personal/wc
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add historical versions

Browse Source
This commit is contained in:
NunoSempere 2023-09-11 16:34:53 +02:00
parent 16168840c3
commit b987143eb6
5 changed files with 1847 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

257
historical/busybox-wc.c Normal file
View File

@ -0,0 +1,257 @@
/* vi: set sw=4 ts=4: */
/*
* wc implementation for busybox
*
* Copyright (C) 2003 Manuel Novoa III <mjn3@codepoet.org>
*
* Licensed under GPLv2 or later, see file LICENSE in this source tree.
*/
/* Mar 16, 2003 Manuel Novoa III (mjn3@codepoet.org)
*
* Rewritten to fix a number of problems and do some size optimizations.
* Problems in the previous busybox implementation (besides bloat) included:
* 1) broken 'wc -c' optimization (read note below)
* 2) broken handling of '-' args
* 3) no checking of ferror on EOF returns
* 4) isprint() wasn't considered when word counting.
*
* NOTES:
*
* The previous busybox wc attempted an optimization using stat for the
* case of counting chars only. I omitted that because it was broken.
* It didn't take into account the possibility of input coming from a
* pipe, or input from a file with file pointer not at the beginning.
*
* To implement such a speed optimization correctly, not only do you
* need the size, but also the file position. Note also that the
* file position may be past the end of file. Consider the example
* (adapted from example in gnu wc.c)
*
* echo hello > /tmp/testfile &&
* (dd ibs=1k skip=1 count=0 &> /dev/null; wc -c) < /tmp/testfile
*
* for which 'wc -c' should output '0'.
*/
//config:config WC
//config: bool "wc (4.7 kb)"
//config: default y
//config: help
//config: wc is used to print the number of bytes, words, and lines,
//config: in specified files.
//config:
//config:config FEATURE_WC_LARGE
//config: bool "Support very large counts"
//config: default y
//config: depends on WC
//config: help
//config: Use "unsigned long long" for counter variables.
//applet:IF_WC(APPLET(wc, BB_DIR_USR_BIN, BB_SUID_DROP))
//kbuild:lib-$(CONFIG_WC) += wc.o
/* BB_AUDIT SUSv3 compliant. */
/* http://www.opengroup.org/onlinepubs/007904975/utilities/wc.html */
#include "libbb.h"
#include "unicode.h"
#if !ENABLE_LOCALE_SUPPORT
# undef isprint
# undef isspace
# define isprint(c) ((unsigned)((c) - 0x20) <= (0x7e - 0x20))
# define isspace(c) ((c) == ' ')
#endif
#if ENABLE_FEATURE_WC_LARGE
# define COUNT_T unsigned long long
# define COUNT_FMT "llu"
#else
# define COUNT_T unsigned
# define COUNT_FMT "u"
#endif
/* We support -m even when UNICODE_SUPPORT is off,
* we just don't advertise it in help text,
* since it is the same as -c in this case.
*/
//usage:#define wc_trivial_usage
//usage: "[-c"IF_UNICODE_SUPPORT("m")"lwL] [FILE]..."
//usage:
//usage:#define wc_full_usage "\n\n"
//usage: "Count lines, words, and bytes for FILEs (or stdin)\n"
//usage: "\n -c Count bytes"
//usage: IF_UNICODE_SUPPORT(
//usage: "\n -m Count characters"
//usage: )
//usage: "\n -l Count newlines"
//usage: "\n -w Count words"
//usage: "\n -L Print longest line length"
//usage:
//usage:#define wc_example_usage
//usage: "$ wc /etc/passwd\n"
//usage: " 31 46 1365 /etc/passwd\n"
