我们从Python开源项目中，提取了以下12个代码示例，用于说明如何使用regex.escape()。
def test_octal_fail(self): """Test that octal fails properly.""" pattern = regex.compile(b'Test') with pytest.raises(ValueError) as excinfo: bregex.compile_replace(pattern, br'\666') assert "octal escape value outside of range 0-0o377!" in str(excinfo.value) with pytest.raises(ValueError) as excinfo: bregex.compile_replace(pattern, br'\C\666\E') assert "octal escape value outside of range 0-0o377!" in str(excinfo.value) with pytest.raises(ValueError) as excinfo: bregex.compile_replace(pattern, br'\c\666') assert "octal escape value outside of range 0-0o377!" in str(excinfo.value)
def quoted(self, i): r"""Handle quoted block.""" quoted = [] raw = [] if not self.in_group(i.index - 1): try: t = next(i) while t != self._esc_end: raw.append(t) t = next(i) except StopIteration: pass if len(raw): quoted.extend([escape(self._empty.join(raw))]) return quoted
def test_bug_449964(self): # Fails for group followed by other escape. self.assertEqual(regex.sub(r'(?P<unk>x)', r'\g<1>\g<1>\b', 'xx'), "xx\bxx\b")
def test_re_escape(self): p = "" self.assertEqual(regex.escape(p), p) for i in range(0, 256): p += chr(i) self.assertEqual(bool(regex.match(regex.escape(chr(i)), chr(i))), True) self.assertEqual(regex.match(regex.escape(chr(i)), chr(i)).span(), (0, 1)) pat = regex.compile(regex.escape(p)) self.assertEqual(pat.match(p).span(), (0, 256))
def test_bug_612074(self): pat = u"[" + regex.escape(u"\u2039") + u"]" self.assertEqual(regex.compile(pat) and 1, 1)
def test_replacement(self): self.assertEqual(regex.sub("test\?", "result\?\.\a\q\m\n", "test?"), "result\?\.\a\q\m\n") self.assertEqual(regex.sub(r"test\?", "result\?\.\a\q\m\n", "test?"), "result\?\.\a\q\m\n") self.assertEqual(regex.sub('(.)', r"\1\1", 'x'), 'xx') self.assertEqual(regex.sub('(.)', regex.escape(r"\1\1"), 'x'), r"\1\1") self.assertEqual(regex.sub('(.)', r"\\1\\1", 'x'), r"\1\1") self.assertEqual(regex.sub('(.)', lambda m: r"\1\1", 'x'), r"\1\1")
def calc_unwanted_chars_re(self): unwanted_chars_re = u'[^\p{{AlNum}}{safe_chars}]+'.format(safe_chars=re.escape(self._safe_chars or '')) self.unwanted_chars_re = re.compile(unwanted_chars_re, re.IGNORECASE) if self._stop_words: unwanted_chars_and_words_re = unwanted_chars_re + u'|(?<!\p{AlNum})(?:\L<stop_words>)(?!\p{AlNum})' self.unwanted_chars_and_words_re = re.compile(unwanted_chars_and_words_re, re.IGNORECASE, stop_words=self._stop_words) else: self.unwanted_chars_and_words_re = None
def test_quote(self): """Test quoting/escaping.""" result = bregex.RegexSearchTemplate(r'Testing \Q(\s+[quote]*\s+)?\E!').apply() self.assertEqual(r'Testing %s!' % regex.escape(r'(\s+[quote]*\s+)?'), result)
def test_quote_no_end(self): r"""Test quote where no \E is defined.""" result = bregex.RegexSearchTemplate(r'Testing \Q(quote) with no [end]!').apply() self.assertEqual(r'Testing %s' % regex.escape(r'(quote) with no [end]!'), result)
def fill_replace_dict(): global d_replace, re_replace # very first control-chars for i in range(0,20): d_replace["%%%x" % i] = "%00" d_replace["%%%X" % i] = "%00" # javascript charcode for i in range(33,127): c = "%c" % i d_replace["\\%o" % i] = c d_replace["\\%x" % i] = c d_replace["\\%X" % i] = c d_replace["0x%x" % i] = c d_replace["&#%d;" % i] = c d_replace["&#%x;" % i] = c d_replace["&#%X;" % i] = c # SQL words? d_replace["is null"]="=0" d_replace["like null"]="=0" d_replace["utc_time"]="" d_replace["null"]="" d_replace["true"]="" d_replace["false"]="" d_replace["localtime"]="" d_replace["stamp"]="" d_replace["binary"]="" d_replace["ascii"]="" d_replace["soundex"]="" d_replace["md5"]="" d_replace["between"]="=" d_replace["is"]="=" d_replace["not in"]="=" d_replace["xor"]="=" d_replace["rlike"]="=" d_replace["regexp"]="=" d_replace["sounds like"]="=" re_replace = re.compile("(%s)" % "|".join(map(re.escape, d_replace.keys())))
def read_xsampa_table(self): filename = os.path.join('data', 'ipa-xsampa.csv') filename = pkg_resources.resource_filename(__name__, filename) with open(filename, 'rb') as f: xs2ipa = {x[1]: x[0] for x in csv.reader(f, encoding='utf-8')} xs = sorted(xs2ipa.keys(), key=len, reverse=True) xs_regex = re.compile('|'.join(map(re.escape, xs))) return xs_regex, xs2ipa
def parse_template(self, pattern): """Parse template.""" i = ReplaceTokens(self._original, use_format=self.use_format) iter(i) self.result = [self._empty] for t in i: if len(t) > 1: if self.use_format and t[0:1] == self._lc_bracket: self.handle_format_group(t[1:-1].strip()) else: c = t[1:] if c[0:1].isdigit() and (self.use_format or len(c) == 3): value = int(c, 8) if value > 0xFF: if self.binary: # Re fails on octal greater than 0o377 or 0xFF raise ValueError("octal escape value outside of range 0-0o377!") self.result.append('\\u%04x' % value) else: self.result.append(self.string_convert('\\%03o' % value)) elif not self.use_format and (c[0:1].isdigit() or c[0:1] == self._group): self.handle_group(t) elif c == self._lc: self.single_case(i, _LOWER) elif c == self._lc_span: self.span_case(i, _LOWER) elif c == self._uc: self.single_case(i, _UPPER) elif c == self._uc_span: self.span_case(i, _UPPER) elif c == self._end: # This is here just as a reminder that \E is ignored pass else: self.result.append(t) else: self.result.append(t) if len(self.result) > 1: self.literal_slots.append(self._empty.join(self.result)) del self.result[:] self.result.append(self._empty) self.slot += 1 self._template = self._empty.join(self.literal_slots) self.groups, self.literals = self.regex_parse_template(self._template, pattern)
