tasks: add ReleaseIdentDOIList

1 files changed, 19 insertions, 0 deletions

diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py
index 8df25f2..5e53f98 100644
--- a/python/refcat/tasks.py
+++ b/python/refcat/tasks.py
@@ -375,6 +375,25 @@ class ReleaseExportReduced(Refcat):
     def output(self):
         return luigi.LocalTarget(path=self.path(ext="json.zst"), format=Zstd)
 
+class ReleaseIdentDOIList(Refcat):
+    """
+    Create TSV (ident, doi).
+    """
+    def requires(self):
+        return ReleaseExportExpanded()
+
+    def run(self):
+        output = shellout("""
+                          zstdcat -T0 {input} |
+                          parallel --block 10M -j 20 --pipe
+                              "jq -rc 'select(.ext_ids.doi != null) | [.ident, .ext_ids.doi] | @tsv'" > {output}
+                          """,
+                          input=self.input().path)
+        luigi.LocalTarget(output).move(self.output().path)
+
+    def output(self):
+        return luigi.LocalTarget(path=self.path(ext="tsv"))
+
 
 class UnmatchedRefs(Refcat):
     """