From c033a545e83bcbf8d1b99c6c2efd7c75b59d32b0 Mon Sep 17 00:00:00 2001
From: Martin Czygan <martin.czygan@gmail.com>
Date: Sat, 29 May 2021 02:27:34 +0200
Subject: tasks: add UnmatchedOpenLibraryMatchTable

---
 python/refcat/tasks.py | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'python')

diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py
index b8a942c..0656f3c 100644
--- a/python/refcat/tasks.py
+++ b/python/refcat/tasks.py
@@ -862,3 +862,27 @@ class UnmatchedMapped(Refcat):
 
     def output(self):
         return luigi.LocalTarget(path=self.path(ext="tsv.zst"), format=Zstd)
+
+
+class UnmatchedOpenLibraryMatchTable(Refcat):
+    """
+    Run matching and write tabular results to file.
+    """
+    def requires(self):
+        return {
+            "unmatched": UnmatchedMapped(),
+            "ol": OpenLibraryEditionsMapped(),
+        }
+
+    def run(self):
+        output = shellout("""
+                          skate-reduce -m oled
+                              -O <(zstdcat -T0 {ol})
+                              -F <(zstdcat -T0 {unmatched}) |
+                          zstd -c > {output}
+                          """,
+                          ol=self.input().get("ol").path,
+                          unmatched=self.input().get("unmatched").path)
+
+    def output(self):
+        return luigi.LocalTarget(path=self.path(ext="tsv.zst"), format=Zstd)
-- 
cgit v1.2.3