summaryrefslogtreecommitdiff
path: root/src/3p/openbsd/asprintf.c
diff options
context:
space:
mode:
authorGravatar Michael Smith <mikesmiffy128@gmail.com> 2025-12-13 18:26:51 +0000
committerGravatar Michael Smith <mikesmiffy128@gmail.com> 2026-02-16 19:11:24 +0000
commit40f9d989df2c1ff2f567656ccbdbfc0d97e34a77 (patch)
treec3a0e69b2823adfe1d5ccf0f48d77b288e55740a /src/3p/openbsd/asprintf.c
parentf386f2a1fcae885967278710fe997c56e2183476 (diff)
downloadsst-40f9d989df2c1ff2f567656ccbdbfc0d97e34a77.tar.gz
sst-40f9d989df2c1ff2f567656ccbdbfc0d97e34a77.zip
Switch cmeta from chibicc to a new homegrown lexer
This lexer is being written as a chunklet, not quite quite complete yet as it lacks some functionality to make it generally useful for things, but good enough for the gluegen use case now. So it's in the repo now and we can go ahead and use it for this instead of having this hacked-to-pieces third party thing that's nowhere near as efficient. In the future the goal is to have a decently usable library for any sort of C metaprogramming needs, not just within this project. This design does the data-oriented thing of storing as little about each token as possible (just 5 bytes), and re-lexing specific pieces only when necessary. In some cases, full validation of correct syntax is only possible through this secondary step. Since the use case is metaprogramming and code-generation rather than the reimplementation of Clang, this slight sloppiness in validation doesn't seem too bad. It's been a while since I did a proper performance measurement of this code but in some crude tests I did in the past the primary tokenisation step was running at well over 500MB/s, which is fast enough for me. It's possible that this version is a tiny bit slower due to the added complexity of making UCNs work. UCNs, incidentally, are one of the dumbest features of C by far. However, unlike trigraphs - which this lexer does not handle - UCNs are still in the language, so it's kind of sort of necessary to support them. It's probably still possible to come up with a faster design with some SIMD trickery, but the main loop is currently branchless and the lookup tables are too big for the SIMD lookup things, so that seems kind of hard. A separate SIMD path for whitespace or comment runs seems dubious as it would introduce branch mispredictions everywhere. I also made previous attempts to unroll the main loop and every attempt just made it slower, so I guess code size is a significant factor. Optimising the secondary tokenisation of identifiers (and later numerals and string/character literals once those are handled) is still on the cards, but since that happens less often, I don't know how much difference it'll make. At any rate, in a multithreaded context this thing would already come pretty close to SSD speeds, if open-read-close syscall overhead doesn't get in the way first. I imagine it's fast enough for anyone who hasn't *already* written something faster.
Diffstat (limited to 'src/3p/openbsd/asprintf.c')
-rw-r--r--src/3p/openbsd/asprintf.c81
1 files changed, 0 insertions, 81 deletions
diff --git a/src/3p/openbsd/asprintf.c b/src/3p/openbsd/asprintf.c
deleted file mode 100644
index 195efce..0000000
--- a/src/3p/openbsd/asprintf.c
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- * Copyright (c) 2004 Darren Tucker.
- *
- * Based originally on asprintf.c from OpenBSD:
- * Copyright (c) 1997 Todd C. Miller <Todd.Miller@courtesan.com>
- *
- * Permission to use, copy, modify, and distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- */
-
-#include <errno.h>
-#include <limits.h> /* for INT_MAX */
-#include <stdarg.h>
-#include <stdio.h> /* for vsnprintf */
-#include <stdlib.h>
-
-#define INIT_SZ 128
-
-int
-vasprintf(char **str, const char *fmt, va_list ap)
-{
- int ret;
- va_list ap2;
- char *string, *newstr;
- size_t len;
-
- if ((string = malloc(INIT_SZ)) == NULL)
- goto fail;
-
- va_copy(ap2, ap);
- ret = vsnprintf(string, INIT_SZ, fmt, ap2);
- va_end(ap2);
- if (ret >= 0 && ret < INIT_SZ) { /* succeeded with initial alloc */
- *str = string;
- } else if (ret == INT_MAX || ret < 0) { /* Bad length */
- free(string);
- goto fail;
- } else { /* bigger than initial, realloc allowing for nul */
- len = (size_t)ret + 1;
- if ((newstr = realloc(string, len)) == NULL) {
- free(string);
- goto fail;
- }
- va_copy(ap2, ap);
- ret = vsnprintf(newstr, len, fmt, ap2);
- va_end(ap2);
- if (ret < 0 || (size_t)ret >= len) { /* failed with realloc'ed string */
- free(newstr);
- goto fail;
- }
- *str = newstr;
- }
- return (ret);
-
-fail:
- *str = NULL;
- errno = ENOMEM;
- return (-1);
-}
-
-int asprintf(char **str, const char *fmt, ...)
-{
- va_list ap;
- int ret;
-
- *str = NULL;
- va_start(ap, fmt);
- ret = vasprintf(str, fmt, ap);
- va_end(ap);
-
- return ret;
-}