7 files changed, 598 insertions, 2 deletions
diff --git a/tests/checkdiffs.py b/tests/checkdiffs.py
new file mode 100755
index 0000000..4d11888
--- /dev/null
+++ b/tests/checkdiffs.py
@@ -0,0 +1,81 @@
+#! /usr/bin/env python2
+
+import sys
+import os
+import subprocess
+import hashlib
+
+import expected
+import static_pdfs
+
+source_pdfs = static_pdfs.pdffiles[0]
+source_pdfs = dict((os.path.basename(x), x) for x in source_pdfs)
+
+result_dir = expected.result_dir
+
+for subdir in sorted(os.listdir(result_dir)):
+    dstd = os.path.join(result_dir, subdir)
+    if not os.path.isdir(dstd):
+        continue
+    for pdffile in sorted(os.listdir(dstd)):
+        testname = '%s/%s' % (subdir, pdffile)
+        srcf = source_pdfs.get(pdffile)
+        dstf = os.path.join(dstd, pdffile)
+        if pdffile not in source_pdfs:
+            print('\n Skipping %s -- source not found' % testname)
+            continue
+
+        with open(dstf, 'rb') as f:
+            data = f.read()
+        hash = hashlib.md5(data).hexdigest()
+        skipset = set((hash, 'skip', 'xfail', 'fail', '!' + hash))
+        if expected.results[testname] & skipset:
+            print('\n Skipping %s -- marked done' % testname)
+            continue
+        if os.path.exists('foobar.pdf'):
+            os.remove('foobar.pdf')
+        builtdiff = False
+        while 1:
+            sys.stdout.write('''
+                Test case %s
+
+                c = compare using imagemagick and okular
+                f = display foobar.pdf (result from comparison)
+                o = display results with okular
+                a = display results with acrobat
+
+                s = mark 'skip' and go to next PDF
+                g = mark as good and go to next PDF
+                b = mark as bad and go to next PDF
+                n = next pdf without marking
+                q = quit
+-->  ''' % testname)
+            sel = raw_input()
+            if sel == 'q':
+                raise SystemExit(0)
+            if sel == 'n':
+                break
+            if sel == 'c':
+                subprocess.call(('compare', '-verbose', srcf, dstf,
+                                 'foobar.pdf'))
+                builtdiff = True
+                continue
+            if sel == 'f':
+                subprocess.call(('okular', 'foobar.pdf'))
+                continue
+            if sel == 'o':
+                subprocess.call(('okular', srcf, dstf))
+                continue
+            if sel == 'a':
+                if builtdiff:
+                    subprocess.call(('acroread', srcf, dstf, 'foobar.pdf'))
+                else:
+                    subprocess.call(('acroread', srcf, dstf))
+                continue
+
+            if sel in 'sgb':
+                results = (hash if sel == 'g' else
+                           '    skip' if sel == 's' else '!'+hash)
+                with open(expected.expectedf, 'a') as f:
+                    f.write('%s %s\n' % (testname, results))
+                break
diff --git a/tests/expected.py b/tests/expected.py
new file mode 100644
index 0000000..a65c989
--- /dev/null
+++ b/tests/expected.py
@@ -0,0 +1,41 @@
+# A part of pdfrw (https://github.com/pmaupin/pdfrw)
+# Copyright (C) 2006-2015 Patrick Maupin, Austin, Texas
+# MIT license -- See LICENSE.txt for details
+
+'''
+    Read expected.txt, which should be in the format:
+
+       testname/srcname.pdf validhash
+
+    More than one validhash is allowed (on separate lines),
+    and hash-delimited comments are allowed.
