Python code coverage for Lib/html/init.py

#	count	content
1	n/a	"""
2	n/a	General functions for HTML manipulation.
3	n/a	"""
4	n/a
5	n/a	import re as _re
6	n/a	from html.entities import html5 as _html5
7	n/a
8	n/a
9	n/a	__all__ = ['escape', 'unescape']
10	n/a
11	n/a
12	n/a	def escape(s, quote=True):
13	n/a	"""
14	n/a	Replace special characters "&", "<" and ">" to HTML-safe sequences.
15	n/a	If the optional flag quote is true (the default), the quotation mark
16	n/a	characters, both double quote (") and single quote (') characters are also
17	n/a	translated.
18	n/a	"""
19	n/a	s = s.replace("&", "&") # Must be done first!
20	n/a	s = s.replace("<", "<")
21	n/a	s = s.replace(">", ">")
22	n/a	if quote:
23	n/a	s = s.replace('"', """)
24	n/a	s = s.replace('\'', "'")
25	n/a	return s
26	n/a
27	n/a
28	n/a	# see http://www.w3.org/TR/html5/syntax.html#tokenizing-character-references
29	n/a
30	n/a	_invalid_charrefs = {
31	n/a	0x00: '\ufffd', # REPLACEMENT CHARACTER
32	n/a	0x0d: '\r', # CARRIAGE RETURN
33	n/a	0x80: '\u20ac', # EURO SIGN
34	n/a	0x81: '\x81', # <control>
35	n/a	0x82: '\u201a', # SINGLE LOW-9 QUOTATION MARK
36	n/a	0x83: '\u0192', # LATIN SMALL LETTER F WITH HOOK
37	n/a	0x84: '\u201e', # DOUBLE LOW-9 QUOTATION MARK
38	n/a	0x85: '\u2026', # HORIZONTAL ELLIPSIS
39	n/a	0x86: '\u2020', # DAGGER
40	n/a	0x87: '\u2021', # DOUBLE DAGGER
41	n/a	0x88: '\u02c6', # MODIFIER LETTER CIRCUMFLEX ACCENT
42	n/a	0x89: '\u2030', # PER MILLE SIGN
43	n/a	0x8a: '\u0160', # LATIN CAPITAL LETTER S WITH CARON
44	n/a	0x8b: '\u2039', # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
45	n/a	0x8c: '\u0152', # LATIN CAPITAL LIGATURE OE
46	n/a	0x8d: '\x8d', # <control>
47	n/a	0x8e: '\u017d', # LATIN CAPITAL LETTER Z WITH CARON
48	n/a	0x8f: '\x8f', # <control>
49	n/a	0x90: '\x90', # <control>
50	n/a	0x91: '\u2018', # LEFT SINGLE QUOTATION MARK
51	n/a	0x92: '\u2019', # RIGHT SINGLE QUOTATION MARK
52	n/a	0x93: '\u201c', # LEFT DOUBLE QUOTATION MARK
53	n/a	0x94: '\u201d', # RIGHT DOUBLE QUOTATION MARK
54	n/a	0x95: '\u2022', # BULLET
55	n/a	0x96: '\u2013', # EN DASH
56	n/a	0x97: '\u2014', # EM DASH
57	n/a	0x98: '\u02dc', # SMALL TILDE
58	n/a	0x99: '\u2122', # TRADE MARK SIGN
59	n/a	0x9a: '\u0161', # LATIN SMALL LETTER S WITH CARON
60	n/a	0x9b: '\u203a', # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
61	n/a	0x9c: '\u0153', # LATIN SMALL LIGATURE OE
62	n/a	0x9d: '\x9d', # <control>
63	n/a	0x9e: '\u017e', # LATIN SMALL LETTER Z WITH CARON
64	n/a	0x9f: '\u0178', # LATIN CAPITAL LETTER Y WITH DIAERESIS
65	n/a	}
66	n/a
67	n/a	_invalid_codepoints = {
68	n/a	# 0x0001 to 0x0008
