Count paragraph in file - c

i am working in file system in that i am counting paragraph from the file but
i am not getting please suggest me how can i do that i tried this but not getting what i want
int main()
{
FILE *fp=fopen("200_content.txt ","r");
int pCount=0;
char c;
while ((c=fgetc(fp))!=EOF)
{
if(c=='\n'){pCount++;}
else{continue;}
}
printf("%d",pCount);
return 0;
}

You should declare c as int instead of char.
Also, remember to fclose(fp); before main() returns.

A paragraph contains two subsequent '\n's, use a variable for counting the two '\n's, like this,
int main()
{
FILE *fp=fopen("200_content.txt ","r");
int pCount=0;
char c;
int newln_cnt=0;
while ((c=fgetc(fp))!=EOF)
{
if(c=='\n')
{
newln_cnt++;
if(newln_cnt==2)
{
pCount++;
newln_cnt=0;
}
}
else{continue;}
}
printf("%d",pCount);
return 0;
}

You code counts the number of newline '\n' characters, not empty line which demarcates the paragraphs. Use fgets to read lines from the file. I suggest this -
#include <stdio.h>
// maximum length a line can have in the file.
// +1 for the terminating null byte added by fgets
#define MAX_LEN 100+1
int main(void) {
char line[MAX_LEN];
FILE *fp = fopen("200_content.txt", "r");
if(fp == NULL) {
printf("error in opening the file\n");
return 1;
}
int pcount = 0;
int temp = 0;
while(fgets(line, sizeof line, fp) != NULL) {
if(line[0] == '\n') {
// if newline is found and temp is 1 then
// this means end of the paragraph. increase
// the paragraph counter pcount and set temp to 0
if(temp == 1)
pcount++;
temp = 0;
}
else {
// if a non-empty line is found, this means
// the start of the paragraph
temp = 1;
}
}
// if the last para doesn't end with empty line(s)
if(temp == 1)
pcount++;
printf("number of para in the file is %d\n", pcount);
return 0;
}

For starters, I assume that you consider a new line to be a new paragraph.
i.e.
This is line 1.
This is line 2.
has 2 paragraphs.
What your code does is neglect the case where there is an EOF and not a newline character (\n) after This is line 2.
One way to fix this is to use an extra char variable.
int main()
{
FILE *fp=fopen("200_content.txt ","r");
int pCount=0;
char c; // char that checks
char last_c; //record of the last character read in the loop
while ((c=fgetc(fp))!=EOF)
{
if(c=='\n'){pCount++;}
last_c = c;
else{continue;} //this line is redundant. You can remove it
}
if (last_c != '\n') pCount++; //if EOF at the end of line and not '\n'
printf("%d",pCount);
return 0;
}

void analyze_file(const char *filename) {
FILE* out_file;
out_file = fopen(filename,"r");
int size;
if(out_file == NULL)
{
printf("Error(analyze_file): Could not open file %s\n",filename);
return;
}
fseek(out_file,0,SEEK_SET);
char ch,ch1;
int alpha_count = 0,num_count = 0,non_alnum =0,charac=0;
int word_count =0,line=0;
int para=0;
while(!feof(out_file))
{
ch = fgetc(out_file);
if (isalpha(ch))
alpha_count++;
else if(isdigit(ch))
num_count++;
else if(!isalnum(ch) && ch!='\n' && !isspace(ch))
++non_alnum;
else if(ch=='\n')
{ line++;
ch1 = fgetc(out_file);// courser moves ahead , as we read
fseek(out_file,-1,SEEK_CUR); // bringing courser back
}
else if(ch == ch1)
{para++; //paragraph counter
word_count--;
}
if(ch==' '||ch=='\n')
{
word_count++;
}
if(ch==EOF)
{
word_count++;line++;para++;
}
}
non_alnum -=1;// EOF character subtracted.
charac = alpha_count + non_alnum + num_count;
fclose(out_file);
printf("#Paragraphs = %d\n",para);
printf("#lines = %d\n",line);
printf("#Words = %d\n",word_count);
printf("#Characters = %d\n",charac);
printf("Alpha = %d\n",alpha_count);
printf("Numerical = %d\n",num_count);
printf("Other = %d\n",non_alnum);
printf("\n");
return;
}

