From b1a049f060a880cbdd405e11ab4843b037452c55 Mon Sep 17 00:00:00 2001
From: Jake <jakeroggenbuck2@gmail.com>
Date: Mon, 24 Jun 2024 19:28:43 -0700
Subject: [PATCH 1/9] Add more lex tests

---
 src/lexer/lex.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/src/lexer/lex.c b/src/lexer/lex.c
index ca37c14..8d25600 100644
--- a/src/lexer/lex.c
+++ b/src/lexer/lex.c
@@ -25,10 +25,10 @@ int is_valid_numeric_or_id_char(char c) {
     return isalnum(c) || (c == '_') || (c == '.');
 }
 
-int real_lex(Lexer*, Token*);
+int real_lex(Lexer *, Token *);
 
 /**
- * This produces a list of tokens after having been processed by the 
+ * This produces a list of tokens after having been processed by the
  * preprocessor. For example, if the code is
  * #define MAX_ARRAY 5
  * int arr[MAX_ARRAY];
@@ -40,7 +40,7 @@ int real_lex(Lexer*, Token*);
  * ]
  * ;
  */
-int lex(Lexer* l, Token* t) {
+int lex(Lexer *l, Token *t) {
     // For now, all we need to do is skip newlines
     for (;;) {
         real_lex(l, t);
@@ -531,6 +531,9 @@ const char *ttype_name(TokenType tt) { return ttype_names[tt]; }
 int test_ttype_from_string() {
     testing_func_setup();
 
+    tassert(ttype_from_string("+") == TT_PLUS);
+    tassert(ttype_from_string("=") == TT_ASSIGN);
+
     tassert(ttype_from_string("1") == TT_LITERAL);
     tassert(ttype_from_string("1.2") == TT_LITERAL);
 

From bfee00247ad539ece4aa321fe49db4690c247207 Mon Sep 17 00:00:00 2001
From: Jake <jakeroggenbuck2@gmail.com>
Date: Mon, 24 Jun 2024 19:32:26 -0700
Subject: [PATCH 2/9] Add better docs

---
 src/lexer/lex.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/src/lexer/lex.c b/src/lexer/lex.c
index 8d25600..cfe8ba8 100644
--- a/src/lexer/lex.c
+++ b/src/lexer/lex.c
@@ -203,6 +203,7 @@ int skip_to_token(Lexer *l) {
     return -1; // EOF was reached
 }
 
+// This is a function for parsing single char tokens
 TokenType ttype_one_char(char c) {
     switch (c) {
     case '(':
@@ -256,6 +257,7 @@ TokenType ttype_one_char(char c) {
     return TT_NO_TOKEN;
 }
 
+// This is a function for parsing exclusively tokens with more than one char
 TokenType ttype_many_chars(const char *contents) {
     if (STREQ(contents, "auto")) {
         return TT_AUTO;
@@ -423,6 +425,7 @@ TokenType ttype_many_chars(const char *contents) {
     return TT_IDENTIFIER;
 }
 
+// This is the function for parsing all tokens from strings
 TokenType ttype_from_string(const char *contents) {
     int len;
 

From a076961acfc5ba70ad6f38277386563eb49855df Mon Sep 17 00:00:00 2001
From: Jake <jakeroggenbuck2@gmail.com>
Date: Mon, 24 Jun 2024 19:39:26 -0700
Subject: [PATCH 3/9] Add assert for error

---
 src/lexer/lex.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/src/lexer/lex.c b/src/lexer/lex.c
index cfe8ba8..7615a2b 100644
--- a/src/lexer/lex.c
+++ b/src/lexer/lex.c
@@ -259,6 +259,10 @@ TokenType ttype_one_char(char c) {
 
 // This is a function for parsing exclusively tokens with more than one char
 TokenType ttype_many_chars(const char *contents) {
+	if (strlen(contents) == 1) {
+        PRINT_ERROR("Please use ttype_from_string instead of ttype_many_chars for general use of tokenizing");
+	}
+
     if (STREQ(contents, "auto")) {
         return TT_AUTO;
     } else if (STREQ(contents, "break")) {

