Pushing to repo for safety.

1 files changed, 182 insertions, 0 deletions

diff --git a/src/lexer.h b/src/lexer.h
new file mode 100644
index 0000000..ca2b790
--- /dev/null
+++ b/src/lexer.h
@@ -0,0 +1,182 @@
+
+#ifndef INCLUDE_lexerlexer
+#define INCLUDE_lexerlexer
+
+#include "token.h"
+#include <ctype.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+typedef struct {
+  const char *buf;
+  int pos;
+  int line;
+  int col;
+} _LX;
+
+/* Error reporting with line/column info */
+static void perror_at(_LX *lx, const char *msg) {
+  fprintf(stderr, "[LEXER] Error at line %d, column %d: %s\n", lx->line, lx->col, msg);
+  exit(1);
+}
+
+#define sic static inline char
+#define sii static inline int
+#define siv static inline void
+#define sit static inline _T
+
+sic lxpeek(_LX *lx) { return lx->buf[lx->pos]; }
+
+sic lxget(_LX *lx) { return lx->buf[lx->pos++]; }
+
+static inline char *lx_strdup_checked(_LX *lx, const char *s) {
+  char *p = strdup(s);
+  if (!p) {
+    perror_at(lx, "out of memory");
+  }
+  return p;
+}
+
+siv lxskipws(_LX *lx) {
+  while (lxpeek(lx) == ' ' || lxpeek(lx) == '\t') {
+    if (lxpeek(lx) == '\t') lx->col += 8; else lx->col++;
+    lxget(lx);
+  }
+}
+
+sit lxnext(_LX *lx) {
+  lxskipws(lx);
+  char c = lxpeek(lx);
+  if (c == 0)
+    return (_T){TK_EOF, 0, NULL};
+  
+  // Track newlines
+  if (c == '\n') {
+    lx->line++;
+    lx->col = 0;
+    lxget(lx);
+    return lxnext(lx); // recurse to get next token
+  }
+
+  if (isalpha(c) || c == '_') {
+    int start = lx->pos;
+    while (isalnum(lxpeek(lx)) || lxpeek(lx) == '_')
+      lxget(lx);
+    int len = lx->pos - start;
+    char *text = strndup(lx->buf + start, len);
+    if (!text) {
+      perror_at(lx, "out of memory");
+    }
+    return (_T){checkkw(text), 0, text};
+  }
+  if (isdigit(c)) {
+    int start = lx->pos;
+    while (isdigit(lxpeek(lx)))
+      lxget(lx);
+    int len = lx->pos - start;
+    char *text = strndup(lx->buf + start, len);
+    if (!text) {
+      perror_at(lx, "out of memory");
+    }
+    return (_T){TK_NUMBER, atoi(text), text};
+  }
+
+  lxget(lx);
+  lx->col++;
+  // handle multi-char tokens
+  if (c == '=') {
+    if (lxpeek(lx) == '=') { lxget(lx); lx->col++; return (_T){TK_EQ,0,lx_strdup_checked(lx,"==")}; }
+    return (_T){TK_ASSIGN, 0, lx_strdup_checked(lx,"=")};
+  }
+  if (c == '!') {
+    if (lxpeek(lx) == '=') { lxget(lx); lx->col++; return (_T){TK_NE,0,lx_strdup_checked(lx,"!=")}; }
+    return (_T){TK_BANG,0,lx_strdup_checked(lx,"!")};
+  }
+  if (c == '<') {
+    if (lxpeek(lx) == '=') { lxget(lx); lx->col++; return (_T){TK_LE,0,lx_strdup_checked(lx,"<=")}; }
+    if (lxpeek(lx) == '<') { lxget(lx); lx->col++; return (_T){TK_SHL,0,lx_strdup_checked(lx,"<<")}; }
+    return (_T){TK_LT,0,lx_strdup_checked(lx,"<")};
+  }
+  if (c == '>') {
+    if (lxpeek(lx) == '=') { lxget(lx); lx->col++; return (_T){TK_GE,0,lx_strdup_checked(lx,">=")}; }
+    if (lxpeek(lx) == '>') { lxget(lx); lx->col++; return (_T){TK_SHR,0,lx_strdup_checked(lx,">>")}; }
+    return (_T){TK_GT,0,lx_strdup_checked(lx,">")};
+  }
+  if (c == '&') {
+    if (lxpeek(lx) == '&') { lxget(lx); lx->col++; return (_T){TK_AND,0,lx_strdup_checked(lx,"&&")}; }
+  }
+  if (c == '|') {
+    if (lxpeek(lx) == '|') { lxget(lx); lx->col++; return (_T){TK_OR,0,lx_strdup_checked(lx,"||")}; }
+  }
+  if (c == '"') {
+    // String literal
+    int start = lx->pos; // pos is already after the opening quote
+    while (lxpeek(lx) != '"' && lxpeek(lx) != 0) {
+      if (lxpeek(lx) == '\\') {
+        lxget(lx); // consume backslash
+        if (lxpeek(lx) != 0) lxget(lx); // consume escaped char
+      } else {
+        lxget(lx);
+      }
+    }
+    if (lxpeek(lx) == '"') {
+      int len = lx->pos - start; // length of content
+      lxget(lx); // consume closing quote
+      char *text = strndup(lx->buf + start, len); // start at content
+      if (!text) {
+        perror_at(lx, "out of memory");
+      }
+      return (_T){TK_STRING, 0, text};
+    } else {
+      perror_at(lx, "unterminated string literal");
+    }
+  }
+  switch (c) {
+  case '(':
+    return (_T){TK_LPAREN, 0, lx_strdup_checked(lx,"(")};
+  case ')':
+    return (_T){TK_RPAREN, 0, lx_strdup_checked(lx,")")};
+  case '{':
+    return (_T){TK_LBRACE, 0, lx_strdup_checked(lx,"{")};
+  case '}':
+    return (_T){TK_RBRACE, 0, lx_strdup_checked(lx,"}")};
+  case ';':
+    return (_T){TK_SEMI, 0, lx_strdup_checked(lx,";")};
+  case '+':
+    return (_T){TK_PLUS, 0, lx_strdup_checked(lx,"+")};
+  case '-':
+    return (_T){TK_MINUS, 0, lx_strdup_checked(lx,"-")};
+  case '*':
+    return (_T){TK_STAR, 0, lx_strdup_checked(lx,"*")};
+  case '/':
+    return (_T){TK_SLASH, 0, lx_strdup_checked(lx,"/")};
+  case '&':
+    return (_T){TK_AMP, 0, lx_strdup_checked(lx,"&")};
+  case '|':
+    return (_T){TK_BAR, 0, lx_strdup_checked(lx,"|")};
+  case '^':
+    return (_T){TK_CARET, 0, lx_strdup_checked(lx,"^")};
+  case '%':
+    return (_T){TK_PERCENT, 0, lx_strdup_checked(lx,"%")};
+  case ',':
+    return (_T){TK_COMMA, 0, lx_strdup_checked(lx,",")};
+  case '\'':
+    return (_T){TK_SQUOTE, 0, lx_strdup_checked(lx,"'")};
+  case '"':
+    return (_T){TK_DQUOTE, 0, lx_strdup_checked(lx,"\"")};
+  case '[':
+    return (_T){TK_LBRACKET, 0, lx_strdup_checked(lx,"[")};
+  case ']':
+    return (_T){TK_RBRACKET, 0, lx_strdup_checked(lx,"]")};
+  default:
+    return (_T){TK_INVALID, 0, NULL};
+  }
+}
+
+#undef sic
+#undef sii
+#undef siv
+#undef sit
+
+#endif