/usr/lib/python2.7/dist-packages/kajiki/text.py is in python-kajiki 0.5.3-1.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 | # -*- coding: utf-8 -*-
'''Text template compiler.
Notable in this module are:
* TextTemplate - function building a template from text string or filename.
* _pattern - the regex used to find the beginnings of tags and expressions.
* _Scanner - scans text and generates a stream of tokens.
* _Parser - parses a stream of tokens into the internal representation (IR)
tree.
* _Parser._parse_<tagname> - consumes the body of a tag and returns an ir.Node.
'''
from __future__ import (absolute_import, division, print_function,
unicode_literals)
import codecs
import re
from .ddict import defaultdict
from itertools import chain
from nine import iteritems, str
from shlex import split as shlex_split # Prior to Python 2.7.3, the
from sys import version_info # *shlex* module did not support
if version_info < (2, 7, 3): # Unicode input. Work around:
_shlex_split = shlex_split
shlex_split = lambda txt: _shlex_split(txt.encode('utf-8'))
del version_info
import kajiki
from . import ir
_pattern = r'''
\$(?:
(?P<expr_escaped>\$) | # Escape $$
(?P<expr_named>[_a-z][_a-z0-9.]*) | # $foo.bar
{(?P<expr_braced>) | # ${....
(?P<expr_invalid>)
) |
^\s*%(?:
(?P<tag_bare>[a-z]+) | # %for, %end, etc.
(?P<tag_bare_invalid>)
)|
^\s*{%-(?P<tag_begin_ljust>[a-z]+)| # {%-for, {%-end, etc.
{%(?:
(?P<tag_begin>[a-z]+) | # {%for, {%end, etc.
(?P<tag_begin_invalid>)
)
'''
_re_pattern = re.compile(_pattern, re.VERBOSE | re.IGNORECASE | re.MULTILINE)
def TextTemplate(source=None, filename=None, autoescape=False,
encoding='utf-8'):
assert source or filename, "You must either provide a *source* argument " \
"or a *filename* argument to TextTemplate()."
if source is None:
with codecs.open(filename, encoding=encoding) as f:
source = f.read()
if filename is None:
filename = '<string>'
assert isinstance(source, str), \
"*source* must be a unicode string, not a {}".format(type(source))
scanner = _Scanner(filename, source)
tree = _Parser(scanner, autoescape).parse()
tree.filename = filename
return kajiki.template.from_ir(tree)
class _Scanner(object):
def __init__(self, filename, source):
self.filename = filename
self.source = source
self.lineno = 1
self.pos = 0
def __iter__(self):
source = self.source
for mo in _re_pattern.finditer(source):
start = mo.start()
if start > self.pos:
yield self.text(source[self.pos:start])
self.pos = start
groups = mo.groupdict()
if groups['expr_braced'] is not None:
self.pos = mo.end()
yield self._get_braced_expr()
elif groups['expr_named'] is not None:
self.pos = mo.end()
yield self.expr(groups['expr_named'])
elif groups['expr_escaped'] is not None:
self.pos = mo.end()
yield self.text('$')
elif groups['tag_bare'] is not None:
self.pos = mo.end()
yield self._get_tag_bare(groups['tag_bare'])
elif groups['tag_begin'] is not None:
self.pos = mo.end()
yield self._get_tag(groups['tag_begin'])
elif groups['tag_begin_ljust'] is not None:
self.pos = mo.end()
yield self._get_tag(groups['tag_begin_ljust'])
elif groups['tag_bare_invalid'] is not None:
continue
else:
msg = 'Syntax error %s:%s' % (self.filename, self.lineno)
for i, line in enumerate(self.source.splitlines()):
print('%3d %s' % (i + 1, line))
print(msg)
assert False, groups
if self.pos != len(source):
yield self.text(source[self.pos:])
def _get_pos(self):
return self._pos
def _set_pos(self, value):
assert value >= getattr(self, '_pos', 0)
self._pos = value
pos = property(_get_pos, _set_pos)
def text(self, text):
self.lineno += text.count('\n')
return _Text(self.filename, self.lineno, text)
def expr(self, text):
self.lineno += text.count('\n')
return _Expr(self.filename, self.lineno, text)
def tag(self, tagname, body):
tag = _Tag(self.filename, self.lineno, tagname, body)
self.lineno += tag.text.count('\n')
return tag
def _get_tag_bare(self, tagname):
end = self.source.find('\n', self.pos)
if end == -1:
end = len(self.source)
body = self.source[self.pos:end]
self.lineno += 1
self.pos = end + 1
return self.tag(tagname, body)
def _get_tag(self, tagname):
end = self.source.find('%}', self.pos)
assert end > 0
body = self.source[self.pos:end]
self.pos = end + 2
if body.endswith('-'):
body = body[:-1]
while self.source[self.pos] in ' \t':
self.pos += 1
return self.tag(tagname, body)
def _get_braced_expr(self):
try:
compile(self.source[self.pos:], '', 'eval')
