Need to match integer type but it must be only separated integer. Example:
INTEGER (-?[0-9]+)
NOTENDLINE [^$]
%%
{INTEGER}/{NOTENDLINE} {}
%%
If I enter string like "23test", it must be wrong and no integer matched. But my solution don't working as needed. I don't know, what I need in NOTENDLINE.
Would this work for you? It relies on the fact that the lexer will find the longest matched rule, but if two are equal, the first rule will be used.
%option noyywrap
DIGIT [0-9]
OTHER [a-z0-9]*
%%
{DIGIT}+ printf( "Integer: %s (%d)\n", yytext, atoi( yytext ) );
{OTHER} printf( "Other: %s\n", yytext );
[ \t\n]+ /* eat up whitespace */
%%
int main( int argc, char **argv )
{
++argv, --argc; /* skip over program name */
if ( argc > 0 )
yyin = fopen( argv[0], "r" );
else
yyin = stdin;
yylex();
}
Sample Input (file):
test
test123
123
123test
Sample Ouput:
Other: test
Other: test123
Integer: 123 (123)
Other: 123test
If you want to match an integer but only if it is followed by whitespace, do so directly:
-?[[:digit:]]+/[[:space:]]
That will fail if the integer is at the very end of the file without a newline, but text files are not supposed to end with anything other than a newline character. You can, however, do the following:
-?[[:digit:]]+/[[:space:]] { /* Handle an integer */ }
-?[[:digit:]]+/. { /* Handle the error */ }
-?[[:digit:]]+ { /* Handle an integer; this one must be at EOF */ }
Related
I have tried to solve this question "Write a lex program for the pattern that starts with vowel, ends with consonant and might have digits too."
Here is my code:
%{
#include<stdio.h>
#include<string.h>
int cno=0, wno=0, lno=o;
%}
character [a-zA-z]
digit [0-9]
word({character}|{digit})+
line\n
%%
{line}{cno++;lno++;}
{line}{wno++; cno+=strlen(yytext);}{cno++;}
%%
int main(void)
{
yylex();
print("Count alphanumeric pattern: %d;", cno);
print("Length of string: %d;", wno);
print("Line numbers: %d\n", lno);
return 0;
}
Here is the output:
line 23: unrecognized rule
line 23: fatal parse error
I think the following code will solve your problem.
%{
int valid_patterns = 0, invalid_patterns =0;
%}
PATTERN ([aeiouAEIOU][A-Za-z0-9]*[b-df-hj-np-tv-zB-DF-HJ-NP-TV-Z])*
%%
{PATTERN} {printf("\n\t Pattern Matched: %s", yytext); valid_patterns++;}
[A-Za-z0-9]+ {invalid_patterns++;}
"\n" {
printf("\n\n\t Total Matched Patterns : %d", valid_patterns);
printf("\n\t Total Unmatched Patterns: %d\n", invalid_patterns);
valid_patterns = 0; invalid_patterns = 0;
}
%%
/*** User code section***/
int yywrap(){}
int main(int argc, char **argv[])
{
printf("\n Enter your inputs: \n\n");
yylex();
return 0;
}
Explanation of the first rule for PATTERN as per your questions requirements:
[aeiouAEIOU] make sure a pattern starts with a vowel.
[A-Za-z0-9]* indicates that any alphanumeric character can occur in middle.
[b-df-hj-np-tv-zB-DF-HJ-NP-TV-Z] make sure a pattern ends with a consonant.
(...)* indicates there might be 0 or more occurrence of desire pattern.
The second rule [A-Za-z0-9]+ catches any other input that doesn't match the requirements. And the final rule "\n"takes action when you input a new line, it prints information about your inputs.
An I/O example---
Input: Hello amazing people around the world
Output:
Pattern Matched: amazing
Pattern Matched: around
Total Matched Patterns : 2
Total Unmatched Patterns: 4
I am new in C and writing a code to help my data analysis. Part of it opens predetermined files.
