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
|
// Copyright (c) 2012 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#ifndef BASE_JSON_JSON_PARSER_H_
#define BASE_JSON_JSON_PARSER_H_
#include <stddef.h>
#include <stdint.h>
#include <memory>
#include <string>
#include "base/base_export.h"
#include "base/compiler_specific.h"
#include "base/gtest_prod_util.h"
#include "base/json/json_reader.h"
#include "base/macros.h"
#include "base/strings/string_piece.h"
namespace base {
class Value;
namespace internal {
class JSONParserTest;
// The implementation behind the JSONReader interface. This class is not meant
// to be used directly; it encapsulates logic that need not be exposed publicly.
//
// This parser guarantees O(n) time through the input string. It also optimizes
// base::StringValue by using StringPiece where possible when returning Value
// objects by using "hidden roots," discussed in the implementation.
//
// Iteration happens on the byte level, with the functions CanConsume and
// NextChar. The conversion from byte to JSON token happens without advancing
// the parser in GetNextToken/ParseToken, that is tokenization operates on
// the current parser position without advancing.
//
// Built on top of these are a family of Consume functions that iterate
// internally. Invariant: on entry of a Consume function, the parser is wound
// to the first byte of a valid JSON token. On exit, it is on the last byte
// of a token, such that the next iteration of the parser will be at the byte
// immediately following the token, which would likely be the first byte of the
// next token.
class BASE_EXPORT JSONParser {
public:
explicit JSONParser(int options);
~JSONParser();
// Parses the input string according to the set options and returns the
// result as a Value.
// Wrap this in base::FooValue::From() to check the Value is of type Foo and
// convert to a FooValue at the same time.
std::unique_ptr<Value> Parse(StringPiece input);
// Returns the error code.
JSONReader::JsonParseError error_code() const;
// Returns the human-friendly error message.
std::string GetErrorMessage() const;
// Returns the error line number if parse error happened. Otherwise always
// returns 0.
int error_line() const;
// Returns the error column number if parse error happened. Otherwise always
// returns 0.
int error_column() const;
private:
enum Token {
T_OBJECT_BEGIN, // {
T_OBJECT_END, // }
T_ARRAY_BEGIN, // [
T_ARRAY_END, // ]
T_STRING,
T_NUMBER,
T_BOOL_TRUE, // true
T_BOOL_FALSE, // false
T_NULL, // null
T_LIST_SEPARATOR, // ,
T_OBJECT_PAIR_SEPARATOR, // :
T_END_OF_INPUT,
T_INVALID_TOKEN,
};
// A helper class used for parsing strings. One optimization performed is to
// create base::Value with a StringPiece to avoid unnecessary std::string
// copies. This is not possible if the input string needs to be decoded from
// UTF-16 to UTF-8, or if an escape sequence causes characters to be skipped.
// This class centralizes that logic.
class StringBuilder {
public:
// Empty constructor. Used for creating a builder with which to Swap().
StringBuilder();
// |pos| is the beginning of an input string, excluding the |"|.
explicit StringBuilder(const char* pos);
~StringBuilder();
// Swaps the contents of |other| with this.
void Swap(StringBuilder* other);
// Either increases the |length_| of the string or copies the character if
// the StringBuilder has been converted. |c| must be in the basic ASCII
// plane; all other characters need to be in UTF-8 units, appended with
// AppendString below.
void Append(const char& c);
// Appends a string to the std::string. Must be Convert()ed to use.
void AppendString(const std::string& str);
// Converts the builder from its default StringPiece to a full std::string,
// performing a copy. Once a builder is converted, it cannot be made a
// StringPiece again.
void Convert();
// Returns whether the builder can be converted to a StringPiece.
bool CanBeStringPiece() const;
// Returns the StringPiece representation. Returns an empty piece if it
// cannot be converted.
StringPiece AsStringPiece();
// Returns the builder as a std::string.
const std::string& AsString();
private:
// The beginning of the input string.
const char* pos_;
// Number of bytes in |pos_| that make up the string being built.
size_t length_;
// The copied string representation. NULL until Convert() is called.
// Strong. std::unique_ptr<T> has too much of an overhead here.
std::string* string_;
};
// Quick check that the stream has capacity to consume |length| more bytes.
bool CanConsume(int length);
// The basic way to consume a single character in the stream. Consumes one
// byte of the input stream and returns a pointer to the rest of it.
const char* NextChar();
// Performs the equivalent of NextChar N times.
void NextNChars(int n);
// Skips over whitespace and comments to find the next token in the stream.
// This does not advance the parser for non-whitespace or comment chars.
Token GetNextToken();
// Consumes whitespace characters and comments until the next non-that is
// encountered.
void EatWhitespaceAndComments();
// Helper function that consumes a comment, assuming that the parser is
// currently wound to a '/'.
bool EatComment();
// Calls GetNextToken() and then ParseToken().
std::unique_ptr<Value> ParseNextToken();
// Takes a token that represents the start of a Value ("a structural token"
// in RFC terms) and consumes it, returning the result as a Value.
std::unique_ptr<Value> ParseToken(Token token);
// Assuming that the parser is currently wound to '{', this parses a JSON
// object into a DictionaryValue.
std::unique_ptr<Value> ConsumeDictionary();
// Assuming that the parser is wound to '[', this parses a JSON list into a
// std::unique_ptr<ListValue>.
std::unique_ptr<Value> ConsumeList();
// Calls through ConsumeStringRaw and wraps it in a value.
std::unique_ptr<Value> ConsumeString();
// Assuming that the parser is wound to a double quote, this parses a string,
// decoding any escape sequences and converts UTF-16 to UTF-8. Returns true on
// success and Swap()s the result into |out|. Returns false on failure with
// error information set.
bool ConsumeStringRaw(StringBuilder* out);
// Helper function for ConsumeStringRaw() that consumes the next four or 10
// bytes (parser is wound to the first character of a HEX sequence, with the
// potential for consuming another \uXXXX for a surrogate). Returns true on
// success and places the UTF8 code units in |dest_string|, and false on
// failure.
bool DecodeUTF16(std::string* dest_string);
// Helper function for ConsumeStringRaw() that takes a single code point,
// decodes it into UTF-8 units, and appends it to the given builder. The
// point must be valid.
void DecodeUTF8(const int32_t& point, StringBuilder* dest);
// Assuming that the parser is wound to the start of a valid JSON number,
// this parses and converts it to either an int or double value.
std::unique_ptr<Value> ConsumeNumber();
// Helper that reads characters that are ints. Returns true if a number was
// read and false on error.
bool ReadInt(bool allow_leading_zeros);
// Consumes the literal values of |true|, |false|, and |null|, assuming the
// parser is wound to the first character of any of those.
std::unique_ptr<Value> ConsumeLiteral();
// Compares two string buffers of a given length.
static bool StringsAreEqual(const char* left, const char* right, size_t len);
// Sets the error information to |code| at the current column, based on
// |index_| and |index_last_line_|, with an optional positive/negative
// adjustment by |column_adjust|.
void ReportError(JSONReader::JsonParseError code, int column_adjust);
// Given the line and column number of an error, formats one of the error
// message contants from json_reader.h for human display.
static std::string FormatErrorMessage(int line, int column,
const std::string& description);
// base::JSONParserOptions that control parsing.
const int options_;
// Pointer to the start of the input data.
const char* start_pos_;
// Pointer to the current position in the input data. Equivalent to
// |start_pos_ + index_|.
const char* pos_;
// Pointer to the last character of the input data.
const char* end_pos_;
// The index in the input stream to which the parser is wound.
int index_;
// The number of times the parser has recursed (current stack depth).
int stack_depth_;
// The line number that the parser is at currently.
int line_number_;
// The last value of |index_| on the previous line.
int index_last_line_;
// Error information.
JSONReader::JsonParseError error_code_;
int error_line_;
int error_column_;
friend class JSONParserTest;
FRIEND_TEST_ALL_PREFIXES(JSONParserTest, NextChar);
FRIEND_TEST_ALL_PREFIXES(JSONParserTest, ConsumeDictionary);
FRIEND_TEST_ALL_PREFIXES(JSONParserTest, ConsumeList);
FRIEND_TEST_ALL_PREFIXES(JSONParserTest, ConsumeString);
FRIEND_TEST_ALL_PREFIXES(JSONParserTest, ConsumeLiterals);
FRIEND_TEST_ALL_PREFIXES(JSONParserTest, ConsumeNumbers);
FRIEND_TEST_ALL_PREFIXES(JSONParserTest, ErrorMessages);
FRIEND_TEST_ALL_PREFIXES(JSONParserTest, ReplaceInvalidCharacters);
DISALLOW_COPY_AND_ASSIGN(JSONParser);
};
// Used when decoding and an invalid utf-8 sequence is encountered.
BASE_EXPORT extern const char kUnicodeReplacementString[];
} // namespace internal
} // namespace base
#endif // BASE_JSON_JSON_PARSER_H_
|