herbglitch/archeus
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

added parserlang though it is throwing error when it should be good in testing, need to fix

Browse source
This commit is contained in:
herbglitch 2024-11-06 06:45:04 -07:00
parent 9221d1e33e
commit b702431c88
5 changed files with 152 additions and 94 deletions
Download patch file Download diff file Expand all files Collapse all files

117
include/arc/std/parser/parserlang.h
View file

@ -5,9 +5,35 @@
extern "C" {
#endif
#include <arc/std/lexer.h>
#include <arc/std/parser.h>
#include <arc/std/string.h>
#include "arc/std/parser.h"
/*
<line> -> <body> NEWLINE <line> | <body> | NEWLINE <line> | LAMBDA
<body> -> <tag> WHITESPACE ARROW WHITESPACE <arguments>
<arguments> -> <argument> WHITESPACE OR WHITESPACE <arguments> | <tagOrConstant>
<argument> -> <tagOrConstant> WHITESPACE <argument> | <tagOrConstant>
<tagOrConstant> -> <parserLangageTag> | <constant>
<constant> -> ALPHA_UPPER_CHAR <constantBody>
<constantBody> -> <constantChar> <constantBody> | LAMBDA
<constantChar> -> ALPHA_UPPER_CHAR | UNDERSCORE
<tag> -> LESS_THAN <variable> GREATER_THAN
<variable> -> <alphaChar> <variableBody> | UNDERSCORE <variableBody>
<variableBody> -> <variableChar> <variableBody> | LAMBDA
<variableChar> -> <alphaChar> | NUMBER | UNDERSCORE
<alphaChar> -> ALPHA_LOWER_CHAR | ALPHA_UPPER_CHAR
*/
/*
* @brief creates a parser for the Parser Lang
*
* @note the rules will be inited for the parser lang
*
* @param[out] parser the parser to create
*/
void ARC_Parser_CreateAsParserLang(ARC_Parser **parser);
#define ARC_PARSERLANG_TOKEN_NULL 0
#define ARC_PARSERLANG_TOKEN_NUMBER 1
@ -44,91 +70,6 @@ extern "C" {
#define ARC_PARSERLANG_VARIABLE_CHAR 22
#define ARC_PARSERLANG_ALPHA_CHAR 23
void ARC_Language_InitLexerRulesFn(ARC_Lexer *lexer){
//null
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_PARSERLANG_TOKEN_NULL, 0));
//number
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharOrBetween(ARC_PARSERLANG_TOKEN_NUMBER, '0', '9'));
//alpha char
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharOrBetween(ARC_PARSERLANG_TOKEN_ALPHA_LOWER_CHAR, 'a', 'z'));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharOrBetween(ARC_PARSERLANG_TOKEN_ALPHA_UPPER_CHAR, 'A', 'Z'));
//whitespace
ARC_String *whitespaceString;
ARC_String_CreateWithStrlen(&whitespaceString, " \t");
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharInStringRule(ARC_LEXER_TOKEN_WHITESPACE, whitespaceString));
ARC_String_Destroy(whitespaceString);
//single char tokens
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_PARSERLANG_TOKEN_NEWLINE_ID , ARC_PARSERLANG_TOKEN_NEWLINE_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_PARSERLANG_TOKEN_LESS_THAN_ID , ARC_PARSERLANG_TOKEN_LESS_THAN_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_PARSERLANG_TOKEN_GREATER_THAN_ID, ARC_PARSERLANG_TOKEN_GREATER_THAN_CHAR));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_PARSERLANG_TOKEN_OR_ID , ARC_PARSERLANG_TOKEN_OR_CHAR ));
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchCharRule(ARC_PARSERLANG_TOKEN_UNDERSCORE_ID , ARC_PARSERLANG_TOKEN_UNDERSCORE_CHAR ));
//arrow
ARC_String *arrowString;
ARC_String_CreateWithStrlen(&arrowString, ARC_PARSERLANG_TOKEN_ARROW_CSTRING);
ARC_Lexer_RegisterTokenRule(lexer, ARC_LexerTokenRule_CreateAndReturnMatchStringRule(ARC_PARSERLANG_TOKEN_ARROW_ID, arrowString));
ARC_String_Destroy(arrowString);
}
/*
<line> -> <body> NEWLINE <line> | <body> | NEWLINE <line> | LAMBDA
<body> -> <tag> WHITESPACE ARROW <arguments>
<arguments> -> <argument> WHITESPACE OR WHITESPACE <arguments> | <tagOrConstant>
<argument> -> <tagOrConstant> WHITESPACE <argument> | <tagOrConstant>
<tagOrConstant> -> <parserLangageTag> | <constant>
<constant> -> ALPHA_UPPER_CHAR <constantBody>
<constantBody> -> <constantChar> <constantBody> | LAMBDA
<constantChar> -> ALPHA_UPPER_CHAR | UNDERSCORE
<tag> -> LESS_THAN <variable> GREATER_THAN
<variable> -> <noCaseAlphaChar> <variableBody> | UNDERSCORE <variableBody>
<variableBody> -> <variableChar> <variableBody> | LAMBDA
<variableChar> -> <alphaChar> | NUMBER | UNDERSCORE
<alphaChar> -> ALPHA_LOWER_CHAR | ALPHA_UPPER_CHAR
*/
//<variableBody> -> <variableChar> <variableBody> | LAMBDA
uint32_t *variableBody[] = { (uint32_t[]){ 2, ARC_PARSERLANG_VARIABLE_CHAR, ARC_PARSERLANG_VARIABLE_BODY }, (uint32_t[]){ 1, ARC_PARSERLANG_LAMBDA }};
//<variableChar> -> <alphaChar> | NUMBER | UNDERSCORE
uint32_t *variableChar[] = { (uint32_t[]){ 1, ARC_PARSERLANG_ALPHA_CHAR }, (uint32_t[]){ 1, ARC_PARSERLANG_TOKEN_NUMBER }, (uint32_t[]){ 1, ARC_PARSERLANG_TOKEN_NUMBER }};
//<alphaChar> -> ALPHA_LOWER_CHAR | ALPHA_UPPER_CHAR
uint32_t *alphaChar[] = { (uint32_t[]){ 1, ARC_PARSERLANG_TOKEN_ALPHA_LOWER_CHAR }, (uint32_t[]){ 1, ARC_PARSERLANG_TOKEN_ALPHA_UPPER_CHAR }};
/*
ARC_ParserLanguageTag testTags[3] = {
{
VARIABLE, //tagId
variableTokensOrTags, //tokensOrTags
1 //tokenOrTagsSize
},
{
VARIABLE_NAME, //tagId
variableNameTags, //tokensOrTags
2 //tokenOrTagsSize
},
{
CHAR_OR_NUM, //tagId
charOrNumTokens, //tokensOrTags
2 //tokenOrTagsSize
}
};
ARC_Array languageArray = {
3, //size
testTags //data
};
*/
#ifdef __cplusplus
}
#endif