+'''
+
+import os
+import collections
+from pdfrw.py23_diffs import convert_load
+
+root_dir = os.path.dirname(__file__)
+result_dir = 'tmp_results'
+if os.path.exists('ramdisk'):
+    result_dir = os.path.join('ramdisk', result_dir)
+result_dir = os.path.join(root_dir, result_dir)
+
+for sourcef in ('mytests.txt', 'expected.txt'):
+    expectedf = os.path.join(root_dir, sourcef)
+    if os.path.exists(expectedf):
+        break
+
+
+def results():
+    results = collections.defaultdict(set)
+    with open(expectedf, 'rb') as f:
+        for line in f:
+            line = convert_load(line)
+            line = line.split('#', 1)[0].split()
+            if not line:
+                continue
+            key, value = line
+            results[key].add(value)
+    return results
+results = results()
diff --git a/tests/expected.txt b/tests/expected.txt
new file mode 100644
index 0000000..64eecdd
--- /dev/null
+++ b/tests/expected.txt
@@ -0,0 +1,140 @@
+# Example programs
+
+examples/4up_b1c400de699af29ea3f1983bb26870ab               1b73c612c40b5082d955ed72f63644bd
+examples/alter_b1c400de699af29ea3f1983bb26870ab             3c3ee465f45a685ba7098691be05a5ab
+examples/booklet_b1c400de699af29ea3f1983bb26870ab           d711b74110eefb4e9e6bf1a5bea16bfe
+examples/extract_1975ef8db7355b1d691bc79d0749574b           b4f5ee36a288da970ed040a9a733c8b0
+examples/extract_c5c895deecf7a7565393587e0d61be2b           539aad09ef80907bb396c3260eb87d7b
+examples/extract_d711b74110eefb4e9e6bf1a5bea16bfe           26ddfd09c6e6002228f06782c8544ac4
+examples/print_two_b1c400de699af29ea3f1983bb26870ab         73c8a16aba44548c2c06dae6e2551961
+examples/subset_b1c400de699af29ea3f1983bb26870ab_1-3_5      880a9578197130273ccb51265af08029
+examples/unspread_d711b74110eefb4e9e6bf1a5bea16bfe          780a9abe26a9de0b5b95ee22c4835e4b
+
+examples/cat_b1c400de699af29ea3f1983bb26870ab_06c86654f9a77e82f9adaa0086fc391c          62bb9b746ff5932d3f1b88942d36a81d
+examples/rotate_707e3e2d17cbe9ec2273414b3b63f333_270_1-4_7-8_10-50_52-56                841c980dfadf2cc47ad86e4649ca69b6
+examples/watermark_b1c400de699af29ea3f1983bb26870ab_06c86654f9a77e82f9adaa0086fc391c    41989bb2cb6225c6e14262ff5d4f151f
+examples/watermark_b1c400de699af29ea3f1983bb26870ab_06c86654f9a77e82f9adaa0086fc391c_-u e43e3ac0afe1cc242549424755dbf612
+
+# All these are in the poster test
+examples/subset_1975ef8db7355b1d691bc79d0749574b_21     5057f345f1a1109a0e54276a68e8f8df
+examples/rotate_5057f345f1a1109a0e54276a68e8f8df_90_1   881f4dc8dcf069e707bf61af95492d86
+examples/poster_881f4dc8dcf069e707bf61af95492d86        a34be06d22105b6c02394a9f278fec0d
+
+examples/rl1/4up_b1c400de699af29ea3f1983bb26870ab                   959d6246ad8bda72bd023e8681216d17
+examples/rl1/booklet_b1c400de699af29ea3f1983bb26870ab               45b4ae29a038271896b7264bbed63bdf
+examples/rl1/subset_b1c400de699af29ea3f1983bb26870ab_3_5            822bce1cb9e053f1f3f6b922bf27fab8
+examples/rl1/platypus_pdf_template_b1c400de699af29ea3f1983bb26870ab 97ad6a8ca3fe7cc4e1f0ffb8475355e9
+
+# List things that need work here (typically cause exceptions)
+
+# Bad info dict -- works otherwise
+
+simple/b1c400de699af29ea3f1983bb26870ab.pdf         ecf2e28de18a724b53670c0d5637ec28
+repaginate/b1c400de699af29ea3f1983bb26870ab.pdf     4d7d6c5f6e14c6eac1dfc055cebfa499
+
+# 07b0ba4 is missing an object.  Best we can do is report it
+# (and we do)
+
+repaginate/07b0ba4cff1c6ff73fd468b04b013457.pdf     993c763e085bce7ecc941ba104f4c892
+simple/07b0ba4cff1c6ff73fd468b04b013457.pdf         499b9c1b1e1c76b7c5c0d5e3b62889e3
+
+#b107 has a single page, but with an empty contents dict.
