#!/usr/bin/env dub
/+ dub.sdl:
name "sanitizers_valgrind_attribution"
platforms "linux"
targetPath "build"
dflags "-g"
dependency "sparkles:core-cli" path="../../../.."
dflags "-I$PACKAGE_DIR/.." "-i=valgrind_helpers"
+/
/**
* Per-test attribution of valgrind findings via `VALGRIND_PRINTF` markers in
* the `--xml=yes` stream: the child emits a marker client request before each
* "test", each test commits a distinct memory error, and the parent proves the
* XML stream interleaves `<clientmsg>` records IN ORDER with `<error>`
* records — so a runner can attribute every error between marker N and marker
* N+1 to test N. This decides the `--valgrind` mode's attribution design.
*
* 1. The client-request mechanism, hand-rolled in ~20 lines of D inline
* asm: valgrind's amd64 magic preamble is `rol rdi` by 3, 13, 61, 51 (a
* net no-op — 128 bits of rotation) followed by `xchg rbx,rbx`; args go
* through RAX, the result through RDX (`include/valgrind.h.in`). Outside
* valgrind the sequence executes as plain arithmetic and the default
* value flows through — the same trick `etc.valgrind`'s C side uses.
* 2. `VG_USERREQ__PRINTF_VALIST_BY_REF` (0x1403) takes a format pointer and
* a `va_list*`; on linux-x86_64 D's `va_list` is already the pointer to
* the `__va_list_tag` record, so it is passed as-is (NOT `&ap` — the
* deprecated 0x1401 request aborts on amd64 where
* `sizeof(va_list) != sizeof(UWord)`).
* 3. `RUNNING_ON_VALGRIND` (0x1001) gates the child: outside valgrind the
* markers would vanish, so the demo only asserts under the tool.
* 4. The parent asserts the stream shape: clientmsg("test=1") precedes
* error(InvalidRead), which precedes clientmsg("test=2"), which precedes
* error(InvalidWrite). Caveat a runner must own: valgrind DEDUPLICATES
* errors by context — a repeat of an already-seen error in a later test
* emits no new `<error>` record (only end-of-run `<errorcounts>`), so
* marker-window attribution sees only each context's FIRST occurrence.
*
* Companion to docs/research/sanitizers/valgrind.md
* § "Runner integration semantics" (per-test attribution: markers in the XML
* stream).
*
* Run with: dub run --single valgrind-attribution.d
*
* Environment recorded: Linux 6.18.26, AMD Ryzen 9 7940HX, valgrind 3.26.0
* (nixpkgs), LDC 1.41.0 and DMD 2.112.1 (both compilers' `D_InlineAsm_X86_64`
* verified against valgrind 3.26.0's request dispatch).
*
* Portability: hosts without `valgrind` on `PATH`, and ISAs without
* `D_InlineAsm_X86_64`, print a `SKIP:` line and exit 0. Linux-only
* (`platforms "linux"`).
*/
module (module) sanitizers_valgrind_attributionPer-test attribution of valgrind findings via VALGRIND_PRINTF markers in
the --xml=yes stream: the child emits a marker client request before each
"test", each test commits a distinct memory error, and the parent proves the
XML stream interleaves <clientmsg> records IN ORDER with <error>
records — so a runner can attribute every error between marker N and marker
N+1 to test N. This decides the --valgrind mode's attribution design.
The client-request mechanism, hand-rolled in ~20 lines of D inline
asm: valgrind's amd64 magic preamble is rol rdi by 3, 13, 61, 51 (a
net no-op — 128 bits of rotation) followed by xchg rbx,rbx; args go
through RAX, the result through RDX (include/valgrind.h.in). Outside
valgrind the sequence executes as plain arithmetic and the default
value flows through — the same trick etc.valgrind's C side uses.
VG_USERREQ__PRINTF_VALIST_BY_REF (0x1403) takes a format pointer and
a va_list*; on linux-x86_64 D's va_list is already the pointer to
the __va_list_tag record, so it is passed as-is (NOT &ap — the
deprecated 0x1401 request aborts on amd64 where
sizeof(va_list) != sizeof(UWord)).
RUNNING_ON_VALGRIND (0x1001) gates the child: outside valgrind the
markers would vanish, so the demo only asserts under the tool.
The parent asserts the stream shape: clientmsg("test=1") precedes
error(InvalidRead), which precedes clientmsg("test=2"), which precedes
error(InvalidWrite). Caveat a runner must own: valgrind DEDUPLICATES
errors by context — a repeat of an already-seen error in a later test
emits no new <error> record (only end-of-run <errorcounts>), so
marker-window attribution sees only each context's FIRST occurrence.
Companion to docs/research/sanitizers/valgrind.md
§ "Runner integration semantics" (per-test attribution: markers in the XML
stream).
Run with: dub run --single valgrind-attribution.d
Environment recorded: Linux 6.18.26, AMD Ryzen 9 7940HX, valgrind 3.26.0
(nixpkgs), LDC 1.41.0 and DMD 2.112.1 (both compilers' D_InlineAsm_X86_64
verified against valgrind 3.26.0's request dispatch).
Portability
hosts without valgrind on PATH, and ISAs without
D_InlineAsm_X86_64, print a SKIP: line and exit 0. Linux-only
(platforms "linux").
sanitizers_valgrind_attribution;
version (linuxlinux)
{
import (package) stdstd.(module) std.stdioCategory Symbols File handles _popen File isFileHandle openNetwork stderr stdin stdout Reading chunks lines readf readfln readln Writing toFile write writef writefln writeln Misc KeepTerminator LockType StdioException
Standard I/O functions that extend core.stdc.stdio. core.stdc.stdio
is publically imported when importing std.stdio.
There are three layers of I/O:
The lowest layer is the operating system layer. The two main schemes are Windows and Posix.
C's stdio.h which unifies the two operating system schemes.
std.stdio, this module, unifies the various stdio.h implementations into
a high level package for D programs.
Source
std/stdio.d
stdio : (alias template) sanitizers_valgrind_attribution.writefln = std.stdio.writefln(alias fmt, A...)(A args) if (isSomeString!(typeof(fmt)))Equivalent to writef(fmt, args, '\n').
writefln;
import (module) valgrind_helpersShared helpers for the examples/valgrind-*.d probes.
Deliberately one directory above examples/: ci --example-files globs
docs/research/sanitizers/examples/*.d, and a git pathspec's * matches
/ too — so anything under examples/, including a subdirectory, is picked
up and run as an example. This file has no main and no dub.sdl header,
so that would simply fail. Living here keeps it out of the glob while the
examples pull it in with sourceFiles "../valgrind_helpers.d".
valgrind_helpers : (alias) sanitizers_valgrind_attribution.valgrindCanInstrument = bool valgrind_helpers.valgrindCanInstrument(out string reason)Whether valgrind can actually instrument a program here — not merely
whether it answers --version.
The launcher answering a version string proves only that it is on PATH. On
CircleCI's AWS machine executor (kernel 6.14-aws) valgrind 3.26 answers
--version, emits its full XML preamble, and then wedges: the
memcheck-amd64- process sleeps in do_wait forever. A version-only probe
reads that as healthy and sends an example into a hang instead of the skip
it was designed to take.
So instrument something trivial under a deadline. true is the cheapest
guest there is, and a valgrind that cannot finish it in
valgrindProbeDeadline cannot run these examples either. The deadline
is what turns a wedged valgrind into a SKIP rather than a hang —
std.process.execute has no timeout, which is why this goes through
executeMonitored instead.
valgrindCanInstrument;
enum (constant) string sanitizers_valgrind_attribution.childEnvVar = "SANITIZERS_PROBE_CHILD"childEnvVar = "SANITIZERS_PROBE_CHILD";
enum : ulong
{
(enum value) sanitizers_valgrind_attribution.VG_USERREQ__RUNNING_ON_VALGRIND = 4097LUVG_USERREQ__RUNNING_ON_VALGRIND = 0x1001,
(enum value) sanitizers_valgrind_attribution.VG_USERREQ__PRINTF_VALIST_BY_REF = 5123LUVG_USERREQ__PRINTF_VALIST_BY_REF = 0x1403,
}
/// valgrind's client-request trap, amd64 encoding: the rotation preamble
/// plus `xchg rbx,rbx`. Args pointer in RAX, default + result in RDX.
