From 1b56aaa185873e24206e446e980df25fc80e4503 Mon Sep 17 00:00:00 2001
From: Abdelrahman Said <said.abdelrahman89@gmail.com>
Date: Tue, 20 Jun 2023 23:37:56 +0100
Subject: [PATCH] Started implementing the get_next_token function

---
 compile_commands.json | 12 ++++----
 include/lexer/lexer.h |  6 ++++
 src/lexer/lexer.c     | 66 +++++++++++++++++++++++++++++++++++++++++++
 src/main.c            | 16 ++++++++++-
 4 files changed, 93 insertions(+), 7 deletions(-)

diff --git a/compile_commands.json b/compile_commands.json
index 0c2bf13..327951b 100644
--- a/compile_commands.json
+++ b/compile_commands.json
@@ -118,12 +118,12 @@
       "-x",
       "c",
       "-o",
-      "/tmp/main-368473.o",
+      "/tmp/main-1df523.o",
       "src/main.c"
     ],
     "directory": "/mnt/3A5CDF785CDF2CFF/Users/abdoo/dev/say_it_in_json",
     "file": "/mnt/3A5CDF785CDF2CFF/Users/abdoo/dev/say_it_in_json/src/main.c",
-    "output": "/tmp/main-368473.o"
+    "output": "/tmp/main-1df523.o"
   },
   {
     "arguments": [
@@ -187,12 +187,12 @@
       "-x",
       "c",
       "-o",
-      "/tmp/dstring-ea8650.o",
+      "/tmp/dstring-3eff44.o",
       "src/dstring/dstring.c"
     ],
     "directory": "/mnt/3A5CDF785CDF2CFF/Users/abdoo/dev/say_it_in_json",
     "file": "/mnt/3A5CDF785CDF2CFF/Users/abdoo/dev/say_it_in_json/src/dstring/dstring.c",
-    "output": "/tmp/dstring-ea8650.o"
+    "output": "/tmp/dstring-3eff44.o"
   },
   {
     "arguments": [
@@ -256,11 +256,11 @@
       "-x",
       "c",
       "-o",
-      "/tmp/lexer-403cee.o",
+      "/tmp/lexer-b7cbfb.o",
       "src/lexer/lexer.c"
     ],
     "directory": "/mnt/3A5CDF785CDF2CFF/Users/abdoo/dev/say_it_in_json",
     "file": "/mnt/3A5CDF785CDF2CFF/Users/abdoo/dev/say_it_in_json/src/lexer/lexer.c",
-    "output": "/tmp/lexer-403cee.o"
+    "output": "/tmp/lexer-b7cbfb.o"
   }
 ]
diff --git a/include/lexer/lexer.h b/include/lexer/lexer.h
index 808db9d..3e25a72 100644
--- a/include/lexer/lexer.h
+++ b/include/lexer/lexer.h
@@ -33,12 +33,18 @@ typedef union {
 } token_value_t;
 
 typedef struct {
+  u64 line;
+  u64 column;
   token_type_t type;
   token_value_t value;
 } token_t;
 
 typedef struct lexer lexer_t;
 
+void lexer_init(lexer_t **lexer);
+void lexer_free(lexer_t **lexer);
+token_t get_next_token(lexer_t *lexer, const char *text);
+
 bool validate_json(char *json);
 
 #endif // !LEXER_STATES_H
diff --git a/src/lexer/lexer.c b/src/lexer/lexer.c
index dd930da..f49b196 100644
--- a/src/lexer/lexer.c
+++ b/src/lexer/lexer.c
@@ -78,8 +78,11 @@ typedef struct {
 } lexer_string_t;
 
 struct lexer {
+  u64 cursor;
   u64 line;
   u64 column;
+  const char *text;
+  u64 text_length;
   lexer_state_t current;
   state_stack_t stack;
   lexer_string_t keyword;
@@ -124,6 +127,69 @@ lexer_state_t handle_keyword_end(lexer_t *lexer, char input);
 // TODO (Abdelrahman): The printf functions in the state handlers are the exit
 // points for the tokenisation function. Replace them once ready.
 
+void lexer_init(lexer_t **lexer) {
+  if (*lexer) {
+    lexer_free(lexer);
+  }
+
+  *lexer = (lexer_t *)malloc(sizeof(lexer_t));
+
+  if (!(*lexer)) {
+    return;
+  }
+
+  (*lexer)->cursor = 0;
+  (*lexer)->line = 1;
+  (*lexer)->column = 0;
+  (*lexer)->current = LEXER_STATE_START;
+  (*lexer)->keyword.type = LEXER_STRING_KEYWORD;
+  (*lexer)->codepoint.type = LEXER_STRING_UNICODE;
+  (*lexer)->current_string = dstr_with_capacity(STRING_BUF_START_CAPACITY);
+
+  if (!((*lexer)->current_string)) {
+    lexer_free(lexer);
+  }
+}
+
+void lexer_free(lexer_t **lexer) {
+  if (!(*lexer)) {
+    return;
+  }
+
+  free(*lexer);
+  *lexer = NULL;
+}
+
+token_t get_next_token(lexer_t *lexer, const char *text) {
+  if (text != NULL) {
+    lexer->cursor = 0;
+    lexer->text = text;
+    lexer->text_length = strlen(text);
+  }
+
+  char c;
+
+  for (; lexer->cursor < lexer->text_length; ++(lexer->cursor)) {
+    c = lexer->text[lexer->cursor];
+
+    if (c == '\n') {
+      ++(lexer->line);
+      lexer->column = 0;
+      continue;
+    }
+
+    lexer_state_machine(lexer, c);
+
+    // Track the position in the text
+    ++(lexer->column);
+
+    if (lexer->current == LEXER_STATE_ERROR) {
+    }
+  }
+
+  return (token_t){0};
+}
+
 bool validate_json(char *json) {
   lexer_t lexer = {0};
   lexer.line = 1;
diff --git a/src/main.c b/src/main.c
index e07b667..a1edb94 100644
--- a/src/main.c
+++ b/src/main.c
@@ -4,6 +4,8 @@
 #include <stdlib.h>
 #include <string.h>
 
+#define BUFFER_LENGTH 128
+
 int main(int argc, char *argv[]) {
   if (argc < 2) {
     printf("NO FILE PROVIDED\n");
@@ -28,7 +30,19 @@ int main(int argc, char *argv[]) {
 
   fclose(fp);
 
-  printf("\n%35s: %s\n", filename, validate_json(json) ? "VALID" : "INVALID");
+  lexer_t *lexer = NULL;
+
+  lexer_init(&lexer);
+  if (!lexer) {
+    return EXIT_FAILURE;
+  }
+
+  get_next_token(lexer, json);
+
+  lexer_free(&lexer);
+
+  // printf("\n%35s: %s\n", filename, validate_json(json) ? "VALID" :
+  // "INVALID");
 
   return EXIT_SUCCESS;
 }