+
+repaginate/b107669d1dd69eabb89765fabb2cb321.pdf     0652d2da25b50cad75863d0e2bbaa878
+simple/b107669d1dd69eabb89765fabb2cb321.pdf         56025c06ab8633575ddc6c6990d2fbf1
+
+# Encrypted files
+
+repaginate/0ae80b493bc21e6de99f2ff6bbb8bc2c.pdf     skip
+repaginate/6e122f618c27f3aa9a689423e3be6b8d.pdf     skip
+repaginate/7dc787639aa6765214e9ff5494d231ed.pdf     skip
+repaginate/b4b27aaa1f9c7c524298e98be279bebb.pdf     skip
+repaginate/b5b6c6405d7b48418bccf97277957664.pdf     skip
+repaginate/bd0ef57aec16ded45bd89d61b54af0be.pdf     skip
+repaginate/dbb807a878ac1da6b91ac15c9de4e209.pdf     skip
+simple/0ae80b493bc21e6de99f2ff6bbb8bc2c.pdf         skip
+simple/6e122f618c27f3aa9a689423e3be6b8d.pdf         skip
+simple/7dc787639aa6765214e9ff5494d231ed.pdf         skip
+simple/b4b27aaa1f9c7c524298e98be279bebb.pdf         skip
+simple/b5b6c6405d7b48418bccf97277957664.pdf         skip
+simple/bd0ef57aec16ded45bd89d61b54af0be.pdf         skip
+simple/dbb807a878ac1da6b91ac15c9de4e209.pdf         skip
+
+
+
+# List good hashes for round-trips here.
+
+repaginate/06c86654f9a77e82f9adaa0086fc391c.pdf 848966fe40a1e3de842f82700dc6d67b
+repaginate/08f69084d72dabc5dfdcf5c1ff2a719f.pdf b8c60878b0e0ce81cb6e8777038166b1
+repaginate/09715ec1a7b0f3a7ae02b3046f627b9f.pdf daf7cff9c0a15bbb347489f9fbda25f8
+repaginate/0a61de50b5ee0ea4d5d69c95dab817a3.pdf c6cd38b1131c4b856f60ebfcf51da6f5
+repaginate/1975ef8db7355b1d691bc79d0749574b.pdf 53e5510be27db134edf3cf23873914af
+repaginate/1c2af1d2b0db6cac3c8e558a26efd38b.pdf 20dc3be2affe9082564c01b1146d7598
+repaginate/1f5dd128c3757420a881a155f2f8ace3.pdf 019aead1450842406a04c508243e5161
+repaginate/22628a7ed578b622520325673ab2a4f2.pdf 255776a6956918c7b324dede711680ae
+repaginate/2ac7c68e26a8ef797aead15e4875cc6d.pdf e7344551183415d6257e2cab2aef4a61
+repaginate/295d26e61a85635433f8e4b768953f60.pdf 13ece51f4d2ad25707982765abbcd789
+repaginate/2fac0d9a189ca5fcef8626153d050be8.pdf 95fe3d9258ace5bdccb95a55c2c8cb22
+repaginate/319c998910453bc44d40c7748cd2cb79.pdf c1a19d1acc3f172711bdbea000cf392e
+repaginate/35df0b8cff4afec0c08f08c6a5bc9857.pdf 3568e1c885a461b350c790ec5b729af3
+repaginate/365b9c95574ee8944370fe286905d0e8.pdf 84e5fc0d4f30ff8db05780fd244d9cf0
+repaginate/4805fdcd7e142e8df3c04c6ba06025af.pdf 3b5b8254dc99c2f0f62fe2afa42fad4e
+repaginate/49e31fd074eca6af981d78d42d0078ec.pdf 77fd3fa86c7c0166a373b66cfef357d2
+repaginate/536dfc6fbadd87c03eb59375d091eb53.pdf d0b7467d7bd6c7f73b7764b06c0be1aa
+repaginate/569f8094597bbe5b58efc3a7c6e14e87.pdf 6b0ab50c247ca43b70b2b2f27ee2c1a2
