From 8b18e4311aceae98f730dc655c24ba72494dc9ae Mon Sep 17 00:00:00 2001
From: Martin Czygan <martin.czygan@gmail.com>
Date: Mon, 24 May 2021 20:32:42 +0200
Subject: tasks: add UnmatchedMapped, for OL
---
python/refcat/tasks.py | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
(limited to 'python')
diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py
index 54a5890..fa72062 100644
--- a/python/refcat/tasks.py
+++ b/python/refcat/tasks.py
@@ -747,3 +747,24 @@ class OpenLibraryWorksSorted(Refcat):
def output(self):
return luigi.LocalTarget(path=self.path(ext="tsv.zst"), format=Zstd)
+
+class UnmatchedMapped(Refcat):
+ """
+ Map unmatched refs (in release schema) to titles to do approximate title matches with OL.
+ """
+
+ def requires(self):
+ return UnmatchedRefs()
+
+ def run(self):
+ output = shellout("""
+ zstdcat -T0 {input} |
+ skate-map -m ts |
+ LC_ALL=C sort -T {tmpdir} -S25% -k1,1 --parallel 4 |
+ zstd -T0 -c > {output}
+ """,
+ tmpdir=self.tmpdir,
+ input=self.input().path)
+
+ def output(self):
+ return luigi.LocalTarget(path=self.path(ext="tsv.zst"), format=Zstd)
--
cgit v1.2.3