/* Order is important if we want to be compatible with
* column order in "wc -cmlwL" output:
*/
enum {
WC_LINES = 0, /* -l */
WC_WORDS = 1, /* -w */
WC_UNICHARS = 2, /* -m */
WC_BYTES = 3, /* -c */
WC_LENGTH = 4, /* -L */
NUM_WCS = 5,
};
int wc_main(int argc, char **argv) MAIN_EXTERNALLY_VISIBLE;
int wc_main(int argc UNUSED_PARAM, char **argv)
{
const char *arg;
const char *start_fmt = " %9"COUNT_FMT + 1;
const char *fname_fmt = " %s\n";
COUNT_T *pcounts;
COUNT_T counts[NUM_WCS];
COUNT_T totals[NUM_WCS];
int num_files;
smallint status = EXIT_SUCCESS;
unsigned print_type;
init_unicode();
print_type = getopt32(argv, "lwmcL");
if (print_type == 0) {
print_type = (1 << WC_LINES) | (1 << WC_WORDS) | (1 << WC_BYTES);
}
argv += optind;
if (!argv[0]) {
*--argv = (char *) bb_msg_standard_input;
fname_fmt = "\n";
}
if (!argv[1]) { /* zero or one filename? */
if (!((print_type-1) & print_type)) /* exactly one option? */
start_fmt = "%"COUNT_FMT;
}
memset(totals, 0, sizeof(totals));
pcounts = counts;
num_files = 0;
while ((arg = *argv++) != NULL) {
FILE *fp;
const char *s;
unsigned u;
unsigned linepos;
smallint in_word;
++num_files;
fp = fopen_or_warn_stdin(arg);
if (!fp) {
status = EXIT_FAILURE;
continue;
}
memset(counts, 0, sizeof(counts));
linepos = 0;
in_word = 0;
while (1) {
int c;
/* Our -w doesn't match GNU wc exactly... oh well */
c = getc(fp);
if (c == EOF) {
if (ferror(fp)) {
bb_simple_perror_msg(arg);
status = EXIT_FAILURE;
}
goto DO_EOF; /* Treat an EOF as '\r'. */
}
/* Cater for -c and -m */
++counts[WC_BYTES];
if (unicode_status != UNICODE_ON /* every byte is a new char */
|| (c & 0xc0) != 0x80 /* it isn't a 2nd+ byte of a Unicode char */
) {
++counts[WC_UNICHARS];
}
if (isprint_asciionly(c)) { /* FIXME: not unicode-aware */
++linepos;
if (!isspace(c)) {
in_word = 1;
continue;
}
} else if ((unsigned)(c - 9) <= 4) {
/* \t 9
* \n 10
* \v 11
* \f 12
* \r 13
*/
if (c == '\t') {
linepos = (linepos | 7) + 1;
} else { /* '\n', '\r', '\f', or '\v' */
DO_EOF:
if (linepos > counts[WC_LENGTH]) {
counts[WC_LENGTH] = linepos;
}
if (c == '\n') {
++counts[WC_LINES];
}
if (c != '\v') {
linepos = 0;
}
}
} else {
continue;
}
counts[WC_WORDS] += in_word;
in_word = 0;
if (c == EOF) {
break;
}
}
fclose_if_not_stdin(fp);
if (totals[WC_LENGTH] < counts[WC_LENGTH]) {
totals[WC_LENGTH] = counts[WC_LENGTH];
}
totals[WC_LENGTH] -= counts[WC_LENGTH];
OUTPUT:
/* coreutils wc tries hard to print pretty columns
* (saves results for all files, finds max col len etc...)
* we won't try that hard, it will bloat us too much */
s = start_fmt;
u = 0;
do {
if (print_type & (1 << u)) {
printf(s, pcounts[u]);
s = " %9"COUNT_FMT; /* Ok... restore the leading space. */
}
totals[u] += pcounts[u];
} while (++u < NUM_WCS);
printf(fname_fmt, arg);
}
/* If more than one file was processed, we want the totals. To save some
* space, we set the pcounts ptr to the totals array. This has the side
* effect of trashing the totals array after outputting it, but that's
* irrelavent since we no longer need it. */
if (num_files > 1) {
num_files = 0; /* Make sure we don't get here again. */
arg = "total";
pcounts = totals;
--argv;
goto OUTPUT;
}
fflush_stdout_and_exit(status);
}

1034
historical/gnu-wc.c Normal file
View File

File diff suppressed because it is too large Load Diff

118
historical/plan9-wc.c Normal file
View File

@ -0,0 +1,118 @@
/*
* Count bytes within runes, if it fits in a uvlong, and other things.
*/
#include <u.h>
#include <libc.h>
#include <bio.h>
/* flags, per-file counts, and total counts */
static int pline, pword, prune, pbadr, pchar;
static uvlong nline, nword, nrune, nbadr, nchar;
static uvlong tnline, tnword, tnrune, tnbadr, tnchar;
enum{Space, Word};
static void
wc(Biobuf *bin)
{
int where;
long r;
nline = 0;
nword = 0;
nrune = 0;
nbadr = 0;
where = Space;
while ((long)(r = Bgetrune(bin)) >= 0) {
nrune++;
if(r == Runeerror) {
nbadr++;
continue;
}
if(r == '\n')
nline++;
if(where == Word){
if(isspacerune(r))
where = Space;
}else
if(isspacerune(r) == 0){
where = Word;
nword++;
}
}
nchar = Boffset(bin);
tnline += nline;
tnword += nword;
tnrune += nrune;
tnbadr += nbadr;
tnchar += nchar;
}
static void
report(uvlong nline, uvlong nword, uvlong nrune, uvlong nbadr, uvlong nchar, char *fname)
{
char line[1024], *s, *e;
s = line;
e = line + sizeof line;
line[0] = 0;
if(pline)
s = seprint(s, e, " %7llud", nline);
if(pword)
s = seprint(s, e, " %7llud", nword);
if(prune)
s = seprint(s, e, " %7llud", nrune);
if(pbadr)
s = seprint(s, e, " %7llud", nbadr);
if(pchar)
s = seprint(s, e, " %7llud", nchar);
if(fname != nil)
seprint(s, e, " %s", fname);
print("%s\n", line+1);
}
void
main(int argc, char *argv[])
{
char *sts;
Biobuf sin, *bin;
int i;
sts = nil;
ARGBEGIN {
case 'l': pline++; break;
case 'w': pword++; break;
case 'r': prune++; break;
case 'b': pbadr++; break;
case 'c': pchar++; break;
default:
fprint(2, "Usage: %s [-lwrbc] [file ...]\n", argv0);
exits("usage");
} ARGEND
if(pline+pword+prune+pbadr+pchar == 0){
pline = 1;
pword = 1;
pchar = 1;
}
if(argc == 0){
Binit(&sin, 0, OREAD);
wc(&sin);
report(nline, nword, nrune, nbadr, nchar, nil);
Bterm(&sin);
}else{
for(i = 0; i < argc; i++){
bin = Bopen(argv[i], OREAD);
if(bin == nil){
perror(argv[i]);
sts = "can't open";
continue;
}
wc(bin);
report(nline, nword, nrune, nbadr, nchar, argv[i]);
Bterm(bin);
}
if(argc>1)
report(tnline, tnword, tnrune, tnbadr, tnchar, "total");
}
exits(sts);
}

352
historical/plan9port-wc.c Normal file
View File

@ -0,0 +1,352 @@
/*
* wc -- count things in utf-encoded text files
* Bugs:
* The only white space characters recognized are ' ', '\t' and '\n', even though
* ISO 10646 has many more blanks scattered through it.
* Should count characters that cannot occur in any rune (hex f0-ff) separately.
* Should count non-canonical runes (e.g. hex c1,80 instead of hex 40).
*/
#include <u.h>
#include <libc.h>
#define NBUF (8*1024)
uvlong nline, tnline, pline;
uvlong nword, tnword, pword;
uvlong nrune, tnrune, prune;
uvlong nbadr, tnbadr, pbadr;
uvlong nchar, tnchar, pchar;
void count(int, char *);
void report(uvlong, uvlong, uvlong, uvlong, uvlong, char *);
void
main(int argc, char *argv[])
{
char *status="";
int i, f;
ARGBEGIN {
case 'l': pline++; break;
case 'w': pword++; break;
case 'r': prune++; break;
case 'b': pbadr++; break;
case 'c': pchar++; break;
default:
fprint(2, "Usage: %s [-lwrbc] [file ...]\n", argv0);
exits("usage");
} ARGEND
if(pline+pword+prune+pbadr+pchar == 0) {
pline = 1;
pword = 1;
pchar = 1;
}
if(argc==0)
count(0, 0);
else{
for(i=0;i<argc;i++){
f=open(argv[i], OREAD);
if(f<0){
perror(argv[i]);
status="can't open";
}
else{
count(f, argv[i]);
tnline+=nline;
tnword+=nword;
tnrune+=nrune;
tnbadr+=nbadr;
tnchar+=nchar;
close(f);
}
}
if(argc>1)
report(tnline, tnword, tnrune, tnbadr, tnchar, "total");
}
exits(status);
}
void
report(uvlong nline, uvlong nword, uvlong nrune, uvlong nbadr, uvlong nchar, char *fname)
{
char line[1024], word[128];
line[0] = '\0';
if(pline){
sprint(word, " %7llud", nline);
strcat(line, word);
}
if(pword){
sprint(word, " %7llud", nword);
strcat(line, word);
}
if(prune){
sprint(word, " %7llud", nrune);
strcat(line, word);
}
if(pbadr){
sprint(word, " %7llud", nbadr);
strcat(line, word);
}
if(pchar){
sprint(word, " %7llud", nchar);
strcat(line, word);
}
if(fname){
sprint(word, " %s", fname);
strcat(line, word);
}
print("%s\n", line+1);
}
/*
* How it works. Start in statesp. Each time we read a character,
* increment various counts, and do state transitions according to the
* following table. If we're not in statesp or statewd when done, the
* file ends with a partial rune.
* | character
* state |09,20| 0a |00-7f|80-bf|c0-df|e0-ef|f0-f7|f8-ff
* -------+-----+-----+-----+-----+-----+-----+-----+-----
* statesp|ASP |ASPN |AWDW |AWDWX|AC2W |AC3W |AC4W |AWDWX
* statewd|ASP |ASPN |AWD |AWDX |AC2 |AC3 |AC4 |AWDX
* statec2|ASPX |ASPNX|AWDX |AWDR |AC2X |AC3X |AC4X |AWDX
* statec3|ASPX |ASPNX|AWDX |AC2R |AC2X |AC3X |AC4X |AWDX
* statec4|ASPX |ASPNX|AWDX |AC3R |AC2X |AC3X |AC4X |AWDX f4 8f bf bf
*/
enum{ /* actions */
AC2, /* enter statec2 */
AC2R, /* enter statec2, don't count a rune */
AC2W, /* enter statec2, count a word */
AC2X, /* enter statec2, count a bad rune */
AC3, /* enter statec3 */
AC3R, /* enter statec3, don't count a rune */
AC3W, /* enter statec3, count a word */
AC3X, /* enter statec3, count a bad rune */
AC4, /* enter statec4 */
AC4W, /* enter statec4, count a word */
AC4X, /* enter statec4, count a bad rune */
ASP, /* enter statesp */
ASPN, /* enter statesp, count a newline */
ASPNX, /* enter statesp, count a newline, count a bad rune */
ASPX, /* enter statesp, count a bad rune */
AWD, /* enter statewd */
AWDR, /* enter statewd, don't count a rune */
AWDW, /* enter statewd, count a word */
AWDWX, /* enter statewd, count a word, count a bad rune */
AWDX, /* enter statewd, count a bad rune */
};
uchar statesp[256]={ /* looking for the start of a word */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 00-07 */
AWDW, ASP, ASPN, AWDW, AWDW, AWDW, AWDW, AWDW, /* 08-0f */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 10-17 */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 18-1f */
ASP, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 20-27 */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 28-2f */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 30-37 */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 38-3f */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 40-47 */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 48-4f */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 50-57 */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 58-5f */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 60-67 */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 68-6f */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 70-77 */
AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, /* 78-7f */
AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* 80-87 */
AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* 88-8f */
AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* 90-97 */
AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* 98-9f */
AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* a0-a7 */
AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* a8-af */
AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* b0-b7 */
AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* b8-bf */
AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, /* c0-c7 */
AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, /* c8-cf */
AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, /* d0-d7 */
AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, /* d8-df */
AC3W, AC3W, AC3W, AC3W, AC3W, AC3W, AC3W, AC3W, /* e0-e7 */
AC3W, AC3W, AC3W, AC3W, AC3W, AC3W, AC3W, AC3W, /* e8-ef */
AC4W, AC4W, AC4W, AC4W, AC4W, AC4W, AC4W, AC4W, /* f0-f7 */
AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* f8-ff */
};
uchar statewd[256]={ /* looking for the next character in a word */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 00-07 */
AWD, ASP, ASPN, AWD, AWD, AWD, AWD, AWD, /* 08-0f */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 10-17 */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 18-1f */
ASP, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 20-27 */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 28-2f */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 30-37 */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 38-3f */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 40-47 */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 48-4f */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 50-57 */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 58-5f */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 60-67 */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 68-6f */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 70-77 */
AWD, AWD, AWD, AWD, AWD, AWD, AWD, AWD, /* 78-7f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 80-87 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 88-8f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 90-97 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 98-9f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* a0-a7 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* a8-af */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* b0-b7 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* b8-bf */
AC2, AC2, AC2, AC2, AC2, AC2, AC2, AC2, /* c0-c7 */
AC2, AC2, AC2, AC2, AC2, AC2, AC2, AC2, /* c8-cf */
AC2, AC2, AC2, AC2, AC2, AC2, AC2, AC2, /* d0-d7 */
AC2, AC2, AC2, AC2, AC2, AC2, AC2, AC2, /* d8-df */
AC3, AC3, AC3, AC3, AC3, AC3, AC3, AC3, /* e0-e7 */
AC3, AC3, AC3, AC3, AC3, AC3, AC3, AC3, /* e8-ef */
AC4, AC4, AC4, AC4, AC4, AC4, AC4, AC4, /* f0-f7 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* f8-ff */
};
