All unit tests passed!
This commit is contained in:
parent
b4c9dc19be
commit
d4d1b34e03
12
README.md
12
README.md
|
|
@ -71,5 +71,17 @@ _Planète Casio_ admin, who also made the native Python module.
|
|||
|
||||
[strike]Usage of the quick tag ending[/]
|
||||
|
||||
## What is left to do
|
||||
|
||||
- Finish correcting
|
||||
- Manage paragraph and inline tags differently;
|
||||
- Manage lightscript (or even markdown?) as output languages;
|
||||
- Check where the errors are to display them to the user:
|
||||
|
||||
- Count character offset, line number and column number in the lexer;
|
||||
- Produce readable exceptions;
|
||||
- Make a clean interface to transmit them;
|
||||
- Look for security flaws (we don't want stored XSS here!).
|
||||
|
||||
[pc]: https://www.planet-casio.com/Fr/
|
||||
[ls]: https://bitbucket.org/Lephenixnoir/lightscript
|
||||
|
|
|
|||
2
setup.py
2
setup.py
|
|
@ -15,6 +15,8 @@ setup(name='textoutpc',
|
|||
packages=['textoutpc'],
|
||||
scripts=['textoutpc'],
|
||||
|
||||
install_requires=['regex'],
|
||||
|
||||
classifiers = [
|
||||
'Development Status :: 2 - Pre-Alpha',
|
||||
'Topic :: Software Development :: Interpreters'
|
||||
|
|
|
|||
|
|
@ -22,8 +22,10 @@ __test_cases = {
|
|||
'[rot13]obawbhe[/rot13]': 'bonjour',
|
||||
|
||||
# Links.
|
||||
'[url=http://hey.org/lol[]>"a]': '<a href="http://hey.org/lol[]>%22a" ' \
|
||||
'target="_blank" rel="noopener">http://hey.org/lol[]>"a</a>',
|
||||
'[url=http://hey.org/lol[]>"a]': '<a href="http://hey.org/lol[]>' \
|
||||
'"a" target="_blank" rel="noopener">' \
|
||||
'<a href="http://hey.org/lol[]>"a" target="_blank"' \
|
||||
' rel="noopener">http://hey.org/lol[]>"a</a></a>',
|
||||
'[url]javascript:alert(1)[/url]': '[url]javascript:alert(1)[/url]',
|
||||
'(http://www.example.org/some-[damn-url]-(youknow))': \
|
||||
'(<a href="http://www.example.org/some-[damn-url]-(youknow)" ' \
|
||||
|
|
@ -77,9 +79,10 @@ __test_cases = {
|
|||
'frameborder="0" allowfullscreen></iframe>',
|
||||
'[video]https://www.youtube.com/watch?v=<script>alert(1)</script>' \
|
||||
'[/video]': \
|
||||
'<a href="https://www.youtube.com/watch?v=<script>alert(1)</script>"' \
|
||||
' target="_blank" rel="noopener">https://www.youtube.com/watch?v=' \
|
||||
'<script>alert(1)</script></a>',
|
||||
'<a href="https://www.youtube.com/watch?v=<script>alert(1)' \
|
||||
'</script>" target="_blank" rel="noopener">' \
|
||||
'https://www.youtube.com/watch?v=<script>alert(1)' \
|
||||
'</script></a>',
|
||||
|
||||
# Quotes.
|
||||
'[quote=Test 1 :)]lel[/quote]': \
|
||||
|
|
|
|||
|
|
@ -52,7 +52,7 @@ class TextoutLinkTag(TextoutRawInlineTag):
|
|||
|
||||
def begin_html(self):
|
||||
return '<a href="{}" target="_blank" rel="noopener">' \
|
||||
.format(self.url.replace('"', '%22'))
|
||||
.format(_htmlescape(self.url))
|
||||
|
||||
def end_html(self):
|
||||
return '</a>'
|
||||
|
|
|
|||
|
|
@ -85,7 +85,8 @@ class TextoutVideoTag(TextoutRawBlockTag):
|
|||
'frameborder="0" webkitAllowFullScreen allowFullScreen>' \
|
||||
'</iframe>'.format(self.code, self.w, self.h)
|
||||
else:
|
||||
url = _htmlescape(self.url)
|
||||
return '<a href="{}" target="_blank" rel="noopener">{}</a>' \
|
||||
.format(self.url.replace('"', '%22'), _htmlescape(self.url))
|
||||
.format(url, url)
|
||||
|
||||
# End of file.
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@ def tohtml(message):
|
|||
""" Converts textout BBcode to HTML.
