Gson源码分析开篇

反序列化

Gson所做的反序列化工作大致如下：

json本质上讲是一个结构型的文本。而Gson的核心功能之一，也是词法分析。以下是json文法。

object = {} | { members }
members = pair | pair , members
pair = string : value
array = [] | [ elements ]
elements = value  | value , elements
value = string | number | object | array | true | false | null
string = "" | " chars "
chars = char | char chars
char = any-Unicode-character-except-"-or-\-or- control-character | \" | \\ | \/ | \b | \f | \n | \r | \t | \u four-hex-digits
number = int | int frac | int exp | int frac exp
int = digit | digit1-9 digits  | - digit | - digit1-9 digits
frac = . digits
exp = e digits
digits = digit | digit digits
e = e | e+ | e-  | E | E+ | E-

词法分析的任务是要解析出Token流，Token是一个二元组，由符号和种别码构成。

public enum JsonToken {

  BEGIN_ARRAY, //数组开始

  END_ARRAY,//数组结束

  BEGIN_OBJECT,//对象开始

  END_OBJECT,//对象结束

  NAME,//键和值

  STRING,//字符串

  NUMBER,//数字

  BOOLEAN,//布尔型

  NULL,//空

  END_DOCUMENT//文本结束
}

JsonToken中包含json字符串中的所有情况。JsonScope定义了token的种别码。

final class JsonScope {

    static final int EMPTY_ARRAY = 1;

    static final int NONEMPTY_ARRAY = 2;

    static final int EMPTY_OBJECT = 3;

    static final int DANGLING_NAME = 4;

    static final int NONEMPTY_OBJECT = 5;

    static final int EMPTY_DOCUMENT = 6;

    static final int NONEMPTY_DOCUMENT = 7;
    
    static final int CLOSED = 8;
}

其中DANGLING_NAME通俗点讲就是key，当出现这种类型的字串，接下来解析出来的便是value。

解析的核心部分放在JsonReader中：

  public JsonToken peek() throws IOException {
    int p = peeked;
    if (p == PEEKED_NONE) {
      p = doPeek();
    }

    switch (p) {
    case PEEKED_BEGIN_OBJECT:
      return JsonToken.BEGIN_OBJECT;
    case PEEKED_END_OBJECT:
      return JsonToken.END_OBJECT;
    case PEEKED_BEGIN_ARRAY:
      return JsonToken.BEGIN_ARRAY;
    case PEEKED_END_ARRAY:
      return JsonToken.END_ARRAY;
    case PEEKED_SINGLE_QUOTED_NAME:
    case PEEKED_DOUBLE_QUOTED_NAME:
    case PEEKED_UNQUOTED_NAME:
      return JsonToken.NAME;
    case PEEKED_TRUE:
    case PEEKED_FALSE:
      return JsonToken.BOOLEAN;
    case PEEKED_NULL:
      return JsonToken.NULL;
    case PEEKED_SINGLE_QUOTED:
    case PEEKED_DOUBLE_QUOTED:
    case PEEKED_UNQUOTED:
    case PEEKED_BUFFERED:
      return JsonToken.STRING;
    case PEEKED_LONG:
    case PEEKED_NUMBER:
      return JsonToken.NUMBER;
    case PEEKED_EOF:
      return JsonToken.END_DOCUMENT;
    default:
      throw new AssertionError();
    }
  }

变量p便是token的种别码。peek函数返回的是一个JsonToken，调用一次，返回一个，并非一次性全部解析完。PEEKED_NONE表示一次读取完毕，每次调用完，p都会被赋值为PEEKED_NONE，所以会调用doPeek():

