aboutsummaryrefslogtreecommitdiffstats
path: root/pig/tests/files/papers_url_words.cdx
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2018-05-08 10:06:14 -0700
committerBryan Newbold <bnewbold@archive.org>2018-05-08 10:06:20 -0700
commit18a55d37a87d4391bd8161201c523dd7d7f0f1e7 (patch)
tree86db4c84cf4fd0dde5ea9508617344018e640104 /pig/tests/files/papers_url_words.cdx
parent1831a3b4495aee275e4b4b187fa545eba75eb87b (diff)
downloadsandcrawler-18a55d37a87d4391bd8161201c523dd7d7f0f1e7.tar.gz
sandcrawler-18a55d37a87d4391bd8161201c523dd7d7f0f1e7.zip
fix tests post-DISTINCT
Confirms it's working!
Diffstat (limited to 'pig/tests/files/papers_url_words.cdx')
-rw-r--r--pig/tests/files/papers_url_words.cdx24
1 files changed, 12 insertions, 12 deletions
diff --git a/pig/tests/files/papers_url_words.cdx b/pig/tests/files/papers_url_words.cdx
index e9bf661..8d4fe01 100644
--- a/pig/tests/files/papers_url_words.cdx
+++ b/pig/tests/files/papers_url_words.cdx
@@ -13,15 +13,15 @@
# 12 matches:
-uk,ac,surrey,ee,personal)/Personal/R.Bowden/publications/2012/Gilbert_ACCV_2012pp.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
-gov,ed,eric,files)/fulltext/EJ798626.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
-edu,hbs,www)/research/pdf/10-108.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
-ch,unifr,www)/biochem/assets/files/albrecht/publications/Abraham06.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
-edu,cmu,cnbc,www)/cns/papers/Kassetal2005.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
-org,macrothink,www)/journal/index.php/ijhrs/article/download/5765/4663 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
-ca,math,pims,www)/science/2004/fpsac/Papers/Liskovets.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
-at,ac,uni-linz,risc,www)/publications/download/risc_3287/synasc_revised.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
-gr,uoi,cs,softsys)/dbglobe/publications/wi04.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
-za,ac,journals,lexikos)/pub/article/download/1048/564 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
-org,siam,www)/proceedings/analco/2007/anl07_029ecesaratto.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
-uk,ac,bris,cs,www)/Publications/Papers/2000249.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+uk,ac,surrey,ee,personal)/Personal/R.Bowden/publications/2012/Gilbert_ACCV_2012pp.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 1QHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+gov,ed,eric,files)/fulltext/EJ798626.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 2QHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+edu,hbs,www)/research/pdf/10-108.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 3QHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+ch,unifr,www)/biochem/assets/files/albrecht/publications/Abraham06.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 4QHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+edu,cmu,cnbc,www)/cns/papers/Kassetal2005.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 5QHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+org,macrothink,www)/journal/index.php/ijhrs/article/download/5765/4663 20170706005950 http://mit.edu/file.pdf application/pdf 200 6QHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+ca,math,pims,www)/science/2004/fpsac/Papers/Liskovets.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 7QHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+at,ac,uni-linz,risc,www)/publications/download/risc_3287/synasc_revised.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 8QHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+gr,uoi,cs,softsys)/dbglobe/publications/wi04.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 9QHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+za,ac,journals,lexikos)/pub/article/download/1048/564 20170706005950 http://mit.edu/file.pdf application/pdf 200 HQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+org,siam,www)/proceedings/analco/2007/anl07_029ecesaratto.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 DQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+uk,ac,bris,cs,www)/Publications/Papers/2000249.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 SQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz