problem collecting data from input file

Hello to all.

I am unable to collect data from my input files. The format of the input files is standardized.

the format is something like this:

>blah blah blah
SDJKDJDJKFJDSKLJGDKLJFDKJDFJDSKJ

I need to be able to take the info after the ">" and store in a structure called
loadedSequences.name and then take the characters after that and store in
a structure named loadedSequences.data.

I am able to deal with input files and get the first part but unable to collect the second part.

Here is the relevant code:

Code:

if( (strcmp ( command, "read" )) == 0 )
                    {
                        
                        filename = strtok(NULL, " \t\n" ) ; // collect filename                       
                        if( filename ) 
                            { 
                                input = fopen(filename, "r") ;
                                if ( !input )
                                    {
                                        perror(filename);
                                        continue ;
                                    }                                
                            }                            
                       
                        fgets( header_data, 1000, input) ; 
                        
                        seqName = &header_data[1] ;   // After the > in FASTA format  
                        
                        loadedSequences[nSequences].name = 
                            (char *) malloc( ( strlen(seqName) + 1 ) * sizeof( char ) ) ;
                            
                        strcpy( loadedSequences[nSequences].name , seqName ) ;
                        
                        // Collect the sequence from FASTA file
                        
                        loadedSequences[nSequences].data[n++] = 0 ;
                        
                         while (c = getc(input) != EOF)
                                    {
                                        if(c >= 'A' && c <= 'Z')
                                            {
                                                loadedSequences[nSequences].data[n++] = c ;
                                            }
                                    }  
                                       
                        
                        loadedSequences[nSequences].length = strlen((loadedSequences[nSequences].data)) ;
                        
                        fclose(input) ;
                        
                        ++nSequences ;
               
                    }

Any help would be great.

loadedSequences.data will always be an empty string, if you put a 0 in the first element. Of course that assumes that you initialize n at all, which it doesn't appear that you do. But you don't ever ever ever ever ever ever ever want your strings to start with a 0.

Still not able to get data.


Here is my code again with the declarations:

Code:

#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include <stdlib.h>

typedef struct { char *name ; char data[1000000] ; int length ; int type ; } sequence ;

sequence loadedSequences[1000] ;

int nSequences = 0 ;
    
int main()
    {
        char std_input[1000] ;  // prev. buffer
        char header_data[1000] ;
        char seq_data[100000] ;
        char buffer[100000] ;
        
        FILE *input ;
        
        char *seqName ;        
        char *command ;
        char *filename, *list_num ;
        
        int i = 0 ;
        int c ;
        int n = 0 ;
        
        for(;;)
            {
                printf("SeqTool> ") ;
                
                fgets(std_input, 1000, stdin) ;
                fpurge(stdin) ;
                
                // Eliminating the newline character
                char *p = strchr(std_input, '\n') ;
                if (p) 
                    {
                        *p = '\0' ; 
                    } 
                                          
                command = strtok( std_input, " \t\n" ) ; 
                
////////////////// Load sequence in FASTA format //////////////////////////
                
                if( (strcmp ( command, "read" )) == 0 )
                    {
                        
                        filename = strtok(NULL, " \t\n" ) ; // collect filename                       
                        if( filename ) 
                            { 
                                input = fopen(filename, "r") ;
                                if ( !input )
                                    {
                                        perror(filename);
                                        continue ;
                                    }                                
                            }                            
                       
                        fgets( header_data, 1000, input) ; 
                        
                        seqName = &header_data[1] ;   // After the > in FASTA format  
                        
                        loadedSequences[nSequences].name = 
                            (char *) malloc( ( strlen(seqName) + 1 ) * sizeof( char ) ) ;
                            
                        strcpy( loadedSequences[nSequences].name , seqName ) ;
                        
                        // Collect the sequence from FASTA file
                        
                        
                         while (c = getc(input) != EOF)
                                    {
                                        if(c >= 'A' && c <= 'Z')
                                            {
                                                loadedSequences[nSequences].data[n++] = c ;
                                            }
                                    }  
                                       
                        
                        loadedSequences[nSequences].length = strlen((loadedSequences[nSequences].data)) ;
                        
                        fclose(input) ;
                        
                        ++nSequences ;
               
                    }

You still need to re-initialize n to 0 each time through.

Still not able to collect data with code.

Code:

if( (strcmp ( command, "read" )) == 0 )
                    {
                        
                        filename = strtok(NULL, " \t\n" ) ; // collect filename                       
                        if( filename ) 
                            { 
                                input = fopen(filename, "r") ;
                                if ( !input )
                                    {
                                        perror(filename);
                                        continue ;
                                    }                                
                            }                            
                       
                        fgets( header_data, 1000, input) ; 
                        
                        seqName = &header_data[1] ;   // After the > in FASTA format  
                        
                        loadedSequences[nSequences].name = 
                            (char *) malloc( ( strlen(seqName) + 1 ) * sizeof( char ) ) ;
                            
                        strcpy( loadedSequences[nSequences].name , seqName ) ;
                        
                        // Collect the sequence from FASTA file
                        
                        
                         while (c = getc(input) != EOF)
                                    {
                                        n = 0 ;
                                        if(c >= 'A' && c <= 'Z')
                                            {
                                                loadedSequences[nSequences].data[n++] = c ;
                                             
                                            }
                                    }  
                                       
                        
                        loadedSequences[nSequences].length = strlen((loadedSequences[nSequences].data)) ;
                        
                        fclose(input) ;
                        
                        ++nSequences ;
               
                    }

Now you're overwriting loadedSequences[nSequences].data[0] each time. In the big loop, but not inside that while loop.

