From 45cbe5b9e22c5ace69c6dcead5872ef1b80e143e Mon Sep 17 00:00:00 2001
From: Username404-59 <w.iron.zombie@gmail.com>
Date: Mon, 22 Feb 2021 19:42:20 +0100
Subject: [PATCH] Lex the entire strings.

---
 src/etc/lexer.cpp   | 72 +++++++++++++++++++++++++++++----------------
 src/headers/lex.hpp |  8 ++---
 2 files changed, 51 insertions(+), 29 deletions(-)

diff --git a/src/etc/lexer.cpp b/src/etc/lexer.cpp
index 2cb7341..30a5586 100644
--- a/src/etc/lexer.cpp
+++ b/src/etc/lexer.cpp
@@ -10,35 +10,57 @@ vector<tok> resVal;
 
 void separate() {resVal.emplace_back(tok::SEPARATOR, "");}
 
-vector<tok> lex(const string& in)
+string generatedStr;
+bool isLexingString = false;
+
+tok::type getIdentifierCharType(const char& Char) {
+    if (isalpha(Char)) return tok::IDENTIFIER;
+    else if (isalnum(Char)) return tok::NUMBER;
+    else return tok::UNEXPECTED;
+}
+
+vector<tok>& lex(const string& in)
 {
     for (const char& current : in) {
-        switch (current) {
-            case '#': resVal.emplace_back(tok::TAG, "#"); break;
-            case '=': resVal.emplace_back(tok::DEFINE, "="); break;
-            case '(': resVal.emplace_back(tok::LPAR, "("); break;
-            case ')': resVal.emplace_back(tok::RPAR, ")"); break;
-            case '{': resVal.emplace_back(tok::LBRACE, "{"); break;
-            case '}': resVal.emplace_back(tok::RBRACE, "}"); break;
-            case '[': resVal.emplace_back(tok::LBRACKET, "["); break;
-            case ']': resVal.emplace_back(tok::RBRACKET, "]"); break;
-            case '+': resVal.emplace_back(tok::PLUS, "+"); break;
-            case '-': resVal.emplace_back(tok::HYPHEN, "-"); break;
-            case '>': resVal.emplace_back(tok::LCOMP, ">"); break;
-            case '<': resVal.emplace_back(tok::RCOMP, "<"); break;
-            case '\'': resVal.emplace_back(tok::SQUOTE, "\'"); break;
-            case '"': resVal.emplace_back(tok::DQUOTE, "\""); break;
-            case ' ': case '\t': case '\r':
-            case '\n': separate(); break;
-            default: {
-                if (isdigit(current))
-                    resVal.emplace_back(tok::INT, string(1, current));
-                else if (isalpha(current))
-                    resVal.emplace_back(tok::ALPHACHAR, string(1, current));
-                else resVal.emplace_back(tok::OTHER, string(1, current));
-                break;
+        if (!isLexingString) {
+            if (!generatedStr.empty()) {
+                resVal.emplace_back(tok::STRING, generatedStr);
+                generatedStr = "";
             }
+            switch (current) {
+                case '#': resVal.emplace_back(tok::TAG, "#"); break;
+                case '=': resVal.emplace_back(tok::DEFINE, "="); break;
+                case '(': resVal.emplace_back(tok::LPAR, "("); break;
+                case ')': resVal.emplace_back(tok::RPAR, ")"); break;
+                case '{': resVal.emplace_back(tok::LBRACE, "{"); break;
+                case '}': resVal.emplace_back(tok::RBRACE, "}"); break;
+                case '[': resVal.emplace_back(tok::LBRACKET, "["); break;
+                case ']': resVal.emplace_back(tok::RBRACKET, "]"); break;
+                case '+': resVal.emplace_back(tok::PLUS, "+"); break;
+                case '-': resVal.emplace_back(tok::HYPHEN, "-"); break;
+                case '>': resVal.emplace_back(tok::LCOMP, ">"); break;
+                case '<': resVal.emplace_back(tok::RCOMP, "<"); break;
+                case '\'': resVal.emplace_back(tok::SQUOTE, "\'"); break;
+                case '"': isLexingString = true; break;
+                case ' ': case '\t': case '\r':
+                case '\n': separate(); break;
+                default: {
+                    tok::type type = getIdentifierCharType(current);
+                    if (type != tok::UNEXPECTED) resVal.emplace_back(type, string(1, current));
+                }
+            }
+        } else {
+            if ((current == '"')) { // TODO Permit the usage of double quotes in strings using '\' (an example would be "\"")
+                isLexingString = false;
+            } else generatedStr.append(string(1, current));
         }
     }
+    /* Test
+    for (const auto& it : resVal) {
+        if (it.toktype == tok::STRING) cout << '"' << it.toktext << '"' << '\n';
+        if (it.toktype == tok::NUMBER) cout << it.toktext << "= number\n";
+        if (it.toktype == tok::IDENTIFIER) cout << it.toktext << '\n';
+    }
+    */
     return resVal;
 }
\ No newline at end of file
diff --git a/src/headers/lex.hpp b/src/headers/lex.hpp
index fcd7759..b4a519c 100644
--- a/src/headers/lex.hpp
+++ b/src/headers/lex.hpp
@@ -7,16 +7,16 @@
 
 struct tok {
     enum type {
-        DEFINE, TAG, INT, PLUS, MINUS, LPAR, LBRACE, LBRACKET, RPAR, RBRACE, RBRACKET, ALPHACHAR, HYPHEN, LCOMP, RCOMP,
-        SQUOTE, DQUOTE,
+        DEFINE, TAG, NUMBER, PLUS, LPAR, LBRACE, LBRACKET, RPAR, RBRACE, RBRACKET, ALPHACHAR, HYPHEN, LCOMP, RCOMP,
+        SQUOTE,
         STRING,
         IDENTIFIER,
         SEPARATOR,
-        OTHER
+        UNEXPECTED
     };
     type toktype;
     std::string toktext;
     tok(type Type, std::string Text): toktype(Type), toktext(Text) {}
     friend std::ostream& operator<<(std::ostream& output, const tok& it) { return output << it.toktext; }
 };
-std::vector<tok> lex(const std::string& in);
\ No newline at end of file
+std::vector<tok>& lex(const std::string& in);
\ No newline at end of file