]>
git.ipfire.org Git - thirdparty/squid.git/blob - src/parser/Tokenizer.h
2 * Copyright (C) 1996-2015 The Squid Software Foundation and contributors
4 * Squid software is distributed under GPLv2+ license and includes
5 * contributions from numerous individuals and organizations.
6 * Please see the COPYING and CONTRIBUTORS files for details.
9 #ifndef SQUID_PARSER_TOKENIZER_H_
10 #define SQUID_PARSER_TOKENIZER_H_
12 #include "base/CharacterSet.h"
15 /// Generic protocol-agnostic parsing tools
20 * Lexical processor to tokenize a buffer.
22 * Allows arbitrary delimiters and token character sets to
23 * be provided by callers.
25 * All methods start from the beginning of the input buffer.
26 * Methods returning true consume bytes from the buffer.
27 * Methods returning false have no side-effects.
32 explicit Tokenizer(const SBuf
&inBuf
) : buf_(inBuf
), parsed_(0) {}
35 SBuf
buf() const { return buf_
; }
37 /// number of parsed bytes, including skipped ones
38 SBuf::size_type
parsedSize() const { return parsed_
; }
40 /// whether the end of the buffer has been reached
41 bool atEnd() const { return buf_
.isEmpty(); }
43 /// the remaining unprocessed section of buffer
44 const SBuf
& remaining() const { return buf_
; }
46 /// reinitialize processing for a new buffer
47 void reset(const SBuf
&newBuf
) { buf_
= newBuf
; parsed_
= 0; }
50 * Skips all leading delimiters (if any),
51 * extracts all characters up to the next delimiter (a token), and
52 * skips all trailing delimiters (at least one must be present).
54 * Want to extract delimiters? Use prefix() instead.
56 * Note that Tokenizer cannot tell whether the trailing delimiters will
57 * continue when/if more input data becomes available later.
59 * \return true if found a non-empty token followed by a delimiter
61 bool token(SBuf
&returnedToken
, const CharacterSet
&delimiters
);
63 /** Extracts all sequential permitted characters up to an optional length limit.
65 * Note that Tokenizer cannot tell whether the prefix will
66 * continue when/if more input data becomes available later.
68 * \retval true one or more characters were found, the sequence (string) is placed in returnedToken
69 * \retval false no characters from the permitted set were found
71 bool prefix(SBuf
&returnedToken
, const CharacterSet
&tokenChars
, SBuf::size_type limit
= SBuf::npos
);
73 /** skips a given character sequence (string)
75 * \return whether the exact character sequence was found and skipped
77 bool skip(const SBuf
&tokenToSkip
);
79 /** skips a given single character
81 * \return whether the character was skipped
83 bool skip(const char tokenChar
);
85 /** Skips a single character from the set.
87 * \return whether a character was skipped
89 bool skipOne(const CharacterSet
&discardables
);
91 /** Skips all sequential characters from the set, in any order.
93 * \returns the number of skipped characters
95 SBuf::size_type
skipAll(const CharacterSet
&discardables
);
97 /** Extracts an unsigned int64_t at the beginning of the buffer.
99 * strtoll(3)-alike function: tries to parse unsigned 64-bit integer
100 * at the beginning of the parse buffer, in the base specified by the user
101 * or guesstimated; consumes the parsed characters.
103 * \param result Output value. Not touched if parsing is unsuccessful.
104 * \param base Specify base to do the parsing in, with the same restrictions
105 * as strtoll. Defaults to 0 (meaning guess)
107 * \return whether the parsing was successful
109 bool int64(int64_t &result
, int base
= 0);
112 SBuf
consume(const SBuf::size_type n
);
113 SBuf::size_type
success(const SBuf::size_type n
);
116 SBuf buf_
; ///< yet unparsed input
117 SBuf::size_type parsed_
; ///< bytes successfully parsed, including skipped
120 } /* namespace Parser */
122 #endif /* SQUID_PARSER_TOKENIZER_H_ */