shell:
    "seqtk seq -r  {input} > {output}"

wrapper:
    "0.35.1/bio/fastqc"

wrapper:
    "0.35.1/bio/multiqc"

from Bio import SeqIO, Seq
from pathlib import Path

for abi in snakemake.input:
    abi_name=Path(abi).name
    out_fastq= "{0}/{1}".format("fastq", abi_name.replace("ab1", "fastq"))
    SeqIO.convert(abi, "abi", out_fastq, "fastq")

def Read_blast(blast_tab):
    import pandas as pd

    blast_table = pd.read_csv(blast_tab, sep="\t", comment="#", names=['QAcc', 'SubAcc',
    'Perc_ident', 'Align_len', 'Num_mis','Num_gaps','Q_start', 'Q_stop', 'Sub_start', 'Sub_end', 'Evalue','Bitscore', 'Sub_len','Q_cov', 'Q_covhsp', 'Q_covus','S_taxid', 'S_sci_names'])

    return blast_table

table_name = snakemake.output[0]
df = Read_blast(snakemake.input[0])
print("table {} already read".format(table_name))
df.sort_values(by=['Bitscore','Q_cov','Perc_ident','Align_len'], axis=0,
               ascending=False).head(10).to_csv(path_or_buf=table_name, sep='\t',index=False,float_format = "%.3f")

import re
from collections import defaultdict
import pandas as pd
import sys
import matplotlib
matplotlib.use("agg")
import matplotlib.pyplot as plt
from pathlib import Path
import seaborn as sns

# matplotlib.use("agg")
sys.stdout = open(snakemake.log[0], 'w')
print("pandas version:", pd.__version__)
merger_files =snakemake.input #glob("*[1-9]*.merger")
pat = re.compile(r'([0-9]+\.[0-9]+)%')
parse_dic = defaultdict(list)

for f in merger_files:
    print("merger_files", repr(f))
    with open(f, mode='r', encoding='utf8') as fh:
        for line in fh:
            match = re.search(pat, line)
            if match:
                idx_name = Path(f).name
                parse_dic[idx_name].append(match.group(1)) 
print(parse_dic)
df = pd.DataFrame.from_dict(parse_dic, orient='index',columns=["Identity %","Similarity %","number of Gaps"]).astype(float)
print(df)
# fig, ax = plt.subplots(figsize=(8,6))
# plot = df.plot(rot=60, alpha=0.5, ax=ax, title="Phred quality")
# ax.set_xlabel("Merged reads")
# #fig = plot.get_figure()
# locs, labels = plt.xticks()
# plt.setp(labels, rotation=50)

fig, ax = plt.subplots(figsize=(8,6))
sns.lineplot(data=df, sort=False, alpha=0.6)
locs, labels = plt.xticks()
plt.setp(labels, rotation=50)
plt.tight_layout()
fig.savefig(snakemake.output[0])

from ete3 import NCBITaxa

#The first time this will download the taxonomic NCBI database and save a parsed version
#of it in  `~/.etetoolkit/taxa.sqlite`.May take some minutes
ncbi = NCBITaxa()
print("ncbi.dbfile", ncbi.dbfile)

with open(snakemake.input[0], 'r', encoding='utf8') as fh:
    genus_list = fh.read().strip().split('\n')

genus_to_taxid = ncbi.get_name_translator(genus_list)
tax_id_vals = genus_to_taxid.values()

tree = ncbi.get_topology([genus_id for subls in tax_id_vals for genus_id in subls], intermediate_nodes=True)

# `get_ascii()` has a bug, prints the taxons before to genus without any separation between them, so a way to avoid that is using extra attribues, `dist` seems to be less invasive. Also, numbers from 'dist' are replaced
with open(snakemake.output[0], mode='w', encoding='utf8') as fh:
    print(tree.get_ascii(attributes=["dist", "sci_name"]).replace('1.0,','-'), file=fh)

__author__ = "Julian de Ruiter"
__copyright__ = "Copyright 2017, Julian de Ruiter"
__email__ = "julianderuiter@gmail.com"
__license__ = "MIT"


from os import path
from tempfile import TemporaryDirectory

from snakemake.shell import shell

log = snakemake.log_fmt_shell(stdout=False, stderr=True)

def basename_without_ext(file_path):
    """Returns basename of file path, without the file extension."""

    base = path.basename(file_path)

    split_ind = 2 if base.endswith(".gz") else 1
    base = ".".join(base.split(".")[:-split_ind])

    return base


# Run fastqc, since there can be race conditions if multiple jobs 
# use the same fastqc dir, we create a temp dir.
with TemporaryDirectory() as tempdir:
    shell("fastqc {snakemake.params} --quiet "
          "--outdir {tempdir} {snakemake.input[0]}"
          " {log}")

    # Move outputs into proper position.
    output_base = basename_without_ext(snakemake.input[0])
    html_path = path.join(tempdir, output_base + "_fastqc.html")
    zip_path = path.join(tempdir, output_base + "_fastqc.zip")

    if snakemake.output.html != html_path:
        shell("mv {html_path} {snakemake.output.html}")

    if snakemake.output.zip != zip_path:
        shell("mv {zip_path} {snakemake.output.zip}")