`*scanf()` fixes to make TeX work (#1109)
* Fix reading the same symbol twice when using `{f,}scanf()`
PR #924 appears to use `unget()` subtly incorrectly when parsing
floating point numbers. The rest of the code only uses `unget()`
immediately followed by `goto Done;` to return back the symbol that
can't possibly belong to the directive we're processing.
With floating-point, however, the ungot characters could very well
be valid for the *next* directive, so we will essentially read them
twice. It can't be seen in `sscanf()` tests because `unget()` is a
no-op there, but the test I added for `fscanf()` fails like this:
...
EXPECT_EQ(0xDEAD, i1)
need 57005 (or 0xdead) =
got 908973 (or 0x000ddead)
...
EXPECT_EQ(0xBEEF, i2)
need 48879 (or 0xbeef) =
got 769775 (or 0x000bbeef)
This means we read 0xDDEAD instead of 0xDEAD and 0xBBEEF instead of
0xBEEF. I checked that both musl and glibc read 0xDEAD/0xBEEF, as
expected.
Fix the failing test by removing the unneeded `unget()` calls.
* Don't read invalid floating-point numbers in `*scanf()`
Currently, we just ignore any errors from `strtod()`. They can
happen either because no valid float can be parsed at all, or
because the state machine recognizes only a prefix of a valid
floating-point number.
Fix this by making sure `strtod()` parses everything we recognized,
provided it's non-empty. This requires to pop the last character
off the FP buffer, which is supposed to be parsed by the next
`*scanf()` directive.
* Make `%c` parsing in `*scanf()` respect the C standard
Currently, `%c`-style directives always succeed even if there
are actually fewer characters in the input than requested.
Before the fix, the added test fails like this:
...
EXPECT_EQ(2, sscanf("ab", "%c %c %c", &c2, &c3, &c4))
need 2 (or 0x02 or '\2' or ENOENT) =
got 3 (or 0x03 or '\3' or ESRCH)
...
EXPECT_EQ(0, sscanf("abcd", "%5c", s2))
need 0 (or 0x0 or '\0') =
got 1 (or 0x01 or '\1' or EPERM)
musl and glibc pass this test.
2024-02-23 15:15:30 +00:00
|
|
|
/*-*- mode:c;indent-tabs-mode:nil;c-basic-offset:2;tab-width:8;coding:utf-8 -*-│
|
|
|
|
|
│ vi: set et ft=c ts=2 sts=2 sw=2 fenc=utf-8 :vi │
|
|
|
|
|
╞══════════════════════════════════════════════════════════════════════════════╡
|
|
|
|
|
│ Copyright 2024 Ivan Komarov │
|
|
|
|
|
│ │
|
|
|
|
|
│ Permission to use, copy, modify, and/or 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 "libc/math.h"
|
|
|
|
|
#include "libc/stdio/stdio.h"
|
|
|
|
|
#include "libc/testlib/testlib.h"
|
|
|
|
|
|
|
|
|
|
TEST(fscanf, test_readAfterFloat) {
|
|
|
|
|
FILE *f = fmemopen("infDEAD-.125e-2BEEF", 19, "r");
|
|
|
|
|
float f1 = 666.666f, f2 = f1;
|
|
|
|
|
int i1 = 666, i2 = i1;
|
|
|
|
|
EXPECT_EQ(4, fscanf(f, "%f%x%f%x", &f1, &i1, &f2, &i2));
|
|
|
|
|
EXPECT_TRUE(isinf(f1));
|
|
|
|
|
EXPECT_EQ(0xDEAD, i1);
|
2024-09-15 00:11:04 +00:00
|
|
|
EXPECT_FLOAT_EXACTLY_EQ(-0.125e-2f, f2);
|
`*scanf()` fixes to make TeX work (#1109)
* Fix reading the same symbol twice when using `{f,}scanf()`
PR #924 appears to use `unget()` subtly incorrectly when parsing
floating point numbers. The rest of the code only uses `unget()`
immediately followed by `goto Done;` to return back the symbol that
can't possibly belong to the directive we're processing.
With floating-point, however, the ungot characters could very well
be valid for the *next* directive, so we will essentially read them
twice. It can't be seen in `sscanf()` tests because `unget()` is a
no-op there, but the test I added for `fscanf()` fails like this:
...
EXPECT_EQ(0xDEAD, i1)
need 57005 (or 0xdead) =
got 908973 (or 0x000ddead)
...
EXPECT_EQ(0xBEEF, i2)
need 48879 (or 0xbeef) =
got 769775 (or 0x000bbeef)
This means we read 0xDDEAD instead of 0xDEAD and 0xBBEEF instead of
0xBEEF. I checked that both musl and glibc read 0xDEAD/0xBEEF, as
expected.
Fix the failing test by removing the unneeded `unget()` calls.
* Don't read invalid floating-point numbers in `*scanf()`
Currently, we just ignore any errors from `strtod()`. They can
happen either because no valid float can be parsed at all, or
because the state machine recognizes only a prefix of a valid
floating-point number.
Fix this by making sure `strtod()` parses everything we recognized,
provided it's non-empty. This requires to pop the last character
off the FP buffer, which is supposed to be parsed by the next
`*scanf()` directive.
* Make `%c` parsing in `*scanf()` respect the C standard
Currently, `%c`-style directives always succeed even if there
are actually fewer characters in the input than requested.
Before the fix, the added test fails like this:
...
EXPECT_EQ(2, sscanf("ab", "%c %c %c", &c2, &c3, &c4))
need 2 (or 0x02 or '\2' or ENOENT) =
got 3 (or 0x03 or '\3' or ESRCH)
...
EXPECT_EQ(0, sscanf("abcd", "%5c", s2))
need 0 (or 0x0 or '\0') =
got 1 (or 0x01 or '\1' or EPERM)
musl and glibc pass this test.
2024-02-23 15:15:30 +00:00
|
|
|
EXPECT_EQ(0xBEEF, i2);
|
|
|
|
|
fclose(f);
|
|
|
|
|
}
|
