diff options
author | Bryan Newbold <bnewbold@archive.org> | 2018-08-17 17:36:53 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2018-08-21 20:31:45 -0700 |
commit | 38a0a73e7b1aa6d0002f4f1807171fffac19542f (patch) | |
tree | 816d296f18ab503692a2125c5ec42bce660c9867 /match_test_data/NOTES.txt | |
parent | 96f45740599a9d9ed06cf22eba8cd0a0e0927a42 (diff) | |
download | sandcrawler-38a0a73e7b1aa6d0002f4f1807171fffac19542f.tar.gz sandcrawler-38a0a73e7b1aa6d0002f4f1807171fffac19542f.zip |
add matching bibjson files
Diffstat (limited to 'match_test_data/NOTES.txt')
-rw-r--r-- | match_test_data/NOTES.txt | 13 |
1 files changed, 13 insertions, 0 deletions
diff --git a/match_test_data/NOTES.txt b/match_test_data/NOTES.txt new file mode 100644 index 0000000..c72f60a --- /dev/null +++ b/match_test_data/NOTES.txt @@ -0,0 +1,13 @@ + +Converted older .tsv from pdf-extraction comparison work with: + + cat 1k_random_identified_combined.tsv | jq -c --slurp --raw-input --raw-output 'split("\n") | .[:-1] | map(split("\t")) | map({"doi": .[0], "title": .[1], "authors": ( .[2] | split(";") ), "year": .[3], "journal": .[4], "publisher": .[5], "subject": .[6], "type": .[7], "sha": .[8]}) | .[]' > crossref_sample.bibjson + +Note that neither bibjson file is a superset of the either: + + 944 unique SHA1 which exist in both lists + 964 in crossref_sample.sha1 + 979 in grobid_sample.sha1 + +So scoring should be on a basis of "out of 944 lines". If this is confusing we +can trim the files down. |