Related

Function is not correctly incrementing variable by 1

I have a function that returns the number of lines, characters, and words in an array. For some reason, when i loop through the array to print the values I am only getting the corrrect value for lines, the characters and words are returning as 0. All the functions are predetermined by my professor and my job is to fill them in.
int main(int argc, char **argv)
{
int *myArray = get_counts(argv[1]);
for (int i = 0; i < 3; i++)
{
printf("%d\n", myArray[i]);
}
return 0;
}
int *get_counts(char *filename)
{
FILE *file;
file = fopen(filename, "r");
if (file == NULL)
{
printf("NULL FILE");
}
char c;
int h;
bool whitespace = true;
static int arr[3] = {0,0,0};
do
{
c = fgetc(file);
if (c == '\n')
{
arr[0] ++;
}
}while (c != EOF);
while (true)
{
h = fgetc(file);
if (feof(file))
{
break;
}
else if (ferror(file))
{
printf("error reading file");
}
arr[2] ++;
if (whitespace && !isspace(h))
{
arr[1] ++;
whitespace = false;
}
else if (!whitespace &&isspace(h))
{
whitespace = true;
}
}
fclose(file);
return arr;
}
The best option is probably to just iterate through the file in one loop (you could also rewind() after the first loop). Use the return value of fgetc() to determine of you are at EOF instead of separate feof() calls. I also made the the result array an (out) argument instead of using a static variable (the latter is not reentrant if you ever want to call this from multiple threads and it's easy to do):
#include <ctype.h>
#include <stdbool.h>
#include <stdio.h>
#include <string.h>
void get_counts(char *filename, int arr[3]) {
memset(arr, 0, 3 * sizeof(int));
FILE *file = fopen(filename, "r");
if (file == NULL) {
printf("NULL FILE");
return;
}
bool whitespace = true;
for(;;) {
int c = fgetc(file);
if(c == EOF)
break;
else if(c == '\n')
arr[0]++;
else if (whitespace && !isspace(c)) {
arr[1]++;
whitespace = false;
} else if (!whitespace && isspace(c))
whitespace = true;
arr[2]++;
}
fclose(file);
}
int main(int argc, char **argv) {
int myArray[3];
get_counts(argv[1], myArray);
for (int i = 0; i < 3; i++) {
printf("%d\n", myArray[i]);
}
}
The output on the above file is:
39
94
715
The word count 94 doesn't agree with wc -w but you could be using a different definition of what a word is.
It's a good idea to separate calculations and i/o, so consider opening and closing the file in main() and pass in the file handle. It becomes easy, for instance, to use the stdin file handle instead if you don't want to use a physical file.
After the first do-while loop the condition EOF occurs.
do
{
c = fgetc(file);
if (c == '\n')
{
arr[0] ++;
}
}while (c != EOF);
So the following while loop has no effect.
You should use only one loop to count lines, words and characters.
Pay attention to that the variable c should be declared as having the type int
int c;
Also you need to exit the function if the file was not opened.

