Mxx_ru 1.1.0

data/tests/c/pcre/perltest

@@ -0,0 +1,211 @@
+#! /usr/bin/perl
+
+# Program for testing regular expressions with perl to check that PCRE handles
+# them the same. This is the version that supports /8 for UTF-8 testing. As it
+# stands, it requires at least Perl 5.8 for UTF-8 support. For Perl 5.6, it
+# can be used as is for non-UTF-8 testing, but you have to uncomment the
+# "use utf8" lines in order to to UTF-8 stuff (and you mustn't uncomment them
+# for non-UTF-8 use).
+
+
+# Function for turning a string into a string of printing chars. There are
+# currently problems with UTF-8 strings; this fudges round them.
+
+sub pchars {
+my($t) = "";
+
+if ($utf8)
+  {
+#  use utf8;                    <=============== For UTF-8 in Perl 5.6
+  @p = unpack('U*', $_[0]);
+  foreach $c (@p)
+    {
+    if ($c >= 32 && $c < 127) { $t .= chr $c; }
+      else { $t .= sprintf("\\x{%02x}", $c); }
+    }
+  }
+
+else
+  {
+  foreach $c (split(//, $_[0]))
+    {
+    if (ord $c >= 32 && ord $c < 127) { $t .= $c; }
+      else { $t .= sprintf("\\x%02x", ord $c); }
+    }
+  }
+
+$t;
+}
+
+
+
+# Read lines from named file or stdin and write to named file or stdout; lines
+# consist of a regular expression, in delimiters and optionally followed by
+# options, followed by a set of test data, terminated by an empty line.
+
+# Sort out the input and output files
+
+if (@ARGV > 0)
+  {
+  open(INFILE, "<$ARGV[0]") || die "Failed to open $ARGV[0]\n";
+  $infile = "INFILE";
+  }
+else { $infile = "STDIN"; }
+
+if (@ARGV > 1)
+  {
+  open(OUTFILE, ">$ARGV[1]") || die "Failed to open $ARGV[1]\n";
+  $outfile = "OUTFILE";
+  }
+else { $outfile = "STDOUT"; }
+
+printf($outfile "Perl $] Regular Expressions\n\n");
+
+# Main loop
+
+NEXT_RE:
+for (;;)
+  {
+  printf "  re> " if $infile eq "STDIN";
+  last if ! ($_ = <$infile>);
+  printf $outfile "$_" if $infile ne "STDIN";
+  next if ($_ eq "");
+
+  $pattern = $_;
+
+  while ($pattern !~ /^\s*(.).*\1/s)
+    {
+    printf "    > " if $infile eq "STDIN";
+    last if ! ($_ = <$infile>);
+    printf $outfile "$_" if $infile ne "STDIN";
+    $pattern .= $_;
+    }
+
+   chomp($pattern);
+   $pattern =~ s/\s+$//;
+
+  # The private /+ modifier means "print $' afterwards".
+
+  $showrest = ($pattern =~ s/\+(?=[a-z]*$)//);
+
+  # The private /8 modifier means "operate in UTF-8". Currently, Perl
+  # has bugs that we try to work around using this flag.
+
+  $utf8 = ($pattern =~ s/8(?=[a-z]*$)//);
+
+  # Check that the pattern is valid
+
+  if ($utf8)
+    {
+#    use utf8;                    <=============== For UTF-8 in Perl 5.6
+    eval "\$_ =~ ${pattern}";
+    }
+  else
+    {
+    eval "\$_ =~ ${pattern}";
+    }
+
+  if ($@)
+    {
+    printf $outfile "Error: $@";
+    next NEXT_RE;
+    }
+
+  # If the /g modifier is present, we want to put a loop round the matching;
+  # otherwise just a single "if".
+
+  $cmd = ($pattern =~ /g[a-z]*$/)? "while" : "if";
+
+  # If the pattern is actually the null string, Perl uses the most recently
+  # executed (and successfully compiled) regex is used instead. This is a
+  # nasty trap for the unwary! The PCRE test suite does contain null strings
+  # in places - if they are allowed through here all sorts of weird and
+  # unexpected effects happen. To avoid this, we replace such patterns with
+  # a non-null pattern that has the same effect.
+
+  $pattern = "/(?#)/$2" if ($pattern =~ /^(.)\1(.*)$/);
+
+  # Read data lines and test them
+
+  for (;;)
+    {
+    printf "data> " if $infile eq "STDIN";
+    last NEXT_RE if ! ($_ = <$infile>);
+    chomp;
+    printf $outfile "$_\n" if $infile ne "STDIN";
+
+    s/\s+$//;
+    s/^\s+//;
+
+    last if ($_ eq "");
+
+    $x = eval "\"$_\"";   # To get escapes processed
+
+    # Empty array for holding results, then do the matching.
