aboutsummaryrefslogtreecommitdiffstats
path: root/python
diff options
context:
space:
mode:
Diffstat (limited to 'python')
-rw-r--r--python/notes/version_4.md62
1 files changed, 62 insertions, 0 deletions
diff --git a/python/notes/version_4.md b/python/notes/version_4.md
index 9296089..0e3bdfc 100644
--- a/python/notes/version_4.md
+++ b/python/notes/version_4.md
@@ -384,3 +384,65 @@ A matching OL edition record:
```
+----
+
+# Completeness
+
+```
+{
+ "biblio": {
+ "container_name": "La vida y época de Prebisch",
+ "year": 2010
+ },
+ "index": 5,
+ "key": "key20191115064515_B6",
+ "ref_source": "crossref",
+ "release_year": 2019,
+ "release_ident": "oc6nhkoah5gcnjfsjpct4ij3ea",
+ "work_ident": "aaachbf2kbdnxekwdujbmnlw4a"
+}
+```
+
+* https://fatcat.wiki/release/oc6nhkoah5gcnjfsjpct4ij3ea/references
+* https://www.iberoamericana.se/articles/10.16993/iberoamericana.467/galley/445/download/
+
+In the PDF, we find a DOI as well, but it seems to be not extracted. In fact;
+the ref data comes from crossref.
+
+Grobid gets the DOI:
+
+```
+<biblStruct xml:id="b5">
+ <monogr>
+ <title level="m" type="main">La vida y época de Prebisch. 1901-1986. Madrid: Marcial Pons</title>
+ <author>
+ <persName xmlns="http://www.tei-c.org/ns/1.0"><forename type="first">E</forename><forename type="middle">J</forename><surname>Dosman</surname></persName>
+ </author>
+ <idno type="DOI">10.18356/40a5d411-es</idno>
+ <ptr target="https://doi.org/10.18356/40a5d411-es" />
+ <imprint>
+ <date type="published" when="2010" />
+ </imprint>
+ </monogr>
+</biblStruct>
+```
+
+Other issues:
+
+* year vs release_year
+
+```
+{
+ "biblio": {
+ "container_name": "The Methodology of Scientific Research Programmes",
+ "year": 1980
+ },
+ "index": 13,
+ "key": "key20191115064515_B14",
+ "ref_source": "crossref",
+ "release_year": 2019,
+ "release_ident": "oc6nhkoah5gcnjfsjpct4ij3ea",
+ "work_ident": "aaachbf2kbdnxekwdujbmnlw4a"
+}
+```
+