Reading, a set line range from a file in C

I' am writing a C program which allows the user to dynamically specify the File name from which the data is to be read. Next the user enters a lower bound and an upper bound. The data in the lines from between the bounds is to be printed.
For this the main function makes a call: readValues(cTargetName, iLower, iHiger);
The function readValues is supposed to work as follows:
Check if file exist, if yes. Open it with fopen
Read with feof and fgets line by line the whole file, and store each line in char string
With a for loop, print the correct range of lines from the string
I'm not sure why but the while loop doesn't seem to exit although I use the feof statement, which should terminate after the end of the File is reached.
The code looks as follows:
#include <stdio.h>
#include <stdlib.h>
void readValues(char cFileName[75], int n, int m)
{
//Variable declaration;
char strArray[50][50];
char *parser;
int i = 0;
FILE *Data;
if(Data = fopen(cFileName, "rt") == NULL){
printf("File could not be opened");
return 1; //Can you return 1 in a void function?
}
//Read the file line by line
while(feof(Data)==0){
fgets(strArray[i], 200, Data);
i++;
}
//Reading the specified lines
for(n; n<=m; n++){
printf("%s", strArray[n]);
}
}
int main()
{
char cTargetName[75] = {"C:/Users/User1/Desktop/C_Projects_1/TestData.txt"};
int iLower = 2;
int iHiger = 4;
readValues(cTargetName, iLower, iHiger);
return 0;
}
All help is appreciated. Thanks in advance!
Here is my solution to your question:
#include <stdio.h>
#include <stdlib.h>
#define MIN_LINE_LENGTH 64
typedef enum {
false, true
} bool;
int main() {
char filename[PATH_MAX] = {0};
printf("Enter filename:\n");
fgets(filename, PATH_MAX, stdin); // get filename from stdin
char *ptr = filename;
while (*ptr) { // remove trailing newline at the end of filename (fgets() includes newline)
if (*ptr == '\n') {
*ptr = 0;
}
++ptr;
}
printf("Enter starting line and end line, separated by a space:\n");
size_t startLine = 0;
size_t endLine = 0;
bool hasFirstNum = false;
bool hasSecondNum = false;
bool hasMiddleSpace = false;
bool hasLastSpace = false;
size_t numCount = 0;
int ch;
while ((ch = fgetc(stdin)) != EOF && ch != '\n') { // continually receive chars from stdin
if (ch != 32 && !(ch >= 48 && ch <= 57)) { // if not a space or number, raise error
fprintf(stderr, "Only numerical values (and spaces) can be entered.\n");
return 1;
}
if (ch == 32) {
if (hasFirstNum) {
hasMiddleSpace = true;
}
if (hasSecondNum) {
hasLastSpace = true;
}
continue;
}
else if (!hasFirstNum) {
++numCount;
hasFirstNum = true;
}
else if (!hasSecondNum && hasMiddleSpace) {
++numCount;
hasSecondNum = true;
}
else if (hasLastSpace) {
++numCount;
}
if (numCount == 1) {
startLine *= 10;
startLine += ch - 48; // '0' character in ASCII is 48
}
else if (numCount == 2){
endLine *= 10;
endLine += ch - 48;
}
else {
break;
}
}
FILE *fp = fopen(filename, "r");
if (fp == NULL) {
fprintf(stderr, "Error opening file.\n");
return 1;
}
char **lines = malloc(sizeof(char *));
char *line = malloc(MIN_LINE_LENGTH);
*lines = line;
int c;
size_t char_count = 0;
size_t line_count = 1;
while ((c = fgetc(fp)) != EOF) { // continually get chars from file stream
if (c == '\n') { // expand lines pointer if a newline is encountered
*(line + char_count) = 0;
++line_count;
lines = realloc(lines, line_count*sizeof(char *));
line = (*(lines + line_count - 1) = malloc(MIN_LINE_LENGTH));
char_count = 0;
continue;
}
if ((char_count + 1) % MIN_LINE_LENGTH == 0 && char_count != 0) { // expand line pointer if needed
line = realloc(line, char_count + MIN_LINE_LENGTH);
}
*(line + char_count) = c;
++char_count;
}
*(line + char_count) = 0; // to ensure the last line always ends with the null byte
if (startLine >= line_count) { // raise error if starting line specified is greater than num. of lines in doc.
fprintf(stderr, "Specified starting line is less than total lines in document.\n");
return 1;
}
if (endLine > line_count) { // adjust ending line if it is greater than number of lines in doc.
endLine = line_count;
}
if (startLine == 0) { // we will be using the starting index of 1 as the first line
startLine = 1;
}
char **linesPtr = lines + startLine - 1;
while (startLine++ <= endLine) { // print lines
printf("%s\n", *linesPtr++);
}
for (size_t i = 0; i < line_count; ++i) { // free all memory
free(*(lines + i));
}
free(lines);
return 0;
}
It is a little more convoluted, but because it uses dynamic memory allocation, it can handle lines of any length within a text file.
If there is anything unclear, please let me know and I would be happy to explain.
Hope this helps!!
several issues here,
first, you limited the length of lines to 200, not exactly what you might expect to get.
the fgets function returns lines up to specified length unless hit by newline character - this should be taken into account.
additionally, fgets returns NULL if you hit EOF - no real need to use feof.
second, you could save yourself a lot of pain and simply count the number of times you get a string, and for the times you are within the range just print it immediately. will save you a nice amount of overhead
like this:
#include <stdio.h>
#include <stdlib.h>
#define MAXLINE 200//or anything else you want
void readValues(char cFileName[75], int n, int m)
{
//Variable declaration;
char line[MAXLINE];
int i = 0;
FILE *Data;
if((Data = fopen(cFileName, "rt")) == NULL){
printf("File could not be opened");
return 1; //Can you return 1 in a void function?
}
//Read the file line by line and print within range of lines
while((line=fgets(line, MAXLINE,Data))!=NULL){//terminates upon EOF
if (++i>=n&&i<=m)
printf(""%s\n",line);
}
}

How to clear blank lines in files using c?

I am working on a management system project and want to clear the file before adding data to it. I am using this code as a reference. I have rewritten the code from the reference and instead of writing the data from the temporary file(tmp) back to the original(FILE_NAME), I have printed it out to the terminal.
When I compile and run the program, it prints all the content and a few more lines after the end of the file. After this it stops and doesn't finish execution. I have added to comments to help understand my thought process better.
#include<stdio.h>
#include<stdlib.h>
#include<ctype.h>
#define BUFFER_SIZE 1000
#define FILE_NAME "data.csv"
int main()
{
FILE* file;
char buffer[BUFFER_SIZE];
// Opening file
if(file = fopen(FILE_NAME, "r+"))
{
char c; // To get character from buffer
int i = 0; // Index for the buffer character
int isEmpty = 1; // If the line is empty
FILE* tmp;
if(tmp = tmpfile())
{
while(1)
{
buffer[i++] = c;
if(c != '\n') // Checking for blank lines
{
isEmpty = 0;
}
else
{
if(c == '\n' && isEmpty == 0) // Read a word; Print to tmp file
{
buffer[i] = '\0';
fprintf(tmp, "%s", buffer);
i = 0;
isEmpty = 1;
}
else if(c == '\n' && isEmpty == 1) // NOT SURE WHY THIS IS IMPORTANT
{
buffer[i] = '\0';
i = 0;
isEmpty = 1;
}
}
if(c == EOF)
{ break; }
while(1) // Loop to print contents of tmp file onto terminal
{
c = getc(tmp);
printf("c: %c", c);
if(c == EOF)
{ break; }
}
}
}
else
{
printf("Unable to open temporary file\n");
}
fclose(file);
}
else
{
printf("Unable to open file.");
}
getchar();
return 0;
}
UPDATE:
I've modified a few lines and have got it working.
I'd forgotten to assign c in the above program. Also #Barmar won't char c work just as well as int c. Characters can be integers as well right?
Why would large indentations lead to bugs? I find the blocks of code to be more differetiated.
#include<stdio.h>
#include<stdlib.h>
#include<ctype.h>
#define BUFFER_SIZE 1000
#define FILE_NAME "data.csv"
int main()
{
// Variable Declaration
FILE* file;
char buffer[BUFFER_SIZE];
// Opening file
if( file = fopen(FILE_NAME, "r+") )
{
char c; // Reading characters from the file
int i; // Index of the characters
int isEmpty = 1; // 1-> character is empty; 0-> character is not empty
FILE* tmp;
if( tmp = fopen("tmp.csv", "a+") )
{
char c; // Reading characters from files
int i = 0; // Index
int isEmpty = 1; // 1->previous word is empty; 0->previous word is not empty
while( (c = getc(file)) != EOF)
{
if( c != '\n' && c != ' ' && c != '\0' && c != ',')
{
isEmpty = 0;
buffer[i++] = c;
}
else
{
if( c == '\n' && isEmpty == 0 )
{
buffer[i] = '\0';
fprintf(tmp, "%s", buffer);
i = 0;
isEmpty = 1;
}
else if( c == '\n' && isEmpty == 1 )
{
buffer[i] = '\0';
i = 0;
}
}
}
fclose(tmp);
}
else
{
printf("Unable to open temporary file\n");
}
fclose(file);
}
else
{
printf("Unable to open file\n");
}
return 0;
}
Are there are ways to simplify the program and make it more compact or less error prone?

How to read and print end of data issuance.csv file?