+
+    @subs = ();
+
+    $pushes = "push \@subs,\$&;" .
+         "push \@subs,\$1;" .
+         "push \@subs,\$2;" .
+         "push \@subs,\$3;" .
+         "push \@subs,\$4;" .
+         "push \@subs,\$5;" .
+         "push \@subs,\$6;" .
+         "push \@subs,\$7;" .
+         "push \@subs,\$8;" .
+         "push \@subs,\$9;" .
+         "push \@subs,\$10;" .
+         "push \@subs,\$11;" .
+         "push \@subs,\$12;" .
+         "push \@subs,\$13;" .
+         "push \@subs,\$14;" .
+         "push \@subs,\$15;" .
+         "push \@subs,\$16;" .
+         "push \@subs,\$'; }";
+
+    if ($utf8)
+      {
+#      use utf8;                    <=============== For UTF-8 in Perl 5.6
+      eval "${cmd} (\$x =~ ${pattern}) {" . $pushes;
+      }
+    else
+      {
+      eval "${cmd} (\$x =~ ${pattern}) {" . $pushes;
+      }
+
+    if ($@)
+      {
+      printf $outfile "Error: $@\n";
+      next NEXT_RE;
+      }
+    elsif (scalar(@subs) == 0)
+      {
+      printf $outfile "No match\n";
+      }
+    else
+      {
+      while (scalar(@subs) != 0)
+        {
+        printf $outfile (" 0: %s\n", &pchars($subs[0]));
+        printf $outfile (" 0+ %s\n", &pchars($subs[17])) if $showrest;
+        $last_printed = 0;
+        for ($i = 1; $i <= 16; $i++)
+          {
+          if (defined $subs[$i])
+            {
+            while ($last_printed++ < $i-1)
+              { printf $outfile ("%2d: <unset>\n", $last_printed); }
+            printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i]));
+            $last_printed = $i;
+            }
+          }
+        splice(@subs, 0, 18);
+        }
+      }
+    }
+  }
+
+printf $outfile "\n";
+
+# End

data/tests/c/pcre/printint.c

@@ -0,0 +1,360 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/*
+This is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language. See
+the file Tech.Notes for some information on the internals.
+
+Written by: Philip Hazel <ph10@cam.ac.uk>
+
+           Copyright (c) 1997-2003 University of Cambridge
+
+-----------------------------------------------------------------------------
+Permission is granted to anyone to use this software for any purpose on any
+computer system, and to redistribute it freely, subject to the following
+restrictions:
+
+1. This software is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+
+2. The origin of this software must not be misrepresented, either by
+   explicit claim or by omission.
+
+3. Altered versions must be plainly marked as such, and must not be
+   misrepresented as being the original software.
+
+4. If PCRE is embedded in any software that is released under the GNU
+   General Purpose Licence (GPL), then the terms of that licence shall
+   supersede any condition above with which it is incompatible.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains a debugging function for printing out the internal form
+of a compiled regular expression. It is kept in a separate file so that it can
+be #included both in the pcretest program, and in the library itself when
+compiled with the debugging switch. */
+
+
+static const char *OP_names[] = { OP_NAME_LIST };
+
+
+/*************************************************
+*       Print single- or multi-byte character    *
+*************************************************/
+
+/* These tables are actually copies of ones in pcre.c. If we compile the
+library with debugging, they are included twice, but that isn't really a
+problem - compiling with debugging is pretty rare and these are very small. */
+
+static const int utf8_t3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
+
+static const uschar utf8_t4[] = {
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
+  3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
+
