/usr/include/kj/parse/char.h is in libcapnp-dev 0.5.3-2ubuntu1.1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 | // Copyright (c) 2013-2014 Sandstorm Development Group, Inc. and contributors
// Licensed under the MIT License:
//
// Permission is hereby granted, free of charge, to any person obtaining a copy
// of this software and associated documentation files (the "Software"), to deal
// in the Software without restriction, including without limitation the rights
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
// copies of the Software, and to permit persons to whom the Software is
// furnished to do so, subject to the following conditions:
//
// The above copyright notice and this permission notice shall be included in
// all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
// THE SOFTWARE.
// This file contains parsers useful for character stream inputs, including parsers to parse
// common kinds of tokens like identifiers, numbers, and quoted strings.
#ifndef KJ_PARSE_CHAR_H_
#define KJ_PARSE_CHAR_H_
#if defined(__GNUC__) && !KJ_HEADER_WARNINGS
#pragma GCC system_header
#endif
#include "common.h"
#include "../string.h"
#include <inttypes.h>
namespace kj {
namespace parse {
// =======================================================================================
// Exact char/string.
class ExactString_ {
public:
constexpr inline ExactString_(const char* str): str(str) {}
template <typename Input>
Maybe<Tuple<>> operator()(Input& input) const {
const char* ptr = str;
while (*ptr != '\0') {
if (input.atEnd() || input.current() != *ptr) return nullptr;
input.next();
++ptr;
}
return Tuple<>();
}
private:
const char* str;
};
constexpr inline ExactString_ exactString(const char* str) {
return ExactString_(str);
}
template <char c>
constexpr ExactlyConst_<char, c> exactChar() {
// Returns a parser that matches exactly the character given by the template argument (returning
// no result).
return ExactlyConst_<char, c>();
}
// =======================================================================================
// Char ranges / sets
class CharGroup_ {
public:
constexpr inline CharGroup_(): bits{0, 0, 0, 0} {}
constexpr inline CharGroup_ orRange(unsigned char first, unsigned char last) const {
return CharGroup_(bits[0] | (oneBits(last + 1) & ~oneBits(first )),
bits[1] | (oneBits(last - 63) & ~oneBits(first - 64)),
bits[2] | (oneBits(last - 127) & ~oneBits(first - 128)),
bits[3] | (oneBits(last - 191) & ~oneBits(first - 192)));
}
constexpr inline CharGroup_ orAny(const char* chars) const {
return *chars == 0 ? *this : orChar(*chars).orAny(chars + 1);
}
constexpr inline CharGroup_ orChar(unsigned char c) const {
return CharGroup_(bits[0] | bit(c),
bits[1] | bit(c - 64),
bits[2] | bit(c - 128),
bits[3] | bit(c - 256));
}
constexpr inline CharGroup_ orGroup(CharGroup_ other) const {
return CharGroup_(bits[0] | other.bits[0],
bits[1] | other.bits[1],
bits[2] | other.bits[2],
bits[3] | other.bits[3]);
}
constexpr inline CharGroup_ invert() const {
return CharGroup_(~bits[0], ~bits[1], ~bits[2], ~bits[3]);
}
template <typename Input>
Maybe<char> operator()(Input& input) const {
if (input.atEnd()) return nullptr;
unsigned char c = input.current();
if ((bits[c / 64] & (1ll << (c % 64))) != 0) {
input.next();
return c;
} else {
return nullptr;
}
}
private:
typedef unsigned long long Bits64;
constexpr inline CharGroup_(Bits64 a, Bits64 b, Bits64 c, Bits64 d): bits{a, b, c, d} {}
Bits64 bits[4];
static constexpr inline Bits64 oneBits(int count) {
return count <= 0 ? 0ll : count >= 64 ? -1ll : ((1ll << count) - 1);
}
static constexpr inline Bits64 bit(int index) {
return index < 0 ? 0 : index >= 64 ? 0 : (1ll << index);
}
};
constexpr inline CharGroup_ charRange(char first, char last) {
// Create a parser which accepts any character in the range from `first` to `last`, inclusive.
// For example: `charRange('a', 'z')` matches all lower-case letters. The parser's result is the
// character matched.
//
// The returned object has methods which can be used to match more characters. The following
// produces a parser which accepts any letter as well as '_', '+', '-', and '.'.
//
// charRange('a', 'z').orRange('A', 'Z').orChar('_').orAny("+-.")
//
// You can also use `.invert()` to match the opposite set of characters.
return CharGroup_().orRange(first, last);
}
constexpr inline CharGroup_ anyOfChars(const char* chars) {
// Returns a parser that accepts any of the characters in the given string (which should usually
// be a literal). The returned parser is of the same type as returned by `charRange()` -- see
// that function for more info.
return CharGroup_().orAny(chars);
}
// =======================================================================================
namespace _ { // private
struct ArrayToString {
inline String operator()(const Array<char>& arr) const {
return heapString(arr);
}
};
} // namespace _ (private)
template <typename SubParser>
constexpr inline auto charsToString(SubParser&& subParser)
-> decltype(transform(kj::fwd<SubParser>(subParser), _::ArrayToString())) {
// Wraps a parser that returns Array<char> such that it returns String instead.
return parse::transform(kj::fwd<SubParser>(subParser), _::ArrayToString());
}
// =======================================================================================
// Basic character classes.
