aboutsummaryrefslogtreecommitdiffstats
path: root/pig/tests/files/papers_url_doi.cdx
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2018-05-08 06:21:29 +0000
committerBryan Newbold <bnewbold@archive.org>2018-05-08 06:21:29 +0000
commite566ee1b4e134bfc06284cf77d8d1370df30d53f (patch)
treef3969054cc5f93608b5c72d41541ea381ef89a6b /pig/tests/files/papers_url_doi.cdx
parent0c398392aa298d28694bf5bd37d3e4912de8a2f5 (diff)
parent65b7d45852af3de557eaaf200471ff9b1a211970 (diff)
downloadsandcrawler-e566ee1b4e134bfc06284cf77d8d1370df30d53f.tar.gz
sandcrawler-e566ee1b4e134bfc06284cf77d8d1370df30d53f.zip
Merge branch 'master' of git.archive.org:webgroup/sandcrawler
Diffstat (limited to 'pig/tests/files/papers_url_doi.cdx')
-rw-r--r--pig/tests/files/papers_url_doi.cdx7
1 files changed, 7 insertions, 0 deletions
diff --git a/pig/tests/files/papers_url_doi.cdx b/pig/tests/files/papers_url_doi.cdx
new file mode 100644
index 0000000..1ad5792
--- /dev/null
+++ b/pig/tests/files/papers_url_doi.cdx
@@ -0,0 +1,7 @@
+#http://journals.ametsoc.org/doi/pdf/10.1175/2008BAMS2370.1
+#http://www.nejm.org:80/doi/pdf/10.1056/NEJMoa1013607
+
+# should match 2:
+
+org,ametsoc,journals)/doi/pdf/10.1175/2008BAMS2370.1 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+org,nejm,www)/doi/pdf/10.1056/NEJMoa1013607 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz