什么是词法分析？
词法分析就是把一门语言中的各个部分区分出来.单独用表示出来.不啰嗦了,上代码.
大概就是这样吧,剩下的看工程吧,example是测试的例子.简单一些示例代码.
源码标签
代码:
typedef struct __token { char * name; short id;}var_token;extern const var_token ext_ecc_token[MAX_TOKEN];extern const var_token ext_ecc_pp[MAX_PP_TOKEN];
注释和类型.
代码:
/*Abstract description of a linked list*/typedef struct ecc_ast_alloc{/*token word list*/ short type_id; char* p_value; short value_len; struct ecc_ast_alloc * front; struct ecc_ast_alloc * after;}ecc_ast;typedef struct __ecc_comment{ char * src_comment; short src_len; short type; struct __ecc_comment * front; struct __ecc_comment * after;}ecc_comment_list;导出变量.extern ecc_comment_list * ext_comment;extern ecc_ast * ext_ecc_ast;
看下标记的枚举类型.
代码:
enum __enum_token_{ token_auto = 0x500, token_enum, token_unsigned, token_break, token_extern, token_return, token_void, token_case, token_float, token_short, token_char, token_for, token_signed, token_while, token_const, token_goto, token_sizeof, token_bool, token_continue, token_if, token_static, token_default, token_inline, token_struct, token_do, token_int, token_switch, token_double, token_long, token_typedef, token_else, token_union,};enum __enum_pp_token{ token_pp_define = 0x600, token_pp_elif, token_pp_else, token_pp_endif, token_pp_if, token_pp_ifdef, token_pp_ifndef, token_pp_include, token_pp_undef,};enum __enum_operate{ token_space = 0x257, /* ' ' \t */ token_eol, /* \n */ token_cpp_comment, /* C++ comment */ token_c_comment, /* C comment */ token_word, /* Word */ token_number, /* A number */ token_complex_divide,/* /= */ token_divide, /* / */ token_left_shift, /* << */ token_less_equal, /* <= */ token_complex_left_shift, /* <<= */ token_less, /* < */ token_right_shift, /* >> */ token_greater_equal, /* >= */ token_complex_right_shift, /* >>= */ token_greater, /* > */ token_front_subtract,/* -- */ token_ptr_member, /* -> */ token_complex_subtract,/* -= */ token_subtract, /* - */ token_complex_add, /* += */ token_add, /* + */ token_equal, /* == */ token_assignment, /* = */ token_not_equal, /* != */ token_logical_not, /* ! */ token_complex_bitwise_not, /* ~= */ token_bitwise_not, /* ~ */ token_complex_bitwise_inclusive_or, /* |= */ token_logical_or, /* || */ token_bitwise_inclusive_or, /* | */ token_logical_and, /* && */ token_complex_bitwise_and, /* &= */ token_bitwise_and, /* & */ token_complex_bitwise_exclusive_or, /* ^= */ token_bitwise_exclusive_or, /* ^ */ token_complex_remainder, /* %= */ token_remainder, /* % */ token_question, /* ? */ token_semicolon, /* ; */ token_colon, /* : */ token_comma, /* , */ token_point, /* . */ token_lparen, /* ( */ token_rparen, /* ) */ token_larray, /* [ */ token_rarray, /* ] */ token_lbrace, /* { */ token_rbrace, /* } */ token_double_quote, /* " */ token_single_quote, /* ' */ token_backslash /* \ */};
需要初始化的标记.
代码:
const var_token ext_ecc_token[MAX_TOKEN]= { {"auto",token_auto}, {"enum",token_enum}, {"unsigned",token_unsigned}, {"break",token_break}, {"extern",token_extern}, {"return",token_return}, {"void",token_void}, {"case",token_case}, {"float",token_float}, {"short",token_short}, {"char",token_char}, {"for",token_for}, {"signed",token_signed}, {"while",token_while}, {"const",token_const}, {"goto",token_goto}, {"sizeof",token_sizeof}, {"bool",token_bool}, {"continue",token_continue}, {"if",token_if}, {"static",token_static}, {"default",token_default}, {"struct",token_struct}, {"do",token_do}, {"int",token_int}, {"switch",token_switch}, {"double",token_double}, {"long",token_long}, {"typedef",token_typedef}, {"else",token_else}, {"union",token_union},};const var_token ext_ecc_pp[MAX_PP_TOKEN] = { {"#define",token_pp_define}, {"#elif",token_pp_elif}, {"#else",token_pp_else}, {"#endif",token_pp_endif}, {"#if",token_pp_if}, {"#ifdef",token_pp_ifdef}, {"#ifndef",token_pp_ifndef}, {"#include",token_pp_include}, {"#undef",token_pp_undef},};
代码:
void ecc_parse(char * src,size_t len){ if(NULL == (ext_ecc_ast = alloc_chunk(sizeof(ecc_ast)))) return; if(NULL == (ext_comment = alloc_chunk(sizeof(ecc_comment_list)))) return; g_src = src; do { if(ecc_preprocessor()) continue; if(ecc_keyword()) continue; if(ecc_identifier()) continue; if(ecc_constants()) continue; if(ecc_comment()) continue; if(ecc_operator()) continue; else ++g_src; }while(*g_src);}
|
