/usr/lib/python3/dist-packages/aeidon/markup.py is in python3-aeidon 0.24.3-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | # -*- coding: utf-8 -*-
# Copyright (C) 2005-2009 Osmo Salomaa
#
# This file is part of Gaupol.
#
# Gaupol 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, either version 3 of the License, or (at your option) any later
# version.
#
# Gaupol 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
# Gaupol. If not, see <http://www.gnu.org/licenses/>.
"""Base class for text markup."""
import aeidon
import re
__all__ = ("Markup",)
class Markup(aeidon.Singleton, metaclass=aeidon.Contractual):
"""
Base class for text markup.
Markup conversions between different formats are done via an internal
format, which has the following BBcode-style tags with angle brackets.
Conversions are best done via the ``_decode_*`` and ``_encode_*`` methods
rather than hard-coding the internal tags in regular expression
substitutions.
* ``<b>...................</b>``
* ``<i>...................</i>``
* ``<u>...................</u>``
* ``<color=#RRGGBB>...</color>``
* ``<font=NAME>........</font>``
* ``<size=POINTS>......</size>``
:class:`Markup` is effectively equivalent to a format with no markup and
can therefore be merely subclassed with a ``pass``-statement by formats
that do not implement any markup. The caller of any tagging methods, e.g.
:meth:`bolden`, must be prepared to handle :exc:`NotImplementedError`.
"""
_flags = re.DOTALL | re.MULTILINE
format = aeidon.formats.NONE
def _decode_apply_require(self, text, regex, replacement, groups):
assert replacement.count("{}") == len(groups)
def _decode_apply(self, text, regex, replacement, groups):
"""
Return `text` with all matches of `regex` replaced.
`replacement` may contain one or more of ``{}``, which are replaced
with parts of the match as defined by `groups`, a ``tuple`` of numbers.
"""
orig_text = text
match = regex.search(text)
if match is None: return text
a, z = match.span()
new = replacement.format(*tuple(map(match.group, groups)))
text = "".join((text[:a], new, text[z:]))
if text == orig_text: return text
return self._decode_apply(text, regex, replacement, groups)
def _decode_b(self, text, pattern, target, flags=0):
"""Return `text` with bold markup converted to internal format."""
regex = self._get_regex(pattern, flags)
return self._decode_apply(text, regex, "<b>{}</b>", (target,))
def _decode_c(self, text, pattern, value, target, flags=0):
"""Return `text` with color markup converted to internal format."""
regex = self._get_regex(pattern, flags)
replacement = "<color=#{}>{}</color>"
return self._decode_apply(text, regex, replacement, (value, target))
def _decode_f(self, text, pattern, value, target, flags=0):
"""Return `text` with font markup converted to internal format."""
regex = self._get_regex(pattern, flags)
replacement = "<font={}>{}</font>"
return self._decode_apply(text, regex, replacement, (value, target))
def _decode_i(self, text, pattern, target, flags=0):
"""Return `text` with italic markup converted to internal format."""
regex = self._get_regex(pattern, flags)
return self._decode_apply(text, regex, "<i>{}</i>", (target,))
def _decode_s(self, text, pattern, value, target, flags=0):
"""Return `text` with size markup converted to internal format."""
regex = self._get_regex(pattern, flags)
replacement = "<size={}>{}</size>"
return self._decode_apply(text, regex, replacement, (value, target))
def _decode_u(self, text, pattern, target, flags=0):
"""Return `text` with underline markup converted to internal format."""
regex = self._get_regex(pattern, flags)
return self._decode_apply(text, regex, "<u>{}</u>", (target,))
def _encode_apply(self, text, regex, method, target, value=None):
"""
Return `text` with internal tags removed and `method` applied.
`method` should be one the tagging methods, e.g. meth:`bolden`.
`target` and `value` should be group numbers in `regex`.
