evennia/evennia/utils/text2html.py

280 lines
9 KiB
Python

"""
ANSI -> html converter
Credit for original idea and implementation
goes to Muhammad Alkarouri and his
snippet #577349 on http://code.activestate.com.
(extensively modified by Griatch 2010)
"""
from __future__ import absolute_import
from builtins import object
import re
import cgi
from .ansi import *
# All xterm256 RGB equivalents
XTERM256_FG = "\033[38;5;%sm"
XTERM256_BG = "\033[48;5;%sm"
class TextToHTMLparser(object):
"""
This class describes a parser for converting from ANSI to html.
"""
tabstop = 4
# mapping html color name <-> ansi code.
hilite = ANSI_HILITE
unhilite = ANSI_UNHILITE
normal = ANSI_NORMAL
underline = ANSI_UNDERLINE
colorcodes = [
('color-000', unhilite + ANSI_BLACK), # pure black
('color-001', unhilite + ANSI_RED),
('color-002', unhilite + ANSI_GREEN),
('color-003', unhilite + ANSI_YELLOW),
('color-004', unhilite + ANSI_BLUE),
('color-005', unhilite + ANSI_MAGENTA),
('color-006', unhilite + ANSI_CYAN),
('color-007', unhilite + ANSI_WHITE), # light grey
('color-008', hilite + ANSI_BLACK), # dark grey
('color-009', hilite + ANSI_RED),
('color-010', hilite + ANSI_GREEN),
('color-011', hilite + ANSI_YELLOW),
('color-012', hilite + ANSI_BLUE),
('color-013', hilite + ANSI_MAGENTA),
('color-014', hilite + ANSI_CYAN),
('color-015', hilite + ANSI_WHITE) # pure white
] + [("color-%03i" % (i+16), XTERM256_FG % ("%03i" % (i+16))) for i in xrange(240)]
colorback = [
('bgcolor-000', ANSI_BACK_BLACK), # pure black
('bgcolor-001', ANSI_BACK_RED),
('bgcolor-002', ANSI_BACK_GREEN),
('bgcolor-003', ANSI_BACK_YELLOW),
('bgcolor-004', ANSI_BACK_BLUE),
('bgcolor-005', ANSI_BACK_MAGENTA),
('bgcolor-006', ANSI_BACK_CYAN),
('bgcolor-007', ANSI_BACK_WHITE), # light grey
('bgcolor-000', unhilite + ANSI_BLACK), # pure black
('bgcolor-001', unhilite + ANSI_RED),
('bgcolor-002', unhilite + ANSI_GREEN),
('bgcolor-003', unhilite + ANSI_YELLOW),
('bgcolor-004', unhilite + ANSI_BLUE),
('bgcolor-005', unhilite + ANSI_MAGENTA),
('bgcolor-006', unhilite + ANSI_CYAN),
('bgcolor-007', unhilite + ANSI_WHITE), # light grey
('bgcolor-008', hilite + ANSI_BLACK), # dark grey
('bgcolor-009', hilite + ANSI_RED),
('bgcolor-010', hilite + ANSI_GREEN),
('bgcolor-011', hilite + ANSI_YELLOW),
('bgcolor-012', hilite + ANSI_BLUE),
('bgcolor-013', hilite + ANSI_MAGENTA),
('bgcolor-014', hilite + ANSI_CYAN),
('bgcolor-015', hilite + ANSI_WHITE), # pure white
] + [("bgcolor-%03i" % (i+16), XTERM256_BG % ("%03i" % (i+16))) for i in range(240)]
# make sure to escape [
colorcodes = [(c, code.replace("[", r"\[")) for c, code in colorcodes]
colorback = [(c, code.replace("[", r"\[")) for c, code in colorback]
# create stop markers
fgstop = [("", c.replace("[", r"\[")) for c in (normal, hilite, underline)]
bgstop = [("", c.replace("[", r"\[")) for c in (normal,)]
fgstop = "|".join(co[1] for co in colorcodes + fgstop + [("", "$")])
bgstop = "|".join(co[1] for co in colorback + bgstop + [("", "$")])
# pre-compile regexes
re_fgs = [(cname, re.compile("(?:%s)(.*?)(?=%s)" % (code, fgstop))) for cname, code in colorcodes]
re_bgs = [(cname, re.compile("(?:%s)(.*?)(?=%s)" % (code, bgstop))) for cname, code in colorback]
re_normal = re.compile(normal.replace("[", r"\["))
re_hilite = re.compile("(?:%s)(.*)(?=%s)" % (hilite.replace("[", r"\["), fgstop))
re_uline = re.compile("(?:%s)(.*?)(?=%s)" % (ANSI_UNDERLINE.replace("[", r"\["), fgstop))
re_string = re.compile(r'(?P<htmlchars>[<&>])|(?P<space> [ \t]+)|(?P<lineend>\r\n|\r|\n)', re.S|re.M|re.I)
re_url = re.compile(r'((?:ftp|www|https?)\W+(?:(?!\.(?:\s|$)|&\w+;)[^"\',;$*^\\(){}<>\[\]\s])+)(\.(?:\s|$)|&\w+;|)')
re_mxplink = re.compile(r'\|lc(.*?)\|lt(.*?)\|le', re.DOTALL)
def re_color(self, text):
"""
Replace ansi colors with html color class names. Let the
client choose how it will display colors, if it wishes to.