/// A no-op returning `defaultResult` when not running under valgrind.
ulong ulong sanitizers_valgrind_attribution.valgrindClientRequest(ulong defaultResult, ulong request, ulong a1 = 0LU, ulong a2 = 0LU, ulong a3 = 0LU, ulong a4 = 0LU, ulong a5 = 0LU) nothrow @nogc @systemvalgrind's client-request trap, amd64 encoding: the rotation preamble
plus xchg rbx,rbx. Args pointer in RAX, default + result in RDX.
A no-op returning defaultResult when not running under valgrind.
valgrindClientRequest(ulong (parameter) ulong defaultResultdefaultResult, ulong (parameter) ulong requestrequest,
ulong (parameter) ulong a1a1 = 0, ulong (parameter) ulong a2a2 = 0, ulong (parameter) ulong a3a3 = 0, ulong (parameter) ulong a4a4 = 0, ulong (parameter) ulong a5a5 = 0)
@system nothrow @nogc
{
version (D_InlineAsm_X86_64D_InlineAsm_X86_64)
{
ulong[6] (local variable) ulong[6] argsargs = [(parameter) ulong requestrequest, (parameter) ulong a1a1, (parameter) ulong a2a2, (parameter) ulong a3a3, (parameter) ulong a4a4, (parameter) ulong a5a5];
ulong (local variable) ulong resultresult = (parameter) ulong defaultResultdefaultResult;
auto (local variable) ulong* pp = (local variable) ulong[6] argsargs.(constant) ulong* ulong[6].ptr = &argsptr;
asm nothrow @nogc
{
mov RAX, p;
mov RDX, result;
rol RDI, 3;
rol RDI, 13;
rol RDI, 61;
rol RDI, 51;
xchg RBX, RBX;
mov result, RDX;
}
return (local variable) ulong resultresult;
}
else
return defaultResult;
}
/// `VALGRIND_PRINTF`: emits a `<clientmsg>` record into the XML stream
/// (a plain user message in text mode). Returns the byte count printed.
extern (C) int int sanitizers_valgrind_attribution.vgPrintf(scope const(char)* format, ...) @systemVALGRIND_PRINTF: emits a <clientmsg> record into the XML stream
(a plain user message in text mode). Returns the byte count printed.
vgPrintf(scope const(char)* (parameter) const(char)* formatformat, ...) @system
{
import (package) corecore.(package) core.stdcstdc.(module) core.stdc.stdargD header file for C99.
pubs.opengroup.org/onlinepubs/009695399/basedefs/stdarg.h.html, stdarg.h
Source
core/stdc/stdarg.d
stdarg : (alias template) va_end = core.stdc.stdarg.va_end()(va_list ap)End use of ap.
va_end, va_list, (alias template) va_start = core.stdc.stdarg.va_start(T)(out va_list ap, ref T parmn)Initialize ap.
parmn should be the last named parameter.
va_start;
va_list (local variable) core.internal.vararg.sysv_x64.__va_list_tag* apap;
void core.stdc.stdarg.va_start!(const(char)*)(out core.internal.vararg.sysv_x64.__va_list_tag* ap, ref const(char)* parmn) nothrow @nogcInitialize ap.
parmn should be the last named parameter.
va_start((local variable) core.internal.vararg.sysv_x64.__va_list_tag* apap, (parameter) const(char)* formatformat);
scope (exit)
void core.stdc.stdarg.va_end!()(core.internal.vararg.sysv_x64.__va_list_tag* ap) pure nothrow @nogc @safeEnd use of ap.
va_end((local variable) core.internal.vararg.sysv_x64.__va_list_tag* apap);
// On linux-x86_64 `va_list` is `__va_list_tag*` — already the address
// the by-ref request wants.
return cast(int) ulong sanitizers_valgrind_attribution.valgrindClientRequest(ulong defaultResult, ulong request, ulong a1 = 0LU, ulong a2 = 0LU, ulong a3 = 0LU, ulong a4 = 0LU, ulong a5 = 0LU) nothrow @nogc @systemvalgrind's client-request trap, amd64 encoding: the rotation preamble
plus xchg rbx,rbx. Args pointer in RAX, default + result in RDX.
A no-op returning defaultResult when not running under valgrind.
valgrindClientRequest(0, (enum value) sanitizers_valgrind_attribution.VG_USERREQ__PRINTF_VALIST_BY_REF = 5123LUVG_USERREQ__PRINTF_VALIST_BY_REF,
cast(ulong) (parameter) const(char)* formatformat, cast(ulong) (local variable) core.internal.vararg.sysv_x64.__va_list_tag* apap);
}
/// Child: two "tests", each announced by a marker, each committing a
/// distinct memory error (distinct kind AND site, so dedup can't fold).
void void sanitizers_valgrind_attribution.markedTestsDemo()Child
two "tests", each announced by a marker, each committing a
distinct memory error (distinct kind AND site, so dedup can't fold).
markedTestsDemo()
{
import (package) corecore.(package) core.stdcstdc.(module) core.stdc.stdioD header file for C99 <stdio.h>
pubs.opengroup.org/onlinepubs/009695399/basedefs/stdio.h.html, stdio.h
Source
core/stdc/stdio.d
stdio : (alias) printf = int core.stdc.stdio.printf(scope const(char*) format, scope const ...) nothrow @nogcprintf;
import (package) corecore.(package) core.stdcstdc.(module) core.stdc.stdlibD header file for C99.
pubs.opengroup.org/onlinepubs/009695399/basedefs/stdlib.h.html, stdlib.h
Source
core/stdc/stdlib.d
stdlib : (alias) free = void core.stdc.stdlib.free(void* ptr) nothrow @nogcfree, (alias) malloc = void* core.stdc.stdlib.malloc(ulong size) nothrow @nogcmalloc;
int sanitizers_valgrind_attribution.vgPrintf(scope const(char)* format, ...) @systemVALGRIND_PRINTF: emits a <clientmsg> record into the XML stream
(a plain user message in text mode). Returns the byte count printed.
vgPrintf("MARKER test=%d name=%s", 1, "first.invalid.read".(constant) immutable(char)* "first.invalid.read".ptr = "first.invalid.read"ptr);
int* (local variable) int* pp = cast(int*) void* core.stdc.stdlib.malloc(ulong size) nothrow @nogcmalloc(4 * int.(constant) ulong int.sizeof = 4LUsizeof);
(local variable) int* pp[0] = 1;
void core.stdc.stdlib.free(void* ptr) nothrow @nogcfree((local variable) int* pp);
int core.stdc.stdio.printf(scope const(char*) format, scope const ...) nothrow @nogcprintf("uaf value: %d\n", (local variable) int* pp[0]); // test 1's finding: InvalidRead
int sanitizers_valgrind_attribution.vgPrintf(scope const(char)* format, ...) @systemVALGRIND_PRINTF: emits a <clientmsg> record into the XML stream
(a plain user message in text mode). Returns the byte count printed.
vgPrintf("MARKER test=%d name=%s", 2, "second.invalid.write".(constant) immutable(char)* "second.invalid.write".ptr = "second.invalid.write"ptr);
char* (local variable) char* qq = cast(char*) void* core.stdc.stdlib.malloc(ulong size) nothrow @nogcmalloc(8);
(local variable) char* qq[9] = 'x'; // test 2's finding: InvalidWrite (heap overflow)
void core.stdc.stdlib.free(void* ptr) nothrow @nogcfree((local variable) char* qq);
}
int int sanitizers_valgrind_attribution.run()run()
{
import (package) stdstd.(package) std.algorithmalgorithm.(module) std.algorithm.searchingThis is a submodule of std.algorithm.
It contains generic searching algorithms.
