable=SC2086
 $gatk LiftoverVcf \
     $args \
     --INPUT "$invcf" \

biopipen/scripts/vcf/VcfSplitSamples.py

@@ -3,12 +3,12 @@ import shlex
 import concurrent.futures
 from subprocess import Popen, check_output
 
-infile = {{in.infile | repr}}  # pyright: ignore
-outdir = {{out.outdir | repr}}  # pyright: ignore
-bcftools = {{envs.bcftools | repr}}  # pyright: ignore
+infile: str = {{in.infile | quote}}  # pyright: ignore  # noqa
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
+bcftools: str = {{envs.bcftools | repr}}  # pyright: ignore
 gz = {{envs.gz | repr}}  # pyright: ignore
 index = {{envs.index | repr}}  # pyright: ignore
-ncores = {{envs.ncores | int}}  # pyright: ignore
+ncores: int = {{envs.ncores | int}}  # pyright: ignore
 private = {{envs.private | repr}}  # pyright: ignore
 
 if index:

biopipen/scripts/vcf/bcftools_utils.py

@@ -0,0 +1,52 @@
+"""Utilities for bcftools"""
+
+from biopipen.utils.misc import run_command, dict_to_cli_args
+from biopipen.utils.reference import tabix_index
+
+
+def bcftools_version(bcftools: str) -> tuple[int, ...]:
+    """Get the version of bcftools
+
+    Args:
+        bcftools (str): Path to bcftools
+
+    Returns:
+        tuple[int, ...]: The version of bcftools
+    """
+    bversion = (
+        run_command([bcftools, "version"], stdout="return")
+        .splitlines()[0]  # bcftools 1.20  # type: ignore
+        .replace("bcftools", "")
+        .strip()  # 1.20
+        .split(".")
+    )
+    return tuple(map(int, bversion))
+
+
+def run_bcftools(
+    args: dict,
+    bcftools: str,  # TODO: get from the first argument of args
+    index: bool,
+    tabix: str
+) -> None:
+    """Run bcftools with the given arguments
+
+    Args:
+        args: Arguments to pass to bcftools
+        bcftools (str): Path to bcftools
+        index (bool): Whether to index the output
+        tabix (str): Path to tabix
+    """
+    if not index:
+        run_command(dict_to_cli_args(args, dashify=True), fg=True)
+    else:
+        bversion = bcftools_version(bcftools)
+        if bversion >= (1, 20):
+            # requires bcftools 1.20+
+            # '--write-index tbi' not working
+            # it has to be '--write-index=tbi'
+            args["write_index=tbi"] = True
+            run_command(dict_to_cli_args(args, dashify=True), fg=True)
+        else:
+            run_command(dict_to_cli_args(args, dashify=True), fg=True)
+            tabix_index(args["o"], "vcf", tmpdir=False, tabix=tabix)

biopipen/scripts/web/Download.py

@@ -2,13 +2,13 @@ from pathlib import Path
 
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
-url = {{in.url | repr}}  # pyright: ignore
-outfile = Path({{out.outfile | repr}})  # pyright: ignore
+url = {{in.url | quote}}  # pyright: ignore # noqa
+outfile = Path({{out.outfile | quote}})  # pyright: ignore
 tool = {{envs.tool | repr}}  # pyright: ignore
 wget = {{envs.wget | repr}}  # pyright: ignore
 aria2c = {{envs.aria2c | repr}}  # pyright: ignore
 ncores = {{envs.ncores | repr}}  # pyright: ignore
-args = {{envs.args | dict}}  # pyright: ignore
+args: dict = {{envs.args | dict}}  # pyright: ignore
 
 if tool == "wget":
     args["_"] = url
@@ -28,4 +28,8 @@ elif tool == "aria2c":
 
 else: # use python
     import urllib
-    urllib.urlretrieve(url, outfile)
+
+    try:
+        urllib.urlretrieve(url, outfile)  # type: ignore
+    except AttributeError:
+        urllib.request.urlretrieve(url, outfile)  # type: ignore

biopipen/scripts/web/DownloadList.py

@@ -2,13 +2,13 @@ from pathlib import Path
 
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
-urlfile = {{in.urlfile | repr}}  # pyright: ignore
-outdir = Path({{out.outdir | repr}})  # pyright: ignore
+urlfile: str = {{in.urlfile | quote}}  # pyright: ignore  # noqa
+outdir = Path({{out.outdir | quote}})  # pyright: ignore
 tool = {{envs.tool | repr}}  # pyright: ignore
 wget = {{envs.wget | repr}}  # pyright: ignore
 aria2c = {{envs.aria2c | repr}}  # pyright: ignore
 ncores = {{envs.ncores | repr}}  # pyright: ignore
-args = {{envs.args | repr}}  # pyright: ignore
+args: dict = {{envs.args | repr}}  # pyright: ignore
 
 if tool == "wget":
     args["i"] = urlfile
@@ -26,10 +26,10 @@ elif tool == "aria2c":
     run_command(dict_to_cli_args(args, dashify=True), fg=True)
 
 else: # use python
-    import urllib
+    from urllib.request import urlretrieve
     from urllib.parse import urlparse
     with open(urlfile, "r") as furl:
         for i, url in enumerate(furl.readlines()):
             parsed = urlparse(url)
             path = Path(parsed.path)
-            urllib.urlretrieve(url, f"{path.stem}-{i}{path.suffix}")
+            urlretrieve(url, f"{path.stem}-{i}{path.suffix}")