This piece of code is giving me problems and I cannot understand why.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define MAXLOGGERS 26
// Declare the input files
char inputfile[];
char inputfile_hum[MAXLOGGERS][8];
// Declare the output files
char newfile[];
char newfile_hum[MAXLOGGERS][8];
int main()
{
int n = 2;
while (n > MAXLOGGERS)
{
printf("n error, n must be < %d: ", MAXLOGGERS);
scanf("%d", &n);
}
// Initialize the input and output file names
strncpy(inputfile_hum[1], "Ahum.csv", 8);
strncpy(inputfile_hum[2], "Bhum.csv", 8);
strncpy(newfile_hum[1], "Ahum.txt", 8);
strncpy(newfile_hum[2], "Bhum.txt", 8);
for (int i = 1; i < n + 1; i++)
{
strncpy(inputfile, inputfile_hum[i], 8);
FILE* file1 = fopen(inputfile, "r");
// Safety check
while (file1 == NULL)
{
printf("\nError: %s == NULL\n", inputfile);
printf("\nPress enter to exit:");
getchar();
return 0;
}
strncpy(newfile, newfile_hum[i], 8);
FILE* file2 = fopen(newfile, "w");
// Safety check
if (file2 == NULL)
{
printf("Error: file2 == NULL\n");
getchar();
return 0;
}
for (int c = fgetc(file1); c != EOF; c = fgetc(file1))
{
fprintf(file2, "%c", c);
}
fclose(file1);
fclose(file2);
}
// system("Ahum.txt");
// system("Bhum.txt");
}
This code produces two files but instead of the names:
Ahum.txt
Bhum.txt
the files are named:
Ahum.txtv
Bhum.txtv
The reason I am using strncpy in the for loop is because n will actually be inputted by the user later.
I see at least three problems here.
The first problem is that your character array is too small for your strings.
"ahum.txt", etc. will need to take nine characters. Eight for the actual text plus one more for the null terminating character.
The second problem is that you have declared the character arrays "newfile" and "inputfile" as empty arrays. These also need to be a number able to contain the strings (at least 9).
You're lucky to have not had a crash from overwriting memory out the program space.
The third and final problem is your use of strcpy().
strncpy(dest, src, n) will copy n characters from src to dest, but it won't copy final null terminator character if n is equal or less than size of the src string.
From strncpy() manpage: https://linux.die.net/man/3/strncpy
The strncpy() function ... at most n bytes of src are copied.
Warning: If there is no null byte among the first n bytes of src,
the string placed in dest will not be null-terminated.
Normally what you would want to do is have "n" be the size of the destination buffer minus 1 to allow for the null character.
For example:
strncpy(dest, src, sizeof(dest) - 1); // assuming dest is char array
There are a couple of problems with your code.
inputfile_hum, newfile_hum, need to be to be one char bigger for the trailing '\0' on strings.
char inputfile_hum[MAXLOGGERS][9];
...
char newfile_hum[MAXLOGGERS][9];
strncpy expects the first argument to be a char * region big enough to hold the expected results, so inputfile[] and outputfile[] need to be declared:
char inputfile[9];
char outputfile[9];
I am very new to lex. I am trying to develop a parser to search a count of specific word in an given input file...
My code is
%{
#include<stdio.h>
#include<stdlib.h>
#include<string.h>
int lnum = 1, fresult = 0, cc=0, wc=0, lc=0, bc=0, sc=0, nc=0, tc=0, result;
char temp[20], str[20], fname[20];
FILE *fp;
#undef yywrap
%}
digit[0-9]+
word [a-zA-Z]+
eol [\n]
blank [ ]
tab [\t]
result [word]
%%
{result} {
if((strstr(temp, str)) != 0)
{
printf(" A match found on line: %d\n", lnum);
fresult++;
wc++;
cc+=yyleng;
}
lnum++;
if(fresult == 0)
{
printf(" Match not found\n");
}
}
{digit} {nc++;}
{word} {wc++; cc+=yyleng;}
{tab} {tc++;}
{blank} {bc++;}
{eol} {lc++;}
. sc++;
%%
int main(int argc, char *argv[])
{
strcpy(fname,argv[1]);
strcpy(str,argv[2]);
fp=fopen(fname,"r+");
yyin=fp;
yylex();
printf(" Total count of the word is :%d\n", fresult);
printf(" Character Count = %d\n", cc);
printf(" Number Count = %d\n", nc);
printf(" Word Count = %d\n", wc);
printf(" Line Count = %d\n", lc);
printf(" Special Character Count = %d\n", sc);
printf(" Blank Count = %d\n", bc);
printf(" Tab Count = %d\n", tc);
return(0);
}
int yywrap()
{
return -1;
}
The word count and others are working perfectly.... But the word search is taking the input but not given the specific count...... How can I improve the code?
Should I need to add anything?
Thanks in Advance...... :)
I have made some changes to your code to help you in the right direction. First, I created a variable to keep track of whether a match is found or not.
Secondly, I am not using strstr() anymore and instead I am using strcmp() because you want to match a word to a word not a word within a sentence and we do not need a pointer returned. strcmp() is nice because we just get an integer.
I see what you were trying to do with result [word] however, as you found out, this will not work. This section of the Flex file is known as the rules section. Here you use the regular expressions that you defined in the above section (definitions) to tell Flex what to do when a rule is matched.
As you can see, I have deleted all occurrences of result[word] - as this will not work. In the rules section, I also deleted the result definition because we no longer have a rule to match it. However, I keep the code for the result definitions and simply apply it to the word definition.
The last major change is adding the <<EOF>> rule which is a special rule that tells Flex what to do when it has encountered the end of the file. In our case, if the match variable is not 1, then we have not found a match and we would like to print this to the screen. We also need to call yyterminate() (definition at the bottom of the page) to stop the lexical analyzer.
Below is the updated code. I hope that helps!
%{
#include<stdio.h>
#include<stdlib.h>
#include<string.h>
int lnum = 1, fresult = 0, cc=0, wc=0, lc=0, bc=0, sc=0, nc=0, tc=0, result;
char temp[20], str[20], fname[20];
FILE *fp;
int match = 0;//For keeping track of matches
#undef yywrap
%}
/*Rules*/
digit [0-9]+
word [a-zA-Z]+
eol [\n]
blank [ ]
tab [\t]
/*Definitions*/
%%
{digit} {
nc++;
}
{tab} {
tc++;
}
{blank} {
bc++;
}
{eol} {
lc++;
}
{word} {
if((strcmp(yytext, str)) == 0)//We found a match
{
printf("\n A match found on line: %d\n", lnum);
fresult++;
wc++;
cc+=yyleng;
match = 1;//We have a match
}
else //We found a word, but it was not a match
{
wc++;
}
}
. {
sc++;
}
<<EOF>> {
if(!match)
{
printf(" Match not found\n");
}
yyterminate();
}
%%
int main(int argc, char *argv[])
{
strcpy(fname,argv[1]);
strcpy(str,argv[2]);
fp = fopen(fname,"r+");
yyin = fp;
yylex();
printf("\n\n Total count of the word is :%d\n", fresult);
printf(" Character Count = %d\n", cc);
printf(" Number Count = %d\n", nc);
printf(" Word Count = %d\n", wc);
printf(" Line Count = %d\n", lc);
printf(" Special Character Count = %d\n", sc);
printf(" Blank Count = %d\n", bc);
printf(" Tab Count = %d\n", tc);
fclose(fp);
return(0);
}
int yywrap()
{
return 1;
}
{result} {
if((strstr(temp, str)) != 0)
result [word]
Result is a regex for the characters 'w', 'o', 'r', 'd', which is not what you want. You probably want to match on {word}. In addition, temp will always be null - I think you want to use yytext instead.
I've checked other similar posts but I think I just need a second set of eyes. This file is for the lex Unix utility.
I created a makefile and this is the error I receive:
gcc -g -c lex.yy.c
cxref.l:57: error: expected ‘;’, ‘,’ or ‘)’ before numeric constant
make: *** [lex.yy.o] Error 1
Line 57 is just inside the void inserID() function near the top.
Here is the code:
%{
#include <stdio.h>
#include <string.h>
char identifier[1000][82];
char linesFound[100][100];
void insertId(char*, int);
int i = 0;
int lineNum = 1;
%}
%x comment
%s str
%%
"/*" BEGIN(comment);
<comment>[^*\n]* /* eat anything that's not a '*' */
<comment>"*"+[^*/\n]* /* eat up '*'s not followed by '/'s */
<comment>\n ++lineNum;
<comment>"*"+"/" BEGIN(INITIAL);
"\n" ++lineNum;
auto ;
break ;
case ;
char ;
continue ;
default ;
do ;
double ;
else ;
extern ;
float ;
for ;
goto ;
if ;
int ;
long ;
register ;
return ;
short ;
sizeof ;
static ;
struct ;
switch ;
typedef ;
union ;
unsigned ;
void ;
while ;
[*]?[a-zA-Z][a-zA-Z0-9_]* insertId(yytext, lineNum);
[^a-zA-Z0-9_]+ ;
[0-9]+ ;
%%
void insertId(char* str, int nLine)
{
char num[2];
sprintf ( num, "%d", nLine);
int iter;
for(iter = 0; iter <= i; iter++)
{
if ( strcmp(identifier[iter], str) == 0 )
{
strcat( linesFound[iter], ", " );
strcat( linesFound[iter], num );
return;
}
}
strcpy( identifier[i], str );
strcat( identifier[i], ": " );
strcpy( linesFound[i], num );
i++;
}
Your problem is:
%s str
There is a reason that it's normal to write condition names in CAPS: it makes them look like macros, which is exactly what they are.
So
void insertId(char* str, int nLine)
get macro expanded to something like:
void insertId(char* 2, int nLine)
and the compiler complains that 2 is not really expected at that point in the declaration.
I have always wondered how people update a previous line in a command line. a great example of this is when using the wget command in linux. It creates an ASCII loading bar of sorts that looks like this:
[======> ] 37%
and of course the loading bar moves and the percent changes, But it doesn't make a new line. I cannot figure out how to do this. Can someone point me in the right direction?
