Merge 0e6be84 into 7094e9e

.gitignore

@@ -5,7 +5,7 @@ dist/
 demux.egg-info/
 
 DEVELOP/
-.idea
+.idea/
 # Distribution / packaging
 *.egg-info/
 *.egg

demux/cli/base.py

@@ -1,16 +1,15 @@
 """Demultiplexing base demux command"""
 
-import logging
-
 import click
 import coloredlogs
+import logging
 import yaml
 
+from .basemask import basemask
 from demux import __version__
+from .indexreport import indexreport
 from .samplesheet import sheet
 
-from .basemask import basemask
-
 LOG = logging.getLogger(__name__)
 LEVELS = ["DEBUG", "INFO", "WARNING", "ERROR"]
 
@@ -36,3 +35,4 @@ def demux(context, log_level, config):
 
 demux.add_command(sheet)
 demux.add_command(basemask)
+demux.add_command(indexreport)

demux/cli/indexreport.py

@@ -0,0 +1,70 @@
+import click
+import logging
+
+from pathlib import Path
+
+from demux.constants import REFERENCE_REPORT_HEADER, REPORT_TABLES_INDEX
+from demux.utils.indexreport import IndexReport
+
+
+LOG = logging.getLogger(__name__)
+
+
+@click.group()
+def indexreport():
+    """Index report commands"""
+
+
+@indexreport.command()
+@click.option(
+    "--cluster-counts",
+    type=int,
+    default=1000000,
+    help=(
+        f"Cluster count cut-off, any samples (besides indexcheck ones) with lower cluster counts are"
+        f" included in the summary"
+    ),
+)
+@click.option(
+    "--dry-run", help="Dry of the function, will not write any report", is_flag=True
+)
+@click.option(
+    "--index-report-path",
+    type=str,
+    required=True,
+    help="Path to bcl2fastq indexcheck report (laneBarcode.html)",
+)
+@click.option(
+    "--out-dir",
+    type=str,
+    required=True,
+    help="Path of outdirectory for summary report",
+)
+@click.option(
+    "--run-parameters-path",
+    type=str,
+    required=True,
+    help="Path to RunParameters.xml file for the flowcell",
+)
+def summary(
+    cluster_counts: int,
+    dry_run: bool,
+    index_report_path: str,
+    out_dir: str,
+    run_parameters_path: str,
+):
+    """Create a summary of the indexcheck report, extracting information on samples with low number of clusters
+    and the topmost common unknown indexes"""
+    index_report = IndexReport(
+        cluster_counts=cluster_counts,
+        index_report_path=Path(index_report_path),
+        out_dir=Path(out_dir),
+        report_tables_index=REPORT_TABLES_INDEX,
+        run_parameters_path=Path(run_parameters_path),
+    )
+    LOG.info(f"Creating summary of laneBarcode.html for FC: {index_report.flowcell_id}")
+    index_report.validate(reference_report_header=REFERENCE_REPORT_HEADER)
+    if not dry_run:
+        index_report.write_summary(report_tables_index=REPORT_TABLES_INDEX)
+    else:
+        LOG.info("This is a dry-run, will not write a summary report")

demux/constants/__init__.py

@@ -0,0 +1,5 @@
+from .indexreport import (
+    REFERENCE_REPORT_HEADER,
+    REPORT_TABLES_INDEX,
+    FLOWCELL_VERSION_LANE_COUNT,
+)

demux/constants/indexreport.py

@@ -0,0 +1,23 @@
+"""
+    Constants for indexcheck report
+"""
+
+
+REFERENCE_REPORT_HEADER = [
+    "Lane",
+    "Project",
+    "Sample",
+    "Barcode sequence",
+    "PF Clusters",
+    "% of the lane",
+    "% Perfect barcode",
+    "% One mismatch barcode",
+    "Yield (Mbases)",
+    "% PF Clusters",
+    "% >= Q30 bases",
+    "Mean Quality Score",
+]
+
+REPORT_TABLES_INDEX = {"cluster_count_table": 1, "top_unknown_barcode_table": 2}
+
+FLOWCELL_VERSION_LANE_COUNT = {"S1": 2, "S4": 4}

demux/exc.py

@@ -0,0 +1,18 @@
+"""
+    Demultiplexing exceptions
+"""
+
+
+class DemuxError(Exception):
+    """
+    Base exception for the package
+    """
+
+    def __init__(self):
+        super(DemuxError, self).__init__()
+
+
+class IndexReportError(DemuxError):
+    """
+    Exception for errors in index report module
+    """

demux/utils/html.py

@@ -0,0 +1,39 @@
+import bs4
+import re
+
+
+from pathlib import Path
+from typing import Tuple
+
+
+def parse_html_header(html_column_header: bs4.element.Tag) -> str:
+    """Purify html header into a string without html syntax"""
+
+    column_header = re.sub("<br/>", " ", str(html_column_header))
+    header = re.sub("<.*?>", "", column_header)
+
+    return header
+
+
+def parse_html_project_cluster_counts(
+    header_index: dict, project_row: bs4.element.Tag
+) -> Tuple[str, int]:
+    """Purify a html project cluster count row from html syntax"""
+
+    project = re.sub(
+        "<.*?>", "", str(project_row.find_all("td")[header_index["Project"]])
+    )
+    cluster_count = re.sub(
+        "<.*?>", "", str(project_row.find_all("td")[header_index["PF Clusters"]])
+    )
+    cluster_count = int(cluster_count.replace(",", ""))
+
+    return project, cluster_count
+
+
+def get_html_content(index_report_path: Path) -> bs4.BeautifulSoup:
+    """Get the content of the report"""
+
+    with index_report_path.open() as f:
+        html_content = bs4.BeautifulSoup(f, "html.parser")
+        return html_content