Function Name Description all all!"a > 0"([1, 2, 3, 4]) returns true because all elements are positive any any!"a > 0"([1, 2, -3, -4]) returns true because at least one element is positive balancedParens balancedParens("((1 + 1) / 2)", '(', ')') returns true because the string has balanced parentheses. boyerMooreFinder find("hello world", boyerMooreFinder("or")) returns "orld" using the Boyer-Moore algorithm. canFind canFind("hello world", "or") returns true. count Counts all elements or elements matching a predicate, specific element or sub-range.
count([1, 2, 1]) returns 3,
count([1, 2, 1], 1) returns 2 and
count!"a < 0"([1, -3, 0]) returns 1. |
| countUntil | countUntil(a, b) returns the number of steps taken in a to reach b; for example, countUntil("hello!", "o") returns 4. |
| commonPrefix | commonPrefix("parakeet", "parachute") returns "para". |
| endsWith | endsWith("rocks", "ks") returns true. |
| extrema | extrema([2, 1, 3, 5, 4]) returns [1, 5]. |
| find | find("hello world", "or") returns "orld" using linear search. (For binary search refer to SortedRange.) |
| findAdjacent | findAdjacent([1, 2, 3, 3, 4]) returns the subrange starting with two equal adjacent elements, i.e. [3, 3, 4]. |
| findAmong | findAmong("abcd", "qcx") returns "cd" because 'c' is among "qcx". |
| findSkip | If a = "abcde", then findSkip(a, "x") returns false and leaves a unchanged, whereas findSkip(a, "c") advances a to "de" and returns true. |
| findSplit | findSplit("abcdefg", "de") returns a tuple of three ranges "abc", "de", and "fg". |
| findSplitAfter | findSplitAfter("abcdefg", "de") returns a tuple of two ranges "abcde" and "fg". |
| findSplitBefore | findSplitBefore("abcdefg", "de") returns a tuple of two ranges "abc" and "defg". |
| minCount | minCount([2, 1, 1, 4, 1]) returns tuple(1, 3). |
| maxCount | maxCount([2, 4, 1, 4, 1]) returns tuple(4, 2). |
| minElement | Selects the minimal element of a range. minElement([3, 4, 1, 2]) returns 1. |
| maxElement | Selects the maximal element of a range. maxElement([3, 4, 1, 2]) returns 4. |
| minIndex | Index of the minimal element of a range. minIndex([3, 4, 1, 2]) returns 2. |
| maxIndex | Index of the maximal element of a range. maxIndex([3, 4, 1, 2]) returns 1. |
| minPos | minPos([2, 3, 1, 3, 4, 1]) returns the subrange [1, 3, 4, 1], i.e., positions the range at the first occurrence of its minimal element. |
| maxPos | maxPos([2, 3, 1, 3, 4, 1]) returns the subrange [4, 1], i.e., positions the range at the first occurrence of its maximal element. |
| skipOver | Assume a = "blah". Then skipOver(a, "bi") leaves a unchanged and returns false, whereas skipOver(a, "bl") advances a to refer to "ah" and returns true. |
| startsWith | startsWith("hello, world", "hello") returns true. |
| until | Lazily iterates a range until a specific value is found. |
Source
std/algorithm/searching.d
searching : (alias template) canFind = std.algorithm.searching.canFind(alias pred = "a == b")Convenience function. Like find, but only returns whether or not the search
was successful.
For more information about pred see $(LREF find).
See_Also:
$(REF among, std,algorithm,comparison) for checking a value against multiple arguments.
canFind;
import (package) stdstd.(module) std.fileUtilities for manipulating files and scanning directories. Functions
in this module handle files as a unit, e.g., read or write one file
at a time. For opening files and manipulating them via handles refer
to module std.stdio.
Category Functions General exists isDir isFile isSymlink rename thisExePath Directories chdir dirEntries getcwd mkdir mkdirRecurse rmdir rmdirRecurse tempDir Files append copy read readText remove slurp write Symlinks symlink readLink Attributes attrIsDir attrIsFile attrIsSymlink getAttributes getLinkAttributes getSize setAttributes Timestamp getTimes getTimesWin setTimes timeLastModified timeLastAccessed timeStatusChanged Other DirEntry FileException PreserveAttributes SpanMode getAvailableDiskSpace
Source
std/file.d
file : (alias template) exists = std.file.exists(R)(R name) if (isSomeFiniteCharInputRange!R && !isConvertibleToString!R)Determine whether the given file (or directory) _exists.
Params:
name = string or range of characters representing the file _name
Returns:
true if the file name specified as input exists
exists, (alias template) readText = std.file.readText(S = string, R)(auto ref R name) if (isSomeString!S && (isSomeFiniteCharInputRange!R || is(StringTypeOf!R)))Reads and validates (using $(REF validate, std, utf)) a text file. S can be
an array of any character type. However, no width or endian conversions are
performed. So, if the width or endianness of the characters in the given
file differ from the width or endianness of the element type of S, then
validation will fail.
Params:
S = the string type of the file
name = string or range of characters representing the file _name
Returns: Array of characters read.
Throws: $(LREF FileException) if there is an error reading the file,
$(REF UTFException, std, utf) on UTF decoding error.
See_Also: $(REF read, std,file) for reading a binary file.
readText, (alias template) remove = std.file.remove(R)(R name) if (isSomeFiniteCharInputRange!R && !isConvertibleToString!R)Delete file name.
Params:
name = string or range of characters representing the file _name
Throws: $(LREF FileException) on error.
remove, (alias) tempDir = string std.file.tempDir() @trustedReturns the path to a directory for temporary files.
On POSIX platforms, it searches through the following list of directories
and returns the first one which is found to exist:
$(OL
$(LI The directory given by the TMPDIR environment variable.)
$(LI The directory given by the `TEMP` environment variable.)
$(LI The directory given by the TMP environment variable.)
$(LI `/tmp/`)
$(LI /var/tmp/)
$(LI /usr/tmp/)
)
On all platforms, tempDir returns the current working directory on failure.
The return value of the function is cached, so the procedures described
below will only be performed the first time the function is called. All
subsequent runs will return the same string, regardless of whether
environment variables and directory structures have changed in the
meantime.
The POSIX tempDir algorithm is inspired by Python's
$(LINK2 http://docs.python.org/library/tempfile.html#tempfile.tempdir, tempfile.tempdir).
Returns:
On Windows, this function returns the result of calling the Windows API function
$(LINK2 http://msdn.microsoft.com/en-us/library/windows/desktop/aa364992.aspx, GetTempPath).
On POSIX platforms, it searches through the following list of directories
and returns the first one which is found to exist:
$(OL
$(LI The directory given by the `TMPDIR` environment variable.)
$(LI The directory given by the `TEMP` environment variable.)
$(LI The directory given by the `TMP` environment variable.)
$(LI `/tmp`)
$(LI `/var/tmp`)
$(LI `/usr/tmp`)
)
On all platforms, `tempDir` returns `"."` on failure, representing
the current working directory.
tempDir, (alias) thisExePath = string std.file.thisExePath() @trustedReturns the full path of the current executable.
Returns:
The path of the executable as a string.
Throws:
$(REF1 Exception, object)
thisExePath;
import (package) stdstd.(module) std.formatThis package provides string formatting functionality using
printf style format strings.
Submodule Function Name Description package format Converts its arguments according to a format string into a string.
| package |
sformat |
Converts its arguments according to a format string into a buffer. |
| package |
FormatException |
Signals a problem while formatting. |
| write |
formattedWrite |
Converts its arguments according to a format string and writes
the result to an output range. |
| write |
formatValue |
Formats a value of any type according to a format specifier and
writes the result to an output range. |
| read |
formattedRead |
Reads an input range according to a format string and stores the read
values into its arguments. |
| read |
unformatValue |
Reads a value from the given input range and converts it according to
a format specifier. |
| spec |
FormatSpec |
A general handler for format strings. |
| spec |
singleSpec |
Helper function that returns a FormatSpec for a single format specifier. |
Limitation
This package does not support localization, but
adheres to the rounding mode of the floating point unit, if
available.
