[examples] write labels.mdesk with examples of labels

docs/metadesk_reference.mdesk

@@ -322,7 +322,7 @@ main:
     @doc("This is a string literal that used triplets (three of its boundary characters in a row, on either side) to mark its boundaries, making it multiline.")
         StringTriplet,
     
-    @doc("The label on this node comes from a token with the @code MD_TokenKind_NumericLiteral kind.")
+    @doc("The label on this node comes from a token with the @code MD_TokenKind_Numeric kind.")
         Numeric,
     @doc("The label on this node comes from a token with the @code MD_TokenKind_Identifier kind.")
         Identifier,

examples/mdesk_files/labels.mdesk

@@ -0,0 +1,96 @@
+////////////////////////////////
+// Identifiers (MD_NodeFlag_Identifier)
+abc _foo_ x123
+almostAnyCIdentifier // not including $
+
+////////////////////////////////
+// Numerics (MD_NodeFlag_Numeric)
+123 0x123ABC 0b10101 123.456
+0.123 123_456_789
+123abc456xyz
+123e+100
+456E-100
+789e+E-e+E-100100xyz
+
+////////////////////////////////
+// String Literals (MD_NodeFlag_StringLiteral)
+
+//(MD_NodeFlag_StringDoubleQuote)
+"Hello World"
+" 'Hello World` "
+"\"Hello World\""
+"\\\a\b\c\d\e\f\""
+""
+
+//(MD_NodeFlag_StringSingleQuote)
+'Hello World'
+' "Hello World` '
+''
+
+//(MD_NodeFlag_StringTick)
+`Hello World`
+` "Hello World' `
+``
+
+////////////////////////////////
+// Multi-Line String Literals (MD_NodeFlag_StringLiteral|MD_NodeFlag_StringTriplet)
+
+//(MD_NodeFlag_StringDoubleQuote)
+"""
+This string can go on
+for as many lines as I want.
+And it can say things like
+"Hello World"
+or you know, whatever.
+"""
+
+//(MD_NodeFlag_StringSingleQuote)
+'''
+Multi-line strings can start
+with a triplet of any of the
+string markers.
+'''
+
+//(MD_NodeFlag_Tick)
+```
+```
+
+////////////////////////////////
+// Symbols (MD_NodeFlag_Symbol)
++ - * / = & ^ % ! | ? < > . ~
+$
+++ -- ** == && ^^ %% !! || ??
+<< >> .. ~~ $$ -> <- => <= ?.
++= -= *= /= |= &= ^= %= != |=
+...
++- +++++++ ??? !? $! $$$ <->
++-*/=&^%~|?<>.~$
+
+/*
+** A few punctuation characters are not counted with the rest
+** of the symbol characters. These are the 'reserved' characters:
+** ( ) { } [ ] : ; , @ # \
+**
+** And the sequences // and /* start comments so no symbol
+** can start with either of those pairs.
+**
+** Block comments are nested */
+*/
+
+
+////////////////////////////////
+// Identifiers, Numbers, Strings, and Symbols are the different kinds
+// of 'labels' in Metadesk. They can all form main metadesk nodes:
+
+_foo_: { bar123456; _123; }
+
+0: (1.0.1.1, 1.2.0.0)
+
+```
+#include <stdio.h>
+int main(){
+ printf("Hello World\n");
+}
+```: "Hello World"
+
+..: . + .

intro_notes.txt

@@ -19,7 +19,7 @@ Example Programs:
 
 Example Metadesk Files:
 [x] Hello world
-[ ] identifiers, numbers, strings, and symbols
+[x] identifiers, numbers, strings, and symbols
 [ ] sets, seperators, labels, and tags
 
 

source/md.c

@@ -619,7 +619,7 @@ MD_CharIsUnreservedSymbol(MD_u8 c)
     return (c == '~' || c == '!' || c == '$' || c == '%' || c == '^' ||
             c == '&' || c == '*' || c == '-' || c == '=' || c == '+' ||
             c == '<' || c == '.' || c == '>' || c == '/' || c == '?' ||
-            c == '|' || c == '\\');
+            c == '|');
 }
 
 MD_FUNCTION_IMPL MD_b32
@@ -1891,7 +1891,7 @@ MD_TokenFromString(MD_String8 string)
                 
             }break;
             
