Lexer.mll 4.1 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124
  1. (*
  2. * Copyright (C) 2011-2017 Intel Corporation. All rights reserved.
  3. *
  4. * Redistribution and use in source and binary forms, with or without
  5. * modification, are permitted provided that the following conditions
  6. * are met:
  7. *
  8. * * Redistributions of source code must retain the above copyright
  9. * notice, this list of conditions and the following disclaimer.
  10. * * Redistributions in binary form must reproduce the above copyright
  11. * notice, this list of conditions and the following disclaimer in
  12. * the documentation and/or other materials provided with the
  13. * distribution.
  14. * * Neither the name of Intel Corporation nor the names of its
  15. * contributors may be used to endorse or promote products derived
  16. * from this software without specific prior written permission.
  17. *
  18. * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  19. * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  20. * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
  21. * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
  22. * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  23. * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
  24. * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
  25. * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
  26. * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  27. * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  28. * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  29. *
  30. *)
  31. {
  32. open Parser
  33. let string_to_int32 s = int_of_string s
  34. }
  35. (* These are some regular expression definitions *)
  36. let open_comment = "/*"
  37. let close_comment = "*/"
  38. let line_comment = "//"
  39. let space = [' ' '\t']
  40. let newline = ('\n' | '\r' '\n')
  41. let digit = ['0' - '9']
  42. let ident = ['_' 'a' - 'z' 'A' - 'Z']
  43. let identifier = ident(ident|digit)*
  44. let number = digit+
  45. let string = '"' [^'"']* '"' (* No embedded '\"' *)
  46. rule tokenize = parse
  47. (* space and newline *)
  48. | space { tokenize lexbuf }
  49. | newline { Lexing.new_line lexbuf; tokenize lexbuf }
  50. (* data types *)
  51. | "char" { Tchar }
  52. | "short" { Tshort }
  53. | "unsigned" { Tunsigned }
  54. | "int" { Tint }
  55. | "float" { Tfloat }
  56. | "double" { Tdouble }
  57. | "int8_t" { Tint8 }
  58. | "int16_t" { Tint16 }
  59. | "int32_t" { Tint32 }
  60. | "int64_t" { Tint64 }
  61. | "uint8_t" { Tuint8 }
  62. | "uint16_t" { Tuint16 }
  63. | "uint32_t" { Tuint32 }
  64. | "uint64_t" { Tuint64 }
  65. | "size_t" { Tsizet }
  66. | "wchar_t" { Twchar }
  67. | "long" { Tlong }
  68. | "void" { Tvoid }
  69. | "struct" { Tstruct }
  70. | "union" { Tunion }
  71. | "enum" { Tenum }
  72. (* specifier *)
  73. | "enclave" { Tenclave }
  74. | "trusted" { Ttrusted }
  75. | "untrusted" { Tuntrusted }
  76. | "from" { Tfrom }
  77. | "import" { Timport }
  78. | "allow" { Tallow }
  79. | "public" { Tpublic }
  80. | "include" { Tinclude }
  81. | "propagate_errno" { Tpropagate_errno }
  82. (* Type qualifier *)
  83. | "const" { Tconst }
  84. (* symbols *)
  85. | '{' { TLBrace }
  86. | '}' { TRBrace }
  87. | '(' { TLParen }
  88. | ')' { TRParen }
  89. | '[' { TLBrack }
  90. | ']' { TRBrack }
  91. | '*' { TPtr }
  92. | '.' { TDot }
  93. | ',' { TComma }
  94. | ';' { TSemicolon }
  95. | '=' { TEqual }
  96. | identifier { Tidentifier(Lexing.lexeme lexbuf) }
  97. | number { Tnumber(string_to_int32(Lexing.lexeme lexbuf)) }
  98. | string { let s = Lexing.lexeme lexbuf in Tstring(String.sub s 1 (String.length s - 2)) }
  99. (* comments *)
  100. | line_comment { eat_until_nl lexbuf }
  101. | open_comment { comment lexbuf }
  102. | eof { EOF }
  103. | _ { failwith ("Invalid token: " ^ Lexing.lexeme(lexbuf)) }
  104. and eat_until_nl = parse
  105. | newline { Lexing.new_line lexbuf; tokenize lexbuf }
  106. | _ { eat_until_nl lexbuf }
  107. and comment = parse (* comments can't be nested *)
  108. close_comment { tokenize lexbuf }
  109. | newline { Lexing.new_line lexbuf; comment lexbuf }
  110. | _ { comment lexbuf }