Tcl Source Code

*.bmp
*.gif
*.png

tools/tcl.hpj.in
tools/tcl.wse.in
win/buildall.vc.bat
win/coffbase.txt
win/makefile.bc
win/makefile.vc
win/rules.vc
win/tcl.dsp
win/tcl.dsw
win/tcl.hpj.in

tools/tcl.hpj.in
tools/tcl.wse.in
win/buildall.vc.bat
win/coffbase.txt
win/makefile.bc
win/makefile.vc
win/rules.vc
win/tcl.dsp
win/tcl.dsw
win/tcl.hpj.in

*.a
*.dll
*.dylib
*.exe
*.exp
*.lib
*.o
*.obj

*.res
*.sl
*.so
*/Makefile
*/config.cache
*/config.log
*/config.status
*/tclConfig.sh
*/tclsh*
*/tcltest*
*/versions.vc

libtommath/bn.ilg
libtommath/bn.ind
libtommath/pretty.build
libtommath/tommath.src
libtommath/*.pdf
libtommath/*.pl
libtommath/*.sh

libtommath/*.out
libtommath/*.tex
unix/autoMkindex.tcl
unix/dltest.marker
unix/tcl.pc
unix/tclIndex
unix/pkgs/*


win/pkgs/*
win/tcl.hpj

cmake_minimum_required(VERSION 2.4.4)
set(CMAKE_ALLOW_LOOSE_LOOP_CONSTRUCTS ON)

project(zlib C)

set(VERSION "1.2.9")

option(ASM686 "Enable building i686 assembly implementation")
option(AMD64 "Enable building amd64 assembly implementation")

set(INSTALL_BIN_DIR "${CMAKE_INSTALL_PREFIX}/bin" CACHE PATH "Installation directory for executables")
set(INSTALL_LIB_DIR "${CMAKE_INSTALL_PREFIX}/lib" CACHE PATH "Installation directory for libraries")
set(INSTALL_INC_DIR "${CMAKE_INSTALL_PREFIX}/include" CACHE PATH "Installation directory for headers")

                ChangeLog file for zlib












Changes in 1.2.9 (31 Dec 2016)
- Fix contrib/minizip to permit unzipping with desktop API [Zouzou]
- Improve contrib/blast to return unused bytes
- Assure that gzoffset() is correct when appending
- Improve compress() and uncompress() to support large lengths
- Fix bug in test/example.c where error code not saved
- Remedy Coverity warning [Randers-Pehrson]

# Makefile for zlib
# Copyright (C) 1995-2016 Jean-loup Gailly, Mark Adler
# For conditions of distribution and use, see copyright notice in zlib.h

# To compile and test, type:
#    ./configure; make test
# Normally configure builds both a static and a shared library.
# If you want to build just a static library, use: ./configure --static

LDFLAGS=
TEST_LDFLAGS=-L. libz.a
LDSHARED=$(CC)
CPP=$(CC) -E

STATICLIB=libz.a
SHAREDLIB=libz.so
SHAREDLIBV=libz.so.1.2.9
SHAREDLIBM=libz.so.1
LIBS=$(STATICLIB) $(SHAREDLIBV)

AR=ar
ARFLAGS=rc
RANLIB=ranlib
LDCONFIG=ldconfig

install-libs: $(LIBS)
	-@if [ ! -d $(DESTDIR)$(exec_prefix)  ]; then mkdir -p $(DESTDIR)$(exec_prefix); fi
	-@if [ ! -d $(DESTDIR)$(libdir)       ]; then mkdir -p $(DESTDIR)$(libdir); fi
	-@if [ ! -d $(DESTDIR)$(sharedlibdir) ]; then mkdir -p $(DESTDIR)$(sharedlibdir); fi
	-@if [ ! -d $(DESTDIR)$(man3dir)      ]; then mkdir -p $(DESTDIR)$(man3dir); fi
	-@if [ ! -d $(DESTDIR)$(pkgconfigdir) ]; then mkdir -p $(DESTDIR)$(pkgconfigdir); fi

	cp $(STATICLIB) $(DESTDIR)$(libdir)
	chmod 644 $(DESTDIR)$(libdir)/$(STATICLIB)
	-@($(RANLIB) $(DESTDIR)$(libdir)/libz.a || true) >/dev/null 2>&1
	-@if test -n "$(SHAREDLIBV)"; then \

	  cp $(SHAREDLIBV) $(DESTDIR)$(sharedlibdir); \
	  echo "cp $(SHAREDLIBV) $(DESTDIR)$(sharedlibdir)"; \
	  chmod 755 $(DESTDIR)$(sharedlibdir)/$(SHAREDLIBV); \
	  echo "chmod 755 $(DESTDIR)$(sharedlibdir)/$(SHAREDLIBV)"; \
	  rm -f $(DESTDIR)$(sharedlibdir)/$(SHAREDLIB) $(DESTDIR)$(sharedlibdir)/$(SHAREDLIBM); \
	  ln -s $(SHAREDLIBV) $(DESTDIR)$(sharedlibdir)/$(SHAREDLIB); \
	  ln -s $(SHAREDLIBV) $(DESTDIR)$(sharedlibdir)/$(SHAREDLIBM); \
	  ($(LDCONFIG) || true)  >/dev/null 2>&1; \
	fi

	cp $(SRCDIR)zlib.3 $(DESTDIR)$(man3dir)
	chmod 644 $(DESTDIR)$(man3dir)/zlib.3

	cp zlib.pc $(DESTDIR)$(pkgconfigdir)
	chmod 644 $(DESTDIR)$(pkgconfigdir)/zlib.pc
# The ranlib in install is needed on NeXTSTEP which checks file times
# ldconfig is for Linux

install: install-libs
	-@if [ ! -d $(DESTDIR)$(includedir)   ]; then mkdir -p $(DESTDIR)$(includedir); fi

	cp $(SRCDIR)zlib.h zconf.h $(DESTDIR)$(includedir)
	chmod 644 $(DESTDIR)$(includedir)/zlib.h $(DESTDIR)$(includedir)/zconf.h

uninstall:
	cd $(DESTDIR)$(includedir) && rm -f zlib.h zconf.h
	cd $(DESTDIR)$(libdir) && rm -f libz.a; \
	if test -n "$(SHAREDLIBV)" -a -f $(SHAREDLIBV); then \

ZLIB DATA COMPRESSION LIBRARY

zlib 1.2.9 is a general purpose data compression library.  All the code is
thread safe.  The data format used by the zlib library is described by RFCs
(Request for Comments) 1950 to 1952 in the files
http://tools.ietf.org/html/rfc1950 (zlib format), rfc1951 (deflate format) and
rfc1952 (gzip format).

All functions of the compression library are documented in the file zlib.h
(volunteer to write man pages welcome, contact [email protected]).  A usage example

PLEASE read the zlib FAQ http://zlib.net/zlib_faq.html before asking for help.

Mark Nelson <[email protected]> wrote an article about zlib for the Jan.  1997
issue of Dr.  Dobb's Journal; a copy of the article is available at
http://marknelson.us/1997/01/01/zlib-engine/ .

The changes made in version 1.2.9 are documented in the file ChangeLog.

Unsupported third party contributions are provided in directory contrib/ .

zlib is available in Java using the java.util.zip package, documented at
http://java.sun.com/developer/technicalArticles/Programming/compression/ .

A Perl interface to zlib written by Paul Marquess <[email protected]> is available

  The deflate format used by zlib was defined by Phil Katz.  The deflate and
  zlib specifications were written by L.  Peter Deutsch.  Thanks to all the
  people who reported problems and suggested various improvements in zlib; they
  are too numerous to cite here.

Copyright notice:

 (C) 1995-2016 Jean-loup Gailly and Mark Adler

  This software is provided 'as-is', without any express or implied
  warranty.  In no event will the authors be held liable for any damages
  arising from the use of this software.

  Permission is granted to anyone to use this software for any purpose,
  including commercial applications, and to alter it and redistribute it

       InBytes = number of bytes in InBuf
  Out: OutBuf = ptr to user-allocated buffer to contain decompressed data
       BufSize = number of bytes in OutBuf   }
procedure DecompressToUserBuf(const InBuf: Pointer; InBytes: Integer;
  const OutBuf: Pointer; BufSize: Integer);

const
  zlib_version = '1.2.9';

type
  EZlibError = class(Exception);
  ECompressionError = class(EZlibError);
  EDecompressionError = class(EZlibError);

implementation

    public class InfoTests
    {
        #region Info tests
        [Test]
        public void Info_Version()
        {
            Info info = new Info();
            Assert.AreEqual("1.2.9", Info.Version);
            Assert.AreEqual(32, info.SizeOfUInt);
            Assert.AreEqual(32, info.SizeOfULong);
            Assert.AreEqual(32, info.SizeOfPointer);
            Assert.AreEqual(32, info.SizeOfOffset);
        }
        #endregion
    }

/* inftree9.c -- generate Huffman trees for efficient decoding
 * Copyright (C) 1995-2016 Mark Adler
 * For conditions of distribution and use, see copyright notice in zlib.h
 */

#include "zutil.h"
#include "inftree9.h"

#define MAXBITS 15

const char inflate9_copyright[] =
   " inflate9 1.2.9 Copyright 1995-2016 Mark Adler ";
/*
  If you use the zlib library in a product, an acknowledgment is welcome
  in the documentation of your product. If for some reason you cannot
  include such an acknowledgment, I would appreciate that you keep this
  copyright string in the executable of your product.
 */

    static const unsigned short lbase[31] = { /* Length codes 257..285 base */
        3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17,
        19, 23, 27, 31, 35, 43, 51, 59, 67, 83, 99, 115,
        131, 163, 195, 227, 3, 0, 0};
    static const unsigned short lext[31] = { /* Length codes 257..285 extra */
        128, 128, 128, 128, 128, 128, 128, 128, 129, 129, 129, 129,
        130, 130, 130, 130, 131, 131, 131, 131, 132, 132, 132, 132,
        133, 133, 133, 133, 144, 192, 79};
    static const unsigned short dbase[32] = { /* Distance codes 0..31 base */
        1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49,
        65, 97, 129, 193, 257, 385, 513, 769, 1025, 1537, 2049, 3073,
        4097, 6145, 8193, 12289, 16385, 24577, 32769, 49153};
    static const unsigned short dext[32] = { /* Distance codes 0..31 extra */
        128, 128, 128, 128, 129, 129, 130, 130, 131, 131, 132, 132,
        133, 133, 134, 134, 135, 135, 136, 136, 137, 137, 138, 138,

#                                               -*- Autoconf -*-
# Process this file with autoconf to produce a configure script.

AC_INIT([minizip], [1.2.9], [bugzilla.redhat.com])
AC_CONFIG_SRCDIR([minizip.c])
AM_INIT_AUTOMAKE([foreign])
LT_INIT

AC_MSG_CHECKING([whether to build example programs])
AC_ARG_ENABLE([demos], AC_HELP_STRING([--enable-demos], [build example programs]))
AM_CONDITIONAL([COND_DEMOS], [test "$enable_demos" = yes])

(* zlibpas -- Pascal interface to the zlib data compression library
 *
 * Copyright (C) 2003 Cosmin Truta.
 * Derived from original sources by Bob Dellaca.
 * For conditions of distribution and use, see copyright notice in readme.txt
 *)

unit zlibpas;

interface

const
  ZLIB_VERSION = '1.2.9';
  ZLIB_VERNUM  = $1290;

type
  alloc_func = function(opaque: Pointer; items, size: Integer): Pointer;
                 cdecl;
  free_func  = procedure(opaque, address: Pointer);
                 cdecl;

Building instructions for the DLL versions of Zlib 1.2.9
========================================================

This directory contains projects that build zlib and minizip using
Microsoft Visual C++ 9.0/10.0.

You don't need to build these projects yourself. You can download the
binaries from:

#include <windows.h>

#define IDR_VERSION1  1
IDR_VERSION1	VERSIONINFO	MOVEABLE IMPURE LOADONCALL DISCARDABLE
  FILEVERSION	 1, 2, 9, 0
  PRODUCTVERSION 1, 2, 9, 0
  FILEFLAGSMASK	VS_FFI_FILEFLAGSMASK
  FILEFLAGS	0
  FILEOS	VOS_DOS_WINDOWS32
  FILETYPE	VFT_DLL
  FILESUBTYPE	0	// not used
BEGIN
  BLOCK "StringFileInfo"
  BEGIN
    BLOCK "040904E4"
    //language ID = U.S. English, char set = Windows, Multilingual

    BEGIN
      VALUE "FileDescription", "zlib data compression and ZIP file I/O library\0"
      VALUE "FileVersion",	"1.2.9\0"
      VALUE "InternalName",	"zlib\0"
      VALUE "OriginalFilename",	"zlibwapi.dll\0"
      VALUE "ProductName",	"ZLib.DLL\0"
      VALUE "Comments","DLL support by Alessandro Iacopetti & Gilles Vollant\0"
      VALUE "LegalCopyright", "(C) 1995-2016 Jean-loup Gailly & Mark Adler\0"
    END
  END
  BLOCK "VarFileInfo"
  BEGIN
    VALUE "Translation", 0x0409, 1252
  END
END

#include <windows.h>

#define IDR_VERSION1  1
IDR_VERSION1	VERSIONINFO	MOVEABLE IMPURE LOADONCALL DISCARDABLE
  FILEVERSION	 1, 2, 9, 0
  PRODUCTVERSION 1, 2, 9, 0
  FILEFLAGSMASK	VS_FFI_FILEFLAGSMASK
  FILEFLAGS	0
  FILEOS	VOS_DOS_WINDOWS32
  FILETYPE	VFT_DLL
  FILESUBTYPE	0	// not used
BEGIN
  BLOCK "StringFileInfo"
  BEGIN
    BLOCK "040904E4"
    //language ID = U.S. English, char set = Windows, Multilingual

    BEGIN
      VALUE "FileDescription", "zlib data compression and ZIP file I/O library\0"
      VALUE "FileVersion",	"1.2.9\0"
      VALUE "InternalName",	"zlib\0"
      VALUE "OriginalFilename",	"zlibwapi.dll\0"
      VALUE "ProductName",	"ZLib.DLL\0"
      VALUE "Comments","DLL support by Alessandro Iacopetti & Gilles Vollant\0"
      VALUE "LegalCopyright", "(C) 1995-2016 Jean-loup Gailly & Mark Adler\0"
    END
  END
  BLOCK "VarFileInfo"
  BEGIN
    VALUE "Translation", 0x0409, 1252
  END
END

#include <windows.h>

#define IDR_VERSION1  1
IDR_VERSION1	VERSIONINFO	MOVEABLE IMPURE LOADONCALL DISCARDABLE
  FILEVERSION	 1, 2, 9, 0
  PRODUCTVERSION 1, 2, 9, 0
  FILEFLAGSMASK	VS_FFI_FILEFLAGSMASK
  FILEFLAGS	0
  FILEOS	VOS_DOS_WINDOWS32
  FILETYPE	VFT_DLL
  FILESUBTYPE	0	// not used
BEGIN
  BLOCK "StringFileInfo"
  BEGIN
    BLOCK "040904E4"
    //language ID = U.S. English, char set = Windows, Multilingual

    BEGIN
      VALUE "FileDescription", "zlib data compression and ZIP file I/O library\0"
      VALUE "FileVersion",	"1.2.8.1\0"
      VALUE "InternalName",	"zlib\0"
      VALUE "OriginalFilename",	"zlibwapi.dll\0"
      VALUE "ProductName",	"ZLib.DLL\0"
      VALUE "Comments","DLL support by Alessandro Iacopetti & Gilles Vollant\0"
      VALUE "LegalCopyright", "(C) 1995-2013 Jean-loup Gailly & Mark Adler\0"
    END
  END
  BLOCK "VarFileInfo"
  BEGIN
    VALUE "Translation", 0x0409, 1252
  END
END

<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <PropertyGroup />
</Project>

<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <PropertyGroup />
</Project>

<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <PropertyGroup />
</Project>

<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <PropertyGroup />
</Project>

#include <windows.h>

#define IDR_VERSION1  1
IDR_VERSION1	VERSIONINFO	MOVEABLE IMPURE LOADONCALL DISCARDABLE
  FILEVERSION	 1, 2, 9, 0
  PRODUCTVERSION 1, 2, 9, 0
  FILEFLAGSMASK	VS_FFI_FILEFLAGSMASK
  FILEFLAGS	0
  FILEOS	VOS_DOS_WINDOWS32
  FILETYPE	VFT_DLL
  FILESUBTYPE	0	// not used
BEGIN
  BLOCK "StringFileInfo"
  BEGIN
    BLOCK "040904E4"
    //language ID = U.S. English, char set = Windows, Multilingual

    BEGIN
      VALUE "FileDescription", "zlib data compression and ZIP file I/O library\0"
      VALUE "FileVersion",	"1.2.8.1\0"
      VALUE "InternalName",	"zlib\0"
      VALUE "OriginalFilename",	"zlibwapi.dll\0"
      VALUE "ProductName",	"ZLib.DLL\0"
      VALUE "Comments","DLL support by Alessandro Iacopetti & Gilles Vollant\0"
      VALUE "LegalCopyright", "(C) 1995-2013 Jean-loup Gailly & Mark Adler\0"
    END
  END
  BLOCK "VarFileInfo"
  BEGIN
    VALUE "Translation", 0x0409, 1252
  END
END

<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <PropertyGroup />
</Project>

<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <PropertyGroup />
</Project>

#include <windows.h>

#define IDR_VERSION1  1
IDR_VERSION1	VERSIONINFO	MOVEABLE IMPURE LOADONCALL DISCARDABLE
  FILEVERSION	 1, 2, 9, 0
  PRODUCTVERSION 1, 2, 9, 0
  FILEFLAGSMASK	VS_FFI_FILEFLAGSMASK
  FILEFLAGS	0
  FILEOS	VOS_DOS_WINDOWS32
  FILETYPE	VFT_DLL
  FILESUBTYPE	0	// not used
BEGIN
  BLOCK "StringFileInfo"
  BEGIN
    BLOCK "040904E4"
    //language ID = U.S. English, char set = Windows, Multilingual

    BEGIN
      VALUE "FileDescription", "zlib data compression and ZIP file I/O library\0"
      VALUE "FileVersion",	"1.2.9\0"
      VALUE "InternalName",	"zlib\0"
      VALUE "OriginalFilename",	"zlibwapi.dll\0"
      VALUE "ProductName",	"ZLib.DLL\0"
      VALUE "Comments","DLL support by Alessandro Iacopetti & Gilles Vollant\0"
      VALUE "LegalCopyright", "(C) 1995-2016 Jean-loup Gailly & Mark Adler\0"
    END
  END
  BLOCK "VarFileInfo"
  BEGIN
    VALUE "Translation", 0x0409, 1252
  END
END

/* deflate.c -- compress data using the deflation algorithm
 * Copyright (C) 1995-2016 Jean-loup Gailly and Mark Adler
 * For conditions of distribution and use, see copyright notice in zlib.h
 */

/*
 *  ALGORITHM
 *
 *      The "deflation" process depends on being able to identify portions

 */

/* @(#) $Id$ */

#include "deflate.h"

const char deflate_copyright[] =
   " deflate 1.2.9 Copyright 1995-2016 Jean-loup Gailly and Mark Adler ";
/*
  If you use the zlib library in a product, an acknowledgment is welcome
  in the documentation of your product. If for some reason you cannot
  include such an acknowledgment, I would appreciate that you keep this
  copyright string in the executable of your product.
 */

local block_state deflate_rle    OF((deflate_state *s, int flush));
local block_state deflate_huff   OF((deflate_state *s, int flush));
local void lm_init        OF((deflate_state *s));
local void putShortMSB    OF((deflate_state *s, uInt b));
local void flush_pending  OF((z_streamp strm));
local unsigned read_buf   OF((z_streamp strm, Bytef *buf, unsigned size));
#ifdef ASMV

      void match_init OF((void)); /* asm code initialization */
      uInt longest_match  OF((deflate_state *s, IPos cur_match));
#else
local uInt longest_match  OF((deflate_state *s, IPos cur_match));
#endif

#ifdef ZLIB_DEBUG

    if (level == Z_DEFAULT_COMPRESSION) level = 6;
#endif
    if (level < 0 || level > 9 || strategy < 0 || strategy > Z_FIXED) {
        return Z_STREAM_ERROR;
    }
    func = configuration_table[s->level].func;

    if ((strategy != s->strategy || func != configuration_table[level].func)) {

        /* Flush the last buffer: */
        int err = deflate(strm, Z_BLOCK);
        if (err == Z_STREAM_ERROR)
            return err;
        if (strm->avail_out == 0)
            return Z_BUF_ERROR;
    }

            flush_pending(strm);
            if (strm->avail_out == 0) {
              s->last_flush = -1; /* avoid BUF_ERROR at next call, see above */
              return Z_OK;
            }
        }
    }
    Assert(strm->avail_out > 0, "bug2");

    if (flush != Z_FINISH) return Z_OK;
    if (s->wrap <= 0) return Z_STREAM_END;

    /* Write the trailer */
#ifdef GZIP
    if (s->wrap == 2) {

     */
    unsigned min_block = MIN(s->pending_buf_size - 5, s->w_size);

    /* Copy as many min_block or larger stored blocks directly to next_out as
     * possible. If flushing, copy the remaining available input to next_out as
     * stored blocks, if there is enough space.
     */
    unsigned len, left, have, last;
    unsigned used = s->strm->avail_in;
    for (;;) {
        /* Set len to the maximum size block that we can copy directly with the
         * available input data and output space. Set left to how much of that
         * would be copied from what's left in the window.
         */
        len = MAX_STORED;       /* maximum deflate stored block length */
        have = (s->bi_valid + 42) >> 3;         /* number of header bytes */


            /* maximum stored block length that will fit in avail_out: */
        have = s->strm->avail_out > have ? s->strm->avail_out - have : 0;
        left = s->strstart - s->block_start;    /* bytes left in window */
        if (len > (ulg)left + s->strm->avail_in)
            len = left + s->strm->avail_in;     /* limit len to the input */
        if (len > have)
            len = have;                         /* limit len to the output */
        if (left > len)
            left = len;                         /* limit window pull to len */

        /* If the stored block would be less than min_block in length, or if
         * unable to copy all of the available input when flushing, then try
         * copying to the window and the pending buffer instead. Also don't
         * write an empty block when flushing -- deflate() does that.
         */

        if (len < min_block && (len == 0 || flush == Z_NO_FLUSH ||
                                len - left != s->strm->avail_in))
            break;

        /* Make a dummy stored block in pending to get the header bytes,
         * including any pending bits. This also updates the debugging counts.
         */
        last = flush == Z_FINISH && len - left == s->strm->avail_in ? 1 : 0;
        _tr_stored_block(s, (char *)0, 0L, last);

        /* Replace the lengths in the dummy stored block with len. */
        s->pending_buf[s->pending - 4] = len;
        s->pending_buf[s->pending - 3] = len >> 8;
        s->pending_buf[s->pending - 2] = ~len;
        s->pending_buf[s->pending - 1] = ~len >> 8;

        /* Write the stored block header bytes. */
        flush_pending(s->strm);

        /* Update debugging counts for the data about to be copied. */
#ifdef ZLIB_DEBUG

        s->compressed_len += len << 3;
        s->bits_sent += len << 3;
#endif

        /* Copy uncompressed bytes from the window to next_out. */
        if (left) {


            zmemcpy(s->strm->next_out, s->window + s->block_start, left);
            s->strm->next_out += left;
            s->strm->avail_out -= left;
            s->strm->total_out += left;
            s->block_start += left;
            len -= left;
        }

        /* Copy uncompressed bytes directly from next_in to next_out, updating
         * the check value.
         */
        if (len) {
            read_buf(s->strm, s->strm->next_out, len);
            s->strm->next_out += len;
            s->strm->avail_out -= len;
            s->strm->total_out += len;
        }
    }

    /* Update the sliding window with the last s->w_size bytes of the copied
     * data, or append all of the copied data to the existing window if less
     * than s->w_size bytes were copied. Also update the number of bytes to
     * insert in the hash tables, in the event that deflateParams() switches to
     * a non-zero compression level.
     */

            }
            zmemcpy(s->window + s->strstart, s->strm->next_in - used, used);
            s->strstart += used;
        }
        s->block_start = s->strstart;
        s->insert += MIN(used, s->w_size - s->insert);
    }







    /* If flushing or finishing and all input has been consumed, then done. If
     * the code above couldn't write a complete block to next_out, then the
     * code following this won't be able to either.
     */
    if (flush != Z_NO_FLUSH && s->strm->avail_in == 0 &&
        (long)s->strstart == s->block_start)
        return flush == Z_FINISH ? finish_done : block_done;

    /* Fill the window with any remaining input. */
    have = s->window_size - s->strstart - 1;
    if (s->strm->avail_in > have && s->block_start >= (long)s->w_size) {
        /* Slide the window down. */
        s->block_start -= s->w_size;
        s->strstart -= s->w_size;
        zmemcpy(s->window, s->window + s->w_size, s->strstart);
        if (s->matches < 2)
            s->matches++;           /* add a pending slide_hash() */
        have += s->w_size;          /* more space now */
    }
    if (have > s->strm->avail_in)
        have = s->strm->avail_in;
    if (have) {
        read_buf(s->strm, s->window + s->strstart, have);
        s->strstart += have;
    }



    /* There was not enough avail_out to write a complete worthy or flushed
     * stored block to next_out. Write a stored block to pending instead, if we
     * have enough input for a worthy block, or if flushing and there is enough
     * room for the remaining input as a stored block in the pending buffer.
     */
    have = (s->bi_valid + 42) >> 3;         /* number of header bytes */
        /* maximum stored block length that will fit in pending: */
    have = MIN(s->pending_buf_size - have, MAX_STORED);
    min_block = MIN(have, s->w_size);
    left = s->strstart - s->block_start;
    if (left >= min_block ||
        (left && flush != Z_NO_FLUSH && s->strm->avail_in == 0 &&
         left <= have)) {
        len = MIN(left, have);
        last = flush == Z_FINISH && s->strm->avail_in == 0 &&
               len == left ? 1 : 0;
        _tr_stored_block(s, (charf *)s->window + s->block_start, len, last);
        s->block_start += len;
        flush_pending(s->strm);
        if (last)
            return finish_started;
    }

    /* We've done all we can with the available input and output. */
    return need_more;
}

/* ===========================================================================
 * Compress as much as possible from the input stream, return the current
 * block state.
 * This function does not perform lazy evaluation of matches and inserts
 * new strings in the dictionary only for unmatched strings or for short

1. Compression algorithm (deflate)

The deflation algorithm used by gzip (also zip and zlib) is a variation of
LZ77 (Lempel-Ziv 1977, see reference below). It finds duplicated strings in
the input data.  The second occurrence of a string is replaced by a
pointer to the previous string, in the form of a pair (distance,
length).  Distances are limited to 32K bytes, and lengths are limited
to 258 bytes. When a string does not occur anywhere in the previous
32K bytes, it is emitted as a sequence of literal bytes.  (In this
description, `string' must be taken as an arbitrary sequence of bytes,
and is not restricted to printable characters.)

Literals or match lengths are compressed with one Huffman tree, and
match distances are compressed with another tree. The trees are stored
in a compact form at the start of each block. The blocks can have any
size (except that the compressed data for one block must fit in
available memory). A block is terminated when deflate() determines that
it would be useful to start another block with fresh trees. (This is
somewhat similar to the behavior of LZW-based _compress_.)

Duplicated strings are found using a hash table. All input strings of
length 3 are inserted in the hash table. A hash index is computed for
the next 3 bytes. If the hash chain for this index is not empty, all
strings in the chain are compared with the current input string, and
the longest match is selected.

The hash chains are searched starting with the most recent strings, to
favor small distances and thus take advantage of the Huffman encoding.
The hash chains are singly linked. There are no deletions from the
hash chains, the algorithm simply discards matches that are too old.

To avoid a worst-case situation, very long hash chains are arbitrarily
truncated at a certain length, determined by a runtime option (level
parameter of deflateInit). So deflate() does not always find the longest
possible match but generally finds a match which is long enough.

deflate() also defers the selection of matches with a lazy evaluation
mechanism. After a match of length N has been found, deflate() searches for
a longer match at the next input byte. If a longer match is found, the
previous match is truncated to a length of one (thus producing a single
literal byte) and the process of lazy evaluation begins again. Otherwise,
the original match is kept, and the next match search is attempted only N
steps later.

The lazy match evaluation is also subject to a runtime parameter. If
the current match is long enough, deflate() reduces the search for a longer
match, thus speeding up the whole process. If compression ratio is more
important than speed, deflate() attempts a complete second search even if
the first match is already long enough.

The lazy match evaluation is not performed for the fastest compression
modes (level parameter 1 to 3). For these fast modes, new strings
are inserted in the hash table only when no match was found, or
when the match is not too long. This degrades the compression ratio
but saves time since there are both fewer insertions and fewer searches.


2. Decompression algorithm (inflate)

2.1 Introduction

The key question is how to represent a Huffman code (or any prefix code) so
that you can decode fast.  The most important characteristic is that shorter
codes are much more common than longer codes, so pay attention to decoding the
short codes fast, and let the long codes take longer to decode.

inflate() sets up a first level table that covers some number of bits of
input less than the length of longest code.  It gets that many bits from the
stream, and looks it up in the table.  The table will tell if the next
code is that many bits or less and how many, and if it is, it will tell
the value, else it will point to the next level table for which inflate()
grabs more bits and tries to decode a longer code.

How many bits to make the first lookup is a tradeoff between the time it
takes to decode and the time it takes to build the table.  If building the
table took no time (and if you had infinite memory), then there would only
be a first level table to cover all the way to the longest code.  However,
building the table ends up taking a lot longer for more bits since short
codes are replicated many times in such a table.  What inflate() does is
simply to make the number of bits in the first table a variable, and  then
to set that variable for the maximum speed.

For inflate, which has 286 possible codes for the literal/length tree, the size
of the first table is nine bits.  Also the distance trees have 30 possible
values, and the size of the first table is six bits.  Note that for each of
those cases, the table ended up one bit longer than the ``average'' code
length, i.e. the code length of an approximately flat code which would be a
little more than eight bits for 286 symbols and a little less than five bits
for 30 symbols.


2.2 More details on the inflate table lookup

Ok, you want to know what this cleverly obfuscated inflate tree actually
looks like.  You are correct that it's not a Huffman tree.  It is simply a
lookup table for the first, let's say, nine bits of a Huffman symbol.  The
symbol could be as short as one bit or as long as 15 bits.  If a particular
symbol is shorter than nine bits, then that symbol's translation is duplicated
in all those entries that start with that symbol's bits.  For example, if the
symbol is four bits, then it's duplicated 32 times in a nine-bit table.  If a
symbol is nine bits long, it appears in the table once.

If the symbol is longer than nine bits, then that entry in the table points
to another similar table for the remaining bits.  Again, there are duplicated
entries as needed.  The idea is that most of the time the symbol will be short
and there will only be one table look up.  (That's whole idea behind data
compression in the first place.)  For the less frequent long symbols, there
will be two lookups.  If you had a compression method with really long
symbols, you could have as many levels of lookups as is efficient.  For
inflate, two is enough.

So a table entry either points to another table (in which case nine bits in
the above example are gobbled), or it contains the translation for the symbol
and the number of bits to gobble.  Then you start again with the next
ungobbled bit.

You may wonder: why not just have one lookup table for how ever many bits the
longest symbol is?  The reason is that if you do that, you end up spending
more time filling in duplicate symbol entries than you do actually decoding.
At least for deflate's output that generates new trees every several 10's of
kbytes.  You can imagine that filling in a 2^15 entry table for a 15-bit code
would take too long if you're only decoding several thousand symbols.  At the
other extreme, you could make a new table for every bit in the code.  In fact,
that's essentially a Huffman tree.  But then you spend too much time
traversing the tree while decoding, even for short symbols.

So the number of bits for the first lookup table is a trade of the time to
fill out the table vs. the time spent looking at the second level and above of
the table.

Here is an example, scaled down:

The code being decoded, with 10 symbols, from 1 to 6 bits long:

A: 0
B: 10
C: 1100
D: 11010
E: 11011
F: 11100
G: 11101
H: 11110
I: 111110
J: 111111

Let's make the first table three bits long (eight entries):

000: A,1
001: A,1
010: A,1
011: A,1
100: B,2
101: B,2
110: -> table X (gobble 3 bits)
111: -> table Y (gobble 3 bits)

Each entry is what the bits decode as and how many bits that is, i.e. how
many bits to gobble.  Or the entry points to another table, with the number of
bits to gobble implicit in the size of the table.

Table X is two bits long since the longest code starting with 110 is five bits
long:

00: C,1
01: C,1
10: D,2
11: E,2

Table Y is three bits long since the longest code starting with 111 is six
bits long:

000: F,2
001: F,2
010: G,2
011: G,2
100: H,2
101: H,2
110: I,3
111: J,3

So what we have here are three tables with a total of 20 entries that had to
be constructed.  That's compared to 64 entries for a single table.  Or
compared to 16 entries for a Huffman tree (six two entry tables and one four
entry table).  Assuming that the code ideally represents the probability of
the symbols, it takes on the average 1.25 lookups per symbol.  That's compared
to one lookup for the single table, or 1.66 lookups per symbol for the
Huffman tree.

There, I think that gives you a picture of what's going on.  For inflate, the
meaning of a particular symbol is often more than just a letter.  It can be a
byte (a "literal"), or it can be either a length or a distance which
indicates a base value and a number of bits to fetch after the code that is
added to the base value.  Or it might be the special end-of-block code.  The
data structures created in inftrees.c try to encode all that information
compactly in the tables.


Jean-loup Gailly        Mark Adler
[email protected]          [email protected]


References:

[LZ77] Ziv J., Lempel A., ``A Universal Algorithm for Sequential Data
Compression,'' IEEE Transactions on Information Theory, Vol. 23, No. 3,
pp. 337-343.

``DEFLATE Compressed Data Format Specification'' available in
http://tools.ietf.org/html/rfc1951

Network Working Group                                         P. Deutsch
Request for Comments: 1950                           Aladdin Enterprises
Category: Informational                                      J-L. Gailly
                                                                Info-ZIP
                                                                May 1996


         ZLIB Compressed Data Format Specification version 3.3

Status of This Memo

   This memo provides information for the Internet community.  This memo
   does not specify an Internet standard of any kind.  Distribution of
   this memo is unlimited.

IESG Note:

   The IESG takes no position on the validity of any Intellectual
   Property Rights statements contained in this document.

Notices

   Copyright (c) 1996 L. Peter Deutsch and Jean-Loup Gailly

   Permission is granted to copy and distribute this document for any
   purpose and without charge, including translations into other
   languages and incorporation into compilations, provided that the
   copyright notice and this notice are preserved, and that any
   substantive changes or deletions from the original are clearly
   marked.

   A pointer to the latest version of this and related documentation in
   HTML format can be found at the URL
   <ftp://ftp.uu.net/graphics/png/documents/zlib/zdoc-index.html>.

Abstract

   This specification defines a lossless compressed data format.  The
   data can be produced or consumed, even for an arbitrarily long
   sequentially presented input data stream, using only an a priori
   bounded amount of intermediate storage.  The format presently uses
   the DEFLATE compression method but can be easily extended to use
   other compression methods.  It can be implemented readily in a manner
   not covered by patents.  This specification also defines the ADLER-32
   checksum (an extension and improvement of the Fletcher checksum),
   used for detection of data corruption, and provides an algorithm for
   computing it.




Deutsch & Gailly             Informational                      [Page 1]

RFC 1950       ZLIB Compressed Data Format Specification        May 1996


Table of Contents

   1. Introduction ................................................... 2
      1.1. Purpose ................................................... 2
      1.2. Intended audience ......................................... 3
      1.3. Scope ..................................................... 3
      1.4. Compliance ................................................ 3
      1.5.  Definitions of terms and conventions used ................ 3
      1.6. Changes from previous versions ............................ 3
   2. Detailed specification ......................................... 3
      2.1. Overall conventions ....................................... 3
      2.2. Data format ............................................... 4
      2.3. Compliance ................................................ 7
   3. References ..................................................... 7
   4. Source code .................................................... 8
   5. Security Considerations ........................................ 8
   6. Acknowledgements ............................................... 8
   7. Authors' Addresses ............................................. 8
   8. Appendix: Rationale ............................................ 9
   9. Appendix: Sample code ..........................................10

1. Introduction

   1.1. Purpose

      The purpose of this specification is to define a lossless
      compressed data format that:

          * Is independent of CPU type, operating system, file system,
            and character set, and hence can be used for interchange;

          * Can be produced or consumed, even for an arbitrarily long
            sequentially presented input data stream, using only an a
            priori bounded amount of intermediate storage, and hence can
            be used in data communications or similar structures such as
            Unix filters;

          * Can use a number of different compression methods;

          * Can be implemented readily in a manner not covered by
            patents, and hence can be practiced freely.

      The data format defined by this specification does not attempt to
      allow random access to compressed data.







Deutsch & Gailly             Informational                      [Page 2]

RFC 1950       ZLIB Compressed Data Format Specification        May 1996


   1.2. Intended audience

      This specification is intended for use by implementors of software
      to compress data into zlib format and/or decompress data from zlib
      format.

      The text of the specification assumes a basic background in
      programming at the level of bits and other primitive data
      representations.

   1.3. Scope

      The specification specifies a compressed data format that can be
      used for in-memory compression of a sequence of arbitrary bytes.

   1.4. Compliance

      Unless otherwise indicated below, a compliant decompressor must be
      able to accept and decompress any data set that conforms to all
      the specifications presented here; a compliant compressor must
      produce data sets that conform to all the specifications presented
      here.

   1.5.  Definitions of terms and conventions used

      byte: 8 bits stored or transmitted as a unit (same as an octet).
      (For this specification, a byte is exactly 8 bits, even on
      machines which store a character on a number of bits different
      from 8.) See below, for the numbering of bits within a byte.

   1.6. Changes from previous versions

      Version 3.1 was the first public release of this specification.
      In version 3.2, some terminology was changed and the Adler-32
      sample code was rewritten for clarity.  In version 3.3, the
      support for a preset dictionary was introduced, and the
      specification was converted to RFC style.

2. Detailed specification

   2.1. Overall conventions

      In the diagrams below, a box like this:

         +---+
         |   | <-- the vertical bars might be missing
         +---+




Deutsch & Gailly             Informational                      [Page 3]

RFC 1950       ZLIB Compressed Data Format Specification        May 1996


      represents one byte; a box like this:

         +==============+
         |              |
         +==============+

      represents a variable number of bytes.

      Bytes stored within a computer do not have a "bit order", since
      they are always treated as a unit.  However, a byte considered as
      an integer between 0 and 255 does have a most- and least-
      significant bit, and since we write numbers with the most-
      significant digit on the left, we also write bytes with the most-
      significant bit on the left.  In the diagrams below, we number the
      bits of a byte so that bit 0 is the least-significant bit, i.e.,
      the bits are numbered:

         +--------+
         |76543210|
         +--------+

      Within a computer, a number may occupy multiple bytes.  All
      multi-byte numbers in the format described here are stored with
      the MOST-significant byte first (at the lower memory address).
      For example, the decimal number 520 is stored as:

             0     1
         +--------+--------+
         |00000010|00001000|
         +--------+--------+
          ^        ^
          |        |
          |        + less significant byte = 8
          + more significant byte = 2 x 256

   2.2. Data format

      A zlib stream has the following structure:

           0   1
         +---+---+
         |CMF|FLG|   (more-->)
         +---+---+








Deutsch & Gailly             Informational                      [Page 4]

RFC 1950       ZLIB Compressed Data Format Specification        May 1996


      (if FLG.FDICT set)

           0   1   2   3
         +---+---+---+---+
         |     DICTID    |   (more-->)
         +---+---+---+---+

         +=====================+---+---+---+---+
         |...compressed data...|    ADLER32    |
         +=====================+---+---+---+---+

      Any data which may appear after ADLER32 are not part of the zlib
      stream.

      CMF (Compression Method and flags)
         This byte is divided into a 4-bit compression method and a 4-
         bit information field depending on the compression method.

            bits 0 to 3  CM     Compression method
            bits 4 to 7  CINFO  Compression info

      CM (Compression method)
         This identifies the compression method used in the file. CM = 8
         denotes the "deflate" compression method with a window size up
         to 32K.  This is the method used by gzip and PNG (see
         references [1] and [2] in Chapter 3, below, for the reference
         documents).  CM = 15 is reserved.  It might be used in a future
         version of this specification to indicate the presence of an
         extra field before the compressed data.

      CINFO (Compression info)
         For CM = 8, CINFO is the base-2 logarithm of the LZ77 window
         size, minus eight (CINFO=7 indicates a 32K window size). Values
         of CINFO above 7 are not allowed in this version of the
         specification.  CINFO is not defined in this specification for
         CM not equal to 8.

      FLG (FLaGs)
         This flag byte is divided as follows:

            bits 0 to 4  FCHECK  (check bits for CMF and FLG)
            bit  5       FDICT   (preset dictionary)
            bits 6 to 7  FLEVEL  (compression level)

         The FCHECK value must be such that CMF and FLG, when viewed as
         a 16-bit unsigned integer stored in MSB order (CMF*256 + FLG),
         is a multiple of 31.




Deutsch & Gailly             Informational                      [Page 5]

RFC 1950       ZLIB Compressed Data Format Specification        May 1996


      FDICT (Preset dictionary)
         If FDICT is set, a DICT dictionary identifier is present
         immediately after the FLG byte. The dictionary is a sequence of
         bytes which are initially fed to the compressor without
         producing any compressed output. DICT is the Adler-32 checksum
         of this sequence of bytes (see the definition of ADLER32
         below).  The decompressor can use this identifier to determine
         which dictionary has been used by the compressor.

      FLEVEL (Compression level)
         These flags are available for use by specific compression
         methods.  The "deflate" method (CM = 8) sets these flags as
         follows:

            0 - compressor used fastest algorithm
            1 - compressor used fast algorithm
            2 - compressor used default algorithm
            3 - compressor used maximum compression, slowest algorithm

         The information in FLEVEL is not needed for decompression; it
         is there to indicate if recompression might be worthwhile.

      compressed data
         For compression method 8, the compressed data is stored in the
         deflate compressed data format as described in the document
         "DEFLATE Compressed Data Format Specification" by L. Peter
         Deutsch. (See reference [3] in Chapter 3, below)

         Other compressed data formats are not specified in this version
         of the zlib specification.

      ADLER32 (Adler-32 checksum)
         This contains a checksum value of the uncompressed data
         (excluding any dictionary data) computed according to Adler-32
         algorithm. This algorithm is a 32-bit extension and improvement
         of the Fletcher algorithm, used in the ITU-T X.224 / ISO 8073
         standard. See references [4] and [5] in Chapter 3, below)

         Adler-32 is composed of two sums accumulated per byte: s1 is
         the sum of all bytes, s2 is the sum of all s1 values. Both sums
         are done modulo 65521. s1 is initialized to 1, s2 to zero.  The
         Adler-32 checksum is stored as s2*65536 + s1 in most-
         significant-byte first (network) order.








Deutsch & Gailly             Informational                      [Page 6]

RFC 1950       ZLIB Compressed Data Format Specification        May 1996


   2.3. Compliance

      A compliant compressor must produce streams with correct CMF, FLG
      and ADLER32, but need not support preset dictionaries.  When the
      zlib data format is used as part of another standard data format,
      the compressor may use only preset dictionaries that are specified
      by this other data format.  If this other format does not use the
      preset dictionary feature, the compressor must not set the FDICT
      flag.

      A compliant decompressor must check CMF, FLG, and ADLER32, and
      provide an error indication if any of these have incorrect values.
      A compliant decompressor must give an error indication if CM is
      not one of the values defined in this specification (only the
      value 8 is permitted in this version), since another value could
      indicate the presence of new features that would cause subsequent
      data to be interpreted incorrectly.  A compliant decompressor must
      give an error indication if FDICT is set and DICTID is not the
      identifier of a known preset dictionary.  A decompressor may
      ignore FLEVEL and still be compliant.  When the zlib data format
      is being used as a part of another standard format, a compliant
      decompressor must support all the preset dictionaries specified by
      the other format. When the other format does not use the preset
      dictionary feature, a compliant decompressor must reject any
      stream in which the FDICT flag is set.

3. References

   [1] Deutsch, L.P.,"GZIP Compressed Data Format Specification",
       available in ftp://ftp.uu.net/pub/archiving/zip/doc/

   [2] Thomas Boutell, "PNG (Portable Network Graphics) specification",
       available in ftp://ftp.uu.net/graphics/png/documents/

   [3] Deutsch, L.P.,"DEFLATE Compressed Data Format Specification",
       available in ftp://ftp.uu.net/pub/archiving/zip/doc/

   [4] Fletcher, J. G., "An Arithmetic Checksum for Serial
       Transmissions," IEEE Transactions on Communications, Vol. COM-30,
       No. 1, January 1982, pp. 247-252.

   [5] ITU-T Recommendation X.224, Annex D, "Checksum Algorithms,"
       November, 1993, pp. 144, 145. (Available from
       gopher://info.itu.ch). ITU-T X.244 is also the same as ISO 8073.







Deutsch & Gailly             Informational                      [Page 7]

RFC 1950       ZLIB Compressed Data Format Specification        May 1996


4. Source code

   Source code for a C language implementation of a "zlib" compliant
   library is available at ftp://ftp.uu.net/pub/archiving/zip/zlib/.

5. Security Considerations

   A decoder that fails to check the ADLER32 checksum value may be
   subject to undetected data corruption.

6. Acknowledgements

   Trademarks cited in this document are the property of their
   respective owners.

   Jean-Loup Gailly and Mark Adler designed the zlib format and wrote
   the related software described in this specification.  Glenn
   Randers-Pehrson converted this document to RFC and HTML format.

7. Authors' Addresses

   L. Peter Deutsch
   Aladdin Enterprises
   203 Santa Margarita Ave.
   Menlo Park, CA 94025

   Phone: (415) 322-0103 (AM only)
   FAX:   (415) 322-1734
   EMail: <[email protected]>


   Jean-Loup Gailly

   EMail: <[email protected]>

   Questions about the technical content of this specification can be
   sent by email to

   Jean-Loup Gailly <[email protected]> and
   Mark Adler <[email protected]>

   Editorial comments on this specification can be sent by email to

   L. Peter Deutsch <[email protected]> and
   Glenn Randers-Pehrson <[email protected]>






Deutsch & Gailly             Informational                      [Page 8]

RFC 1950       ZLIB Compressed Data Format Specification        May 1996


8. Appendix: Rationale

   8.1. Preset dictionaries

      A preset dictionary is specially useful to compress short input
      sequences. The compressor can take advantage of the dictionary
      context to encode the input in a more compact manner. The
      decompressor can be initialized with the appropriate context by
      virtually decompressing a compressed version of the dictionary
      without producing any output. However for certain compression
      algorithms such as the deflate algorithm this operation can be
      achieved without actually performing any decompression.

      The compressor and the decompressor must use exactly the same
      dictionary. The dictionary may be fixed or may be chosen among a
      certain number of predefined dictionaries, according to the kind
      of input data. The decompressor can determine which dictionary has
      been chosen by the compressor by checking the dictionary
      identifier. This document does not specify the contents of
      predefined dictionaries, since the optimal dictionaries are
      application specific. Standard data formats using this feature of
      the zlib specification must precisely define the allowed
      dictionaries.

   8.2. The Adler-32 algorithm

      The Adler-32 algorithm is much faster than the CRC32 algorithm yet
      still provides an extremely low probability of undetected errors.

      The modulo on unsigned long accumulators can be delayed for 5552
      bytes, so the modulo operation time is negligible.  If the bytes
      are a, b, c, the second sum is 3a + 2b + c + 3, and so is position
      and order sensitive, unlike the first sum, which is just a
      checksum.  That 65521 is prime is important to avoid a possible
      large class of two-byte errors that leave the check unchanged.
      (The Fletcher checksum uses 255, which is not prime and which also
      makes the Fletcher check insensitive to single byte changes 0 <->
      255.)

      The sum s1 is initialized to 1 instead of zero to make the length
      of the sequence part of s2, so that the length does not have to be
      checked separately. (Any sequence of zeroes has a Fletcher
      checksum of zero.)








Deutsch & Gailly             Informational                      [Page 9]

RFC 1950       ZLIB Compressed Data Format Specification        May 1996


9. Appendix: Sample code

   The following C code computes the Adler-32 checksum of a data buffer.
   It is written for clarity, not for speed.  The sample code is in the
   ANSI C programming language. Non C users may find it easier to read
   with these hints:

      &      Bitwise AND operator.
      >>     Bitwise right shift operator. When applied to an
             unsigned quantity, as here, right shift inserts zero bit(s)
             at the left.
      <<     Bitwise left shift operator. Left shift inserts zero
             bit(s) at the right.
      ++     "n++" increments the variable n.
      %      modulo operator: a % b is the remainder of a divided by b.

      #define BASE 65521 /* largest prime smaller than 65536 */

      /*
         Update a running Adler-32 checksum with the bytes buf[0..len-1]
       and return the updated checksum. The Adler-32 checksum should be
       initialized to 1.

       Usage example:

         unsigned long adler = 1L;

         while (read_buffer(buffer, length) != EOF) {
           adler = update_adler32(adler, buffer, length);
         }
         if (adler != original_adler) error();
      */
      unsigned long update_adler32(unsigned long adler,
         unsigned char *buf, int len)
      {
        unsigned long s1 = adler & 0xffff;
        unsigned long s2 = (adler >> 16) & 0xffff;
        int n;

        for (n = 0; n < len; n++) {
          s1 = (s1 + buf[n]) % BASE;
          s2 = (s2 + s1)     % BASE;
        }
        return (s2 << 16) + s1;
      }

      /* Return the adler32 of the bytes buf[0..len-1] */




Deutsch & Gailly             Informational                     [Page 10]

RFC 1950       ZLIB Compressed Data Format Specification        May 1996


      unsigned long adler32(unsigned char *buf, int len)
      {
        return update_adler32(1L, buf, len);
      }















































Deutsch & Gailly             Informational                     [Page 11]


Network Working Group                                         P. Deutsch
Request for Comments: 1951                           Aladdin Enterprises
Category: Informational                                         May 1996


        DEFLATE Compressed Data Format Specification version 1.3

Status of This Memo

   This memo provides information for the Internet community.  This memo
   does not specify an Internet standard of any kind.  Distribution of
   this memo is unlimited.

IESG Note:

   The IESG takes no position on the validity of any Intellectual
   Property Rights statements contained in this document.

Notices

   Copyright (c) 1996 L. Peter Deutsch

   Permission is granted to copy and distribute this document for any
   purpose and without charge, including translations into other
   languages and incorporation into compilations, provided that the
   copyright notice and this notice are preserved, and that any
   substantive changes or deletions from the original are clearly
   marked.

   A pointer to the latest version of this and related documentation in
   HTML format can be found at the URL
   <ftp://ftp.uu.net/graphics/png/documents/zlib/zdoc-index.html>.

Abstract

   This specification defines a lossless compressed data format that
   compresses data using a combination of the LZ77 algorithm and Huffman
   coding, with efficiency comparable to the best currently available
   general-purpose compression methods.  The data can be produced or
   consumed, even for an arbitrarily long sequentially presented input
   data stream, using only an a priori bounded amount of intermediate
   storage.  The format can be implemented readily in a manner not
   covered by patents.








Deutsch                      Informational                      [Page 1]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


Table of Contents

   1. Introduction ................................................... 2
      1.1. Purpose ................................................... 2
      1.2. Intended audience ......................................... 3
      1.3. Scope ..................................................... 3
      1.4. Compliance ................................................ 3
      1.5.  Definitions of terms and conventions used ................ 3
      1.6. Changes from previous versions ............................ 4
   2. Compressed representation overview ............................. 4
   3. Detailed specification ......................................... 5
      3.1. Overall conventions ....................................... 5
          3.1.1. Packing into bytes .................................. 5
      3.2. Compressed block format ................................... 6
          3.2.1. Synopsis of prefix and Huffman coding ............... 6
          3.2.2. Use of Huffman coding in the "deflate" format ....... 7
          3.2.3. Details of block format ............................. 9
          3.2.4. Non-compressed blocks (BTYPE=00) ................... 11
          3.2.5. Compressed blocks (length and distance codes) ...... 11
          3.2.6. Compression with fixed Huffman codes (BTYPE=01) .... 12
          3.2.7. Compression with dynamic Huffman codes (BTYPE=10) .. 13
      3.3. Compliance ............................................... 14
   4. Compression algorithm details ................................. 14
   5. References .................................................... 16
   6. Security Considerations ....................................... 16
   7. Source code ................................................... 16
   8. Acknowledgements .............................................. 16
   9. Author's Address .............................................. 17

1. Introduction

   1.1. Purpose

      The purpose of this specification is to define a lossless
      compressed data format that:
          * Is independent of CPU type, operating system, file system,
            and character set, and hence can be used for interchange;
          * Can be produced or consumed, even for an arbitrarily long
            sequentially presented input data stream, using only an a
            priori bounded amount of intermediate storage, and hence
            can be used in data communications or similar structures
            such as Unix filters;
          * Compresses data with efficiency comparable to the best
            currently available general-purpose compression methods,
            and in particular considerably better than the "compress"
            program;
          * Can be implemented readily in a manner not covered by
            patents, and hence can be practiced freely;



Deutsch                      Informational                      [Page 2]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


          * Is compatible with the file format produced by the current
            widely used gzip utility, in that conforming decompressors
            will be able to read data produced by the existing gzip
            compressor.

      The data format defined by this specification does not attempt to:

          * Allow random access to compressed data;
          * Compress specialized data (e.g., raster graphics) as well
            as the best currently available specialized algorithms.

      A simple counting argument shows that no lossless compression
      algorithm can compress every possible input data set.  For the
      format defined here, the worst case expansion is 5 bytes per 32K-
      byte block, i.e., a size increase of 0.015% for large data sets.
      English text usually compresses by a factor of 2.5 to 3;
      executable files usually compress somewhat less; graphical data
      such as raster images may compress much more.

   1.2. Intended audience

      This specification is intended for use by implementors of software
      to compress data into "deflate" format and/or decompress data from
      "deflate" format.

      The text of the specification assumes a basic background in
      programming at the level of bits and other primitive data
      representations.  Familiarity with the technique of Huffman coding
      is helpful but not required.

   1.3. Scope

      The specification specifies a method for representing a sequence
      of bytes as a (usually shorter) sequence of bits, and a method for
      packing the latter bit sequence into bytes.

   1.4. Compliance

      Unless otherwise indicated below, a compliant decompressor must be
      able to accept and decompress any data set that conforms to all
      the specifications presented here; a compliant compressor must
      produce data sets that conform to all the specifications presented
      here.

   1.5.  Definitions of terms and conventions used

      Byte: 8 bits stored or transmitted as a unit (same as an octet).
      For this specification, a byte is exactly 8 bits, even on machines



Deutsch                      Informational                      [Page 3]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


      which store a character on a number of bits different from eight.
      See below, for the numbering of bits within a byte.

      String: a sequence of arbitrary bytes.

   1.6. Changes from previous versions

      There have been no technical changes to the deflate format since
      version 1.1 of this specification.  In version 1.2, some
      terminology was changed.  Version 1.3 is a conversion of the
      specification to RFC style.

2. Compressed representation overview

   A compressed data set consists of a series of blocks, corresponding
   to successive blocks of input data.  The block sizes are arbitrary,
   except that non-compressible blocks are limited to 65,535 bytes.

   Each block is compressed using a combination of the LZ77 algorithm
   and Huffman coding. The Huffman trees for each block are independent
   of those for previous or subsequent blocks; the LZ77 algorithm may
   use a reference to a duplicated string occurring in a previous block,
   up to 32K input bytes before.

   Each block consists of two parts: a pair of Huffman code trees that
   describe the representation of the compressed data part, and a
   compressed data part.  (The Huffman trees themselves are compressed
   using Huffman encoding.)  The compressed data consists of a series of
   elements of two types: literal bytes (of strings that have not been
   detected as duplicated within the previous 32K input bytes), and
   pointers to duplicated strings, where a pointer is represented as a
   pair <length, backward distance>.  The representation used in the
   "deflate" format limits distances to 32K bytes and lengths to 258
   bytes, but does not limit the size of a block, except for
   uncompressible blocks, which are limited as noted above.

   Each type of value (literals, distances, and lengths) in the
   compressed data is represented using a Huffman code, using one code
   tree for literals and lengths and a separate code tree for distances.
   The code trees for each block appear in a compact form just before
   the compressed data for that block.










Deutsch                      Informational                      [Page 4]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


3. Detailed specification

   3.1. Overall conventions In the diagrams below, a box like this:

         +---+
         |   | <-- the vertical bars might be missing
         +---+

      represents one byte; a box like this:

         +==============+
         |              |
         +==============+

      represents a variable number of bytes.

      Bytes stored within a computer do not have a "bit order", since
      they are always treated as a unit.  However, a byte considered as
      an integer between 0 and 255 does have a most- and least-
      significant bit, and since we write numbers with the most-
      significant digit on the left, we also write bytes with the most-
      significant bit on the left.  In the diagrams below, we number the
      bits of a byte so that bit 0 is the least-significant bit, i.e.,
      the bits are numbered:

         +--------+
         |76543210|
         +--------+

      Within a computer, a number may occupy multiple bytes.  All
      multi-byte numbers in the format described here are stored with
      the least-significant byte first (at the lower memory address).
      For example, the decimal number 520 is stored as:

             0        1
         +--------+--------+
         |00001000|00000010|
         +--------+--------+
          ^        ^
          |        |
          |        + more significant byte = 2 x 256
          + less significant byte = 8

      3.1.1. Packing into bytes

         This document does not address the issue of the order in which
         bits of a byte are transmitted on a bit-sequential medium,
         since the final data format described here is byte- rather than



Deutsch                      Informational                      [Page 5]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


         bit-oriented.  However, we describe the compressed block format
         in below, as a sequence of data elements of various bit
         lengths, not a sequence of bytes.  We must therefore specify
         how to pack these data elements into bytes to form the final
         compressed byte sequence:

             * Data elements are packed into bytes in order of
               increasing bit number within the byte, i.e., starting
               with the least-significant bit of the byte.
             * Data elements other than Huffman codes are packed
               starting with the least-significant bit of the data
               element.
             * Huffman codes are packed starting with the most-
               significant bit of the code.

