Refactor charset plugins a bit and add CP437 module.

Now all 8-bit charsets with gaps (not all symbols defined) could be produced through
one macro -- SMB_GENERATE_CHARSET_MODULE_8_BIT_GAP(CHARSETNAME) within source file
with three charset tables. Full source code for such modules can be generated by
source/script/gen-8bit-gap.sh script which was taken from GNU libc and changed slightly
to follow our data types and structure.
(This used to be commit 37042c7bc0f349370e93e4bed37d8fa371013247)

4 files changed, 139 insertions, 0 deletions

diff --git a/source3/script/.cvsignore b/source3/script/.cvsignore
index 7a8114ecd73..0464ca23351 100644
--- a/source3/script/.cvsignore
+++ b/source3/script/.cvsignore
@@ -1 +1,2 @@
 findsmb
+gen-8bit-gap.sh
diff --git a/source3/script/gap.awk b/source3/script/gap.awk
new file mode 100644
index 00000000000..11680d10f9e
--- /dev/null
+++ b/source3/script/gap.awk
@@ -0,0 +1,39 @@
+BEGIN { hv["0"] =  0; hv["1"] =  1; hv["2"] =  2; hv["3"] =  3;
+	hv["4"] =  4; hv["5"] =  5; hv["6"] =  6; hv["7"] =  7;
+	hv["8"] =  8; hv["9"] =  9; hv["A"] = 10; hv["B"] = 11;
+	hv["C"] = 12; hv["D"] = 13; hv["E"] = 14; hv["F"] = 15;
+	hv["a"] = 10; hv["b"] = 11; hv["c"] = 12; hv["d"] = 13;
+	hv["e"] = 14; hv["f"] = 15;
+
+	first = 0; last = 0; idx = 0;
+}
+
+function tonum(str)
+{
+  num=0;
+  cnt=1;
+  while (cnt <= length(str)) {
+    num *= 16;
+    num += hv[substr(str,cnt,1)];
+    ++cnt;
+  }
+  return num;
+}
+
+{
+  u = tonum($1);
+  if (u - last > 6)
+    {
+      if (last)
+	{
+	  printf ("  { 0x%04x, 0x%04x, %5d },\n",
+		  first, last, idx);
+	  idx -= u - last - 1;
+	}
+      first = u;
+    }
+  last = u;
+}
+
+END { printf ("  { 0x%04x, 0x%04x, %5d },\n",
+	      first, last, idx); }
diff --git a/source3/script/gaptab.awk b/source3/script/gaptab.awk
new file mode 100644
index 00000000000..f9d15263610
--- /dev/null
+++ b/source3/script/gaptab.awk
@@ -0,0 +1,48 @@
+BEGIN { hv["0"] =  0; hv["1"] =  1; hv["2"] =  2; hv["3"] =  3;
+	hv["4"] =  4; hv["5"] =  5; hv["6"] =  6; hv["7"] =  7;
+	hv["8"] =  8; hv["9"] =  9; hv["A"] = 10; hv["B"] = 11;
+	hv["C"] = 12; hv["D"] = 13; hv["E"] = 14; hv["F"] = 15;
+	hv["a"] = 10; hv["b"] = 11; hv["c"] = 12; hv["d"] = 13;
+	hv["e"] = 14; hv["f"] = 15;
+
+	first = 0; last = 0; idx = 0; f = 0;
+}
+
+function tonum(str)
+{
+  num=0;
+  cnt=1;
+  while (cnt <= length(str)) {
+    num *= 16;
+    num += hv[substr(str,cnt,1)];
+    ++cnt;
+  }
+  return num;
+}
+
+function fmt(val)
+{
+  if (f++ % 8 == 0)
+    { printf ("\n  '\\x%02x',", val); }
+  else
+    { printf (" '\\x%02x',", val); }
+}
+
+{
+  u = tonum($1); c = tonum($2);
+
+  if (u - last > 6)
+    {
+      if (last) { idx += last - first + 1; }
+      first = u;
+    }
+  else
+    {
+      for (m = last+1; m < u; m++) { fmt(0); }
+    }
+
+  fmt(c);
+  last = u;
+}
+
+END { print "" }
diff --git a/source3/script/gen-8bit-gap.sh.in b/source3/script/gen-8bit-gap.sh.in
new file mode 100755
index 00000000000..e66c654c22d
--- /dev/null
+++ b/source3/script/gen-8bit-gap.sh.in
@@ -0,0 +1,51 @@
+#!/bin/sh
+if test $# -ne 2 ; then
+	echo "Usage: $0 <charmap file> <CHARSET NAME>"
+	exit 1
+fi
+
+CHARMAP=$1
+CHARSETNAME=$2
+
+echo "/* "
+echo " * Conversion table for $CHARSETNAME charset "
+echo " * "
+echo " * Conversion tables are generated using $CHARMAP table "
+echo " * and source/script/gen-8bit-gap.sh script "
+echo " * "
+echo " * This program is free software; you can redistribute it and/or modify "
+echo " * it under the terms of the GNU General Public License as published by "
+echo " * the Free Software Foundation; either version 2 of the License, or "
+echo " * (at your option) any later version. "
+echo " *  "
+echo " * This program is distributed in the hope that it will be useful,"
+echo " * but WITHOUT ANY WARRANTY; without even the implied warranty of "
+echo " * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the "
+echo " * GNU General Public License for more details. "
+echo " *  "
+echo " * You should have received a copy of the GNU General Public License "
+echo " * along with this program; if not, write to the Free Software "
+echo " * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. "
+echo " */"
+
+echo '#include "includes.h"'
+echo
+echo "static const uint16 to_ucs2[256] = {"
+sed -ne '/^[^[:space:]]*[[:space:]]*.x00/d' \
+    -e 's/^<U\(....\)>[[:space:]]*.x\(..\).*/  [0x\2] = 0x\1,/p' \
+    "$CHARMAP" | sort -u
+echo "};"
+echo
+echo "static const struct charset_gap_table from_idx[] = {"
+sed -ne 's/^<U\(....\).*/\1/p' \
+    "$CHARMAP" | sort -u | @AWK@ -f @srcdir@/script/gap.awk
+echo "  { 0xffff, 0xffff, 0 }"
+echo "};"
+echo
+echo "static const unsigned char from_ucs2[] = {"
+sed -ne 's/^<U\(....\)>[[:space:]]*.x\(..\).*/\1 \2/p' \
+    "$CHARMAP" | sort -u | @AWK@ -f @srcdir@/script/gaptab.awk
+echo "};"
+echo 
+echo "SMB_GENERATE_CHARSET_MODULE_8_BIT_GAP($CHARSETNAME)"
+echo