Added xyz file parser/lexer

Basis/Basis_lexer.mll

@@ -12,7 +12,7 @@ let ang_mom  = ['S' 'P' 'D' 'F' 'G' 'H' 'I' 'J' 'K' 'L' 'M' 'N' 'O'
                 's' 'p' 'd' 'f' 'g' 'h' 'i' 'j' 'k' 'l' 'm' 'n' 'o' ]
                white
 let integer  = ['0'-'9']+ 
-let real = '-'? integer '.' integer (['e' 'E'] '-'? integer)? 
+let real = '-'? integer '.' integer (['e' 'E'] ('+'|'-')? integer)? 
 
 
 rule read_all_rule  = parse

Makefile

@@ -1,9 +1,10 @@
 .NOPARALLEL:
 
+INCLUDE_DIRS=Nuclei,Utils,Basis
 LIBS=
 PKGS=
 OCAMLCFLAGS="-g"
-OCAMLBUILD=ocamlbuild -j 0 -cflags $(OCAMLCFLAGS) -lflags $(OCAMLCFLAGS) -I Utils -I Basis
+OCAMLBUILD=ocamlbuild -j 0 -cflags $(OCAMLCFLAGS) -lflags $(OCAMLCFLAGS) -Is $(INCLUDE_DIRS)
 MLLFILES=$(wildcard */*.mll) $(wildcard *.mll) 
 MLYFILES=$(wildcard */*.mly) $(wildcard *.mly) 
 MLFILES= $(wildcard */*.ml)  $(wildcard *.ml) 

Nuclei/Nuclei.ml

@@ -0,0 +1 @@
+type xyz_input = string * ( (string * (float array)) array)

Nuclei/Nuclei_lexer.mll

@@ -0,0 +1,38 @@
+{
+open Nuclei_parser
+}
+
+let eol = ['\n']
+let white = [' ' '\t']+
+let word = [^' ' '\t' '\n']+
+let letter = ['A'-'Z' 'a'-'z']
+let integer = ['0'-'9']+ 
+let real = '-'? integer '.' integer (['e' 'E'] ('+'|'-')? integer)? 
+
+
+rule read_all = parse
+  | eof            { EOF }
+  | eol            { EOL }
+  | white   as w   { SPACE w }
+  | integer as i   { INTEGER (int_of_string i) }
+  | real    as f   { FLOAT (float_of_string f) }
+  | word    as w   { WORD w }
+
+
+{
+ let debug () =
+   let ic = open_in "caffeine.xyz" in
+   let lexbuf = Lexing.from_channel ic in
+   while true do
+     let s = 
+      match read_all lexbuf with
+      | EOL -> "EOL"
+      | SPACE w -> "SPACE("^w^")"
+      | INTEGER i -> "INTEGER("^(string_of_int i)^")"
+      | FLOAT f -> "FLOAT("^(string_of_float f)^")"
+      | WORD w -> "WORD("^w^")"
+      | EOF -> "EOF"
+     in
+     print_endline s
+   done; 
+}

Nuclei/Nuclei_parser.mly

@@ -0,0 +1,55 @@
+/* Parses basis sets in GAMESS format */
+
+%{
+exception InputError of string
+%}
+
+%token EOL
+%token <string> SPACE
+%token <string> WORD
+%token <int> INTEGER
+%token <float> FLOAT
+%token EOF
+
+%start input
+%type <Nuclei.xyz_input> input
+
+%% /* Grammar rules and actions follow */
+
+input:
+  | integer title atoms { 
+     let len = List.length $3 in
+     if len <> $1 then
+       let error_msg = Printf.sprintf "%d atoms entered, expected %d" len $1 in
+       raise (InputError error_msg)
+     else
+        ($2,Array.of_list $3)
+     }
+
+integer:
+  | INTEGER EOL { $1 }
+  | INTEGER SPACE EOL { $1 }
+
+title:
+  | title_list EOL { $1 }
+
+text:
+  | WORD    {$1 }
+  | SPACE   {$1 }
+  | FLOAT   {(string_of_float $1)}
+  | INTEGER {(string_of_int $1)}
+
+title_list:
+  | { "" }
+  | title_list text { $1 ^ $2 }
+
+atoms:
+  | atoms_list EOL { List.rev $1 }
+  | atoms_list EOF { List.rev $1 }
+
+atoms_list:
+  | { [] }
+  | atoms_list WORD SPACE FLOAT SPACE FLOAT SPACE FLOAT EOL { ($2, [| $4;$6;$8 |]) :: $1 }
+  | atoms_list WORD SPACE FLOAT SPACE FLOAT SPACE FLOAT SPACE EOL { ($2, [| $4;$6;$8 |]) :: $1 }
+
+