Format Strings
The functions contained in this package use format strings. A
format string describes the layout of another string for reading or
writing purposes. A format string is composed of normal text
interspersed with format specifiers. A format specifier starts
with a percentage sign '%', optionally followed by one or more
parameters and ends with a format indicator. A format
indicator may be a simple format character or a compound
indicator.
Format strings are composed according to the following grammar:
FormatString:
FormatStringItem FormatString
FormatStringItem:
Character
FormatSpecifier
FormatSpecifier:
'%' Parameters FormatIndicator
FormatIndicator:
FormatCharacter
CompoundIndicator
FormatCharacter:
see remark below
CompoundIndicator:
'(' FormatString '%)'
'(' FormatString '%|' Delimiter '%)'
Delimiter
empty
Character Delimiter
Parameters:
Position Flags Width Precision Separator
Position:
empty
Integer '$'**
*Integer* **':'** *Integer* **'$'
Integer ':' '$'**
*Flags*:
*empty*
*Flag* *Flags*
*Flag*:
**'-'**|**'+'**|**' '**|**'0'**|**'#'**|**'='**
*Width*:
*OptionalPositionalInteger*
*Precision*:
*empty*
**'.'** *OptionalPositionalInteger*
*Separator*:
*empty*
**','** *OptionalInteger*
**','** *OptionalInteger* **'?'**
*OptionalInteger*:
*empty*
*Integer*
**'*'**
*OptionalPositionalInteger*:
*OptionalInteger*
**'*'** *Integer* **'$'
Character
'%%'
AnyCharacterExceptPercent
Integer:
NonZeroDigit Digits
Digits:
empty
Digit Digits
NonZeroDigit:
'1'|'2'|'3'|'4'|'5'|'6'|'7'|'8'|'9'
Digit:
'0'|'1'|'2'|'3'|'4'|'5'|'6'|'7'|'8'|'9'
Note
FormatCharacter is unspecified. It can be any character
that has no other purpose in this grammar, but it is
recommended to assign (lower- and uppercase) letters.
Note
The Parameters of a CompoundIndicator are currently
limited to a '-' flag.
Format Indicator
The format indicator can either be a single character or an
expression surrounded by '%(' and '%)'. It specifies the
basic manner in which a value will be formatted and is the minimum
requirement to format a value.
The following characters can be used as format characters:
FormatCharacter Semantics 's' To be formatted in a human readable format. Can be used with all types. 'c' To be formatted as a character. 'd' To be formatted as a signed decimal integer. 'u' To be formatted as a decimal image of the underlying bit representation. 'b' To be formatted as a binary image of the underlying bit representation. 'o' To be formatted as an octal image of the underlying bit representation. 'x' / 'X' To be formatted as a hexadecimal image of the underlying bit representation. 'e' / 'E' To be formatted as a real number in decimal scientific notation. 'f' / 'F' To be formatted as a real number in decimal natural notation. 'g' / 'G' To be formatted as a real number in decimal short notation. Depending on the number, a scientific notation or a natural notation is used. 'a' / 'A' To be formatted as a real number in hexadecimal scientific notation. 'r' To be formatted as raw bytes. The output may not be printable and depends on endianness.
The compound indicator can be used to describe compound types
like arrays or structs in more detail. A compound type is enclosed
within '%(' and '%)'. The enclosed sub-format string is
applied to individual elements. The trailing portion of the
sub-format string following the specifier for the element is
interpreted as the delimiter, and is therefore omitted following the
last element. The '%|' specifier may be used to explicitly
indicate the start of the delimiter, so that the preceding portion of
the string will be included following the last element.
The format string inside of the compound indicator should
contain exactly one format specifier (two in case of associative
arrays), which specifies the formatting mode of the elements of the
compound type. This format specifier can be a compound
indicator itself.
Note
Inside a compound indicator, strings and characters are
escaped automatically. To avoid this behavior, use "%-("
instead of "%(".
Flags
There are several flags that affect the outcome of the formatting.
Flag Semantics '-' When the formatted result is shorter than the value given by the width parameter, the output is left justified. Without the '-' flag, the output remains right justified.
There are two exceptions where the '-' flag has a
different meaning: (1) with 'r' it denotes to use little
endian and (2) in case of a compound indicator it means that
no special handling of the members is applied. |
| '=' |
When the formatted result is shorter than the value
given by the width parameter, the output is centered.
If the central position is not possible it is moved slightly
to the right. In this case, if '-' flag is present in
addition to the '=' flag, it is moved slightly to the left. |
| '+' / *' '* |
Applies to numerical values. By default, positive numbers are not
formatted to include the + sign. With one of these two flags present,
positive numbers are preceded by a plus sign or a space.
When both flags are present, a plus sign is used.
In case of 'r', a big endian format is used. |
| '0' |
Is applied to numerical values that are printed right justified.
If the zero flag is present, the space left to the number is
filled with zeros instead of spaces. |
| '#' |
Denotes that an alternative output must be used. This depends on the type
to be formatted and the format character used. See the
sections below for more information. |
Width, Precision and Separator
The width parameter specifies the minimum width of the result.
The meaning of precision depends on the format indicator. For
integers it denotes the minimum number of digits printed, for
real numbers it denotes the number of fractional digits and for
strings and compound types it denotes the maximum number of elements
that are included in the output.
A separator is used for formatting numbers. If it is specified,
the output is divided into chunks of three digits, separated by a ','. The number of digits in a chunk can be given explicitly by
providing a number or a ''* after the ','.
In all three cases the number of digits can be replaced by a ''*. In this scenario, the next argument is used as the number of
digits. If the argument is a negative number, the precision and
separator parameters are considered unspecified. For width,
the absolute value is used and the '-' flag is set.
The separator can also be followed by a '?'. In that case,
an additional argument is used to specify the symbol that should be
used to separate the chunks.
Position
By default, the arguments are processed in the provided order. With
the position parameter it is possible to address arguments
directly. It is also possible to denote a series of arguments with
two numbers separated by ':', that are all processed in the same
way. The second number can be omitted. In that case the series ends
with the last argument.
It's also possible to use positional arguments for width, precision and separator by adding a number and a '$' after the ''*.
Types
This section describes the result of combining types with format
characters. It is organized in 2 subsections: a list of general
information regarding the formatting of types in the presence of
format characters and a table that contains details for every
available combination of type and format character.
When formatting types, the following rules apply:
If the format character is upper case, the resulting string will
be formatted using upper case letters.
The default precision for floating point numbers is 6 digits.
Rounding of floating point numbers adheres to the rounding mode
of the floating point unit, if available.
The floating point values NaN and Infinity are formatted as
nan and inf, possibly preceded by '+' or '-' sign.
Formatting reals is only supported for 64 bit reals and 80 bit reals.
All other reals are cast to double before they are formatted. This will
cause the result to be inf for very large numbers.
Characters and strings formatted with the 's' format character
inside of compound types are surrounded by single and double quotes
and unprintable characters are escaped. To avoid this, a '-'
flag can be specified for the compound specifier
(e.g. "%-(%s%)" instead of "%(%s%)" ).
Structs, unions, classes and interfaces are formatted by calling a
toString method if available.
See module std.format.write for more
details.
Only part of these combinations can be used for reading. See
module std.format.read for more
detailed information.
This table contains descriptions for every possible combination of
type and format character:
<th scope="col" width="20%">Type</th> <th scope="col" width="20%">Format Character</th> Formatted as... <td rowspan="1">null</td> 's' null
|<td rowspan="3">bool</td> 's' |
false or true |
| 'b', 'd', 'o', 'u', 'x', 'X' |
As the integrals 0 or 1 with the same format character.
Please note, that 'o' and 'x' with '#' flag
might produce unexpected results due to special handling of
the value 0. |
| 'r' |
\0 or \1 |
|<td rowspan="4">Integral</td> 's', 'd' |
A signed decimal number. The '#' flag is ignored. |
| 'b', 'o', 'u', 'x', 'X' |
An unsigned binary, decimal, octal or hexadecimal number.