+repaginate/5f0cff36d0ad74536a6513a98a755016.pdf b65c2557988db8625c0761bab1d131f1
+repaginate/5f265db2736850782aeaba2571a3c749.pdf 9bb5644ede0ee7cf99642729eda76686
+repaginate/6a42c8c79b807bf164d31071749e07b0.pdf 33a231263e1a4203338b7b1052fc0091
+repaginate/6f3a4de5c68ba3b5093e9b54b7c4e9f4.pdf 93419e831e436d9093a153f35d3441c3
+repaginate/7037a992b80b60f0294016037baa9292.pdf dd41b0104f185206b51e7ffe5b07d261
+repaginate/707e3e2d17cbe9ec2273414b3b63f333.pdf 6c65526ab372d72cb185933e3d2584ef
+repaginate/71a751ce2d93a6a5d6ff21735b701fb7.pdf a825f06c934319b93474902fcf300cd2
+repaginate/72eb207b8f882618899aa7a65d3cecda.pdf 0b64f19a8a39fadfa2a3eec3f1a01233
+repaginate/97ba0a239cefa0dc727c2f1be050ec6c.pdf a94fe7183ce8979174b2ac16dcd9b1ea
+repaginate/9d8626d18b1d8807d271e6ffc409446a.pdf cdfcf8add1af9e612ba1a2ee06a6a273
+repaginate/9f98322c243fe67726d56ccfa8e0885b.pdf 69503ac140a1e4f1322f9350646e3dae
+repaginate/c55eb9a13859a7fbddd8af9c16eba3a7.pdf b0d1f3925423f9c3ecf4a47baa949f75
+repaginate/c5c895deecf7a7565393587e0d61be2b.pdf 59e350c6f7d7b89fab36a4019bb526fd
+repaginate/d2f0b2086160d4f3d325c79a5dc1fb4d.pdf 3623b7f200818c63cb6838f9678a4840
+repaginate/d6fd9567078b48c86710e9c49173781f.pdf 874b532f61139261f71afb5987dd2a68
+repaginate/e9ab02aa769f4c040a6fa52f00d6e3f0.pdf 7d3c3ae13cc7d53e7fa6ef046e15dbaa
+repaginate/ec00d5825f47b9d0faa953b1709163c3.pdf 8e6a481476c2b3bdd64ce8e36f8fe273
+repaginate/ed81787b83cc317c9f049643b853bea3.pdf 4636b68f294302417b81aaaadde1c73d
+
+simple/06c86654f9a77e82f9adaa0086fc391c.pdf 6e2a2e063de895d28dfea9aacb9fe469
+simple/08f69084d72dabc5dfdcf5c1ff2a719f.pdf 5a41601f6033356539e623091a3f79ef
+simple/0a61de50b5ee0ea4d5d69c95dab817a3.pdf 182712dd5be8aebd29decb57cf530334
+simple/09715ec1a7b0f3a7ae02b3046f627b9f.pdf c4e4b3b725bd5fc3b008f1ac6251ad1c
+simple/1975ef8db7355b1d691bc79d0749574b.pdf 475c28c9588f3a7f6110d30f391758c4
+simple/1c2af1d2b0db6cac3c8e558a26efd38b.pdf 3f17f19fd92adf01998bb13a0ee52b92
+simple/1f5dd128c3757420a881a155f2f8ace3.pdf b0d01f9d6ac156326aeb14b940aa73e7
+simple/22628a7ed578b622520325673ab2a4f2.pdf 1163cec415728899e997a29be465d02d
+simple/295d26e61a85635433f8e4b768953f60.pdf fe3b8960c7f877db05c7cd12c9c6e097
+simple/2ac7c68e26a8ef797aead15e4875cc6d.pdf 2623eae06eada9587574f8ddd7fc80fa
+simple/2fac0d9a189ca5fcef8626153d050be8.pdf 458501ecda909b00262b9654f0b09ebf
+simple/319c998910453bc44d40c7748cd2cb79.pdf 8c84e36ec1db8c1dbfaa312646e000b4
+simple/35df0b8cff4afec0c08f08c6a5bc9857.pdf 0a2926c23ad916c449d5dadcfa9d38ef
+simple/365b9c95574ee8944370fe286905d0e8.pdf cf3bfac41f410bf5bd657e3f906dfbc6
