Document more features of cwltool

.github/workflows/gh-pages.yaml

@@ -17,7 +17,7 @@ jobs:
 
       - name: Install apt packages
         run: |
-          sudo apt-get install -y graphviz
+          sudo apt-get install -y graphviz tree
 
       - name: Set up Python
         uses: actions/setup-python@v4

.gitignore

@@ -10,6 +10,7 @@ _site
 .Rhistory
 .RData
 _build/
+build/
 *.egg-info/
 
 src/_includes/cwl/**/output.txt

.readthedocs.yaml

@@ -9,6 +9,7 @@ build:
     nodejs: "16"
   apt_packages:
     - graphviz
+    - tree
 
 sphinx:
   configuration: src/conf.py

src/_includes/cwl/troubleshooting/troubleshooting-wf1-stepb-fixed.cwl

@@ -0,0 +1,48 @@
+cwlVersion: v1.2
+class: Workflow
+
+inputs:
+  text:
+    type: string
+    default: 'Hello World'
+outputs:
+  reversed_message:
+    type: string
+    outputSource: step_b/reversed_message
+
+steps:
+  step_a:
+    run:
+      class: CommandLineTool
+      stdout: stdout.txt
+      inputs:
+        text: string
+      outputs:
+        step_a_stdout:
+          type: File
+          outputBinding:
+            glob: 'stdout.txt'
+      baseCommand: echo
+      arguments: [ '-n', '$(inputs.text)' ]
+    in:
+      text: text
+    out: [step_a_stdout]
+  step_b:
+    run:
+      class: CommandLineTool
+      stdout: stdout.txt
+      inputs:
+        step_a_stdout: File
+      outputs:
+        reversed_message:
+          type: string
+          outputBinding:
+            glob: stdout.txt
+            loadContents: true
+            outputEval: $(self[0].contents)
+      baseCommand: rev
+      arguments: [ $(inputs.step_a_stdout) ]
+    in:
+      step_a_stdout:
+        source: step_a/step_a_stdout
+    out: [reversed_message]

src/_includes/cwl/troubleshooting/troubleshooting-wf1.cwl

@@ -0,0 +1,47 @@
+cwlVersion: v1.2
+class: Workflow
+
+inputs:
+  text:
+    type: string
+    default: 'Hello World'
+outputs:
+  reversed_message:
+    type: string
+    outputSource: step_b/reversed_message
+
+steps:
+  step_a:
+    run:
+      class: CommandLineTool
+      stdout: stdout.txt
+      inputs:
+        text: string
+      outputs:
+        step_a_stdout:
+          type: File
+          outputBinding:
+            glob: 'stdout.txt'
+      arguments: ['echo', '-n', '$(inputs.text)']
+    in:
+      text: text
+    out: [step_a_stdout]
+  step_b:
+    run:
+      class: CommandLineTool
+      stdout: stdout.txt
+      inputs:
+        step_a_stdout: File
+      outputs:
+        reversed_message:
+          type: string
+          outputBinding:
+            glob: stdout.txt
+            loadContents: true
+            outputEval: $(self[0].contents)
+      baseCommand: revv
+      arguments: [ $(inputs.step_a_stdout) ]
+    in:
+      step_a_stdout:
+        source: step_a/step_a_stdout
+    out: [reversed_message]

src/topics/index.md

@@ -21,4 +21,5 @@ best-practices.md
 file-formats.md
 metadata-and-authorship.md
 specifying-software-requirements.md
+troubleshooting.md
 ```

src/topics/inputs.md

@@ -29,6 +29,18 @@ Create a file called `inp-job.yml`:
 :name: inp-job.yml
 ```
 
+````{note}
+You can use `cwltool` to create a template input object. That saves you from having
+to type all the input parameters in a input object file:
+
+```{runcmd} cwltool --make-template inp.cwl
+:working-directory: src/_includes/cwl/inputs
+```
+
+You can redirect the output to a file, i.e. `cwltool --make-template inp.cwl > inp-job.yml`,
+and then modify the default values with your desired input values.
+````
+
 Notice that "example_file", as a `File` type, must be provided as an
 object with the fields `class: File` and `path`.
 

src/topics/troubleshooting.md

@@ -0,0 +1,63 @@
+# Troubleshooting
+
+In this section you will find ways to troubleshoot when you have problems executing CWL.
+We focus on `cwltool` here but some of these techniques may apply to other CWL Runners.
+
+## Run `cwltool` with `cachedir`
+
+You can use the `--cachedir` option when running a workflow to tell `cwltool` to
+cache intermediate files (files that are not input nor output files, but created
+while your workflow is running). By default, these files are created in a
+temporary directory but writing them to a separate directory makes accessing
+them easier.
+
+In the following example `troubleshooting-wf1.cwl` we have two steps, `step_a` and `step_b`.
+The workflow is equivalent to `echo "Hello World" | rev`, which would print the message
+"Hello World" reversed, i.e. "dlroW olleH". However, the second step, `step_b`, **has a typo**,
+where instead of executing the `rev` command it tries to execute `revv`, which
+fails.
+
+```{literalinclude} /_includes/cwl/troubleshooting/troubleshooting-wf1.cwl
+:language: cwl
+:name: "`troubleshooting-wf1.cwl`"
+:caption: "`troubleshooting-wf1.cwl`"
+:emphasize-lines: 42
+```
+
+Let's execute this workflow with `/tmp/cachedir/` as the `--cachedir` value (`cwltool` will
+create the directory for you if it does not exist already):
+
+```{runcmd} cwltool --cachedir /tmp/cachedir/ troubleshooting-wf1.cwl
+:working-directory: src/_includes/cwl/troubleshooting
+:emphasize-lines: 12-14, 19-21
+```
+
+The workflow is in the `permanentFail` status due to `step_b` failing to execute the
+non-existent `revv` command. The `step_a` was executed successfully and its output
+has been cached in your `cachedir` location. You can inspect the intermediate files
+created:
+
+```{runcmd} tree /tmp/cachedir
+:emphasize-lines: 4
+```
+
+Each workflow step has received a unique ID (the long value that looks like a hash).
+The `${HASH}.status` files display the status of each step executed by the workflow.
+And the `step_a` output file `stdout.txt` is visible in the output of the command above.
+
+Now fix the typo so `step_b` executes `rev` (i.e. replace `revv` by `rev` in the
+`step_b`). After fixing the typo, when you execute `cwltool` with the same arguments
+as the previous time, note that now `cwltool` output contains information about
+pre-cached outputs for `step_a`, and about a new cache entry for the output of `step_b`.
+Also note that the status of `step_b` is now of success.
+
+```{runcmd} cwltool --cachedir /tmp/cachedir/ troubleshooting-wf1-stepb-fixed.cwl
+:working-directory: src/_includes/cwl/troubleshooting
+:emphasize-lines: 12, 16-18
+```
+
+In this example the workflow step `step_a` was not re-evaluated as it had been cached, and
+there was no change in its execution or output. Furthermore, `cwltool` was able to recognize
+when it had to re-evaluate `step_b` after we fixed the executable name. This technique is
+useful for troubleshooting your CWL documents and also as a way to prevent `cwltool` to
+re-evaluate steps unnecessarily.