In case of 'o' and 'x', the '#' flag
denotes that the number must be preceded by 0 and 0x, with
the exception of the value 0, where this does not apply. For
'b' and 'u' the '#' flag has no effect. |
| 'e', 'E', 'f', 'F', 'g', 'G', 'a', 'A' |
As a floating point value with the same specifier.
Default precision is large enough to add all digits
of the integral value.
In case of 'a' and 'A', the integral digit can be
any hexadecimal digit.
|
| 'r' |
Characters taken directly from the binary representation. |
|<td rowspan="5">Floating Point</td> 'e', 'E' |
Scientific notation: Exactly one integral digit followed by a dot
and fractional digits, followed by the exponent.
The exponent is formatted as 'e' followed by
a '+' or '-' sign, followed by at least
two digits.
When there are no fractional digits and the '#' flag
is not present, the dot is omitted. |
| 'f', 'F' |
Natural notation: Integral digits followed by a dot and
fractional digits.
When there are no fractional digits and the '#' flag
is not present, the dot is omitted.
Please note: the difference between 'f' and 'F'
is only visible for NaN and Infinity. |
| 's', 'g', 'G' |
Short notation: If the absolute value is larger than 10 ^^ precision
or smaller than 0.0001, the scientific notation is used.
If not, the natural notation is applied.
In both cases precision denotes the count of all digits, including
the integral digits. Trailing zeros (including a trailing dot) are removed.
If '#' flag is present, trailing zeros are not removed. |
| 'a', 'A' |
Hexadecimal scientific notation: 0x followed by 1
(or 0 in case of value zero or denormalized number)
followed by a dot, fractional digits in hexadecimal
notation and an exponent. The exponent is build by p,
followed by a sign and the exponent in decimal notation.
When there are no fractional digits and the '#' flag
is not present, the dot is omitted. |
| 'r' |
Characters taken directly from the binary representation. |
|<td rowspan="3">Character</td> 's', 'c' |
As the character.
Inside of a compound indicator 's' is treated differently: The
character is surrounded by single quotes and non printable
characters are escaped. This can be avoided by preceding
the compound indicator with a '-' flag
(e.g. "%-(%s%)"). |
| 'b', 'd', 'o', 'u', 'x', 'X' |
As the integral that represents the character. |
| 'r' |
Characters taken directly from the binary representation. |
|<td rowspan="3">String</td> 's' |
The sequence of characters that form the string.
Inside of a compound indicator the string is surrounded by double quotes
and non printable characters are escaped. This can be avoided
by preceding the compound indicator with a '-' flag
(e.g. "%-(%s%)"). |
| 'r' |
The sequence of characters, each formatted with 'r'. |
| compound |
As an array of characters. |
|<td rowspan="3">Array</td> 's' |
When the elements are characters, the array is formatted as
a string. In all other cases the array is surrounded by square brackets
and the elements are separated by a comma and a space. If the elements
are strings, they are surrounded by double quotes and non
printable characters are escaped. |
| 'r' |
The sequence of the elements, each formatted with 'r'. |
| compound |
The sequence of the elements, each formatted according to the specifications
given inside of the compound specifier. |
|<td rowspan="2">Associative Array</td> 's' |
As a sequence of the elements in unpredictable order. The output is
surrounded by square brackets. The elements are separated by a
comma and a space. The elements are formatted as key:value. |
| compound |
As a sequence of the elements in unpredictable order. Each element
is formatted according to the specifications given inside of the
compound specifier. The first specifier is used for formatting
the key and the second specifier is used for formatting the value.
The order can be changed with positional arguments. For example
"%(%2$s (%1$s), %)" will write the value, followed by the key in
parenthesis. |
|<td rowspan="2">Enum</td> 's' |
The name of the value. If the name is not available, the base value
is used, preceeded by a cast. |
| All, but 's' |
Enums can be formatted with all format characters that can be used
with the base value. In that case they are formatted like the base value. |
|<td rowspan="3">Input Range</td> 's' |
When the elements of the range are characters, they are written like a string.
In all other cases, the elements are enclosed by square brackets and separated
by a comma and a space. |
| 'r' |
The sequence of the elements, each formatted with 'r'. |
| compound |
The sequence of the elements, each formatted according to the specifications
given inside of the compound specifier. |
|<td rowspan="1">Struct</td> 's' |
When the struct has neither an applicable toString
nor is an input range, it is formatted as follows:
StructType(field1, field2, ...). |
|<td rowspan="1">Class</td> 's' |
When the class has neither an applicable toString
nor is an input range, it is formatted as the
fully qualified name of the class. |
|<td rowspan="1">Union</td> 's' |
When the union has neither an applicable toString
nor is an input range, it is formatted as its base name. |
|<td rowspan="2">Pointer</td> 's' |
A null pointer is formatted as 'null'. All other pointers are
formatted as hexadecimal numbers with the format character 'X'. |
| 'x', 'X' |
Formatted as a hexadecimal number. |
|<td rowspan="3">SIMD vector</td> 's' |
The array is surrounded by square brackets
and the elements are separated by a comma and a space. |
| 'r' |
The sequence of the elements, each formatted with 'r'. |
| compound |
The sequence of the elements, each formatted according to the specifications
given inside of the compound specifier. |
|<td rowspan="1">Delegate</td> 's', 'r', compound |
As the .stringof of this delegate treated as a string.
Please note: The implementation is currently buggy
and its use is discouraged. |
Source
std/format/package.d
Examples
Simple use:
// Easiest way is to use `%s` everywhere:
assert(format("I got %s %s for %s euros.", 30, "eggs", 5.27) == "I got 30 eggs for 5.27 euros.");
// Other format characters provide more control:
assert(format("I got %b %(%X%) for %f euros.", 30, "eggs", 5.27) == "I got 11110 65676773 for 5.270000 euros.");
Compound specifiers allow formatting arrays and other compound types:
/*
The trailing end of the sub-format string following the specifier for
each item is interpreted as the array delimiter, and is therefore
omitted following the last array item:
*/
assert(format("My items are %(%s %).", [1,2,3]) == "My items are 1 2 3.");
assert(format("My items are %(%s, %).", [1,2,3]) == "My items are 1, 2, 3.");
/*
The "%|" delimiter specifier may be used to indicate where the
delimiter begins, so that the portion of the format string prior to
it will be retained in the last array element:
*/
assert(format("My items are %(-%s-%|, %).", [1,2,3]) == "My items are -1-, -2-, -3-.");
/*
These compound format specifiers may be nested in the case of a
nested array argument:
*/
auto mat = [[1, 2, 3],
[4, 5, 6],
[7, 8, 9]];
assert(format("%(%(%d %) - %)", mat), "1 2 3 - 4 5 6 - 7 8 9");
assert(format("[%(%(%d %) - %)]", mat), "[1 2 3 - 4 5 6 - 7 8 9]");
assert(format("[%([%(%d %)]%| - %)]", mat), "[1 2 3] - [4 5 6] - [7 8 9]");
/*
Strings and characters are escaped automatically inside compound
format specifiers. To avoid this behavior, use "%-(" instead of "%(":
*/
assert(format("My friends are %s.", ["John", "Nancy"]) == `My friends are ["John", "Nancy"].`);
assert(format("My friends are %(%s, %).", ["John", "Nancy"]) == `My friends are "John", "Nancy".`);
assert(format("My friends are %-(%s, %).", ["John", "Nancy"]) == `My friends are John, Nancy.`);
Using parameters:
// Flags can be used to influence to outcome:
assert(format("%g != %+#g", 3.14, 3.14) == "3.14 != +3.14000");
// Width and precision help to arrange the formatted result:
assert(format(">%10.2f<", 1234.56789) == "> 1234.57<");
// Numbers can be grouped:
assert(format("%,4d", int.max) == "21,4748,3647");
// It's possible to specify the position of an argument:
assert(format("%3$s %1$s", 3, 17, 5) == "5 3");
Providing parameters as arguments:
// Width as argument
assert(format(">%*s<", 10, "abc") == "> abc<");
// Precision as argument
assert(format(">%.*f<", 5, 123.2) == ">123.20000<");
// Grouping as argument
assert(format("%,*d", 1, int.max) == "2,1,4,7,4,8,3,6,4,7");
// Grouping separator as argument
assert(format("%,3?d", '_', int.max) == "2_147_483_647");
// All at once
assert(format("%*.*,*?d", 20, 15, 6, '/', int.max) == " 000/002147/483647");
format : (alias template) format = std.format.format(Char, Args...)(in Char[] fmt, Args args) if (isSomeChar!Char)Converts its arguments according to a format string into a string.