uchar statec2[256]={ /* looking for 10xxxxxx to complete a rune */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 00-07 */
AWDX, ASPX, ASPNX,AWDX, AWDX, AWDX, AWDX, AWDX, /* 08-0f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 10-17 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 18-1f */
ASPX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 20-27 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 28-2f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 30-37 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 38-3f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 40-47 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 48-4f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 50-57 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 58-5f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 60-67 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 68-6f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 70-77 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 78-7f */
AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, /* 80-87 */
AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, /* 88-8f */
AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, /* 90-97 */
AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, /* 98-9f */
AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, /* a0-a7 */
AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, /* a8-af */
AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, /* b0-b7 */
AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, /* b8-bf */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* c0-c7 */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* c8-cf */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* d0-d7 */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* d8-df */
AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, /* e0-e7 */
AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, /* e8-ef */
AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, /* f0-f7 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* f8-ff */
};
uchar statec3[256]={ /* looking for 10xxxxxx,10xxxxxx to complete a rune */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 00-07 */
AWDX, ASPX, ASPNX,AWDX, AWDX, AWDX, AWDX, AWDX, /* 08-0f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 10-17 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 18-1f */
ASPX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 20-27 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 28-2f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 30-37 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 38-3f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 40-47 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 48-4f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 50-57 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 58-5f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 60-67 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 68-6f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 70-77 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 78-7f */
AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, /* 80-87 */
AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, /* 88-8f */
AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, /* 90-97 */
AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, /* 98-9f */
AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, /* a0-a7 */
AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, /* a8-af */
AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, /* b0-b7 */
AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, /* b8-bf */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* c0-c7 */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* c8-cf */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* d0-d7 */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* d8-df */
AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, /* e0-e7 */
AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, /* e8-ef */
AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, /* f0-f7 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* f8-ff */
};
uchar statec4[256]={ /* looking for 10xxxxxx,10xxxxxx,10xxxxxx to complete a rune */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 00-07 */
AWDX, ASPX, ASPNX,AWDX, AWDX, AWDX, AWDX, AWDX, /* 08-0f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 10-17 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 18-1f */
ASPX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 20-27 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 28-2f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 30-37 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 38-3f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 40-47 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 48-4f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 50-57 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 58-5f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 60-67 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 68-6f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 70-77 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 78-7f */
AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, /* 80-87 */
AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, /* 88-8f */
AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, /* 90-97 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* 98-9f */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* a0-a7 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* a8-af */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* b0-b7 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* b8-bf */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* c0-c7 */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* c8-cf */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* d0-d7 */
AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, /* d8-df */
AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, /* e0-e7 */
AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, /* e8-ef */
AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, /* f0-f7 */
AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, /* f8-ff */
};
void
count(int f, char *name)
{
int n;
uchar buf[NBUF];
uchar *bufp, *ebuf;
uchar *state=statesp;
nline = 0;
nword = 0;
nrune = 0;
nbadr = 0;
nchar = 0;
for(;;){
n=read(f, buf, NBUF);
if(n<=0)
break;
nchar+=n;
nrune+=n; /* might be too large, gets decreased later */
bufp=buf;
ebuf=buf+n;
do{
switch(state[*bufp]){
case AC2: state=statec2; break;
case AC2R: state=statec2; --nrune; break;
case AC2W: state=statec2; nword++; break;
case AC2X: state=statec2; nbadr++; break;
case AC3: state=statec3; break;
case AC3R: state=statec3; --nrune; break;
case AC3W: state=statec3; nword++; break;
case AC3X: state=statec3; nbadr++; break;
case AC4: state=statec4; break;
case AC4W: state=statec4; nword++; break;
case AC4X: state=statec4; nbadr++; break;
case ASP: state=statesp; break;
case ASPN: state=statesp; nline++; break;
case ASPNX: state=statesp; nline++; nbadr++; break;
case ASPX: state=statesp; nbadr++; break;
case AWD: state=statewd; break;
case AWDR: state=statewd; --nrune; break;
case AWDW: state=statewd; nword++; break;
case AWDWX: state=statewd; nword++; nbadr++; break;
case AWDX: state=statewd; nbadr++; break;
}
}while(++bufp!=ebuf);
}
if(state!=statesp && state!=statewd)
nbadr++;
if(n<0)
fprint(2, "%s: %r\n", name);
report(nline, nword, nrune, nbadr, nchar, name);
}

