summaryrefslogtreecommitdiffstats
path: root/Modules/cjkcodecs/multibytecodec.h
blob: 22ea5d4abfce1e0cea2b485a67b8b7b44c2ef698 (plain)
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
/*
 * multibytecodec.h: Common Multibyte Codec Implementation
 *
 * Written by Hye-Shik Chang <perky@FreeBSD.org>
 */

#ifndef _PYTHON_MULTIBYTECODEC_H_
#define _PYTHON_MULTIBYTECODEC_H_
#ifdef __cplusplus
extern "C" {
#endif

#ifdef uint32_t
typedef uint32_t ucs4_t;
#else
typedef unsigned int ucs4_t;
#endif

#ifdef uint16_t
typedef uint16_t ucs2_t, DBCHAR;
#else
typedef unsigned short ucs2_t, DBCHAR;
#endif

typedef union {
	void *p;
	int i;
	unsigned char c[8];
	ucs2_t u2[4];
	ucs4_t u4[2];
} MultibyteCodec_State;

typedef int (*mbcodec_init)(const void *config);
typedef Py_ssize_t (*mbencode_func)(MultibyteCodec_State *state,
			const void *config,
			const Py_UNICODE **inbuf, Py_ssize_t inleft,
			unsigned char **outbuf, Py_ssize_t outleft,
			int flags);
typedef int (*mbencodeinit_func)(MultibyteCodec_State *state,
				 const void *config);
typedef Py_ssize_t (*mbencodereset_func)(MultibyteCodec_State *state,
			const void *config,
			unsigned char **outbuf, Py_ssize_t outleft);
typedef Py_ssize_t (*mbdecode_func)(MultibyteCodec_State *state,
			const void *config,
			const unsigned char **inbuf, Py_ssize_t inleft,
			Py_UNICODE **outbuf, Py_ssize_t outleft);
typedef int (*mbdecodeinit_func)(MultibyteCodec_State *state,
				 const void *config);
typedef Py_ssize_t (*mbdecodereset_func)(MultibyteCodec_State *state,
					 const void *config);

typedef struct {
	const char *encoding;
	const void *config;
	mbcodec_init codecinit;
	mbencode_func encode;
	mbencodeinit_func encinit;
	mbencodereset_func encreset;
	mbdecode_func decode;
	mbdecodeinit_func decinit;
	mbdecodereset_func decreset;
} MultibyteCodec;

typedef struct {
	PyObject_HEAD
	MultibyteCodec *codec;
} MultibyteCodecObject;

#define MultibyteCodec_Check(op) ((op)->ob_type == &MultibyteCodec_Type)

#define _MultibyteStatefulCodec_HEAD		\
	PyObject_HEAD				\
	MultibyteCodec *codec;			\
	MultibyteCodec_State state;		\
	PyObject *errors;
typedef struct {
	_MultibyteStatefulCodec_HEAD
} MultibyteStatefulCodecContext;

#define MAXENCPENDING	2
#define _MultibyteStatefulEncoder_HEAD		\
	_MultibyteStatefulCodec_HEAD		\
	Py_UNICODE pending[MAXENCPENDING];	\
	Py_ssize_t pendingsize;
typedef struct {
	_MultibyteStatefulEncoder_HEAD
} MultibyteStatefulEncoderContext;

#define MAXDECPENDING	8
#define _MultibyteStatefulDecoder_HEAD		\
	_MultibyteStatefulCodec_HEAD		\
	unsigned char pending[MAXDECPENDING];	\
	Py_ssize_t pendingsize;
typedef struct {
	_MultibyteStatefulDecoder_HEAD
} MultibyteStatefulDecoderContext;

typedef struct {
	_MultibyteStatefulEncoder_HEAD
} MultibyteIncrementalEncoderObject;

typedef struct {
	_MultibyteStatefulDecoder_HEAD
} MultibyteIncrementalDecoderObject;

typedef struct {
	_MultibyteStatefulDecoder_HEAD
	PyObject *stream;
} MultibyteStreamReaderObject;

typedef struct {
	_MultibyteStatefulEncoder_HEAD
	PyObject *stream;
} MultibyteStreamWriterObject;

/* positive values for illegal sequences */
#define MBERR_TOOSMALL		(-1) /* insufficient output buffer space */
#define MBERR_TOOFEW		(-2) /* incomplete input buffer */
#define MBERR_INTERNAL		(-3) /* internal runtime error */

#define ERROR_STRICT		(PyObject *)(1)
#define ERROR_IGNORE		(PyObject *)(2)
#define ERROR_REPLACE		(PyObject *)(3)
#define ERROR_ISCUSTOM(p)	((p) < ERROR_STRICT || ERROR_REPLACE < (p))
#define ERROR_DECREF(p) do {			\
	if (p != NULL && ERROR_ISCUSTOM(p)) {	\
		Py_DECREF(p);			\
	}					\
} while (0);

#define MBENC_FLUSH		0x0001 /* encode all characters encodable */
#define MBENC_MAX		MBENC_FLUSH