69	n/a	0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8,
70	n/a	# 0x000E to 0x001F
71	n/a	0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19,
72	n/a	0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
73	n/a	# 0x007F to 0x009F
74	n/a	0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8a,
75	n/a	0x8b, 0x8c, 0x8d, 0x8e, 0x8f, 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
76	n/a	0x97, 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
77	n/a	# 0xFDD0 to 0xFDEF
78	n/a	0xfdd0, 0xfdd1, 0xfdd2, 0xfdd3, 0xfdd4, 0xfdd5, 0xfdd6, 0xfdd7, 0xfdd8,
79	n/a	0xfdd9, 0xfdda, 0xfddb, 0xfddc, 0xfddd, 0xfdde, 0xfddf, 0xfde0, 0xfde1,
80	n/a	0xfde2, 0xfde3, 0xfde4, 0xfde5, 0xfde6, 0xfde7, 0xfde8, 0xfde9, 0xfdea,
81	n/a	0xfdeb, 0xfdec, 0xfded, 0xfdee, 0xfdef,
82	n/a	# others
83	n/a	0xb, 0xfffe, 0xffff, 0x1fffe, 0x1ffff, 0x2fffe, 0x2ffff, 0x3fffe, 0x3ffff,
84	n/a	0x4fffe, 0x4ffff, 0x5fffe, 0x5ffff, 0x6fffe, 0x6ffff, 0x7fffe, 0x7ffff,
85	n/a	0x8fffe, 0x8ffff, 0x9fffe, 0x9ffff, 0xafffe, 0xaffff, 0xbfffe, 0xbffff,
86	n/a	0xcfffe, 0xcffff, 0xdfffe, 0xdffff, 0xefffe, 0xeffff, 0xffffe, 0xfffff,
87	n/a	0x10fffe, 0x10ffff
88	n/a	}
89	n/a
90	n/a
91	n/a	def _replace_charref(s):
92	n/a	s = s.group(1)
93	n/a	if s[0] == '#':
94	n/a	# numeric charref
95	n/a	if s[1] in 'xX':
96	n/a	num = int(s[2:].rstrip(';'), 16)
97	n/a	else:
98	n/a	num = int(s[1:].rstrip(';'))
99	n/a	if num in _invalid_charrefs:
100	n/a	return _invalid_charrefs[num]
101	n/a	if 0xD800 <= num <= 0xDFFF or num > 0x10FFFF:
102	n/a	return '\uFFFD'
103	n/a	if num in _invalid_codepoints:
104	n/a	return ''
105	n/a	return chr(num)
106	n/a	else:
107	n/a	# named charref
108	n/a	if s in _html5:
109	n/a	return _html5[s]
110	n/a	# find the longest matching name (as defined by the standard)
111	n/a	for x in range(len(s)-1, 1, -1):
112	n/a	if s[:x] in _html5:
113	n/a	return _html5[s[:x]] + s[x:]
114	n/a	else:
115	n/a	return '&' + s
116	n/a
117	n/a
118	n/a	_charref = _re.compile(r'&(#[0-9]+;?'
119	n/a	r'\|#[xX][0-9a-fA-F]+;?'
120	n/a	r'\|[^\t\n\f <&#;]{1,32};?)')
121	n/a
122	n/a	def unescape(s):
123	n/a	"""
124	n/a	Convert all named and numeric character references (e.g. >, >,
125	n/a	&x3e;) in the string s to the corresponding unicode characters.
126	n/a	This function uses the rules defined by the HTML 5 standard
127	n/a	for both valid and invalid character references, and the list of
128	n/a	HTML 5 named character references defined in html.entities.html5.
129	n/a	"""
130	n/a	if '&' not in s:
131	n/a	return s
132	n/a	return _charref.sub(_replace_charref, s)

Python code coverage for Lib/html/__init__.py

Python code coverage for Lib/html/init.py