I need to read data store in end of file and print it.
My input file has many numbers, and I have to read last number,
can any one help me??
int main()
{
FILE *fp;
fp = fopen("f:\\Issuance.csv", "a");
if (!fp)
{
printf("can not open file \n");
getchar();
exit(1);
}
int Size = 30;
char FileInfo[100];
fseek( fp , 0 , SEEK_END);
fread(FileInfo, 1, Size, fp);
printf("%d",FileInfo);
}
fcloseall();
}
You need to use the 2nd parameter of fseek().
fseek(fp, -Size, SEEK_END);
fread(FileInfo, 1, Size, fp);
FileInfo[Size] = '\0'; // NULL terminate FileInfo; or declare as char FileInfo[100] = {0};
printf("%s", FileInfo);
To read the last number in a text file (which may have additional junk after it), starting from the beginning, attempt to read a number. If successful, save it, else toss 1 char. Continue until the end of the file.
// Read last number
int ReadLastNumber(FILE *inf, int default_value) {
int last = default_value;
int num;
int cnt;
rewind(inf);
while ((cnt = fscanf(inf,"%d", &num)) != EOF) {
if (cnt == 1) {
last = num;
} else {
fgetc(inf); // toss non-numeric char
}
}
return last;
}
A more sane solution would fseek() to the end, search backwards for digits. Once some digits are found, continue backwards looking for digits, +or -. Something like the following untested code.
#include <ctype.h>
#include <stdbool.h>
#include <stdlib.h>
// Read last number
int ReadLastNumber2(FILE *inf, int default_value) {
int last = 0;
int place = 1;
bool digit_found = false;
long offset = -1;
while (fseek(inf, offset, SEEK_CUR) == 0) {
int ch = fgetc(inf);
if (ch == EOF) // Likely I/O error
return default_value;
if (isdigit(ch)) {
digit_found = true;
last += (ch - '0')*place;
place *= 10;
offset = -2;
} else if (ch == '-') {
return -last;
} else if (digit_found) {
return last;
}
}
return default_value;
}
Not protected against int overflow.

How to count blank lines from file in C?

So what I'm trying to do is to count blank lines, which means not only just containing '\n'but space and tab symbols as well. Any help is appreciated! :)
char line[300];
int emptyline = 0;
FILE *fp;
fp = fopen("test.txt", "r");
if(fp == NULL)
{
perror("Error while opening the file. \n");
system("pause");
}
else
{
while (fgets(line, sizeof line, fp))
{
int i = 0;
if (line[i] != '\n' && line[i] != '\t' && line[i] != ' ')
{
i++;
}
emptyline++;
}
printf("\n The number of empty lines is: %d\n", emptyline);
}
fclose(fp);
You should try and get your code right when posting on SO. You are incrementing both i and emptyline but the use el in your call to printf(). And then I don't know what that is supposed to be in your code where it has }ine. Please, at least make an effort.
For starters, you are incrementing emptyline for every line because it is outside of your if statement.
Second, you need to test the entire line to see if it contains any character that is not a whitespace character. Only if that is true should you increment emptyline.
int IsEmptyLine(char *line)
{
while (*line)
{
if (!isspace(*line++))
return 0;
}
return 1;
}
Before getting into the line loop increment the emptyLine counter and if an non whitespace character is encountred decrement the emptyLine counter then break the loop.
#include <stdio.h>
#include <string.h>
int getEmptyLines(const char *fileName)
{
char line[300];
int emptyLine = 0;
FILE *fp = fopen("text.txt", "r");
if (fp == NULL) {
printf("Error: Could not open specified file!\n");
return -1;
}
else {
while(fgets(line, 300, fp)) {
int i = 0;
int len = strlen(line);
emptyLine++;
for (i = 0; i < len; i++) {
if (line[i] != '\n' && line[i] != '\t' && line[i] != ' ') {
emptyLine--;
break;
}
}
}
return emptyLine;
}
}
int main(void)
{
const char fileName[] = "text.txt";
int emptyLines = getEmptyLines(fileName);
if (emptyLines >= 0) {
printf("The number of empty lines is %d", emptyLines);
}
return 0;
}
You are incrementing emptyline on every iteration, so you should wrap it in an else block.
Let's think of this problem logically, and let's use functions to make it clear what is going on.
First, we want to detect lines that only consist of whitespace. So let's create a function to do that.
bool StringIsOnlyWhitespace(const char * line) {
int i;
for (i=0; line[i] != '\0'; ++i)
if (!isspace(line[i]))
return false;
return true;
}
Now that we have a test function, let's build a loop around it.
while (fgets(line, sizeof line, fp)) {
if (StringIsOnlyWhitespace(line))
emptyline++;
}
printf("\n The number of empty lines is: %d\n", emptyline);
Note that fgets() will not return a full line (just part of it) on lines that have at least sizeof(line) characters.

Resources