usr: touch, tr, rev, cut, uniq

    /# ls -l /bin > b
    /# cut -d \s -f 1 b | uniq -c
    52 -

- touch FILE...: gbfs has no timestamps (an MBC5 cart has no RTC), so touch
  does the half that means something here - make an empty file. O_APPEND is
  exactly right: it creates, and it does not truncate what is already there.
- tr [-d] SET1 [SET2]: ranges (a-z), -d to delete, and a short SET2 padded
  with its last character, like tr(1). ASCII only - a 128-entry map.
- rev, uniq [-c]: one line each, from a file or stdin like the other filters.

Two things the tests caught. A bare "-" is a SET, not a flag, so `tr . -`
has to skip flag-matching only when a letter follows the dash. And uniq
compared an empty "line" against the last run at EOF and flushed a phantom
blank one - a stray "1" in uniq -c output.

tr and cut also take \s \t \n \r escapes, because the shell has no quoting:
`-d ' '` arrives as three tokens, so a space or tab delimiter was simply
untypeable. Shell quoting would be the better fix; this makes the tools
usable today without touching the parser.

Banks 49-53; 10 program slots left in the 1 MB ROM.

1 files changed, 89 insertions, 0 deletions

diff --git a/usr/cut.c b/usr/cut.c
new file mode 100644
index 0000000..18de461
--- /dev/null
+++ b/usr/cut.c
@@ -0,0 +1,89 @@
+#include "gbos.h"
+/* cut -f N [-d C] [file]: print field N of each line.
+ *
+ * The delimiter defaults to TAB, like cut(1); -d takes the first character of
+ * its argument, so `-d :` works - and since the shell has no quoting, `-d \\s`
+ * is how you say space (\\t tab, \\n newline). A line with no delimiter is passed through
+ * whole (what GNU cut does without -s), which is usually what you want when
+ * filtering mixed output on a 40-column screen. */
+
+#define MAXLINE 80
+
+/* The shell has no quoting, so a space or a tab cannot be typed as an
+   argument: "-d ' '" arrives as three tokens. Escapes are how you name them
+   here - \s space, \t tab, \n newline, \\ backslash. */
+static char unesc1(const char *s, unsigned char *used) {
+    *used = 1;
+    if (s[0] != '\\' || !s[1]) return s[0];
+    *used = 2;
+    switch (s[1]) {
+        case 's': return ' ';
+        case 't': return '\t';
+        case 'n': return '\n';
+        case 'r': return '\r';
+        default: return s[1];
+    }
+}
+
+void main(void) {
+    char *argv[8];
+    char line[MAXLINE];
+    unsigned char argc = argv_parse(argv, 8);
+    char *fv = optval(argv, argc, 'f');
+    char *dv = optval(argv, argc, 'd');
+    unsigned char dused;
+    char delim = dv ? unesc1(dv, &dused) : '\t';
+    unsigned char want = fv ? atou(fv) : 1;
+    unsigned char len = 0, fd = NOFD, i, field, start, end;
+    char *fname = 0;
+    int ch;
+
+    if (want == 0) want = 1;
+    for (i = 0; i < argc; i++) {
+        if (argv[i][0] == '-') continue;
+        if (fv == argv[i] || dv == argv[i]) continue;
+        fname = argv[i];
+        break;
+    }
+    if (fname) {
+        fd = open(fname, O_READ);
+        if (fd == EISDIR) {
+            puts("cut: is a directory");
+            nl();
+            sexit(2);
+        }
+        if (fd == NOFD) {
+            puts("cut: no such file");
+            nl();
+            sexit(2);
+        }
+    }
+    for (;;) {
+        if (fd == NOFD) {
+            char c = readc();
+            ch = (c == EOF) ? -1 : c;
+        } else ch = fgetc(fd);
+        if (ch == '\r') continue;
+        if (ch >= 0 && ch != '\n') {
+            if (len < MAXLINE) line[len++] = (char)ch;
+            continue;
+        }
+        if (ch < 0 && len == 0) break;
+        /* walk to the wanted field */
+        field = 1;
+        start = 0;
+        for (i = 0; i <= len; i++) {
+            if (i == len || line[i] == delim) {
+                if (field == want) break;
+                field++;
+                start = (unsigned char)(i + 1);
+            }
+        }
+        end = i;
+        if (field == want && start <= len) writes(line + start, (unsigned char)(end - start));
+        nl();
+        len = 0;
+        if (ch < 0) break;
+    }
+    if (fd != NOFD) close(fd);
+}