From 43ab94e9a2f18b0e40b441fedde5b4ce88046539 Mon Sep 17 00:00:00 2001
From: Tavian Barnes <tavianator@gmail.com>
Date: Mon, 26 Oct 2009 20:26:29 -0400
Subject: Begin tokenizer.

---
 dimension/tokenize.c | 114 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 114 insertions(+)
 create mode 100644 dimension/tokenize.c

(limited to 'dimension/tokenize.c')

diff --git a/dimension/tokenize.c b/dimension/tokenize.c
new file mode 100644
index 0000000..6a9a723
--- /dev/null
+++ b/dimension/tokenize.c
@@ -0,0 +1,114 @@
+/*************************************************************************
+ * Copyright (C) 2009 Tavian Barnes <tavianator@gmail.com>               *
+ *                                                                       *
+ * This file is part of Dimension.                                       *
+ *                                                                       *
+ * Dimension is free software; you can redistribute it and/or modify it  *
+ * under the terms of the GNU General Public License as published by the *
+ * Free Software Foundation; either version 3 of the License, or (at     *
+ * your option) any later version.                                       *
+ *                                                                       *
+ * Dimension is distributed in the hope that it will be useful, but      *
+ * WITHOUT ANY WARRANTY; without even the implied warranty of            *
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU     *
+ * General Public License for more details.                              *
+ *                                                                       *
+ * You should have received a copy of the GNU General Public License     *
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>. *
+ *************************************************************************/
+
+#include "tokenize.h"
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+
+dmnsn_array *
+dmnsn_tokenize(FILE *file)
+{
+  char c;
+  dmnsn_token token;
+  dmnsn_array *tokens = dmnsn_new_array(sizeof(dmnsn_token));
+
+  while (!feof(file)) {
+    fread(&c, 1, 1, file);
+
+    if (isspace(c))
+      continue;
+
+    if (c == '{') {
+      token.type  = DMNSN_LBRACE;
+      token.value = NULL;
+      dmnsn_array_push(tokens, &token);
+    } else if (c == '}') {
+      token.type  = DMNSN_RBRACE;
+      token.value = NULL;
+      dmnsn_array_push(tokens, &token);
+    } else {
+      /* Invalid character */
+      dmnsn_delete_tokens(tokens);
+      return NULL;
+    }
+  }
+
+  return tokens;
+}
+
+void
+dmnsn_delete_tokens(dmnsn_array *tokens)
+{
+  dmnsn_token *token;
+  unsigned int i;
+  for (i = 0; i < dmnsn_array_size(tokens); ++i) {
+    token = dmnsn_array_at(tokens, i);
+    free(token->value);
+  }
+  dmnsn_delete_array(tokens);
+}
+
+static const char *dmnsn_token_name(dmnsn_token_type token_type);
+
+static void
+dmnsn_print_token(FILE *file, dmnsn_token *token)
+{
+  if (token->value) {
+    fprintf(file, "(%s \"%s\")", dmnsn_token_name(token->type), token->value);
+  } else {
+    fprintf(file, "%s", dmnsn_token_name(token->type));
+  }
+}
+
+void
+dmnsn_print_token_sexpr(FILE *file, dmnsn_array *tokens)
+{
+  unsigned int i;
+  if (dmnsn_array_size(tokens) == 0) {
+    fprintf(file, "()");
+  } else {
+    fprintf(file, "(");
+    dmnsn_print_token(file, dmnsn_array_at(tokens, 0));
+
+    for (i = 1; i < dmnsn_array_size(tokens); ++i) {
+      fprintf(file, " ");
+      dmnsn_print_token(file, dmnsn_array_at(tokens, i));
+    }
+
+    fprintf(file, ")");
+  }
+
+  fprintf(file, "\n");
+}
+
+static const char *
+dmnsn_token_name(dmnsn_token_type token_type)
+{
+  switch (token_type) {
+  case DMNSN_LBRACE:
+    return "DMNSN_LBRACE";
+
+  case DMNSN_RBRACE:
+    return "DMNSN_RBRACE";
+
+  default:
+    return "UNRECOGNIZED-TOKEN";
+  }
+}
-- 
cgit v1.2.3