completing grammar

lexer/lexer.mll

@@ -24,6 +24,9 @@ rule read_token = parse
   | "ON"        { ON }
   | "WHERE"     { WHERE }
   | "HAVING"    { HAVING }
+  | "BETWEEN"   { BETWEEN }
+  | "IN"        { IN }
+  | "LIKE"      { LIKE }
   | "GROUP"     { GROUP }
   | "BY"        { BY }
   | "*"         { ASTERISK }
@@ -32,6 +35,7 @@ rule read_token = parse
   | "("         { LEFT_PAREN }
   | ")"         { RIGHT_PAREN }
   | ","         { COMMA }
+  | "|"         { PIPE }
   | whitespace  { read_token lexbuf }
   | alpha alphanumeric* as ident      { IDENT ident }
   | eof         { EOF }

lib/ast.ml

@@ -26,6 +26,7 @@ and predicate =
   | NotBetween of string * string
   | In of string list
   | NotIn of string list
+  | Like of string
 and operator =
   | Equals
   | NotEquals
@@ -37,3 +38,44 @@ and filter =
   | Filter of string
 and search_condition =
   | Search of string
+
+
+let rec pp_query ast = 
+  match ast with
+  | Query(s) ->  pp_select s
+
+and pp_select s = 
+  match s with
+  | Select(cols, _) -> pp_columns cols
+
+and pp_columns cols =
+  match cols with
+  | [] -> "" 
+  | [col] -> pp_column col
+  | col::l -> pp_column col ^ ";" ^ pp_columns l
+
+and pp_column col = 
+  match col with
+  | Column(name) -> name
+  | Asterisk -> "*"
+
+and pp_tables tables =
+  match tables with
+  | [] -> ""
+  | [table] -> pp_table table
+  | table::l -> pp_table table ^ ";" ^ pp_tables l
+
+and pp_table table =
+  match table with
+  | Table(table) -> table
+  | Join(t1, j, t2, _) -> pp_table t1 ^ pp_join_type j ^ pp_table t2
+
+and pp_join_type j =
+  match j with
+  | Inner -> "inner"
+  | Left -> "left"
+  | Right -> "right"
+  | Full -> "full"
+  | Cross -> "cross"
+  | Union -> "union"
+  | Natural -> "natural"

parser/parser.mly

@@ -4,14 +4,14 @@ open Ast
 %}
 
 %token CREATE TABLE
-%token SELECT ALL DISTINCT FROM WHERE HAVING BETWEEN IN
+%token SELECT ALL DISTINCT FROM WHERE HAVING BETWEEN IN LIKE
 %token LEFT RIGHT FULL INNER OUTER
-%token CROSS NATURAL  UNION JOIN
+%token CROSS NATURAL UNION JOIN
 %token GREATER_THAN_OPERATOR LESS_THAN_OPERATOR EQUALS_OPERATOR
 %token MAX MIN SUM COUNT AVG
 %token ASYMMETRIC SYMMETRIC
 %token <string> IDENT
-%token COMMA DOT
+%token COMMA DOT PIPE
 %token LEFT_PAREN RIGHT_PAREN
 %token ASTERISK
 %token AS ON GROUP BY FILTER
@@ -165,7 +165,7 @@ predicate :
   | comparison_predicate { $1 }
   | between_predicate { $1 }
   | in_predicate { $1 }
-  | like_predicate { $1 }
+  (* | like_predicate { $1 } *)
 
 comparison_predicate :
   | row_value_predicand comparison_predicate_part2 { Condition($1, $2) }
@@ -199,6 +199,36 @@ in_value_list:
   | row_value_expression { [$1] }
   | in_value_list COMMA row_value_expression { $3::$1 }
 
+like_predicate :
+  | character_like_predicate { $1 }
+
+character_like_predicate :
+  | row_value_predicand character_like_predicate_part2 { }
+
+character_like_predicate_part2:
+  | LIKE character_pattern {} 
+  | NOT LIKE character_pattern {}
+
+character_pattern :
+  | character_value_expression {}
+
+character_value_expression:
+  | concatenation {}
+  | character_factor {}
+
+concatenation:
+  | character_value_expression concatenation_operator character_factor {}
+
+character_factor :
+  | character_primary {}
+
+character_primary:
+  | value_expression_primary {}
+(*  | string_value_function {} *)
+
+concatenation_operator:
+  | PIPE PIPE {}
+
 row_value_expression :
   | row_value_special_case { $1 }