constexpr auto alpha = charRange('a', 'z').orRange('A', 'Z');
constexpr auto digit = charRange('0', '9');
constexpr auto alphaNumeric = alpha.orGroup(digit);
constexpr auto nameStart = alpha.orChar('_');
constexpr auto nameChar = alphaNumeric.orChar('_');
constexpr auto hexDigit = charRange('0', '9').orRange('a', 'f').orRange('A', 'F');
constexpr auto octDigit = charRange('0', '7');
constexpr auto whitespaceChar = anyOfChars(" \f\n\r\t\v");
constexpr auto controlChar = charRange(0, 0x1f).invert().orGroup(whitespaceChar).invert();
constexpr auto whitespace = many(anyOfChars(" \f\n\r\t\v"));
constexpr auto discardWhitespace = discard(many(discard(anyOfChars(" \f\n\r\t\v"))));
// Like discard(whitespace) but avoids some memory allocation.
// =======================================================================================
// Identifiers
namespace _ { // private
struct IdentifierToString {
inline String operator()(char first, const Array<char>& rest) const {
String result = heapString(rest.size() + 1);
result[0] = first;
memcpy(result.begin() + 1, rest.begin(), rest.size());
return result;
}
};
} // namespace _ (private)
constexpr auto identifier = transform(sequence(nameStart, many(nameChar)), _::IdentifierToString());
// Parses an identifier (e.g. a C variable name).
// =======================================================================================
// Integers
namespace _ { // private
inline char parseDigit(char c) {
if (c < 'A') return c - '0';
if (c < 'a') return c - 'A' + 10;
return c - 'a' + 10;
}
template <uint base>
struct ParseInteger {
inline uint64_t operator()(const Array<char>& digits) const {
return operator()('0', digits);
}
uint64_t operator()(char first, const Array<char>& digits) const {
uint64_t result = parseDigit(first);
for (char digit: digits) {
result = result * base + parseDigit(digit);
}
return result;
}
};
} // namespace _ (private)
constexpr auto integer = sequence(
oneOf(
transform(sequence(exactChar<'0'>(), exactChar<'x'>(), oneOrMore(hexDigit)), _::ParseInteger<16>()),
transform(sequence(exactChar<'0'>(), many(octDigit)), _::ParseInteger<8>()),
transform(sequence(charRange('1', '9'), many(digit)), _::ParseInteger<10>())),
notLookingAt(alpha.orAny("_.")));
// =======================================================================================
// Numbers (i.e. floats)
namespace _ { // private
struct ParseFloat {
double operator()(const Array<char>& digits,
const Maybe<Array<char>>& fraction,
const Maybe<Tuple<Maybe<char>, Array<char>>>& exponent) const;
};
} // namespace _ (private)
constexpr auto number = transform(
sequence(
oneOrMore(digit),
optional(sequence(exactChar<'.'>(), many(digit))),
optional(sequence(discard(anyOfChars("eE")), optional(anyOfChars("+-")), many(digit))),
notLookingAt(alpha.orAny("_."))),
_::ParseFloat());
// =======================================================================================
// Quoted strings
namespace _ { // private
struct InterpretEscape {
char operator()(char c) const {
switch (c) {
case 'a': return '\a';
case 'b': return '\b';
case 'f': return '\f';
case 'n': return '\n';
case 'r': return '\r';
case 't': return '\t';
case 'v': return '\v';
default: return c;
}
}
};
struct ParseHexEscape {
inline char operator()(char first, char second) const {
return (parseDigit(first) << 4) | parseDigit(second);
}
};
struct ParseHexByte {
inline byte operator()(char first, char second) const {
return (parseDigit(first) << 4) | parseDigit(second);
}
};
struct ParseOctEscape {
inline char operator()(char first, Maybe<char> second, Maybe<char> third) const {
char result = first - '0';
KJ_IF_MAYBE(digit1, second) {
result = (result << 3) | (*digit1 - '0');
KJ_IF_MAYBE(digit2, third) {
result = (result << 3) | (*digit2 - '0');
}
}
return result;
}
};
} // namespace _ (private)
constexpr auto escapeSequence =
sequence(exactChar<'\\'>(), oneOf(
transform(anyOfChars("abfnrtv'\"\\\?"), _::InterpretEscape()),
transform(sequence(exactChar<'x'>(), hexDigit, hexDigit), _::ParseHexEscape()),
transform(sequence(octDigit, optional(octDigit), optional(octDigit)),
_::ParseOctEscape())));
// A parser that parses a C-string-style escape sequence (starting with a backslash). Returns
// a char.
constexpr auto doubleQuotedString = charsToString(sequence(
exactChar<'\"'>(),
many(oneOf(anyOfChars("\\\n\"").invert(), escapeSequence)),
exactChar<'\"'>()));
// Parses a C-style double-quoted string.
constexpr auto singleQuotedString = charsToString(sequence(
exactChar<'\''>(),
many(oneOf(anyOfChars("\\\n\'").invert(), escapeSequence)),
exactChar<'\''>()));
// Parses a C-style single-quoted string.
constexpr auto doubleQuotedHexBinary = sequence(
exactChar<'0'>(), exactChar<'x'>(), exactChar<'\"'>(),
oneOrMore(transform(sequence(discardWhitespace, hexDigit, hexDigit), _::ParseHexByte())),
discardWhitespace,
exactChar<'\"'>());
// Parses a double-quoted hex binary literal. Returns Array<byte>.
} // namespace parse
} // namespace kj
#endif // KJ_PARSE_CHAR_H_
|