#ifdef __cplusplus
}
#endif
#endif
..) Matches the RE inside the parentheses. The contents can be retrieved or matched later in the string. (?aiLmsux) Set the A, I, L, M, S, U, or X flag for the RE (see below). (?:...) Non-grouping version of regular parentheses. (?P<name>...) The substring matched by the group is accessible by name. (?P=name) Matches the text matched earlier by the group named name. (?#...) A comment; ignored. (?=...) Matches if ... matches next, but doesn't consume the string. (?!...) Matches if ... doesn't match next. (?<=...) Matches if preceded by ... (must be fixed length). (?<!...) Matches if not preceded by ... (must be fixed length). (?(id/name)yes|no) Matches yes pattern if the group with id/name matched, the (optional) no pattern otherwise. The special sequences consist of "\\" and a character from the list below. If the ordinary character is not on the list, then the resulting RE will match the second character. \number Matches the contents of the group of the same number. \A Matches only at the start of the string. \Z Matches only at the end of the string. \b Matches the empty string, but only at the start or end of a word. \B Matches the empty string, but not at the start or end of a word. \d Matches any decimal digit; equivalent to the set [0-9] in bytes patterns or string patterns with the ASCII flag. In string patterns without the ASCII flag, it will match the whole range of Unicode digits. \D Matches any non-digit character; equivalent to [^\d]. \s Matches any whitespace character; equivalent to [ \t\n\r\f\v] in bytes patterns or string patterns with the ASCII flag. In string patterns without the ASCII flag, it will match the whole range of Unicode whitespace characters. \S Matches any non-whitespace character; equivalent to [^\s]. \w Matches any alphanumeric character; equivalent to [a-zA-Z0-9_] in bytes patterns or string patterns with the ASCII flag. In string patterns without the ASCII flag, it will match the range of Unicode alphanumeric characters (letters plus digits plus underscore). With LOCALE, it will match the set [0-9_] plus characters defined as letters for the current locale. \W Matches the complement of \w. \\ Matches a literal backslash. This module exports the following functions: match Match a regular expression pattern to the beginning of a string. search Search a string for the presence of a pattern. sub Substitute occurrences of a pattern found in a string. subn Same as sub, but also return the number of substitutions made. split Split a string by the occurrences of a pattern. findall Find all occurrences of a pattern in a string. finditer Return an iterator yielding a match object for each match. compile Compile a pattern into a RegexObject. purge Clear the regular expression cache. escape Backslash all non-alphanumerics in a string. Some of the functions in this module takes flags as optional parameters: A ASCII For string patterns, make \w, \W, \b, \B, \d, \D match the corresponding ASCII character categories (rather than the whole Unicode categories, which is the default). For bytes patterns, this flag is the only available behaviour and needn't be specified. I IGNORECASE Perform case-insensitive matching. L LOCALE Make \w, \W, \b, \B, dependent on the current locale. M MULTILINE "^" matches the beginning of lines (after a newline) as well as the string. "$" matches the end of lines (before a newline) as well as the end of the string. S DOTALL "." matches any character at all, including the newline. X VERBOSE Ignore whitespace and comments for nicer looking RE's. U UNICODE For compatibility only. Ignored for string patterns (it is the default), and forbidden for bytes patterns. This module also defines an exception 'error'. """ import sys import sre_compile import sre_parse import functools # public symbols __all__ = [ "match", "search", "sub", "subn", "split", "findall", "compile", "purge", "template", "escape", "A", "I", "L", "M", "S", "X", "U", "ASCII", "IGNORECASE", "LOCALE", "MULTILINE", "DOTALL", "VERBOSE", "UNICODE", "error" ] __version__ = "2.2.1" # flags A = ASCII = sre_compile.SRE_FLAG_ASCII # assume ascii "locale" I = IGNORECASE = sre_compile.SRE_FLAG_IGNORECASE # ignore case L = LOCALE = sre_compile.SRE_FLAG_LOCALE # assume current 8-bit locale U = UNICODE = sre_compile.SRE_FLAG_UNICODE # assume unicode "locale" M = MULTILINE = sre_compile.SRE_FLAG_MULTILINE # make anchors look for newline S = DOTALL = sre_compile.SRE_FLAG_DOTALL # make dot match newline X = VERBOSE = sre_compile.SRE_FLAG_VERBOSE # ignore whitespace and comments # sre extensions (experimental, don't rely on these) T = TEMPLATE = sre_compile.SRE_FLAG_TEMPLATE # disable backtracking DEBUG = sre_compile.SRE_FLAG_DEBUG # dump pattern after compilation # sre exception error = sre_compile.error # -------------------------------------------------------------------- # public interface def match(pattern, string, flags=0): """Try to apply the pattern at the start of the string, returning a match object, or None if no match was found.""" return _compile(pattern, flags).match(string) def search(pattern, string, flags=0): """Scan through string looking for a match to the pattern, returning a match object, or None if no match was found.""" return _compile(pattern, flags).search(string) def sub(pattern, repl, string, count=0, flags=0): """Return the string obtained by replacing the leftmost non-overlapping occurrences of the pattern in string by the replacement repl. repl