commit cfdd3c90877b59dc674cc9f68c0b7b4bb7c14ba8
parent 7dad37effbeaf44ec12d2ae2fcf1643d4d4351b2
Author: Thing1 <thing1@seacrossedlovers.xyz>
Date: Tue, 27 Aug 2024 10:36:18 +0100
rewrite
Diffstat:
15 files changed, 158 insertions(+), 2 deletions(-)
diff --git a/comp/lucas-standen-NEA/code/execution/exec b/comp/lucas-standen-NEA/code/execution/exec
Binary files differ.
diff --git a/comp/lucas-standen-NEA/code/proto/AST/ast b/comp/lucas-standen-NEA/code/proto/AST/ast
Binary files differ.
diff --git a/comp/lucas-standen-NEA/code/proto/parser/test b/comp/lucas-standen-NEA/code/proto/parser/test
Binary files differ.
diff --git a/comp/lucas-standen-NEA/code/tokenizer/parser.c b/comp/lucas-standen-NEA/code/tokenizer/parser.c
@@ -57,7 +57,7 @@ FILE *preProcess(char *contents){
}
char **getExpressions(char *file){ // this doesn't work because str gets overwritten which changes the data stored at it's pointer, memcpy should be used
- char **code = CheckedMalloc((strlen(file)/2)*sizeof(char *));
+ char **code = CheckedMalloc(strlen(file)/4);
int counter = 0;
int depth = 0;
char *str = CheckedMalloc(strlen(file)+1);
@@ -73,7 +73,8 @@ char **getExpressions(char *file){ // this doesn't work because str gets overwri
if (depth == 0) {
str[pos] = '\0';
printf("%s\n", str);
- code[counter] = str;
+ code[counter] = malloc(strlen(str)+1);
+ memcpy(code[counter], str, strlen((str)+1));
counter++;
pos = 0;
}
diff --git a/comp/lucas-standen-NEA/code/zpy/zpy b/comp/lucas-standen-NEA/code/zpy/zpy
Binary files differ.
diff --git a/comp/lucas-standen-NEA/code2/Makefile b/comp/lucas-standen-NEA/code2/Makefile
@@ -0,0 +1,16 @@
+CFLAGS= -O0 -ggdb
+
+all: _zpy _parser _tokenizer _util
+ cc zpy.o parser.o tokenizer.o util.o -o zpy ${CFLAGS}
+
+_zpy: zpy.c
+ cc zpy.c -c -o zpy.o ${CFLAGS}
+_parser: parser.c
+ cc parser.c -c -o parser.o ${CFLAGS}
+_tokenizer: tokenizer.c
+ cc tokenizer.c -c -o tokenizer.o ${CFLAGS}
+_util: util.c
+ cc util.c -c -o util.o ${CFLAGS}
+
+clean:
+ rm -rf zpy *.o
diff --git a/comp/lucas-standen-NEA/code2/TODO b/comp/lucas-standen-NEA/code2/TODO
@@ -0,0 +1,2 @@
+make the tokenizer work, it needs to call recursively whenever it see's a '(' execept the first
+expression, perhaps cut them off before the call
diff --git a/comp/lucas-standen-NEA/code2/parser.c b/comp/lucas-standen-NEA/code2/parser.c
@@ -0,0 +1,51 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "util.h"
+
+int countChars(char *s, char c){
+ int count = 0;
+ for (int i = 0; i < strlen(s); i++){
+ if (s[i] == c) count++;
+ }
+ return count;
+}
+
+char **parse(FILE *f){
+ fseek(f, 0, SEEK_END);
+ int len = ftell(f);
+ rewind(f);
+
+ char *contents = malloc(len);
+
+ if (fread(contents, 1, len, f) == 0){
+ die("failed to read file, is it formated properly");
+ }
+
+ char **tokens = malloc(countChars(contents, '\n'));
+
+ int tokCount = 0;
+ int charCount = 0;
+ char *line = malloc(strlen(contents));
+ for (int i = 0; i < len; i++){
+ line[charCount] = contents[i];
+ charCount++;
+
+ if (contents[i] == '\n'){
+ charCount--;
+ line[charCount] = '\0';
+ tokens[tokCount] = malloc(strlen(line)+1);
+
+ memcpy(tokens[tokCount], line, strlen(line)+1);
+ charCount = 0;
+ tokCount++;
+ }
+ }
+
+ free(line);
+ free(contents);
+
+ return tokens;
+}
diff --git a/comp/lucas-standen-NEA/code2/parser.h b/comp/lucas-standen-NEA/code2/parser.h
@@ -0,0 +1,3 @@
+#include <stdio.h>
+
+char **parse(FILE *f);
diff --git a/comp/lucas-standen-NEA/code2/sample.zpy b/comp/lucas-standen-NEA/code2/sample.zpy
@@ -0,0 +1 @@
+(let a:i64 (+ 2 3))
diff --git a/comp/lucas-standen-NEA/code2/tokenizer.c b/comp/lucas-standen-NEA/code2/tokenizer.c
@@ -0,0 +1,42 @@
+#include <stdlib.h>
+#include <stdio.h>
+#include<string.h>
+
+#include "util.h"
+
+typedef struct astNode {
+ char *funcName;
+ char *args[8];
+ struct astNode *children[8];
+} astNode;
+
+astNode *tokenize(char *line){
+ astNode *head = malloc(sizeof(astNode));
+
+ int depth = 0;
+ int charCount = 0;
+ int argCount = 0;
+
+
+ for (int i = 0; i < strlen(line); i++){
+ switch (line[i]){
+ case ' ':
+ argCount++;
+ charCount = 0;
+ break;
+ case '(':
+ 1
+ default:
+ if (argCount >= 1){
+ head->args[argCount][charCount] = line[i];
+ charCount++;
+ }
+ else {
+ head->funcName[charCount] = line[i];
+ charCount++;
+ }
+ }
+ }
+
+ return NULL;
+}
diff --git a/comp/lucas-standen-NEA/code2/tokenizer.h b/comp/lucas-standen-NEA/code2/tokenizer.h
@@ -0,0 +1,7 @@
+typedef struct astNode {
+ char *funcName;
+ char *args[8];
+ struct astNode *children[8];
+} astNode;
+
+astNode *tokenize(char *line);
diff --git a/comp/lucas-standen-NEA/code2/util.c b/comp/lucas-standen-NEA/code2/util.c
@@ -0,0 +1,9 @@
+#include <stdlib.h>
+#include <stdio.h>
+
+void die(char *msg){
+ fprintf(stderr, "zpy: %s\n", msg);
+ exit(1);
+
+}
+
diff --git a/comp/lucas-standen-NEA/code2/util.h b/comp/lucas-standen-NEA/code2/util.h
@@ -0,0 +1 @@
+void die(char *msg);
diff --git a/comp/lucas-standen-NEA/code2/zpy.c b/comp/lucas-standen-NEA/code2/zpy.c
@@ -0,0 +1,23 @@
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "util.h"
+#include "parser.h"
+#include "tokenizer.h"
+
+int main(int argc, char **argv){
+ if (argc < 2)
+ die("no input files!");
+
+ FILE *f = fopen(argv[1], "r");
+ if (f == NULL)
+ die("no such file or directory");
+
+ char **stringTokens = parse(f);
+
+ if (stringTokens == NULL)
+ die("couldn't parse file, is it formated properly?");
+
+ tokenize(stringTokens[0]);
+
+}