From 3a33bee5eb337e90f759de1ae6c89ce135086404 Mon Sep 17 00:00:00 2001
From: Jake <jakeroggenbuck2@gmail.com>
Date: Mon, 24 Jun 2024 19:53:20 -0700
Subject: [PATCH 4/9] Add more tests

---
 src/lexer/lex.c        | 40 ++++++++++++++++++++++++++++++++++++----
 src/lexer/lex.h        |  6 ++++++
 src/lexer/test_lexer.c |  3 +++
 3 files changed, 45 insertions(+), 4 deletions(-)

diff --git a/src/lexer/lex.c b/src/lexer/lex.c
index 7615a2b..aa11533 100644
--- a/src/lexer/lex.c
+++ b/src/lexer/lex.c
@@ -259,10 +259,6 @@ TokenType ttype_one_char(char c) {
 
 // This is a function for parsing exclusively tokens with more than one char
 TokenType ttype_many_chars(const char *contents) {
-	if (strlen(contents) == 1) {
-        PRINT_ERROR("Please use ttype_from_string instead of ttype_many_chars for general use of tokenizing");
-	}
-
     if (STREQ(contents, "auto")) {
         return TT_AUTO;
     } else if (STREQ(contents, "break")) {
@@ -535,6 +531,42 @@ static const char *ttype_names[] = {
 
 const char *ttype_name(TokenType tt) { return ttype_names[tt]; }
 
+int test_ttype_many_chars() {
+    testing_func_setup();
+
+    tassert(ttype_many_chars("foo") == TT_IDENTIFIER);
+    tassert(ttype_many_chars("struct") == TT_STRUCT);
+    tassert(ttype_many_chars("while") == TT_WHILE);
+
+    return 0;
+}
+
+int test_ttype_one_char() {
+    testing_func_setup();
+
+    // Use ttype_from_string
+    tassert(ttype_one_char('a') == TT_NO_TOKEN);
+    tassert(ttype_one_char('1') == TT_NO_TOKEN);
+
+    tassert(ttype_one_char('+') == TT_PLUS);
+    tassert(ttype_one_char('-') == TT_MINUS);
+    tassert(ttype_one_char('>') == TT_GREATER);
+    tassert(ttype_one_char('~') == TT_BNOT);
+
+    return 0;
+}
+
+int test_ttype_name() {
+    testing_func_setup();
+
+    tassert(strcmp(ttype_name(TT_LITERAL), "literal") == 0);
+    tassert(strcmp(ttype_name(TT_PLUS), "+") == 0);
+    tassert(strcmp(ttype_name(TT_SIZEOF), "sizeof") == 0);
+    tassert(strcmp(ttype_name(TT_WHILE), "while") == 0);
+
+    return 0;
+}
+
 int test_ttype_from_string() {
     testing_func_setup();
 
diff --git a/src/lexer/lex.h b/src/lexer/lex.h
index 8ed0489..016da90 100644
--- a/src/lexer/lex.h
+++ b/src/lexer/lex.h
@@ -40,3 +40,9 @@ const char *ttype_name(TokenType tt);
 
 // Test for ttype_from_string
 int test_ttype_from_string();
+
+int test_ttype_many_chars();
+
+int test_ttype_one_char();
+
+int test_ttype_name();
diff --git a/src/lexer/test_lexer.c b/src/lexer/test_lexer.c
index 83a3087..9364a22 100644
--- a/src/lexer/test_lexer.c
+++ b/src/lexer/test_lexer.c
@@ -8,7 +8,10 @@
 int test_lexer() {
     testing_module_setup();
 
+    test_ttype_name();
     test_ttype_from_string();
+    test_ttype_many_chars();
+    test_ttype_one_char();
 
     testing_module_cleanup();
     return 0;

From b9cc2de2fbf272461ebbab506b748722a1f7dda7 Mon Sep 17 00:00:00 2001
From: Jake <jakeroggenbuck2@gmail.com>
Date: Tue, 25 Jun 2024 10:56:52 -0700
Subject: [PATCH 5/9] Change to underscore