+simple/4805fdcd7e142e8df3c04c6ba06025af.pdf 3b5b8254dc99c2f0f62fe2afa42fad4e
+simple/49e31fd074eca6af981d78d42d0078ec.pdf 2c316537a5b0917634cbbdc5b91511df
+simple/536dfc6fbadd87c03eb59375d091eb53.pdf 319851765c70ba103c4191f7ec2148db
+simple/569f8094597bbe5b58efc3a7c6e14e87.pdf 025f1bf95cc537c36b8c3a044758b86c
+simple/5f0cff36d0ad74536a6513a98a755016.pdf 8476fd75e75394fcbbe02816d0640e7d
+simple/5f265db2736850782aeaba2571a3c749.pdf d4d2e93ab22e866c86e32da84421f6f9
+simple/6a42c8c79b807bf164d31071749e07b0.pdf 221fec351c925a43f5f409fe03d90013
+simple/6f3a4de5c68ba3b5093e9b54b7c4e9f4.pdf fe8dd16dd7fef40338140e0610d0cbbf
+simple/7037a992b80b60f0294016037baa9292.pdf 6a2ef24e5f74dd74969ff8cefdfc6a05
+simple/707e3e2d17cbe9ec2273414b3b63f333.pdf 4bdf1e57a96ce42717110b4e55098c1a
+simple/71a751ce2d93a6a5d6ff21735b701fb7.pdf a825f06c934319b93474902fcf300cd2
+simple/72eb207b8f882618899aa7a65d3cecda.pdf 4ce7ff29531cc417c26389af28dc1c5e
+simple/97ba0a239cefa0dc727c2f1be050ec6c.pdf c24873bab85b8ecc7c5433d8d802bceb
+simple/9d8626d18b1d8807d271e6ffc409446a.pdf 2358d654bf20d2b9d179ab009a615c4e
+simple/9f98322c243fe67726d56ccfa8e0885b.pdf 9290b4c32f005e1e4c7f431955246c4c
+simple/c55eb9a13859a7fbddd8af9c16eba3a7.pdf 6b406128e0ed1ac23dc5a0ee34d1f717
+simple/c5c895deecf7a7565393587e0d61be2b.pdf 2cc3c75e56d5dd562ca5b1f994bd9d5c
+simple/d2f0b2086160d4f3d325c79a5dc1fb4d.pdf 2083f0e55cf06d88df02956a21bfef23
+simple/d6fd9567078b48c86710e9c49173781f.pdf 77464ec5cfdacb61a73b506bc4945631
+simple/e9ab02aa769f4c040a6fa52f00d6e3f0.pdf 5bc96989bc4f4b6438da953443336124
+simple/ec00d5825f47b9d0faa953b1709163c3.pdf 708f66049169c28ac39b0553908dc318
+simple/ed81787b83cc317c9f049643b853bea3.pdf c227d627217dc6808c50e80063734d27
+
diff --git a/tests/myprofile.py b/tests/myprofile.py
new file mode 100644
index 0000000..af18a64
--- /dev/null
+++ b/tests/myprofile.py
@@ -0,0 +1,5 @@
+import cProfile
+import unittest
+import test_roundtrip
+
+cProfile.run('unittest.main(test_roundtrip)')
diff --git a/tests/test_examples.py b/tests/test_examples.py
new file mode 100755
index 0000000..baa98a6
--- /dev/null
+++ b/tests/test_examples.py
@@ -0,0 +1,195 @@
+#! /usr/bin/env python
+
+# A part of pdfrw (https://github.com/pmaupin/pdfrw)
+# Copyright (C) 2015 Patrick Maupin, Austin, Texas
+# MIT license -- See LICENSE.txt for details
+
+'''
+Run from the directory above like so:
+
+   python -m tests.test_examples
+
+A PDF that has been determined to be good or bad
+should be added to expected.txt with either a good
+checksum, or just the word "fail".