except SyntaxError as se:
end = se.offset + self.pos
text = self.source[self.pos:end - 1]
self.pos = end
return self.expr(text)
class _Parser(object):
def __init__(self, tokenizer, autoescape=False):
self.tokenizer = tokenizer
self.functions = defaultdict(list)
self.functions['__main__()'] = []
self.mod_py = [] # module-level python blocks
self.iterator = iter(self.tokenizer)
self.autoescape = autoescape
self._in_def = False
self._is_child = False
def parse(self):
body = list(self._parse_body())
self.functions['__main__()'] = body[:-1]
defs = [ir.DefNode(k, *v) for k, v in iteritems(self.functions)]
return ir.TemplateNode(self.mod_py, defs)
def text(self, token):
text = ''.join(_unescape_newlines(token.text))
node = ir.TextNode(text)
node.filename = token.filename
node.lineno = token.lineno
return node
def expr(self, token):
node = ir.ExprNode(token.text, safe=not self.autoescape)
node.filename = token.filename
node.lineno = token.lineno
return node
def push_tok(self, token):
self.iterator = chain([token], self.iterator)
def _parse_body(self, *stoptags):
while True:
try:
token = next(self.iterator)
if isinstance(token, _Text):
yield self.text(token)
elif isinstance(token, _Expr):
yield self.expr(token)
elif isinstance(token, _Tag):
if token.tagname in stoptags:
yield token
break
parser = getattr(self, '_parse_%s' % token.tagname)
yield parser(token)
else:
msg = 'Parse error: %r unexpected' % token
assert False, msg
except StopIteration:
yield None
break
def _parse_def(self, token):
old_in_def, self._in_def = self._in_def, True
body = list(self._parse_body('end'))
self._in_def = old_in_def
if self._in_def:
return ir.InnerDefNode(token.body, *body[:-1])
else:
self.functions[token.body.strip()] = body[:-1]
return None
def _parse_call(self, token):
b = token.body.find('(')
e = token.body.find(')', b)
assert e > b > -1
arglist = token.body[b:e + 1]
call = token.body[e + 1:].strip()
body = list(self._parse_body('end'))
return ir.CallNode(
'$caller%s' % arglist,
call.replace('%caller', '$caller'),
*body[:-1])
def _parse_if(self, token):
body = list(self._parse_body('end', 'else'))
stoptok = body[-1]
if stoptok.tagname == 'else':
self.push_tok(stoptok)
return ir.IfNode(token.body, *body[:-1])
def _parse_for(self, token):
body = list(self._parse_body('end'))
return ir.ForNode(token.body, *body[:-1])
def _parse_switch(self, token):
body = list(self._parse_body('end'))
return ir.SwitchNode(token.body, *body[:-1])
def _parse_case(self, token):
body = list(self._parse_body('case', 'else', 'end'))
stoptok = body[-1]
self.push_tok(stoptok)
return ir.CaseNode(token.body, *body[:-1])
def _parse_else(self, token):
body = list(self._parse_body('end'))
return ir.ElseNode(*body[:-1])
def _parse_extends(self, token):
parts = shlex_split(token.body)
fn = parts[0]
assert len(parts) == 1
self._is_child = True
return ir.ExtendNode(fn)
def _parse_import(self, token):
parts = shlex_split(token.body)
fn = parts[0]
if len(parts) > 1:
assert parts[1] == 'as'
return ir.ImportNode(fn, parts[2])
else:
return ir.ImportNode(fn)
def _parse_include(self, token):
parts = shlex_split(token.body)
fn = parts[0]
assert len(parts) == 1
return ir.IncludeNode(fn)
def _parse_py(self, token):
body = token.body.strip()
if body:
body = [ir.TextNode(body), None]
else:
body = list(self._parse_body('end'))
node = ir.PythonNode(*body[:-1])
if node.module_level:
self.mod_py.append(node)
return None
else:
return node
def _parse_block(self, token):
fname = '_kj_block_' + token.body.strip()
decl = fname + '()'
body = list(self._parse_body('end'))[:-1]
self.functions[decl] = body
if self._is_child:
parent_block = 'parent.' + fname
body.insert(0,
ir.PythonNode(ir.TextNode('parent_block=%s' % parent_block)))
return None
else:
return ir.ExprNode(decl)
class _Token(object):
def __init__(self, filename, lineno, text):
self.filename = filename
self.lineno = lineno
self.text = text
def __repr__(self): # pragma no cover
return '<%s %r>' % (
self.__class__.__name__,
self.text)
class _Expr(_Token):
pass
class _Text(_Token):
pass
class _Tag(_Token):
def __init__(self, filename, lineno, tagname, body):
self.tagname = tagname
self.body = body
text = tagname + ' ' + body
super(_Tag, self).__init__(filename, lineno, text)
def _unescape_newlines(text):
i = 0
while i < len(text):
if text[i] == '\\':
if text[i + 1] != '\n':
yield text[i + 1]
i += 2
else:
yield text[i]
i += 1
|