It is still not getting the data

Code:

if( (strcmp ( command, "read" )) == 0 )
                    {
                        
                        filename = strtok(NULL, " \t\n" ) ; // collect filename                       
                        if( filename ) 
                            { 
                                input = fopen(filename, "r") ;
                                if ( !input )
                                    {
                                        perror(filename);
                                        continue ;
                                    }                                
                            }                            
                       
                        fgets( header_data, 1000, input) ; 
                        
                        seqName = &header_data[1] ;   // After the > in FASTA format  
                        
                        loadedSequences[nSequences].name = 
                            (char *) malloc( ( strlen(seqName) + 1 ) * sizeof( char ) ) ;
                            
                        strcpy( loadedSequences[nSequences].name , seqName ) ;
                        
                        // Collect the sequence from FASTA file                                             
                        
                        n = 0 ;
                        
                        while(fgets(seq_data, 1000, input))
                            {                     
                                 while (c = (getc(input) != EOF))
                                            {
                                                if(c >= 'A' && c <= 'Z')
                                                    {
                                                        loadedSequences[nSequences].data[n++] = c ;
                                                     
                                                    }
                                            }  
                            }          
                        
                        loadedSequences[nSequences].length = strlen((loadedSequences[nSequences].data)) ;
                        
                        fclose(input) ;
                        
                        ++nSequences ;
               
                    }

Originally Posted by gkoenig

It is still not getting the data

Code:

if( (strcmp ( command, "read" )) == 0 )
                    {
                        
                        filename = strtok(NULL, " \t\n" ) ; // collect filename                       
                        if( filename ) 
                            { 
                                input = fopen(filename, "r") ;
                                if ( !input )
                                    {
                                        perror(filename);
                                        continue ;
                                    }                                
                            }                            
                       
                        fgets( header_data, 1000, input) ; 
                        
                        seqName = &header_data[1] ;   // After the > in FASTA format  
                        
                        loadedSequences[nSequences].name = 
                            (char *) malloc( ( strlen(seqName) + 1 ) * sizeof( char ) ) ;
                            
                        strcpy( loadedSequences[nSequences].name , seqName ) ;
                        
                        // Collect the sequence from FASTA file                                             
                        
                        n = 0 ;
                        
                        while(fgets(seq_data, 1000, input)) /*WTF?*/
                            {                     
                                 while (c = (getc(input) != EOF))
                                            {
                                                if(c >= 'A' && c <= 'Z')
                                                    {
                                                        loadedSequences[nSequences].data[n++] = c ;
                                                     
                                                    }
                                            }  
                            }          
                        
                        loadedSequences[nSequences].length = strlen((loadedSequences[nSequences].data)) ;
                        
                        fclose(input) ;
                        
                        ++nSequences ;
               
                    }

So you added a line there from last time, which takes 1000 characters from your input file and throws them away. Why?

I am trying to set myself at the second line of the input file so that I can read data from there until the end of the file.

Code:

n = 0 ;
                                            
                         while (c = (getc(input) != EOF))
                                    {
                                        if(c >= 'A' && c <= 'Z')
                                            {
                                                loadedSequences[nSequences].data[n++] = c ;
                                             
                                            }
                                    }

Originally Posted by gkoenig

I am trying to set myself at the second line of the input file so that I can read data from there until the end of the file.

Code:

n = 0 ;
                                            
                         while (c = (getc(input) != EOF))
                                    {
                                        if(c >= 'A' && c <= 'Z')
                                            {
                                                loadedSequences[nSequences].data[n++] = c ;
                                             
                                            }
                                    }

Well, you were already at the second line of the file, since you read the first one with the bit about name. Also, I think you've got some parentheses sideways:

Code:

while ((c = getc(input)) != EOF)

otherwise the truth value would come from the assignment, not the comparison.

Still unable to collect sequence data with code:

Code:

 if( (strcmp ( command, "read" )) == 0 )
                    {
                        
                        filename = strtok(NULL, " \t\n" ) ; // collect filename                       
                        if( filename ) 
                            { 
                                input = fopen(filename, "r") ;
                                if ( !input )
                                    {
                                        perror(filename);
                                        continue ;
                                    }                                
                            }                            
                       
                        fgets( header_data, 1000, input) ; 
                        
                        seqName = &header_data[1] ;   // After the > in FASTA format  
                        
                        loadedSequences[nSequences].name = 
                            (char *) malloc( ( strlen(seqName) + 1 ) * sizeof( char ) ) ;
                            
                        strcpy( loadedSequences[nSequences].name , seqName ) ;
                        
                        // Collect the sequence from FASTA file                                             
                        
                        n = 0 ;
                                            
                         while (c = getc(input) != EOF)
                                    {
                                        if(c >= 'A' && c <= 'Z')
                                            {
                                                loadedSequences[nSequences].data[n++] = c ;
                                             
                                            }
                                    }  
                                  
                        
                        loadedSequences[nSequences].length = strlen((loadedSequences[nSequences].data)) ;
                        
                        fclose(input) ;
                        
                        ++nSequences ;
               
                    }

Any suggestions would be great

(c = getc(input)) != EOF

Thank you for the help. Everything seems to be going fine. Sorry the newbie mistake.