The second version of format takes the format string as template
argument. In this case, it is checked for consistency at
compile-time and produces slightly faster code, because the length of
the output buffer can be estimated in advance.
Params:
fmt = a $(MREF_ALTTEXT format string, std,format)
args = a variadic list of arguments to be formatted
Char = character type of fmt
Args = a variadic list of types of the arguments
Returns:
The formatted string.
Throws:
A $(LREF FormatException) if formatting did not succeed.
See_Also:
$(LREF sformat) for a variant, that tries to avoid garbage collection.
format;
import (package) stdstd.(module) std.pathThis module is used to manipulate path strings.
All functions, with the exception of expandTilde (and in some
cases absolutePath and relativePath), are pure
string manipulation functions; they don't depend on any state outside
the program, nor do they perform any actual file system actions.
This has the consequence that the module does not make any distinction
between a path that points to a directory and a path that points to a
file, and it does not know whether or not the object pointed to by the
path actually exists in the file system.
To differentiate between these cases, use isDir and
exists.
Note that on Windows, both the backslash (\) and the slash (/)
are in principle valid directory separators. This module treats them
both on equal footing, but in cases where a new separator is
added, a backslash will be used. Furthermore, the buildNormalizedPath
function will replace all slashes with backslashes on that platform.
In general, the functions in this module assume that the input paths
are well-formed. (That is, they should not contain invalid characters,
they should follow the file system's path format, etc.) The result
of calling a function on an ill-formed path is undefined. When there
is a chance that a path or a file name is invalid (for instance, when it
has been input by the user), it may sometimes be desirable to use the
isValidFilename and isValidPath functions to check
this.
Most functions do not perform any memory allocations, and if a string is
returned, it is usually a slice of an input string. If a function
allocates, this is explicitly mentioned in the documentation.
Category Functions Normalization absolutePath asAbsolutePath asNormalizedPath asRelativePath buildNormalizedPath buildPath chainPath expandTilde Partitioning baseName dirName dirSeparator driveName pathSeparator pathSplitter relativePath rootName stripDrive Validation isAbsolute isDirSeparator isRooted isValidFilename isValidPath Extension defaultExtension extension setExtension stripExtension withDefaultExtension withExtension Other filenameCharCmp filenameCmp globMatch CaseSensitive
Source
std/path.d
path : (alias template) buildPath = std.path.buildPath(Range)(scope Range segments) if (isInputRange!Range && !isInfinite!Range && isSomeString!(ElementType!Range))Combines one or more path segments.
This function takes a set of path segments, given as an input
range of string elements or as a set of string arguments,
and concatenates them with each other. Directory separators
are inserted between segments if necessary. If any of the
path segments are absolute (as defined by $(LREF isAbsolute)), the
preceding segments will be dropped.
On Windows, if one of the path segments are rooted, but not absolute
(e.g. $(D `\foo`)), all preceding path segments down to the previous
root will be dropped. (See below for an example.)
This function always allocates memory to hold the resulting path.
The variadic overload is guaranteed to only perform a single
allocation, as is the range version if `paths` is a forward
range.
Params:
segments = An $(REF_ALTTEXT input range, isInputRange, std,range,primitives)
of segments to assemble the path from.
Returns: The assembled path.
buildPath;
import (package) stdstd.(module) std.processFunctions for starting and interacting with other processes, and for
working with the current process' execution environment.
Process handling
`spawnProcess` spawns a new `process`, optionally assigning it an
arbitrary set of standard input, output, and error streams.
The function returns immediately, leaving the child process to execute
in parallel with its parent. All other functions in this module that
spawn processes are built around spawnProcess.
`wait` makes the parent `process` wait for a child `process` to
terminate. In general one should always do this, to avoid
child processes becoming "zombies" when the parent process exits.
Scope guards are perfect for this – see the spawnProcess
documentation for examples. tryWait is similar to wait,
but does not block if the process has not yet terminated.
`pipeProcess` also spawns a child `process` which runs
in parallel with its parent. However, instead of taking
arbitrary streams, it automatically creates a set of
pipes that allow the parent to communicate with the child
through the child's standard input, output, and/or error streams.
This function corresponds roughly to C's popen function.
`execute` starts a new `process` and waits for it
to complete before returning. Additionally, it captures
the process' standard output and error streams and returns
the output of these as a string.
`spawnShell`, `pipeShell` and `executeShell` work like
spawnProcess, pipeProcess and execute, respectively,
except that they take a single command string and run it through
the current user's default command interpreter.
executeShell corresponds roughly to C's system function.
`kill` attempts to terminate a running `process`.
The following table compactly summarises the different process creation
functions and how they relate to each other:
Runs program directly
Runs shell command Low-level process creation spawnProcess spawnShell Automatic input/output redirection using pipes pipeProcess pipeShell Execute and wait for completion, collect output execute executeShell
Other functionality
`pipe` is used to create unidirectional pipes.
`environment` is an interface through which the current `process`'
environment variables can be read and manipulated.
`escapeShellCommand` and `escapeShellFileName` are useful
for constructing shell command lines in a portable way.
Source
std/process.d
Note
Most of the functionality in this module is not available on iOS, tvOS
and watchOS. The only functions available on those platforms are:
environment, thisProcessID and thisThreadID.
process : (class) std.process.environmentManipulates environment variables using an associative-array-like
interface.
This class contains only static methods, and cannot be instantiated.
See below for examples of use.
environment, (alias) execute = std.typecons.Tuple!(int, "status", string, "output") std.process.execute(scope const(char[])[] args, const(string[string]) env = cast(const(string[string]))null, std.process.Config config = Config(Flags.none, null, null), ulong maxOutput = 18446744073709551615LU, scope const(char)[] workDir = null) @safeExecutes the given program or shell command and returns its exit
code and output.
execute and executeShell start a new process using
$(LREF spawnProcess) and $(LREF spawnShell), respectively, and wait
for the process to complete before returning. The functions capture
what the child process prints to both its standard output and
standard error streams, and return this together with its exit code.
auto dmd = execute("dmd", "myapp.d");
if (dmd.status != 0) writeln("Compilation failed:\n", dmd.output);
auto ls = executeShell("ls -l");
if (ls.status != 0) writeln("Failed to retrieve file listing");
else writeln(ls.output);
The args/program/command, env and config
parameters are forwarded straight to the underlying spawn functions,
and we refer to their documentation for details.
Params:
args = An array which contains the program name as the zeroth element
and any command-line arguments in the following elements.
(See $(LREF spawnProcess) for details.)
program = The program name, $(I without) command-line arguments.
(See $(LREF spawnProcess) for details.)
command = A shell command which is passed verbatim to the command
interpreter. (See $(LREF spawnShell) for details.)
env = Additional environment variables for the child process.
(See $(LREF spawnProcess) for details.)
config = Flags that control process creation. See $(LREF Config)
for an overview of available flags, and note that the
retainStd... flags have no effect in this function.
maxOutput = The maximum number of bytes of output that should be
captured.
workDir = The working directory for the new process.
By default the child process inherits the parent's working
directory.
shellPath = The path to the shell to use to run the specified program.
By default this is $(LREF nativeShell).
Returns:
An $(D std.typecons.Tuple!(int, "status", string, "output")).
POSIX_specific:
If the process is terminated by a signal, the status field of
the return value will contain a negative number whose absolute
value is the signal number. (See $(LREF wait) for details.)
