summary refs log blame commit diff stats
path: root/tests/mmaptest.nim
blob: c304920af54bcf69774a5532efcd1eccabad24b8 (plain) (tree) 
7efe817ca ^
















































1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
















































                                                                            
# Small test program to test for mmap() weirdnesses

include "lib/system/ansi_c"

const
  PageSize = 4096
  PROT_READ  = 1             # page can be read 
  PROT_WRITE = 2             # page can be written 
  MAP_PRIVATE = 2            # Changes are private 

when defined(macosx) or defined(bsd):
  const MAP_ANONYMOUS = 0x1000
elif defined(solaris): 
  const MAP_ANONYMOUS = 0x100
else:
  var
    MAP_ANONYMOUS {.importc: "MAP_ANONYMOUS", header: "<sys/mman.h>".}: cint
  
proc mmap(adr: pointer, len: int, prot, flags, fildes: cint,
          off: int): pointer {.header: "<sys/mman.h>".}

proc munmap(adr: pointer, len: int) {.header: "<sys/mman.h>".}

proc osAllocPages(size: int): pointer {.inline.} = 
  result = mmap(nil, size, PROT_READ or PROT_WRITE, 
                         MAP_PRIVATE or MAP_ANONYMOUS, -1, 0)
  if result == nil or result == cast[pointer](-1):
    quit 1
  cfprintf(c_stdout, "allocated pages %p..%p\n", result, 
                     cast[int](result) + size)
    
proc osDeallocPages(p: pointer, size: int) {.inline} =
  cfprintf(c_stdout, "freed pages %p..%p\n", p, cast[int](p) + size)
  munmap(p, size-1)

proc `+!!`(p: pointer, size: int): pointer {.inline.} =
  result = cast[pointer](cast[int](p) + size)

var p = osAllocPages(3 * PageSize)

osDeallocPages(p, PageSize)
# If this fails the OS has freed the whole block starting at 'p':
echo(cast[ptr int](p +!! (pageSize*2))[])

