aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/python/Pygments/py2/pygments/scanner.py
diff options
context:
space:
mode:
authornkozlovskiy <nmk@ydb.tech>2023-09-29 12:24:06 +0300
committernkozlovskiy <nmk@ydb.tech>2023-09-29 12:41:34 +0300
commite0e3e1717e3d33762ce61950504f9637a6e669ed (patch)
treebca3ff6939b10ed60c3d5c12439963a1146b9711 /contrib/python/Pygments/py2/pygments/scanner.py
parent38f2c5852db84c7b4d83adfcb009eb61541d1ccd (diff)
downloadydb-e0e3e1717e3d33762ce61950504f9637a6e669ed.tar.gz
add ydb deps
Diffstat (limited to 'contrib/python/Pygments/py2/pygments/scanner.py')
-rw-r--r--contrib/python/Pygments/py2/pygments/scanner.py105
1 files changed, 105 insertions, 0 deletions
diff --git a/contrib/python/Pygments/py2/pygments/scanner.py b/contrib/python/Pygments/py2/pygments/scanner.py
new file mode 100644
index 0000000000..bcb19ed9c6
--- /dev/null
+++ b/contrib/python/Pygments/py2/pygments/scanner.py
@@ -0,0 +1,105 @@
+# -*- coding: utf-8 -*-
+"""
+ pygments.scanner
+ ~~~~~~~~~~~~~~~~
+
+ This library implements a regex based scanner. Some languages
+ like Pascal are easy to parse but have some keywords that
+ depend on the context. Because of this it's impossible to lex
+ that just by using a regular expression lexer like the
+ `RegexLexer`.
+
+ Have a look at the `DelphiLexer` to get an idea of how to use
+ this scanner.
+
+ :copyright: Copyright 2006-2019 by the Pygments team, see AUTHORS.
+ :license: BSD, see LICENSE for details.
+"""
+import re
+
+
+class EndOfText(RuntimeError):
+ """
+ Raise if end of text is reached and the user
+ tried to call a match function.
+ """
+
+
+class Scanner(object):
+ """
+ Simple scanner
+
+ All method patterns are regular expression strings (not
+ compiled expressions!)
+ """
+
+ def __init__(self, text, flags=0):
+ """
+ :param text: The text which should be scanned
+ :param flags: default regular expression flags
+ """
+ self.data = text
+ self.data_length = len(text)
+ self.start_pos = 0
+ self.pos = 0
+ self.flags = flags
+ self.last = None
+ self.match = None
+ self._re_cache = {}
+
+ def eos(self):
+ """`True` if the scanner reached the end of text."""
+ return self.pos >= self.data_length
+ eos = property(eos, eos.__doc__)
+
+ def check(self, pattern):
+ """
+ Apply `pattern` on the current position and return
+ the match object. (Doesn't touch pos). Use this for
+ lookahead.
+ """
+ if self.eos:
+ raise EndOfText()
+ if pattern not in self._re_cache:
+ self._re_cache[pattern] = re.compile(pattern, self.flags)
+ return self._re_cache[pattern].match(self.data, self.pos)
+
+ def test(self, pattern):
+ """Apply a pattern on the current position and check
+ if it patches. Doesn't touch pos.
+ """
+ return self.check(pattern) is not None
+
+ def scan(self, pattern):
+ """
+ Scan the text for the given pattern and update pos/match
+ and related fields. The return value is a boolen that
+ indicates if the pattern matched. The matched value is
+ stored on the instance as ``match``, the last value is
+ stored as ``last``. ``start_pos`` is the position of the
+ pointer before the pattern was matched, ``pos`` is the
+ end position.
+ """
+ if self.eos:
+ raise EndOfText()
+ if pattern not in self._re_cache:
+ self._re_cache[pattern] = re.compile(pattern, self.flags)
+ self.last = self.match
+ m = self._re_cache[pattern].match(self.data, self.pos)
+ if m is None:
+ return False
+ self.start_pos = m.start()
+ self.pos = m.end()
+ self.match = m.group()
+ return True
+
+ def get_char(self):
+ """Scan exactly one char."""
+ self.scan('.')
+
+ def __repr__(self):
+ return '<%s %d/%d>' % (
+ self.__class__.__name__,
+ self.pos,
+ self.data_length
+ )