1/* Part of SWI-Prolog 2 3 Author: Jan Wielemaker 4 E-mail: J.Wielemaker@vu.nl 5 WWW: http://www.swi-prolog.org 6 Copyright (c) 2006-2011, University of Amsterdam 7 All rights reserved. 8 9 Redistribution and use in source and binary forms, with or without 10 modification, are permitted provided that the following conditions 11 are met: 12 13 1. Redistributions of source code must retain the above copyright 14 notice, this list of conditions and the following disclaimer. 15 16 2. Redistributions in binary form must reproduce the above copyright 17 notice, this list of conditions and the following disclaimer in 18 the documentation and/or other materials provided with the 19 distribution. 20 21 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 22 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 23 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS 24 FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 25 COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, 26 INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, 27 BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 28 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 29 CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30 LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN 31 ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 32 POSSIBILITY OF SUCH DAMAGE. 33*/ 34 35:- module(unicode_derived_core_properties, 36 [ unicode_derived_core_property/2, % ?Code, ?Prop 37 unicode_property/3 % +File, ?Code, ?Prop 38 ]). 39:- use_module(library(debug), [debug/3]). 40:- use_module(library(lists), [member/2, numlist/3]). 41:- use_module(library(readutil), [read_line_to_codes/2]). 42 43:- dynamic 44 derived_property/3, 45 loaded/1. 46 47% unicode_derived_core_property(+File, ?Code, ?Prop) 48% 49% 50 51unicode_derived_core_property(Code, Prop) :- 52 unicode_property('DerivedCoreProperties.txt', Code, Prop). 53 54unicode_property(File, Code, Prop) :- 55 loaded(File), !, 56 derived_property(Code, Prop, File). 57unicode_property(File, Code, Prop) :- 58 retractall(derived_property(_, _,File)), 59 process_file(File), 60 assert(loaded(File)), 61 unicode_property(File, Code, Prop). 62 63 64process_file(File) :- 65 open(File, read, In), 66 call_cleanup(process_stream(In, File), close(In)). 67 68process_stream(In, File) :- 69 read_line_to_codes(In, Line), 70 ( Line == end_of_file 71 -> true 72 ; process_line(Line, File), 73 process_stream(In, File) 74 ). 75 76process_line(Line, File) :- 77 debug(unicode_data, 'Line "~s"', [Line]), 78 ( phrase(line(Codes, Class), Line) 79 -> forall(member(C, Codes), 80 assert(derived_property(C, Class, File))) 81 ; format('ERROR: Could not parse "~s"~n', [Line]), 82 abort 83 ). 84 85 86 87line([], -) --> 88 ws, "#", skip_rest, !. 89line([], -) --> 90 ws. 91line(Codes, Class) --> 92 ucc(First), 93 ( ".." 94 -> ucc(Last), 95 { numlist(First, Last, Codes) } 96 ; { Codes = [First] } 97 ), 98 ws, ";", ws, 99 class(Class), 100 ws, 101 "#", 102 skip_rest. 103 104class(Class) --> 105 identifier(Id), 106 { downcase_atom(Id, Class) }. 107 108identifier(Word) --> 109 [C0], { code_type(C0, csymf) }, 110 csyms(Cs), 111 { atom_codes(Word, [C0|Cs]) }. 112 113csyms([H|T]) --> 114 [H], { code_type(H, csym) }, !, 115 csyms(T). 116csyms([]) --> 117 []. 118 119ucc(Val) --> 120 hex_digit(D0), 121 hex_digit(D1), 122 hex_digit(D2), 123 hex_digit(D3), 124 { Val0 is D0<<12 + D1<<8 + D2<<4 + D3 }, 125 xucc(Val0, Val). 126 127xucc(Val0, Val) --> 128 hex_digit(D), !, 129 { Val1 is Val0<<4 + D }, 130 xucc(Val1, Val). 131xucc(Val, Val) --> 132 []. 133 134hex_digit(D) --> 135 [C], 136 { code_type(C, xdigit(D)) }. 137 138w --> 139 [C], 140 { code_type(C, white) }. 141 142ws --> 143 w, !, 144 ws. 145ws --> 146 []. 147 148skip_rest(_, []). 149