From fda10154b50ab44970d2841e0ea74a4651b7b920 Mon Sep 17 00:00:00 2001
From: Martin Czygan <martin.czygan@gmail.com>
Date: Mon, 7 Jun 2021 19:19:25 +0200
Subject: task: add OpenLibraryReleaseMapped

---
 python/refcat/tasks.py | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'python')

diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py
index 75e40b5..88d4473 100644
--- a/python/refcat/tasks.py
+++ b/python/refcat/tasks.py
@@ -1116,6 +1116,26 @@ class BrefZipOpenLibrary(Refcat):
     def output(self):
         return luigi.LocalTarget(path=self.path(ext="json.zst"), format=Zstd)
 
+class OpenLibraryReleaseMapped(Refcat):
+    mapper = luigi.Parameter(default="isbn", description="mapper short name")
+
+    def requires(self):
+        return OpenLibraryEditionsToRelease()
+
+    def run(self):
+        output = shellout("""
+                          zstdcat -T0 {input} |
+                          skate-map -m {mapper} -skip-on-empty 1 |
+                          LC_ALL=C sort -T {tmpdir} -k1,1 -S25% --parallel 4 |
+                          zstd -T0 -c > {output}
+                          """,
+                          mapper=self.mapper,
+                          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)
 
 #
 # Combined Bref File
-- 
cgit v1.2.3