---
 src/lexer/lex.c | 24 ++++++++++++------------
 src/lexer/lex.h |  4 ++--
 2 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/src/lexer/lex.c b/src/lexer/lex.c
index aa11533..423939f 100644
--- a/src/lexer/lex.c
+++ b/src/lexer/lex.c
@@ -204,7 +204,7 @@ int skip_to_token(Lexer *l) {
 }
 
 // This is a function for parsing single char tokens
-TokenType ttype_one_char(char c) {
+TokenType _ttype_one_char(char c) {
     switch (c) {
     case '(':
         return TT_OPAREN; // (
@@ -258,7 +258,7 @@ TokenType ttype_one_char(char c) {
 }
 
 // This is a function for parsing exclusively tokens with more than one char
-TokenType ttype_many_chars(const char *contents) {
+TokenType _ttype_many_chars(const char *contents) {
     if (STREQ(contents, "auto")) {
         return TT_AUTO;
     } else if (STREQ(contents, "break")) {
@@ -433,7 +433,7 @@ TokenType ttype_from_string(const char *contents) {
 
     // Single character contents
     if (len == 1) {
-        TokenType token = ttype_one_char(contents[0]);
+        TokenType token = _ttype_one_char(contents[0]);
 
         if (token != TT_NO_TOKEN) {
             return token;
@@ -534,9 +534,9 @@ const char *ttype_name(TokenType tt) { return ttype_names[tt]; }
 int test_ttype_many_chars() {
     testing_func_setup();
 
-    tassert(ttype_many_chars("foo") == TT_IDENTIFIER);
-    tassert(ttype_many_chars("struct") == TT_STRUCT);
-    tassert(ttype_many_chars("while") == TT_WHILE);
+    tassert(_ttype_many_chars("foo") == TT_IDENTIFIER);
+    tassert(_ttype_many_chars("struct") == TT_STRUCT);
+    tassert(_ttype_many_chars("while") == TT_WHILE);
 
     return 0;
 }
@@ -545,13 +545,13 @@ int test_ttype_one_char() {
     testing_func_setup();
 
     // Use ttype_from_string
-    tassert(ttype_one_char('a') == TT_NO_TOKEN);
-    tassert(ttype_one_char('1') == TT_NO_TOKEN);
+    tassert(_ttype_one_char('a') == TT_NO_TOKEN);
+    tassert(_ttype_one_char('1') == TT_NO_TOKEN);
 
-    tassert(ttype_one_char('+') == TT_PLUS);
-    tassert(ttype_one_char('-') == TT_MINUS);
-    tassert(ttype_one_char('>') == TT_GREATER);
-    tassert(ttype_one_char('~') == TT_BNOT);
+    tassert(_ttype_one_char('+') == TT_PLUS);
+    tassert(_ttype_one_char('-') == TT_MINUS);
+    tassert(_ttype_one_char('>') == TT_GREATER);
+    tassert(_ttype_one_char('~') == TT_BNOT);
 
     return 0;
 }
diff --git a/src/lexer/lex.h b/src/lexer/lex.h
index 016da90..f09e02c 100644
--- a/src/lexer/lex.h
+++ b/src/lexer/lex.h
@@ -23,10 +23,10 @@ int lex(Lexer *l, Token *token);
 int unlex(Lexer *l, Token *token);
 
 // Find token type for single char
-TokenType ttype_one_char(char c);
+TokenType _ttype_one_char(char c);
 
 // Find token type for a char* with multiple characters
-TokenType ttype_many_chars(const char *contents);
+TokenType _ttype_many_chars(const char *contents);
 
 // Discern the token type from the given contents of unknown length
 TokenType ttype_from_string(const char *contents);

From 5fc13ba6e6cfd99469adb4c7e0f5c5b42846061e Mon Sep 17 00:00:00 2001
From: Jake <jakeroggenbuck2@gmail.com>
Date: Tue, 25 Jun 2024 10:59:04 -0700
Subject: [PATCH 6/9] Rename

---
 src/lexer/lex.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/src/lexer/lex.c b/src/lexer/lex.c
index 0411cde..01b2f1f 100644
--- a/src/lexer/lex.c
+++ b/src/lexer/lex.c
@@ -169,7 +169,7 @@ int real_lex(Lexer *l, Token *t) {
     // First up, we can just end here.
     if (in_string(init, single_char_tokens)) {
         t->length = pos;
-        t->type = ttype_one_char(init);
+        t->type = _ttype_one_char(init);
         return 0;
     }
 
@@ -196,7 +196,7 @@ int real_lex(Lexer *l, Token *t) {
         // We've ended!
         ungetc(c, l->fp);
         t->contents[pos] = '\0';
-        t->type = ttype_many_chars(t->contents);
+        t->type = _ttype_many_chars(t->contents);
         t->length = pos;
         return 0;
     }
@@ -331,7 +331,6 @@ TokenType _ttype_one_char(char c) {
     case '?':
         return TT_QMARK;
     default:
-        PRINT_ERROR("Token type for token '%c' not recognized", c);
         return TT_NO_TOKEN;
     }
 }
@@ -521,7 +520,7 @@ TokenType ttype_from_string(const char *contents) {
         }
     }
 
-    return ttype_many_chars(contents);
+    return _ttype_many_chars(contents);
 }
 
 static const char *ttype_names[] = {

From 74f6a0d092b67b33fcb4a4d8d155e587d22415c1 Mon Sep 17 00:00:00 2001
From: Jake <jakeroggenbuck2@gmail.com>
Date: Tue, 25 Jun 2024 11:01:49 -0700
Subject: [PATCH 7/9] Revert "Rename"

This reverts commit 5fc13ba6e6cfd99469adb4c7e0f5c5b42846061e.
---
 src/lexer/lex.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/src/lexer/lex.c b/src/lexer/lex.c
index 01b2f1f..0411cde 100644
--- a/src/lexer/lex.c
+++ b/src/lexer/lex.c
@@ -169,7 +169,7 @@ int real_lex(Lexer *l, Token *t) {
     // First up, we can just end here.
     if (in_string(init, single_char_tokens)) {
         t->length = pos;
-        t->type = _ttype_one_char(init);
+        t->type = ttype_one_char(init);
         return 0;
     }
 
@@ -196,7 +196,7 @@ int real_lex(Lexer *l, Token *t) {
         // We've ended!
         ungetc(c, l->fp);
         t->contents[pos] = '\0';
-        t->type = _ttype_many_chars(t->contents);
+        t->type = ttype_many_chars(t->contents);
         t->length = pos;
         return 0;
     }
@@ -331,6 +331,7 @@ TokenType _ttype_one_char(char c) {
     case '?':
         return TT_QMARK;
     default:
+        PRINT_ERROR("Token type for token '%c' not recognized", c);
         return TT_NO_TOKEN;
     }
 }
@@ -520,7 +521,7 @@ TokenType ttype_from_string(const char *contents) {
         }
     }
 
-    return _ttype_many_chars(contents);
+    return ttype_many_chars(contents);
 }
 
 static const char *ttype_names[] = {

From 29717793f464ddedbef0fb62efa4e29b872dff60 Mon Sep 17 00:00:00 2001
From: Jake <jakeroggenbuck2@gmail.com>
Date: Tue, 25 Jun 2024 11:07:17 -0700
Subject: [PATCH 8/9] Change to expected behavior for ttype functions

---
 src/lexer/lex.c | 32 ++++++++++++++++++--------------
 src/lexer/lex.h |  4 ++--
 2 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/src/lexer/lex.c b/src/lexer/lex.c
index 0411cde..3ec7760 100644
--- a/src/lexer/lex.c
+++ b/src/lexer/lex.c
@@ -278,7 +278,8 @@ int skip_to_token(Lexer *l) {
 }
 
 // This is a function for parsing single char tokens
-TokenType _ttype_one_char(char c) {
+// Now handles all cases of single char tokens
+TokenType ttype_one_char(char c) {
     switch (c) {
     case '(':
         return TT_OPAREN; // (
@@ -331,13 +332,16 @@ TokenType _ttype_one_char(char c) {
     case '?':
         return TT_QMARK;
     default:
-        PRINT_ERROR("Token type for token '%c' not recognized", c);
-        return TT_NO_TOKEN;
+		if (isdigit(c)) {
+			return TT_LITERAL;
+		} else {
+			return TT_IDENTIFIER;
+		}
     }
 }
 
