poezio/src/xhtml.py

230 lines
7.4 KiB
Python
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#!/usr/bin/env python3
#
# Copyright 2010-2011 Le Coz Florent <louiz@louiz.org>
#
# This file is part of Poezio.
#
# Poezio is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# Poezio is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Poezio. If not, see <http://www.gnu.org/licenses/>.
"""
Various methods to convert
shell colors to poezio colors,
xhtml code to shell colors,
poezio colors to xhtml code
"""
import re
import subprocess
from sleekxmpp.xmlstream import ET
from xml.etree.ElementTree import ElementTree
from sys import version_info
from config import config
import logging
digits = '0123456789' # never trust the modules
log = logging.getLogger(__name__)
shell_colors_re = re.compile(r'(\[(?:\d+;)*(?:\d+m))')
start_indent_re = re.compile(r'\[0;30m\[0;37m ')
newline_indent_re = re.compile('\n\[0;37m ')
def get_body_from_message_stanza(message):
"""
Returns a string with xhtml markups converted to
poezio colors if there's an xhtml_im element, or
the body (without any color) otherwise
"""
if config.get('enable_xhtml_im', 'true') == 'true':
xhtml_body = message['xhtml_im']
if xhtml_body:
xhtml_body = convert_links_to_plaintext(xhtml_body)
try:
shell_body = xhtml_code_to_shell_colors(xhtml_body)
except OSError:
log.error('html parsing failed')
else:
return shell_colors_to_poezio_colors(shell_body)
return message['body']
def convert_links_to_plaintext(text):
"""
Replace
<a href='URL'>click</a>
by
<url> (click)
in plain text
"""
log.debug(text)
xml = ElementTree(ET.fromstring(text))
for parent in xml.getiterator():
previous_child = None
for child in parent:
if child.tag == '{http://www.w3.org/1999/xhtml}a':
if child.attrib['href'] != child.text:
if child.text is None and 'title' in child.attrib:
link_text = '\n%s (%s)' % (child.attrib['href'], child.attrib['title'])
else:
link_text = '\n%s (%s)' % (child.attrib['href'], child.text)
else:
link_text = child.text
if previous_child is not None:
if previous_child.tail is None:
previous_child.tail = link_text
else:
previous_child.tail += link_text
else:
if parent.text is None:
parent.text = link_text
else:
parent.text += link_text
parent.remove(child)
previous_child = child
if version_info.minor <= 1:
return ET.tostring(xml.getroot())
return ET.tostring(xml.getroot(), encoding=str)
def clean_text(string):
"""
Remove all \x19 from the string
"""
pos = string.find('\x19')
while pos != -1:
string = string[:pos] + string[pos+2:]
pos = string.find('\x19')
return string
number_to_color_names = {
1: 'red',
2: 'green',
3: 'yellow',
4: 'blue',
5: 'violet',
6: 'turquoise',
7: 'white'
}
def poezio_colors_to_html(string):
"""
Convert poezio colors to html makups
(e.g. \x191: <span style='color: red'>)
"""
# TODO underlined
# a list of all opened elements, e.g. ['strong', 'span']
# So that we know what we need to close
opened_elements = []
res = "<body xmlns='http://www.w3.org/1999/xhtml'><p>"
next_attr_char = string.find('\x19')
while next_attr_char != -1:
attr_char = string[next_attr_char+1].lower()
if next_attr_char != 0:
res += string[:next_attr_char]
string = string[next_attr_char+2:]
if attr_char == 'o':
for elem in opened_elements[::-1]:
res += '</%s>' % (elem,)
opened_elements = []
elif attr_char == 'b':
if 'strong' not in opened_elements:
opened_elements.append('strong')
res += '<strong>'
elif attr_char in digits:
number = int(attr_char)
if number in number_to_color_names:
if 'strong' in opened_elements:
res += '</strong>'
opened_elements.remove('strong')
if 'span' in opened_elements:
res += '</span>'
else:
opened_elements.append('span')
res += "<span style='color: %s'>" % (number_to_color_names[number])
next_attr_char = string.find('\x19')
res += string
for elem in opened_elements[::-1]:
res += '</%s>' % (elem,)
res += "</p></body>"
return res.replace('\n', '<br />')
def shell_colors_to_poezio_colors(string):
"""
'shell colors' means something like:
Bonjour ^[[0;32msalut^[[0m
The current understanding of this syntax is:
n = 0: reset all attributes to defaults
n = 1: activate bold
n >= 30 and n <= 37: set the foreground to n-30
"""
def repl(matchobj):
exp = matchobj.group(0)[2:-1]
numbers = [int(nb) for nb in exp.split(';')]
res = ''
for num in numbers:
if num == 0:
res += '\x19o'
elif num == 1:
res += '\x19b'
elif num >= 31 and num <= 37:
res += '\x19%d' % ((num-30)%7,)
return res
def remove_elinks_indent(string):
lines = string.split('\n')
for i, line in enumerate(lines):
lines[i] = re.sub(' ', '', line, 1)
return '\n'.join(lines)
res = shell_colors_re.sub(repl, string).strip()
res = remove_elinks_indent(res)
return res
def xhtml_code_to_shell_colors(string):
"""
Use a console browser to parse the xhtml and
make it return a shell-colored string
"""
process = subprocess.Popen(["elinks", "-dump", "-dump-color-mode", "2"], stdout=subprocess.PIPE, stdin=subprocess.PIPE)
result = process.communicate(input=string.encode('utf-8'))[0]
return result.decode('utf-8').strip()
def poezio_colors_to_xhtml(string):
"""
Generate a valid xhtml string from
the poezio colors in the given string
"""
res = "<body xmlns='http://www.w3.org/1999/xhtml'>"
next_attr_char = string.find('\x19')
open_elements = []
while next_attr_char != -1:
attr_char = string[next_attr_char+1].lower()
if next_attr_char != 0:
res += string[:next_attr_char]
string = string[next_attr_char+2:]
if attr_char == 'o':
# close all opened elements
for elem in open_elements:
res += '</%s>'
open_elements = []
elif attr_char == 'b':
if 'strong' not in open_elements:
res += '<strong>'
open_elements.append('strong')
elif attr_char in digits:
self._win.attron(common.curses_color_pair(int(attr_char)))
next_attr_char = string.find('\x19')