PLearn 0.1
TypesNumeriques.cc
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // PLearn (A C++ Machine Learning Library)
00004 // Copyright (C) 1998 Pascal Vincent
00005 // Copyright (C) 1999,2000 Pascal Vincent, Yoshua Bengio and University of Montreal
00006 //
00007 // Redistribution and use in source and binary forms, with or without
00008 // modification, are permitted provided that the following conditions are met:
00009 //
00010 //  1. Redistributions of source code must retain the above copyright
00011 //     notice, this list of conditions and the following disclaimer.
00012 //
00013 //  2. Redistributions in binary form must reproduce the above copyright
00014 //     notice, this list of conditions and the following disclaimer in the
00015 //     documentation and/or other materials provided with the distribution.
00016 //
00017 //  3. The name of the authors may not be used to endorse or promote
00018 //     products derived from this software without specific prior written
00019 //     permission.
00020 //
00021 // THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS OR
00022 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
00023 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
00024 // NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
00025 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
00026 // TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
00027 // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
00028 // LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
00029 // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
00030 // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
00031 //
00032 // This file is part of the PLearn library. For more information on the PLearn
00033 // library, go to the PLearn Web site at www.plearn.org
00034 
00035 /* *******************************************************      
00036  * $Id: TypesNumeriques.cc 3994 2005-08-25 13:35:03Z chapados $
00037  * AUTHORS: Steven Pigeon & Yoshua Bengio
00038  * This file is part of the PLearn library.
00039  ******************************************************* */
00040 
00041 #include <cstdlib>
00042 #include <cstring>
00043 #include "TypesNumeriques.h"
00044 
00045 namespace PLearn {
00046 using namespace std;
00047 
00048 
00050 const char    DIGITsymbols[] = "0123456789";
00051 const char    ALPHAsymbols[] = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ";
00052 const char *ORDINALS[] = {"d","nd","th","st",0}; // 3d, 2nd, 12th, 1st
00053 
00055 const char *eNumericTypeNames(int a)
00056 {
00057     static char retour[128];
00058 
00059     // all that applies
00060     if (a==NT_NOT_NUMERIC)
00061         return "not numeric";
00062     else {
00063         retour[0]=0;
00064         if (a & NT_ORDINAL)  strcat(retour,"ordinal ");
00065         if (a & NT_CARDINAL) strcat(retour,"cardinal ");
00066         if (a & NT_CURRENCY) strcat(retour,"currency ");
00067         if (a & NT_PREFIXED) strcat(retour,"prefixe ");
00068         if (a & NT_SUFFIXED) strcat(retour,"suffixe ");
00069         if (a & NT_PERCENT)  strcat(retour,"pourcentage ");
00070         if (a & NT_RANGE)    strcat(retour,"range ");
00071         if (a & NT_TIME)     strcat(retour,"temps ");
00072         if (a & NT_CODE)     strcat(retour,"code ");
00073         if (a & NT_UNKNOWN_NUMERIC_TYPE) strcat(retour," ??? ");
00074         return retour;
00075     }
00076 }
00077 
00079 bool containsChar(const char *s, const char *symbols)
00080 {
00081     bool found = false;
00082     int  i=0;
00083     while (!found && symbols[i])
00084     {
00085         found = (bool)strchr(s,symbols[i]);
00086         i++;
00087     }
00088     return found;
00089 }
00090 
00091 
00093 char * stringPos(const char *s, const char *strings[])
00094 {
00095     char *t = 0;
00096     int  i=0;
00097     while (!t && strings[i])
00098     {
00099         t = strstr(s,strings[i]);
00100         i++;
00101     }
00102     return t;
00103 }
00104 
00105 
00107 bool looksNumeric(const char *s)
00108 {
00109     return containsChar(s,DIGITsymbols);
00110 }
00111 
00113 bool elementOf(const char *s, const char t)
00114 {
00115     return (bool)strchr(s,t);
00116 }
00117 
00119 void compactRepresentationTranslate(char *t)
00120 {
00121     int d=0;
00122     int s=0;
00123 