Args:
text (str): the string with color to replace.
Returns:
text (str): Re-colored text.
"""
for colorname, regex in self.re_fgs:
text = regex.sub(r'''<span class="%s">\1</span>''' % colorname, text)
for bgname, regex in self.re_bgs:
text = regex.sub(r'''<span class="%s">\1</span>''' % bgname, text)
text = self.re_normal.sub("", text)
return text
def re_bold(self, text):
"""
Clean out superfluous hilights rather than set <strong>to make
it match the look of telnet.
Args:
text (str): Text to process.
Returns:
text (str): Processed text.
"""
return self.re_hilite.sub(r'<strong>\1</strong>', text)
def re_underline(self, text):
"""
Replace ansi underline with html underline class name.
Args:
text (str): Text to process.
Returns:
text (str): Processed text.
"""
return self.re_uline.sub(r'<span class="underline">\1</span>', text)
def remove_bells(self, text):
"""
Remove ansi specials
Args:
text (str): Text to process.
Returns:
text (str): Processed text.
"""
return text.replace('\07', '')
def remove_backspaces(self, text):
"""
Removes special escape sequences
Args:
text (str): Text to process.
Returns:
text (str): Processed text.
"""
backspace_or_eol = r'(.\010)|(\033\[K)'
n = 1
while n > 0:
text, n = re.subn(backspace_or_eol, '', text, 1)
return text
def convert_linebreaks(self, text):
"""
Extra method for cleaning linebreaks
Args:
text (str): Text to process.
Returns:
text (str): Processed text.
"""
return text.replace(r'\n', r'<br>')
def convert_urls(self, text):
"""
Replace urls (http://...) by valid HTML.
Args:
text (str): Text to process.
Returns:
text (str): Processed text.
"""
# -> added target to output prevent the web browser from attempting to
# change pages (and losing our webclient session).
return self.re_url.sub(r'<a href="\1" target="_blank">\1</a>\2', text)
def convert_links(self, text):
"""
Replaces links with HTML code.
Args:
text (str): Text to process.
Returns:
text (str): Processed text.
"""
return self.re_mxplink.sub(r"""<a id='mxplink' href='#' onclick='Evennia.msg("text",["\1"],{}); return false;'>\2</a>""", text)
def do_sub(self, match):
"""
Helper method to be passed to re.sub,
for handling all substitutions.
Args:
match (re.Matchobject): Match for substitution.
Returns:
text (str): Processed text.
"""
cdict = match.groupdict()
if cdict['htmlchars']:
return cgi.escape(cdict['htmlchars'])
if cdict['lineend']:
return '<br>'
elif cdict['space'] == '\t':
return ' ' * self.tabstop
elif cdict['space']:
text = match.group().replace('\t', '&nbsp;' * self.tabstop)
text = text.replace(' ', '&nbsp;')
return text
def parse(self, text, strip_ansi=False):
"""
Main access function, converts a text containing ANSI codes
into html statements.
Args:
text (str): Text to process.
strip_ansi (bool, optional):
Returns:
text (str): Parsed text.
"""
# parse everything to ansi first
text = parse_ansi(text, strip_ansi=strip_ansi, xterm256=True, mxp=True)
# convert all ansi to html
result = re.sub(self.re_string, self.do_sub, text)
result = self.re_color(result)
result = self.re_bold(result)
result = self.re_underline(result)
result = self.remove_bells(result)
result = self.convert_linebreaks(result)
result = self.remove_backspaces(result)
result = self.convert_urls(result)
result = self.convert_links(result)
# clean out eventual ansi that was missed
#result = parse_ansi(result, strip_ansi=True)
return result
HTML_PARSER = TextToHTMLparser()
#
# Access function
#
def parse_html(string, strip_ansi=False, parser=HTML_PARSER):
"""
Parses a string, replace ANSI markup with html
"""
return parser.parse(string, strip_ansi=strip_ansi)