Pattern Matching Application

Compare the advantages and disadvantages of the classical brute-force algorithm and the efficiency of the KMP algorithm.

#include <stdio.h> #include <stdlib.h> #include <string.h> #define MAXSIZE typedef struct {      Char Str[maxsize];  int length;      }seqstring;  int B_findex (seqstring s,int pos,seqstring t,int *count);  int Kmp_index (seqstring s,int pos,seqstring t,int next[],int *count);  void GetNext (seqstring t,int next[]);  void Getnextval (seqstring t,int nextval[]);  void PrintArray (seqstring t,int next[],int nextval[],int length); void Strassign (seqstring *s,char cstr[]);//The assignment of the string int strempty (seqstring s);//Determine if the string is an empty int strlength (seqstring s);//Find the length of the string degree operation void Strcopy (seqstring *t,seqstring S);//String copy operation int Strcompare (seqstring s,seqstring T);//string comparison operation int Strinsert (SEQS Tring *s,int pos,seqstring T);//string insert operation int Strdelete (seqstring *s,int pos,int len);//string delete operation int Strconcat (seqstring *t,s Eqstring S);//string connection operation int SubString (seqstring *sub,seqstring s,int poos,int len);//intercept substring operation int Strreplace (seqstring *s,seq String t,seqstring V);//string substitution operation int Strindex (SEQSTRing s,int pos,seqstring T);//string positioning operation void Strclear (seqstring *s);//empty string operation void Strprint (seqstring S);//String Output declaration #include "S Tring.h "/* Classic pattern matching algorithm brute-force*//* Assuming that the string is stored in sequential storage, then the Brute-force matching algorithm is as follows */int b_findex (seqstring s,int pos,seqstring t,i      NT *count)/* starts looking for the substring T in the first POS position in the main string s, and returns the position of the substring in the main string if found; otherwise returns -1*/{int i,j;      i = pos-1;      j = 0;      *count = 0; while (I < s.length && J < t.length) {if (s.str[i] = = T.str[j])/* If string S and string T correspond to the position of the character              Equal, the next character continues to be compared */{i++;          j + +;              } else/* If the characters of the current corresponding position are not equal, start with the next character of string s, starting from the No. 0 character of T */{i = i-j+1;          j = 0;      } (*count) + +;      } if (J >= t.length)/* If a string T is found in string s, the position of the substring T in the main string s is returned */{return i-j+1;      } else {return-1;String t,int next[],int *count) {int i,j;      i = pos-1;      j = 0;      *count = 0; while (I < s.length && J < t.length) {if ( -1 = = J | |              S.str[i] = = T.str[j])/* If the j=-1 or the current character is equal, continue to compare the following characters */{i++;          j + +; } else/* If the current character is not equal, move the pattern string to the right */{j = next[j];/* array Next save next function Value *} (*count      )++;      if (J >= t.length)/* matches successfully, returns the position of the substring T in the main string s, otherwise returns -1*/{return i-t.length+1;      } else {return-1;      }}/* The next function value/////* algorithm is described as follows */void GetNext (seqstring t,int next[]) {int j,k;      j = 0;      K =-1;      Next[0] =-1; while (J < t.length) {if ( -1 = = k | |              T.STR[J] = = T.str[k]) {j + +;              k++;          NEXT[J] = k;          } else {k = next[k]; }}}/* Improved algorithm as follows */void Getnextval (seqstring t,int nextval[])  {int j,k;      j = 0;      K =-1;      Nextval[0] =-1; while (J < t.length) {if ( -1 = = k | |              T.STR[J] = = T.str[k]) {j + +;              k++;              if (t.str[j]! = T.str[k]) {nextval[j] = k;              } else {nextval[j] = nextval[k];          }} else {k = nextval[k];      }}} void PrintArray (seqstring t,int next[],int nextval[],int length) {int J;      printf ("j:\t\t");      for (j = 0;j < length;j++) {printf ("%3d", j);      } printf ("\ n");      printf ("pattern string: \ t");      for (j = 0;j < length;j++) {printf ("%3c", T.str[j]);      } printf ("\ n");      printf ("next[j]:\t");      for (j = 0;j < length;j++) {printf ("%3d", Next[j]);      } printf ("\ n");      printf ("nextval[j]:\t"); for (j = 0;j < length;j++) {priNTF ("%3d", Nextval[j]);  } printf ("\ n");      } void Strassign (Seqstring *s,char cstr[])//String assignment operation (the character CStr value in the constant assigned to string S) {int i = 0;      for (i = 0;cstr[i]!= '; i++) {s->str[i] = Cstr[i];  } s->length = i;      } int Strempty (seqstring S)//Determine if the string is empty {if (s.length = = 0) {return 1;      } else {return 0;  }} int Strlength (seqstring S)//To find the length of the string operation {return s.length;      } void Strcopy (seqstring *t,seqstring s)//String copy operation (assigned each word in string S to T) {int i;      for (i = 0;i < s.length; i++) {t->str[i] = S.str[i];  } t->length = s.length;      } int Strcompare (seqstring s,seqstring T)//string comparison operation {int i; for (i = 0;i < S.length&&i < t.length; i++)//Compare the characters in two strings {if (S.str[i]! = T.str[i])//If there are different characters, return          Two-character Difference {return (s.str[i]-t.str[i]); }} return (s.length-t.length);//If the comparison is complete, returns the difference of the length of the two string} int Strinsert (SEQSTRing *s,int pos,seqstring t)//String insert operation (Insert string T at pos position of string S) {int i;          if (pos < 0 | | pos-1 > S->length) {printf ("Incorrect insertion position \ n");      return 0;  if (s->length + t.length <= MAXSIZE)//substring is fully inserted into the string {//before inserting the substring T, move the POS character in S to the back of Len position for (i          = S->length+t.length-1;i >= pos+t.length-1;i--) {S->str[i] = s->str[i-t.length];          }//Insert the string into S for (i = 0;i < T.length; i++) {s->str[pos+i-1] = T.str[i];          } s->length = S->length +t.length;      return 1; The Else if (POS +t.length <= MAXSIZE)//substring is completely inserted in S, but the characters in s are truncated {for (i = maxsize-1;i > T.length +pos-1          ; i--) {S->str[i] = s->str[i-t.length];          } for (i = 0;i < T.length; i++) {s->str[i+pos-1] = T.str[i];          } s->length = MAXSIZE;      return 0; } elseThe substring t cannot be completely inserted into S, and T will have characters discarded {for (i = 0;i < maxsize-pos;i++) {s->str[i+pos-1] = T.          Str[i];          } s->length = MAXSIZE;      return 0;      }} int Strdelete (seqstring *s,int pos,int len)//String delete operation (delete the Len character starting at Pos in string S, and then move the following character forward) {int i,flag;          if (pos < 0 | | Len < 0 | | pos+len-1 > S->length) {printf ("Incorrect delete location, parameter len not valid \ n");      Flag = 0; } else {for (i = pos+len;i <= s->length-1;i++) {S->str[i-len] = S->s          Tr[i];      } s->length = s->length-len;//modifies the length of the string S flag = 1;  } return flag;      } int Strconcat (seqstring *t,seqstring s)//String connection operation (connect the string S to the back of the string T) {int i,flag;          if (t->length +s.length <= MAXSIZE) {for (i = t->length; i < t->length +s.length; i++)          {T->str[i] = s.str[i-t->length]; } t->length = T->length +s.leNgth;      flag = 1;              } else if (T->length < MAXSIZE) {for (i = t->length; I < maxsize;i++) {          T->str[i] = s.str[i-t->length];          } t->length = MAXSIZE;      Flag = 0;  } return flag;      } int SubString (seqstring *sub,seqstring s,int pos,int len)//Intercept substring operation (intercept string S in the sequence of characters starting from Pos, length len, and assign to sub) {int i;          if (pos < 0 | | Len < 0 | | pos+len-1 > S.length) {printf ("parameter pos and len not valid \ n");      return 0;          } else {for (i = 0;i < len;i++) {Sub->str[i] = s.str[i+pos-1];          } sub->length = Len;      return 1; }} int Strindex (seqstring s,int pos,seqstring T)//String positioning operation (in the main string s in the first POS position to find the substring T, if there is a substring equal to the string T value in the main string s),      Returns the first occurrence of a substring after the POS character of the main string {int i,j;      if (Strempty (T)) {return 0;      } i = pos;      j = 0; while (I < s.length && J < t.length) {IF (s.str[i] = = T.str[j]) {i++;          j + +;              } else//if the characters of the current corresponding position are not equal, start with the next character of string s, starting from the No. 0 character of T, {i = i-j+1;          j = 0;      }} if (J >= t.length)//If a string T is found in string s, the position of the substring T in the main string s {return i-j+1 is returned;      } else {return-1;      }} int Strreplace (seqstring *s,seqstring t,seqstring V)//String substitution operation (if substring t exists in string s, then V replaces all substring T in string s) {int flag;      int i = 0;      if (Strempty (T)) {return 0; } while (i) {i = Strindex (*s,i,t);//Find the position of T in string S using the string's positioning if (i) {strdelete                  (S,i,strlength (T));//If a substring T is found, the string T in S is removed from flag = Strinsert (s,i,v);//Insert V if (!flag) {              return 0;          } i + = Strlength (V);  }} return 1;  } void Strclear (seqstring *s)//empty string operation {s->length = 0;      } void Strprint (seqstring S)//string output declaration {int i; For(i = 0;i < s.length; i++)      {printf ("%c", S.str[i]);  } printf ("\ n");      } #include "string.h" int main (void) {seqstring s,t;      int count1 = 0;      int count2 = 0;      int count3 = 0;      int find;      int next[40];      int nextval[40];      Strassign (&s, "Abaababaddecab");      Strassign (&t, "Abad");      GetNext (T,next);      Getnextval (T,nextval);      printf ("The next of pattern string T and the value of the improved Next: \ n");      PrintArray (T,next,nextval,strlength (T));      Find = B_findex (s,1,t,&count1);      if (Find > 0) {printf ("Brute-force algorithm compares the number of times:%2d\n", count1);      } find = Kmp_index (S,1,t,next,&count2);      if (Find > 0) {printf ("Using Next's KMP algorithm compares the number of times:%2d\n", Count2);      } find = Kmp_index (S,1,T,NEXTVAL,&AMP;COUNT3);      if (Find > 0) {printf ("Using Nextval's KMP algorithm compares the number of times:%2d\n", COUNT3);      } strassign (&s, "CBCCCCBCACBCCBACBCCBCBCBC");      Strassign (&t, "CBCCBCBC");   GetNext (T,next);   Getnextval (T,nextval);      printf ("The next of pattern string T and the value of the improved Next: \ n");      PrintArray (T,next,nextval,strlength (T));      Find = B_findex (s,1,t,&count1);      if (Find > 0) {printf ("Brute-force algorithm compares the number of times:%2d\n", count1);      } find = Kmp_index (S,1,t,next,&count2);      if (Find > 0) {printf ("Using Next's KMP algorithm compares the number of times:%2d\n", Count2);      } find = Kmp_index (S,1,T,NEXTVAL,&AMP;COUNT3);      if (Find > 0) {printf ("Using Nextval's KMP algorithm compares the number of times:%2d\n", COUNT3);  } return 0;   }

The results of the operation are as follows:

Copyright NOTICE: This article for Bo Master original article, without Bo Master permission not reproduced.

Pattern Matching Application