pywb/tests_disabled/test_rewrite_content.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
# full seq
#>>> print RewriteContent._decode_buff(b'\xce\xb4\xce\xbf\xce\xba', BytesIO(b''), 'utf-8')
δοκ

# read split bytes, read rest
#>>> b = BytesIO('\xbf\xce\xba')
#>>> sys.stdout.write(RewriteContent._decode_buff(b'\xce\xb4\xce', b, 'utf-8')); sys.stdout.write(RewriteContent._decode_buff(b.read(), b, 'utf-8'))
δοκ

# invalid seq
#>>> print RewriteContent._decode_buff(b'\xce\xb4\xce', BytesIO(b'\xfe'), 'utf-8')
Traceback (most recent call last):
"UnicodeDecodeError: 'utf8' codec can't decode byte 0xce in position 2: invalid continuation byte"


"""

from pywb.rewrite.rewrite_content import RewriteContent
from io import BytesIO
import sys


def test_type_detect_1():
    text_type, stream = RewriteContent._resolve_text_type('js', 'html', BytesIO(b' <html></html>'))
    assert(text_type == 'html')
    assert(stream.read() == b' <html></html>')


def test_type_detect_2():
    text_type, stream = RewriteContent._resolve_text_type('js', 'html', BytesIO(b' function() { return 0; }'))
    assert(text_type == 'js')
    assert(stream.read() == b' function() { return 0; }')


if __name__ == "__main__":
    import doctest
    doctest.testmod()
refactor: simplify rewrite_content and replay_views, remove redundant code.. everything goes through rewrite_content(), is sanitized (for transfer encoding) if needed additional testing for decode_buff fix failed_files bug in resolvingloader, add tests 2014-04-03 12:44:00 -07:00			`#!/usr/bin/env python`
			`# -- coding: utf-8 --`

py3: all tests pass, at last! but not yet py2... need to resolve encoding in rewriting issues 2016-02-23 13:26:53 -08:00			`"""`
refactor: simplify rewrite_content and replay_views, remove redundant code.. everything goes through rewrite_content(), is sanitized (for transfer encoding) if needed additional testing for decode_buff fix failed_files bug in resolvingloader, add tests 2014-04-03 12:44:00 -07:00			`# full seq`
py3: all tests pass, at last! but not yet py2... need to resolve encoding in rewriting issues 2016-02-23 13:26:53 -08:00			`#>>> print RewriteContent._decode_buff(b'\xce\xb4\xce\xbf\xce\xba', BytesIO(b''), 'utf-8')`
refactor: simplify rewrite_content and replay_views, remove redundant code.. everything goes through rewrite_content(), is sanitized (for transfer encoding) if needed additional testing for decode_buff fix failed_files bug in resolvingloader, add tests 2014-04-03 12:44:00 -07:00			`δοκ`

			`# read split bytes, read rest`
rewrite: content detection for specific case: if content type is html and mod type is css or js, peek stream to determine actual type. Addresses #31 in part. Fix typo in wb_frame.js 2014-12-26 13:08:35 -08:00			`#>>> b = BytesIO('\xbf\xce\xba')`
py3: all tests pass, at last! but not yet py2... need to resolve encoding in rewriting issues 2016-02-23 13:26:53 -08:00			`#>>> sys.stdout.write(RewriteContent._decode_buff(b'\xce\xb4\xce', b, 'utf-8')); sys.stdout.write(RewriteContent._decode_buff(b.read(), b, 'utf-8'))`
refactor: simplify rewrite_content and replay_views, remove redundant code.. everything goes through rewrite_content(), is sanitized (for transfer encoding) if needed additional testing for decode_buff fix failed_files bug in resolvingloader, add tests 2014-04-03 12:44:00 -07:00			`δοκ`

			`# invalid seq`
py3: all tests pass, at last! but not yet py2... need to resolve encoding in rewriting issues 2016-02-23 13:26:53 -08:00			`#>>> print RewriteContent._decode_buff(b'\xce\xb4\xce', BytesIO(b'\xfe'), 'utf-8')`
refactor: simplify rewrite_content and replay_views, remove redundant code.. everything goes through rewrite_content(), is sanitized (for transfer encoding) if needed additional testing for decode_buff fix failed_files bug in resolvingloader, add tests 2014-04-03 12:44:00 -07:00			`Traceback (most recent call last):`
rewrite: content detection for specific case: if content type is html and mod type is css or js, peek stream to determine actual type. Addresses #31 in part. Fix typo in wb_frame.js 2014-12-26 13:08:35 -08:00			`"UnicodeDecodeError: 'utf8' codec can't decode byte 0xce in position 2: invalid continuation byte"`


refactor: simplify rewrite_content and replay_views, remove redundant code.. everything goes through rewrite_content(), is sanitized (for transfer encoding) if needed additional testing for decode_buff fix failed_files bug in resolvingloader, add tests 2014-04-03 12:44:00 -07:00			`"""`

			`from pywb.rewrite.rewrite_content import RewriteContent`
			`from io import BytesIO`
			`import sys`

py3: all tests pass, at last! but not yet py2... need to resolve encoding in rewriting issues 2016-02-23 13:26:53 -08:00

			`def test_type_detect_1():`
			`text_type, stream = RewriteContent._resolve_text_type('js', 'html', BytesIO(b' <html></html>'))`
			`assert(text_type == 'html')`
			`assert(stream.read() == b' <html></html>')`


			`def test_type_detect_2():`
			`text_type, stream = RewriteContent._resolve_text_type('js', 'html', BytesIO(b' function() { return 0; }'))`
			`assert(text_type == 'js')`
			`assert(stream.read() == b' function() { return 0; }')`





refactor: simplify rewrite_content and replay_views, remove redundant code.. everything goes through rewrite_content(), is sanitized (for transfer encoding) if needed additional testing for decode_buff fix failed_files bug in resolvingloader, add tests 2014-04-03 12:44:00 -07:00			`if __name__ == "__main__":`
			`import doctest`
			`doctest.testmod()`