  int doPeek() throws IOException {
    int peekStack = stack[stackSize - 1];
    if (peekStack == JsonScope.EMPTY_ARRAY) {
      stack[stackSize - 1] = JsonScope.NONEMPTY_ARRAY;
    } else if (peekStack == JsonScope.NONEMPTY_ARRAY) {
      // Look for a comma before the next element.
      int c = nextNonWhitespace(true);
      switch (c) {
      case ']':
        return peeked = PEEKED_END_ARRAY;
      case ';':
        checkLenient(); // fall-through
      case ',':
        break;
      default:
        throw syntaxError("Unterminated array");
      }
    } else if (peekStack == JsonScope.EMPTY_OBJECT || peekStack == JsonScope.NONEMPTY_OBJECT) {
      stack[stackSize - 1] = JsonScope.DANGLING_NAME;
      // Look for a comma before the next element.
      if (peekStack == JsonScope.NONEMPTY_OBJECT) {
        int c = nextNonWhitespace(true);
        switch (c) {
        case '}':
          return peeked = PEEKED_END_OBJECT;
        case ';':
          checkLenient(); // fall-through
        case ',':
          break;
        default:
          throw syntaxError("Unterminated object");
        }
      }
      int c = nextNonWhitespace(true);
      switch (c) {
      case '"':
        return peeked = PEEKED_DOUBLE_QUOTED_NAME;
      case '\'':
        checkLenient();
        return peeked = PEEKED_SINGLE_QUOTED_NAME;
      case '}':
        if (peekStack != JsonScope.NONEMPTY_OBJECT) {
          return peeked = PEEKED_END_OBJECT;
        } else {
          throw syntaxError("Expected name");
        }
      default:
        checkLenient();
        pos--; // Don't consume the first character in an unquoted string.
        if (isLiteral((char) c)) {
          return peeked = PEEKED_UNQUOTED_NAME;
        } else {
          throw syntaxError("Expected name");
        }
      }
    } else if (peekStack == JsonScope.DANGLING_NAME) {
      stack[stackSize - 1] = JsonScope.NONEMPTY_OBJECT;
      // Look for a colon before the value.
      int c = nextNonWhitespace(true);
      switch (c) {
      case ':':
        break;
      case '=':
        checkLenient();
        if ((pos < limit || fillBuffer(1)) && buffer[pos] == '>') {
          pos++;
        }
        break;
      default:
        throw syntaxError("Expected ':'");
      }
    } else if (peekStack == JsonScope.EMPTY_DOCUMENT) {
      if (lenient) {
        consumeNonExecutePrefix();
      }
      stack[stackSize - 1] = JsonScope.NONEMPTY_DOCUMENT;
    } else if (peekStack == JsonScope.NONEMPTY_DOCUMENT) {
      int c = nextNonWhitespace(false);
      if (c == -1) {
        return peeked = PEEKED_EOF;
      } else {
        checkLenient();
        pos--;
      }
    } else if (peekStack == JsonScope.CLOSED) {
      throw new IllegalStateException("JsonReader is closed");
    }

    int c = nextNonWhitespace(true);
    switch (c) {
    case ']':
      if (peekStack == JsonScope.EMPTY_ARRAY) {
        return peeked = PEEKED_END_ARRAY;
      }
      // fall-through to handle ",]"
    case ';':
    case ',':
      // In lenient mode, a 0-length literal in an array means 'null'.
      if (peekStack == JsonScope.EMPTY_ARRAY || peekStack == JsonScope.NONEMPTY_ARRAY) {
        checkLenient();
        pos--;
        return peeked = PEEKED_NULL;
      } else {
        throw syntaxError("Unexpected value");
      }
    case '\'':
      checkLenient();
      return peeked = PEEKED_SINGLE_QUOTED;
    case '"':
      return peeked = PEEKED_DOUBLE_QUOTED;
    case '[':
      return peeked = PEEKED_BEGIN_ARRAY;
    case '{':
      return peeked = PEEKED_BEGIN_OBJECT;
    default:
      pos--; // Don't consume the first character in a literal value.
    }

    int result = peekKeyword();
    if (result != PEEKED_NONE) {
      return result;
    }

    result = peekNumber();
    if (result != PEEKED_NONE) {
      return result;
    }

    if (!isLiteral(buffer[pos])) {
      throw syntaxError("Expected value");
    }

    checkLenient();
    return peeked = PEEKED_UNQUOTED;
  }

调用nextNonWhitespace返回一个字符，然后根据这个字符，返回不同的类型。JsonReader中定义如下：

  private static final int PEEKED_NONE = 0;
  private static final int PEEKED_BEGIN_OBJECT = 1;
  private static final int PEEKED_END_OBJECT = 2;
  private static final int PEEKED_BEGIN_ARRAY = 3;
  private static final int PEEKED_END_ARRAY = 4;
  private static final int PEEKED_TRUE = 5;
  private static final int PEEKED_FALSE = 6;
  private static final int PEEKED_NULL = 7;
  private static final int PEEKED_SINGLE_QUOTED = 8;
  private static final int PEEKED_DOUBLE_QUOTED = 9;
  private static final int PEEKED_UNQUOTED = 10;
  /** When this is returned, the string value is stored in peekedString. */
  private static final int PEEKED_BUFFERED = 11;
  private static final int PEEKED_SINGLE_QUOTED_NAME = 12;
  private static final int PEEKED_DOUBLE_QUOTED_NAME = 13;
  private static final int PEEKED_UNQUOTED_NAME = 14;
  /** When this is returned, the integer value is stored in peekedLong. */
  private static final int PEEKED_LONG = 15;
  private static final int PEEKED_NUMBER = 16;
  private static final int PEEKED_EOF = 17;

JsonReader中，读取字符流，然后根据json方法，生成Token。