One way to do this is to repeatedly update the line of text with the current progress. For example:
def status(percent):
sys.stdout.write("%3d%%\r" % percent)
sys.stdout.flush()
Note that I used sys.stdout.write instead of print (this is Python) because print automatically prints "\r\n" (carriage-return new-line) at the end of each line. I just want the carriage-return which returns the cursor to the start of the line. Also, the flush() is necessary because by default, sys.stdout only flushes its output after a newline (or after its buffer gets full).
There are two ways I know of to do this:
Use the backspace escape character ('\b') to erase your line
Use the curses package, if your programming language of choice has bindings for it.
And a Google revealed ANSI Escape Codes, which appear to be a good way. For reference, here is a function in C++ to do this:
void DrawProgressBar(int len, double percent) {
cout << "\x1B[2K"; // Erase the entire current line.
cout << "\x1B[0E"; // Move to the beginning of the current line.
string progress;
for (int i = 0; i < len; ++i) {
if (i < static_cast<int>(len * percent)) {
progress += "=";
} else {
progress += " ";
}
}
cout << "[" << progress << "] " << (static_cast<int>(100 * percent)) << "%";
flush(cout); // Required.
}
The secret is to print only \r instead of \n or \r\n at the and of the line.
\r is called carriage return and it moves the cursor at the start of the line
\n is called line feed and it moves the cursor on the next line
In the console. If you only use \r you overwrite the previously written line.
So first write a line like the following:
[ ]
then add a sign for each tick
\r[= ]
\r[== ]
...
\r[==========]
and so on.
You can use 10 chars, each representing a 10%.
Also, if you want to display a message when finished, don't forget to also add enough white chars so that you overwrite the previously written equal signs like so:
\r[done ]
below is my answer,use the windows APIConsoles(Windows), coding of C.
/*
* file: ProgressBarConsole.cpp
* description: a console progress bar Demo
* author: lijian <hustlijian#gmail.com>
* version: 1.0
* date: 2012-12-06
*/
#include <stdio.h>
#include <windows.h>
HANDLE hOut;
CONSOLE_SCREEN_BUFFER_INFO bInfo;
char charProgress[80] =
{"================================================================"};
char spaceProgress = ' ';
/*
* show a progress in the [row] line
* row start from 0 to the end
*/
int ProgressBar(char *task, int row, int progress)
{
char str[100];
int len, barLen,progressLen;
COORD crStart, crCurr;
GetConsoleScreenBufferInfo(hOut, &bInfo);
crCurr = bInfo.dwCursorPosition; //the old position
len = bInfo.dwMaximumWindowSize.X;
barLen = len - 17;//minus the extra char
progressLen = (int)((progress/100.0)*barLen);
crStart.X = 0;
crStart.Y = row;
sprintf(str,"%-10s[%-.*s>%*c]%3d%%", task,progressLen,charProgress, barLen-progressLen,spaceProgress,50);
#if 0 //use stdand libary
SetConsoleCursorPosition(hOut, crStart);
printf("%s\n", str);
#else
WriteConsoleOutputCharacter(hOut, str, len,crStart,NULL);
#endif
SetConsoleCursorPosition(hOut, crCurr);
return 0;
}
int main(int argc, char* argv[])
{
int i;
hOut = GetStdHandle(STD_OUTPUT_HANDLE);
GetConsoleScreenBufferInfo(hOut, &bInfo);
for (i=0;i<100;i++)
{
ProgressBar("test", 0, i);
Sleep(50);
}
return 0;
}
PowerShell has a Write-Progress cmdlet that creates an in-console progress bar that you can update and modify as your script runs.
Here is the answer for your question... (python)
def disp_status(timelapse, timeout):
if timelapse and timeout:
percent = 100 * (float(timelapse)/float(timeout))
sys.stdout.write("progress : ["+"*"*int(percent)+" "*(100-int(percent-1))+"]"+str(percent)+" %")
sys.stdout.flush()
stdout.write("\r \r")
As a follow up to Greg's answer, here is an extended version of his function that allows you to display multi-line messages; just pass in a list or tuple of the strings you want to display/refresh.
def status(msgs):
assert isinstance(msgs, (list, tuple))
sys.stdout.write(''.join(msg + '\n' for msg in msgs[:-1]) + msgs[-1] + ('\x1b[A' * (len(msgs) - 1)) + '\r')
sys.stdout.flush()
Note: I have only tested this using a linux terminal, so your mileage may vary on Windows-based systems.
If your using a scripting language you could use the "tput cup" command to get this done...
P.S. This is a Linux/Unix thing only as far as I know...