 // This is a function for parsing exclusively tokens with more than one char
-TokenType _ttype_many_chars(const char *contents) {
+TokenType ttype_many_chars(const char *contents) {
     if (STREQ(contents, "auto")) {
         return TT_AUTO;
     } else if (STREQ(contents, "break")) {
@@ -514,7 +518,7 @@ TokenType ttype_from_string(const char *contents) {
 
     // Single character contents
     if (len == 1) {
-        TokenType token = _ttype_one_char(contents[0]);
+        TokenType token = ttype_one_char(contents[0]);
 
         if (token != TT_NO_TOKEN) {
             return token;
@@ -618,9 +622,9 @@ const char *ttype_name(TokenType tt) { return ttype_names[tt]; }
 int test_ttype_many_chars() {
     testing_func_setup();
 
-    tassert(_ttype_many_chars("foo") == TT_IDENTIFIER);
-    tassert(_ttype_many_chars("struct") == TT_STRUCT);
-    tassert(_ttype_many_chars("while") == TT_WHILE);
+    tassert(ttype_many_chars("foo") == TT_IDENTIFIER);
+    tassert(ttype_many_chars("struct") == TT_STRUCT);
+    tassert(ttype_many_chars("while") == TT_WHILE);
 
     return 0;
 }
@@ -629,13 +633,13 @@ int test_ttype_one_char() {
     testing_func_setup();
 
     // Use ttype_from_string
-    tassert(_ttype_one_char('a') == TT_NO_TOKEN);
-    tassert(_ttype_one_char('1') == TT_NO_TOKEN);
+    tassert(ttype_one_char('a') == TT_IDENTIFIER);
+    tassert(ttype_one_char('1') == TT_LITERAL);
 
-    tassert(_ttype_one_char('+') == TT_PLUS);
-    tassert(_ttype_one_char('-') == TT_MINUS);
-    tassert(_ttype_one_char('>') == TT_GREATER);
-    tassert(_ttype_one_char('~') == TT_BNOT);
+    tassert(ttype_one_char('+') == TT_PLUS);
+    tassert(ttype_one_char('-') == TT_MINUS);
+    tassert(ttype_one_char('>') == TT_GREATER);
+    tassert(ttype_one_char('~') == TT_BNOT);
 
     return 0;
 }
diff --git a/src/lexer/lex.h b/src/lexer/lex.h
index f09e02c..016da90 100644
--- a/src/lexer/lex.h
+++ b/src/lexer/lex.h
@@ -23,10 +23,10 @@ int lex(Lexer *l, Token *token);
 int unlex(Lexer *l, Token *token);
 
 // Find token type for single char
-TokenType _ttype_one_char(char c);
+TokenType ttype_one_char(char c);
 
 // Find token type for a char* with multiple characters
-TokenType _ttype_many_chars(const char *contents);
+TokenType ttype_many_chars(const char *contents);
 
 // Discern the token type from the given contents of unknown length
 TokenType ttype_from_string(const char *contents);

From 07c772d059f3d54a5c87bae8dfae40c5a9623c6e Mon Sep 17 00:00:00 2001
From: Jake <jakeroggenbuck2@gmail.com>
Date: Tue, 25 Jun 2024 11:37:43 -0700
Subject: [PATCH 9/9] Remove unreachable if

---
 src/lexer/lex.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/src/lexer/lex.c b/src/lexer/lex.c
index 3ec7760..a716de9 100644
--- a/src/lexer/lex.c
+++ b/src/lexer/lex.c
@@ -519,10 +519,7 @@ TokenType ttype_from_string(const char *contents) {
     // Single character contents
     if (len == 1) {
         TokenType token = ttype_one_char(contents[0]);
-
-        if (token != TT_NO_TOKEN) {
-            return token;
-        }
+		return token;
     }
 
     return ttype_many_chars(contents);