diff options
| -rw-r--r-- | python/refcat/tasks.py | 26 |
1 files changed, 26 insertions, 0 deletions
diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py index 36250ba..c4e5b56 100644 --- a/python/refcat/tasks.py +++ b/python/refcat/tasks.py @@ -279,6 +279,7 @@ class OpenLibraryAuthors(luigi.ExternalTask, Refcat): def output(self): return luigi.LocalTarget(path=settings.OL_DUMP_AUTHORS, format=Zstd) + # ----8< Derivations # @@ -1039,6 +1040,31 @@ class UnmatchedOpenLibraryMatchTable(Refcat): return luigi.LocalTarget(path=self.path(ext="tsv.zst"), format=Zstd) +class BrefZipOpenLibrary(Refcat): + """ + Export fuzzy matches to open library targets. + """ + 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) + luigi.LocalTarget(output).move(self.output().path) + + def output(self): + return luigi.LocalTarget(path=self.path(ext="json.zst"), format=Zstd) + + # # Extra # ----- |