match and enrich notes+script

2 files changed, 64 insertions, 0 deletions

diff --git a/notes/match_filter_enrich.txt b/notes/match_filter_enrich.txt
new file mode 100644
index 0000000..e555d46
--- /dev/null
+++ b/notes/match_filter_enrich.txt
@@ -0,0 +1,19 @@
+
+This could all be a single scalding job eventually.
+
+First, run matchcrossref and dumpfilemeta, and copy the output down to an SSD
+somewhere.
+
+    bnewbold@ia601101$ zcat 2018-09-14-0559.05-dumpfilemeta.tsv.gz | wc -l
+    30728100
+
+Reduce down the scored matches to just {sha1, dois}, sorted:
+
+    zcat 2018-08-27-2352.17-matchcrossref.tsv.gz | ./filter_scored_matches.py | pv -l | sort > 2018-08-27-2352.17-matchcrossref.filtered.tsv
+    # 5.79M 0:18:54 [5.11k/s]
+
+Join/merge the output:
+
+    zcat 2018-09-14-0559.05-dumpfilemeta.tsv.gz | LC_ALL=C join -t$'\t' 2018-08-27-2352.17-matchcrossref.filtered.tsv - | pv -l | enrich_scored_matches.py | gzip > 2018-08-27-2352.17-matchcrossref.insertable.json.gz
+    # 5.79M 0:09:09 [10.5k/s]
+
diff --git a/python/enrich_scored_matches.py b/python/enrich_scored_matches.py
new file mode 100755
index 0000000..9fe1499
--- /dev/null
+++ b/python/enrich_scored_matches.py
@@ -0,0 +1,45 @@
+#!/usr/bin/env python3
+"""
+Takes an "joined" TSV input stream:
+
+- sha1
+- dois (JSON list)
+- cdx (JSON object)
+    - url
+    - dt
+    (etc)
+- mimetype
+- size (integer)
+
+And outputs JSON objects that are can be imported into fatcat with the
+"matched" script.
+
+No dependencies (only python3 stdlib)
+"""
+
+import sys
+import json
+import base64
+
+def run():
+    for line in sys.stdin:
+        line = line.split('\t')
+        assert len(line) == 5
+        raw_sha1 = line[0].replace('sha1:', '')
+        dois = json.loads(line[1])
+        cdx = json.loads(line[2])
+        mimetype = line[3]
+        size = int(line[4])
+
+        sha1 = base64.b16encode(base64.b32decode(raw_sha1)).decode('ascii').lower()
+
+        obj = dict(
+            sha1=sha1,
+            dois=dois,
+            cdx=[dict(url=cdx['url'], dt=cdx['dt'])],
+            size=size,
+            mimetype=mimetype)
+        print(json.dumps(obj))
+
+if __name__=='__main__':
+    run()