aboutsummaryrefslogtreecommitdiffstats
path: root/pig/tests/files/papers_url_words.cdx
diff options
context:
space:
mode:
Diffstat (limited to 'pig/tests/files/papers_url_words.cdx')
-rw-r--r--pig/tests/files/papers_url_words.cdx27
1 files changed, 27 insertions, 0 deletions
diff --git a/pig/tests/files/papers_url_words.cdx b/pig/tests/files/papers_url_words.cdx
new file mode 100644
index 0000000..e9bf661
--- /dev/null
+++ b/pig/tests/files/papers_url_words.cdx
@@ -0,0 +1,27 @@
+#http://personal.ee.surrey.ac.uk/Personal/R.Bowden/publications/2012/Gilbert_ACCV_2012pp.pdf
+#http://files.eric.ed.gov/fulltext/EJ798626.pdf
+#http://www.hbs.edu/research/pdf/10-108.pdf
+#http://www.unifr.ch/biochem/assets/files/albrecht/publications/Abraham06.pdf
+#http://www.cnbc.cmu.edu/cns/papers/Kassetal2005.pdf
+#http://www.macrothink.org/journal/index.php/ijhrs/article/download/5765/4663
+#http://www.pims.math.ca:80/science/2004/fpsac/Papers/Liskovets.pdf
+#http://www.risc.uni-linz.ac.at/publications/download/risc_3287/synasc_revised.pdf
+#http://softsys.cs.uoi.gr/dbglobe/publications/wi04.pdf
+#http://lexikos.journals.ac.za/pub/article/download/1048/564
+#http://www.siam.org/proceedings/analco/2007/anl07_029ecesaratto.pdf
+#http://www.cs.bris.ac.uk/Publications/Papers/2000249.pdf
+
+# 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