From 85908ae0c40cf84d6f2fd08340b307ebb535aa5c Mon Sep 17 00:00:00 2001
From: Danila Fedorin <danila.fedorin@gmail.com>
Date: Mon, 5 Aug 2019 00:09:59 -0700
Subject: [PATCH] Write first draft of Bison-based parser and lexer

---
 code/compiler_parser.y              | 97 +++++++++++++++++++++++++++--
 code/compiler_scanner_bison.l       | 34 ++++++++++
 content/blog/02_compiler_parsing.md |  4 ++
 3 files changed, 129 insertions(+), 6 deletions(-)
 create mode 100644 code/compiler_scanner_bison.l

diff --git a/code/compiler_parser.y b/code/compiler_parser.y
index a72d14d..70950b4 100644
--- a/code/compiler_parser.y
+++ b/code/compiler_parser.y
@@ -1,15 +1,19 @@
 %{
 #include <string>
 #include <iostream>
-#include "ast.hpp"
-#include "parser.hpp"
+#include "compiler_ast.hpp"
+#include "compiler_parser.hpp"
+
+std::vector<definition_ptr> program;
+extern yy::parser::symbol_type yylex();
+
 %}
 
 %token PLUS
 %token TIMES
 %token MINUS
 %token DIVIDE
-%token INT
+%token <int> INT
 %token DEFN
 %token DATA
 %token CASE
@@ -20,7 +24,88 @@
 %token CPAREN
 %token COMMA
 %token ARROW
-%token EQUA
-%token LID
-%token UID
+%token EQUAL
+%token <std::string> LID
+%token <std::string> UID
 
+%language "c++"
+%define api.value.type variant
+%define api.token.constructor
+
+%type <std::vector<std::string>> lowercaseParams
+%type <std::vector<definition_ptr>> program definitions
+%type <std::vector<branch_ptr>> branches
+%type <ast_ptr> aAdd aMul case app appBase
+%type <definition_ptr> definition
+%type <branch_ptr> branch
+%type <pattern_ptr> pattern
+
+%start program
+
+%%
+
+program
+    : definitions { program = std::move($1); }
+    ;
+
+definitions
+    : definitions definition { $$ = std::move($1); $$.push_back(std::move($2)); }
+    | definition { $$ = std::vector<definition_ptr>(); $$.push_back(std::move($1)); }
+    ;
+
+definition
+    : DEFN LID lowercaseParams EQUAL OCURLY aAdd CCURLY
+        { $$ = definition_ptr(
+            new definition_defn(std::move($2), std::move($3), std::move($6))); }
+    ;
+
+lowercaseParams
+    : %empty { $$ = std::vector<std::string>(); }
+    | lowercaseParams LID { $$ = std::move($1); $$.push_back(std::move($2)); }
+    ;
+
+aAdd
+    : aAdd PLUS aMul { $$ = ast_ptr(new ast_binop(PLUS, std::move($1), std::move($3))); }
+    | aAdd MINUS aMul { $$ = ast_ptr(new ast_binop(MINUS, std::move($1), std::move($3))); }
+    | aMul { $$ = std::move($1); }
+    ;
+
+aMul
+    : aMul TIMES app { $$ = ast_ptr(new ast_binop(TIMES, std::move($1), std::move($3))); }
+    | aMul DIVIDE app { $$ = ast_ptr(new ast_binop(DIVIDE, std::move($1), std::move($3))); }
+    | app { $$ = std::move($1); }
+    ;
+
+app
+    : app appBase { $$ = ast_ptr(new ast_app(std::move($1), std::move($2))); }
+    | appBase { $$ = std::move($1); }
+    ;
+
+appBase
+    : INT { $$ = ast_ptr(new ast_int($1)); }
+    | LID { $$ = ast_ptr(new ast_lid(std::move($1))); }
+    | UID { $$ = ast_ptr(new ast_uid(std::move($1))); }
+    | OPAREN aAdd CPAREN { $$ = std::move($2); }
+    | case { $$ = std::move($1); }
+    ;
+
+case
+    : CASE aAdd OF OCURLY branches CCURLY 
+        { $$ = ast_ptr(new ast_case(std::move($2), std::move($5))); }
+    ;
+
+branches
+    : branches COMMA branch { $$ = std::move($1); $1.push_back(std::move($3)); }
+    | branch { $$ = std::vector<branch_ptr>(); $$.push_back(std::move($1));}
+    ;
+
+branch
+    : pattern ARROW OCURLY aAdd CCURLY
+        { $$ = branch_ptr(new branch(std::move($1), std::move($4))); }
+    ;
+
+pattern
+    : LID { $$ = pattern_ptr(new pattern_var(std::move($1))); }
+    | UID lowercaseParams
+        { $$ = pattern_ptr(new pattern_constr(std::move($1), std::move($2))); }
+    ;
diff --git a/code/compiler_scanner_bison.l b/code/compiler_scanner_bison.l
new file mode 100644
index 0000000..af90ca7
--- /dev/null
+++ b/code/compiler_scanner_bison.l
@@ -0,0 +1,34 @@
+%option noyywrap
+
+%{
+#include <iostream>
+#include "compiler_ast.hpp"
+#include "compiler_parser.hpp"
+
+#define YY_DECL yy::parser::symbol_type yylex()
+
+%}
+
+%%
+
+[ \n]+ {}
+\+ { return yy::parser::make_PLUS(); }
+\* { return yy::parser::make_TIMES(); }
+- { return yy::parser::make_MINUS(); }
+\/ { return yy::parser::make_DIVIDE(); }
+[0-9]+ { return yy::parser::make_INT(atoi(yytext)); }
+defn { return yy::parser::make_DEFN(); }
+data { return yy::parser::make_DATA(); }
+case { return yy::parser::make_CASE(); }
+of { return yy::parser::make_OF(); }
+\{ { return yy::parser::make_OCURLY(); }
+\} { return yy::parser::make_CCURLY(); }
+\( { return yy::parser::make_OPAREN(); }
+\) { return yy::parser::make_CPAREN(); }
+,  { return yy::parser::make_COMMA(); }
+-> { return yy::parser::make_ARROW(); }
+= { return yy::parser::make_EQUAL(); }
+[a-z][a-zA-Z]* { return yy::parser::make_LID(std::string(yytext)); }
+[A-Z][a-zA-Z]* { return yy::parser::make_UID(std::string(yytext)); }
+
+%%
diff --git a/content/blog/02_compiler_parsing.md b/content/blog/02_compiler_parsing.md
index 473c753..2bdeb3d 100644
--- a/content/blog/02_compiler_parsing.md
+++ b/content/blog/02_compiler_parsing.md
@@ -226,6 +226,10 @@ It's called Bison, and it is frequently used with Flex. Before we get to bison,
 incurred - the implementation of our AST. Such a tree is language-specific, so Bison doesn't generate it for us. Here's what
 I came up with:
 {{< codeblock "C++" "compiler_ast.hpp" >}}
+We create a base class for an expression tree, which we call `ast`. Then, for each possible syntactic construct in our language
+(a number, a variable, a binary operation, a case expression) we create a subclass of `ast`. The `ast_case` subclass
+is the most complex, since it must contain a list of case expression branches, which are a combination of a `pattern` and
+another expression.
 
 Finally, we get to writing our Bison file, `parser.y`. Here's what I come up with:
 {{< rawblock "compiler_parser.y" >}}