Merge branch 'develop'

CHANGES.rst

@@ -1,3 +1,12 @@
+pywb 0.5.1 changelist
+~~~~~~~~~~~~~~~~~~~~~
+minor fixes:
+
+* cdxindexer accepts unicode filenames, encodes via sys encoding
+
+* SCRIPT_NAME now defaults to '' if not present
+
+
 pywb 0.5.0 changelist
 ~~~~~~~~~~~~~~~~~~~~~
 

README.rst

@@ -1,4 +1,4 @@
-PyWb 0.5.0
+PyWb 0.5.1
 ==========
 
 .. image:: https://travis-ci.org/ikreymer/pywb.png?branch=master

pywb/framework/archivalrouter.py

@@ -49,12 +49,13 @@ class ArchivalRouter(object):
     def parse_request(self, route, env, matcher, coll, request_uri,
                       use_abs_prefix=False):
         matched_str = matcher.group(0)
+        rel_prefix = env.get('SCRIPT_NAME', '') + '/'
+
         if matched_str:
-            rel_prefix = env['SCRIPT_NAME'] + '/' + matched_str + '/'
+            rel_prefix += matched_str + '/'
             # remove the '/' + rel_prefix part of uri
             wb_url_str = request_uri[len(matched_str) + 2:]
         else:
-            rel_prefix = env['SCRIPT_NAME'] + '/'
             # the request_uri is the wb_url, since no coll
             wb_url_str = request_uri[1:]
 
@@ -157,7 +158,7 @@ class ReferRedirect:
 
         path = ref_split.path
 
-        app_path = env['SCRIPT_NAME']
+        app_path = env.get('SCRIPT_NAME', '')
 
         if app_path:
             # must start with current app name, if not root

pywb/warc/cdxindexer.py

@@ -109,7 +109,6 @@ def cdx_filename(filename):
 
 #=================================================================
 def write_multi_cdx_index(output, inputs, **options):
-
     # write one cdx per dir
     if output != '-' and os.path.isdir(output):
         for fullpath, filename in iter_file_or_dir(inputs):
@@ -145,6 +144,9 @@ def write_multi_cdx_index(output, inputs, **options):
 def write_cdx_index(outfile, infile, filename, **options):
     writer_cls = options.get('writer_cls')
 
+    if type(filename) is unicode:
+        filename = filename.encode(sys.getfilesystemencoding())
+
     if writer_cls:
         pass
     elif options.get('sort'):

pywb/warc/test/test_indexing.py

@@ -130,8 +130,8 @@ com,example)/?example=1 20140103030321 http://example.com?example=1 text/html 20
 org,iana)/domains/example 20140128051539 http://www.iana.org/domains/example text/html 302 JZ622UA23G5ZU6Y3XAKH4LINONUEICEG - - 577 2907 example.warc.gz
 4
 
-# test writing to temp dir
+# test writing to temp dir, also use unicode filename
->>> cli_lines_with_dir(TEST_WARC_DIR + 'example.warc.gz')
+>>> cli_lines_with_dir(unicode(TEST_WARC_DIR + 'example.warc.gz'))
 example.cdx
 com,example)/?example=1 20140103030321 http://example.com?example=1 text/html 200 B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A - - 1043 333 example.warc.gz
 org,iana)/domains/example 20140128051539 http://www.iana.org/domains/example text/html 302 JZ622UA23G5ZU6Y3XAKH4LINONUEICEG - - 577 2907 example.warc.gz

pywb/webapp/replay_views.py

@@ -67,8 +67,7 @@ class BaseContentView(object):
         # (not supported in proxy mode)
         if (self.is_frame_mode and wbrequest.wb_url and
             not wbrequest.wb_url.mod and
-            not wbrequest.options['is_proxy'] and
+            not wbrequest.options['is_proxy']):
-            not wbrequest.options.get('is_timegate', False)):
 
             embed_url = wbrequest.wb_url.to_str(mod=self._mp_mod)
             timestamp = datetime_to_timestamp(datetime.datetime.utcnow())

setup.py

@@ -34,7 +34,7 @@ class PyTest(TestCommand):
 
 setup(
     name='pywb',
-    version='0.5.0',
+    version='0.5.1',
     url='https://github.com/ikreymer/pywb',
     author='Ilya Kreymer',
     author_email='ikreymer@gmail.com',