         In other words, if one were to print out the compressed data as
         a sequence of bytes, starting with the first byte at the
         *right* margin and proceeding to the *left*, with the most-
         significant bit of each byte on the left as usual, one would be
         able to parse the result from right to left, with fixed-width
         elements in the correct MSB-to-LSB order and Huffman codes in
         bit-reversed order (i.e., with the first bit of the code in the
         relative LSB position).

   3.2. Compressed block format

      3.2.1. Synopsis of prefix and Huffman coding

         Prefix coding represents symbols from an a priori known
         alphabet by bit sequences (codes), one code for each symbol, in
         a manner such that different symbols may be represented by bit
         sequences of different lengths, but a parser can always parse
         an encoded string unambiguously symbol-by-symbol.

         We define a prefix code in terms of a binary tree in which the
         two edges descending from each non-leaf node are labeled 0 and
         1 and in which the leaf nodes correspond one-for-one with (are
         labeled with) the symbols of the alphabet; then the code for a
         symbol is the sequence of 0's and 1's on the edges leading from
         the root to the leaf labeled with that symbol.  For example:











Deutsch                      Informational                      [Page 6]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


                          /\              Symbol    Code
                         0  1             ------    ----
                        /    \                A      00
                       /\     B               B       1
                      0  1                    C     011
                     /    \                   D     010
                    A     /\
                         0  1
                        /    \
                       D      C

         A parser can decode the next symbol from an encoded input
         stream by walking down the tree from the root, at each step
         choosing the edge corresponding to the next input bit.

         Given an alphabet with known symbol frequencies, the Huffman
         algorithm allows the construction of an optimal prefix code
         (one which represents strings with those symbol frequencies
         using the fewest bits of any possible prefix codes for that
         alphabet).  Such a code is called a Huffman code.  (See
         reference [1] in Chapter 5, references for additional
         information on Huffman codes.)

         Note that in the "deflate" format, the Huffman codes for the
         various alphabets must not exceed certain maximum code lengths.
         This constraint complicates the algorithm for computing code
         lengths from symbol frequencies.  Again, see Chapter 5,
         references for details.

      3.2.2. Use of Huffman coding in the "deflate" format

         The Huffman codes used for each alphabet in the "deflate"
         format have two additional rules:

             * All codes of a given bit length have lexicographically
               consecutive values, in the same order as the symbols
               they represent;

             * Shorter codes lexicographically precede longer codes.












Deutsch                      Informational                      [Page 7]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


         We could recode the example above to follow this rule as
         follows, assuming that the order of the alphabet is ABCD:

            Symbol  Code
            ------  ----
            A       10
            B       0
            C       110
            D       111

         I.e., 0 precedes 10 which precedes 11x, and 110 and 111 are
         lexicographically consecutive.

         Given this rule, we can define the Huffman code for an alphabet
         just by giving the bit lengths of the codes for each symbol of
         the alphabet in order; this is sufficient to determine the
         actual codes.  In our example, the code is completely defined
         by the sequence of bit lengths (2, 1, 3, 3).  The following
         algorithm generates the codes as integers, intended to be read
         from most- to least-significant bit.  The code lengths are
         initially in tree[I].Len; the codes are produced in
         tree[I].Code.

         1)  Count the number of codes for each code length.  Let
             bl_count[N] be the number of codes of length N, N >= 1.

         2)  Find the numerical value of the smallest code for each
             code length:

                code = 0;
                bl_count[0] = 0;
                for (bits = 1; bits <= MAX_BITS; bits++) {
                    code = (code + bl_count[bits-1]) << 1;
                    next_code[bits] = code;
                }

         3)  Assign numerical values to all codes, using consecutive
             values for all codes of the same length with the base
             values determined at step 2. Codes that are never used
             (which have a bit length of zero) must not be assigned a
             value.

                for (n = 0;  n <= max_code; n++) {
                    len = tree[n].Len;
                    if (len != 0) {
                        tree[n].Code = next_code[len];
                        next_code[len]++;
                    }



Deutsch                      Informational                      [Page 8]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


                }

         Example:

         Consider the alphabet ABCDEFGH, with bit lengths (3, 3, 3, 3,
         3, 2, 4, 4).  After step 1, we have:

            N      bl_count[N]
            -      -----------
            2      1
            3      5
            4      2

         Step 2 computes the following next_code values:

            N      next_code[N]
            -      ------------
            1      0
            2      0
            3      2
            4      14

         Step 3 produces the following code values:

            Symbol Length   Code
            ------ ------   ----
            A       3        010
            B       3        011
            C       3        100
            D       3        101
            E       3        110
            F       2         00
            G       4       1110
            H       4       1111

      3.2.3. Details of block format

         Each block of compressed data begins with 3 header bits
         containing the following data:

            first bit       BFINAL
            next 2 bits     BTYPE

         Note that the header bits do not necessarily begin on a byte
         boundary, since a block does not necessarily occupy an integral
         number of bytes.





Deutsch                      Informational                      [Page 9]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


         BFINAL is set if and only if this is the last block of the data
         set.

         BTYPE specifies how the data are compressed, as follows:

            00 - no compression
            01 - compressed with fixed Huffman codes
            10 - compressed with dynamic Huffman codes
            11 - reserved (error)

         The only difference between the two compressed cases is how the
         Huffman codes for the literal/length and distance alphabets are
         defined.

         In all cases, the decoding algorithm for the actual data is as
         follows:

            do
               read block header from input stream.
               if stored with no compression
                  skip any remaining bits in current partially
                     processed byte
                  read LEN and NLEN (see next section)
                  copy LEN bytes of data to output
               otherwise
                  if compressed with dynamic Huffman codes
                     read representation of code trees (see
                        subsection below)
                  loop (until end of block code recognized)
                     decode literal/length value from input stream
                     if value < 256
                        copy value (literal byte) to output stream
                     otherwise
                        if value = end of block (256)
                           break from loop
                        otherwise (value = 257..285)
                           decode distance from input stream

                           move backwards distance bytes in the output
                           stream, and copy length bytes from this
                           position to the output stream.
                  end loop
            while not last block

         Note that a duplicated string reference may refer to a string
         in a previous block; i.e., the backward distance may cross one
         or more block boundaries.  However a distance cannot refer past
         the beginning of the output stream.  (An application using a



Deutsch                      Informational                     [Page 10]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


         preset dictionary might discard part of the output stream; a
         distance can refer to that part of the output stream anyway)
         Note also that the referenced string may overlap the current
         position; for example, if the last 2 bytes decoded have values
         X and Y, a string reference with <length = 5, distance = 2>
         adds X,Y,X,Y,X to the output stream.

         We now specify each compression method in turn.

      3.2.4. Non-compressed blocks (BTYPE=00)

         Any bits of input up to the next byte boundary are ignored.
         The rest of the block consists of the following information:

              0   1   2   3   4...
            +---+---+---+---+================================+
            |  LEN  | NLEN  |... LEN bytes of literal data...|
            +---+---+---+---+================================+

         LEN is the number of data bytes in the block.  NLEN is the
         one's complement of LEN.

      3.2.5. Compressed blocks (length and distance codes)

         As noted above, encoded data blocks in the "deflate" format
         consist of sequences of symbols drawn from three conceptually
         distinct alphabets: either literal bytes, from the alphabet of
         byte values (0..255), or <length, backward distance> pairs,
         where the length is drawn from (3..258) and the distance is
         drawn from (1..32,768).  In fact, the literal and length
         alphabets are merged into a single alphabet (0..285), where
         values 0..255 represent literal bytes, the value 256 indicates
         end-of-block, and values 257..285 represent length codes
         (possibly in conjunction with extra bits following the symbol
         code) as follows:
















Deutsch                      Informational                     [Page 11]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


                 Extra               Extra               Extra
            Code Bits Length(s) Code Bits Lengths   Code Bits Length(s)
            ---- ---- ------     ---- ---- -------   ---- ---- -------
             257   0     3       267   1   15,16     277   4   67-82
             258   0     4       268   1   17,18     278   4   83-98
             259   0     5       269   2   19-22     279   4   99-114
             260   0     6       270   2   23-26     280   4  115-130
             261   0     7       271   2   27-30     281   5  131-162
             262   0     8       272   2   31-34     282   5  163-194
             263   0     9       273   3   35-42     283   5  195-226
             264   0    10       274   3   43-50     284   5  227-257
             265   1  11,12      275   3   51-58     285   0    258
             266   1  13,14      276   3   59-66

         The extra bits should be interpreted as a machine integer
         stored with the most-significant bit first, e.g., bits 1110
         represent the value 14.

                  Extra           Extra               Extra
             Code Bits Dist  Code Bits   Dist     Code Bits Distance
             ---- ---- ----  ---- ----  ------    ---- ---- --------
               0   0    1     10   4     33-48    20    9   1025-1536
               1   0    2     11   4     49-64    21    9   1537-2048
               2   0    3     12   5     65-96    22   10   2049-3072
               3   0    4     13   5     97-128   23   10   3073-4096
               4   1   5,6    14   6    129-192   24   11   4097-6144
               5   1   7,8    15   6    193-256   25   11   6145-8192
               6   2   9-12   16   7    257-384   26   12  8193-12288
               7   2  13-16   17   7    385-512   27   12 12289-16384
               8   3  17-24   18   8    513-768   28   13 16385-24576
               9   3  25-32   19   8   769-1024   29   13 24577-32768

      3.2.6. Compression with fixed Huffman codes (BTYPE=01)

         The Huffman codes for the two alphabets are fixed, and are not
         represented explicitly in the data.  The Huffman code lengths
         for the literal/length alphabet are:

                   Lit Value    Bits        Codes
                   ---------    ----        -----
                     0 - 143     8          00110000 through
                                            10111111
                   144 - 255     9          110010000 through
                                            111111111
                   256 - 279     7          0000000 through
                                            0010111
                   280 - 287     8          11000000 through
                                            11000111



Deutsch                      Informational                     [Page 12]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


         The code lengths are sufficient to generate the actual codes,
         as described above; we show the codes in the table for added
         clarity.  Literal/length values 286-287 will never actually
         occur in the compressed data, but participate in the code
         construction.

         Distance codes 0-31 are represented by (fixed-length) 5-bit
         codes, with possible additional bits as shown in the table
         shown in Paragraph 3.2.5, above.  Note that distance codes 30-
         31 will never actually occur in the compressed data.

      3.2.7. Compression with dynamic Huffman codes (BTYPE=10)

         The Huffman codes for the two alphabets appear in the block
         immediately after the header bits and before the actual
         compressed data, first the literal/length code and then the
         distance code.  Each code is defined by a sequence of code
         lengths, as discussed in Paragraph 3.2.2, above.  For even
         greater compactness, the code length sequences themselves are
         compressed using a Huffman code.  The alphabet for code lengths
         is as follows:

               0 - 15: Represent code lengths of 0 - 15
                   16: Copy the previous code length 3 - 6 times.
                       The next 2 bits indicate repeat length
                             (0 = 3, ... , 3 = 6)
                          Example:  Codes 8, 16 (+2 bits 11),
                                    16 (+2 bits 10) will expand to
                                    12 code lengths of 8 (1 + 6 + 5)
                   17: Repeat a code length of 0 for 3 - 10 times.
                       (3 bits of length)
                   18: Repeat a code length of 0 for 11 - 138 times
                       (7 bits of length)

         A code length of 0 indicates that the corresponding symbol in
         the literal/length or distance alphabet will not occur in the
         block, and should not participate in the Huffman code
         construction algorithm given earlier.  If only one distance
         code is used, it is encoded using one bit, not zero bits; in
         this case there is a single code length of one, with one unused
         code.  One distance code of zero bits means that there are no
         distance codes used at all (the data is all literals).

         We can now define the format of the block:

               5 Bits: HLIT, # of Literal/Length codes - 257 (257 - 286)
               5 Bits: HDIST, # of Distance codes - 1        (1 - 32)
               4 Bits: HCLEN, # of Code Length codes - 4     (4 - 19)



Deutsch                      Informational                     [Page 13]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


               (HCLEN + 4) x 3 bits: code lengths for the code length
                  alphabet given just above, in the order: 16, 17, 18,
                  0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15

                  These code lengths are interpreted as 3-bit integers
                  (0-7); as above, a code length of 0 means the
                  corresponding symbol (literal/length or distance code
                  length) is not used.

               HLIT + 257 code lengths for the literal/length alphabet,
                  encoded using the code length Huffman code

               HDIST + 1 code lengths for the distance alphabet,
                  encoded using the code length Huffman code

               The actual compressed data of the block,
                  encoded using the literal/length and distance Huffman
                  codes

               The literal/length symbol 256 (end of data),
                  encoded using the literal/length Huffman code

         The code length repeat codes can cross from HLIT + 257 to the
         HDIST + 1 code lengths.  In other words, all code lengths form
         a single sequence of HLIT + HDIST + 258 values.

   3.3. Compliance

      A compressor may limit further the ranges of values specified in
      the previous section and still be compliant; for example, it may
      limit the range of backward pointers to some value smaller than
      32K.  Similarly, a compressor may limit the size of blocks so that
      a compressible block fits in memory.

      A compliant decompressor must accept the full range of possible
      values defined in the previous section, and must accept blocks of
      arbitrary size.

4. Compression algorithm details

   While it is the intent of this document to define the "deflate"
   compressed data format without reference to any particular
   compression algorithm, the format is related to the compressed
   formats produced by LZ77 (Lempel-Ziv 1977, see reference [2] below);
   since many variations of LZ77 are patented, it is strongly
   recommended that the implementor of a compressor follow the general
   algorithm presented here, which is known not to be patented per se.
   The material in this section is not part of the definition of the



Deutsch                      Informational                     [Page 14]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


   specification per se, and a compressor need not follow it in order to
   be compliant.

   The compressor terminates a block when it determines that starting a
   new block with fresh trees would be useful, or when the block size
   fills up the compressor's block buffer.

   The compressor uses a chained hash table to find duplicated strings,
   using a hash function that operates on 3-byte sequences.  At any
   given point during compression, let XYZ be the next 3 input bytes to
   be examined (not necessarily all different, of course).  First, the
   compressor examines the hash chain for XYZ.  If the chain is empty,
   the compressor simply writes out X as a literal byte and advances one
   byte in the input.  If the hash chain is not empty, indicating that
   the sequence XYZ (or, if we are unlucky, some other 3 bytes with the
   same hash function value) has occurred recently, the compressor
   compares all strings on the XYZ hash chain with the actual input data
   sequence starting at the current point, and selects the longest
   match.

   The compressor searches the hash chains starting with the most recent
   strings, to favor small distances and thus take advantage of the
   Huffman encoding.  The hash chains are singly linked. There are no
   deletions from the hash chains; the algorithm simply discards matches
   that are too old.  To avoid a worst-case situation, very long hash
   chains are arbitrarily truncated at a certain length, determined by a
   run-time parameter.

   To improve overall compression, the compressor optionally defers the
   selection of matches ("lazy matching"): after a match of length N has
   been found, the compressor searches for a longer match starting at
   the next input byte.  If it finds a longer match, it truncates the
   previous match to a length of one (thus producing a single literal
   byte) and then emits the longer match.  Otherwise, it emits the
   original match, and, as described above, advances N bytes before
   continuing.

   Run-time parameters also control this "lazy match" procedure.  If
   compression ratio is most important, the compressor attempts a
   complete second search regardless of the length of the first match.
   In the normal case, if the current match is "long enough", the
   compressor reduces the search for a longer match, thus speeding up
   the process.  If speed is most important, the compressor inserts new
   strings in the hash table only when no match was found, or when the
   match is not "too long".  This degrades the compression ratio but
   saves time since there are both fewer insertions and fewer searches.





Deutsch                      Informational                     [Page 15]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


5. References

   [1] Huffman, D. A., "A Method for the Construction of Minimum
       Redundancy Codes", Proceedings of the Institute of Radio
       Engineers, September 1952, Volume 40, Number 9, pp. 1098-1101.

   [2] Ziv J., Lempel A., "A Universal Algorithm for Sequential Data
       Compression", IEEE Transactions on Information Theory, Vol. 23,
       No. 3, pp. 337-343.

   [3] Gailly, J.-L., and Adler, M., ZLIB documentation and sources,
       available in ftp://ftp.uu.net/pub/archiving/zip/doc/

   [4] Gailly, J.-L., and Adler, M., GZIP documentation and sources,
       available as gzip-*.tar in ftp://prep.ai.mit.edu/pub/gnu/

   [5] Schwartz, E. S., and Kallick, B. "Generating a canonical prefix
       encoding." Comm. ACM, 7,3 (Mar. 1964), pp. 166-169.

   [6] Hirschberg and Lelewer, "Efficient decoding of prefix codes,"
       Comm. ACM, 33,4, April 1990, pp. 449-459.

6. Security Considerations

   Any data compression method involves the reduction of redundancy in
   the data.  Consequently, any corruption of the data is likely to have
   severe effects and be difficult to correct.  Uncompressed text, on
   the other hand, will probably still be readable despite the presence
   of some corrupted bytes.

   It is recommended that systems using this data format provide some
   means of validating the integrity of the compressed data.  See
   reference [3], for example.

7. Source code

   Source code for a C language implementation of a "deflate" compliant
   compressor and decompressor is available within the zlib package at
   ftp://ftp.uu.net/pub/archiving/zip/zlib/.

8. Acknowledgements

   Trademarks cited in this document are the property of their
   respective owners.

   Phil Katz designed the deflate format.  Jean-Loup Gailly and Mark
   Adler wrote the related software described in this specification.
   Glenn Randers-Pehrson converted this document to RFC and HTML format.



Deutsch                      Informational                     [Page 16]

RFC 1951      DEFLATE Compressed Data Format Specification      May 1996


9. Author's Address

   L. Peter Deutsch
   Aladdin Enterprises
   203 Santa Margarita Ave.
   Menlo Park, CA 94025

   Phone: (415) 322-0103 (AM only)
   FAX:   (415) 322-1734
   EMail: <[email protected]>

   Questions about the technical content of this specification can be
   sent by email to:

   Jean-Loup Gailly <[email protected]> and
   Mark Adler <[email protected]>

   Editorial comments on this specification can be sent by email to:

   L. Peter Deutsch <[email protected]> and
   Glenn Randers-Pehrson <[email protected]>






























Deutsch                      Informational                     [Page 17]


Network Working Group                                         P. Deutsch
Request for Comments: 1952                           Aladdin Enterprises
Category: Informational                                         May 1996


               GZIP file format specification version 4.3

Status of This Memo

   This memo provides information for the Internet community.  This memo
   does not specify an Internet standard of any kind.  Distribution of
   this memo is unlimited.

IESG Note:

   The IESG takes no position on the validity of any Intellectual
   Property Rights statements contained in this document.

Notices

   Copyright (c) 1996 L. Peter Deutsch

   Permission is granted to copy and distribute this document for any
   purpose and without charge, including translations into other
   languages and incorporation into compilations, provided that the
   copyright notice and this notice are preserved, and that any
   substantive changes or deletions from the original are clearly
   marked.

   A pointer to the latest version of this and related documentation in
   HTML format can be found at the URL
   <ftp://ftp.uu.net/graphics/png/documents/zlib/zdoc-index.html>.

Abstract

   This specification defines a lossless compressed data format that is
   compatible with the widely used GZIP utility.  The format includes a
   cyclic redundancy check value for detecting data corruption.  The
   format presently uses the DEFLATE method of compression but can be
   easily extended to use other compression methods.  The format can be
   implemented readily in a manner not covered by patents.










Deutsch                      Informational                      [Page 1]

RFC 1952             GZIP File Format Specification             May 1996


Table of Contents

   1. Introduction ................................................... 2
      1.1. Purpose ................................................... 2
      1.2. Intended audience ......................................... 3
      1.3. Scope ..................................................... 3
      1.4. Compliance ................................................ 3
      1.5. Definitions of terms and conventions used ................. 3
      1.6. Changes from previous versions ............................ 3
   2. Detailed specification ......................................... 4
      2.1. Overall conventions ....................................... 4
      2.2. File format ............................................... 5
      2.3. Member format ............................................. 5
          2.3.1. Member header and trailer ........................... 6
              2.3.1.1. Extra field ................................... 8
              2.3.1.2. Compliance .................................... 9
      3. References .................................................. 9
      4. Security Considerations .................................... 10
      5. Acknowledgements ........................................... 10
      6. Author's Address ........................................... 10
      7. Appendix: Jean-Loup Gailly's gzip utility .................. 11
      8. Appendix: Sample CRC Code .................................. 11

1. Introduction

   1.1. Purpose

      The purpose of this specification is to define a lossless
      compressed data format that:

          * Is independent of CPU type, operating system, file system,
            and character set, and hence can be used for interchange;
          * Can compress or decompress a data stream (as opposed to a
            randomly accessible file) to produce another data stream,
            using only an a priori bounded amount of intermediate
            storage, and hence can be used in data communications or
            similar structures such as Unix filters;
          * Compresses data with efficiency comparable to the best
            currently available general-purpose compression methods,
            and in particular considerably better than the "compress"
            program;
          * Can be implemented readily in a manner not covered by
            patents, and hence can be practiced freely;
          * Is compatible with the file format produced by the current
            widely used gzip utility, in that conforming decompressors
            will be able to read data produced by the existing gzip
            compressor.




Deutsch                      Informational                      [Page 2]

RFC 1952             GZIP File Format Specification             May 1996


      The data format defined by this specification does not attempt to:

          * Provide random access to compressed data;
          * Compress specialized data (e.g., raster graphics) as well as
            the best currently available specialized algorithms.

   1.2. Intended audience

      This specification is intended for use by implementors of software
      to compress data into gzip format and/or decompress data from gzip
      format.

      The text of the specification assumes a basic background in
      programming at the level of bits and other primitive data
      representations.

   1.3. Scope

      The specification specifies a compression method and a file format
      (the latter assuming only that a file can store a sequence of
      arbitrary bytes).  It does not specify any particular interface to
      a file system or anything about character sets or encodings
      (except for file names and comments, which are optional).

   1.4. Compliance

      Unless otherwise indicated below, a compliant decompressor must be
      able to accept and decompress any file that conforms to all the
      specifications presented here; a compliant compressor must produce
      files that conform to all the specifications presented here.  The
      material in the appendices is not part of the specification per se
      and is not relevant to compliance.

   1.5. Definitions of terms and conventions used

      byte: 8 bits stored or transmitted as a unit (same as an octet).
      (For this specification, a byte is exactly 8 bits, even on
      machines which store a character on a number of bits different
      from 8.)  See below for the numbering of bits within a byte.

   1.6. Changes from previous versions

      There have been no technical changes to the gzip format since
      version 4.1 of this specification.  In version 4.2, some
      terminology was changed, and the sample CRC code was rewritten for
      clarity and to eliminate the requirement for the caller to do pre-
      and post-conditioning.  Version 4.3 is a conversion of the
      specification to RFC style.



Deutsch                      Informational                      [Page 3]

RFC 1952             GZIP File Format Specification             May 1996


2. Detailed specification

   2.1. Overall conventions

      In the diagrams below, a box like this:

         +---+
         |   | <-- the vertical bars might be missing
         +---+

      represents one byte; a box like this:

         +==============+
         |              |
         +==============+

      represents a variable number of bytes.

      Bytes stored within a computer do not have a "bit order", since
      they are always treated as a unit.  However, a byte considered as
      an integer between 0 and 255 does have a most- and least-
      significant bit, and since we write numbers with the most-
      significant digit on the left, we also write bytes with the most-
      significant bit on the left.  In the diagrams below, we number the
      bits of a byte so that bit 0 is the least-significant bit, i.e.,
      the bits are numbered:

         +--------+
         |76543210|
         +--------+

      This document does not address the issue of the order in which
      bits of a byte are transmitted on a bit-sequential medium, since
      the data format described here is byte- rather than bit-oriented.

      Within a computer, a number may occupy multiple bytes.  All
      multi-byte numbers in the format described here are stored with
      the least-significant byte first (at the lower memory address).
      For example, the decimal number 520 is stored as:

             0        1
         +--------+--------+
         |00001000|00000010|
         +--------+--------+
          ^        ^
          |        |
          |        + more significant byte = 2 x 256
          + less significant byte = 8



Deutsch                      Informational                      [Page 4]

RFC 1952             GZIP File Format Specification             May 1996


   2.2. File format

      A gzip file consists of a series of "members" (compressed data
      sets).  The format of each member is specified in the following
      section.  The members simply appear one after another in the file,
      with no additional information before, between, or after them.

   2.3. Member format

      Each member has the following structure:

         +---+---+---+---+---+---+---+---+---+---+
         |ID1|ID2|CM |FLG|     MTIME     |XFL|OS | (more-->)
         +---+---+---+---+---+---+---+---+---+---+

      (if FLG.FEXTRA set)

         +---+---+=================================+
         | XLEN  |...XLEN bytes of "extra field"...| (more-->)
         +---+---+=================================+

      (if FLG.FNAME set)

         +=========================================+
         |...original file name, zero-terminated...| (more-->)
         +=========================================+

      (if FLG.FCOMMENT set)

         +===================================+
         |...file comment, zero-terminated...| (more-->)
         +===================================+

      (if FLG.FHCRC set)

         +---+---+
         | CRC16 |
         +---+---+

         +=======================+
         |...compressed blocks...| (more-->)
         +=======================+

           0   1   2   3   4   5   6   7
         +---+---+---+---+---+---+---+---+
         |     CRC32     |     ISIZE     |
         +---+---+---+---+---+---+---+---+




Deutsch                      Informational                      [Page 5]

RFC 1952             GZIP File Format Specification             May 1996


      2.3.1. Member header and trailer

         ID1 (IDentification 1)
         ID2 (IDentification 2)
            These have the fixed values ID1 = 31 (0x1f, \037), ID2 = 139
            (0x8b, \213), to identify the file as being in gzip format.

         CM (Compression Method)
            This identifies the compression method used in the file.  CM
            = 0-7 are reserved.  CM = 8 denotes the "deflate"
            compression method, which is the one customarily used by
            gzip and which is documented elsewhere.

         FLG (FLaGs)
            This flag byte is divided into individual bits as follows:

               bit 0   FTEXT
               bit 1   FHCRC
               bit 2   FEXTRA
               bit 3   FNAME
               bit 4   FCOMMENT
               bit 5   reserved
               bit 6   reserved
               bit 7   reserved

            If FTEXT is set, the file is probably ASCII text.  This is
            an optional indication, which the compressor may set by
            checking a small amount of the input data to see whether any
            non-ASCII characters are present.  In case of doubt, FTEXT
            is cleared, indicating binary data. For systems which have
            different file formats for ascii text and binary data, the
            decompressor can use FTEXT to choose the appropriate format.
            We deliberately do not specify the algorithm used to set
            this bit, since a compressor always has the option of
            leaving it cleared and a decompressor always has the option
            of ignoring it and letting some other program handle issues
            of data conversion.

            If FHCRC is set, a CRC16 for the gzip header is present,
            immediately before the compressed data. The CRC16 consists
            of the two least significant bytes of the CRC32 for all
            bytes of the gzip header up to and not including the CRC16.
            [The FHCRC bit was never set by versions of gzip up to
            1.2.4, even though it was documented with a different
            meaning in gzip 1.2.4.]

            If FEXTRA is set, optional extra fields are present, as
            described in a following section.



Deutsch                      Informational                      [Page 6]

RFC 1952             GZIP File Format Specification             May 1996


            If FNAME is set, an original file name is present,
            terminated by a zero byte.  The name must consist of ISO
            8859-1 (LATIN-1) characters; on operating systems using
            EBCDIC or any other character set for file names, the name
            must be translated to the ISO LATIN-1 character set.  This
            is the original name of the file being compressed, with any
            directory components removed, and, if the file being
            compressed is on a file system with case insensitive names,
            forced to lower case. There is no original file name if the
            data was compressed from a source other than a named file;
            for example, if the source was stdin on a Unix system, there
            is no file name.

            If FCOMMENT is set, a zero-terminated file comment is
            present.  This comment is not interpreted; it is only
            intended for human consumption.  The comment must consist of
            ISO 8859-1 (LATIN-1) characters.  Line breaks should be
            denoted by a single line feed character (10 decimal).

            Reserved FLG bits must be zero.

         MTIME (Modification TIME)
            This gives the most recent modification time of the original
            file being compressed.  The time is in Unix format, i.e.,
            seconds since 00:00:00 GMT, Jan.  1, 1970.  (Note that this
            may cause problems for MS-DOS and other systems that use
            local rather than Universal time.)  If the compressed data
            did not come from a file, MTIME is set to the time at which
            compression started.  MTIME = 0 means no time stamp is
            available.

         XFL (eXtra FLags)
            These flags are available for use by specific compression
            methods.  The "deflate" method (CM = 8) sets these flags as
            follows:

               XFL = 2 - compressor used maximum compression,
                         slowest algorithm
               XFL = 4 - compressor used fastest algorithm

         OS (Operating System)
            This identifies the type of file system on which compression
            took place.  This may be useful in determining end-of-line
            convention for text files.  The currently defined values are
            as follows:






Deutsch                      Informational                      [Page 7]

RFC 1952             GZIP File Format Specification             May 1996


                 0 - FAT filesystem (MS-DOS, OS/2, NT/Win32)
                 1 - Amiga
                 2 - VMS (or OpenVMS)
                 3 - Unix
                 4 - VM/CMS
                 5 - Atari TOS
                 6 - HPFS filesystem (OS/2, NT)
                 7 - Macintosh
                 8 - Z-System
                 9 - CP/M
                10 - TOPS-20
                11 - NTFS filesystem (NT)
                12 - QDOS
                13 - Acorn RISCOS
               255 - unknown

         XLEN (eXtra LENgth)
            If FLG.FEXTRA is set, this gives the length of the optional
            extra field.  See below for details.

         CRC32 (CRC-32)
            This contains a Cyclic Redundancy Check value of the
            uncompressed data computed according to CRC-32 algorithm
            used in the ISO 3309 standard and in section 8.1.1.6.2 of
            ITU-T recommendation V.42.  (See http://www.iso.ch for
            ordering ISO documents. See gopher://info.itu.ch for an
            online version of ITU-T V.42.)

         ISIZE (Input SIZE)
            This contains the size of the original (uncompressed) input
            data modulo 2^32.

      2.3.1.1. Extra field

         If the FLG.FEXTRA bit is set, an "extra field" is present in
         the header, with total length XLEN bytes.  It consists of a
         series of subfields, each of the form:

            +---+---+---+---+==================================+
            |SI1|SI2|  LEN  |... LEN bytes of subfield data ...|
            +---+---+---+---+==================================+

         SI1 and SI2 provide a subfield ID, typically two ASCII letters
         with some mnemonic value.  Jean-Loup Gailly
         <[email protected]> is maintaining a registry of subfield
         IDs; please send him any subfield ID you wish to use.  Subfield
         IDs with SI2 = 0 are reserved for future use.  The following
         IDs are currently defined:



Deutsch                      Informational                      [Page 8]

RFC 1952             GZIP File Format Specification             May 1996


            SI1         SI2         Data
            ----------  ----------  ----
            0x41 ('A')  0x70 ('P')  Apollo file type information

         LEN gives the length of the subfield data, excluding the 4
         initial bytes.

      2.3.1.2. Compliance

         A compliant compressor must produce files with correct ID1,
         ID2, CM, CRC32, and ISIZE, but may set all the other fields in
         the fixed-length part of the header to default values (255 for
         OS, 0 for all others).  The compressor must set all reserved
         bits to zero.

         A compliant decompressor must check ID1, ID2, and CM, and
         provide an error indication if any of these have incorrect
         values.  It must examine FEXTRA/XLEN, FNAME, FCOMMENT and FHCRC
         at least so it can skip over the optional fields if they are
         present.  It need not examine any other part of the header or
         trailer; in particular, a decompressor may ignore FTEXT and OS
         and always produce binary output, and still be compliant.  A
         compliant decompressor must give an error indication if any
         reserved bit is non-zero, since such a bit could indicate the
         presence of a new field that would cause subsequent data to be
         interpreted incorrectly.

3. References

   [1] "Information Processing - 8-bit single-byte coded graphic
       character sets - Part 1: Latin alphabet No.1" (ISO 8859-1:1987).
       The ISO 8859-1 (Latin-1) character set is a superset of 7-bit
       ASCII. Files defining this character set are available as
       iso_8859-1.* in ftp://ftp.uu.net/graphics/png/documents/

   [2] ISO 3309

   [3] ITU-T recommendation V.42

   [4] Deutsch, L.P.,"DEFLATE Compressed Data Format Specification",
       available in ftp://ftp.uu.net/pub/archiving/zip/doc/

   [5] Gailly, J.-L., GZIP documentation, available as gzip-*.tar in
       ftp://prep.ai.mit.edu/pub/gnu/

   [6] Sarwate, D.V., "Computation of Cyclic Redundancy Checks via Table
       Look-Up", Communications of the ACM, 31(8), pp.1008-1013.




Deutsch                      Informational                      [Page 9]

RFC 1952             GZIP File Format Specification             May 1996


   [7] Schwaderer, W.D., "CRC Calculation", April 85 PC Tech Journal,
       pp.118-133.

   [8] ftp://ftp.adelaide.edu.au/pub/rocksoft/papers/crc_v3.txt,
       describing the CRC concept.

4. Security Considerations

   Any data compression method involves the reduction of redundancy in
   the data.  Consequently, any corruption of the data is likely to have
   severe effects and be difficult to correct.  Uncompressed text, on
   the other hand, will probably still be readable despite the presence
   of some corrupted bytes.

   It is recommended that systems using this data format provide some
   means of validating the integrity of the compressed data, such as by
   setting and checking the CRC-32 check value.

5. Acknowledgements

   Trademarks cited in this document are the property of their
   respective owners.

   Jean-Loup Gailly designed the gzip format and wrote, with Mark Adler,
   the related software described in this specification.  Glenn
   Randers-Pehrson converted this document to RFC and HTML format.

6. Author's Address

   L. Peter Deutsch
   Aladdin Enterprises
   203 Santa Margarita Ave.
   Menlo Park, CA 94025

   Phone: (415) 322-0103 (AM only)
   FAX:   (415) 322-1734
   EMail: <[email protected]>

   Questions about the technical content of this specification can be
   sent by email to:

   Jean-Loup Gailly <[email protected]> and
   Mark Adler <[email protected]>

   Editorial comments on this specification can be sent by email to:

   L. Peter Deutsch <[email protected]> and
   Glenn Randers-Pehrson <[email protected]>



Deutsch                      Informational                     [Page 10]

RFC 1952             GZIP File Format Specification             May 1996


7. Appendix: Jean-Loup Gailly's gzip utility

   The most widely used implementation of gzip compression, and the
   original documentation on which this specification is based, were
   created by Jean-Loup Gailly <[email protected]>.  Since this
   implementation is a de facto standard, we mention some more of its
   features here.  Again, the material in this section is not part of
   the specification per se, and implementations need not follow it to
   be compliant.

   When compressing or decompressing a file, gzip preserves the
   protection, ownership, and modification time attributes on the local
   file system, since there is no provision for representing protection
   attributes in the gzip file format itself.  Since the file format
   includes a modification time, the gzip decompressor provides a
   command line switch that assigns the modification time from the file,
   rather than the local modification time of the compressed input, to
   the decompressed output.

8. Appendix: Sample CRC Code

   The following sample code represents a practical implementation of
   the CRC (Cyclic Redundancy Check). (See also ISO 3309 and ITU-T V.42
   for a formal specification.)

   The sample code is in the ANSI C programming language. Non C users
   may find it easier to read with these hints:

      &      Bitwise AND operator.
      ^      Bitwise exclusive-OR operator.
      >>     Bitwise right shift operator. When applied to an
             unsigned quantity, as here, right shift inserts zero
             bit(s) at the left.
      !      Logical NOT operator.
      ++     "n++" increments the variable n.
      0xNNN  0x introduces a hexadecimal (base 16) constant.
             Suffix L indicates a long value (at least 32 bits).

      /* Table of CRCs of all 8-bit messages. */
      unsigned long crc_table[256];

      /* Flag: has the table been computed? Initially false. */
      int crc_table_computed = 0;

      /* Make the table for a fast CRC. */
      void make_crc_table(void)
      {
        unsigned long c;



Deutsch                      Informational                     [Page 11]

RFC 1952             GZIP File Format Specification             May 1996


        int n, k;
        for (n = 0; n < 256; n++) {
          c = (unsigned long) n;
          for (k = 0; k < 8; k++) {
            if (c & 1) {
              c = 0xedb88320L ^ (c >> 1);
            } else {
              c = c >> 1;
            }
          }
          crc_table[n] = c;
        }
        crc_table_computed = 1;
      }

      /*
         Update a running crc with the bytes buf[0..len-1] and return
       the updated crc. The crc should be initialized to zero. Pre- and
       post-conditioning (one's complement) is performed within this
       function so it shouldn't be done by the caller. Usage example:

         unsigned long crc = 0L;

         while (read_buffer(buffer, length) != EOF) {
           crc = update_crc(crc, buffer, length);
         }
         if (crc != original_crc) error();
      */
      unsigned long update_crc(unsigned long crc,
                      unsigned char *buf, int len)
      {
        unsigned long c = crc ^ 0xffffffffL;
        int n;

        if (!crc_table_computed)
          make_crc_table();
        for (n = 0; n < len; n++) {
          c = crc_table[(c ^ buf[n]) & 0xff] ^ (c >> 8);
        }
        return c ^ 0xffffffffL;
      }

      /* Return the CRC of the bytes buf[0..len-1]. */
      unsigned long crc(unsigned char *buf, int len)
      {
        return update_crc(0L, buf, len);
      }




Deutsch                      Informational                     [Page 12]


A Fast Method for Identifying Plain Text Files
==============================================


Introduction
------------

Given a file coming from an unknown source, it is sometimes desirable
to find out whether the format of that file is plain text.  Although
this may appear like a simple task, a fully accurate detection of the
file type requires heavy-duty semantic analysis on the file contents.
It is, however, possible to obtain satisfactory results by employing
various heuristics.

Previous versions of PKZip and other zip-compatible compression tools
were using a crude detection scheme: if more than 80% (4/5) of the bytes
found in a certain buffer are within the range [7..127], the file is
labeled as plain text, otherwise it is labeled as binary.  A prominent
limitation of this scheme is the restriction to Latin-based alphabets.
Other alphabets, like Greek, Cyrillic or Asian, make extensive use of
the bytes within the range [128..255], and texts using these alphabets
are most often misidentified by this scheme; in other words, the rate
of false negatives is sometimes too high, which means that the recall
is low.  Another weakness of this scheme is a reduced precision, due to
the false positives that may occur when binary files containing large
amounts of textual characters are misidentified as plain text.

In this article we propose a new, simple detection scheme that features
a much increased precision and a near-100% recall.  This scheme is
designed to work on ASCII, Unicode and other ASCII-derived alphabets,
and it handles single-byte encodings (ISO-8859, MacRoman, KOI8, etc.)
and variable-sized encodings (ISO-2022, UTF-8, etc.).  Wider encodings
(UCS-2/UTF-16 and UCS-4/UTF-32) are not handled, however.


The Algorithm
-------------

The algorithm works by dividing the set of bytecodes [0..255] into three
categories:
- The white list of textual bytecodes:
  9 (TAB), 10 (LF), 13 (CR), 32 (SPACE) to 255.
- The gray list of tolerated bytecodes:
  7 (BEL), 8 (BS), 11 (VT), 12 (FF), 26 (SUB), 27 (ESC).
- The black list of undesired, non-textual bytecodes:
  0 (NUL) to 6, 14 to 31.

If a file contains at least one byte that belongs to the white list and
no byte that belongs to the black list, then the file is categorized as
plain text; otherwise, it is categorized as binary.  (The boundary case,
when the file is empty, automatically falls into the latter category.)


Rationale
---------

The idea behind this algorithm relies on two observations.

The first observation is that, although the full range of 7-bit codes
[0..127] is properly specified by the ASCII standard, most control
characters in the range [0..31] are not used in practice.  The only
widely-used, almost universally-portable control codes are 9 (TAB),
10 (LF) and 13 (CR).  There are a few more control codes that are
recognized on a reduced range of platforms and text viewers/editors:
7 (BEL), 8 (BS), 11 (VT), 12 (FF), 26 (SUB) and 27 (ESC); but these
codes are rarely (if ever) used alone, without being accompanied by
some printable text.  Even the newer, portable text formats such as
XML avoid using control characters outside the list mentioned here.

The second observation is that most of the binary files tend to contain
control characters, especially 0 (NUL).  Even though the older text
detection schemes observe the presence of non-ASCII codes from the range
[128..255], the precision rarely has to suffer if this upper range is
labeled as textual, because the files that are genuinely binary tend to
contain both control characters and codes from the upper range.  On the
other hand, the upper range needs to be labeled as textual, because it
is used by virtually all ASCII extensions.  In particular, this range is
used for encoding non-Latin scripts.

Since there is no counting involved, other than simply observing the
presence or the absence of some byte values, the algorithm produces
consistent results, regardless what alphabet encoding is being used.
(If counting were involved, it could be possible to obtain different
results on a text encoded, say, using ISO-8859-16 versus UTF-8.)

There is an extra category of plain text files that are "polluted" with
one or more black-listed codes, either by mistake or by peculiar design
considerations.  In such cases, a scheme that tolerates a small fraction
of black-listed codes would provide an increased recall (i.e. more true
positives).  This, however, incurs a reduced precision overall, since
false positives are more likely to appear in binary files that contain
large chunks of textual data.  Furthermore, "polluted" plain text should
be regarded as binary by general-purpose text detection schemes, because
general-purpose text processing algorithms might not be applicable.
Under this premise, it is safe to say that our detection method provides
a near-100% recall.

Experiments have been run on many files coming from various platforms
and applications.  We tried plain text files, system logs, source code,
formatted office documents, compiled object code, etc.  The results
confirm the optimistic assumptions about the capabilities of this
algorithm.


--
Cosmin Truta
Last updated: 2006-May-28

/* gzlib.c -- zlib functions common to reading and writing gzip files
 * Copyright (C) 2004, 2010, 2011, 2012, 2013, 2016 Mark Adler
 * For conditions of distribution and use, see copyright notice in zlib.h
 */

#include "gzguts.h"

#if defined(_WIN32) && !defined(__BORLANDC__) && !defined(__MINGW32__)
#  define LSEEK _lseeki64

        if (len)
            wcstombs(state->path, path, len + 1);
        else
            *(state->path) = 0;
    else
#endif
#if !defined(NO_snprintf) && !defined(NO_vsnprintf)
        snprintf(state->path, len + 1, "%s", (const char *)path);
#else
        strcpy(state->path, path);
#endif

    /* compute the flags for open() */
    oflag =
#ifdef O_LARGEFILE

{
    char *path;         /* identifier for error messages */
    gzFile gz;

    if (fd == -1 || (path = (char *)malloc(7 + 3 * sizeof(int))) == NULL)
        return NULL;
#if !defined(NO_snprintf) && !defined(NO_vsnprintf)
    snprintf(path, 7 + 3 * sizeof(int), "<fd:%d>", fd); /* for debugging */
#else
    sprintf(path, "<fd:%d>", fd);   /* for debugging */
#endif
    gz = gz_open(path, fd, mode);
    free(path);
    return gz;
}

    /* construct error message with path */
    if ((state->msg = (char *)malloc(strlen(state->path) + strlen(msg) + 3)) ==
            NULL) {
        state->err = Z_MEM_ERROR;
        return;
    }
#if !defined(NO_snprintf) && !defined(NO_vsnprintf)
    snprintf(state->msg, strlen(state->path) + strlen(msg) + 3,
             "%s%s%s", state->path, ": ", msg);
#else
    strcpy(state->msg, state->path);
    strcat(state->msg, ": ");
    strcat(state->msg, msg);
#endif
}

/* gzwrite.c -- zlib functions for writing gzip files
 * Copyright (C) 2004, 2005, 2010, 2011, 2012, 2013, 2016 Mark Adler
 * For conditions of distribution and use, see copyright notice in zlib.h
 */

#include "gzguts.h"

/* Local functions */
local int gz_init OF((gz_statep));

                    return -1;
                }
                state->x.next += writ;
            }
            if (strm->avail_out == 0) {
                strm->avail_out = state->size;
                strm->next_out = state->out;

            }
        }

        /* compress */
        have = strm->avail_out;
        ret = deflate(strm, flush);
        if (ret == Z_STREAM_ERROR) {

/* inffast.c -- fast decoding
 * Copyright (C) 1995-2008, 2010, 2013, 2016 Mark Adler
 * For conditions of distribution and use, see copyright notice in zlib.h
 */

#include "zutil.h"
#include "inftrees.h"
#include "inflate.h"
#include "inffast.h"

#ifndef ASMINF



/*
   Decode literal, length, and distance codes and write out the resulting
   literal and match bytes until either not enough input or output is
   available, an end-of-block is encountered, or a data error is encountered.
   When large enough input and output buffers are supplied to inflate(), for
   example, a 16K input buffer and a 64K output buffer, more than 95% of the

/* inftrees.c -- generate Huffman trees for efficient decoding
 * Copyright (C) 1995-2016 Mark Adler
 * For conditions of distribution and use, see copyright notice in zlib.h
 */

#include "zutil.h"
#include "inftrees.h"

#define MAXBITS 15

const char inflate_copyright[] =
   " inflate 1.2.9 Copyright 1995-2016 Mark Adler ";
/*
  If you use the zlib library in a product, an acknowledgment is welcome
  in the documentation of your product. If for some reason you cannot
  include such an acknowledgment, I would appreciate that you keep this
  copyright string in the executable of your product.
 */

    unsigned short count[MAXBITS+1];    /* number of codes of each length */
    unsigned short offs[MAXBITS+1];     /* offsets in table for each length */
    static const unsigned short lbase[31] = { /* Length codes 257..285 base */
        3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31,
        35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0};
    static const unsigned short lext[31] = { /* Length codes 257..285 extra */
        16, 16, 16, 16, 16, 16, 16, 16, 17, 17, 17, 17, 18, 18, 18, 18,
        19, 19, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 16, 192, 79};
    static const unsigned short dbase[32] = { /* Distance codes 0..29 base */
        1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193,
        257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145,
        8193, 12289, 16385, 24577, 0, 0};
    static const unsigned short dext[32] = { /* Distance codes 0..29 extra */
        16, 16, 16, 16, 17, 17, 18, 18, 19, 19, 20, 20, 21, 21, 22, 22,
        23, 23, 24, 24, 25, 25, 26, 26, 27, 27,

        ZLIB version 1.2.9 for OS/400 installation instructions

1) Download and unpack the zlib tarball to some IFS directory.
   (i.e.: /path/to/the/zlib/ifs/source/directory)

   If the installed IFS command suppors gzip format, this is straightforward,
else you have to unpack first to some directory on a system supporting it,
then move the whole directory to the IFS via the network (via SMB or FTP).

#      Create and compile the identification source file.

echo '#pragma comment(user, "ZLIB version '"${VERSION}"'")' > os400.c
echo '#pragma comment(user, __DATE__)' >> os400.c
echo '#pragma comment(user, __TIME__)' >> os400.c
echo '#pragma comment(copyright, "Copyright (C) 1995-2016 Jean-Loup Gailly, Mark Adler. OS/400 version by P. Monnerat.")' >> os400.c
make_module     OS400           os400.c
LINK=                           # No need to rebuild service program yet.
MODULES=


#       Get source list.

      *  ZLIB.INC - Interface to the general purpose compression library
      *
      *  ILE RPG400 version by Patrick Monnerat, DATASPHERE.
      *  Version 1.2.9
      *
      *
      *  WARNING:
      *     Procedures inflateInit(), inflateInit2(), deflateInit(),
      *         deflateInit2() and inflateBackInit() need to be called with
      *         two additional arguments:
      *         the package version string and the stream control structure.
      *         size. This is needed because RPG lacks some macro feature.
      *         Call these procedures as:
      *             inflateInit(...: ZLIB_VERSION: %size(z_stream))
      *
      /if not defined(ZLIB_H_)
      /define ZLIB_H_
      *
      **************************************************************************
      *                               Constants
      **************************************************************************
      *
      *  Versioning information.
      *
     D ZLIB_VERSION    C                   '1.2.9'
     D ZLIB_VERNUM     C                   X'1290'
     D ZLIB_VER_MAJOR  C                   1
     D ZLIB_VER_MINOR  C                   2
     D ZLIB_VER_REVISION...
     D                 C                   9
     D ZLIB_VER_SUBREVISION...
     D                 C                   0
      *
      *  Other equates.
      *
     D Z_NO_FLUSH      C                   0
     D Z_PARTIAL_FLUSH...

      <QPG:EmailAddress></QPG:EmailAddress>
   </QPG:Responsible>

   <QPG:Values>
      <QPG:Files>
         <QPG:Add file="../zconf.h" install="/opt/include/" user="root:sys" permission="644"/>
         <QPG:Add file="../zlib.h" install="/opt/include/" user="root:sys" permission="644"/>
         <QPG:Add file="../libz.so.1.2.9" install="/opt/lib/" user="root:bin" permission="644"/>
         <QPG:Add file="libz.so" install="/opt/lib/" component="dev" filetype="symlink" linkto="libz.so.1.2.9"/>
         <QPG:Add file="libz.so.1" install="/opt/lib/" filetype="symlink" linkto="libz.so.1.2.9"/>
         <QPG:Add file="../libz.so.1.2.9" install="/opt/lib/" component="slib"/>
      </QPG:Files>

      <QPG:PackageFilter>
         <QPM:PackageManifest>
            <QPM:PackageDescription>
               <QPM:PackageType>Library</QPM:PackageType>
               <QPM:PackageReleaseNotes></QPM:PackageReleaseNotes>

               <QPM:ProductDescriptionShort>A massively spiffy yet delicately unobtrusive compression library.</QPM:ProductDescriptionShort>
               <QPM:ProductDescriptionLong>zlib is designed to be a free, general-purpose, legally unencumbered, lossless data compression library for use on virtually any computer hardware and operating system.</QPM:ProductDescriptionLong>
               <QPM:ProductDescriptionURL>http://www.gzip.org/zlib</QPM:ProductDescriptionURL>
               <QPM:ProductDescriptionEmbedURL></QPM:ProductDescriptionEmbedURL>
            </QPM:ProductDescription>

            <QPM:ReleaseDescription>
               <QPM:ReleaseVersion>1.2.9</QPM:ReleaseVersion>
               <QPM:ReleaseUrgency>Medium</QPM:ReleaseUrgency>
               <QPM:ReleaseStability>Stable</QPM:ReleaseStability>
               <QPM:ReleaseNoteMinor></QPM:ReleaseNoteMinor>
               <QPM:ReleaseNoteMajor></QPM:ReleaseNoteMajor>
               <QPM:ExcludeCountries>
                  <QPM:Country></QPM:Country>
               </QPM:ExcludeCountries>

<?xml version="1.0" ?>
<package name="zlib" version="1.2.9">
    <library name="zlib" dlversion="1.2.9" dlname="z">
	<property name="description"> zip compression library </property>
	<property name="include-target-dir" value="$(@PACKAGE/install-includedir)" />

	<!-- fixme: not implemented yet -->
	<property name="compiler/c/inline" value="yes" />

	<include-file name="zlib.h" scope="public" mode="644" />

/* trees.c -- output deflated data using Huffman coding
 * Copyright (C) 1995-2016 Jean-loup Gailly
 * detect_data_type() function provided freely by Cosmin Truta, 2006
 * For conditions of distribution and use, see copyright notice in zlib.h
 */

/*
 *  ALGORITHM
 *

    s->compressed_len += 10L; /* 3 for block type, 7 for EOB */
#endif
    bi_flush(s);
}

/* ===========================================================================
 * Determine the best encoding for the current block: dynamic trees, static
 * trees or store, and output the encoded block to the zip file.
 */
void ZLIB_INTERNAL _tr_flush_block(s, buf, stored_len, last)
    deflate_state *s;
    charf *buf;       /* input block, or NULL if too old */
    ulg stored_len;   /* length of input block */
    int last;         /* one if this is the last block for a file */
{

# Makefile for zlib using Microsoft (Visual) C
# zlib is copyright (C) 1995-2006 Jean-loup Gailly and Mark Adler
#
# Usage:
#   nmake -f win32/Makefile.msc                          (standard build)
#   nmake -f win32/Makefile.msc LOC=-DFOO                (nonstandard build)
#   nmake -f win32/Makefile.msc LOC="-DASMV -DASMINF" \
#         OBJA="inffas32.obj match686.obj"               (use ASM code, x86)
#   nmake -f win32/Makefile.msc AS=ml64 LOC="-DASMV -DASMINF -I." \

ZLIB DATA COMPRESSION LIBRARY

zlib 1.2.9 is a general purpose data compression library.  All the code is
thread safe.  The data format used by the zlib library is described by RFCs
(Request for Comments) 1950 to 1952 in the files
http://www.ietf.org/rfc/rfc1950.txt (zlib format), rfc1951.txt (deflate format)
and rfc1952.txt (gzip format).

All functions of the compression library are documented in the file zlib.h
(volunteer to write man pages welcome, contact [email protected]).  Two compiled

PLEASE read DLL_FAQ.txt, and the the zlib FAQ http://zlib.net/zlib_faq.html
before asking for help.


Manifest:

The package zlib-1.2.9-win32-x86.zip will contain the following files:

  README-WIN32.txt This document
  ChangeLog        Changes since previous zlib packages
  DLL_FAQ.txt      Frequently asked questions about zlib1.dll
  zlib.3.pdf       Documentation of this library in Adobe Acrobat format

  example.exe      A statically-bound example (using zlib.lib, not the dll)

zlib specifications were written by L.  Peter Deutsch.  Thanks to all the
people who reported problems and suggested various improvements in zlib; they
are too numerous to cite here.


Copyright notice:

  (C) 1995-2012 Jean-loup Gailly and Mark Adler

  This software is provided 'as-is', without any express or implied
  warranty.  In no event will the authors be held liable for any damages
  arising from the use of this software.

  Permission is granted to anyone to use this software for any purpose,
  including commercial applications, and to alter it and redistribute it

What's here
===========
  The official ZLIB1.DLL


Source
======
  zlib version 1.2.8
  available at http://www.gzip.org/zlib/


Specification and rationale
===========================
  See the accompanying DLL_FAQ.txt


Usage
=====
  See the accompanying USAGE.txt


Build info
==========
  Contributed by Jan Nijtmans.

  Compiler:
    i686-w64-mingw32-gcc (GCC) 4.5.3
  Library:
    mingw64-i686-runtime/headers: 3.0b_svn5747-1
  Build commands:
    i686-w64-mingw32-gcc -c -DASMV contrib/asm686/match.S
    i686-w64-mingw32-gcc -c -DASMINF -I. -O3 contrib/inflate86/inffas86.c
    make -f win32/Makefile.gcc PREFIX=i686-w64-mingw32- LOC="-mms-bitfields -DASMV -DASMINF" OBJA="inffas86.o match.o"
   Finally, from VS commandline (VS2005 or higher):
    lib -machine:X86 -name:zlib1.dll -def:zlib.def -out:zdll.lib

Copyright notice
================
  Copyright (C) 1995-2010 Jean-loup Gailly and Mark Adler

  This software is provided 'as-is', without any express or implied
  warranty.  In no event will the authors be held liable for any damages
  arising from the use of this software.

  Permission is granted to anyone to use this software for any purpose,
  including commercial applications, and to alter it and redistribute it

Installing ZLIB1.DLL
====================
  Copy ZLIB1.DLL to the SYSTEM or the SYSTEM32 directory.





Using ZLIB1.DLL with Microsoft Visual C++
=========================================
   1. Install the supplied header files "zlib.h" and "zconf.h"
      into a directory found in the INCLUDE path list.

   2. Install the supplied library file "zdll.lib" into a
      directory found in the LIB path list.

   3. Add "zdll.lib" to your project.


Using ZLIB1.DLL with gcc/MinGW
==============================
   1. Install the supplied header files "zlib.h" and "zconf.h"
      into the INCLUDE directory.

   2. Copy the supplied library file "zdll.lib" to "libzdll.a":
        cp lib/zdll.lib lib/libzdll.a

      OR






   2' Build the import library from the supplied "zlib.def":
        dlltool -D zlib1.dll -d lib/zlib.def -l lib/libzdll.a

   3. Install "libzdll.a" into the LIB directory.

   4. Add "libzdll.a" to your project, or use the -lzdll option.

To build zlib using the Microsoft Visual C++ environment,
use the appropriate project from the projects/ directory.

