Merge pull request #1 from robsyme/patch-1

Update pipeline-gantt.py

.github/workflows/linting.yml

@@ -65,4 +65,4 @@ jobs:
 
             Thanks again for your contribution!
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-          allow-repeats: false
+          allow-repeats: false

.nf-core.yml

@@ -1 +1 @@
-repository_type: pipeline
+repository_type: pipeline

LICENSE.txt

@@ -35,7 +35,7 @@ Mozilla Public License Version 2.0
     means any form of the work other than Source Code Form.
 
 1.7. "Larger Work"
-    means a work that combines Covered Software with other material, in 
+    means a work that combines Covered Software with other material, in
     a separate file or files, that is not Covered Software.
 
 1.8. "License"
@@ -355,9 +355,9 @@ notice described in Exhibit B of this License must be attached.
 Exhibit A - Source Code Form License Notice
 -------------------------------------------
 
-  This Source Code Form is subject to the terms of the Mozilla Public
-  License, v. 2.0. If a copy of the MPL was not distributed with this
-  file, You can obtain one at http://mozilla.org/MPL/2.0/.
+    This Source Code Form is subject to the terms of the Mozilla Public
+    License, v. 2.0. If a copy of the MPL was not distributed with this
+    file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 If it is not possible or desirable to put the notice in a particular
 file, then You may include the notice in a location (such as a LICENSE
@@ -369,5 +369,5 @@ You may add additional accurate notices of copyright ownership.
 Exhibit B - "Incompatible With Secondary Licenses" Notice
 ---------------------------------------------------------
 
-  This Source Code Form is "Incompatible With Secondary Licenses", as
-  defined by the Mozilla Public License, v. 2.0.
+    This Source Code Form is "Incompatible With Secondary Licenses", as
+    defined by the Mozilla Public License, v. 2.0.

assets/schema_input.json

@@ -14,4 +14,4 @@
             }
         }
     }
-}
+}

assets/test_run_ids.csv

@@ -1,4 +1,4 @@
 4Bi5xBK6E2Nbhj
 4LWT4uaXDaGcDY
 38QXz4OfQDpwOV
-2lXd1j7OwZVfxh
+2lXd1j7OwZVfxh

bin/pipeline-gantt.py

@@ -1,61 +1,90 @@
 #!/usr/bin/env python3
 
 import json
-import tarfile
 from datetime import datetime
 from typing import IO
+from pathlib import Path
 
 import click
 import pandas as pd
 import plotly.express as px
 
 
-def extract_instance(fusion_logs: str, lines: IO) -> str:
-    for i, line in enumerate(lines):
-        try:
-            log = json.loads(line)
-            if 'instance-id' in log:
-                return log['instance-id']
-        except json.JSONDecodeError:
-            print(f"WARN: invalid JSON at '{fusion_logs}' line {i}")
-    return ""
+def extract_instance(fusion_logs: Path) -> str:
+    with fusion_logs.open() as file:
+        for line_number, line in enumerate(file, start=1):
+            try:
+                log = json.loads(line)
+                if "instance-id" in log:
+                    return log["instance-id"]
+            except json.JSONDecodeError:
+                print(f"WARN: invalid JSON at '{fusion_logs}' line {line_number}")
+        return ""
 
 
 @click.command()
-@click.option('--title', default='Pipeline GANTT', help='Plot title.')
-@click.option('--input-file', type=click.Path(), help='The pipeline dump tar.gz input file.')
-@click.option('--output-file', type=click.Path(), help='The HTML output file')
-def build_gantt(title: str, input_file: str, output_file: str):
+@click.option("--title", default="Pipeline GANTT", help="Plot title.")
+@click.option(
+    "--input-dir", type=click.Path(), help="The pipeline dump tar.gz input file."
+)
+@click.option("--output-file", type=click.Path(), help="The HTML output file")
+def build_gantt(title: str, input_dir: str, output_file: str):
     tasks = []
     instance_ids = {}
 