-            // NOTE(allen): Identifiers, Numbers, Operators
+            // NOTE(allen): Identifiers, Numbers, Symbols
             default:
             {
                 if (MD_CharIsAlpha(*at) || *at == '_')
@@ -1905,7 +1905,7 @@ MD_TokenFromString(MD_String8 string)
                 else if (MD_CharIsDigit(*at))
                 {
                     token.node_flags |= MD_NodeFlag_Numeric;
-                    token.kind = MD_TokenKind_NumericLiteral;
+                    token.kind = MD_TokenKind_Numeric;
                     at += 1;
                     
                     for (; at < one_past_last;){
@@ -1932,6 +1932,7 @@ MD_TokenFromString(MD_String8 string)
                 {
                     symbol_lex:
                     
+                    token.node_flags |= MD_NodeFlag_Symbol;
                     token.kind = MD_TokenKind_Symbol;
                     at += 1;
                     MD_TokenizerScan(MD_CharIsUnreservedSymbol(*at));

source/md.h

@@ -584,6 +584,7 @@ enum
     MD_NodeFlag_Numeric                 = (1<<14),
     MD_NodeFlag_Identifier              = (1<<15),
     MD_NodeFlag_StringLiteral           = (1<<16),
+    MD_NodeFlag_Symbol                  = (1<<17),
 };
 
 typedef struct MD_Node MD_Node;
@@ -670,7 +671,7 @@ typedef MD_u32 MD_TokenKind;
 enum
 {
     MD_TokenKind_Identifier          = (1<<0),
-    MD_TokenKind_NumericLiteral      = (1<<1),
+    MD_TokenKind_Numeric             = (1<<1),
     MD_TokenKind_StringLiteral       = (1<<2),
     MD_TokenKind_Symbol              = (1<<3),
     MD_TokenKind_Reserved            = (1<<4),
@@ -692,7 +693,7 @@ enum
                                MD_TokenGroup_Whitespace),
     MD_TokenGroup_Regular = ~MD_TokenGroup_Irregular,
     MD_TokenGroup_Label   = (MD_TokenKind_Identifier|
-                             MD_TokenKind_NumericLiteral|
+                             MD_TokenKind_Numeric|
                              MD_TokenKind_StringLiteral|
                              MD_TokenKind_Symbol),
     MD_TokenGroup_Error   = (MD_TokenKind_BrokenComment|

tests/sanity_tests.c

@@ -104,15 +104,15 @@ int main(void)
         TestResult(TokenMatch(tokens[1], MD_S8Lit(" "), MD_TokenKind_Whitespace));
         TestResult(TokenMatch(tokens[2], MD_S8Lit("def"), MD_TokenKind_Identifier));
         TestResult(TokenMatch(tokens[3], MD_S8Lit(" "), MD_TokenKind_Whitespace));
-        TestResult(TokenMatch(tokens[4], MD_S8Lit("123"), MD_TokenKind_NumericLiteral));
+        TestResult(TokenMatch(tokens[4], MD_S8Lit("123"), MD_TokenKind_Numeric));
         TestResult(TokenMatch(tokens[5], MD_S8Lit(" "), MD_TokenKind_Whitespace));
-        TestResult(TokenMatch(tokens[6], MD_S8Lit("456"), MD_TokenKind_NumericLiteral));
+        TestResult(TokenMatch(tokens[6], MD_S8Lit("456"), MD_TokenKind_Numeric));
         TestResult(TokenMatch(tokens[7], MD_S8Lit(" "), MD_TokenKind_Whitespace));
-        TestResult(TokenMatch(tokens[8], MD_S8Lit("123_456"), MD_TokenKind_NumericLiteral));
+        TestResult(TokenMatch(tokens[8], MD_S8Lit("123_456"), MD_TokenKind_Numeric));
         TestResult(TokenMatch(tokens[9], MD_S8Lit(" "), MD_TokenKind_Whitespace));
         TestResult(TokenMatch(tokens[10], MD_S8Lit("abc123"), MD_TokenKind_Identifier));
         TestResult(TokenMatch(tokens[11], MD_S8Lit(" "), MD_TokenKind_Whitespace));
-        TestResult(TokenMatch(tokens[12], MD_S8Lit("123abc"), MD_TokenKind_NumericLiteral));
+        TestResult(TokenMatch(tokens[12], MD_S8Lit("123abc"), MD_TokenKind_Numeric));
         TestResult(TokenMatch(tokens[13], MD_S8Lit(" "), MD_TokenKind_Whitespace));
         TestResult(TokenMatch(tokens[14], MD_S8Lit("+-*"), MD_TokenKind_Symbol));
     }