  BEGIN
    BLOCK "040904E4"
    //language ID = U.S. English, char set = Windows, Multilingual
    BEGIN
      VALUE "FileDescription",	"zlib data compression library\0"
      VALUE "FileVersion",	ZLIB_VERSION "\0"
      VALUE "InternalName",	"zlib1.dll\0"
      VALUE "LegalCopyright",	"(C) 1995-2013 Jean-loup Gailly & Mark Adler\0"
      VALUE "OriginalFilename",	"zlib1.dll\0"
      VALUE "ProductName",	"zlib\0"
      VALUE "ProductVersion",	ZLIB_VERSION "\0"
      VALUE "Comments",		"For more information visit http://www.zlib.net/\0"
    END
  END
  BLOCK "VarFileInfo"

.TH ZLIB 3 "31 Dec 2016"
.SH NAME
zlib \- compression/decompression library
.SH SYNOPSIS
[see
.I zlib.h
for full description]
.SH DESCRIPTION

.IP
http://zlib.net/zlib_faq.html
.LP
before asking for help.
Send questions and/or comments to [email protected],
or (for the Windows DLL version) to Gilles Vollant ([email protected]).
.SH AUTHORS AND LICENSE
Version 1.2.9
.LP
Copyright (C) 1995-2016 Jean-loup Gailly and Mark Adler
.LP
This software is provided 'as-is', without any express or implied
warranty.  In no event will the authors be held liable for any damages
arising from the use of this software.
.LP
Permission is granted to anyone to use this software for any purpose,
including commercial applications, and to alter it and redistribute it

/* zlib.h -- interface of the 'zlib' general purpose compression library
  version 1.2.9, December 31st, 2016

  Copyright (C) 1995-2016 Jean-loup Gailly and Mark Adler

  This software is provided 'as-is', without any express or implied
  warranty.  In no event will the authors be held liable for any damages
  arising from the use of this software.

  Permission is granted to anyone to use this software for any purpose,
  including commercial applications, and to alter it and redistribute it

#include "zconf.h"

#ifdef __cplusplus
extern "C" {
#endif

#define ZLIB_VERSION "1.2.9"
#define ZLIB_VERNUM 0x1290
#define ZLIB_VER_MAJOR 1
#define ZLIB_VER_MINOR 2
#define ZLIB_VER_REVISION 9
#define ZLIB_VER_SUBREVISION 0

/*
    The 'zlib' compression library provides in-memory compression and
  decompression functions, including integrity checks of the uncompressed data.
  This version of the library supports only one compression method (deflation)
  but other algorithms will be added later and will have the same stream

/*
ZEXTERN int ZEXPORT inflateInit OF((z_streamp strm));

     Initializes the internal stream state for decompression.  The fields
   next_in, avail_in, zalloc, zfree and opaque must be initialized before by
   the caller.  In the current version of inflate, the provide input is not
   read or consumed.  Any memory allocation will be deferred to the first call

   of inflate.  If zalloc and zfree are set to Z_NULL, inflateInit updates them
   to use default allocation functions.

     inflateInit returns Z_OK if success, Z_MEM_ERROR if there was not enough
   memory, Z_VERSION_ERROR if the zlib library version is incompatible with the
   version assumed by the caller, or Z_STREAM_ERROR if the parameters are
   invalid, such as a null pointer to the structure.  msg is set to null if
   there is no error message.  inflateInit does not perform any decompression.
   Actual decompression will be done by inflate().  So next_in, and avail_in,

  forced to flush.

  The detailed semantics are as follows.  inflate performs one or both of the
  following actions:

  - Decompress more input starting at next_in and update next_in and avail_in
    accordingly.  If not all input can be processed (because there is not
    enough room in the output buffer), then next_in and avail_on are updated
    accordingly, and processing will resume at this point for the next call of
    inflate().

  - Generate more output starting at next_out and update next_out and avail_out
    accordingly.  inflate() provides as much output as possible, until there is
    no more input data or no more space in the output buffer (see below about
    the flush parameter).

                                      int strategy));
/*
     Dynamically update the compression level and compression strategy.  The
   interpretation of level and strategy is as in deflateInit2().  This can be
   used to switch between compression and straight copy of the input data, or
   to switch to a different kind of input data requiring a different strategy.
   If the compression approach (which is a function of the level) or the

   strategy is changed, then the input available so far is compressed with the
   old level and strategy using deflate(strm, Z_BLOCK).  There are three
   approaches for the compression levels 0, 1..3, and 4..9 respectively.  The
   new level and strategy will take effect at the next call of deflate().

     If a deflate(strm, Z_BLOCK) is performed by deflateParams(), and it does
   not have enough output space to complete, then the parameter change will not
   take effect.  In this case, deflateParams() can be called again with the
   same parameters and more output space to try again.

     In order to assure a change in the parameters on the first try, the

ZEXTERN int ZEXPORT compress OF((Bytef *dest,   uLongf *destLen,
                                 const Bytef *source, uLong sourceLen));
/*
     Compresses the source buffer into the destination buffer.  sourceLen is
   the byte length of the source buffer.  Upon entry, destLen is the total size
   of the destination buffer, which must be at least the value returned by
   compressBound(sourceLen).  Upon exit, destLen is the actual size of the
   compressed buffer.  compress() is equivalent to compress2() with a level
   parameter of Z_DEFAULT_COMPRESSION.

     compress returns Z_OK if success, Z_MEM_ERROR if there was not
   enough memory, Z_BUF_ERROR if there was not enough room in the output
   buffer.
*/

ZEXTERN int ZEXPORT compress2 OF((Bytef *dest,   uLongf *destLen,
                                  const Bytef *source, uLong sourceLen,
                                  int level));
/*
     Compresses the source buffer into the destination buffer.  The level
   parameter has the same meaning as in deflateInit.  sourceLen is the byte
   length of the source buffer.  Upon entry, destLen is the total size of the
   destination buffer, which must be at least the value returned by
   compressBound(sourceLen).  Upon exit, destLen is the actual size of the
   compressed buffer.

     compress2 returns Z_OK if success, Z_MEM_ERROR if there was not enough
   memory, Z_BUF_ERROR if there was not enough room in the output buffer,
   Z_STREAM_ERROR if the level parameter is invalid.
*/

ZEXTERN uLong ZEXPORT compressBound OF((uLong sourceLen));

/* zutil.c -- target dependent utility functions for the compression library
 * Copyright (C) 1995-2005, 2010, 2011, 2012, 2016 Jean-loup Gailly
 * For conditions of distribution and use, see copyright notice in zlib.h
 */

/* @(#) $Id$ */

#include "zutil.h"
#ifndef Z_SOLO

#    endif
#  endif
#endif
    return flags;
}

#ifdef ZLIB_DEBUG

#  ifndef verbose
#    define verbose 0
#  endif
int ZLIB_INTERNAL z_verbose = verbose;

void ZLIB_INTERNAL z_error (m)
    char *m;

about to be returned from the topmost \fBTcl_EvalObjEx\fR
invocation for \fIinterp\fR,
it converts the return code to \fBTCL_ERROR\fR
and sets \fIinterp\fR's result to an error message indicating that
the \fBreturn\fR, \fBbreak\fR, or \fBcontinue\fR command was
invoked in an inappropriate place.
This means that top-level applications should never see a return code
from \fBTcl_EvalObjEx\fR other then \fBTCL_OK\fR or \fBTCL_ERROR\fR.

.SH KEYWORDS
execute, file, global, result, script, value

with which values might be exchanged.  The C integral types for which Tcl
provides value exchange routines are \fBint\fR, \fBlong int\fR,
\fBTcl_WideInt\fR, and \fBmp_int\fR.  The \fBint\fR and \fBlong int\fR types
are provided by the C language standard.  The \fBTcl_WideInt\fR type is a
typedef defined to be whatever signed integral type covers at least the
64-bit integer range (-9223372036854775808 to 9223372036854775807).  Depending
on the platform and the C compiler, the actual type might be
\fBlong int\fR, \fBlong long int\fR, \fBint64\fR, or something else.
The \fBmp_int\fR type is a multiple-precision integer type defined
by the LibTomMath multiple-precision integer library.
.PP
The \fBTcl_NewIntObj\fR, \fBTcl_NewLongObj\fR, \fBTcl_NewWideIntObj\fR,
and \fBTcl_NewBignumObj\fR routines each create and return a new
Tcl value initialized to the integral value of the argument.  The
returned Tcl value is unshared.

\fBTCL_LINK_READ_ONLY\fR:
.TP
\fBTCL_LINK_INT\fR
The C variable is of type \fBint\fR.
Any value written into the Tcl variable must have a proper integer
form acceptable to \fBTcl_GetIntFromObj\fR;  attempts to write
non-integer values into \fIvarName\fR will be rejected with
Tcl errors.


.TP
\fBTCL_LINK_UINT\fR
The C variable is of type \fBunsigned int\fR.
Any value written into the Tcl variable must have a proper unsigned
integer form acceptable to \fBTcl_GetWideIntFromObj\fR and in the
platform's defined range for the \fBunsigned int\fR type; attempts to
write non-integer values (or values outside the range) into
\fIvarName\fR will be rejected with Tcl errors.


.TP
\fBTCL_LINK_CHAR\fR
The C variable is of type \fBchar\fR.
Any value written into the Tcl variable must have a proper integer
form acceptable to \fBTcl_GetIntFromObj\fR and be in the range of the
\fBchar\fR datatype; attempts to write non-integer or out-of-range
values into \fIvarName\fR will be rejected with Tcl errors.


.TP
\fBTCL_LINK_UCHAR\fR
The C variable is of type \fBunsigned char\fR.
Any value written into the Tcl variable must have a proper unsigned
integer form acceptable to \fBTcl_GetIntFromObj\fR and in the
platform's defined range for the \fBunsigned char\fR type; attempts to
write non-integer values (or values outside the range) into
\fIvarName\fR will be rejected with Tcl errors.


.TP
\fBTCL_LINK_SHORT\fR
The C variable is of type \fBshort\fR.
Any value written into the Tcl variable must have a proper integer
form acceptable to \fBTcl_GetIntFromObj\fR and be in the range of the
\fBshort\fR datatype; attempts to write non-integer or out-of-range
values into \fIvarName\fR will be rejected with Tcl errors.


.TP
\fBTCL_LINK_USHORT\fR
The C variable is of type \fBunsigned short\fR.
Any value written into the Tcl variable must have a proper unsigned
integer form acceptable to \fBTcl_GetIntFromObj\fR and in the
platform's defined range for the \fBunsigned short\fR type; attempts to
write non-integer values (or values outside the range) into
\fIvarName\fR will be rejected with Tcl errors.


.TP
\fBTCL_LINK_LONG\fR
The C variable is of type \fBlong\fR.
Any value written into the Tcl variable must have a proper integer
form acceptable to \fBTcl_GetLongFromObj\fR; attempts to write
non-integer or out-of-range
values into \fIvarName\fR will be rejected with Tcl errors.


.TP
\fBTCL_LINK_ULONG\fR
The C variable is of type \fBunsigned long\fR.
Any value written into the Tcl variable must have a proper unsigned
integer form acceptable to \fBTcl_GetWideIntFromObj\fR and in the
platform's defined range for the \fBunsigned long\fR type; attempts to
write non-integer values (or values outside the range) into
\fIvarName\fR will be rejected with Tcl errors.


.TP
\fBTCL_LINK_DOUBLE\fR
The C variable is of type \fBdouble\fR.
Any value written into the Tcl variable must have a proper real
form acceptable to \fBTcl_GetDoubleFromObj\fR;  attempts to write
non-real values into \fIvarName\fR will be rejected with
Tcl errors.


.TP
\fBTCL_LINK_FLOAT\fR
The C variable is of type \fBfloat\fR.
Any value written into the Tcl variable must have a proper real
form acceptable to \fBTcl_GetDoubleFromObj\fR and must be within the
range acceptable for a \fBfloat\fR; attempts to
write non-real values (or values outside the range) into
\fIvarName\fR will be rejected with Tcl errors.


.TP
\fBTCL_LINK_WIDE_INT\fR
The C variable is of type \fBTcl_WideInt\fR (which is an integer type
at least 64-bits wide on all platforms that can support it.)
Any value written into the Tcl variable must have a proper integer
form acceptable to \fBTcl_GetWideIntFromObj\fR;  attempts to write
non-integer values into \fIvarName\fR will be rejected with
Tcl errors.


.TP
\fBTCL_LINK_WIDE_UINT\fR
The C variable is of type \fBTcl_WideUInt\fR (which is an unsigned
integer type at least 64-bits wide on all platforms that can support
it.)
Any value written into the Tcl variable must have a proper unsigned
integer form acceptable to \fBTcl_GetWideIntFromObj\fR (it will be
cast to unsigned);
.\" FIXME! Use bignums instead.
attempts to write non-integer values into \fIvarName\fR will be
rejected with Tcl errors.


.TP
\fBTCL_LINK_BOOLEAN\fR
The C variable is of type \fBint\fR.
If its value is zero then it will read from Tcl as
.QW 0 ;
otherwise it will read from Tcl as
.QW 1 .

'\"
'\" Copyright (c) 1996-7 Sun Microsystems, Inc.
'\"
'\" See the file "license.terms" for information on usage and redistribution
'\" of this file, and for a DISCLAIMER OF ALL WARRANTIES.
'\"
.TH Tcl_OpenTcpClient 3 8.0 Tcl "Tcl Library Procedures"
.so man.macros
.BS
'\" Note:  do not modify the .SH NAME line immediately below!
.SH NAME
Tcl_OpenTcpClient, Tcl_MakeTcpClientChannel, Tcl_OpenTcpServer \- procedures to open channels using TCP sockets
.SH SYNOPSIS
.nf
\fB#include <tcl.h> \fR
.sp
Tcl_Channel
\fBTcl_OpenTcpClient\fR(\fIinterp, port, host, myaddr, myport, async\fR)
.sp
Tcl_Channel
\fBTcl_MakeTcpClientChannel\fR(\fIsock\fR)
.sp
Tcl_Channel
\fBTcl_OpenTcpServer\fR(\fIinterp, port, myaddr, proc, clientData\fR)
.sp



.SH ARGUMENTS
.AS Tcl_TcpAcceptProc clientData
.AP Tcl_Interp *interp in
Tcl interpreter to use for error reporting.  If non-NULL and an
error occurs, an error message is left in the interpreter's result.
.AP int port in
A port number to connect to as a client or to listen on as a server.



.AP "const char" *host in
A string specifying a host name or address for the remote end of the connection.
.AP int myport in
A port number for the client's end of the socket.  If 0, a port number
is allocated at random.
.AP "const char" *myaddr in
A string specifying the host name or address for network interface to use
for the local end of the connection.  If NULL, a default interface is
chosen.
.AP int async in
If nonzero, the client socket is connected asynchronously to the server.



.AP ClientData sock in
Platform-specific handle for client TCP socket.
.AP Tcl_TcpAcceptProc *proc in
Pointer to a procedure to invoke each time a new connection is
accepted via the socket.
.AP ClientData clientData in
Arbitrary one-word value to pass to \fIproc\fR.

a remote client is pending.
.PP
The newly created channel is not registered in the supplied interpreter; to
register it, use \fBTcl_RegisterChannel\fR.
If one of the standard channels, \fBstdin\fR, \fBstdout\fR or \fBstderr\fR was
previously closed, the act of creating the new channel also assigns it as a
replacement for the standard channel.





.SH "PLATFORM ISSUES"
.PP
On Unix platforms, the socket handle is a Unix file descriptor as
returned by the \fBsocket\fR system call.  On the Windows platform, the
socket handle is a \fBSOCKET\fR as defined in the WinSock API.
.SH "SEE ALSO"
Tcl_OpenFileChannel(3), Tcl_RegisterChannel(3), vwait(n)
.SH KEYWORDS
channel, client, server, socket, TCP

the command at global level instead of the current stack level.
.BE

.SH DESCRIPTION
.PP
\fBTcl_RecordAndEvalObj\fR is invoked to record a command as an event
on the history list and then execute it using \fBTcl_EvalObjEx\fR
(or \fBTcl_GlobalEvalObj\fR if the \fBTCL_EVAL_GLOBAL\fR bit is set
in \fIflags\fR).
It returns a completion code such as \fBTCL_OK\fR just like \fBTcl_EvalObjEx\fR,
as well as a result value containing additional information
(a result value or error message)
that can be retrieved using \fBTcl_GetObjResult\fR.
If you do not want the command recorded on the history list then
you should invoke \fBTcl_EvalObjEx\fR instead of \fBTcl_RecordAndEvalObj\fR.
Normally \fBTcl_RecordAndEvalObj\fR is only called with top-level

.CS
set foo {foo {a b} bar 2 baz 3}
\fBdict with\fR foo {}
puts $foo
#    prints: \fIa b foo {a b} bar 2 baz 3\fR
.CE
.SH "SEE ALSO"
append(n), array(n), foreach(n), mapeach(n), incr(n), list(n), lappend(n), set(n)
.SH KEYWORDS
dictionary, create, update, lookup, iterate, filter, map
'\" Local Variables:
'\" mode: nroff
'\" End:

\fBinfo library\fR
.
Returns the name of the library directory in which standard Tcl
scripts are stored.
This is actually the value of the \fBtcl_library\fR
variable and may be changed by setting \fBtcl_library\fR.
.TP
\fBinfo loaded \fR?\fIinterp\fR?
.

Returns a list describing all of the packages that have been loaded into
\fIinterp\fR with the \fBload\fR command.
Each list element is a sub-list with two elements consisting of the
name of the file from which the package was loaded and the name of
the package.
For statically-loaded packages the file name will be an empty string.
If \fIinterp\fR is omitted then information is returned for all packages
loaded in any interpreter in the process.
To get a list of just the packages in the current interpreter, specify

\fB\-dictionary\fR
.
Use dictionary-style comparison.  This is the same as \fB\-ascii\fR
except (a) case is ignored except as a tie-breaker and (b) if two
strings contain embedded numbers, the numbers compare as integers,
not characters.  For example, in \fB\-dictionary\fR mode, \fBbigBoy\fR
sorts between \fBbigbang\fR and \fBbigboy\fR, and \fBx10y\fR
sorts between \fBx9y\fR and \fBx11y\fR.

.TP
\fB\-integer\fR
.
Convert list elements to integers and use integer comparison.
.TP
\fB\-real\fR
.

.so man.macros
.BS
'\" Note:  do not modify the .SH NAME line immediately below!
.SH NAME
package \- Facilities for package loading and version control
.SH SYNOPSIS
.nf

\fBpackage forget\fR ?\fIpackage package ...\fR?
\fBpackage ifneeded \fIpackage version\fR ?\fIscript\fR?
\fBpackage names\fR
\fBpackage present \fIpackage \fR?\fIrequirement...\fR?
\fBpackage present \-exact \fIpackage version\fR
\fBpackage provide \fIpackage \fR?\fIversion\fR?
\fBpackage require \fIpackage \fR?\fIrequirement...\fR?

This command also detects and reports version clashes.
Typically, only the \fBpackage require\fR and \fBpackage provide\fR
commands are invoked in normal Tcl scripts;  the other commands are used
primarily by system scripts that maintain the package database.
.PP
The behavior of the \fBpackage\fR command is determined by its first argument.
The following forms are permitted:







.TP
\fBpackage forget\fR ?\fIpackage package ...\fR?
.
Removes all information about each specified package from this interpreter,
including information provided by both \fBpackage ifneeded\fR and
\fBpackage provide\fR.
.TP

and \fB=]\fR is an equivalence class, standing for the sequences of
characters of all collating elements equivalent to that one, including
itself. (If there are no other equivalent collating elements, the
treatment is as if the enclosing delimiters were
.QW \fB[.\fR \&
and
.QW \fB.]\fR .)
For example, if \fBo\fR and \fB\*(qo\fR are the members of an
equivalence class, then
.QW \fB[[=o=]]\fR ,
.QW \fB[[=\*(qo=]]\fR ,
and
.QW \fB[o\*(qo]\fR \&
are all synonymous. An equivalence class may not be an endpoint of a range.
.RS
.PP
(\fINote:\fR Tcl implements only the Unicode locale. It does not define any
equivalence classes. The examples above are just illustrations.)
.RE
.SH ESCAPES

server-side network interface to use for the connection.  This option
may be useful if the server machine has multiple network interfaces.
If the option is omitted then the server socket is bound to the
wildcard address so that it can accept connections from any
interface. If \fIaddr\fR is a domain name that resolves to multiple IP
addresses that are available on the local machine, the socket will
listen on all of them.










.PP
Server channels cannot be used for input or output; their sole use is to
accept new client connections. The channels created for each incoming
client connection are opened for input and output. Closing the server
channel shuts down the server so that no new connections will be
accepted;  however, existing connections will be unaffected.
.PP

static const crange alphaRangeTable[] = {
    {0x41, 0x5a}, {0x61, 0x7a}, {0xc0, 0xd6}, {0xd8, 0xf6},
    {0xf8, 0x2c1}, {0x2c6, 0x2d1}, {0x2e0, 0x2e4}, {0x370, 0x374},
    {0x37a, 0x37d}, {0x388, 0x38a}, {0x38e, 0x3a1}, {0x3a3, 0x3f5},
    {0x3f7, 0x481}, {0x48a, 0x52f}, {0x531, 0x556}, {0x561, 0x587},
    {0x5d0, 0x5ea}, {0x5f0, 0x5f2}, {0x620, 0x64a}, {0x671, 0x6d3},
    {0x6fa, 0x6fc}, {0x712, 0x72f}, {0x74d, 0x7a5}, {0x7ca, 0x7ea},
    {0x800, 0x815}, {0x840, 0x858}, {0x8a0, 0x8b4}, {0x8b6, 0x8bd},
    {0x904, 0x939}, {0x958, 0x961}, {0x971, 0x980}, {0x985, 0x98c},
    {0x993, 0x9a8}, {0x9aa, 0x9b0}, {0x9b6, 0x9b9}, {0x9df, 0x9e1},
    {0xa05, 0xa0a}, {0xa13, 0xa28}, {0xa2a, 0xa30}, {0xa59, 0xa5c},
    {0xa72, 0xa74}, {0xa85, 0xa8d}, {0xa8f, 0xa91}, {0xa93, 0xaa8},
    {0xaaa, 0xab0}, {0xab5, 0xab9}, {0xb05, 0xb0c}, {0xb13, 0xb28},
    {0xb2a, 0xb30}, {0xb35, 0xb39}, {0xb5f, 0xb61}, {0xb85, 0xb8a},
    {0xb8e, 0xb90}, {0xb92, 0xb95}, {0xba8, 0xbaa}, {0xbae, 0xbb9},
    {0xc05, 0xc0c}, {0xc0e, 0xc10}, {0xc12, 0xc28}, {0xc2a, 0xc39},
    {0xc58, 0xc5a}, {0xc85, 0xc8c}, {0xc8e, 0xc90}, {0xc92, 0xca8},
    {0xcaa, 0xcb3}, {0xcb5, 0xcb9}, {0xd05, 0xd0c}, {0xd0e, 0xd10},
    {0xd12, 0xd3a}, {0xd54, 0xd56}, {0xd5f, 0xd61}, {0xd7a, 0xd7f},
    {0xd85, 0xd96}, {0xd9a, 0xdb1}, {0xdb3, 0xdbb}, {0xdc0, 0xdc6},
    {0xe01, 0xe30}, {0xe40, 0xe46}, {0xe94, 0xe97}, {0xe99, 0xe9f},
    {0xea1, 0xea3}, {0xead, 0xeb0}, {0xec0, 0xec4}, {0xedc, 0xedf},
    {0xf40, 0xf47}, {0xf49, 0xf6c}, {0xf88, 0xf8c}, {0x1000, 0x102a},
    {0x1050, 0x1055}, {0x105a, 0x105d}, {0x106e, 0x1070}, {0x1075, 0x1081},
    {0x10a0, 0x10c5}, {0x10d0, 0x10fa}, {0x10fc, 0x1248}, {0x124a, 0x124d},
    {0x1250, 0x1256}, {0x125a, 0x125d}, {0x1260, 0x1288}, {0x128a, 0x128d},
    {0x1290, 0x12b0}, {0x12b2, 0x12b5}, {0x12b8, 0x12be}, {0x12c2, 0x12c5},
    {0x12c8, 0x12d6}, {0x12d8, 0x1310}, {0x1312, 0x1315}, {0x1318, 0x135a},
    {0x1380, 0x138f}, {0x13a0, 0x13f5}, {0x13f8, 0x13fd}, {0x1401, 0x166c},
    {0x166f, 0x167f}, {0x1681, 0x169a}, {0x16a0, 0x16ea}, {0x16f1, 0x16f8},
    {0x1700, 0x170c}, {0x170e, 0x1711}, {0x1720, 0x1731}, {0x1740, 0x1751},
    {0x1760, 0x176c}, {0x176e, 0x1770}, {0x1780, 0x17b3}, {0x1820, 0x1877},
    {0x1880, 0x1884}, {0x1887, 0x18a8}, {0x18b0, 0x18f5}, {0x1900, 0x191e},
    {0x1950, 0x196d}, {0x1970, 0x1974}, {0x1980, 0x19ab}, {0x19b0, 0x19c9},
    {0x1a00, 0x1a16}, {0x1a20, 0x1a54}, {0x1b05, 0x1b33}, {0x1b45, 0x1b4b},
    {0x1b83, 0x1ba0}, {0x1bba, 0x1be5}, {0x1c00, 0x1c23}, {0x1c4d, 0x1c4f},
    {0x1c5a, 0x1c7d}, {0x1c80, 0x1c88}, {0x1ce9, 0x1cec}, {0x1cee, 0x1cf1},
    {0x1d00, 0x1dbf}, {0x1e00, 0x1f15}, {0x1f18, 0x1f1d}, {0x1f20, 0x1f45},
    {0x1f48, 0x1f4d}, {0x1f50, 0x1f57}, {0x1f5f, 0x1f7d}, {0x1f80, 0x1fb4},
    {0x1fb6, 0x1fbc}, {0x1fc2, 0x1fc4}, {0x1fc6, 0x1fcc}, {0x1fd0, 0x1fd3},
    {0x1fd6, 0x1fdb}, {0x1fe0, 0x1fec}, {0x1ff2, 0x1ff4}, {0x1ff6, 0x1ffc},
    {0x2090, 0x209c}, {0x210a, 0x2113}, {0x2119, 0x211d}, {0x212a, 0x212d},
    {0x212f, 0x2139}, {0x213c, 0x213f}, {0x2145, 0x2149}, {0x2c00, 0x2c2e},
    {0x2c30, 0x2c5e}, {0x2c60, 0x2ce4}, {0x2ceb, 0x2cee}, {0x2d00, 0x2d25},
    {0x2d30, 0x2d67}, {0x2d80, 0x2d96}, {0x2da0, 0x2da6}, {0x2da8, 0x2dae},
    {0x2db0, 0x2db6}, {0x2db8, 0x2dbe}, {0x2dc0, 0x2dc6}, {0x2dc8, 0x2dce},
    {0x2dd0, 0x2dd6}, {0x2dd8, 0x2dde}, {0x3031, 0x3035}, {0x3041, 0x3096},
    {0x309d, 0x309f}, {0x30a1, 0x30fa}, {0x30fc, 0x30ff}, {0x3105, 0x312d},
    {0x3131, 0x318e}, {0x31a0, 0x31ba}, {0x31f0, 0x31ff}, {0x3400, 0x4db5},
    {0x4e00, 0x9fd5}, {0xa000, 0xa48c}, {0xa4d0, 0xa4fd}, {0xa500, 0xa60c},
    {0xa610, 0xa61f}, {0xa640, 0xa66e}, {0xa67f, 0xa69d}, {0xa6a0, 0xa6e5},
    {0xa717, 0xa71f}, {0xa722, 0xa788}, {0xa78b, 0xa7ae}, {0xa7b0, 0xa7b7},
    {0xa7f7, 0xa801}, {0xa803, 0xa805}, {0xa807, 0xa80a}, {0xa80c, 0xa822},
    {0xa840, 0xa873}, {0xa882, 0xa8b3}, {0xa8f2, 0xa8f7}, {0xa90a, 0xa925},
    {0xa930, 0xa946}, {0xa960, 0xa97c}, {0xa984, 0xa9b2}, {0xa9e0, 0xa9e4},
    {0xa9e6, 0xa9ef}, {0xa9fa, 0xa9fe}, {0xaa00, 0xaa28}, {0xaa40, 0xaa42},
    {0xaa44, 0xaa4b}, {0xaa60, 0xaa76}, {0xaa7e, 0xaaaf}, {0xaab9, 0xaabd},
    {0xaadb, 0xaadd}, {0xaae0, 0xaaea}, {0xaaf2, 0xaaf4}, {0xab01, 0xab06},
    {0xab09, 0xab0e}, {0xab11, 0xab16}, {0xab20, 0xab26}, {0xab28, 0xab2e},
    {0xab30, 0xab5a}, {0xab5c, 0xab65}, {0xab70, 0xabe2}, {0xac00, 0xd7a3},
    {0xd7b0, 0xd7c6}, {0xd7cb, 0xd7fb}, {0xdc00, 0xdc3e}, {0xdc40, 0xdc7e},
    {0xdc80, 0xdcbe}, {0xdcc0, 0xdcfe}, {0xdd00, 0xdd3e}, {0xdd40, 0xdd7e},
    {0xdd80, 0xddbe}, {0xddc0, 0xddfe}, {0xde00, 0xde3e}, {0xde40, 0xde7e},
    {0xde80, 0xdebe}, {0xdec0, 0xdefe}, {0xdf00, 0xdf3e}, {0xdf40, 0xdf7e},
    {0xdf80, 0xdfbe}, {0xdfc0, 0xdffe}, {0xf900, 0xfa6d}, {0xfa70, 0xfad9},
    {0xfb00, 0xfb06}, {0xfb13, 0xfb17}, {0xfb1f, 0xfb28}, {0xfb2a, 0xfb36},
    {0xfb38, 0xfb3c}, {0xfb46, 0xfbb1}, {0xfbd3, 0xfd3d}, {0xfd50, 0xfd8f},
    {0xfd92, 0xfdc7}, {0xfdf0, 0xfdfb}, {0xfe70, 0xfe74}, {0xfe76, 0xfefc},
    {0xff21, 0xff3a}, {0xff41, 0xff5a}, {0xff66, 0xffbe}, {0xffc2, 0xffc7},
    {0xffca, 0xffcf}, {0xffd2, 0xffd7}, {0xffda, 0xffdc}
#if TCL_UTF_MAX > 4
    ,{0x10000, 0x1000b}, {0x1000d, 0x10026}, {0x10028, 0x1003a}, {0x1003f, 0x1004d},
    {0x10050, 0x1005d}, {0x10080, 0x100fa}, {0x10280, 0x1029c}, {0x102a0, 0x102d0},
    {0x10300, 0x1031f}, {0x10330, 0x10340}, {0x10342, 0x10349}, {0x10350, 0x10375},
    {0x10380, 0x1039d}, {0x103a0, 0x103c3}, {0x103c8, 0x103cf}, {0x10400, 0x1049d},
    {0x104b0, 0x104d3}, {0x104d8, 0x104fb}, {0x10500, 0x10527}, {0x10530, 0x10563},
    {0x10600, 0x10736}, {0x10740, 0x10755}, {0x10760, 0x10767}, {0x10800, 0x10805},
    {0x1080a, 0x10835}, {0x1083f, 0x10855}, {0x10860, 0x10876}, {0x10880, 0x1089e},
    {0x108e0, 0x108f2}, {0x10900, 0x10915}, {0x10920, 0x10939}, {0x10980, 0x109b7},
    {0x10a10, 0x10a13}, {0x10a15, 0x10a17}, {0x10a19, 0x10a33}, {0x10a60, 0x10a7c},
    {0x10a80, 0x10a9c}, {0x10ac0, 0x10ac7}, {0x10ac9, 0x10ae4}, {0x10b00, 0x10b35},
    {0x10b40, 0x10b55}, {0x10b60, 0x10b72}, {0x10b80, 0x10b91}, {0x10c00, 0x10c48},
    {0x10c80, 0x10cb2}, {0x10cc0, 0x10cf2}, {0x11003, 0x11037}, {0x11083, 0x110af},
    {0x110d0, 0x110e8}, {0x11103, 0x11126}, {0x11150, 0x11172}, {0x11183, 0x111b2},
    {0x111c1, 0x111c4}, {0x11200, 0x11211}, {0x11213, 0x1122b}, {0x11280, 0x11286},
    {0x1128a, 0x1128d}, {0x1128f, 0x1129d}, {0x1129f, 0x112a8}, {0x112b0, 0x112de},
    {0x11305, 0x1130c}, {0x11313, 0x11328}, {0x1132a, 0x11330}, {0x11335, 0x11339},
    {0x1135d, 0x11361}, {0x11400, 0x11434}, {0x11447, 0x1144a}, {0x11480, 0x114af},
    {0x11580, 0x115ae}, {0x115d8, 0x115db}, {0x11600, 0x1162f}, {0x11680, 0x116aa},
    {0x11700, 0x11719}, {0x118a0, 0x118df}, {0x11ac0, 0x11af8}, {0x11c00, 0x11c08},

    {0x11c0a, 0x11c2e}, {0x11c72, 0x11c8f}, {0x12000, 0x12399}, {0x12480, 0x12543},
    {0x13000, 0x1342e}, {0x14400, 0x14646}, {0x16800, 0x16a38}, {0x16a40, 0x16a5e},
    {0x16ad0, 0x16aed}, {0x16b00, 0x16b2f}, {0x16b40, 0x16b43}, {0x16b63, 0x16b77},
    {0x16b7d, 0x16b8f}, {0x16f00, 0x16f44}, {0x16f93, 0x16f9f}, {0x17000, 0x187ec},

    {0x18800, 0x18af2}, {0x1bc00, 0x1bc6a}, {0x1bc70, 0x1bc7c}, {0x1bc80, 0x1bc88},
    {0x1bc90, 0x1bc99}, {0x1d400, 0x1d454}, {0x1d456, 0x1d49c}, {0x1d4a9, 0x1d4ac},
    {0x1d4ae, 0x1d4b9}, {0x1d4bd, 0x1d4c3}, {0x1d4c5, 0x1d505}, {0x1d507, 0x1d50a},
    {0x1d50d, 0x1d514}, {0x1d516, 0x1d51c}, {0x1d51e, 0x1d539}, {0x1d53b, 0x1d53e},
    {0x1d540, 0x1d544}, {0x1d54a, 0x1d550}, {0x1d552, 0x1d6a5}, {0x1d6a8, 0x1d6c0},
    {0x1d6c2, 0x1d6da}, {0x1d6dc, 0x1d6fa}, {0x1d6fc, 0x1d714}, {0x1d716, 0x1d734},
    {0x1d736, 0x1d74e}, {0x1d750, 0x1d76e}, {0x1d770, 0x1d788}, {0x1d78a, 0x1d7a8},
    {0x1d7aa, 0x1d7c2}, {0x1d7c4, 0x1d7cb}, {0x1e800, 0x1e8c4}, {0x1e900, 0x1e943},
    {0x1ee00, 0x1ee03}, {0x1ee05, 0x1ee1f}, {0x1ee29, 0x1ee32}, {0x1ee34, 0x1ee37},
    {0x1ee4d, 0x1ee4f}, {0x1ee67, 0x1ee6a}, {0x1ee6c, 0x1ee72}, {0x1ee74, 0x1ee77},
    {0x1ee79, 0x1ee7c}, {0x1ee80, 0x1ee89}, {0x1ee8b, 0x1ee9b}, {0x1eea1, 0x1eea3},
    {0x1eea5, 0x1eea9}, {0x1eeab, 0x1eebb}, {0x20000, 0x2a6d6}, {0x2a700, 0x2b734},
    {0x2b740, 0x2b81d}, {0x2b820, 0x2cea1}, {0x2f800, 0x2fa1d}
#endif
};

#define NUM_ALPHA_RANGE (sizeof(alphaRangeTable)/sizeof(crange))

static const chr alphaCharTable[] = {
    0xaa, 0xb5, 0xba, 0x2ec, 0x2ee, 0x376, 0x377, 0x37f, 0x386,
    0x38c, 0x559, 0x66e, 0x66f, 0x6d5, 0x6e5, 0x6e6, 0x6ee, 0x6ef,
    0x6ff, 0x710, 0x7b1, 0x7f4, 0x7f5, 0x7fa, 0x81a, 0x824, 0x828,
    0x93d, 0x950, 0x98f, 0x990, 0x9b2, 0x9bd, 0x9ce, 0x9dc, 0x9dd,
    0x9f0, 0x9f1, 0xa0f, 0xa10, 0xa32, 0xa33, 0xa35, 0xa36, 0xa38,
    0xa39, 0xa5e, 0xab2, 0xab3, 0xabd, 0xad0, 0xae0, 0xae1, 0xaf9,
    0xb0f, 0xb10, 0xb32, 0xb33, 0xb3d, 0xb5c, 0xb5d, 0xb71, 0xb83,
    0xb99, 0xb9a, 0xb9c, 0xb9e, 0xb9f, 0xba3, 0xba4, 0xbd0, 0xc3d,
    0xc60, 0xc61, 0xc80, 0xcbd, 0xcde, 0xce0, 0xce1, 0xcf1, 0xcf2,
    0xd3d, 0xd4e, 0xdbd, 0xe32, 0xe33, 0xe81, 0xe82, 0xe84, 0xe87,
    0xe88, 0xe8a, 0xe8d, 0xea5, 0xea7, 0xeaa, 0xeab, 0xeb2, 0xeb3,
    0xebd, 0xec6, 0xf00, 0x103f, 0x1061, 0x1065, 0x1066, 0x108e, 0x10c7,
    0x10cd, 0x1258, 0x12c0, 0x17d7, 0x17dc, 0x18aa, 0x1aa7, 0x1bae, 0x1baf,
    0x1cf5, 0x1cf6, 0x1f59, 0x1f5b, 0x1f5d, 0x1fbe, 0x2071, 0x207f, 0x2102,
    0x2107, 0x2115, 0x2124, 0x2126, 0x2128, 0x214e, 0x2183, 0x2184, 0x2cf2,
    0x2cf3, 0x2d27, 0x2d2d, 0x2d6f, 0x2e2f, 0x3005, 0x3006, 0x303b, 0x303c,
    0xa62a, 0xa62b, 0xa8fb, 0xa8fd, 0xa9cf, 0xaa7a, 0xaab1, 0xaab5, 0xaab6,
    0xaac0, 0xaac2, 0xfb1d, 0xfb3e, 0xfb40, 0xfb41, 0xfb43, 0xfb44
#if TCL_UTF_MAX > 4
    ,0x1003c, 0x1003d, 0x10808, 0x10837, 0x10838, 0x1083c, 0x108f4, 0x108f5, 0x109be,
    0x109bf, 0x10a00, 0x11176, 0x111da, 0x111dc, 0x11288, 0x1130f, 0x11310, 0x11332,
    0x11333, 0x1133d, 0x11350, 0x114c4, 0x114c5, 0x114c7, 0x11644, 0x118ff, 0x11c40,

    0x16f50, 0x16fe0, 0x1b000, 0x1b001, 0x1d49e, 0x1d49f, 0x1d4a2, 0x1d4a5, 0x1d4a6,
    0x1d4bb, 0x1d546, 0x1ee21, 0x1ee22, 0x1ee24, 0x1ee27, 0x1ee39, 0x1ee3b, 0x1ee42,
    0x1ee47, 0x1ee49, 0x1ee4b, 0x1ee51, 0x1ee52, 0x1ee54, 0x1ee57, 0x1ee59, 0x1ee5b,
    0x1ee5d, 0x1ee5f, 0x1ee61, 0x1ee62, 0x1ee64, 0x1ee7e
#endif
};

#define NUM_ALPHA_CHAR (sizeof(alphaCharTable)/sizeof(chr))

/*
 * Unicode: control characters.

    {0x1c50, 0x1c59}, {0xa620, 0xa629}, {0xa8d0, 0xa8d9}, {0xa900, 0xa909},
    {0xa9d0, 0xa9d9}, {0xa9f0, 0xa9f9}, {0xaa50, 0xaa59}, {0xabf0, 0xabf9},
    {0xff10, 0xff19}
#if TCL_UTF_MAX > 4
    ,{0x104a0, 0x104a9}, {0x11066, 0x1106f}, {0x110f0, 0x110f9}, {0x11136, 0x1113f},
    {0x111d0, 0x111d9}, {0x112f0, 0x112f9}, {0x11450, 0x11459}, {0x114d0, 0x114d9},
    {0x11650, 0x11659}, {0x116c0, 0x116c9}, {0x11730, 0x11739}, {0x118e0, 0x118e9},
    {0x11c50, 0x11c59}, {0x16a60, 0x16a69}, {0x16b50, 0x16b59}, {0x1d7ce, 0x1d7ff},
    {0x1e950, 0x1e959}
#endif
};

#define NUM_DIGIT_RANGE (sizeof(digitRangeTable)/sizeof(crange))

/*
 * no singletons of digit characters.

    {0x55a, 0x55f}, {0x66a, 0x66d}, {0x700, 0x70d}, {0x7f7, 0x7f9},
    {0x830, 0x83e}, {0xf04, 0xf12}, {0xf3a, 0xf3d}, {0xfd0, 0xfd4},
    {0x104a, 0x104f}, {0x1360, 0x1368}, {0x16eb, 0x16ed}, {0x17d4, 0x17d6},
    {0x17d8, 0x17da}, {0x1800, 0x180a}, {0x1aa0, 0x1aa6}, {0x1aa8, 0x1aad},
    {0x1b5a, 0x1b60}, {0x1bfc, 0x1bff}, {0x1c3b, 0x1c3f}, {0x1cc0, 0x1cc7},
    {0x2010, 0x2027}, {0x2030, 0x2043}, {0x2045, 0x2051}, {0x2053, 0x205e},
    {0x2308, 0x230b}, {0x2768, 0x2775}, {0x27e6, 0x27ef}, {0x2983, 0x2998},
    {0x29d8, 0x29db}, {0x2cf9, 0x2cfc}, {0x2e00, 0x2e2e}, {0x2e30, 0x2e44},
    {0x3001, 0x3003}, {0x3008, 0x3011}, {0x3014, 0x301f}, {0xa60d, 0xa60f},
    {0xa6f2, 0xa6f7}, {0xa874, 0xa877}, {0xa8f8, 0xa8fa}, {0xa9c1, 0xa9cd},
    {0xaa5c, 0xaa5f}, {0xfe10, 0xfe19}, {0xfe30, 0xfe52}, {0xfe54, 0xfe61},
    {0xff01, 0xff03}, {0xff05, 0xff0a}, {0xff0c, 0xff0f}, {0xff3b, 0xff3d},
    {0xff5f, 0xff65}
#if TCL_UTF_MAX > 4
    ,{0x10100, 0x10102}, {0x10a50, 0x10a58}, {0x10af0, 0x10af6}, {0x10b39, 0x10b3f},
    {0x10b99, 0x10b9c}, {0x11047, 0x1104d}, {0x110be, 0x110c1}, {0x11140, 0x11143},
    {0x111c5, 0x111c9}, {0x111dd, 0x111df}, {0x11238, 0x1123d}, {0x1144b, 0x1144f},
    {0x115c1, 0x115d7}, {0x11641, 0x11643}, {0x11660, 0x1166c}, {0x1173c, 0x1173e},

    {0x11c41, 0x11c45}, {0x12470, 0x12474}, {0x16b37, 0x16b3b}, {0x1da87, 0x1da8b}
#endif
};

#define NUM_PUNCT_RANGE (sizeof(punctRangeTable)/sizeof(crange))

static const chr punctCharTable[] = {
    0x3a, 0x3b, 0x3f, 0x40, 0x5f, 0x7b, 0x7d, 0xa1, 0xa7,
    0xab, 0xb6, 0xb7, 0xbb, 0xbf, 0x37e, 0x387, 0x589, 0x58a,
    0x5be, 0x5c0, 0x5c3, 0x5c6, 0x5f3, 0x5f4, 0x609, 0x60a, 0x60c,
    0x60d, 0x61b, 0x61e, 0x61f, 0x6d4, 0x85e, 0x964, 0x965, 0x970,
    0xaf0, 0xdf4, 0xe4f, 0xe5a, 0xe5b, 0xf14, 0xf85, 0xfd9, 0xfda,
    0x10fb, 0x1400, 0x166d, 0x166e, 0x169b, 0x169c, 0x1735, 0x1736, 0x1944,
    0x1945, 0x1a1e, 0x1a1f, 0x1c7e, 0x1c7f, 0x1cd3, 0x207d, 0x207e, 0x208d,
    0x208e, 0x2329, 0x232a, 0x27c5, 0x27c6, 0x29fc, 0x29fd, 0x2cfe, 0x2cff,
    0x2d70, 0x3030, 0x303d, 0x30a0, 0x30fb, 0xa4fe, 0xa4ff, 0xa673, 0xa67e,
    0xa8ce, 0xa8cf, 0xa8fc, 0xa92e, 0xa92f, 0xa95f, 0xa9de, 0xa9df, 0xaade,
    0xaadf, 0xaaf0, 0xaaf1, 0xabeb, 0xfd3e, 0xfd3f, 0xfe63, 0xfe68, 0xfe6a,
    0xfe6b, 0xff1a, 0xff1b, 0xff1f, 0xff20, 0xff3f, 0xff5b, 0xff5d
#if TCL_UTF_MAX > 4
    ,0x1039f, 0x103d0, 0x1056f, 0x10857, 0x1091f, 0x1093f, 0x10a7f, 0x110bb, 0x110bc,
    0x11174, 0x11175, 0x111cd, 0x111db, 0x112a9, 0x1145b, 0x1145d, 0x114c6, 0x11c70,
    0x11c71, 0x16a6e, 0x16a6f, 0x16af5, 0x16b44, 0x1bc9f, 0x1e95e, 0x1e95f
#endif
};

static const crange graphRangeTable[] = {
    {0x21, 0x7e}, {0xa1, 0xac}, {0xae, 0x377}, {0x37a, 0x37f},
    {0x384, 0x38a}, {0x38e, 0x3a1}, {0x3a3, 0x52f}, {0x531, 0x556},
    {0x559, 0x55f}, {0x561, 0x587}, {0x58d, 0x58f}, {0x591, 0x5c7},
    {0x5d0, 0x5ea}, {0x5f0, 0x5f4}, {0x606, 0x61b}, {0x61e, 0x6dc},
    {0x6de, 0x70d}, {0x710, 0x74a}, {0x74d, 0x7b1}, {0x7c0, 0x7fa},
    {0x800, 0x82d}, {0x830, 0x83e}, {0x840, 0x85b}, {0x8a0, 0x8b4},
    {0x8b6, 0x8bd}, {0x8d4, 0x8e1}, {0x8e3, 0x983}, {0x985, 0x98c},
    {0x993, 0x9a8}, {0x9aa, 0x9b0}, {0x9b6, 0x9b9}, {0x9bc, 0x9c4},
    {0x9cb, 0x9ce}, {0x9df, 0x9e3}, {0x9e6, 0x9fb}, {0xa01, 0xa03},
    {0xa05, 0xa0a}, {0xa13, 0xa28}, {0xa2a, 0xa30}, {0xa3e, 0xa42},
    {0xa4b, 0xa4d}, {0xa59, 0xa5c}, {0xa66, 0xa75}, {0xa81, 0xa83},
    {0xa85, 0xa8d}, {0xa8f, 0xa91}, {0xa93, 0xaa8}, {0xaaa, 0xab0},
    {0xab5, 0xab9}, {0xabc, 0xac5}, {0xac7, 0xac9}, {0xacb, 0xacd},
    {0xae0, 0xae3}, {0xae6, 0xaf1}, {0xb01, 0xb03}, {0xb05, 0xb0c},
    {0xb13, 0xb28}, {0xb2a, 0xb30}, {0xb35, 0xb39}, {0xb3c, 0xb44},
    {0xb4b, 0xb4d}, {0xb5f, 0xb63}, {0xb66, 0xb77}, {0xb85, 0xb8a},
    {0xb8e, 0xb90}, {0xb92, 0xb95}, {0xba8, 0xbaa}, {0xbae, 0xbb9},
    {0xbbe, 0xbc2}, {0xbc6, 0xbc8}, {0xbca, 0xbcd}, {0xbe6, 0xbfa},
    {0xc00, 0xc03}, {0xc05, 0xc0c}, {0xc0e, 0xc10}, {0xc12, 0xc28},
    {0xc2a, 0xc39}, {0xc3d, 0xc44}, {0xc46, 0xc48}, {0xc4a, 0xc4d},
    {0xc58, 0xc5a}, {0xc60, 0xc63}, {0xc66, 0xc6f}, {0xc78, 0xc83},
    {0xc85, 0xc8c}, {0xc8e, 0xc90}, {0xc92, 0xca8}, {0xcaa, 0xcb3},
    {0xcb5, 0xcb9}, {0xcbc, 0xcc4}, {0xcc6, 0xcc8}, {0xcca, 0xccd},
    {0xce0, 0xce3}, {0xce6, 0xcef}, {0xd01, 0xd03}, {0xd05, 0xd0c},
    {0xd0e, 0xd10}, {0xd12, 0xd3a}, {0xd3d, 0xd44}, {0xd46, 0xd48},
    {0xd4a, 0xd4f}, {0xd54, 0xd63}, {0xd66, 0xd7f}, {0xd85, 0xd96},
    {0xd9a, 0xdb1}, {0xdb3, 0xdbb}, {0xdc0, 0xdc6}, {0xdcf, 0xdd4},
    {0xdd8, 0xddf}, {0xde6, 0xdef}, {0xdf2, 0xdf4}, {0xe01, 0xe3a},
    {0xe3f, 0xe5b}, {0xe94, 0xe97}, {0xe99, 0xe9f}, {0xea1, 0xea3},
    {0xead, 0xeb9}, {0xebb, 0xebd}, {0xec0, 0xec4}, {0xec8, 0xecd},
    {0xed0, 0xed9}, {0xedc, 0xedf}, {0xf00, 0xf47}, {0xf49, 0xf6c},
    {0xf71, 0xf97}, {0xf99, 0xfbc}, {0xfbe, 0xfcc}, {0xfce, 0xfda},
    {0x1000, 0x10c5}, {0x10d0, 0x1248}, {0x124a, 0x124d}, {0x1250, 0x1256},
    {0x125a, 0x125d}, {0x1260, 0x1288}, {0x128a, 0x128d}, {0x1290, 0x12b0},
    {0x12b2, 0x12b5}, {0x12b8, 0x12be}, {0x12c2, 0x12c5}, {0x12c8, 0x12d6},
    {0x12d8, 0x1310}, {0x1312, 0x1315}, {0x1318, 0x135a}, {0x135d, 0x137c},
    {0x1380, 0x1399}, {0x13a0, 0x13f5}, {0x13f8, 0x13fd}, {0x1400, 0x167f},
    {0x1681, 0x169c}, {0x16a0, 0x16f8}, {0x1700, 0x170c}, {0x170e, 0x1714},
    {0x1720, 0x1736}, {0x1740, 0x1753}, {0x1760, 0x176c}, {0x176e, 0x1770},
    {0x1780, 0x17dd}, {0x17e0, 0x17e9}, {0x17f0, 0x17f9}, {0x1800, 0x180d},
    {0x1810, 0x1819}, {0x1820, 0x1877}, {0x1880, 0x18aa}, {0x18b0, 0x18f5},
    {0x1900, 0x191e}, {0x1920, 0x192b}, {0x1930, 0x193b}, {0x1944, 0x196d},
    {0x1970, 0x1974}, {0x1980, 0x19ab}, {0x19b0, 0x19c9}, {0x19d0, 0x19da},
    {0x19de, 0x1a1b}, {0x1a1e, 0x1a5e}, {0x1a60, 0x1a7c}, {0x1a7f, 0x1a89},
    {0x1a90, 0x1a99}, {0x1aa0, 0x1aad}, {0x1ab0, 0x1abe}, {0x1b00, 0x1b4b},
    {0x1b50, 0x1b7c}, {0x1b80, 0x1bf3}, {0x1bfc, 0x1c37}, {0x1c3b, 0x1c49},
    {0x1c4d, 0x1c88}, {0x1cc0, 0x1cc7}, {0x1cd0, 0x1cf6}, {0x1d00, 0x1df5},
    {0x1dfb, 0x1f15}, {0x1f18, 0x1f1d}, {0x1f20, 0x1f45}, {0x1f48, 0x1f4d},
    {0x1f50, 0x1f57}, {0x1f5f, 0x1f7d}, {0x1f80, 0x1fb4}, {0x1fb6, 0x1fc4},
    {0x1fc6, 0x1fd3}, {0x1fd6, 0x1fdb}, {0x1fdd, 0x1fef}, {0x1ff2, 0x1ff4},
    {0x1ff6, 0x1ffe}, {0x2010, 0x2027}, {0x2030, 0x205e}, {0x2074, 0x208e},
    {0x2090, 0x209c}, {0x20a0, 0x20be}, {0x20d0, 0x20f0}, {0x2100, 0x218b},
    {0x2190, 0x23fe}, {0x2400, 0x2426}, {0x2440, 0x244a}, {0x2460, 0x2b73},
    {0x2b76, 0x2b95}, {0x2b98, 0x2bb9}, {0x2bbd, 0x2bc8}, {0x2bca, 0x2bd1},
    {0x2bec, 0x2bef}, {0x2c00, 0x2c2e}, {0x2c30, 0x2c5e}, {0x2c60, 0x2cf3},
    {0x2cf9, 0x2d25}, {0x2d30, 0x2d67}, {0x2d7f, 0x2d96}, {0x2da0, 0x2da6},
    {0x2da8, 0x2dae}, {0x2db0, 0x2db6}, {0x2db8, 0x2dbe}, {0x2dc0, 0x2dc6},
    {0x2dc8, 0x2dce}, {0x2dd0, 0x2dd6}, {0x2dd8, 0x2dde}, {0x2de0, 0x2e44},
    {0x2e80, 0x2e99}, {0x2e9b, 0x2ef3}, {0x2f00, 0x2fd5}, {0x2ff0, 0x2ffb},
    {0x3001, 0x303f}, {0x3041, 0x3096}, {0x3099, 0x30ff}, {0x3105, 0x312d},
    {0x3131, 0x318e}, {0x3190, 0x31ba}, {0x31c0, 0x31e3}, {0x31f0, 0x321e},
    {0x3220, 0x32fe}, {0x3300, 0x4db5}, {0x4dc0, 0x9fd5}, {0xa000, 0xa48c},
    {0xa490, 0xa4c6}, {0xa4d0, 0xa62b}, {0xa640, 0xa6f7}, {0xa700, 0xa7ae},
    {0xa7b0, 0xa7b7}, {0xa7f7, 0xa82b}, {0xa830, 0xa839}, {0xa840, 0xa877},
    {0xa880, 0xa8c5}, {0xa8ce, 0xa8d9}, {0xa8e0, 0xa8fd}, {0xa900, 0xa953},
    {0xa95f, 0xa97c}, {0xa980, 0xa9cd}, {0xa9cf, 0xa9d9}, {0xa9de, 0xa9fe},
    {0xaa00, 0xaa36}, {0xaa40, 0xaa4d}, {0xaa50, 0xaa59}, {0xaa5c, 0xaac2},
    {0xaadb, 0xaaf6}, {0xab01, 0xab06}, {0xab09, 0xab0e}, {0xab11, 0xab16},
    {0xab20, 0xab26}, {0xab28, 0xab2e}, {0xab30, 0xab65}, {0xab70, 0xabed},

    {0xfe20, 0xfe52}, {0xfe54, 0xfe66}, {0xfe68, 0xfe6b}, {0xfe70, 0xfe74},
    {0xfe76, 0xfefc}, {0xff01, 0xffbe}, {0xffc2, 0xffc7}, {0xffca, 0xffcf},
    {0xffd2, 0xffd7}, {0xffda, 0xffdc}, {0xffe0, 0xffe6}, {0xffe8, 0xffee}
#if TCL_UTF_MAX > 4
    ,{0x10000, 0x1000b}, {0x1000d, 0x10026}, {0x10028, 0x1003a}, {0x1003f, 0x1004d},
    {0x10050, 0x1005d}, {0x10080, 0x100fa}, {0x10100, 0x10102}, {0x10107, 0x10133},
    {0x10137, 0x1018e}, {0x10190, 0x1019b}, {0x101d0, 0x101fd}, {0x10280, 0x1029c},
    {0x102a0, 0x102d0}, {0x102e0, 0x102fb}, {0x10300, 0x10323}, {0x10330, 0x1034a},
    {0x10350, 0x1037a}, {0x10380, 0x1039d}, {0x1039f, 0x103c3}, {0x103c8, 0x103d5},
    {0x10400, 0x1049d}, {0x104a0, 0x104a9}, {0x104b0, 0x104d3}, {0x104d8, 0x104fb},
    {0x10500, 0x10527}, {0x10530, 0x10563}, {0x10600, 0x10736}, {0x10740, 0x10755},
    {0x10760, 0x10767}, {0x10800, 0x10805}, {0x1080a, 0x10835}, {0x1083f, 0x10855},
    {0x10857, 0x1089e}, {0x108a7, 0x108af}, {0x108e0, 0x108f2}, {0x108fb, 0x1091b},
    {0x1091f, 0x10939}, {0x10980, 0x109b7}, {0x109bc, 0x109cf}, {0x109d2, 0x10a03},
    {0x10a0c, 0x10a13}, {0x10a15, 0x10a17}, {0x10a19, 0x10a33}, {0x10a38, 0x10a3a},

    {0x1128f, 0x1129d}, {0x1129f, 0x112a9}, {0x112b0, 0x112ea}, {0x112f0, 0x112f9},
    {0x11300, 0x11303}, {0x11305, 0x1130c}, {0x11313, 0x11328}, {0x1132a, 0x11330},
    {0x11335, 0x11339}, {0x1133c, 0x11344}, {0x1134b, 0x1134d}, {0x1135d, 0x11363},
    {0x11366, 0x1136c}, {0x11370, 0x11374}, {0x11400, 0x11459}, {0x11480, 0x114c7},
    {0x114d0, 0x114d9}, {0x11580, 0x115b5}, {0x115b8, 0x115dd}, {0x11600, 0x11644},
    {0x11650, 0x11659}, {0x11660, 0x1166c}, {0x11680, 0x116b7}, {0x116c0, 0x116c9},
    {0x11700, 0x11719}, {0x1171d, 0x1172b}, {0x11730, 0x1173f}, {0x118a0, 0x118f2},

    {0x11ac0, 0x11af8}, {0x11c00, 0x11c08}, {0x11c0a, 0x11c36}, {0x11c38, 0x11c45},
    {0x11c50, 0x11c6c}, {0x11c70, 0x11c8f}, {0x11c92, 0x11ca7}, {0x11ca9, 0x11cb6},

    {0x12000, 0x12399}, {0x12400, 0x1246e}, {0x12470, 0x12474}, {0x12480, 0x12543},
    {0x13000, 0x1342e}, {0x14400, 0x14646}, {0x16800, 0x16a38}, {0x16a40, 0x16a5e},
    {0x16a60, 0x16a69}, {0x16ad0, 0x16aed}, {0x16af0, 0x16af5}, {0x16b00, 0x16b45},
    {0x16b50, 0x16b59}, {0x16b5b, 0x16b61}, {0x16b63, 0x16b77}, {0x16b7d, 0x16b8f},
    {0x16f00, 0x16f44}, {0x16f50, 0x16f7e}, {0x16f8f, 0x16f9f}, {0x17000, 0x187ec},
    {0x18800, 0x18af2}, {0x1bc00, 0x1bc6a}, {0x1bc70, 0x1bc7c}, {0x1bc80, 0x1bc88},
    {0x1bc90, 0x1bc99}, {0x1bc9c, 0x1bc9f}, {0x1d000, 0x1d0f5}, {0x1d100, 0x1d126},
    {0x1d129, 0x1d172}, {0x1d17b, 0x1d1e8}, {0x1d200, 0x1d245}, {0x1d300, 0x1d356},
    {0x1d360, 0x1d371}, {0x1d400, 0x1d454}, {0x1d456, 0x1d49c}, {0x1d4a9, 0x1d4ac},
    {0x1d4ae, 0x1d4b9}, {0x1d4bd, 0x1d4c3}, {0x1d4c5, 0x1d505}, {0x1d507, 0x1d50a},
    {0x1d50d, 0x1d514}, {0x1d516, 0x1d51c}, {0x1d51e, 0x1d539}, {0x1d53b, 0x1d53e},
    {0x1d540, 0x1d544}, {0x1d54a, 0x1d550}, {0x1d552, 0x1d6a5}, {0x1d6a8, 0x1d7cb},
    {0x1d7ce, 0x1da8b}, {0x1da9b, 0x1da9f}, {0x1daa1, 0x1daaf}, {0x1e000, 0x1e006},
    {0x1e008, 0x1e018}, {0x1e01b, 0x1e021}, {0x1e026, 0x1e02a}, {0x1e800, 0x1e8c4},
    {0x1e8c7, 0x1e8d6}, {0x1e900, 0x1e94a}, {0x1e950, 0x1e959}, {0x1ee00, 0x1ee03},
    {0x1ee05, 0x1ee1f}, {0x1ee29, 0x1ee32}, {0x1ee34, 0x1ee37}, {0x1ee4d, 0x1ee4f},
    {0x1ee67, 0x1ee6a}, {0x1ee6c, 0x1ee72}, {0x1ee74, 0x1ee77}, {0x1ee79, 0x1ee7c},
    {0x1ee80, 0x1ee89}, {0x1ee8b, 0x1ee9b}, {0x1eea1, 0x1eea3}, {0x1eea5, 0x1eea9},
    {0x1eeab, 0x1eebb}, {0x1f000, 0x1f02b}, {0x1f030, 0x1f093}, {0x1f0a0, 0x1f0ae},
    {0x1f0b1, 0x1f0bf}, {0x1f0c1, 0x1f0cf}, {0x1f0d1, 0x1f0f5}, {0x1f100, 0x1f10c},
    {0x1f110, 0x1f12e}, {0x1f130, 0x1f16b}, {0x1f170, 0x1f1ac}, {0x1f1e6, 0x1f202},
    {0x1f210, 0x1f23b}, {0x1f240, 0x1f248}, {0x1f300, 0x1f6d2}, {0x1f6e0, 0x1f6ec},

    {0x1f6f0, 0x1f6f6}, {0x1f700, 0x1f773}, {0x1f780, 0x1f7d4}, {0x1f800, 0x1f80b},
    {0x1f810, 0x1f847}, {0x1f850, 0x1f859}, {0x1f860, 0x1f887}, {0x1f890, 0x1f8ad},
    {0x1f910, 0x1f91e}, {0x1f920, 0x1f927}, {0x1f933, 0x1f93e}, {0x1f940, 0x1f94b},
    {0x1f950, 0x1f95e}, {0x1f980, 0x1f991}, {0x20000, 0x2a6d6}, {0x2a700, 0x2b734},
    {0x2b740, 0x2b81d}, {0x2b820, 0x2cea1}, {0x2f800, 0x2fa1d}, {0xe0100, 0xe01ef}
#endif
};

#define NUM_GRAPH_RANGE (sizeof(graphRangeTable)/sizeof(crange))

static const chr graphCharTable[] = {
    0x38c, 0x589, 0x58a, 0x85e, 0x98f, 0x990, 0x9b2, 0x9c7, 0x9c8,
    0x9d7, 0x9dc, 0x9dd, 0xa0f, 0xa10, 0xa32, 0xa33, 0xa35, 0xa36,
    0xa38, 0xa39, 0xa3c, 0xa47, 0xa48, 0xa51, 0xa5e, 0xab2, 0xab3,
    0xad0, 0xaf9, 0xb0f, 0xb10, 0xb32, 0xb33, 0xb47, 0xb48, 0xb56,
    0xb57, 0xb5c, 0xb5d, 0xb82, 0xb83, 0xb99, 0xb9a, 0xb9c, 0xb9e,
    0xb9f, 0xba3, 0xba4, 0xbd0, 0xbd7, 0xc55, 0xc56, 0xcd5, 0xcd6,
    0xcde, 0xcf1, 0xcf2, 0xd82, 0xd83, 0xdbd, 0xdca, 0xdd6, 0xe81,
    0xe82, 0xe84, 0xe87, 0xe88, 0xe8a, 0xe8d, 0xea5, 0xea7, 0xeaa,
    0xeab, 0xec6, 0x10c7, 0x10cd, 0x1258, 0x12c0, 0x1772, 0x1773, 0x1940,
    0x1cf8, 0x1cf9, 0x1f59, 0x1f5b, 0x1f5d, 0x2070, 0x2071, 0x2d27, 0x2d2d,
    0x2d6f, 0x2d70, 0xfb3e, 0xfb40, 0xfb41, 0xfb43, 0xfb44, 0xfffc, 0xfffd
#if TCL_UTF_MAX > 4
    ,0x1003c, 0x1003d, 0x101a0, 0x1056f, 0x10808, 0x10837, 0x10838, 0x1083c, 0x108f4,
    0x108f5, 0x1093f, 0x10a05, 0x10a06, 0x11288, 0x1130f, 0x11310, 0x11332, 0x11333,
    0x11347, 0x11348, 0x11350, 0x11357, 0x1145b, 0x1145d, 0x118ff, 0x16a6e, 0x16a6f,
    0x16fe0, 0x1b000, 0x1b001, 0x1d49e, 0x1d49f, 0x1d4a2, 0x1d4a5, 0x1d4a6, 0x1d4bb,
    0x1d546, 0x1e023, 0x1e024, 0x1e95e, 0x1e95f, 0x1ee21, 0x1ee22, 0x1ee24, 0x1ee27,
    0x1ee39, 0x1ee3b, 0x1ee42, 0x1ee47, 0x1ee49, 0x1ee4b, 0x1ee51, 0x1ee52, 0x1ee54,
    0x1ee57, 0x1ee59, 0x1ee5b, 0x1ee5d, 0x1ee5f, 0x1ee61, 0x1ee62, 0x1ee64, 0x1ee7e,
    0x1eef0, 0x1eef1, 0x1f250, 0x1f251, 0x1f930, 0x1f9c0
#endif
};

#define NUM_GRAPH_CHAR (sizeof(graphCharTable)/sizeof(chr))

/*
 *	End of auto-generated Unicode character ranges declarations.

    int Tcl_EvalObjv(Tcl_Interp *interp, int objc, Tcl_Obj *const objv[],
	    int flags)
}
declare 293 {
    int Tcl_EvalObjEx(Tcl_Interp *interp, Tcl_Obj *objPtr, int flags)
}
declare 294 {
    void Tcl_ExitThread(int status)
}
declare 295 {
    int Tcl_ExternalToUtf(Tcl_Interp *interp, Tcl_Encoding encoding,
	    const char *src, int srcLen, int flags,
	    Tcl_EncodingState *statePtr, char *dst, int dstLen,
	    int *srcReadPtr, int *dstWrotePtr, int *dstCharsPtr)
}

# TIP #400
declare 630 {
    void Tcl_ZlibStreamSetCompressionDictionary(Tcl_ZlibStream zhandle,
	    Tcl_Obj *compressionDictionaryObj)
}

# ----- BASELINE -- FOR -- 8.6.0 ----- #












##############################################################################

# Define the platform specific public Tcl interface. These functions are only
# available on the designated platform.

interface tclPlat

 * When version numbers change here, must also go into the following files and
 * update the version numbers:
 *
 * library/init.tcl	(1 LOC patch)
 * unix/configure.ac	(2 LOC Major, 2 LOC minor, 1 LOC patch)
 * win/configure.ac	(as above)
 * win/tcl.m4		(not patchlevel)
 * win/makefile.bc	(not patchlevel) 2 LOC
 * README		(sections 0 and 2, with and without separator)
 * macosx/Tcl.pbproj/project.pbxproj (not patchlevel) 1 LOC
 * macosx/Tcl.pbproj/default.pbxuser (not patchlevel) 1 LOC
 * macosx/Tcl.xcode/project.pbxproj (not patchlevel) 2 LOC
 * macosx/Tcl.xcode/default.pbxuser (not patchlevel) 1 LOC
 * macosx/Tcl-Common.xcconfig (not patchlevel) 1 LOC
 * win/README		(not patchlevel) (sections 0 and 2)
 * unix/tcl.spec	(1 LOC patch)
 * tools/tcl.hpj.in	(not patchlevel, for windows installer)
 */

#define TCL_MAJOR_VERSION   8
#define TCL_MINOR_VERSION   7
#define TCL_RELEASE_LEVEL   TCL_ALPHA_RELEASE
#define TCL_RELEASE_SERIAL  0

#define TCL_VERSION	    "8.7"
#define TCL_PATCH_LEVEL	    "8.7a0"


/*
 *----------------------------------------------------------------------------
 * The following definitions set up the proper options for Windows compilers.
 * We use this method because there is no autoconf equivalent.
 */

#ifdef _WIN32

#  define STRINGIFY(x) STRINGIFY1(x)
#  define STRINGIFY1(x) #x
#endif
#ifndef JOIN
#  define JOIN(a,b) JOIN1(a,b)
#  define JOIN1(a,b) a##b
#endif


/*
 * A special definition used to allow this header file to be included from
 * windows resource files so that they can obtain version information.
 * RC_INVOKED is defined by default by the windows RC tool.
 *
 * Resource compilers don't like all the C stuff, like typedefs and function

 */

#include <stdarg.h>
#ifndef TCL_NO_DEPRECATED
#    define TCL_VARARGS(type, name) (type name, ...)
#    define TCL_VARARGS_DEF(type, name) (type name, ...)
#    define TCL_VARARGS_START(type, name, list) (va_start(list, name), name)
#endif
#if defined(__GNUC__) && (__GNUC__ > 2)
#   define TCL_FORMAT_PRINTF(a,b) __attribute__ ((__format__ (__printf__, a, b)))
#   define TCL_NORETURN __attribute__ ((noreturn))
#   define TCL_NOINLINE __attribute__ ((noinline))
#   if defined(BUILD_tcl) || defined(BUILD_tk)
#	define TCL_NORETURN1 __attribute__ ((noreturn))
#   else

 *
 * New code should use prototypes.
 */

#ifndef TCL_NO_DEPRECATED
#   undef _ANSI_ARGS_
#   define _ANSI_ARGS_(x)	x
#endif

/*
 * Definitions that allow this header file to be used either with or without
 * ANSI C features.
 */

#ifndef INLINE

/*
 * Define Tcl_WideInt to be a type that is (at least) 64-bits wide, and define
 * Tcl_WideUInt to be the unsigned variant of that type (assuming that where
 * we have one, we can have the other.)
 *
 * Also defines the following macros:
 * TCL_WIDE_INT_IS_LONG - if wide ints are really longs (i.e. we're on a real
 *	64-bit system.)
 * Tcl_WideAsLong - forgetful converter from wideInt to long.
 * Tcl_LongAsWide - sign-extending converter from long to wideInt.
 * Tcl_WideAsDouble - converter from wideInt to double.
 * Tcl_DoubleAsWide - converter from double to wideInt.
 *
 * The following invariant should hold for any long value 'longVal':
 *	longVal == Tcl_WideAsLong(Tcl_LongAsWide(longVal))
 *
 * Note on converting between Tcl_WideInt and strings. This implementation (in
 * tclObj.c) depends on the function
 * sprintf(...,"%" TCL_LL_MODIFIER "d",...).
 */

#if !defined(TCL_WIDE_INT_TYPE)&&!defined(TCL_WIDE_INT_IS_LONG)
#   if defined(_WIN32)
#      define TCL_WIDE_INT_TYPE __int64
#      ifdef __BORLANDC__
#         define TCL_LL_MODIFIER	"L"
#      else /* __BORLANDC__ */
#         define TCL_LL_MODIFIER	"I64"
#      endif /* __BORLANDC__ */
#   elif defined(__GNUC__)
#      define TCL_WIDE_INT_TYPE long long
#      define TCL_LL_MODIFIER	"ll"
#   else /* ! _WIN32 && ! __GNUC__ */
/*
 * Don't know what platform it is and configure hasn't discovered what is
 * going on for us. Try to guess...

#   define TCL_WIDE_INT_TYPE	long
#endif /* TCL_WIDE_INT_IS_LONG */

typedef TCL_WIDE_INT_TYPE		Tcl_WideInt;
typedef unsigned TCL_WIDE_INT_TYPE	Tcl_WideUInt;

#ifdef TCL_WIDE_INT_IS_LONG
#   define Tcl_WideAsLong(val)		((long)(val))
#   define Tcl_LongAsWide(val)		((long)(val))
#   define Tcl_WideAsDouble(val)	((double)((long)(val)))
#   define Tcl_DoubleAsWide(val)	((long)((double)(val)))
#   ifndef TCL_LL_MODIFIER
#      define TCL_LL_MODIFIER		"l"
#   endif /* !TCL_LL_MODIFIER */
#else /* TCL_WIDE_INT_IS_LONG */
/*
 * The next short section of defines are only done when not running on Windows
 * or some other strange platform.
 */
#   ifndef TCL_LL_MODIFIER
#      define TCL_LL_MODIFIER		"ll"
#   endif /* !TCL_LL_MODIFIER */


#   define Tcl_WideAsLong(val)		((long)((Tcl_WideInt)(val)))
#   define Tcl_LongAsWide(val)		((Tcl_WideInt)((long)(val)))
#   define Tcl_WideAsDouble(val)	((double)((Tcl_WideInt)(val)))
#   define Tcl_DoubleAsWide(val)	((Tcl_WideInt)((double)(val)))
#endif /* TCL_WIDE_INT_IS_LONG */

#if defined(_WIN32)
#   ifdef __BORLANDC__
	typedef struct stati64 Tcl_StatBuf;
#   elif defined(_WIN64)
	typedef struct __stat64 Tcl_StatBuf;
#   elif (defined(_MSC_VER) && (_MSC_VER < 1400)) || defined(_USE_32BIT_TIME_T)
	typedef struct _stati64	Tcl_StatBuf;

				/* When TCL_ERROR is returned, this gives the
				 * line number within the command where the
				 * error occurred (1 if first line). */
#else
    int errorLineDontUse; /* Don't use in extensions! */
#endif
}
#endif /* TCL_NO_DEPRECATED */
Tcl_Interp;

typedef struct Tcl_AsyncHandler_ *Tcl_AsyncHandler;
typedef struct Tcl_Channel_ *Tcl_Channel;
typedef struct Tcl_ChannelTypeVersion_ *Tcl_ChannelTypeVersion;
typedef struct Tcl_Command_ *Tcl_Command;
typedef struct Tcl_Condition_ *Tcl_Condition;

    char staticSpace[TCL_DSTRING_STATIC_SIZE];
				/* Space to use in common case where string is
				 * small. */
} Tcl_DString;

#define Tcl_DStringLength(dsPtr) ((dsPtr)->length)
#define Tcl_DStringValue(dsPtr) ((dsPtr)->string)

#define Tcl_DStringTrunc Tcl_DStringSetLength


/*
 * Definitions for the maximum number of digits of precision that may be
 * specified in the "tcl_precision" variable, and the number of bytes of
 * buffer space required by Tcl_PrintDouble.
 */

 * always parsed whenever the part2 is NULL. (This is to avoid a common error
 * when converting code to use the new object based APIs and forgetting to
 * give the flag)
 */

#ifndef TCL_NO_DEPRECATED
#   define TCL_PARSE_PART1	0x400
#endif

/*
 * Types for linked variables:
 */

#define TCL_LINK_INT		1
#define TCL_LINK_DOUBLE		2
#define TCL_LINK_BOOLEAN	3
#define TCL_LINK_STRING		4
#define TCL_LINK_WIDE_INT	5
#define TCL_LINK_CHAR		6
#define TCL_LINK_UCHAR		7
#define TCL_LINK_SHORT		8
#define TCL_LINK_USHORT		9
#define TCL_LINK_UINT		10




#define TCL_LINK_LONG		11
#define TCL_LINK_ULONG		12

#define TCL_LINK_FLOAT		13
#define TCL_LINK_WIDE_UINT	14
#define TCL_LINK_READ_ONLY	0x80

/*
 *----------------------------------------------------------------------------
 * Forward declarations of Tcl_HashTable and related types.

 *----------------------------------------------------------------------------
 * Definitions needed for the Tcl_LoadFile function. [TIP #416]
 */

#define TCL_LOAD_GLOBAL 1
#define TCL_LOAD_LAZY 2








/*
 *----------------------------------------------------------------------------
 * Single public declaration for NRE.
 */

typedef int (Tcl_NRPostProc) (ClientData data[], Tcl_Interp *interp,
				int result);

#ifdef TCL_MEM_DEBUG
#  undef  Tcl_NewBignumObj
#  define Tcl_NewBignumObj(val) \
     Tcl_DbNewBignumObj(val, __FILE__, __LINE__)
#  undef  Tcl_NewBooleanObj
#  define Tcl_NewBooleanObj(val) \
     Tcl_DbNewBooleanObj(val, __FILE__, __LINE__)
#  undef  Tcl_NewByteArrayObj
#  define Tcl_NewByteArrayObj(bytes, len) \
     Tcl_DbNewByteArrayObj(bytes, len, __FILE__, __LINE__)
#  undef  Tcl_NewDoubleObj
#  define Tcl_NewDoubleObj(val) \
     Tcl_DbNewDoubleObj(val, __FILE__, __LINE__)
#  undef  Tcl_NewIntObj

#   define Tcl_Ckrealloc	Tcl_Realloc
#   define Tcl_Return		Tcl_SetResult
#   define Tcl_TildeSubst	Tcl_TranslateFileName
#if !defined(__APPLE__) /* On OSX, there is a conflict with "mach/mach.h" */
#   define panic		Tcl_Panic
#endif
#   define panicVA		Tcl_PanicVA
#endif /* !TCL_NO_DEPRECATED */

/*
 *----------------------------------------------------------------------------
 * Convenience declaration of Tcl_AppInit for backwards compatibility. This
 * function is not *implemented* by the tcl library, so the storage class is
 * neither DLLEXPORT nor DLLIMPORT.
 */

extern Tcl_AppInitProc Tcl_AppInit;



#endif /* RC_INVOKED */

/*
 * end block for C++
 */

typedef enum TalInstType {
    ASSEM_1BYTE,		/* Fixed arity, 1-byte instruction */
    ASSEM_BEGIN_CATCH,		/* Begin catch: one 4-byte jump offset to be
				 * converted to appropriate exception
				 * ranges */
    ASSEM_BOOL,			/* One Boolean operand */
    ASSEM_BOOL_LVT4,		/* One Boolean, one 4-byte LVT ref. */


    ASSEM_CONCAT1,		/* 1-byte unsigned-integer operand count, must
				 * be strictly positive, consumes N, produces
				 * 1 */
    ASSEM_DICT_GET,		/* 'dict get' and related - consumes N+1
				 * operands, produces 1, N > 0 */
    ASSEM_DICT_SET,		/* specifies key count and LVT index, consumes
				 * N+1 operands, produces 1, N > 0 */

    {"arrayMakeStk",	ASSEM_1BYTE,	INST_ARRAY_MAKE_STK,	1,	0},
    {"beginCatch",	ASSEM_BEGIN_CATCH,
					INST_BEGIN_CATCH4,	0,	0},
    {"bitand",		ASSEM_1BYTE,	INST_BITAND,		2,	1},
    {"bitnot",		ASSEM_1BYTE,	INST_BITNOT,		1,	1},
    {"bitor",		ASSEM_1BYTE,	INST_BITOR,		2,	1},
    {"bitxor",		ASSEM_1BYTE,	INST_BITXOR,		2,	1},

    {"concat",		ASSEM_CONCAT1,	INST_STR_CONCAT1,	INT_MIN,1},
    {"concatStk",	ASSEM_LIST,	INST_CONCAT_STK,	INT_MIN,1},
    {"coroName",	ASSEM_1BYTE,	INST_COROUTINE_NAME,	0,	1},
    {"currentNamespace",ASSEM_1BYTE,	INST_NS_CURRENT,	0,	1},
    {"dictAppend",	ASSEM_LVT4,	INST_DICT_APPEND,	2,	1},
    {"dictExists",	ASSEM_DICT_GET, INST_DICT_EXISTS,	INT_MIN,1},
    {"dictExpand",	ASSEM_1BYTE,	INST_DICT_EXPAND,	3,	1},

	localVar = FindLocalVar(assemEnvPtr, &tokenPtr);
	if (localVar < 0) {
	    goto cleanup;
	}
	BBEmitInstInt1(assemEnvPtr, tblIdx, opnd, 0);
	TclEmitInt4(localVar, envPtr);
	break;


















    case ASSEM_CONCAT1:
	if (parsePtr->numWords != 2) {
	    Tcl_WrongNumArgs(interp, 1, &instNameObj, "imm8");
	    goto cleanup;
	}
	if (GetIntegerOperand(assemEnvPtr, &tokenPtr, &opnd) != TCL_OK

    Tcl_AddErrorInfo(interp, "\n    in assembly code between lines ");
    lineNo = Tcl_NewIntObj(bbPtr->startLine);
    Tcl_IncrRefCount(lineNo);
    Tcl_AppendObjToErrorInfo(interp, lineNo);
    Tcl_AddErrorInfo(interp, " and ");
    if (bbPtr->successor1 != NULL) {
	Tcl_SetIntObj(lineNo, bbPtr->successor1->startLine);
	Tcl_AppendObjToErrorInfo(interp, lineNo);
    } else {
	Tcl_AddErrorInfo(interp, "end of assembly code");
    }
    Tcl_DecrRefCount(lineNo);
}


    /*
     * Commands in the generic core.
     */

    {"append",		Tcl_AppendObjCmd,	TclCompileAppendCmd,	NULL,	CMD_IS_SAFE},
    {"apply",		Tcl_ApplyObjCmd,	NULL,			TclNRApplyObjCmd,	CMD_IS_SAFE},
    {"break",		Tcl_BreakObjCmd,	TclCompileBreakCmd,	NULL,	CMD_IS_SAFE},
#ifndef EXCLUDE_OBSOLETE_COMMANDS
    {"case",		Tcl_CaseObjCmd,		NULL,			NULL,	CMD_IS_SAFE},
#endif
    {"catch",		Tcl_CatchObjCmd,	TclCompileCatchCmd,	TclNRCatchObjCmd,	CMD_IS_SAFE},
    {"concat",		Tcl_ConcatObjCmd,	TclCompileConcatCmd,	NULL,	CMD_IS_SAFE},
    {"continue",	Tcl_ContinueObjCmd,	TclCompileContinueCmd,	NULL,	CMD_IS_SAFE},
    {"coroutine",	NULL,			NULL,			TclNRCoroutineObjCmd,	CMD_IS_SAFE},
    {"error",		Tcl_ErrorObjCmd,	TclCompileErrorCmd,	NULL,	CMD_IS_SAFE},

     * Commands in the OS-interface. Note that many of these are unsafe.
     */

    {"after",		Tcl_AfterObjCmd,	NULL,			NULL,	CMD_IS_SAFE},
    {"cd",		Tcl_CdObjCmd,		NULL,			NULL,	0},
    {"close",		Tcl_CloseObjCmd,	NULL,			NULL,	CMD_IS_SAFE},
    {"eof",		Tcl_EofObjCmd,		NULL,			NULL,	CMD_IS_SAFE},
    {"encoding",	Tcl_EncodingObjCmd,	NULL,			NULL,	0},
    {"exec",		Tcl_ExecObjCmd,		NULL,			NULL,	0},
    {"exit",		Tcl_ExitObjCmd,		NULL,			NULL,	0},
    {"fblocked",	Tcl_FblockedObjCmd,	NULL,			NULL,	CMD_IS_SAFE},
    {"fconfigure",	Tcl_FconfigureObjCmd,	NULL,			NULL,	0},
    {"fcopy",		Tcl_FcopyObjCmd,	NULL,			NULL,	CMD_IS_SAFE},
    {"fileevent",	Tcl_FileEventObjCmd,	NULL,			NULL,	CMD_IS_SAFE},
    {"flush",		Tcl_FlushObjCmd,	NULL,			NULL,	CMD_IS_SAFE},

     * (whose name is ""; an alias is "::"). This also initializes the Tcl
     * object type table and other object management code.
     */

    iPtr = ckalloc(sizeof(Interp));
    interp = (Tcl_Interp *) iPtr;




    iPtr->result = iPtr->resultSpace;

    iPtr->freeProc = NULL;
    iPtr->errorLine = 0;
    iPtr->objResultPtr = Tcl_NewObj();
    Tcl_IncrRefCount(iPtr->objResultPtr);
    iPtr->handle = TclHandleCreate(iPtr);
    iPtr->globalNsPtr = NULL;
    iPtr->hiddenCmdTablePtr = NULL;

    Tcl_IncrRefCount(iPtr->ecVar);
    iPtr->returnLevel = 1;
    iPtr->returnCode = TCL_OK;

    iPtr->rootFramePtr = NULL;	/* Initialise as soon as :: is available */
    iPtr->lookupNsPtr = NULL;


    iPtr->appendResult = NULL;
    iPtr->appendAvl = 0;
    iPtr->appendUsed = 0;


    Tcl_InitHashTable(&iPtr->packageTable, TCL_STRING_KEYS);
    iPtr->packageUnknown = NULL;

    /* TIP #268 */
#if (TCL_RELEASE_LEVEL == TCL_FINAL_RELEASE)
    if (getenv("TCL_PKG_PREFER_LATEST") == NULL) {

    iPtr->activeCmdTracePtr = NULL;
    iPtr->activeInterpTracePtr = NULL;
    iPtr->assocData = NULL;
    iPtr->execEnvPtr = NULL;	/* Set after namespaces initialized. */
    iPtr->emptyObjPtr = Tcl_NewObj();
				/* Another empty object. */
    Tcl_IncrRefCount(iPtr->emptyObjPtr);

    iPtr->resultSpace[0] = 0;

    iPtr->threadId = Tcl_GetCurrentThread();

    /* TIP #378 */
#ifdef TCL_INTERP_DEBUG_FRAME
    iPtr->flags |= INTERP_DEBUG_FRAME;
#else
    if (getenv("TCL_INTERP_DEBUG_FRAME") != NULL) {

	    cmdPtr->tracePtr = NULL;
	    cmdPtr->nreProc = cmdInfoPtr->nreProc;
	    Tcl_SetHashValue(hPtr, cmdPtr);
	}
    }

    /*
     * Create the "array", "binary", "chan", "dict", "file", "info",
     * "namespace" and "string" ensembles. Note that all these commands (and
     * their subcommands that are not present in the global namespace) are
     * wholly safe *except* for "file".
     */

    TclInitArrayCmd(interp);
    TclInitBinaryCmd(interp);
    TclInitChanCmd(interp);
    TclInitDictCmd(interp);

    TclInitFileCmd(interp);
    TclInitInfoCmd(interp);
    TclInitNamespaceCmd(interp);
    TclInitStringCmd(interp);
    TclInitPrefixCmd(interp);

    /*

	return TCL_ERROR;
    }
    for (cmdInfoPtr = builtInCmds; cmdInfoPtr->name != NULL; cmdInfoPtr++) {
	if (!(cmdInfoPtr->flags & CMD_IS_SAFE)) {
	    Tcl_HideCommand(interp, cmdInfoPtr->name, cmdInfoPtr->name);
	}
    }

    TclMakeFileCommandSafe(interp);     /* Ugh! */
    return TCL_OK;
}

/*
 *--------------------------------------------------------------
 *

    Tcl_InterpDeleteProc *proc,	/* Function to call when interpreter is about
				 * to be deleted. */
    ClientData clientData)	/* One-word value to pass to proc. */
{
    Interp *iPtr = (Interp *) interp;
    static Tcl_ThreadDataKey assocDataCounterKey;
    int *assocDataCounterPtr =
	    Tcl_GetThreadData(&assocDataCounterKey, (int)sizeof(int));
    int isNew;
    char buffer[32 + TCL_INTEGER_SPACE];
    AssocData *dPtr = ckalloc(sizeof(AssocData));
    Tcl_HashEntry *hPtr;

    sprintf(buffer, "Assoc Data Key #%d", *assocDataCounterPtr);
    (*assocDataCounterPtr)++;

    Tcl_DecrRefCount(iPtr->upLiteral);
    Tcl_DecrRefCount(iPtr->callLiteral);
    Tcl_DecrRefCount(iPtr->innerLiteral);
    Tcl_DecrRefCount(iPtr->innerContext);
    if (iPtr->returnOpts) {
	Tcl_DecrRefCount(iPtr->returnOpts);
    }

    if (iPtr->appendResult != NULL) {
	ckfree(iPtr->appendResult);
	iPtr->appendResult = NULL;
    }

    TclFreePackageInfo(iPtr);
    while (iPtr->tracePtr != NULL) {
	Tcl_DeleteTrace((Tcl_Interp *) iPtr, (Tcl_Trace) iPtr->tracePtr);
    }
    if (iPtr->execEnvPtr != NULL) {
	TclDeleteExecEnv(iPtr->execEnvPtr);
    }

	switch (args[k].type) {
	case TCL_EITHER:
	    if (Tcl_GetLongFromObj(NULL, valuePtr, &args[k].intValue)
		    == TCL_OK) {
		args[k].type = TCL_INT;
		break;
	    }
	    if (Tcl_GetWideIntFromObj(interp, valuePtr, &args[k].wideValue)
		    == TCL_OK) {
		args[k].type = TCL_WIDE_INT;
		break;
	    }
	    args[k].type = TCL_DOUBLE;
	    /* FALLTHROUGH */

	    break;
	case TCL_WIDE_INT:
	    if (ExprWideFunc(NULL, interp, 2, &objv[j-1]) != TCL_OK) {
		ckfree(args);
		return TCL_ERROR;
	    }
	    valuePtr = Tcl_GetObjResult(interp);
	    Tcl_GetWideIntFromObj(NULL, valuePtr, &args[k].wideValue);
	    Tcl_ResetResult(interp);
	    break;
	}
    }

    /*
     * Call the function.

    Command **cmdPtrPtr,
    Tcl_Obj *commandPtr,
    int objc,
    Tcl_Obj *const objv[])
{
    Interp *iPtr = (Interp *) interp;
    Command *cmdPtr = *cmdPtrPtr;
    int newEpoch, cmdEpoch = cmdPtr->cmdEpoch;
    int length, traceCode = TCL_OK;
    const char *command = TclGetStringFromObj(commandPtr, &length);

    /*
     * Call trace functions.
     * Execute any command or execution traces. Note that we bump up the
     * command's reference count for the duration of the calling of the

 *
 * Side effects:
 *	Can be almost arbitrary, depending on the commands in the script.
 *
 *----------------------------------------------------------------------
 */


#undef Tcl_Eval
int
Tcl_Eval(
    Tcl_Interp *interp,		/* Token for command interpreter (returned by
				 * previous call to Tcl_CreateInterp). */
    const char *script)		/* Pointer to TCL command to execute. */
{

int
Tcl_GlobalEvalObj(
    Tcl_Interp *interp,
    Tcl_Obj *objPtr)
{
    return Tcl_EvalObjEx(interp, objPtr, TCL_EVAL_GLOBAL);
}


/*
 *----------------------------------------------------------------------
 *
 * Tcl_EvalObjEx, TclEvalObjEx --
 *
 *	Execute Tcl commands stored in a Tcl object. These commands are

	    flags |= TCL_EVAL_SOURCE_IN_FRAME;
	}

	TclMarkTailcall(interp);
        TclNRAddCallback(interp, TEOEx_ListCallback, listPtr, eoFramePtr,
		objPtr, NULL);

	ListObjGetElements(listPtr, objc, objv);
	return TclNREvalObjv(interp, objc, objv, flags, NULL);
    }

    if (!(flags & TCL_EVAL_DIRECT)) {
	/*
	 * Let the compiler/engine subsystem do the evaluation.
	 *

#undef Tcl_AddObjErrorInfo
void
Tcl_AppendObjToErrorInfo(
    Tcl_Interp *interp,		/* Interpreter to which error information
				 * pertains. */
    Tcl_Obj *objPtr)		/* Message to record. */
{
    int length;
    const char *message = TclGetStringFromObj(objPtr, &length);

    Tcl_IncrRefCount(objPtr);
    Tcl_AddObjErrorInfo(interp, message, length);
    Tcl_DecrRefCount(objPtr);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_AddErrorInfo --

 *	The contents of message are appended to the errorInfo field. If we are
 *	just starting to log an error, errorInfo is initialized from the error
 *	message in the interpreter's result.
 *
 *----------------------------------------------------------------------
 */


#undef Tcl_AddErrorInfo
void
Tcl_AddErrorInfo(
    Tcl_Interp *interp,		/* Interpreter to which error information
				 * pertains. */
    const char *message)	/* Message to record. */
{
    Tcl_AddObjErrorInfo(interp, message, -1);
}


/*
 *----------------------------------------------------------------------
 *
 * Tcl_AddObjErrorInfo --
 *
 *	Add information to the errorInfo field that describes the current

 *	The command string is executed in interp, and the execution is carried
 *	out in the variable context of global level (no functions active),
 *	just as if an "uplevel #0" command were being executed.
 *
 *----------------------------------------------------------------------
 */


#undef Tcl_GlobalEval
int
Tcl_GlobalEval(
    Tcl_Interp *interp,		/* Interpreter in which to evaluate
				 * command. */
    const char *command)	/* Command to evaluate. */
{
    register Interp *iPtr = (Interp *) interp;
    int result;
    CallFrame *savedVarFramePtr;

    savedVarFramePtr = iPtr->varFramePtr;
    iPtr->varFramePtr = iPtr->rootFramePtr;
    result = Tcl_EvalEx(interp, command, -1, 0);
    iPtr->varFramePtr = savedVarFramePtr;
    return result;
}


/*
 *----------------------------------------------------------------------
 *
 * Tcl_SetRecursionLimit --
 *
 *	Set the maximum number of recursive calls that may be active for an

	}
	if (SIGN(&big) == MP_NEG) {
	    mp_clear(&big);
	    goto negarg;
	}
	break;
    default:
	if (Tcl_GetWideIntFromObj(interp, objv[1], &w) != TCL_OK) {
	    return TCL_ERROR;
	}
	if (w < 0) {
	    goto negarg;
	}
	d = (double) w;
#ifdef IEEE_FLOATING_POINT

    Tcl_WideInt wResult;
    Tcl_Obj *objPtr;

    if (ExprEntierFunc(NULL, interp, objc, objv) != TCL_OK) {
	return TCL_ERROR;
    }
    objPtr = Tcl_GetObjResult(interp);
    if (Tcl_GetWideIntFromObj(NULL, objPtr, &wResult) != TCL_OK) {
	/*
	 * Truncate the bignum; keep only bits in wide int range.
	 */

	mp_int big;

	Tcl_GetBignumFromObj(NULL, objPtr, &big);
	mp_mod_2d(&big, (int) CHAR_BIT * sizeof(Tcl_WideInt), &big);
	objPtr = Tcl_NewBignumObj(&big);
	Tcl_IncrRefCount(objPtr);
	Tcl_GetWideIntFromObj(NULL, objPtr, &wResult);
	Tcl_DecrRefCount(objPtr);
    }
    Tcl_SetObjResult(interp, Tcl_NewWideIntObj(wResult));
    return TCL_OK;
}

static int

    return TCL_OK;
}

/*
 *----------------------------------------------------------------------
 *





























 * NRCoroInjectObjCmd --
 *
 *      Implementation of [::tcl::unsupported::inject] command.
 *
 *----------------------------------------------------------------------
 */

    /*
     * Add the callback to the coro's execEnv, so that it is the first thing
     * to happen when the coro is resumed.
     */

    iPtr->execEnvPtr = corPtr->eePtr;
    TclNREvalObjEx(interp, Tcl_NewListObj(objc-2, objv+2), 0, NULL, INT_MIN);

    iPtr->execEnvPtr = savedEEPtr;

    return TCL_OK;
}

int
TclNRInterpCoroutine(

 * value in the range [0-255].  To be a Tcl value type, we need a way to
 * encode each value in the value set as a Tcl string.  The simplest
 * encoding is to represent each byte value as the same codepoint value.
 * A bytearray of N bytes is encoded into a Tcl string of N characters
 * where the codepoint of each character is the value of corresponding byte.
 * This approach creates a one-to-one map between all bytearray values
 * and a subset of Tcl string values.
 * 
 * When converting a Tcl string value to the bytearray internal rep, the
 * question arises what to do with strings outside that subset?  That is,
 * those Tcl strings containing at least one codepoint greater than 255?
 * The obviously correct answer is to raise an error!  That string value
 * does not represent any valid bytearray value. Full Stop.  The
 * setFromAnyProc signature has a completion code return value for just
 * this reason, to reject invalid inputs.
 * 
 * Unfortunately this was not the path taken by the authors of the
 * original tclByteArrayType.  They chose to accept all Tcl string values
 * as acceptable string encodings of the bytearray values that result
 * from masking away the high bits of any codepoint value at all. This
 * meant that every bytearray value had multiple accepted string
 * representations.
 *

 * in normal Tcl operations unless we burden the script writer with the
 * cognitive burden of avoiding it.  The price is also paid by callers
 * of the C interface.  The routine
 *
 *	unsigned char *Tcl_GetByteArrayFromObj(objPtr, lenPtr)
 *
 * has a guarantee to always return a non-NULL value, but that value
 * points to a byte sequence that cannot be used by the caller to  
 * process the Tcl value absent some sideband testing that objPtr
 * is "pure".  Tcl offers no public interface to perform this test,
 * so callers either break encapsulation or are unavoidably buggy.  Tcl
 * has defined a public interface that cannot be used correctly. The
 * Tcl source code itself suffers the same problem, and has been buggy,
 * but progressively less so as more and more portions of the code have
 * been retrofitted with the required "purity testing".  The set of values
 * able to pass the purity test can be increased via the introduction of
 * a "canonical" flag marker, but the only way the broken interface itself
 * can be discarded is to start over and define the Tcl_ObjType properly.
 * Bytearrays should simply be usable as bytearrays without a kabuki
 * dance of testing.
 *
 * The Tcl_ObjType "properByteArrayType" is (nearly) a correct 
 * implementation of bytearrays.  Any Tcl value with the type
 * properByteArrayType can have its bytearray value fetched and
 * used with confidence that acting on that value is equivalent to
 * acting on the true Tcl string value.  This still implies a side
 * testing burden -- past mistakes will not let us avoid that
 * immediately, but it is at least a conventional test of type, and
 * can be implemented entirely by examining the objPtr fields, with

    src = TclGetString(objPtr);
    length = objPtr->length;
    srcEnd = src + length;

    byteArrayPtr = ckalloc(BYTEARRAY_SIZE(length));
    for (dst = byteArrayPtr->bytes; src < srcEnd; ) {
	src += Tcl_UtfToUniChar(src, &ch);
	improper = improper || (ch > 255);
	*dst++ = UCHAR(ch);
    }

    byteArrayPtr->used = dst - byteArrayPtr->bytes;
    byteArrayPtr->allocated = length;

    goto error;

 badField:
    {
	Tcl_UniChar ch;
	char buf[TCL_UTF_MAX + 1];

	Tcl_UtfToUniChar(errorString, &ch);
	buf[Tcl_UniCharToUtf(ch, buf)] = '\0';
	Tcl_SetObjResult(interp, Tcl_ObjPrintf(
		"bad field specifier \"%s\"", buf));
	return TCL_ERROR;
    }

 error:

    goto error;

 badField:
    {
	Tcl_UniChar ch;
	char buf[TCL_UTF_MAX + 1];

	Tcl_UtfToUniChar(errorString, &ch);
	buf[Tcl_UniCharToUtf(ch, buf)] = '\0';
	Tcl_SetObjResult(interp, Tcl_ObjPrintf(
		"bad field specifier \"%s\"", buf));
	return TCL_ERROR;
    }

 error:

	(*formatPtr)++;
	*flagsPtr |= BINARY_UNSIGNED;
    }
    if (**formatPtr == '*') {
	(*formatPtr)++;
	*countPtr = BINARY_ALL;
    } else if (isdigit(UCHAR(**formatPtr))) { /* INTL: digit */



	*countPtr = strtoul(*formatPtr, (char **) formatPtr, 10);





    } else {
	*countPtr = BINARY_NOCOUNT;
    }
    return 1;
}

/*

 * mem_header. It is used to get back to the header pointer from the body
 * pointer that's used by clients.
 */

#define BODY_OFFSET \
	((size_t) (&((struct mem_header *) 0)->body))

static int total_mallocs = 0;
static int total_frees = 0;
static size_t current_bytes_malloced = 0;
static size_t maximum_bytes_malloced = 0;
static int current_malloc_packets = 0;
static int maximum_malloc_packets = 0;
static int break_on_malloc = 0;
static int trace_on_at_malloc = 0;
static int alloc_tracing = FALSE;
static int init_malloced_bodies = TRUE;
#ifdef MEM_VALIDATE
static int validate_memory = TRUE;
#else
static int validate_memory = FALSE;
#endif

{
    char buf[1024];

    if (clientData == NULL) {
        return 0;
    }
    sprintf(buf,
	    "total mallocs             %10d\n"
	    "total frees               %10d\n"
	    "current packets allocated %10d\n"
	    "current bytes allocated   %10lu\n"
	    "maximum packets allocated %10d\n"
	    "maximum bytes allocated   %10lu\n",
	    total_mallocs,
	    total_frees,
	    current_malloc_packets,
	    (unsigned long)current_bytes_malloced,
	    maximum_malloc_packets,
	    (unsigned long)maximum_bytes_malloced);
    if (flags == 0) {
	fprintf((FILE *)clientData, "%s", buf);
    } else {
	/* Assume objPtr to append to */
	Tcl_AppendToObj((Tcl_Obj *) clientData, buf, -1);
    }
    return 1;

	    return TCL_ERROR;
	}
    }

    Tcl_MutexLock(ckallocMutexPtr);
    for (memScanP = allocHead; memScanP != NULL; memScanP = memScanP->flink) {
	address = &memScanP->body[0];
	fprintf(fileP, "%8" TCL_LL_MODIFIER "x - %8" TCL_LL_MODIFIER "x  %7" TCL_LL_MODIFIER "d @ %s %d %s",
		(Tcl_WideInt)(size_t)address,
		(Tcl_WideInt)((size_t)address + memScanP->length - 1),
		(Tcl_WideInt)memScanP->length, memScanP->file, memScanP->line,
		(memScanP->tagPtr == NULL) ? "" : memScanP->tagPtr->string);
	(void) fputc('\n', fileP);
    }
    Tcl_MutexUnlock(ckallocMutexPtr);

    if (fileP != stderr) {

	allocHead->blink = result;
    }
    allocHead = result;

    total_mallocs++;
    if (trace_on_at_malloc && (total_mallocs >= trace_on_at_malloc)) {
	(void) fflush(stdout);
	fprintf(stderr, "reached malloc trace enable point (%d)\n",
		total_mallocs);
	fflush(stderr);
	alloc_tracing = TRUE;
	trace_on_at_malloc = 0;
    }

    if (alloc_tracing) {
	fprintf(stderr,"ckalloc %p %u %s %d\n",
		result->body, size, file, line);
    }

    if (break_on_malloc && (total_mallocs >= break_on_malloc)) {
	break_on_malloc = 0;
	(void) fflush(stdout);
	Tcl_Panic("reached malloc break limit (%d)", total_mallocs);
    }

    current_malloc_packets++;
    if (current_malloc_packets > maximum_malloc_packets) {
	maximum_malloc_packets = current_malloc_packets;
    }
    current_bytes_malloced += size;

	    Tcl_SetObjResult(interp, Tcl_ObjPrintf("error accessing %s: %s",
                    argv[2], Tcl_PosixError(interp)));
	    return TCL_ERROR;
	}
	return TCL_OK;
    }
    if (strcmp(argv[1],"break_on_malloc") == 0) {

	if (argc != 3) {
	    goto argError;
	}
	if (Tcl_GetInt(interp, argv[2], &break_on_malloc) != TCL_OK) {
	    return TCL_ERROR;
	}

	return TCL_OK;
    }
    if (strcmp(argv[1],"info") == 0) {
	Tcl_SetObjResult(interp, Tcl_ObjPrintf(
		"%-25s %10d\n%-25s %10d\n%-25s %10d\n%-25s %10lu\n%-25s %10d\n%-25s %10lu\n",
		"total mallocs", total_mallocs, "total frees", total_frees,
		"current packets allocated", current_malloc_packets,
		"current bytes allocated", (unsigned long)current_bytes_malloced,
		"maximum packets allocated", maximum_malloc_packets,
		"maximum bytes allocated", (unsigned long)maximum_bytes_malloced));
	return TCL_OK;
    }
    if (strcmp(argv[1], "init") == 0) {
	if (argc != 3) {
	    goto bad_suboption;
	}
	init_malloced_bodies = (strcmp(argv[2],"on") == 0);

	    goto bad_suboption;
	}
	alloc_tracing = (strcmp(argv[2],"on") == 0);
	return TCL_OK;
    }

    if (strcmp(argv[1],"trace_on_at_malloc") == 0) {

	if (argc != 3) {
	    goto argError;
	}
	if (Tcl_GetInt(interp, argv[2], &trace_on_at_malloc) != TCL_OK) {
	    return TCL_ERROR;
	}

	return TCL_OK;
    }
    if (strcmp(argv[1],"validate") == 0) {
	if (argc != 3) {
	    goto bad_suboption;
	}
	validate_memory = (strcmp(argv[2],"on") == 0);

    "year"
};

/*
 * Structure containing the client data for [clock]
 */

typedef struct ClockClientData {
    size_t refCount;		/* Number of live references. */
    Tcl_Obj **literals;		/* Pool of object literals. */
} ClockClientData;

/*
 * Structure containing the fields used in [clock format] and [clock scan]
 */

				 * the end of the table. */
    Tcl_ObjCmdProc *objCmdProc;	/* Function that implements the command. This
				 * will always have the ClockClientData sent
				 * to it, but may well ignore this data. */
};

static const struct ClockCommand clockCommands[] = {
    { "clicks",			ClockClicksObjCmd },
    { "getenv",			ClockGetenvObjCmd },
    { "microseconds",		ClockMicrosecondsObjCmd },
    { "milliseconds",		ClockMillisecondsObjCmd },
    { "seconds",		ClockSecondsObjCmd },
    { "Oldscan",		TclClockOldscanObjCmd },
    { "ConvertLocalToUTC",	ClockConvertlocaltoutcObjCmd },
    { "GetDateFields",		ClockGetdatefieldsObjCmd },
    { "GetJulianDayFromEraYearMonthDay",
		ClockGetjuliandayfromerayearmonthdayObjCmd },
    { "GetJulianDayFromEraYearWeekDay",
		ClockGetjuliandayfromerayearweekdayObjCmd },

    const struct ClockCommand *clockCmdPtr;
    char cmdName[50];		/* Buffer large enough to hold the string
				 *::tcl::clock::GetJulianDayFromEraYearMonthDay
				 * plus a terminating NUL. */
    ClockClientData *data;
    int i;














    /*
     * Safe interps get [::clock] as alias to a master, so do not need their
     * own copies of the support routines.
     */

    if (Tcl_IsSafe(interp)) {
	return;

    for (i = 0; i < LIT__END; ++i) {
	data->literals[i] = Tcl_NewStringObj(literals[i], -1);
	Tcl_IncrRefCount(data->literals[i]);
    }

    /*
     * Install the commands.

     */

#define TCL_CLOCK_PREFIX_LEN 14 /* == strlen("::tcl::clock::") */
    memcpy(cmdName, "::tcl::clock::", TCL_CLOCK_PREFIX_LEN);
    for (clockCmdPtr=clockCommands ; clockCmdPtr->name!=NULL ; clockCmdPtr++) {
	strcpy(cmdName + TCL_CLOCK_PREFIX_LEN, clockCmdPtr->name);
	data->refCount++;
	Tcl_CreateObjCommand(interp, cmdName, clockCmdPtr->objCmdProc, data,
		ClockDeleteCmdProc);
    }




}

/*
 *----------------------------------------------------------------------
 *
 * ClockConvertlocaltoutcObjCmd --
 *

	return TCL_ERROR;
    }
    if (secondsObj == NULL) {
	Tcl_SetObjResult(interp, Tcl_NewStringObj("key \"localseconds\" not "
		"found in dictionary", -1));
	return TCL_ERROR;
    }
    if ((Tcl_GetWideIntFromObj(interp, secondsObj,
	    &fields.localSeconds) != TCL_OK)
	|| (TclGetIntFromObj(interp, objv[3], &changeover) != TCL_OK)
	|| ConvertLocalToUTC(interp, &fields, objv[2], changeover)) {
	return TCL_ERROR;
    }

    /*

     * Check params.
     */

    if (objc != 4) {
	Tcl_WrongNumArgs(interp, 1, objv, "seconds tzdata changeover");
	return TCL_ERROR;
    }
    if (Tcl_GetWideIntFromObj(interp, objv[1], &fields.seconds) != TCL_OK
	    || TclGetIntFromObj(interp, objv[3], &changeover) != TCL_OK) {
	return TCL_ERROR;
    }

    /*
     * fields.seconds could be an unsigned number that overflowed. Make sure
     * that it isn't.

    Tcl_WideInt compVal;

    /*
     * Examine the first row to make sure we're in bounds.
     */

    if (Tcl_ListObjIndex(interp, rowv[0], 0, &compObj) != TCL_OK
	    || Tcl_GetWideIntFromObj(interp, compObj, &compVal) != TCL_OK) {
	return NULL;
    }

    /*
     * Bizarre case - first row doesn't begin at MIN_WIDE_INT. Return it
     * anyway.
     */

    l = 0;
    u = rowc-1;
    while (l < u) {
	int m = (l + u + 1) / 2;

	if (Tcl_ListObjIndex(interp, rowv[m], 0, &compObj) != TCL_OK ||
		Tcl_GetWideIntFromObj(interp, compObj, &compVal) != TCL_OK) {
	    return NULL;
	}
	if (tick >= compVal) {
	    l = m;
	} else {
	    u = m-1;
	}

    ym1o4 = ym1 / 4;
#else
    /*
     * Have to make sure quotient is truncated towards 0 when negative.
     * See above bug for details. The casts are necessary.
     */
    if (ym1 >= 0)
        ym1o4 = ym1 / 4;
    else {
        ym1o4 = - (int) (((unsigned int) -ym1) / 4);
    }
#endif
    if (ym1 % 4 < 0) {
	ym1o4--;
    }
    ym1o100 = ym1 / 100;
    if (ym1 % 100 < 0) {

 *----------------------------------------------------------------------
 */

static int
IsGregorianLeapYear(
    TclDateFields *fields)	/* Date to test */
{
    int year;

    if (fields->era == BCE) {
	year = 1 - fields->year;
    } else {
	year = fields->year;
    }
    if (year%4 != 0) {
	return 0;
    } else if (!(fields->gregorian)) {
	return 1;
    } else if (year%400 == 0) {
	return 1;

    const time_t *timePtr)	/* Pointer to the number of seconds since the
				 * local system's epoch */
{
    /*
     * Get a thread-local buffer to hold the returned time.
     */

    struct tm *tmPtr = Tcl_GetThreadData(&tmKey, (int) sizeof(struct tm));
#ifdef HAVE_LOCALTIME_R
    localtime_r(timePtr, tmPtr);
#else
    struct tm *sysTmPtr;

    Tcl_MutexLock(&clockMutex);
    sysTmPtr = localtime(timePtr);

	saw |= 1 << optionIndex;
    }

    /*
     * Check options.
     */

    if (Tcl_GetWideIntFromObj(interp, objv[1], &clockVal) != TCL_OK) {
	return TCL_ERROR;
    }
    if ((saw & (1 << CLOCK_FORMAT_GMT))
	    && (saw & (1 << CLOCK_FORMAT_TIMEZONE))) {
	Tcl_SetObjResult(interp, litPtr[LIT_CANNOT_USE_GMT_AND_TIMEZONE]);
	Tcl_SetErrorCode(interp, "CLOCK", "gmtWithTimezone", NULL);
	return TCL_ERROR;

/*
 * Prototypes for local procedures defined in this file:
 */

static int		CheckAccess(Tcl_Interp *interp, Tcl_Obj *pathPtr,
			    int mode);









static int		EncodingDirsObjCmd(ClientData dummy,
			    Tcl_Interp *interp, int objc,






			    Tcl_Obj *const objv[]);
static inline int	ForeachAssignments(Tcl_Interp *interp,
			    struct ForeachState *statePtr);
static inline void	ForeachCleanup(Tcl_Interp *interp,
			    struct ForeachState *statePtr);
static int		GetStatBuf(Tcl_Interp *interp, Tcl_Obj *pathPtr,
			    Tcl_FSStatProc *statProc, Tcl_StatBuf *statPtr);

 *	A standard Tcl object result.
 *
 * Side effects:
 *	See the user documentation.
 *
 *----------------------------------------------------------------------
 */

	/* ARGSUSED */
int
Tcl_CaseObjCmd(
    ClientData dummy,		/* Not used. */
    Tcl_Interp *interp,		/* Current interpreter. */
    int objc,			/* Number of arguments. */
    Tcl_Obj *const objv[])	/* Argument objects. */

    /*
     * Nothing matched: return nothing.
     */

    return TCL_OK;
}


/*
 *----------------------------------------------------------------------
 *
 * Tcl_CatchObjCmd --
 *
 *	This object-based procedure is invoked to process the "catch" Tcl

    if (Tcl_GetIndexFromObj(interp, objv[1], optionStrings, "option", 0,
	    &index) != TCL_OK) {
	return TCL_ERROR;
    }

    switch ((enum options) index) {
    case ENC_CONVERTTO:

    case ENC_CONVERTFROM: {
	Tcl_Obj *data;
	Tcl_DString ds;
	Tcl_Encoding encoding;
	int length;
	const char *stringPtr;

	if (objc == 3) {
	    encoding = Tcl_GetEncoding(interp, NULL);
	    data = objv[2];
	} else if (objc == 4) {
	    if (Tcl_GetEncodingFromObj(interp, objv[2], &encoding) != TCL_OK) {
		return TCL_ERROR;
	    }
	    data = objv[3];
	} else {
	    Tcl_WrongNumArgs(interp, 2, objv, "?encoding? data");
	    return TCL_ERROR;
	}

	if ((enum options) index == ENC_CONVERTFROM) {
	    /*
	     * Treat the string as binary data.
	     */

	    stringPtr = (char *) Tcl_GetByteArrayFromObj(data, &length);
	    Tcl_ExternalToUtfDString(encoding, stringPtr, length, &ds);

	    /*
	     * Note that we cannot use Tcl_DStringResult here because it will
	     * truncate the string at the first null byte.
	     */

	    Tcl_SetObjResult(interp, TclDStringToObj(&ds));
	} else {
	    /*
	     * Store the result as binary data.
	     */

	    stringPtr = TclGetStringFromObj(data, &length);
	    Tcl_UtfToExternalDString(encoding, stringPtr, length, &ds);
	    Tcl_SetObjResult(interp, Tcl_NewByteArrayObj(
		    (unsigned char *) Tcl_DStringValue(&ds),
		    Tcl_DStringLength(&ds)));
	    Tcl_DStringFree(&ds);
	}

	Tcl_FreeEncoding(encoding);
	break;
    }
    case ENC_DIRS:
	return EncodingDirsObjCmd(dummy, interp, objc, objv);
    case ENC_NAMES:
	if (objc > 2) {
	    Tcl_WrongNumArgs(interp, 2, objv, NULL);
	    return TCL_ERROR;
	}
	Tcl_GetEncodingNames(interp);
	break;
    case ENC_SYSTEM:











































































































































































	if (objc > 3) {








	    Tcl_WrongNumArgs(interp, 2, objv, "?encoding?");



























































	    return TCL_ERROR;
	}
	if (objc == 2) {
	    Tcl_SetObjResult(interp, Tcl_NewStringObj(
		    Tcl_GetEncodingName(NULL), -1));
	} else {



	    return Tcl_SetSystemEncoding(interp, TclGetString(objv[2]));



	}






	break;



    }

    return TCL_OK;

}

/*
 *----------------------------------------------------------------------
 *
 * EncodingDirsObjCmd --
 *