From: Thomas Bruce <tdb@tdbio.me>
Date: Thu, 20 Feb 2025 05:56:24 +0000 (-0500)
Subject: properly parse function calls
X-Git-Url: https://git.deglebe.com/sitemap.xml?a=commitdiff_plain;h=d10c822e78b6b66ab6e3b0765e267501e26d5f14;p=barec%2Fbarec.git

properly parse function calls
---

diff --git a/docs/lexer-doc.txt b/docs/lexer-doc.txt
new file mode 100644
index 0000000..5040973
--- /dev/null
+++ b/docs/lexer-doc.txt
@@ -0,0 +1,57 @@
+bareC lexer documentation
+date: 20/02/2025
+=========================
+
+overview:
+---------
+the bareC lexer converts the raw source code into a stream of tokens that the
+parser can easily process. it reads the source file character-by-character,
+skips whitespace and comments (single-line only), and recognizes:
+	- keywords
+	- identifiers
+	- literals (integers)
+	- operators (+, -, /, *, ==, =, >)
+	- punctuation
+
+token types:
+------------
+the lexer recognizes the following token types:
+	- keywords: "int", "return", "if", "else", "while"
+	- identifiers: variable and function names
+	- literals: integer literals
+	- operators: "=", "==", ">", "+", "-", "/", "*"
+	- punctuation: "(", ")", "{", "}", ";", ","
+	- end-of-file: eof and unknown
+
+EBNF for lexical elements:
+--------------------------
+1. letters and digits:
+	<letter>	= "A" | "B" | ... | "Z" | "a" | "b" | ... | "z" ;
+	<digit>		= "0" | "1" | ... | "9" ;
+
+2. identifier:
+	<identifier>	= ( <letter> | "_" ) { <letter> | <digit> | "_" } ;
+
+3. integer literal:
+	<number> = <digit> { <digit> };
+
+TODO: keywords, operators
+
+whitespace and comments:
+------------------------
+	- whitespace (space, tab, newline) is skipped
+	- single-line comments start with "//" and terminate at line end
+	- unrecognized returns as TK_UNKNOWN
+
+processing flow:
+----------------
+1. open the source file and prime the first character
+2. repeat:
+	- skip whitespace and comments
+	- check current character:
+		- if digit -> accumulate a number
+		- if letter or _, accumulate an identifier and check reserved
+		- match multi-character operators
+		- directly return tokens
+3. continue until EOF
+
diff --git a/lexer.c b/lexer.c
index d259454..9098221 100644
--- a/lexer.c
+++ b/lexer.c
@@ -87,6 +87,7 @@ Token getNextToken(void) {
 	if (g_currentChar == '{') { advance(); return makeToken(TK_LBRACE, "{"); }
 	if (g_currentChar == '}') { advance(); return makeToken(TK_RBRACE, "}"); }
 	if (g_currentChar == ';') { advance(); return makeToken(TK_SEMICOLON, ";"); }
+	if (g_currentChar == ',') { advance(); return makeToken(TK_COMMA, ","); }
 	if (g_currentChar == '>') { advance(); return makeToken(TK_GT, ">"); }
 
 	/* handle numeric literal */