Merge pull request #170 from nextflow-io/fix-yaml-bugs

Fix YAML samplesheet issues

Author: awgymer

CHANGELOG.md

@@ -20,6 +20,8 @@
 1. CSV and TSV files with trailing commas or tabs will now be properly sanitized. This fixes issues with CSV and TSV files that contained empty header columns.
 2. Unidentified parameters are no longer printed out on failure of the parameter validation. This is to prevent a bug where all parameters would be printed out on failure.
 3. Fixed an issue where default values of `null` weren't being set correctly in `samplesheetToList()`.
+4. Fixed an undocumented limit of `3MB` for `YAML` format samplesheets (new limit is `50MB`).
+5. Fixed issue where an empty string in a yaml for a file type string format would throw a Java error instead of reporting a proper validation error.
 
 ## Logging configuration
 

src/main/groovy/nextflow/validation/utils/Files.groovy

@@ -1,6 +1,7 @@
 package nextflow.validation.utils
 
 import org.yaml.snakeyaml.Yaml
+import org.yaml.snakeyaml.LoaderOptions
 import org.json.JSONArray
 import org.json.JSONObject
 import org.json.JSONPointer
@@ -85,7 +86,9 @@ public class Files {
         }
 
         if(fileType == "yaml"){
-            return new Yaml().load((file.text))
+            def LoaderOptions yamlLoaderOptions = new LoaderOptions()
+            yamlLoaderOptions.setCodePointLimit(50 * 1024 * 1024)
+            return new Yaml(yamlLoaderOptions).load((file.text))
         }
         else if(fileType == "json"){
             return new JsonSlurper().parseText(file.text)

src/main/groovy/nextflow/validation/validators/evaluators/ExistsEvaluator.groovy

@@ -30,8 +30,8 @@ class ExistsEvaluator implements Evaluator {
         }
 
         def String value = node.asString()
-        def Path file = Nextflow.file(value) as Path
         def Boolean exists
+        def Path file
 
         try {
             file = Nextflow.file(value) as Path