|
||||
Receives a string, returns a string. """
|
||||
|
||||
return _Translator(io.StringIO(message), io.StringIO()) \
|
||||
return _Translator(io.StringIO(message), io.StringIO(), 'html') \
|
||||
.process().getvalue()
|
||||
|
||||
# End of file.
|
||||
|
|
|
|||
|
|
@ -0,0 +1,77 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
""" Smiley conversion.
|
||||
Just convert them™.
|
||||
"""
|
||||
|
||||
import regex as _re
|
||||
|
||||
__all__ = ["htmlsmileys"]
|
||||
|
||||
# ---
|
||||
# List of them.
|
||||
# ---
|
||||
|
||||
_Smileys_prefix = "/images/smileys/"
|
||||
|
||||
_Smileys = {
|
||||
'>:)': 'twisted.gif',
|
||||
'>:(': '/images/smileys/evil.gif',
|
||||
':)': '/images/smileys/smile.gif',
|
||||
';)': '/images/smileys/wink.gif',
|
||||
':(': '/images/smileys/sad.gif',
|
||||
':D': '/images/smileys/grin.gif',
|
||||
':p': '/images/smileys/hehe.gif',
|
||||
'8-)': '/images/smileys/cool2.gif',
|
||||
':@': '/images/smileys/mad.gif',
|
||||
'0_0': '/images/smileys/eek.gif',
|
||||
':E': '/images/smileys/mrgreen.gif',
|
||||
':O': '/images/smileys/shocked.gif',
|
||||
':s': '/images/smileys/confused2.gif',
|
||||
'^^': '/images/smileys/eyebrows.gif',
|
||||
":'(": '/images/smileys/cry.gif',
|
||||
# ':-°': ('/images/smileys/whistle.gif', 'height: 15px;'),
|
||||
|
||||
# Name-based smileys.
|
||||
|
||||
':lol:': '/images/smileys/lol.gif',
|
||||
':oops:': '/images/smileys/confused2.gif',
|
||||
':grr:': '/images/smileys/evil.gif',
|
||||
':sry:': '/images/smileys/redface.gif',
|
||||
':mmm:': '/images/smileys/rolleyes.gif',
|
||||
':waza:': '/images/smileys/waza.gif',
|
||||
# ':whistle:': ('/images/smileys/whistle.gif', 'height: 15px;'),
|
||||
':here:': '/images/smileys/pointer.gif',
|
||||
':bow:': '/images/smileys/bow.gif',
|
||||
':cool:': '/images/smileys/cool.gif',
|
||||
':good:': '/images/smileys/welldone.gif',
|
||||
':love:': '/images/smileys/love.gif',
|
||||
':aie:': '/images/smileys/banghead2.gif',
|
||||
':cry:': '/images/smileys/cry.gif',
|
||||
':facepalm:': '/images/smileys/facepalm.gif',
|
||||
':argh:': '/images/smileys/insults.gif',
|
||||
':?:': '/images/smileys/what.gif',
|
||||
':!:': '/images/smileys/excl.gif',
|
||||
':arrow:': '/images/smileys/here.gif',
|
||||
':grin:': '/images/smileys/grin.gif',
|
||||
}
|
||||
|
||||
def _Smiley_sub(m):
|
||||
return m.group(1) + '<img src="{}{}">'.format(_Smileys_prefix,
|
||||
_Smileys[m.group(2)]) + m.group(3)
|
||||
|
||||
_Smiley_re = _re.compile('(^|\\s)(' + '|'.join(map(_re.escape,
|
||||
_Smileys.keys())) + ')(\\s|$)')