86
historical/unix-v7-wc.c Normal file
View File

@ -0,0 +1,86 @@
/* wc line and word count */
#include <stdio.h>
main(argc, argv)
char **argv;
{
int i, token;
register FILE *fp;
long linect, wordct, charct;
long tlinect=0, twordct=0, tcharct=0;
char *wd;
register int c;
wd = "lwc";
if(argc > 1 && *argv[1] == '-') {
wd = ++argv[1];
argc--;
argv++;
}
i = 1;
fp = stdin;
do {
if(argc>1 && (fp=fopen(argv[i], "r")) == NULL) {
fprintf(stderr, "wc: can't open %s\n", argv[i]);
continue;
}
linect = 0;
wordct = 0;
charct = 0;
token = 0;
for(;;) {
c = getc(fp);
if (c == EOF)
break;
charct++;
if(' '<c&&c<0177) {
if(!token) {
wordct++;
token++;
}
continue;
}
if(c=='\n')
linect++;
else if(c!=' '&&c!='\t')
continue;
token = 0;
}
/* print lines, words, chars */
wcp(wd, charct, wordct, linect);
if(argc>1) {
printf(" %s\n", argv[i]);
} else
printf("\n");
fclose(fp);
tlinect += linect;
twordct += wordct;
tcharct += charct;
} while(++i<argc);
if(argc > 2) {
wcp(wd, tcharct, twordct, tlinect);
printf(" total\n");
}
exit(0);
}
wcp(wd, charct, wordct, linect)
register char *wd;
long charct; long wordct; long linect;
{
while (*wd) switch (*wd++) {
case 'l':
printf("%7ld", linect);
break;
case 'w':
printf("%7ld ", wordct);
break;
case 'c':
printf("%7ld", charct);
break;
}
}