osDeallocPages(p +!! PageSize*2, PageSize)
osDeallocPages(p +!! PageSize, PageSize)
generated by cgit-pink 1.4.1-2-gfad0 (git 2.36.2.497.gbbea4dcf42) at 2025-02-21 08:40:32 +0000
================================= meta character meaning ============== ============================================================ ``\`` general escape character with several uses ``^`` assert start of string (or line, in multiline mode) ``$`` assert end of string (or line, in multiline mode) ``.`` match any character except newline (by default) ``[`` start character class definition ``|`` start of alternative branch ``(`` start subpattern ``)`` end subpattern ``?`` extends the meaning of ``(`` also 0 or 1 quantifier also quantifier minimizer ``*`` 0 or more quantifier ``+`` 1 or more quantifier also "possessive quantifier" ``{`` start min/max quantifier ============== ============================================================ Part of a pattern that is in square brackets is called a "character class". In a character class the only metacharacters are: ============== ============================================================ meta character meaning ============== ============================================================ ``\`` general escape character ``^`` negate the class, but only if the first character ``-`` indicates character range ``[`` POSIX character class (only if followed by POSIX syntax) ``]`` terminates the character class ============== ============================================================ The following sections describe the use of each of the metacharacters. Backslash --------- The `backslash`:idx: character has several uses. Firstly, if it is followed by a non-alphanumeric character, it takes away any special meaning that character may have. This use of backslash as an escape character applies both inside and outside character classes. For example, if you want to match a ``*`` character, you write ``\*`` in the pattern. This escaping action applies whether or not the following character would otherwise be interpreted as a metacharacter, so it is always safe to precede a non-alphanumeric with backslash to specify that it stands for itself. In particular, if you want to match a backslash, you write ``\\``. Non-printing characters ----------------------- A second use of backslash provides a way of encoding non-printing characters in patterns in a visible manner. There is no restriction on the appearance of non-printing characters, apart from the binary zero that terminates a pattern, but when a pattern is being prepared by text editing, it is usually easier to use one of the following escape sequences than the binary character it represents:: ============== ============================================================ character meaning ============== ============================================================ ``\a`` alarm, that is, the BEL character (hex 07) ``\e`` escape (hex 1B) ``\f`` formfeed (hex 0C) ``\n`` newline (hex 0A) ``\r`` carriage return (hex 0D) ``\t`` tab (hex 09) ``\ddd`` character with octal code ddd, or backreference ``\xhh`` character with hex code hh ============== ============================================================ After ``\x``, from zero to two hexadecimal digits are read (letters can be in upper or lower case). In UTF-8 mode, any number of hexadecimal digits may appear between ``\x{`` and ``}``, but the value of the character code must be less than 2**31 (that is, the maximum hexadecimal value is 7FFFFFFF). If characters other than hexadecimal digits appear between ``\x{`` and ``}``, or if there is no terminating ``}``, this form of escape is not recognized. Instead, the initial ``\x`` will be interpreted as a basic hexadecimal escape, with no following digits, giving a character whose value is zero. After ``\0`` up to two further octal digits are read. In both cases, if there are fewer than two digits, just those that are present are used. Thus the sequence ``\0\x\07`` specifies two binary zeros followed by a BEL character (code value 7). Make sure you supply two digits after the initial zero if the pattern character that follows is itself an octal digit. The handling of a backslash followed by a digit other than 0 is complicated. Outside a character class, PCRE reads it and any following digits as a decimal number. If the number is less than 10, or if there have been at least that many previous capturing left parentheses in the expression, the entire sequence is taken as a back reference. A description of how this works is given later, following the discussion of parenthesized subpatterns. Inside a character class, or if the decimal number is greater than 9 and there have not been that many capturing subpatterns, PCRE re-reads up to three octal digits following the backslash, and generates a single byte from the least significant 8 bits of the value. Any subsequent digits stand for themselves. For example: ============== ============================================================ example meaning ============== ============================================================ ``\040`` is another way of writing a space ``\40`` is the same, provided there are fewer than 40 previous capturing subpatterns ``\7`` is always a back reference ``\11`` might be a back reference, or another way of writing a tab ``\011`` is always a tab ``\0113`` is a tab followed by the character "3" ``\113`` might be a back reference, otherwise the character with octal code 113 ``\377`` might be a back reference, otherwise the byte consisting entirely of 1 bits ``\81`` is either a back reference, or a binary zero followed by the two characters "8" and "1" ============== ============================================================ Note that octal values of 100 or greater must not be introduced by a leading zero, because no more than three octal digits are ever read. All the sequences that define a single byte value or a single UTF-8 character (in UTF-8 mode) can be used both inside and outside character classes. In addition, inside a character class, the sequence ``\b`` is interpreted as the backspace character (hex 08), and the sequence ``\X`` is interpreted as the character "X". Outside a character class, these sequences have different meanings (see below). Generic character types ----------------------- The third use of backslash is for specifying `generic character types`:idx:. The following are always recognized: ============== ============================================================ character type meaning ============== ============================================================ ``\d`` any decimal digit ``\D`` any character that is not a decimal digit ``\s`` any whitespace character ``\S`` any character that is not a whitespace character ``\w`` any "word" character ``\W`` any "non-word" character ============== ============================================================ Each pair of escape sequences partitions the complete set of characters into two disjoint sets. Any given character matches one, and only one, of each pair. These character type sequences can appear both inside and outside character classes. They each match one character of the appropriate type. If the current matching point is at the end of the subject string, all of them fail, since there is no character to match. For compatibility with Perl, ``\s`` does not match the VT character (code 11). This makes it different from the the POSIX "space" class. The ``\s`` characters are HT (9), LF (10), FF (12), CR (13), and space (32). A "word" character is an underscore or any character less than 256 that is a letter or digit. The definition of letters and digits is controlled by PCRE's low-valued character tables, and may vary if locale-specific matching is taking place (see "Locale support" in the pcreapi page). For example, in the "fr_FR" (French) locale, some character codes greater than 128 are used for accented letters, and these are matched by ``\w``. In UTF-8 mode, characters with values greater than 128 never match ``\d``, ``\s``, or ``\w``, and always match ``\D``, ``\S``, and ``\W``. This is true even when Unicode character property support is available. Simple assertions ----------------- The fourth use of backslash is for certain `simple assertions`:idx:. An assertion specifies a condition that has to be met at a particular point in a match, without consuming any characters from the subject string. The use of subpatterns for more complicated assertions is described below. The backslashed assertions are:: ============== ============================================================ assertion meaning ============== ============================================================ ``\b`` matches at a word boundary ``\B`` matches when not at a word boundary ``\A`` matches at start of subject ``\Z`` matches at end of subject or before newline at end ``\z`` matches at end of subject ``\G`` matches at first matching position in subject ============== ============================================================ These assertions may not appear in character classes (but note that ``\b`` has a different meaning, namely the backspace character, inside a character class). A word boundary is a position in the subject string where the current character and the previous character do not both match ``\w`` or ``\W`` (i.e. one matches ``\w`` and the other matches ``\W``), or the start or end of the string if the first or last character matches ``\w``, respectively. The ``\A``, ``\Z``, and ``\z`` assertions differ from the traditional circumflex and dollar in that they only ever match at the very start and end of the subject string, whatever options are set. The difference between ``\Z`` and ``\z`` is that ``\Z`` matches before a newline that is the last character of the string as well as at the end of the string, whereas ``\z`` matches only at the end.
generated by cgit-pink 1.4.1-2-gfad0 (git 2.36.2.497.gbbea4dcf42) at 2025-02-21 08:40:25 +0000