Improve -dump-hashes output adding json format (nextflow-io#4369)

Signed-off-by: Ben Sherman <bentshermann@gmail.com>
Signed-off-by: Paolo Di Tommaso <paolo.ditommaso@gmail.com>
Co-authored-by: Paolo Di Tommaso <paolo.ditommaso@gmail.com>

docs/cache-and-resume.md

@@ -186,6 +186,8 @@ nextflow run rnaseq-nf -resume 4dc656d2-c410-44c8-bc32-7dd0ea87bebf
 
 You can use the {ref}`cli-log` command to view all previous runs as well as the task executions for each run.
 
+(cache-compare-hashes)=
+
 ### Comparing the hashes of two runs
 
 One way to debug a resumed run is to compare the task hashes of each run using the `-dump-hashes` option.
@@ -196,3 +198,28 @@ One way to debug a resumed run is to compare the task hashes of each run using t
 4. Compare the runs with a diff viewer
 
 While some manual effort is required, the final diff can often reveal the exact change that caused a task to be re-executed.
+
+:::{versionadded} 23.10.0
+:::
+
+When using `-dump-hashes json`, the task hashes can be more easily extracted into a diff. Here is an example Bash script to perform two runs and produce a diff:
+
+```bash
+nextflow -log run_1.log run $pipeline -dump-hashes json
+nextflow -log run_2.log run $pipeline -dump-hashes json -resume
+
+get_hashes() {
+    cat $1 \
+    | grep 'cache hash:' \
+    | cut -d ' ' -f 10- \
+    | sort \
+    | awk '{ print; print ""; }'
+}
+
+get_hashes run_1.log > run_1.tasks.log
+get_hashes run_2.log > run_2.tasks.log
+
+diff run_1.tasks.log run_2.tasks.log
+```
+
+You can then view the `diff` output or use a graphical diff viewer to compare `run_1.tasks.log` and `run_2.tasks.log`.

docs/cli.md

@@ -1154,7 +1154,10 @@ The `run` command is used to execute a local pipeline script or remote pipeline
 : Dump channels for debugging purpose.
 
 `-dump-hashes`
-: Dump task hash keys for debugging purpose.
+: Dump task hash keys for debugging purposes.
+: :::{versionadded} 23.10.0
+  You can use `-dump-hashes json` to dump the task hash keys as JSON for easier post-processing. See the {ref}`caching and resuming tips <cache-compare-hashes>` for more details.
+  :::
 
 `-e.<key>=<value>`
 : Add the specified variable to execution environment.

modules/nextflow/src/main/groovy/nextflow/Session.groovy

@@ -247,11 +247,11 @@ class Session implements ISession {
 
     boolean getStatsEnabled() { statsEnabled }
 
-    private boolean dumpHashes
+    private String dumpHashes
 
     private List<String> dumpChannels
 
-    boolean getDumpHashes() { dumpHashes }
+    String getDumpHashes() { dumpHashes }
 
     List<String> getDumpChannels() { dumpChannels }
 

modules/nextflow/src/main/groovy/nextflow/cli/CmdRun.groovy

@@ -223,7 +223,7 @@ class CmdRun extends CmdBase implements HubOptions {
     String profile
 
     @Parameter(names=['-dump-hashes'], description = 'Dump task hash keys for debugging purpose')
-    boolean dumpHashes
+    String dumpHashes
 
     @Parameter(names=['-dump-channels'], description = 'Dump channels for debugging purpose')
     String dumpChannels

modules/nextflow/src/main/groovy/nextflow/cli/Launcher.groovy

@@ -224,6 +224,10 @@ class Launcher {
                 normalized << '%all'
             }
 
+            else if( current == '-dump-hashes' && (i==args.size() || args[i].startsWith('-'))) {
+                normalized << '-'
+            }
+
             else if( current == '-with-cloudcache' && (i==args.size() || args[i].startsWith('-'))) {
                 normalized << '-'
             }

modules/nextflow/src/main/groovy/nextflow/config/ConfigBuilder.groovy

@@ -595,9 +595,10 @@ class ConfigBuilder {
         if( config.isSet('resume') )
             config.resume = normalizeResumeId(config.resume as String)
 
-        // -- sets `dumpKeys` option
-        if( cmdRun.dumpHashes )
-            config.dumpHashes = cmdRun.dumpHashes
+        // -- sets `dumpHashes` option
+        if( cmdRun.dumpHashes ) {
+            config.dumpHashes = cmdRun.dumpHashes != '-' ? cmdRun.dumpHashes : 'default'
+        }
 
         if( cmdRun.dumpChannels )
             config.dumpChannels = cmdRun.dumpChannels.tokenize(',')

modules/nextflow/src/main/groovy/nextflow/processor/TaskProcessor.groovy

@@ -32,6 +32,7 @@ import java.util.regex.Pattern
 
 import ch.artecat.grengine.Grengine
 import com.google.common.hash.HashCode
+import groovy.json.JsonOutput
 import groovy.transform.CompileStatic
 import groovy.transform.Memoized
 import groovy.transform.PackageScope
@@ -2155,7 +2156,9 @@ class TaskProcessor {
         final mode = config.getHashMode()
         final hash = computeHash(keys, mode)
         if( session.dumpHashes ) {
-            traceInputsHashes(task, keys, mode, hash)
+            session.dumpHashes=='json'
+                ? traceInputsHashesJson(task, keys, mode, hash)
+                : traceInputsHashes(task, keys, mode, hash)
         }
         return hash
     }
@@ -2191,6 +2194,16 @@ class TaskProcessor {
         return result
     }
 
+    private void traceInputsHashesJson( TaskRun task, List entries, CacheHelper.HashMode mode, hash ) {
+        final collector = (item) -> [
+            hash: CacheHelper.hasher(item, mode).hash().toString(),
+            type: item?.getClass()?.getName(),
+            value: item?.toString()
+        ]
+        final json = JsonOutput.toJson(entries.collect(collector))
+        log.info "[${safeTaskName(task)}] cache hash: ${hash}; mode: ${mode}; entries: ${JsonOutput.prettyPrint(json)}"
+    }
+
     private void traceInputsHashes( TaskRun task, List entries, CacheHelper.HashMode mode, hash ) {
 
         def buffer = new StringBuilder()