Throws:
$(LREF ProcessException) on failure to start the process.$(BR)
$(REF StdioException, std,stdio) on failure to capture output.
execute, (alias) thisProcessID = int std.process.thisProcessID() nothrow @nogc @property @trustedReturns the process ID of the current process,
which is guaranteed to be unique on the system.
Example:
writefln("Current process ID: %d", thisProcessID);
---
thisProcessID;
import (package) stdstd.(module) std.stringString handling functions.
Category Functions Searching column indexOf indexOfAny indexOfNeither lastIndexOf lastIndexOfAny lastIndexOfNeither Comparison isNumeric Mutation capitalize Pruning and Filling center chomp chompPrefix chop detabber detab entab entabber leftJustify outdent rightJustify strip stripLeft stripRight wrap Substitution abbrev soundex soundexer succ tr translate Miscellaneous assumeUTF fromStringz lineSplitter representation splitLines toStringz Objects of types string, wstring, and dstring are value types and cannot be mutated element-by-element. For using mutation during building strings, use char[], wchar[], or dchar[]. The xxxstring types are preferable because they don't exhibit undesired aliasing, thus making code more robust.
The following functions are publicly imported:
Module Functions Publicly imported functions std.algorithm cmp, std,algorithm,comparison count, std,algorithm,searching endsWith, std,algorithm,searching startsWith, std,algorithm,searching std.array join, std,array replace, std,array replaceInPlace, std,array split, std,array empty, std,array std.format format, std,format sformat, std,format std.uni icmp, std,uni toLower, std,uni toLowerInPlace, std,uni toUpper, std,uni toUpperInPlace, std,uni There is a rich set of functions for string handling defined in other modules. Functions related to Unicode and ASCII are found in std.uni and std.ascii, respectively. Other functions that have a wider generality than just strings can be found in std.algorithm and std.range.
Source
std/string.d
string : (alias template) indexOf = std.string.indexOf(Range)(Range s, dchar c, CaseSensitive cs = Yes.caseSensitive) if (isInputRange!Range && isSomeChar!(ElementType!Range) && !isSomeString!Range)Searches for a character in a string or range.
Params:
s = string or InputRange of characters to search for `c` in
c = character to search for in `s`
startIdx = index to a well-formed code point in `s` to start
searching from; defaults to 0
cs = specifies whether comparisons are case-sensitive
(`Yes.caseSensitive`) or not (`No.caseSensitive`).
Returns:
If `c` is found in `s`, then the index of its first occurrence is
returned. If `c` is not found or `startIdx` is greater than or equal to
`s.length`, then -1 is returned. If the parameters are not valid UTF,
the result will still be either -1 or in the range [`startIdx` ..
`s.length`], but will not be reliable otherwise.
Throws:
If the sequence starting at `startIdx` does not represent a well-formed
code point, then a $(REF UTFException, std,utf) may be thrown.
See_Also: $(REF countUntil, std,algorithm,searching)
indexOf;
version (D_InlineAsm_X86_64D_InlineAsm_X86_64)
{
}
else
{
writefln("SKIP: the hand-rolled client request needs x86_64 inline asm");
return 0;
}
if ((class) std.process.environmentManipulates environment variables using an associative-array-like
interface.
This class contains only static methods, and cannot be instantiated.
See below for examples of use.
environment.string std.process.environment.get(scope const(char)[] name, string defaultValue = null) @safeRetrieves the value of the environment variable with the given name,
or a default value if the variable doesn't exist.
Unlike environment.opIndex, this function never throws on Posix.
auto sh = environment.get("SHELL", "/bin/sh");
This function is also useful in checking for the existence of an
environment variable.
auto myVar = environment.get("MYVAR");
if (myVar is null)
{
// Environment variable doesn't exist.
// Note that we have to use 'is' for the comparison, since
// myVar == null is also true if the variable exists but is
// empty.
}
get((constant) string sanitizers_valgrind_attribution.childEnvVar = "SANITIZERS_PROBE_CHILD"childEnvVar) == "valgrind-markers")
{
if (ulong sanitizers_valgrind_attribution.valgrindClientRequest(ulong defaultResult, ulong request, ulong a1 = 0LU, ulong a2 = 0LU, ulong a3 = 0LU, ulong a4 = 0LU, ulong a5 = 0LU) nothrow @nogc @systemvalgrind's client-request trap, amd64 encoding: the rotation preamble
plus xchg rbx,rbx. Args pointer in RAX, default + result in RDX.
A no-op returning defaultResult when not running under valgrind.
valgrindClientRequest(0, (enum value) sanitizers_valgrind_attribution.VG_USERREQ__RUNNING_ON_VALGRIND = 4097LUVG_USERREQ__RUNNING_ON_VALGRIND) == 0)
{
void std.stdio.writefln!char(in char[] fmt) @safeEquivalent to writef(fmt, args, '\n').
writefln("child not under valgrind?");
return 1;
}
void sanitizers_valgrind_attribution.markedTestsDemo()Child
two "tests", each announced by a marker, each committing a
distinct memory error (distinct kind AND site, so dedup can't fold).
markedTestsDemo();
return 0;
}
(alias) object.string = stringstring (local variable) string whyNotUsablewhyNotUsable;
if (!bool valgrind_helpers.valgrindCanInstrument(out string reason)Whether valgrind can actually instrument a program here — not merely
whether it answers --version.
The launcher answering a version string proves only that it is on PATH. On
CircleCI's AWS machine executor (kernel 6.14-aws) valgrind 3.26 answers
--version, emits its full XML preamble, and then wedges: the
memcheck-amd64- process sleeps in do_wait forever. A version-only probe
reads that as healthy and sends an example into a hang instead of the skip
it was designed to take.
So instrument something trivial under a deadline. true is the cheapest
guest there is, and a valgrind that cannot finish it in
valgrindProbeDeadline cannot run these examples either. The deadline
is what turns a wedged valgrind into a SKIP rather than a hang —
std.process.execute has no timeout, which is why this goes through
executeMonitored instead.
valgrindCanInstrument((local variable) string whyNotUsablewhyNotUsable))
{
void std.stdio.writefln!(char, string)(in char[] fmt, string __param_1) @safeEquivalent to writef(fmt, args, '\n').
writefln("SKIP: %s", (local variable) string whyNotUsablewhyNotUsable);
return 0;
}
const (local variable) const(string) xmlFilexmlFile = string std.path.buildPath!char(const(char)[][] paths...) pure nothrow @safeCombines one or more path segments.
This function takes a set of path segments, given as an input
range of string elements or as a set of string arguments,
and concatenates them with each other. Directory separators
are inserted between segments if necessary. If any of the
path segments are absolute (as defined by isAbsolute), the
preceding segments will be dropped.
On Windows, if one of the path segments are rooted, but not absolute
(e.g. \foo), all preceding path segments down to the previous
root will be dropped. (See below for an example.)
This function always allocates memory to hold the resulting path.
The variadic overload is guaranteed to only perform a single
allocation, as is the range version if paths is a forward
range.
Examples
version (Posix)
{
assert(buildPath("foo", "bar", "baz") == "foo/bar/baz");
assert(buildPath("/foo/", "bar/baz") == "/foo/bar/baz");
assert(buildPath("/foo", "/bar") == "/bar");
}
version (Windows)
{
assert(buildPath("foo", "bar", "baz") == `foo\bar\baz`);
assert(buildPath(`c:\foo`, `bar\baz`) == `c:\foo\bar\baz`);
assert(buildPath("foo", `d:\bar`) == `d:\bar`);
assert(buildPath("foo", `\bar`) == `\bar`);
assert(buildPath(`c:\foo`, `\bar`) == `c:\bar`);
}
buildPath(string std.file.tempDir() @trustedReturns the path to a directory for temporary files.
On POSIX platforms, it searches through the following list of directories
and returns the first one which is found to exist:
The directory given by the TMPDIR environment variable.
The directory given by the TEMP environment variable.
The directory given by the TMP environment variable.
/tmp/
/var/tmp/
/usr/tmp/
On all platforms, tempDir returns the current working directory on failure.