-    tar = tarfile.open(input_file, "r:gz")
-    for member in tar.getmembers():
-        if member.name == "workflow-tasks.json":
-            tasks = json.load(tar.extractfile(member))
-        if member.name.endswith(".fusion.log"):
-            _, task_id, _ = member.name.split('/')
-            instance_id = extract_instance(member.name, tar.extractfile(member))
-            instance_ids[int(task_id)] = instance_id
+    for path in Path(input_dir).glob("workflow-tasks.json"):
+        with path.open() as json_file:
+            tasks = json.load(json_file)
+    for path in Path(input_dir).glob("**/.fusion.log"):
+        task_id = int(path.parent.name)
+        instance_id = extract_instance(path)
+        instance_ids[task_id] = instance_id
 
     for t in tasks:
-        t['instanceId'] = instance_ids.get(t['taskId'], "unknow")
-
-    data = [{k: v for k, v in t.items() if k in ['taskId', 'name', 'start', 'complete', 'memory', 'cpus', 'machineType', 'instanceId']} for t in tasks]
-    df = pd.DataFrame({
-                          'id': f"T{d['taskId']}",
-                          'name': d['name'],
-                          'size': f"{d['cpus']}c_{d['memory'] / 1024 ** 3:.0f}GB",
-                          'start': datetime.strptime(d['start'], '%Y-%m-%dT%H:%M:%SZ'),
-                          'complete': datetime.strptime(d['complete'], '%Y-%m-%dT%H:%M:%SZ'),
-                          'instance': f"{d['instanceId']} ({d['machineType']})"
-                      }
-                      for d in data
-                      )
-
-    fig = px.timeline(df, title=title, x_start="start", x_end="complete", y="id", color="instance", text="name", pattern_shape="size")
+        t["instanceId"] = instance_ids.get(t["taskId"], "unknow")
+
+    data = [
+        {
+            k: v
+            for k, v in t.items()
+            if k
+            in [
+                "taskId",
+                "name",
+                "start",
+                "complete",
+                "memory",
+                "cpus",
+                "machineType",
+                "instanceId",
+            ]
+        }
+        for t in tasks
+    ]
+    df = pd.DataFrame(
+        {
+            "id": f"T{d['taskId']}",
+            "name": d["name"],
+            "size": f"{d['cpus']}c_{d['memory'] / 1024 ** 3:.0f}GB",
+            "start": datetime.strptime(d["start"], "%Y-%m-%dT%H:%M:%SZ"),
+            "complete": datetime.strptime(d["complete"], "%Y-%m-%dT%H:%M:%SZ"),
+            "instance": f"{d['instanceId']} ({d['machineType']})",
+        }
+        for d in data
+    )
+
+    fig = px.timeline(
+        df,
+        title=title,
+        x_start="start",
+        x_end="complete",
+        y="id",
+        color="instance",
+        text="name",
+        pattern_shape="size",
+    )
     fig.write_html(output_file)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     build_gantt()

conf/modules.config

@@ -52,4 +52,4 @@ process {
         ]
     }
 
-}
+}

main.nf

@@ -62,4 +62,4 @@ workflow {
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     THE END
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-*/
+*/

modules/local/pipeline_gantt/main.nf

@@ -17,7 +17,7 @@ process PIPELINE_GANTT {
     """
     pipeline-gantt.py \\
         --title "GANTT Plot for run: $run_id" \\
-        --input-file $run_dump \\
+        --input-dir $run_dump \\
         --output-file ./${prefix}_gantt.html
 
     cat <<-END_VERSIONS > versions.yml
@@ -28,4 +28,4 @@ process PIPELINE_GANTT {
         click: \$(python -c "import click; print(click.__version__)")
     END_VERSIONS
     """
-}
+}

modules/local/seqera_runs_dump/main.nf

@@ -34,7 +34,7 @@ process SEQERA_RUNS_DUMP {
         -xvf \\
         ${prefix}_run_dump.tar.gz \\
         -C ${prefix}_run_dump
-    
+
     cp ${prefix}_run_dump/workflow.json .
 
     cat <<-END_VERSIONS > versions.yml

nextflow_schema.json

@@ -27,7 +27,7 @@
                     "default": "community/showcase",
                     "description": "Workspace on the Seqera Platform to fetch run information.",
                     "fa_icon": "fas fa-folder-open"
-                },                
+                },
                 "outdir": {
                     "type": "string",
                     "format": "directory-path",

tower.yml

@@ -1,3 +1,3 @@
 reports:
   multiqc_report.html:
-    display: "MultiQC HTML report"
+    display: "MultiQC HTML report"