参考

《gcc源码分析》

词法分析

词法分析的过程就是将源代码识别成一个一个的词法符号，并在词法分析的过程中创建一些树节点，用来保存某些词法符号的值（value）。这些需要创建树节点的词法符号主要包括标识符（CPP_NAME）、关键字（CPP_KEYWORD）、数值（CPP_NUMBER）常量等。在后续的语法分析过程中，会将这些AST节点（或者AST子树）根据语法规则链接起来，形成某个函数完整的AST结构。

语法分析

语法分析就是，提前预读两个词法符号的自顶向下的语法推导过程：包括提前预读词法符号，语法分析状态以及上下文信息。

这些信息通常将保存在c_parser 这个结构体当中：

/* A parser structure recording information about the state and
   context of parsing.  Includes lexer information with up to two
   tokens of look-ahead; more are not needed for C.  */
typedef struct c_parser GTY(())
{
  /* The look-ahead tokens.  */
  c_token tokens[2];
  /* How many look-ahead tokens are available (0, 1 or 2).  */
  short tokens_avail;
  /* True if a syntax error is being recovered from; false otherwise.
     c_parser_error sets this flag.  It should clear this flag when
     enough tokens have been consumed to recover from the error.  */
  BOOL_BITFIELD error : 1;
  /* True if we're processing a pragma, and shouldn't automatically
     consume CPP_PRAGMA_EOL.  */
  BOOL_BITFIELD in_pragma : 1;
  /* True if we're parsing the outermost block of an if statement.  */
  BOOL_BITFIELD in_if_block : 1;
  /* True if we want to lex an untranslated string.  */
  BOOL_BITFIELD lex_untranslated_string : 1;
  /* Objective-C specific parser/lexer information.  */
  BOOL_BITFIELD objc_pq_context : 1;
  /* The following flag is needed to contextualize Objective-C lexical
     analysis.  In some cases (e.g., 'int NSObject;'), it is
     undesirable to bind an identifier to an Objective-C class, even
     if a class with that name exists.  */
  BOOL_BITFIELD objc_need_raw_identifier : 1;
} c_parser;

gcc对c语言进行语法分析的入口函数为c_parse_file ：

/* Parse a single source file.  */

void
c_parse_file (void)
{
  /* Use local storage to begin.  If the first token is a pragma, parse it.
     If it is #pragma GCC pch_preprocess, then this will load a PCH file
     which will cause garbage collection.  */
  c_parser tparser;

  memset (&tparser, 0, sizeof tparser);
  the_parser = &tparser;

  if (c_parser_peek_token (&tparser)->pragma_kind == PRAGMA_GCC_PCH_PREPROCESS)
    c_parser_pragma_pch_preprocess (&tparser);

  the_parser = GGC_NEW (c_parser);
  *the_parser = tparser;

  c_parser_translation_unit (the_parser);
  the_parser = NULL;
}

预读一个符号

预读一个符号，如果是PRAGMA_GCC_PCH_PREPROCESS，将进行编译的预处理工作，c_parser_pragma_pch_preprocess 为预处理函数。
c_parser_peek_token 会解析出一个token，这时会返回指向下个token的指针：

/* Return a pointer to the next token from PARSER, reading it in if
   necessary.  */

static inline c_token *
c_parser_peek_token (c_parser *parser)
{
  if (parser->tokens_avail == 0)
    {
      c_lex_one_token (parser, &parser->tokens[0]);
      parser->tokens_avail = 1;
    }
  return &parser->tokens[0];
}

解析一个单独的词法符号时，调用c_lex_one_token

/* Read in and lex a single token, storing it in *TOKEN.  */

static void
c_lex_one_token (c_parser *parser, c_token *token)
{
  timevar_push (TV_LEX);

  token->type = c_lex_with_flags (&token->value, &token->location, NULL,
				  (parser->lex_untranslated_string
				   ? C_LEX_STRING_NO_TRANSLATE : 0));
  token->id_kind = C_ID_NONE;
  token->keyword = RID_MAX;
  token->pragma_kind = PRAGMA_NONE;

  switch (token->type)
    {
    case CPP_NAME:
      {
	tree decl;

	bool objc_force_identifier = parser->objc_need_raw_identifier;
	if (c_dialect_objc ())
	  parser->objc_need_raw_identifier = false;

	if (C_IS_RESERVED_WORD (token->value))
	  {
	    enum rid rid_code = C_RID_CODE (token->value);

	    if (rid_code == RID_CXX_COMPAT_WARN)
	      {
		warning_at (token->location,
			    OPT_Wc___compat,
			    "identifier %qs conflicts with C++ keyword",
			    IDENTIFIER_POINTER (token->value));
	      }
	    else if (c_dialect_objc ())
	      {
		if (!objc_is_reserved_word (token->value)
		    && (!OBJC_IS_PQ_KEYWORD (rid_code)
			|| parser->objc_pq_context))
		  {
		    /* Return the canonical spelling for this keyword.  */
		    token->value = ridpointers[(int) rid_code];
		    token->type = CPP_KEYWORD;
		    token->keyword = rid_code;
		    break;
		  }
	      }
	    else
	      {
		token->type = CPP_KEYWORD;
		token->keyword = rid_code;
		break;
	      }
	  }

	decl = lookup_name (token->value);
	if (decl)
	  {
	    if (TREE_CODE (decl) == TYPE_DECL)
	      {
		token->id_kind = C_ID_TYPENAME;
		break;
	      }
	  }
	else if (c_dialect_objc ())
	  {
	    tree objc_interface_decl = objc_is_class_name (token->value);
	    /* Objective-C class names are in the same namespace as
	       variables and typedefs, and hence are shadowed by local
	       declarations.  */
	    if (objc_interface_decl
		&& (global_bindings_p ()
		    || (!objc_force_identifier && !decl)))
	      {
		token->value = objc_interface_decl;
		token->id_kind = C_ID_CLASSNAME;
		break;
	      }
	  }
        token->id_kind = C_ID_ID;
      }
      break;
    case CPP_AT_NAME:
      /* This only happens in Objective-C; it must be a keyword.  */
      token->type = CPP_KEYWORD;
      token->keyword = C_RID_CODE (token->value);
      break;
    case CPP_COLON:
    case CPP_COMMA:
    case CPP_CLOSE_PAREN:
    case CPP_SEMICOLON:
      /* These tokens may affect the interpretation of any identifiers
	 following, if doing Objective-C.  */
      if (c_dialect_objc ())
	parser->objc_need_raw_identifier = false;
      break;
    case CPP_PRAGMA:
      /* We smuggled the cpp_token->u.pragma value in an INTEGER_CST.  */
      token->pragma_kind = (enum pragma_kind) TREE_INT_CST_LOW (token->value);
      token->value = NULL;
      break;
    default:
      break;
    }
  timevar_pop (TV_LEX);
}

语法分析函数调用关系

重点函数分析

c_parse_file

函数c_parse_filer如上所述，是C语法分析的入口函数，该函数首先对当前的词法符号进行判断，如果该符号的编译制导类型是PRAGMA_GCC_PCH_PREPROCESS，则调用函数c_parser_pragma_pch_preprocess对进行源代码的预处理，否则，调用函数c_parser_translation_unit()进行语法推导。

c_parser_translation_unit

这个函数是进行语法分析的主流程函数：