usr: grep, more, cp, nc - and make pollcon pump the link

The shell has had pipes for a while with nothing to pipe *through*, and
an 18-row screen with no way to stop output scrolling off it.

- grep [-vin] PAT [file]: substring match (no regex), stdin or a file,
  grep(1)'s exit convention. The other end of the pipe, at last.
- more [file]: pages 17 lines at a time, --More-- bar in white-on-blue,
  any key pages, q quits. Counts *screen* rows, so wrapped lines pay
  their real cost. Keys come from pollin/pollcon, not stdin, so
  `cat big | more` still has a keyboard.
- cp SRC DST: the fs has rm/mkdir but no way to duplicate a file. mv is
  this plus rm (there is no rename). Rejects SRC == DST, which would
  otherwise truncate the source via O_WRITE before reading a byte.
- nc [-s] HOST PORT: raw TCP. Interactive (START sends the line with a
  CRLF, /q quits) or -s to pump stdin and print the reply with its own
  wall-clock idle timeout, because the kernel's blocking recv counts
  pumps, not seconds. Generalizes what chat/irc hardcode:
  `nc towel.blinkenlights.nl 23` works.

sys_pollcon now pumps the link before draining the console ring. The
ring is filled *by* net_pump, so a program that never touches the
network polled a ring nothing would ever fill: host-injected keys
(gbtype/gbdemo) hung `more` forever, and the Game Boy stopped answering
pings for as long as it ran. KGetc already pumps for this reason.

New tools take banks 35-38. Locals over statics in all four: a program's
_DATA starts at $A000, where the shell leaves the command line.

1 files changed, 99 insertions, 0 deletions

diff --git a/usr/grep.c b/usr/grep.c
new file mode 100644
index 0000000..3d2b325
--- /dev/null
+++ b/usr/grep.c
@@ -0,0 +1,99 @@
+#include "gbos.h"
+/* grep [-v][-i][-n] PAT [file]: print the lines of a file (or stdin) that
+ * contain the substring PAT. Plain substring matching, no regex - '.' and '*'
+ * are literal characters. -v inverts the match, -i folds case, -n prefixes
+ * each hit with its line number.
+ *
+ * NB: no statics here. A program's _DATA area starts at $A000, which is also
+ * where the shell leaves the command line (usr/sh.c ARGV0), so statics would
+ * eat argv. Locals live on the task stack below $BFFF and are always safe. */
+
+#define MAXLINE 80 /* two terminal rows; longer lines are clipped */
+
+static char fold(char c, unsigned char ic) {
+    if (ic && c >= 'A' && c <= 'Z') return (char)(c + 32);
+    return c;
+}
+
+/* is pat[] present anywhere in line[0..len)? */
+static unsigned char contains(char *line, unsigned char len, char *pat, unsigned char ic) {
+    unsigned char i, j;
+    if (!pat[0]) return 1; /* empty pattern matches all */
+    for (i = 0; i < len; i++) {
+        for (j = 0;; j++) {
+            if (!pat[j]) return 1;   /* ran out of pattern: a hit */
+            if (i + j >= len) break; /* ran out of line: no hit here */
+            if (fold(line[i + j], ic) != fold(pat[j], ic)) break;
+        }
+    }
+    return 0;
+}
+
+void main(void) {
+    char *argv[8];
+    char line[MAXLINE];
+    unsigned char argc = argv_parse(argv, 8);
+    unsigned char inv = hasflag(argv, argc, 'v') ? 1 : 0;
+    unsigned char ic = hasflag(argv, argc, 'i') ? 1 : 0;
+    unsigned char num = hasflag(argv, argc, 'n') ? 1 : 0;
+    unsigned char i, len = 0, hits = 0, fd = NOFD;
+    unsigned int lineno = 0;
+    char *pat = 0, *fname = 0;
+    int ch;
+
+    /* first non-flag word is the pattern, second (if any) is the file */
+    for (i = 0; i < argc; i++) {
+        if (argv[i][0] == '-') continue;
+        if (!pat) pat = argv[i];
+        else {
+            fname = argv[i];
+            break;
+        }
+    }
+    if (!pat) {
+        puts("usage: grep [-vin] PAT [file]");
+        nl();
+        sexit(2);
+    }
+
+    if (fname) {
+        fd = open(fname, O_READ);
+        if (fd == EISDIR) {
+            puts("grep: is a directory");
+            nl();
+            sexit(2);
+        }
+        if (fd == NOFD) {
+            puts("grep: 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;    /* CRLF: the LF ends the line */
+        if (ch >= 0 && ch != '\n') { /* ordinary character */
+            if (len < MAXLINE) line[len++] = (char)ch;
+            continue;
+        }
+        if (ch < 0 && len == 0) break; /* EOF, nothing pending */
+        lineno++;
+        if (contains(line, len, pat, ic) != inv) {
+            if (num) {
+                putu(lineno);
+                putc(':');
+            }
+            writes(line, len); /* one batched render */
+            nl();
+            hits = 1;
+        }
+        len = 0;
+        if (ch < 0) break; /* EOF after a final partial line */
+    }
+    if (fd != NOFD) close(fd);
+    sexit(hits ? 0 : 1); /* grep(1) exit convention */
+}