d/freebsd-dev
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

wc(1): Extend non-controversial optimizations to '-c' mode

Browse Source 
wc(1)'s slow path for counting words or multibyte characters requires
conversion of the 8-bit input stream to wide characters.  However, a faster
path can be used for counting only lines ('-l' -- newlines have the same
representation in all supported encodings) or bytes ('-c').

The existing line count optimization was not used if the input was the
implicit stdin.  Additionally, it wasn't used if only byte counting was
requested.  This change expands the fast path to both of these scenarios.

Expanding the buffer size from 64 kB helps reduce the number of read(2)
calls needed, but exactly what impact that change has and what size to
expand the buffer to are still under discussion.

PR:		224160
Tested by:	wosch (earlier version)
Sponsored by:	Dell EMC Isilon
This commit is contained in:
Conrad Meyer 2017-12-09 21:55:19 +00:00
parent 219afc4fe2
commit de1430411d
Notes: svn2git 2020-12-20 02:59:44 +00:00 
svn path=/head/; revision=326736
1 changed files with 51 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

101
usr.bin/wc/wc.c
View File

@ -206,30 +206,30 @@ cnt(const char *file)
linect = wordct = charct = llct = tmpll = 0;
if (file == NULL)
fd = STDIN_FILENO;
else {
if ((fd = open(file, O_RDONLY, 0)) < 0) {
xo_warn("%s: open", file);
return (1);
}
if (doword || (domulti && MB_CUR_MAX != 1))
goto word;
/*
* Line counting is split out because it's a lot faster to get
* lines than to get words, since the word count requires some
* logic.
*/
if (doline) {
while ((len = read(fd, buf, MAXBSIZE))) {
if (len == -1) {
xo_warn("%s: read", file);
(void)close(fd);
return (1);
}
if (siginfo) {
show_cnt(file, linect, wordct, charct,
llct);
}
charct += len;
else if ((fd = open(file, O_RDONLY, 0)) < 0) {
xo_warn("%s: open", file);
return (1);
}
if (doword || (domulti && MB_CUR_MAX != 1))
goto word;
/*
* Line counting is split out because it's a lot faster to get
* lines than to get words, since the word count requires some
* logic.
*/
if (doline || dochar) {
while ((len = read(fd, buf, MAXBSIZE))) {
if (len == -1) {
xo_warn("%s: read", file);
(void)close(fd);
return (1);
}
if (siginfo) {
show_cnt(file, linect, wordct, charct,
llct);
}
charct += len;
if (doline) {
for (p = buf; len--; ++p)
if (*p == '\n') {
if (tmpll > llct)
@ -239,37 +239,38 @@ cnt(const char *file)
} else
tmpll++;
}
reset_siginfo();
}
reset_siginfo();
if (doline)
tlinect += linect;
if (dochar)
tcharct += charct;
if (dolongline) {
if (llct > tlongline)
tlongline = llct;
}
if (dochar)
tcharct += charct;
if (dolongline) {
if (llct > tlongline)
tlongline = llct;
}
show_cnt(file, linect, wordct, charct, llct);
(void)close(fd);
return (0);
}
/*
* If all we need is the number of characters and it's a
* regular file, just stat the puppy.
*/
if (dochar || domulti) {
if (fstat(fd, &sb)) {
xo_warn("%s: fstat", file);
(void)close(fd);
return (1);
}
if (S_ISREG(sb.st_mode)) {
reset_siginfo();
charct = sb.st_size;
show_cnt(file, linect, wordct, charct, llct);
tcharct += charct;
(void)close(fd);
return (0);
}
/*
* If all we need is the number of characters and it's a
* regular file, just stat the puppy.
*/
if (dochar || domulti) {
if (fstat(fd, &sb)) {
xo_warn("%s: fstat", file);
(void)close(fd);
return (1);
}
if (S_ISREG(sb.st_mode)) {
reset_siginfo();
charct = sb.st_size;
show_cnt(file, linect, wordct, charct, llct);
tcharct += charct;
(void)close(fd);
return (0);
}
}
}
/* Do it the hard way... */