00124     while (t[s])
00125     { 
00126         if (elementOf(DIGITsymbols,t[s]))
00127         {
00128             t[d++]='n';
00129             // skip to the next non-digit
00130             do { s++; } while (t[s] && (elementOf(DIGITsymbols,t[s]) || (t[s]==',')) );
00131         }
00132         else if (elementOf(ALPHAsymbols,t[s]))
00133         {
00134             if ( (stringPos(&t[s],ORDINALS)==&t[s]) // starts here
00135                  && (t[d-1]=='n') ) // and the previous run was composed of digits
00136                 t[d++]='o';
00137             else t[d++]='a';
00138             // skip to the next non-alpha
00139             do { s++; } while (t[s] && elementOf(ALPHAsymbols,t[s]));
00140         }
00141         else t[d++]=t[s++];
00142     }
00143     t[d]=0;
00144 
00145 }
00146 
00148 void compactRepresentationShrinkNum(char *t)
00149 {
00150     // remplace n.n ou .n par n, 
00151     // mais laisse les constructions du genre n.n.n intactes
00152     int d=0;
00153     int s=0;
00154 
00155     while (t[s])
00156     {
00157         if ( (strstr(&t[s],"n.n") == &t[s]) && 
00158              (t[s+3]!='.') && 
00159              ( (s-1<0) || (t[s-1]!='.') )
00160             )
00161         {
00162             t[d++]='n';
00163             s+=3;
00164         }
00165         else if ( (strstr(&t[s],".n") == &t[s]) &&
00166                   (t[s+2]!='.') &&
00167                   ( (s-1<0) || t[s-1]!='n')) 
00168         {
00169             t[d++]='n';
00170             s+=2;
00171         }
00172         else t[d++]=t[s++];
00173     }
00174     t[d]=0;
00175 }
00176 
00178 void compactRepresentationRangesAndOrdinals(char *t)
00179 {
00180     // remplace n-n par r et no par o
00181     int d=0;
00182     int s=0;
00183 
00184     while (t[s])
00185     {
00186         if ( strstr(&t[s],"n-n") == &t[s])
00187         {
00188             t[d++]='r';
00189             s+=3;
00190         }
00191         else if ( strstr(&t[s],"no") == &t[s])
00192         {
00193             t[d++]='o';
00194             s+=2;
00195         }
00196         else t[d++]=t[s++];
00197     }
00198     t[d]=0;
00199 }
00200 
00202 void compactRepresentation(char *t)
00203 {
00204     compactRepresentationTranslate(t); // remplace les lettres et chiffres par des codes.
00205     compactRepresentationShrinkNum(t); // replace n.n par n, etc.
00206     compactRepresentationRangesAndOrdinals(t); // remplace n-n par r et no par o
00207 
00208     int s=0;
00209     int d=0;
00210 
00211     // strip les tirets -  
00212     while (t[s]) 
00213         if (t[s]!='-') 
00214             t[d++]=t[s++]; 
00215         else s++;
00216 
00217     t[d]=0;
00218 
00219     // copie une seule instance du meme symbole.
00220     s=0;
00221     d=0;
00222     while (t[s])
00223     {
00224         t[d++]=t[s++];
00225         while (t[s] && (t[s]==t[d-1])) s++;
00226     }
00227 
00228     if (t[d-1]=='.') d--; // trailing .
00229     t[d]=0;
00230 
00231     char c = '#';
00232     d=0;
00233     do 
00234     {
00235         char tt = t[d];
00236         t[d]=c;
00237         c=tt;
00238         d++;
00239     } while (c);
00240     t[d]=0;
00241 }
00242 
00244 int numericType(const char *mot)
00245 {
00246     if (looksNumeric(mot))
00247     {
00248         int classe=0;
00249         char t[128];
00250         bool pourcent=false;
00251         strcpy(t,mot);
00252 
00253         compactRepresentation(t); 
00254 
00255         // skips the # in the begining
00256 
00257         if (char *tt= strchr(t,'%')) 
00258             *tt=0, pourcent = true; // delete trailing %
00259 
00260         for (int i=0; (rules[i].pattern[0]) && (!classe); i++)
00261             if (strcmp(rules[i].pattern,t)==0) classe = rules[i].attributs;
00262 
00263         if (pourcent) classe += NT_PERCENT;
00264 
00265         return classe ?  classe : NT_UNKNOWN_NUMERIC_TYPE;
00266     }
00267     else return NT_NOT_NUMERIC;
00268 }
00269 
00270 
00271 
00272 } // end of namespace PLearn
00273 
00274 
00275 /*
00276   Local Variables:
00277   mode:c++
00278   c-basic-offset:4
00279   c-file-style:"stroustrup"
00280   c-file-offsets:((innamespace . 0)(inline-open . 0))
00281   indent-tabs-mode:nil
00282   fill-column:79
00283   End:
00284 */
00285 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines