static qse_rex_node_t* comp_atom (comp_t* com)
{
qse_rex_node_t* atom;
if (!IS_ESC(com))
{
switch (com->c.value)
{
case QSE_T('('):
atom = comp_group (com);
if (atom == QSE_NULL) return QSE_NULL;
break;
case QSE_T('.'):
atom = newnode (com, QSE_REX_NODE_ANY);
if (atom == QSE_NULL) return QSE_NULL;
if (getc_esc(com) <= -1) return QSE_NULL;
break;
case QSE_T('^'):
atom = newnode (com, QSE_REX_NODE_BOL);
if (atom == QSE_NULL) return QSE_NULL;
if (getc_esc(com) <= -1) return QSE_NULL;
break;
case QSE_T('$'):
atom = newnode (com, QSE_REX_NODE_EOL);
if (atom == QSE_NULL) return QSE_NULL;
if (getc_esc(com) <= -1) return QSE_NULL;
break;
case QSE_T('['):
atom = newnode (com, QSE_REX_NODE_CSET);
if (atom == QSE_NULL) return QSE_NULL;
if (getc_esc(com) <= -1) return QSE_NULL;
if (charset(com, atom) <= -1) return QSE_NULL;
break;
default:
if (com->rex->option & QSE_REX_STRICT)
{
/* check if a special charcter is at the
* position that requires a normal character. */
switch (com->c.value)
{
case QSE_T('{'):
/* { is a normal charcter when bound is disabled */
if (com->rex->option & QSE_REX_NOBOUND) break;
case QSE_T(')'):
case QSE_T('?'):
case QSE_T('*'):
case QSE_T('+'):
/* it's at the wrong postion */
com->rex->errnum = QSE_REX_ESPCAWP;
return QSE_NULL;
}
}
goto normal_char;
}
}
else
{
normal_char:
/* normal character */
atom = newcharnode (com, com->c.value);
if (atom == QSE_NULL) return QSE_NULL;
if (getc_esc(com) <= -1) return QSE_NULL;
}
atom->occ.min = 1;
atom->occ.max = 1;
if (!IS_ESC(com))
{
/* handle the occurrence specifier, if any */
if (comp_occ (com, atom) == QSE_NULL) return QSE_NULL;
}
return atom;
}
int main (int argc, char **argv)
{
/* Declare main function variables */
struct charnode* head;
FILE* thefile;
char c; /* active character*/
struct wordnode* pointer; /*where you are in the word (long words require more than one node)*/
struct wordnode* word; /*current word*/
struct charnode* pos; /*position in tree*/
struct varnode* test; /* for testing new words against existing variation*/
struct varnode* lag; /*lags test by one position to allow insertion at end of linked list*/
int i; /* counter variable for iterators*/
if (argc != 2)
{
fprintf (stderr, "The wrong number of arguments were entered. Please try again.\n");
return 0;
}
if (strcmp(argv[1], "-h") == 0)
{
fprintf (stdout, "\n\nWordstat has the following usage interface: wordstat <argument>;\n\nwhere <argument> is either the name of the file that wordstat should process,\n\nor -h, which means that wordstat should print this help menu.\n\nWhen invoked with a valid file name, wordstat should find and output \n\nall the unique words in the file in lexicographical order,\n\nalong with the total number of times each word appears (case-insensitive) \n\nand a count of different case-sensitive versions of the word.\n\n");
return 0;
}
thefile = fopen(argv[1],"r");
if (thefile == NULL)
{
fprintf (stderr, "File could not be opened. Please check the file name and try again.\n");
fprintf (stderr, "%s\n", argv[1]);
return 0;
}
head=newcharnode();
c=fgetc(thefile);
/* read in file*/
while (c != EOF)
{
/*get the word*/
if (isalpha(c)!=0)
{
word = newwordnode();
pointer=word;
i=0;
while(isalnum(c)!=0)
{
if(i==39)
{
pointer->next = newwordnode();
}
if(i==40)
{
pointer=pointer->next;
i=0;
}
pointer->word[i]=c;
i++;
c=fgetc(thefile);
}
/*put the word in the tree*/
c=word->word[0];
pointer=word;
pos=head;
i=0;
while (c!='\0')
{
if (pos->next==NULL)
{
pos->next=newnextarray();
}
if (isalpha(c)!=0)
{
if(pos->next->next[tolower(c)-'a']==NULL)
{
pos->next->next[tolower(c)-'a']=newcharnode();
}
pos = pos->next->next[tolower(c)-'a'];
}
if (isdigit(c)!=0)
{
if(pos->next->next[tolower(c)-'0'+26]==NULL)
{
pos->next->next[tolower(c)-'0'+26]=newcharnode();
}
pos = pos->next->next[tolower(c)-'0'+26];
}
i++;
if(i==40)
{
i=0;
pointer=pointer->next;
}
c=pointer->word[i];
}
pos->occurcount++;
/* scan variations */
/* write this method*/
if(pos->variations==NULL)
{
pos->variations=newvarnode();
pos->variations->thisvar=word;
pos->varcount++;
}else
{
test=pos->variations;
i=0; /*using i for a boolean here*/
while(test != NULL)
{
lag=test;
pointer=test->thisvar;
if(compare(pointer,word)==1)
{
i=1;
freewordnode(word);
break;
}
test=test->next;
}
if(i==0)
{
lag->next=newvarnode();
lag->next->thisvar=word;
pos->varcount++;
}
}
}
c=fgetc(thefile);
}
/*end file read in*/
i=fclose(thefile);
if (i!=0)
{
fprintf(stderr, "the file failed to close");
}
/*print and free*/
print(head);
freecharnode(head);
return 0;
}
