def testUnreasonablyLongFile(self):
contents = '\n' * (filecontent.SOURCE_FILE_MAX_LINES + 2)
_contents, is_binary, is_long = filecontent.DecodeFileContents(
contents)
self.assertFalse(is_binary)
self.assertTrue(is_long)
contents = '\n' * 100
_contents, is_binary, is_long = filecontent.DecodeFileContents(
contents)
self.assertFalse(is_binary)
self.assertFalse(is_long)
def GatherPageData(self, mr):
"""Build up a dictionary of data values to use when rendering the page.
Args:
mr: commonly used info parsed from the request.
Returns:
Dict of values used by EZT for rendering the page.
"""
issue, comment = self._GetIssueAndComment(mr)
message_body_unicode, is_binary, _is_long = (
filecontent.DecodeFileContents(comment.inbound_message))
# Take out the iso8859-1 non-breaking-space characters that gmail
# inserts between consecutive spaces when quoting text in a reply.
# You can see this in gmail by sending a plain text reply to a
# message that had multiple spaces on some line, then use the
# "Show original" menu item to view your reply, you will see "=A0".
#message_body_unicode = message_body_unicode.replace(u'\xa0', u' ')
page_data = {
'local_id': issue.local_id,
'seq': comment.sequence,
'is_binary': ezt.boolean(is_binary),
'message_body': message_body_unicode,
}
return page_data
def testFileIsTextByPath(self):
bin_string = ''.join([chr(c) for c in range(122, 252)] * 100)
unicode_str = (
u'Some non-ascii chars - '
u'\xa2\xfa\xb6\xe7\xfc\xea\xd0\xf4\xe6\xf0\xce\xf6\xbe')
long_line = (unicode_str * 100)[:filecontent._MAX_SOURCE_LINE_LEN_LOWER+1]
long_line = long_line.encode('iso-8859-1')
for contents in [bin_string, long_line]:
self.assertTrue(filecontent.DecodeFileContents(contents, path=None)[1])
self.assertTrue(filecontent.DecodeFileContents(contents, path='')[1])
self.assertTrue(filecontent.DecodeFileContents(contents, path='foo')[1])
self.assertTrue(
filecontent.DecodeFileContents(contents, path='foo.bin')[1])
self.assertTrue(
filecontent.DecodeFileContents(contents, path='foo.zzz')[1])
for path in ['a/b/Makefile.in', 'README', 'a/file.js', 'b.txt']:
self.assertFalse(
filecontent.DecodeFileContents(contents, path=path)[1])
def IsBinary(self, contents):
_contents, is_binary, _is_long = (
filecontent.DecodeFileContents(contents))
return is_binary
def testFileIsBinaryByCommonExtensions(self):
contents = 'this is not examined'
self.assertTrue(filecontent.DecodeFileContents(
contents, path='junk.zip')[1])
self.assertTrue(filecontent.DecodeFileContents(
contents, path='JUNK.ZIP')[1])
self.assertTrue(filecontent.DecodeFileContents(
contents, path='/build/HelloWorld.o')[1])
self.assertTrue(filecontent.DecodeFileContents(
contents, path='/build/Hello.class')[1])
self.assertTrue(filecontent.DecodeFileContents(
contents, path='/trunk/libs.old/swing.jar')[1])
self.assertFalse(filecontent.DecodeFileContents(
contents, path='HelloWorld.cc')[1])
self.assertFalse(filecontent.DecodeFileContents(
contents, path='Hello.java')[1])
self.assertFalse(filecontent.DecodeFileContents(
contents, path='README')[1])
self.assertFalse(filecontent.DecodeFileContents(
contents, path='READ.ME')[1])
self.assertFalse(filecontent.DecodeFileContents(
contents, path='README.txt')[1])
self.assertFalse(filecontent.DecodeFileContents(
contents, path='README.TXT')[1])
self.assertFalse(filecontent.DecodeFileContents(
contents, path='/trunk/src/com/monorail/Hello.java')[1])
self.assertFalse(filecontent.DecodeFileContents(
contents, path='/branches/1.2/resource.el')[1])
self.assertFalse(filecontent.DecodeFileContents(
contents, path='/wiki/PageName.wiki')[1])
def GatherPageData(self, mr):
"""Parse the attachment ID from the request and serve its content.
Args:
mr: commonly used info parsed from the request.
Returns:
Dict of values used by EZT for rendering almost the page.
"""
with mr.profiler.Phase('get issue, comment, and attachment'):
try:
attachment, issue = tracker_helpers.GetAttachmentIfAllowed(
mr, self.services)
except exceptions.NoSuchIssueException:
webapp2.abort(404, 'issue not found')
except exceptions.NoSuchAttachmentException:
webapp2.abort(404, 'attachment not found')
except exceptions.NoSuchCommentException:
webapp2.abort(404, 'comment not found')
content = []
if attachment.gcs_object_id:
bucket_name = app_identity.get_default_gcs_bucket_name()
full_path = '/' + bucket_name + attachment.gcs_object_id
logging.info("reading gcs: %s" % full_path)
with cloudstorage.open(full_path, 'r') as f:
content = f.read()
filesize = len(content)
# This servlet only displays safe textual attachments. The user should
# not have been given a link to this servlet for any other kind.
if not attachment_helpers.IsViewableText(attachment.mimetype,
filesize):
self.abort(400, 'not a text file')
u_text, is_binary, too_large = filecontent.DecodeFileContents(content)
lines = prettify.PrepareSourceLinesForHighlighting(
u_text.encode('utf8'))
config = self.services.config.GetProjectConfig(mr.cnxn, mr.project_id)
granted_perms = tracker_bizobj.GetGrantedPerms(issue,
mr.auth.effective_ids,
config)
page_perms = self.MakePagePerms(mr,
issue,
permissions.DELETE_ISSUE,
permissions.CREATE_ISSUE,
granted_perms=granted_perms)
page_data = {
'issue_tab_mode': 'issueDetail',
'local_id': issue.local_id,
'filename': attachment.filename,
'filesize': template_helpers.BytesKbOrMb(filesize),
'file_lines': lines,
'is_binary': ezt.boolean(is_binary),
'too_large': ezt.boolean(too_large),
'code_reviews': None,
'page_perms': page_perms,
}
if is_binary or too_large:
page_data['should_prettify'] = ezt.boolean(False)
else:
page_data.update(
prettify.BuildPrettifyData(len(lines), attachment.filename))
return page_data