Add test files for unicode sequences

compile_commands.json

@@ -95,12 +95,12 @@
       "-x",
       "c",
       "-o",
-      "/tmp/main-977e60.o",
+      "/tmp/main-dc9945.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-977e60.o"
+    "output": "/tmp/main-dc9945.o"
   },
   {
     "arguments": [
@@ -162,11 +162,11 @@
       "-x",
       "c",
       "-o",
-      "/tmp/lexer_states-04f606.o",
+      "/tmp/lexer_states-e000bc.o",
       "src/lexer/lexer_states.c"
     ],
     "directory": "/mnt/3A5CDF785CDF2CFF/Users/abdoo/dev/say_it_in_json",
     "file": "/mnt/3A5CDF785CDF2CFF/Users/abdoo/dev/say_it_in_json/src/lexer/lexer_states.c",
-    "output": "/tmp/lexer_states-04f606.o"
+    "output": "/tmp/lexer_states-e000bc.o"
   }
 ]

src/lexer/lexer_states.c

@@ -90,6 +90,8 @@ lexer_state_t stack_pop(state_stack_t *stack);
 void append_to_string(lexer_string_t *str, char input);
 void clear_string(lexer_string_t *str);
 bool strequal(const char *first, const char *second);
+bool is_valid_hex_char(const char input);
+bool ishex(const char input);
 
 void lexer_state_machine(lexer_t *lexer, char input);
 lexer_state_t handle_lexer_start(char input);
@@ -102,6 +104,7 @@ lexer_state_t handle_value(lexer_t *lexer, char input);
 lexer_state_t handle_string(char input);
 lexer_state_t handle_string_end(lexer_t *lexer, char input);
 lexer_state_t handle_escape_sequence(char input);
+lexer_state_t handle_unicode_sequence(lexer_t *lexer, char input);
 lexer_state_t handle_decimal(char input);
 lexer_state_t handle_number(lexer_t *lexer, char input);
 lexer_state_t handle_fraction(lexer_t *lexer, char input);
@@ -173,6 +176,8 @@ void append_to_string(lexer_string_t *lex_str, char input) {
     return;
   }
 
+  assert(str != NULL);
+
   str[(lex_str->size)++] = input;
 }
 
@@ -203,6 +208,30 @@ bool strequal(const char *first, const char *second) {
   return strcmp(first, second) == 0;
 }
 
+bool is_valid_hex_char(const char input) {
+  switch (input) {
+  case 'A':
+  case 'B':
+  case 'C':
+  case 'D':
+  case 'E':
+  case 'F':
+  case 'a':
+  case 'b':
+  case 'c':
+  case 'd':
+  case 'e':
+  case 'f':
+    return true;
+  }
+
+  return false;
+}
+
+bool ishex(const char input) {
+  return isdigit(input) || is_valid_hex_char(input);
+}
+
 void lexer_state_machine(lexer_t *lexer, char input) {
   switch (lexer->current) {
   case LEXER_STATE_START:
@@ -270,6 +299,7 @@ void lexer_state_machine(lexer_t *lexer, char input) {
     lexer->current = handle_escape_sequence(input);
     break;
   case LEXER_STATE_UNICODE_HEX:
+    lexer->current = handle_unicode_sequence(lexer, input);
     break;
   case LEXER_STATE_TRUE:
     lexer->current = handle_true(lexer, input);
@@ -445,6 +475,22 @@ lexer_state_t handle_escape_sequence(char input) {
   return LEXER_STATE_ERROR;
 }
 
+lexer_state_t handle_unicode_sequence(lexer_t *lexer, char input) {
+  append_to_string(&(lexer->codepoint), input);
+
+  if (!ishex(input)) {
+    clear_string(&(lexer->codepoint));
+
+    return LEXER_STATE_ERROR;
+  } else if (lexer->codepoint.size == UNICODE_LENGTH) {
+    clear_string(&(lexer->codepoint));
+
+    return LEXER_STATE_STRING;
+  }
+
+  return LEXER_STATE_UNICODE_HEX;
+}
+
 lexer_state_t handle_decimal(char input) {
   if (input == '.') {
     return LEXER_STATE_FRACTION;

src/main.c

@@ -11,7 +11,9 @@ int main(int argc, char *argv[]) {
     return EXIT_FAILURE;
   }
 
-  FILE *fp = fopen(argv[1], "r");
+  const char *filename = argv[1];
+
+  FILE *fp = fopen(filename, "r");
 
   fseek(fp, 0, SEEK_END);
 
@@ -26,7 +28,7 @@ int main(int argc, char *argv[]) {
 
   fclose(fp);
 
-  printf("\n%s\n", validate_json(json) ? "VALID" : "INVALID");
+  printf("\n%35s: %s\n", filename, validate_json(json) ? "VALID" : "INVALID");
 
   return EXIT_SUCCESS;
 }

test_files/unicode_invalid_01.json

@@ -0,0 +1,3 @@
+{
+	"hello\u124": "testing"
+}

test_files/unicode_invalid_02.json

@@ -0,0 +1,3 @@
+{
+	"hello\\u124f": "tes\uting"
+}

test_files/unicode_valid_01.json

@@ -0,0 +1,3 @@
+{
+	"hello\\u124f": "testing"
+}

test_files/unicode_valid_02.json

@@ -0,0 +1,3 @@
+{
+	"hello\\u124ffdr": "tes\\u7eacting"
+}