The return value of the function is cached, so the procedures described
below will only be performed the first time the function is called. All
subsequent runs will return the same string, regardless of whether
environment variables and directory structures have changed in the
meantime.
The POSIX tempDir algorithm is inspired by Python's
tempfile.tempdir.
Examples
import std.ascii : letters;
import std.conv : to;
import std.path : buildPath;
import std.random : randomSample;
import std.utf : byCodeUnit;
// random id with 20 letters
auto id = letters.byCodeUnit.randomSample(20).to!string;
auto myFile = tempDir.buildPath(id ~ "my_tmp_file");
scope(exit) myFile.remove;
myFile.write("hello");
assert(myFile.readText == "hello");
tempDir, string std.format.format!("vg-attribution-%d.xml", int)(int __param_0) pure @safeExamples
The format string can be checked at compile-time:
auto s = format!"%s is %s"("Pi", 3.14);
assert(s == "Pi is 3.14");
// This line doesn't compile, because 3.14 cannot be formatted with %d:
// s = format!"%s is %d"("Pi", 3.14);
format!"vg-attribution-%d.xml"(int std.process.thisProcessID() nothrow @nogc @property @trustedReturns the process ID of the current process,
which is guaranteed to be unique on the system.
Example
writefln("Current process ID: %d", thisProcessID);
thisProcessID));
scope (exit)
if ((local variable) const(string) xmlFilexmlFile.bool std.file.exists!string(string name) nothrow @nogc @safeDetermine whether the given file (or directory) exists.
exists)
(local variable) const(string) xmlFilexmlFile.void std.file.remove!string(string name) @safeDelete file name.
remove();
const (local variable) const(std.typecons.Tuple!(int, "status", string, "output")) childchild = std.typecons.Tuple!(int, "status", string, "output") std.process.execute(scope const(char[])[] args, const(string[string]) env = cast(const(string[string]))null, std.process.Config config = Config(Flags.none, null, null), ulong maxOutput = 18446744073709551615LU, scope const(char)[] workDir = null) @safeExecutes the given program or shell command and returns its exit
code and output.
execute and executeShell start a new process using
spawnProcess and spawnShell, respectively, and wait
for the process to complete before returning. The functions capture
what the child process prints to both its standard output and
standard error streams, and return this together with its exit code.
auto dmd = execute(["dmd", "myapp.d"]);
if (dmd.status != 0) writeln("Compilation failed:\n", dmd.output);
auto ls = executeShell("ls -l");
if (ls.status != 0) writeln("Failed to retrieve file listing");
else writeln(ls.output);
The args/program/command, env and config
parameters are forwarded straight to the underlying spawn functions,
and we refer to their documentation for details.
POSIX specific
If the process is terminated by a signal, the status field of
the return value will contain a negative number whose absolute
value is the signal number. (See wait for details.)
execute(
[
"valgrind", "--xml=yes", "--xml-file=" ~ (local variable) const(string) xmlFilexmlFile,
"--error-exitcode=99", string std.file.thisExePath() @trustedReturns the full path of the current executable.
Examples
import std.path : isAbsolute;
auto path = thisExePath();
assert(path.exists);
assert(path.isAbsolute);
assert(path.isFile);
thisExePath
],
[(constant) string sanitizers_valgrind_attribution.childEnvVar = "SANITIZERS_PROBE_CHILD"childEnvVar: "valgrind-markers"]);
assert((local variable) const(std.typecons.Tuple!(int, "status", string, "output")) childchild.status == 99,
string std.format.format!("expected exit 99 from --error-exitcode, got %d", const(int))(const(int) __param_0) pure @safeExamples
The format string can be checked at compile-time:
auto s = format!"%s is %s"("Pi", 3.14);
assert(s == "Pi is 3.14");
// This line doesn't compile, because 3.14 cannot be formatted with %d:
// s = format!"%s is %d"("Pi", 3.14);
format!"expected exit 99 from --error-exitcode, got %d"((local variable) const(std.typecons.Tuple!(int, "status", string, "output")) childchild.status));
const (local variable) const(string) xmlxml = string std.file.readText!(string, const(string))(ref const(string) name) @safeReads and validates (using validate) a text file. S can be
an array of any character type. However, no width or endian conversions are
performed. So, if the width or endianness of the characters in the given
file differ from the width or endianness of the element type of S, then
validation will fail.
Examples
Read file with UTF-8 text.
write(deleteme, "abc"); // deleteme is the name of a temporary file
scope(exit) remove(deleteme);
string content = readText(deleteme);
assert(content == "abc");
readText((local variable) const(string) xmlFilexmlFile);
// The four records, in stream order: marker 1, its error, marker 2,
// its error. `indexOf` positions prove the interleaving.
const (local variable) const(long) m1m1 = (local variable) const(string) xmlxml.long std.string.indexOf!(const(string), char)(ref const(string) s, const(char)[] sub) pure nothrow @nogc @safeindexOf("MARKER test=1 name=first.invalid.read");
const (local variable) const(long) e1e1 = (local variable) const(string) xmlxml.long std.string.indexOf!(const(string), char)(ref const(string) s, const(char)[] sub) pure nothrow @nogc @safeindexOf("<kind>InvalidRead</kind>");
const (local variable) const(long) m2m2 = (local variable) const(string) xmlxml.long std.string.indexOf!(const(string), char)(ref const(string) s, const(char)[] sub) pure nothrow @nogc @safeindexOf("MARKER test=2 name=second.invalid.write");
const (local variable) const(long) e2e2 = (local variable) const(string) xmlxml.long std.string.indexOf!(const(string), char)(ref const(string) s, const(char)[] sub) pure nothrow @nogc @safeindexOf("<kind>InvalidWrite</kind>");
assert((local variable) const(long) m1m1 >= 0, "marker 1 missing — <clientmsg> not in the XML stream?");
assert((local variable) const(long) e1e1 >= 0, "InvalidRead error missing");
assert((local variable) const(long) m2m2 >= 0, "marker 2 missing");
assert((local variable) const(long) e2e2 >= 0, "InvalidWrite error missing");
assert((local variable) const(long) m1m1 < (local variable) const(long) e1e1 && (local variable) const(long) e1e1 < (local variable) const(long) m2m2 && (local variable) const(long) m2m2 < (local variable) const(long) e2e2,
string std.format.format!("stream order violated: m1=%d e1=%d m2=%d e2=%d", const(long), const(long), const(long), const(long))(const(long) __param_0, const(long) __param_1, const(long) __param_2, const(long) __param_3) pure @safeExamples
The format string can be checked at compile-time:
auto s = format!"%s is %s"("Pi", 3.14);
assert(s == "Pi is 3.14");
// This line doesn't compile, because 3.14 cannot be formatted with %d:
// s = format!"%s is %d"("Pi", 3.14);
format!"stream order violated: m1=%d e1=%d m2=%d e2=%d"((local variable) const(long) m1m1, (local variable) const(long) e1e1, (local variable) const(long) m2m2, (local variable) const(long) e2e2));
void std.stdio.writefln!(char, const(long), const(long), const(long), const(long))(in char[] fmt, const(long) __param_1, const(long) __param_2, const(long) __param_3, const(long) __param_4) @safeEquivalent to writef(fmt, args, '\n').
writefln("stream order: clientmsg(test=1) @%d < error(InvalidRead) @%d "
~ "< clientmsg(test=2) @%d < error(InvalidWrite) @%d", (local variable) const(long) m1m1, (local variable) const(long) e1e1, (local variable) const(long) m2m2, (local variable) const(long) e2e2);
void std.stdio.writefln!char(in char[] fmt) @safeEquivalent to writef(fmt, args, '\n').
writefln("PASS: VALGRIND_PRINTF markers segment one process's XML error "
~ "stream by test — marker-window attribution is viable");
return 0;
}
}
int int D main()main()
{
version (linuxlinux)
return int sanitizers_valgrind_attribution.run()run();
else
{
import std.stdio : writefln;
writefln("SKIP: valgrind probes are Linux-only here");
return 0;
}
}