Initial commit

2025-11-23 13:37:08 +11:00
commit d1711accde
10 changed files with 499 additions and 0 deletions
--- a/src/lexer.c
+++ b/src/lexer.c
@@ -0,0 +1,144 @@
+#include "lexer.h"
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <string.h>
+
+void addTokenToLine(TokenLine* line, Token tok) {
+    line->count++;
+    Token* newTokens = realloc(line->tokens, line->count * sizeof(Token));
+    if (!newTokens) {
+        perror("Failed to allocate token");
+        exit(EXIT_FAILURE);
+    }
+    line->tokens = newTokens;
+    line->tokens[line->count - 1] = tok;
+}
+
+void addLineToLexed(LexedFile* lf, TokenLine line) {
+    lf->lineCount++;
+    TokenLine* newLines = realloc(lf->lines, lf->lineCount * sizeof(TokenLine));
+    if (!newLines) {
+        perror("Failed to allocate line");
+        exit(EXIT_FAILURE);
+    }
+    lf->lines = newLines;
+    lf->lines[lf->lineCount - 1] = line;
+}
+
+LexedFile lexFile(const char* fileContents) {
+    LexedFile result = {0};
+    result.lines = NULL;
+    result.lineCount = 0;
+    
+    TokenLine currentLine = {0};
+    currentLine.tokens = NULL;
+    currentLine.count = 0;
+    
+    char buf[1024] = {0};
+    size_t bufLen = 0;
+    bool inString = false;
+    bool inChar = false;
+    bool isComment = false;
+    
+    for (size_t i = 0; fileContents[i] != '\0'; i++) {
+        char c = fileContents[i];
+        
+        switch (c) {
+            case '"':
+                if (!isComment) {
+                    if (inChar) {
+                        buf[bufLen++] = c;
+                    } else {
+                        inString = !inString;
+                        buf[bufLen++] = c;
+                    }
+                }
+                break;
+                
+            case '\'':
+                if (!isComment) {
+                    if (inString) {
+                        buf[bufLen++] = c;
+                    } else {
+                        inChar = !inChar;
+                        buf[bufLen++] = c;
+                    }
+                }
+                break;
+                
+            case '\n':
+                if (!inString && !inChar) {
+                    // Add current token to line if exists
+                    if (bufLen > 0) {
+                        buf[bufLen] = '\0';
+                        Token tok;
+                        tok.text = strdup(buf);
+                        // Add tok to currentLine (need helper function)
+                        addTokenToLine(&currentLine, tok);
+                        bufLen = 0;
+                    }
+                    // Add line to result (need helper function)
+                    addLineToLexed(&result, currentLine);
+                    // Reset for next line
+                    currentLine.tokens = NULL;
+                    currentLine.count = 0;
+                    isComment = false;
+                } else if (!isComment) {
+                    buf[bufLen++] = c;
+                }
+                break;
+                
+            case '#':
+                if (!inString && !inChar) {
+                    isComment = true;
+                    if (bufLen > 0) {
+                        buf[bufLen] = '\0';
+                        Token tok;
+                        tok.text = strdup(buf);
+                        addTokenToLine(&currentLine, tok);
+                        bufLen = 0;
+                    }
+                    addLineToLexed(&result, currentLine);
+                    currentLine.tokens = NULL;
+                    currentLine.count = 0;
+                } else {
+                    buf[bufLen++] = c;
+                }
+                break;
+                
+            case ' ':
+                if (!inString && !inChar) {
+                    if (bufLen > 0 && !isComment) {
+                        buf[bufLen] = '\0';
+                        Token tok;
+                        tok.text = strdup(buf);
+                        addTokenToLine(&currentLine, tok);
+                        bufLen = 0;
+                    }
+                } else {
+                    buf[bufLen++] = c;
+                }
+                break;
+                
+            default:
+                if (!isComment) {
+                    buf[bufLen++] = c;
+                }
+                break;
+        }
+    }
+    
+    // Handle any remaining content
+    if (bufLen > 0) {
+        buf[bufLen] = '\0';
+        Token tok;
+        tok.text = strdup(buf);
+        addTokenToLine(&currentLine, tok);
+    }
+    if (currentLine.count > 0) {
+        addLineToLexed(&result, currentLine);
+    }
+    
+    return result;
+}