From 4fda7f72a87a863641138126c0b0e117a9b93d7b Mon Sep 17 00:00:00 2001
From: Martin Czygan <martin.czygan@gmail.com>
Date: Mon, 10 May 2021 23:53:17 +0200
Subject: add RefsDOI

---
 python/refcat/tasks.py | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py
index 5b54b51..fbe7b1a 100644
--- a/python/refcat/tasks.py
+++ b/python/refcat/tasks.py
@@ -275,7 +275,7 @@ class UnmatchedRefs(Refcat):
 
 class URLTabs(Refcat):
     """
-    Extract (work ident, release ident, url, doc).
+    Extract (work ident, release ident, url, doc). 519m45.710s (about 55k docs/s).
     """
     def requires(self):
         return RefsWithUnstructured()
@@ -295,4 +295,24 @@ class URLTabs(Refcat):
     def output(self):
         return luigi.LocalTarget(path=self.path(ext="tsv.zst"), format=Zstd)
 
+class RefsDOI(Refcat):
+    """
+    Sorted (doi, doc) tuplics from refs.
+    """
+    def requires(self):
+        return RefsWithUnstructured()
+
+    def run(self):
+        output = shellout("""
+                          zstdcat -T0 {input} |
+                          skate-map -m ff -x biblio.doi |
+                          LC_ALL=C sort -T {tmpdir} -k2,2 -S25% --parallel 4 |
+                          zstd -T0 -c > {output}
+                          """,
+                          n=self.n,
+                          tmpdir=self.tmpdir,
+                          input=self.input().path)
+        luigi.LocalTarget(output).move(self.output().path)
 
+    def output(self):
+        return luigi.LocalTarget(path=self.path(ext="tsv.zst"), format=Zstd)
-- 
cgit v1.2.3