with open(r"/tmp/cgspace-countries.txt",'r') as f :
+with open(r"/tmp/cgspace-countries.txt",'r') as f:
countries = [name.rstrip().lower() for name in f]
return "||".join([x for x in value.split(' ') if x.lower() in countries])
@@ -320,7 +320,7 @@ Our request to add CC-BY-3.0-IGO to SPDX was approved a few weeks ago
import re
-with open(r"/tmp/agrovoc-subjects.txt",'r') as f :
+with open(r"/tmp/agrovoc-subjects.txt",'r') as f:
terms = [name.rstrip().lower() for name in f]
return "||".join([term for term in terms if re.match(r".*\b" + term + r"\b.*", value.lower())])
diff --git a/docs/2023-02/index.html b/docs/2023-02/index.html
index 355689546..ce35cf7b8 100644
--- a/docs/2023-02/index.html
+++ b/docs/2023-02/index.html
@@ -18,7 +18,7 @@ I want to try to expand my use of their data to journals, publishers, volumes, i
-
+
@@ -42,9 +42,9 @@ I want to try to expand my use of their data to journals, publishers, volumes, i
"@type": "BlogPosting",
"headline": "February, 2023",
"url": "https://alanorth.github.io/cgspace-notes/2023-02/",
- "wordCount": "2333",
+ "wordCount": "2566",
"datePublished": "2023-02-01T10:57:36+03:00",
- "dateModified": "2023-02-15T19:47:13+03:00",
+ "dateModified": "2023-02-21T20:46:53+03:00",
"author": {
"@type": "Person",
"name": "Alan Orth"
@@ -508,7 +508,48 @@ I want to try to expand my use of their data to journals, publishers, volumes, i
# grep 'RTB website BOT' /var/log/nginx/rest.log | awk '{print $9}' | sort | uniq -c | sort -h
2023 200
-
+- Start reviewing and fixing metadata for Sam’s ~250 CAS publications from last year
+
+- Both Abenet and Peter have already looked at them and Sam has been waiting for months on this
+
+
+
+2023-02-22
+
+- Continue proofing CAS records for Sam
+
+- I downloaded all the PDFs manually and checked the issue dates for each from the PDF, noting some that had licenses, ISBNs, etc
+- I combined the title, abstract, and system subjects into one column to mine them for AGROVOC terms:
+
+
+
+toLowercase(value) + toLowercase(cells["dcterms.abstract"].value) + toLowercase(cells["cg.subject.system"].value.replace("||", " "))
+
+- Then I extracted a list of AGROVOC terms the same way I did in August, 2022 and used this Jython code to extract matching terms:
+
+import re
+
+with open(r"/tmp/agrovoc-subjects.txt",'r') as f :
+ terms = [name.rstrip().lower() for name in f]
+
+return "||".join([term for term in terms if re.match(r".*\b" + term + r"\b.*", value.lower())])
+
deduped_list = list(set(value.split("||")))
+return '||'.join(map(str, deduped_list))
+