+
+These tests are incomplete, but they allow us to try
+out various PDFs.  There is a collection of difficult
+PDFs available on github.
+
+In order to use them:
+
+  1) Insure that github.com/pmaupin/static_pdfs is on your path.
+
+  2) Use the imagemagick compare program to look at differences
+     between the static_pdfs/global directory and the tmp_results
+     directory after you run this.
+
+
+'''
+import sys
+import os
+import hashlib
+import subprocess
+import static_pdfs
+import expected
+
+from pdfrw.py23_diffs import convert_store
+from pdfrw import PdfReader, PdfWriter
+
+try:
+    import unittest2 as unittest
+except ImportError:
+    import unittest
+
+
+prog_dir = os.path.join(expected.root_dir, '..', 'examples', '%s.py')
+prog_dir = os.path.abspath(prog_dir)
+dstdir = os.path.join(expected.result_dir, 'examples')
+hashfile = os.path.join(expected.result_dir, 'hashes.txt')
+
+lookup = static_pdfs.pdffiles[0]
+lookup = dict((os.path.basename(x)[:-4], x) for x in lookup)
+
+
+class TestOnePdf(unittest.TestCase):
+
+    def do_test(self, params, prev_results=[''], scrub=False):
+        params = params.split()
+        hashkey = 'examples/%s' % '_'.join(params)
+        params = [lookup.get(x, x) for x in params]
+        progname = params[0]
+        params[0] = prog_dir % progname
+        srcf = params[1]
+        params.insert(0, sys.executable)
+        subdir, progname = os.path.split(progname)
+        subdir = os.path.join(dstdir, subdir)
+        if not os.path.exists(subdir):
+            os.makedirs(subdir)
+        os.chdir(subdir)
+        dstf = '%s.%s' % (progname, os.path.basename(srcf))
+        scrub = scrub and dstf
+        dstf = dstf if not scrub else 'final.%s' % dstf
+        hash = '------no-file-generated---------'
+        expects = expected.results[hashkey]
+
+        # If the test has been deliberately skipped,
+        # we are done.  Otherwise, execute it even
+        # if we don't know about it yet, so we have
+        # results to compare.
+
+        result = 'fail'
+        size = 0
+        try:
+            if 'skip' in expects:
+                result = 'skip requested'
+                return self.skipTest(result)
+            elif 'xfail' in expects:
+                result = 'xfail requested'
+                return self.fail(result)
+
+            exists = os.path.exists(dstf)
+            if expects or not exists:
+                if exists:
+                    os.remove(dstf)
+                if scrub and os.path.exists(scrub):
+                    os.remove(scrub)
+                subprocess.call(params)
+                if scrub:
+                    PdfWriter().addpages(PdfReader(scrub).pages).write(dstf)
+            with open(dstf, 'rb') as f:
+                data = f.read()
+            size = len(data)
+            if data:
+                hash = hashlib.md5(data).hexdigest()
+                lookup[hash] = dstf
+                prev_results[0] = hash
+            else:
+                os.remove(dstf)
+            if expects:
+                if len(expects) == 1:
+                    expects, = expects
+                    self.assertEqual(hash, expects)
+                else:
+                    self.assertIn(hash, expects)
+                result = 'pass'
+            else:
+                result = 'skip'
+                self.skipTest('No hash available')
+        finally:
+            result = '%8d %-20s %s %s\n' % (size, result, hashkey, hash)
+            with open(hashfile, 'ab') as f:
+                f.write(convert_store(result))
+
+    def test_4up(self):
+        self.do_test('4up b1c400de699af29ea3f1983bb26870ab')
+
