sort: Fix line comparison when col buffer contains data from longer line
I'm not sure if there are other implications of this or not, but
the issue is that columns() uses len to store the allocated buffer
size, but linecmp() compares up to len bytes. If those trailing
bytes do not match, the line is considered not matching, even though
the relevant parts of the buffer do match.
To resolve this, also keep track of column capacity. Additionally,
since there is no reason to keep the existing data when resizing,
just use free and emalloc rather than erealloc.
The simplest case I could reduce it to is this:
if [ "$(printf '%s\n' a a xxb xxc | ./sort -u)" = "$(printf '%s\n' a xxb xxc)" ] ; then
echo pass
else
echo fail
fi
diff --git a/sort.c b/sort.c
index 90ee911..623b81e 100644
--- a/sort.c
+++ b/sort.c
@@ -18,6 +18,11 @@
TAILQ_ENTRY(keydef) entry;
};
+struct column {
+ struct line line;
+ size_t cap;
+};
+
enum {
MOD_N = 1 << 0,
MOD_STARTB = 1 << 1,
@@ -33,7 +38,7 @@
static int Cflag = 0, cflag = 0, uflag = 0;
static char *fieldsep = NULL;
static size_t fieldseplen = 0;
-static struct line col1, col2;
+static struct column col1, col2;
static void
skipblank(struct line *a)
@@ -76,12 +81,12 @@
}
}
-static size_t
-columns(struct line *line, const struct keydef *kd, struct line *col)
+static void
+columns(struct line *line, const struct keydef *kd, struct column *col)
{
Rune r;
struct line start, end;
- size_t len, utflen, rlen;
+ size_t utflen, rlen;
int i;
start.data = line->data;
@@ -118,15 +123,13 @@
end.data += end.len - 1;
end.len = 1;
}
- len = MAX(0, end.data - start.data);
- if (!(col->data) || col->len < len)
- col->data = erealloc(col->data, len + 1);
- memcpy(col->data, start.data, len);
- col->data[len] = '\0';
- if (col->len < len)
- col->len = len;
-
- return len;
+ col->line.len = MAX(0, end.data - start.data);
+ if (!(col->line.data) || col->cap < col->line.len + 1) {
+ free(col->line.data);
+ col->line.data = emalloc(col->line.len + 1);
+ }
+ memcpy(col->line.data, start.data, col->line.len);
+ col->line.data[col->line.len] = '\0';
}
static int
@@ -187,13 +190,13 @@
TAILQ_LAST(&kdhead, kdhead) != TAILQ_FIRST(&kdhead)) {
res = 0;
} else if (kd->flags & MOD_N) {
- x = strtold(col1.data, NULL);
- y = strtold(col2.data, NULL);
+ x = strtold(col1.line.data, NULL);
+ y = strtold(col2.line.data, NULL);
res = (x < y) ? -1 : (x > y);
} else if (kd->flags & (MOD_D | MOD_F | MOD_I)) {
- res = skipmodcmp(&col1, &col2, kd->flags);
+ res = skipmodcmp(&col1.line, &col2.line, kd->flags);
} else {
- res = linecmp(&col1, &col2);
+ res = linecmp(&col1.line, &col2.line);
}
if (kd->flags & MOD_R)