|
||||
|
||||
# ---
|
||||
# Functions.
|
||||
# ---
|
||||
|
||||
def htmlsmileys(text):
|
||||
""" HTML smileys """
|
||||
|
||||
text = _Smiley_re.sub(_Smiley_sub, text)
|
||||
text = _Smiley_re.sub(_Smiley_sub, text)
|
||||
return text
|
||||
|
||||
# End of file.
|
||||
|
|
@ -7,87 +7,13 @@
|
|||
import regex as _re
|
||||
from io import StringIO as _sio
|
||||
from html import escape as _htmlescape
|
||||
from .Stream import *
|
||||
from .stream import *
|
||||
from .Tags import TextoutRawTag, TextoutInlineTag, TextoutBlockTag, get_tag
|
||||
from .smileys import htmlsmileys as _htmlsmileys
|
||||
from .urls import htmlurls as _htmlurls
|
||||
|
||||
__all__ = ["Translator"]
|
||||
|
||||
# ---
|
||||
# Naked URLs regex.
|
||||
# ---
|
||||
|
||||
def _NakedURLs_sub(m):
|
||||
sp = m.groups('sp')
|
||||
url = m.groups('url')
|
||||
aft = ''
|
||||
|
||||
# Hack for the last comma.
|
||||
if url[-1] == ',':
|
||||
url, aft = url[:-1], ','
|
||||
|
||||
return '{}<a href="{}" target="_blank" rel="noopener">{}</a>{}' \
|
||||
.format(sp, url, url, aft)
|
||||
|
||||
_NakedURLs_re = _re.compile(r"""\
|
||||
(?P<sp>^|\s|[[:punct:]])
|
||||
(?P<url>(https?|ftp):
|
||||
(?P<ucore>[^\[\]\(\)\s]* (\[(?&ucore)\]?)* (\((?&ucore)\)?)*)*
|
||||
)
|
||||
""", _re.VERBOSE | _re.M)
|
||||
|
||||
# ---
|
||||
# Smileys.
|
||||
# ---
|
||||
|
||||
_Smileys = {
|
||||
'>:)': '/images/smileys/twisted.gif',
|
||||
'>:(': '/images/smileys/evil.gif',
|
||||
':)': '/images/smileys/smile.gif',
|
||||
';)': '/images/smileys/wink.gif',
|
||||
':(': '/images/smileys/sad.gif',
|
||||
':D': '/images/smileys/grin.gif',
|
||||
':p': '/images/smileys/hehe.gif',
|
||||
'8-)': '/images/smileys/cool2.gif',
|
||||
':@': '/images/smileys/mad.gif',
|
||||
'0_0': '/images/smileys/eek.gif',
|
||||
':E': '/images/smileys/mrgreen.gif',
|
||||
':O': '/images/smileys/shocked.gif',
|
||||
':s': '/images/smileys/confused2.gif',
|
||||
'^^': '/images/smileys/eyebrows.gif',
|
||||
":'(": '/images/smileys/cry.gif',
|
||||
# ':-°': ('/images/smileys/whistle.gif', 'height: 15px;'),
|
||||
|
||||
# Name-based smileys.
|
||||
|
||||
':lol:': '/images/smileys/lol.gif',
|
||||
':oops:': '/images/smileys/confused2.gif',
|
||||
':grr:': '/images/smileys/evil.gif',
|
||||
':sry:': '/images/smileys/redface.gif',
|
||||
':mmm:': '/images/smileys/rolleyes.gif',
|
||||
':waza:': '/images/smileys/waza.gif',
|
||||
# ':whistle:': ('/images/smileys/whistle.gif', 'height: 15px;'),
|
||||
':here:': '/images/smileys/pointer.gif',
|
||||
':bow:': '/images/smileys/bow.gif',
|
||||
':cool:': '/images/smileys/cool.gif',
|
||||
':good:': '/images/smileys/welldone.gif',
|
||||
':love:': '/images/smileys/love.gif',
|
||||
':aie:': '/images/smileys/banghead2.gif',
|
||||
':cry:': '/images/smileys/cry.gif',
|
||||
':facepalm:': '/images/smileys/facepalm.gif',
|
||||
':argh:': '/images/smileys/insults.gif',
|
||||
':?:': '/images/smileys/what.gif',
|
||||
':!:': '/images/smileys/excl.gif',
|
||||
':arrow:': '/images/smileys/here.gif',
|
||||
':grin:': '/images/smileys/grin.gif',
|
||||
}
|
||||
|
||||
def _Smiley_sub(m):
|
||||
return m.group(1) + '<img src="{}">'.format(_Smileys[m.group(2)]) \
|
||||
+ m.group(3)
|
||||
|
||||
_Smiley_re = _re.compile('(^|\\s)(' + '|'.join(map(_re.escape,
|
||||
_Smileys.keys())) + ')(\\s|$)')
|
||||
|
||||
# ---
|
||||
# Translator main class.
|
||||
# ---
|
||||
|
|
@ -99,9 +25,13 @@ class Translator:
|
|||
You can even chain calls as the `process()` method returns
|
||||
the output stream object. """
|
||||
|
||||
def __init__(self, inp, outp):
|
||||
def __init__(self, inp, outp, output_type):
|
||||
""" Initializer. """
|
||||
|
||||
if output_type != 'html':
|
||||
raise Exception("Invalid output type")
|
||||
self.output_type = output_type
|
||||
|
||||
self.inp = inp
|
||||
self.outp = outp
|
||||
|
||||
|
|
@ -152,17 +82,11 @@ class Translator:
|
|||
|
||||
# In all cases, we want to escape for HTML things, so that the
|
||||
# user doesn't insert raw HTML tags (which would be a security flaw!).
|
||||
text = _htmlescape(self.text_group)
|
||||
if self.output_type == 'html':
|
||||
text = _htmlescape(self.text_group)
|
||||
|
||||
if not self.raw_mode:
|
||||
# Naked URL conversion.
|
||||
|
||||
text = _NakedURLs_re.sub(_NakedURLs_sub, text)
|
||||
|
||||
# Smiley conversion. Basically sub and replace.
|
||||
|
||||
text = _Smiley_re.sub(_Smiley_sub, text)
|
||||
text = _Smiley_re.sub(_Smiley_sub, text)
|
||||
if not self.raw_mode and self.output_type == 'html':
|
||||
text = _htmlsmileys(_htmlurls(text))
|
||||
|
||||
return text
|
||||
|
||||
|
|
@ -401,7 +325,7 @@ class Translator:
|
|||
# If the tag is unknown, output the full thing and just
|
||||
# go on.
|
||||
|
||||
tag = get_tag(tagdata.name, tagdata.value, 'html')
|
||||
tag = get_tag(tagdata.name, tagdata.value, self.output_type)
|
||||
if not tag:
|
||||
self.put_text(tagdata.full)
|
||||
continue
|
||||
|
|
|
|||
|
|
@ -0,0 +1,42 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
""" Autolinking (URL extraction from raw text) in HTML. """
|
||||
|
||||
import regex as _re
|
||||
from html import escape as _htmlescape
|
||||
|
||||
__all__ = ["htmlurls"]
|
||||
|
||||
# ---
|
||||
# Autolinking regex.
|
||||
# FIXME: they don't work yet by the look of it.
|
||||
# ---
|
||||
|
||||
def _sub(m):
|
||||
sp = m.group('sp')
|
||||
url = m.group('url')
|
||||
aft = ''
|
||||
|
||||
# Hack for the last comma.
|
||||
if url[-1] == ',':
|
||||
url, aft = url[:-1], ','
|
||||
|
||||
text = '{}<a href="{}" target="_blank" rel="noopener">{}</a>{}' \
|
||||
.format(sp, url, url, aft)
|
||||
return text
|
||||
|
||||
_reg = _re.compile("""\
|
||||
(?P<sp>^|\s|[[:punct:]])
|
||||
(?P<url>(https?|ftp):
|
||||
(?P<ucore>[^\[\]\(\)\s]* (\[(?&ucore)\]?)* (\((?&ucore)\)?)*)*
|
||||
)
|
||||
""", _re.VERBOSE | _re.M)
|
||||
|
||||
# ---
|
||||
# Main function.
|
||||
# ---
|
||||
|
||||
def htmlurls(text):
|
||||
return _reg.sub(_sub, text)
|
||||
|
||||
# End of file.
|
||||
Loading…
Reference in New Issue