+static int
+print_char(FILE *f, uschar *ptr, BOOL utf8)
+{
+int c = *ptr;
+
+if (!utf8 || (c & 0xc0) != 0xc0)
+  {
+  if (isprint(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c);
+  return 0;
+  }
+else
+  {
+  int i;
+  int a = utf8_t4[c & 0x3f];  /* Number of additional bytes */
+  int s = 6*a;
+  c = (c & utf8_t3[a]) << s;
+  for (i = 1; i <= a; i++)
+    {
+    s -= 6;
+    c |= (ptr[i] & 0x3f) << s;
+    }
+  if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c);
+  return a;
+  }
+}
+
+
+
+
+/*************************************************
+*         Print compiled regex                   *
+*************************************************/
+
+static void
+print_internals(pcre *external_re, FILE *f)
+{
+real_pcre *re = (real_pcre *)external_re;
+uschar *codestart =
+  (uschar *)re + sizeof(real_pcre) + re->name_count * re->name_entry_size;
+uschar *code = codestart;
+BOOL utf8 = (re->options & PCRE_UTF8) != 0;
+
+for(;;)
+  {
+  uschar *ccode;
+  int c;
+  int extra = 0;
+
+  fprintf(f, "%3d ", code - codestart);
+
+  if (*code >= OP_BRA)
+    {
+    if (*code - OP_BRA > EXTRACT_BASIC_MAX)
+      fprintf(f, "%3d Bra extra\n", GET(code, 1));
+    else
+      fprintf(f, "%3d Bra %d\n", GET(code, 1), *code - OP_BRA);
+    code += OP_lengths[OP_BRA];
+    continue;
+    }
+
+  switch(*code)
+    {
+    case OP_END:
+    fprintf(f, "    %s\n", OP_names[*code]);
+    fprintf(f, "------------------------------------------------------------------\n");
+    return;
+
+    case OP_OPT:
+    fprintf(f, " %.2x %s", code[1], OP_names[*code]);
+    break;
+
+    case OP_CHARS:
+      {
+      int charlength = code[1];
+      ccode = code + 2;
+      extra = charlength;
+      fprintf(f, "%3d ", charlength);
+      while (charlength > 0)
+        {
+        int extrabytes = print_char(f, ccode, utf8);
+        ccode += 1 + extrabytes;
+        charlength -= 1 + extrabytes;
+        }
+      }
+    break;
+
+    case OP_KETRMAX:
+    case OP_KETRMIN:
+    case OP_ALT:
+    case OP_KET:
+    case OP_ASSERT:
+    case OP_ASSERT_NOT:
+    case OP_ASSERTBACK:
+    case OP_ASSERTBACK_NOT:
+    case OP_ONCE:
+    case OP_COND:
+    case OP_REVERSE:
+    fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]);
+    break;
+
+    case OP_BRANUMBER:
+    printf("%3d %s", GET2(code, 1), OP_names[*code]);
+    break;
+
+    case OP_CREF:
+    if (GET2(code, 1) == CREF_RECURSE)
+      fprintf(f, "    Cond recurse");
+    else
+      fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]);
+    break;
+
+    case OP_STAR:
+    case OP_MINSTAR:
+    case OP_PLUS:
+    case OP_MINPLUS:
+    case OP_QUERY:
+    case OP_MINQUERY:
+    case OP_TYPESTAR:
+    case OP_TYPEMINSTAR:
+    case OP_TYPEPLUS:
+    case OP_TYPEMINPLUS:
+    case OP_TYPEQUERY:
+    case OP_TYPEMINQUERY:
+    fprintf(f, "    ");
+    if (*code >= OP_TYPESTAR) fprintf(f, "%s", OP_names[code[1]]);
+      else extra = print_char(f, code+1, utf8);
+    fprintf(f, "%s", OP_names[*code]);
+    break;
+
+    case OP_EXACT:
+    case OP_UPTO:
+    case OP_MINUPTO:
+    fprintf(f, "    ");
+    extra = print_char(f, code+3, utf8);
+    fprintf(f, "{");
+    if (*code != OP_EXACT) fprintf(f, ",");
+    fprintf(f, "%d}", GET2(code,1));
+    if (*code == OP_MINUPTO) fprintf(f, "?");
+    break;
+
+    case OP_TYPEEXACT:
+    case OP_TYPEUPTO:
+    case OP_TYPEMINUPTO:
+    fprintf(f, "    %s{", OP_names[code[3]]);
+    if (*code != OP_TYPEEXACT) fprintf(f, "0,");
+    fprintf(f, "%d}", GET2(code,1));
+    if (*code == OP_TYPEMINUPTO) fprintf(f, "?");
+    break;
+
+    case OP_NOT:
+    if (isprint(c = code[1])) fprintf(f, "    [^%c]", c);
+      else fprintf(f, "    [^\\x%02x]", c);
+    break;
+
+    case OP_NOTSTAR:
+    case OP_NOTMINSTAR:
+    case OP_NOTPLUS:
