From 3f85b3a35dff8dbcfa8bd8ae1390c9610e0f34a8 Mon Sep 17 00:00:00 2001
From: Martin Czygan <martin.czygan@gmail.com>
Date: Mon, 2 Aug 2021 15:55:27 +0200
Subject: update notes

---
 python/notes/coci_notes.md | 62 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)

(limited to 'python')

diff --git a/python/notes/coci_notes.md b/python/notes/coci_notes.md
index 6d7a968..b6e2b0e 100644
--- a/python/notes/coci_notes.md
+++ b/python/notes/coci_notes.md
@@ -41,3 +41,65 @@ Example approach:
 * from fatcat db dump, extract source id and ext ids, sort by source ident
 * "zip together"
 
+Unify CSV files:
+
+```
+$ zstdcat -T0 6741422v9.csv.zst | wc -l
+759516506
+```
+
+Nomenclature:
+
+* citing = source
+* cited = target
+
+Example:
+
+```
+10.3846/16111699.2012.720591,10.1016/0024-6301(96)00041-6
+```
+
+> citing: 10.3846/16111699.2012.720591, https://fatcat.wiki/release/52znjflg2bdd5h2q2icu3zjhki
+> cited: 10.1016/0024-6301(96)00041-6, https://fatcat.wiki/release/mz6dkakhknd47h3skd7ttomwga
+
+```
+$ curl -s "localhost:9200/fatcat_ref_v02_20210716/_search?q=source_release_ident:52znjflg2bdd5h2q2icu3zjhki+AND+target_release_ident:mz6dkakhknd47h3skd7ttomwga" | jq .
+{
+  "took": 259,
+  "timed_out": false,
+  "_shards": {
+    "total": 6,
+    "successful": 6,
+    "skipped": 0,
+    "failed": 0
+  },
+  "hits": {
+    "total": {
+      "value": 1,
+      "relation": "eq"
+    },
+    "max_score": 32.16953,
+    "hits": [
+      {
+        "_index": "fatcat_ref_v02_20210716",
+        "_type": "_doc",
+        "_id": "52znjflg2bdd5h2q2icu3zjhki_2",
+        "_score": 32.16953,
+        "_source": {
+          "indexed_ts": "2021-07-10T12:04:57Z",
+          "match_provenance": "crossref",
+          "match_reason": "doi",
+          "match_status": "exact",
+          "ref_index": 2,
+          "ref_key": "cit0005",
+          "source_release_ident": "52znjflg2bdd5h2q2icu3zjhki",
+          "source_work_ident": "76yenkekovfh5bnvuxwvtvxy5q",
+          "source_year": "2014",
+          "target_release_ident": "mz6dkakhknd47h3skd7ttomwga",
+          "target_work_ident": "um37w3kdcnhqvnp5jeh3mvhumy"
+        }
+      }
+    ]
+  }
+}
+```
-- 
cgit v1.2.3