Last active
December 16, 2015 04:39
-
-
Save tacke758/5379180 to your computer and use it in GitHub Desktop.
C program that removes escaped line breaks, which are surrounded by double quotes from CSV file and change it into unix style file format (using line feed (LF) as line break).
This program implements an automaton that accepts CSV, so it's short and run fast.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <unistd.h> | |
#include <stdio.h> | |
#include <stdlib.h> | |
/* Size of atomic reads. */ | |
#define BUFFER_SIZE (16 * 1024) | |
int state = 0; | |
void exit_with_error(int state, char c) { | |
fprintf(stderr, "error when %d (%x)", state, c); | |
exit(-1); | |
} | |
/* | |
Qs={0}, Qf={7} | |
0: (init) | |
1: " | |
2: (any character) | |
3: " | |
4: " | |
5: , | |
6: EOF | |
7: CR | |
8: LF | |
0 1 | |
1 2 3 | |
2 2 3 | |
3 4 5 6 7 8 | |
4 2 3 | |
5 1 | |
7 1 6 8 | |
8 1 6 | |
*/ | |
int main() { | |
char buf[BUFFER_SIZE + 1]; | |
size_t bytes_read; | |
while (0 < (bytes_read = read(0, buf, BUFFER_SIZE))) { | |
int i; | |
for (i = 0; i < bytes_read; i ++) { | |
char next = buf[i]; | |
switch(state) { | |
case 0: | |
if (next == '"') { | |
state = 1; | |
putchar(next); | |
} | |
else { | |
exit_with_error(state, next); | |
} | |
break; | |
case 1: | |
/* Fall through */ | |
case 2: | |
/* Fall through */ | |
case 4: | |
if (next == '"') { | |
state = 3; | |
putchar(next); | |
} | |
else { | |
state = 2; | |
// CR/LFは空白を出力 | |
if (next == 0x0D || next == 0x0A) { | |
putchar(' '); | |
} | |
else { | |
putchar(next); | |
} | |
} | |
break; | |
case 3: | |
if (next == '"') { | |
state = 4; | |
putchar(next); | |
} | |
else if (next == ',') { | |
state = 5; | |
putchar(next); | |
} | |
else if (next == EOF) { | |
state = 6; | |
exit(0); | |
} | |
else if (next == 0x0D) { | |
// CRを出力しない | |
state = 7; | |
//putchar(next); | |
} | |
else if (next == 0x0A) { | |
state = 8; | |
putchar(next); | |
} | |
break; | |
case 5: | |
if (next == '"') { | |
state = 1; | |
putchar(next); | |
} | |
else { | |
exit_with_error(state, next); | |
} | |
break; | |
case 7: | |
if (next == EOF) { | |
state = 6; | |
exit(0); | |
} | |
else if (next == '"') { | |
state = 1; | |
putchar(next); | |
} | |
else if (next == 0x0A) { | |
state = 8; | |
putchar(next); | |
} | |
else { | |
exit_with_error(state, next); | |
} | |
break; | |
case 8: | |
if (next == EOF) { | |
state = 6; | |
exit(0); | |
} | |
else if (next == '"') { | |
state = 1; | |
putchar(next); | |
} | |
else { | |
exit_with_error(state, next); | |
} | |
break; | |
default: | |
exit_with_error(state, next); | |
break; | |
} | |
} | |
} | |
//printf("finish!\n"); | |
exit(0); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment