From 54b6ab070ae13fe2fc09b0313b0e3f7243b843d6 Mon Sep 17 00:00:00 2001
From: Scott Morrison <scott@tqft.net>
Date: Thu, 2 May 2013 20:06:18 +1000
Subject: [PATCH] initial attempt to pairwise diff testing

---
 .gitignore              |  3 +++
 tests/diff/comparediffs | 23 +++++++++++++++++++++++
 tests/diff/urls         |  8 ++++++++
 3 files changed, 34 insertions(+)
 create mode 100755 tests/diff/comparediffs
 create mode 100644 tests/diff/urls

diff --git a/.gitignore b/.gitignore
index 4278ff0..66b8e49 100644
--- a/.gitignore
+++ b/.gitignore
@@ -13,3 +13,6 @@ pdfparanoia.egg-info/
 
 # ignore pdfs in the top-level dir
 /*.pdf
+
+# temporary pdfs in tests/diff/
+tests/diff/*.pdf
diff --git a/tests/diff/comparediffs b/tests/diff/comparediffs
new file mode 100755
index 0000000..f49bd51
--- /dev/null
+++ b/tests/diff/comparediffs
@@ -0,0 +1,23 @@
+for url in `cat urls`; do
+	echo "Retrieving $url";
+	# TODO allow customizing the proxies, or more generally the retrieval mechanisms
+	# TODO allow local caching
+	curl --socks localhost:1080 $url > 1.pdf
+	curl --socks localhost:1083 $url > 2.pdf
+	# TODO verify that we actually obtained pdfs
+	if diff 1.pdf 2.pdf; then
+		echo "PDFs are identical already, no need to use pdfparanoia"
+	else
+		cat 1.pdf | pdfparanoia > 1.cleaned.pdf
+		cat 2.pdf | pdfparanoia > 2.cleaned.pdf
+		if diff 1.cleaned.pdf 2.cleaned.pdf; then
+			echo "pdfparanoia successful scrubbed the PDFs"
+		else
+			echo "pdfparanoia failed!"
+		fi
+		rm 1.cleaned.pdf
+		rm 2.cleaned.pdf
+	fi
+	rm 1.pdf
+	rm 2.pdf
+done
diff --git a/tests/diff/urls b/tests/diff/urls
new file mode 100644
index 0000000..0900fbc
--- /dev/null
+++ b/tests/diff/urls
@@ -0,0 +1,8 @@
+http://link.springer.com/content/pdf/10.1007/s00440-011-0397-9
+http://msp.org/apde/2012/5-2/apde-v5-n2-p07-s.pdf
+http://annals.math.princeton.edu/wp-content/uploads/annals-v176-n2-p11-s.pdf
+http://www.worldscientific.com/doi/pdf/10.1142/S2010326311500018
+http://www.sciencedirect.com/science?_ob=MiamiImageURL&_cid=272585&_user=994540&_pii=S0001870812001806&_check=y&_origin=article&_zone=toolbar&_coverDate=10-Sep-2012&view=c&originContentFamily=serial&wchp=dGLzVlt-zSkWb&md5=bfeb5e0619d45362640529aff02baeda&pid=1-s2.0-S0001870812001806-main.pdf
+http://www.ams.org/journals/mcom/2012-81-278/S0025-5718-2011-02542-1/S0025-5718-2011-02542-1.pdf
+http://www.ems-ph.org/journals/show_pdf.php?issn=1661-7207&vol=5&iss=2&rank=6
+http://nyjm.albany.edu/j/2009/15-14p.pdf