+    case OP_NOTMINPLUS:
+    case OP_NOTQUERY:
+    case OP_NOTMINQUERY:
+    if (isprint(c = code[1])) fprintf(f, "    [^%c]", c);
+      else fprintf(f, "    [^\\x%02x]", c);
+    fprintf(f, "%s", OP_names[*code]);
+    break;
+
+    case OP_NOTEXACT:
+    case OP_NOTUPTO:
+    case OP_NOTMINUPTO:
+    if (isprint(c = code[3])) fprintf(f, "    [^%c]{", c);
+      else fprintf(f, "    [^\\x%02x]{", c);
+    if (*code != OP_NOTEXACT) fprintf(f, ",");
+    fprintf(f, "%d}", GET2(code,1));
+    if (*code == OP_NOTMINUPTO) fprintf(f, "?");
+    break;
+
+    case OP_RECURSE:
+    fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]);
+    break;
+
+    case OP_REF:
+    fprintf(f, "    \\%d", GET2(code,1));
+    ccode = code + OP_lengths[*code];
+    goto CLASS_REF_REPEAT;
+
+    case OP_CALLOUT:
+    fprintf(f, "    %s %d", OP_names[*code], code[1]);
+    break;
+
+    /* OP_XCLASS can only occur in UTF-8 mode. However, there's no harm in
+    having this code always here, and it makes it less messy without all those
+    #ifdefs. */
+
+    case OP_CLASS:
+    case OP_NCLASS:
+    case OP_XCLASS:
+      {
+      int i, min, max;
+      BOOL printmap;
+
+      fprintf(f, "    [");
+
+      if (*code == OP_XCLASS)
+        {
+        extra = GET(code, 1);
+        ccode = code + LINK_SIZE + 1;
+        printmap = (*ccode & XCL_MAP) != 0;
+        if ((*ccode++ & XCL_NOT) != 0) fprintf(f, "^");
+        }
+      else
+        {
+        printmap = TRUE;
+        ccode = code + 1;
+        }
+
+      /* Print a bit map */
+
+      if (printmap)
+        {
+        for (i = 0; i < 256; i++)
+          {
+          if ((ccode[i/8] & (1 << (i&7))) != 0)
+            {
+            int j;
+            for (j = i+1; j < 256; j++)
+              if ((ccode[j/8] & (1 << (j&7))) == 0) break;
+            if (i == '-' || i == ']') fprintf(f, "\\");
+            if (isprint(i)) fprintf(f, "%c", i); else fprintf(f, "\\x%02x", i);
+            if (--j > i)
+              {
+              fprintf(f, "-");
+              if (j == '-' || j == ']') fprintf(f, "\\");
+              if (isprint(j)) fprintf(f, "%c", j); else fprintf(f, "\\x%02x", j);
+              }
+            i = j;
+            }
+          }
+        ccode += 32;
+        }
+
+      /* For an XCLASS there is always some additional data */
+
+      if (*code == OP_XCLASS)
+        {
+        int ch;
+        while ((ch = *ccode++) != XCL_END)
+          {
+          ccode += 1 + print_char(f, ccode, TRUE);
+          if (ch == XCL_RANGE)
+            {
+            fprintf(f, "-");
+            ccode += 1 + print_char(f, ccode, TRUE);
+            }
+          }
+        }
+
+      /* Indicate a non-UTF8 class which was created by negation */
+
+      fprintf(f, "]%s", (*code == OP_NCLASS)? " (neg)" : "");
+
+      /* Handle repeats after a class or a back reference */
+
+      CLASS_REF_REPEAT:
+      switch(*ccode)
+        {
+        case OP_CRSTAR:
+        case OP_CRMINSTAR:
+        case OP_CRPLUS:
+        case OP_CRMINPLUS:
+        case OP_CRQUERY:
+        case OP_CRMINQUERY:
+        fprintf(f, "%s", OP_names[*ccode]);
+        extra = OP_lengths[*ccode];
+        break;
+
+        case OP_CRRANGE:
+        case OP_CRMINRANGE:
+        min = GET2(ccode,1);
+        max = GET2(ccode,3);
+        if (max == 0) fprintf(f, "{%d,}", min);
+        else fprintf(f, "{%d,%d}", min, max);
+        if (*ccode == OP_CRMINRANGE) fprintf(f, "?");
+        extra = OP_lengths[*ccode];
+        break;
+        }
+      }
+    break;
+
+    /* Anything else is just an item with no data*/
+
+    default:
+    fprintf(f, "    %s", OP_names[*code]);
+    break;
+    }
+
+  code += OP_lengths[*code] + extra;
+  fprintf(f, "\n");
+  }
+}
+
+/* End of printint.c */