can be either a string or a callable; if a string, backslash escapes in it are processed. If it is a callable, it's passed the match object and must return a replacement string to be used.""" return _compile(pattern, flags).sub(repl, string, count) def subn(pattern, repl, string, count=0, flags=0): """Return a 2-tuple containing (new_string, number). new_string is the string obtained by replacing the leftmost non-overlapping occurrences of the pattern in the source string by the replacement repl. number is the number of substitutions that were made. repl can be either a string or a callable; if a string, backslash escapes in it are processed. If it is a callable, it's passed the match object and must return a replacement string to be used.""" return _compile(pattern, flags).subn(repl, string, count) def split(pattern, string, maxsplit=0, flags=0): """Split the source string by the occurrences of the pattern, returning a list containing the resulting substrings. If capturing parentheses are used in pattern, then the text of all groups in the pattern are also returned as part of the resulting list. If maxsplit is nonzero, at most maxsplit splits occur, and the remainder of the string is returned as the final element of the list.""" return _compile(pattern, flags).split(string, maxsplit) def findall(pattern, string, flags=0): """Return a list of all non-overlapping matches in the string. If one or more capturing groups are present in the pattern, return a list of groups; this will be a list of tuples if the pattern has more than one group. Empty matches are included in the result.""" return _compile(pattern, flags).findall(string) if sys.hexversion >= 0x02020000: __all__.append("finditer") def finditer(pattern, string, flags=0): """Return an iterator over all non-overlapping matches in the string. For each match, the iterator returns a match object. Empty matches are included in the result.""" return _compile(pattern, flags).finditer(string) def compile(pattern, flags=0): "Compile a regular expression pattern, returning a pattern object." return _compile(pattern, flags) def purge(): "Clear the regular expression caches" _cache.clear() _cache_repl.clear() def template(pattern, flags=0): "Compile a template pattern, returning a pattern object" return _compile(pattern, flags|T) _alphanum_str = frozenset( "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890") _alphanum_bytes = frozenset( b"abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890") def escape(pattern): "Escape all non-alphanumeric characters in pattern." if isinstance(pattern, str): alphanum = _alphanum_str s = list(pattern) for i, c in enumerate(pattern): if c not in alphanum: if c == "\000": s[i] = "\\000" else: s[i] = "\\" + c return "".join(s) else: alphanum = _alphanum_bytes s = [] esc = ord(b"\\") for c in pattern: if c in alphanum: s.append(c) else: if c == 0: s.extend(b"\\000") else: s.append(esc) s.append(c) return bytes(s) # -------------------------------------------------------------------- # internals _cache = {} _cache_repl = {} _pattern_type = type(sre_compile.compile("", 0)) _MAXCACHE = 512 def _compile(pattern, flags): # internal: compile pattern try: return _cache[type(pattern), pattern, flags] except KeyError: pass if isinstance(pattern, _pattern_type): if flags: raise ValueError( "Cannot process flags argument with a compiled pattern") return pattern if not sre_compile.isstring(pattern): raise TypeError("first argument must be string or compiled pattern") p = sre_compile.compile(pattern, flags) if len(_cache) >= _MAXCACHE: _cache.clear() _cache[type(pattern), pattern, flags] = p return p def _compile_repl(repl, pattern): # internal: compile replacement pattern try: return _cache_repl[repl, pattern] except KeyError: pass p = sre_parse.parse_template(repl, pattern) if len(_cache_repl) >= _MAXCACHE: _cache_repl.clear() _cache_repl[repl, pattern] = p return p def _expand(pattern, match, template): # internal: match.expand implementation hook template = sre_parse.parse_template(template, pattern) return sre_parse.expand_template(template, match) def _subx(pattern, template): # internal: pattern.sub/subn implementation helper template = _compile_repl(template, pattern) if not template[0] and len(template[1]) == 1: # literal replacement return template[1][0] def filter(match, template=template): return sre_parse.expand_template(template, match) return filter # register myself for pickling import copyreg def _pickle(p): return _compile, (p.pattern, p.flags) copyreg.pickle(_pattern_type, _pickle, _compile) # -------------------------------------------------------------------- # experimental stuff (see python-dev discussions for details) class Scanner: def __init__(self, lexicon, flags=0): from sre_constants import BRANCH, SUBPATTERN self.lexicon = lexicon # combine phrases into a compound pattern p = [] s = sre_parse.Pattern() s.flags = flags for phrase, action in lexicon: p.append(sre_parse.SubPattern(s, [ (SUBPATTERN, (len(p)+1, sre_parse.parse(phrase, flags))), ])) s.groups = len(p)+1 p = sre_parse.SubPattern(s, [(BRANCH, (None, p))]) self.scanner = sre_compile.compile(p) def scan(self, string): result = [] append = result.append match = self.scanner.scanner(string).match i = 0 while 1: m = match() if not m: break j = m.end() if i == j: break action = self.lexicon[m.lastindex-1][1] if callable(action): self.match = m action = action(self, m.group()) if action is not None: append(action) i = j return result, string[i:]