about summary refs log tree commit diff stats
path: root/411string.mu
blob: cf0471aca570c659f3e2732f33638a7abb0759df (plain) (blame)
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
28pre { line-height: 125%; }
td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
.highlight .hll { background-color: #ffffcc }
.highlight .c { color: #888888 } /* Comment */
.highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */
.highlight .k { color: #008800; font-weight: bold } /* Keyword */
.highlight .ch { color: #888888 } /* Comment.Hashbang */
.highlight .cm { color: #888888 } /* Comment.Multiline */
.highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */
.highlight .cpf { color: #888888 } /* Comment.PreprocFile */
.highlight .c1 { color: #888888 } /* Comment.Single */
.highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */
.highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */
.highlight .ge { font-style: italic } /* Generic.Emph */
.highlight .ges { font-weight: bold; font-style: italic } /* Generic.EmphStrong */
.highlight .gr { color: #aa0000 } /* Generic.Error */
.highlight .gh { color: #333333 } /* Generic.Heading */
.highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #555555 } /* Generic.Prompt */
.highlight .gs { font-weight: bold } /* Generic.Strong */
.highlight .gu { color: #666666 } /* Generic.Subheading */
.highlight .gt { color: #aa0000 } /* Generic.Traceback */
.highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */
.highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */
.highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */
.highlight .kp { color: #008800 } /* Keyword.Pseudo */
.highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */
.highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */
.highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */
.highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */
.highlight .na { color: #336699 } /* Name.Attribute */
.highlight .nb { color: #003388 } /* Name.Builtin */
.highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */
.highlight .no { color: #003366; font-weight: bold } /* Name.Constant */
.highlight .nd { color: #555555 } /* Name.Decorator */
.highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */
.highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */
.highlight .nl { color: #336699; font-style: italic } /* Name.Label */
.highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */
.highlight .py { color: #336699; font-weight: bold } /* Name.Property */
.highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag *
# read up to 'len' graphemes after skipping the first 'start' ones
fn substring in: (addr array byte), start: int, len: int, out-ah: (addr handle array byte) {
  var in-stream: (stream byte 0x100)
  var in-stream-addr/esi: (addr stream byte) <- address in-stream
  write in-stream-addr, in
  var out-stream: (stream byte 0x100)
  var out-stream-addr/edi: (addr stream byte) <- address out-stream
  $substring:core: {
    # skip 'start' graphemes
    var i/eax: int <- copy 0
    {
      compare i, start
      break-if->=
      {
        var dummy/eax: grapheme <- read-grapheme in-stream-addr
        compare dummy, 0xffffffff/end-of-file
        break-if-= $substring:core
      }
      i <- increment
      loop
    }
    # copy 'len' graphemes
    i <- copy 0
    {
      compare i, len
      break-if->=
      {
        var g/eax: grapheme <- read-grapheme in-stream-addr
        compare g, 0xffffffff/end-of-file
        break-if-= $substring:core
        write-grapheme out-stream-addr, g
      }
      i <- increment
      loop
    }
  }
  stream-to-array out-stream-addr, out-ah
}

fn test-substring {
  var out-h: (handle array byte)
  var out-ah/edi: (addr handle array byte) <- address out-h
  # prefix substrings
  substring 0, 0, 3, out-ah
  var out/eax: (addr array byte) <- lookup *out-ah
  check-strings-equal out, "", "F - test-substring/null"
  substring "", 0, 3, out-ah
  var out/eax: (addr array byte) <- lookup *out-ah
#?   print-string-to-real-screen out
#?   print-string-to-real-screen "\n"
  check-strings-equal out, "", "F - test-substring/empty"
  #
  substring "abcde", 0, 3, out-ah
  var out/eax: (addr array byte) <- lookup *out-ah
#?   print-string-to-real-screen out
#?   print-string-to-real-screen "\n"
  check-strings-equal out, "abc", "F - test-substring/truncate"
  #
  substring "abcde", 0, 5, out-ah
  var out/eax: (addr array byte) <- lookup *out-ah
  check-strings-equal out, "abcde", "F - test-substring/all"
  #
  substring "abcde", 0, 7, out-ah
  var out/eax: (addr array byte) <- lookup *out-ah
  check-strings-equal out, "abcde", "F - test-substring/too-small"
  # substrings outside string
  substring "abcde", 6, 1, out-ah
  var out/eax: (addr array byte) <- lookup *out-ah
  check-strings-equal out, "", "F - test-substring/start-too-large"
  # trim prefix
  substring "", 2, 3, out-ah
  var out/eax: (addr array byte) <- lookup *out-ah
  check-strings-equal out, "", "F - test-substring/middle-empty"
  #
  substring "abcde", 1, 2, out-ah
  var out/eax: (addr array byte) <- lookup *out-ah
  check-strings-equal out, "bc", "F - test-substring/middle-truncate"
  #
  substring "abcde", 1, 4, out-ah
  var out/eax: (addr array byte) <- lookup *out-ah
  check-strings-equal out, "bcde", "F - test-substring/middle-all"
  #
  substring "abcde", 1, 5, out-ah
  var out/eax: (addr array byte) <- lookup *out-ah
  check-strings-equal out, "bcde", "F - test-substring/middle-too-small"
}

fn split-string in: (addr array byte), delim: grapheme, out: (addr handle array (handle array byte)) {
  var in-stream: (stream byte 0x100)
  var in-stream-addr/esi: (addr stream byte) <- address in-stream
  write in-stream-addr, in
  var tokens-stream: (stream (handle array byte) 0x100)
  var tokens-stream-addr/edi: (addr stream (handle array byte)) <- address tokens-stream
  var curr-stream: (stream byte 0x100)
  var curr-stream-addr/ecx: (addr stream byte) <- address curr-stream
  $split-string:core: {
    var g/eax: grapheme <- read-grapheme in-stream-addr
    compare g, 0xffffffff
    break-if-=
#?     print-grapheme-to-real-screen g
#?     print-string-to-real-screen "\n"
    compare g, delim
    {
      break-if-!=
      # token complete; flush
      var token: (handle array byte)
      var token-ah/eax: (addr handle array byte) <- address token
      stream-to-array curr-stream-addr, token-ah
      write-to-stream tokens-stream-addr, token-ah
      clear-stream curr-stream-addr
      loop $split-string:core
    }
    write-grapheme curr-stream-addr, g
    loop
  }
  stream-to-array tokens-stream-addr, out
}

fn test-split-string {
  var out-h: (handle array (handle array byte))
  var out-ah/edi: (addr handle array (handle array byte)) <- address out-h
  # prefix substrings
  split-string "bab", 0x61, out-ah
  # no crash
}