POSIX specifies that -d '\0' sets the delimiter to an empty string.
---
libutf/utf.c | 12 ++++++++++++
libutf/utftorunestr.c | 12 ++++++++++++
libutil/unescape.c | 3 ++-
paste.c | 27 +++++++++++++++------------
utf.h | 4 +++-
5 files changed, 44 insertions(+), 14 deletions(-)
diff --git a/libutf/utf.c b/libutf/utf.c
index 897c5ef..cf46e57 100644
--- a/libutf/utf.c
+++ b/libutf/utf.c
@@ -62,6 +62,18 @@ utfnlen(const char *s, size_t len)
return i;
}
+size_t
+utfmemlen(const char *s, size_t len)
+{
+ const char *p = s;
+ size_t i;
+ Rune r;
+
+ for(i = 0; p - s < len; i++)
+ p += chartorune(&r, p);
+ return i;
+}
+
char *
utfrune(const char *s, Rune r)
{
diff --git a/libutf/utftorunestr.c b/libutf/utftorunestr.c
index 005fe8a..5da9d5f 100644
--- a/libutf/utftorunestr.c
+++ b/libutf/utftorunestr.c
@@ -11,3 +11,15 @@ utftorunestr(const char *str, Rune *r)
return i;
}
+
+int
+utfntorunestr(const char *str, size_t len, Rune *r)
+{
+ int i, n;
+ const char *p = str;
+
+ for(i = 0; (n = chartorune(&r[i], p)) && p - str < len; i++)
+ p += n;
+
+ return i;
+}
diff --git a/libutil/unescape.c b/libutil/unescape.c
index d8ed2a2..deca948 100644
--- a/libutil/unescape.c
+++ b/libutil/unescape.c
@@ -21,7 +21,8 @@ unescape(char *s)
['n'] = '\n',
['r'] = '\r',
['t'] = '\t',
- ['v'] = '\v'
+ ['v'] = '\v',
+ ['0'] = '\0'
};
size_t m, q;
char *r, *w;
diff --git a/paste.c b/paste.c
index b0ac761..051ca72 100644
--- a/paste.c
+++ b/paste.c
@@ -53,7 +53,8 @@ nextline:
for (; efgetrune(&c, dsc[i].fp, dsc[i].name) ;) {
for (m = last + 1; m < i; m++)
- efputrune(&(delim[m % delimlen]), stdout,
"<stdout>");
+ if (delim[m % delimlen] != '\0')
+ efputrune(&(delim[m % delimlen]),
stdout, "<stdout>");
last = i;
if (c == '\n') {
if (i != fdescrlen - 1)
@@ -68,7 +69,8 @@ nextline:
if (i == fdescrlen - 1)
putchar('\n');
else
- efputrune(&d, stdout, "<stdout>");
+ if (d != '\0')
+ efputrune(&d, stdout, "<stdout>");
last++;
}
}
@@ -86,18 +88,18 @@ int
main(int argc, char *argv[])
{
struct fdescr *dsc;
- Rune *delim;
- size_t delimlen, i;
+ Rune *delim_rune = NULL;
+ size_t delim_runelen, i, delim_bytelen = 1;
int seq = 0, ret = 0;
- char *adelim = "\t";
+ char *delim = "\t";
ARGBEGIN {
case 's':
seq = 1;
break;
case 'd':
- adelim = EARGF(usage());
- unescape(adelim);
+ delim = EARGF(usage());
+ delim_bytelen = unescape(delim);
break;
default:
usage();
@@ -107,10 +109,11 @@ main(int argc, char *argv[])
usage();
/* populate delimiters */
- /* TODO: fix libutf to accept sizes */
- delim = ereallocarray(NULL, utflen(adelim) + 1, sizeof(*delim));
- if (!(delimlen = utftorunestr(adelim, delim)))
+ delim_rune = ereallocarray(NULL,
+ utfmemlen(delim, delim_bytelen) + 1, sizeof(*delim_rune));
+ if (!(delim_runelen = utfntorunestr(delim, delim_bytelen, delim_rune)))
{
usage();
+ }
/* populate file list */
dsc = ereallocarray(NULL, argc, sizeof(*dsc));
@@ -126,9 +129,9 @@ main(int argc, char *argv[])
}
if (seq) {
- sequential(dsc, argc, delim, delimlen);
+ sequential(dsc, argc, delim_rune, delim_runelen);
} else {
- parallel(dsc, argc, delim, delimlen);
+ parallel(dsc, argc, delim_rune, delim_runelen);
}
for (i = 0; i < argc; i++)
diff --git a/utf.h b/utf.h
index 23a9887..fa04f6b 100644
--- a/utf.h
+++ b/utf.h
@@ -38,6 +38,7 @@ int fullrune(const char *, size_t);
char *utfecpy(char *, char *, const char *);
size_t utflen(const char *);
size_t utfnlen(const char *, size_t);
+size_t utfmemlen(const char *, size_t);
char *utfrune(const char *, Rune);
char *utfrrune(const char *, Rune);
char *utfutf(const char *, const char *);
@@ -59,7 +60,8 @@ int isxdigitrune(Rune);
Rune tolowerrune(Rune);
Rune toupperrune(Rune);
-int utftorunestr(const char*, Rune *);
+int utftorunestr(const char *, Rune *);
+int utfntorunestr(const char *, size_t, Rune *);
int fgetrune(Rune *, FILE *);
int efgetrune(Rune *, FILE *, const char *);
--
2.25.1