+    def test_booklet_unspread(self):
+        prev = [None]
+        self.do_test('booklet b1c400de699af29ea3f1983bb26870ab', prev)
+        if prev[0] is not None:
+            self.do_test('unspread ' + prev[0])
+            self.do_test('extract  ' + prev[0])
+
+    def test_print_two(self):
+        self.do_test('print_two b1c400de699af29ea3f1983bb26870ab')
+
+    def test_watermarks(self):
+        self.do_test('watermark b1c400de699af29ea3f1983bb26870ab '
+                     '06c86654f9a77e82f9adaa0086fc391c')
+        self.do_test('watermark b1c400de699af29ea3f1983bb26870ab '
+                     '06c86654f9a77e82f9adaa0086fc391c -u')
+
+    def test_subset(self):
+        self.do_test('subset b1c400de699af29ea3f1983bb26870ab 1-3 5')
+
+    def test_alter(self):
+        self.do_test('alter b1c400de699af29ea3f1983bb26870ab')
+
+    def test_cat(self):
+        self.do_test('cat b1c400de699af29ea3f1983bb26870ab '
+                     '06c86654f9a77e82f9adaa0086fc391c')
+
+    def test_rotate(self):
+        self.do_test('rotate 707e3e2d17cbe9ec2273414b3b63f333 '
+                     '270 1-4 7-8 10-50 52-56')
+
+    def test_poster(self):
+        prev = [None]
+        self.do_test('subset 1975ef8db7355b1d691bc79d0749574b 21', prev)
+        self.do_test('rotate %s 90 1' % prev[0], prev)
+        self.do_test('poster %s' % prev[0], prev)
+
+    def test_extract(self):
+        self.do_test('extract 1975ef8db7355b1d691bc79d0749574b')
+        self.do_test('extract c5c895deecf7a7565393587e0d61be2b')
+
+    def test_rl1_4up(self):
+        if sys.version_info < (2, 7):
+            return
+        self.do_test('rl1/4up     b1c400de699af29ea3f1983bb26870ab',
+                     scrub=True)
+
+    def test_rl1_booklet(self):
+        if sys.version_info < (2, 7):
+            return
+        self.do_test('rl1/booklet b1c400de699af29ea3f1983bb26870ab',
+                     scrub=True)
+
+    def test_rl1_subset(self):
+        if sys.version_info < (2, 7):
+            return
+        self.do_test('rl1/subset  b1c400de699af29ea3f1983bb26870ab 3 5',
+                     scrub=True)
+
+    def test_rl1_platypus(self):
+        if sys.version_info < (2, 7):
+            return
+        self.do_test('rl1/platypus_pdf_template b1c400de699af29ea3f1983bb26870ab',
+                     scrub=True)
+
+def main():
+    unittest.main()
+
+if __name__ == '__main__':
+    main()
diff --git a/tests/test_pdfstring.py b/tests/test_pdfstring.py
index 4dcd2df..fce47ef 100644
--- a/tests/test_pdfstring.py
+++ b/tests/test_pdfstring.py
@@ -1,3 +1,5 @@
+#! /usr/bin/env python
+
 '''
 Run from the directory above like so:
 python -m tests.test_pdfstring
@@ -12,11 +14,11 @@ class TestEncoding(unittest.TestCase):
 
     @staticmethod
     def decode(value):
-        return pdfrw.pdfobjects.PdfString(value).decode()
+        return pdfrw.objects.PdfString(value).decode()
 
     @staticmethod
     def encode(value):
-        return str(pdfrw.pdfobjects.PdfString.encode(value))
+        return str(pdfrw.objects.PdfString.encode(value))
 
     @classmethod
     def encode_decode(cls, value):
diff --git a/tests/test_roundtrip.py b/tests/test_roundtrip.py
new file mode 100755
index 0000000..cb3645e
--- /dev/null
+++ b/tests/test_roundtrip.py
@@ -0,0 +1,132 @@
+#! /usr/bin/env python
+
+# A part of pdfrw (https://github.com/pmaupin/pdfrw)
+# Copyright (C) 2015 Patrick Maupin, Austin, Texas
+# MIT license -- See LICENSE.txt for details
+
+'''
+Run from the directory above like so:
+
+   python -m tests.test_roundtrip
+
+A PDF that has been determined to be good or bad
+should be added to expected.txt with either a good
+checksum, or just the word "fail".
+
+These tests are incomplete, but they allow us to try
+out various PDFs.  There is a collection of difficult
+PDFs available on github.
+
+In order to use them:
+
+  1) Insure that github.com/pmaupin/static_pdfs is on your path.
+
+  2) Use the imagemagick compare program to look at differences
+     between the static_pdfs/global directory and the tmp_results
+     directory after you run this.
+
+
+'''
+import os
+import hashlib
+import pdfrw
+import static_pdfs
+import expected
+
+from pdfrw.py23_diffs import convert_store
+
+try:
+    import unittest2 as unittest
+except ImportError:
+    import unittest
+
+
+class TestOnePdf(unittest.TestCase):
+
+    def roundtrip(self, testname, basename, srcf, decompress=False,
+                  compress=False, repaginate=False):
+        dstd = os.path.join(expected.result_dir, testname)
+        if not os.path.exists(dstd):
+            os.makedirs(dstd)
+        dstf = os.path.join(dstd, basename)
+        hashfile = os.path.join(expected.result_dir, 'hashes.txt')
+        hashkey = '%s/%s' % (testname, basename)
+        hash = '------no-file-generated---------'
+        expects = expected.results[hashkey]
+
+        # If the test has been deliberately skipped,
+        # we are done.  Otherwise, execute it even
+        # if we don't know about it yet, so we have
+        # results to compare.
+
+        result = 'fail'
+        size = 0
+        try:
+            if 'skip' in expects:
+                result = 'skip requested'
+                return self.skipTest(result)
+            elif 'xfail' in expects:
+                result = 'xfail requested'
+                return self.fail(result)
+
+            exists = os.path.exists(dstf)
+            if expects or not exists:
+                if exists:
+                    os.remove(dstf)
+                trailer = pdfrw.PdfReader(srcf, decompress=decompress,
+                                          verbose=False)
+                if trailer.Encrypt:
+                    result = 'skip -- encrypt'
+                    hash = '------skip-encrypt-no-file------'
+                    return self.skipTest('File encrypted')
+                writer = pdfrw.PdfWriter(compress=compress)
+                if repaginate:
+                    writer.addpages(trailer.pages)
+                    trailer = None
+                writer.write(dstf, trailer)
+            with open(dstf, 'rb') as f:
+                data = f.read()
+            size = len(data)
+            if data:
+                hash = hashlib.md5(data).hexdigest()
+            else:
+                os.remove(dstf)
+            if expects:
+                if len(expects) == 1:
+                    expects, = expects
+                    self.assertEqual(hash, expects)
+                else:
+                    self.assertIn(hash, expects)
+                result = 'pass'
+            else:
+                result = 'skip'
+                self.skipTest('No hash available')
+        finally:
+            result = '%8d %-20s %s %s\n' % (size, result, hashkey, hash)
+            with open(hashfile, 'ab') as f:
+                f.write(convert_store(result))
+
+
+def build_tests():
+    def test_closure(*args, **kw):
+        def test(self):
+            self.roundtrip(*args, **kw)
+        return test
+    for mytest, repaginate in (
+            ('simple', False),
+            ('repaginate', True)
+            ):
+        for srcf in static_pdfs.pdffiles[0]:
+            basename = os.path.basename(srcf)
+            test_name = 'test_%s_%s' % (mytest, basename)
+            test = test_closure(mytest, basename, srcf,
+                                repaginate=repaginate)
+            setattr(TestOnePdf, test_name, test)
+build_tests()
+
+
+def main():
+    unittest.main()
+
+if __name__ == '__main__':
+    main()