"""
orig_text = text
match = regex.search(text)
if match is None: return text
text = regex.sub(r"\{}".format(target), text, 1)
a = match.start()
z = a + len(match.group(target))
args = (text, (a, z))
if value is not None:
args = (text, match.group(value), (a, z))
try: text = method(*args)
except NotImplementedError: pass
if text == orig_text: return text
return self._encode_apply(text, regex, method, target, value)
def _encode_b(self, text):
"""Return `text` with bold markup converted to this format."""
regex = self._get_regex(r"<b>(.*?)</b>")
return self._encode_apply(text, regex, self.bolden, 1)
def _encode_c(self, text):
"""Return `text` with color markup converted to this format."""
regex = self._get_regex(r"<color=#([a-fA-F0-9]{6})>(.*?)</color>")
return self._encode_apply(text, regex, self.colorize, 2, 1)
def _encode_f(self, text):
"""Return `text` with font markup converted to this format."""
regex = self._get_regex(r"<font=(.+?)>(.*?)</font>")
return self._encode_apply(text, regex, self.fontify, 2, 1)
def _encode_i(self, text):
"""Return `text` with italic markup converted to this format."""
regex = self._get_regex(r"<i>(.*?)</i>")
return self._encode_apply(text, regex, self.italicize, 1)
def _encode_s(self, text):
"""Return `text` with size markup converted to this format."""
regex = self._get_regex(r"<size=(\d+)>(.*?)</size>")
return self._encode_apply(text, regex, self.scale, 2, 1)
def _encode_u(self, text):
"""Return `text` with underline markup converted to this format."""
regex = self._get_regex(r"<u>(.*?)</u>")
return self._encode_apply(text, regex, self.underline, 1)
@aeidon.deco.memoize(100)
def _get_regex(self, pattern, flags=0):
"""Return compiled regular expression from cache."""
flags = self._flags | flags
return re.compile(pattern, flags)
def _main_decode(self, text):
"""Return `text` with decodable markup decoded."""
return text
def _post_decode(self, text):
"""Return `text` with markup finalized after decoding."""
return text
def _pre_decode(self, text):
"""Return `text` with markup prepared for decoding."""
return text
def _substitute(self, text, pattern, replacement, flags=0):
"""Return `text` with matches of `pattern` replaced."""
regex = self._get_regex(pattern, flags)
return regex.sub(replacement, text)
def bolden_require(self, text, bounds=None):
if bounds is not None:
assert 0 <= bounds[0] <= bounds[1] <= len(text)
def bolden(self, text, bounds=None):
"""Return bolded `text`."""
raise NotImplementedError
def clean(self, text):
"""
Return `text` with less ugly markup.
Subclasses can implement this to, for example, remove redundant markup,
finetune tag positioning or to join or split tags, in general, whatever
that changes the style of the markup but not that of the text.
"""
return text
def colorize_require(self, text, color, bounds=None):
regex = self._get_regex(r"[0-9a-fA-F]{6}")
assert regex.match(color) is not None
if bounds is not None:
assert 0 <= bounds[0] <= bounds[1] <= len(text)
def colorize(self, text, color, bounds=None):
"""Return `text` colorized to hexadecimal value."""
raise NotImplementedError
def decode(self, text):
"""Return `text` with markup converted from this to internal format."""
text = self._pre_decode(text)
text = self._main_decode(text)
return self._post_decode(text)
def encode(self, text):
"""Return `text` with markup converted from internal to this format."""
text = self._encode_b(text)
text = self._encode_c(text)
text = self._encode_f(text)
text = self._encode_i(text)
text = self._encode_s(text)
return self._encode_u(text)
def fontify_require(self, text, font, bounds=None):
if bounds is not None:
assert 0 <= bounds[0] <= bounds[1] <= len(text)
def fontify(self, text, font, bounds=None):
"""Return `text` changed to `font`."""
raise NotImplementedError
@property
def italic_tag(self):
"""Regular expression for an italic markup tag or ``None``."""
return None
def italicize_require(self, text, bounds=None):
if bounds is not None:
assert 0 <= bounds[0] <= bounds[1] <= len(text)
def italicize(self, text, bounds=None):
"""Return italicized `text`."""
raise NotImplementedError
def scale_require(self, text, size, bounds=None):
assert isinstance(size, int) or size.isdigit()
if bounds is not None:
assert 0 <= bounds[0] <= bounds[1] <= len(text)
def scale(self, text, size, bounds=None):
"""Return `text` scaled to `size`."""
raise NotImplementedError
@property
def tag(self):
"""Regular expression for any markup tag or ``None``."""
return None
def underline_require(self, text, bounds=None):
if bounds is not None:
assert 0 <= bounds[0] <= bounds[1] <= len(text)
def underline(self, text, bounds=None):
"""Return underlined `text`."""
raise NotImplementedError
|