GopherProxy

	csvtofsv.c - csvtofsv - Convert CSV to FSV (`fs' (0x1c) as FS and `rs' (0x1e) a…
	hg clone https://bitbucket.org/iamleot/csvtofsv
	Log
	Files
	Refs
	README
	---
	csvtofsv.c
	---
	1 /*-
	2 * Copyright (c) 2019 Leonardo Taccari
	3 * All rights reserved.
	4 *
	5 * Redistribution and use in source and binary forms, with or without
	6 * modification, are permitted provided that the following conditions
	7 * are met:
	8 *
	9 * 1. Redistributions of source code must retain the above copyright
	10 * notice, this list of conditions and the following disclaimer.
	11 * 2. Redistributions in binary form must reproduce the above copyright
	12 * notice, this list of conditions and the following disclaimer in the
	13 * documentation and/or other materials provided with the distributio…
	14 *
	15 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
	16 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIM…
	17 * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTI…
	18 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CON…
	19 * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
	20 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
	21 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSIN…
	22 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER …
	23 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWIS…
	24 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED O…
	25 * POSSIBILITY OF SUCH DAMAGE.
	26 */
	27
	28
	29 #include <stdbool.h>
	30 #include <stdio.h>
	31
	32
	33 #define FS 034
	34 #define RS 036
	35
	36
	37 /*
	38 * Convert a CSV from stdin to FSV with `fs' ASCII char (0x1c) as field
	39 * separator and `rs' ASCII char (0x1e) as record separator.
	40 */
	41 int
	42 main(int argc, char *argv[])
	43 {
	44 int c, nc, pc;
	45 bool first, quoted;
	46
	47 first = true;
	48 quoted = false;
	49 pc = '\0';
	50 while ((c = getchar()) != EOF) {
	51 pc = c;
	52 switch (c) {
	53 case '"':
	54 if (first) {
	55 quoted = true;
	56 first = false;
	57 } else if (!quoted) {
	58 /*
	59 * RFC 4180 says: `Fields containing [..…
	60 * double quotes [...] should be enclose…
	61 * double-quotes.'. This violates that …
	62 * printing alone `"' as-is.
	63 */
	64 putchar(c);
	65 } else if ((nc = getchar()) != EOF) {
	66 pc = nc;
	67 if (nc == '"') {
	68 putchar('"');
	69 } else if (nc == ',') {
	70 putchar(FS);
	71 first = true;
	72 quoted = false;
	73 } else if ((nc == '\n') \|\|
	74 ((nc == '\r') &&
	75 ((nc = getchar()) == '\n')…
	76 pc = nc;
	77 putchar(RS);
	78 first = true;
	79 quoted = false;
	80 } else {
	81 ungetc(nc, stdin);
	82 }
	83 }
	84 break;
	85 case ',':
	86 if (quoted) {
	87 putchar(',');
	88 } else {
	89 putchar(FS);
	90 first = true;
	91 }
	92 break;
	93 case '\n':
	94 if (quoted) {
	95 putchar('\n');
	96 } else {
	97 putchar(RS);
	98 first = true;
	99 }
	100 break;
	101 case '\r':
	102 /* ignore */
	103 break;
	104 case FS:
	105 fprintf(stderr, "FS character found, stopping.\n…
	106 return 1;
	107 break; /* NOTREACHED */
	108 case RS:
	109 fprintf(stderr, "RS character found, stopping.\n…
	110 return 1;
	111 break; /* NOTREACHED */
	112 default:
	113 putchar(c);
	114 break;
	115 }
	116 }
	117
	118 if (pc != '\0' && pc != '\n')
	119 putchar(RS);
	120
	121 return 0;
	122 }