File: bibclean.html

package info (click to toggle)
bibclean 2.11.4-6
links: PTS
area: main
in suites: etch, etch-m68k, lenny
size: 5,212 kB
ctags: 1,545
sloc: ansic: 10,737; makefile: 817; perl: 66; sh: 40; awk: 27; sed: 6
file content (1682 lines) | stat: -rw-r--r-- 71,011 bytes
parent folder | download | duplicates (5)
<!-- -*-html-*- -->
<!-- /u/sy/beebe/tex/bibclean/2-11-4/bibclean.html -->
<!-- Prettyprinted by html-pretty flex version 1.00 [04-Dec-1997] -->
<!-- on Fri Feb  5 09:04:50 1999 -->
<!-- for Nelson H. F. Beebe (beebe@plot79.math.utah.edu) -->

<!-- Warning: Do NOT edit this file. -->
<!-- It was created automatically by man2html.awk Version 1.06 [24-Oct-1997] on Fri Feb  5 09:04:50 MST 1999 -->
<!-- from the file  at plot79.math.utah.edu -->

<!DOCTYPE HTML public "-//IETF//DTD HTML//EN">
<!-- ===================================================================== -->
<!--   @Troff-man-file{ -->
<!--      author          = "Nelson H. F. Beebe", -->
<!--      version         = "2.11.4", -->
<!--      date            = "09 May 1998", -->
<!--      time            = "23:28:54 MDT", -->
<!--      filename        = "bibclean.man", -->
<!--      address         = "Center for Scientific Computing -->
<!--                         University of Utah -->
<!--                         Department of Mathematics, 322 INSCC -->
<!--                         155 S 1400 E RM 233 -->
<!--                         Salt Lake City, UT 84112-0090 -->
<!--                         USA -->
<!--      telephone       = "+1 801 581 5254", -->
<!--      FAX             = "+1 801 585 1640, +1 801 581 4148", -->
<!--      URL             = "http://www.math.utah.edu/~beebe", -->
<!--      checksum        = "23507 1682 6839 71011", -->
<!--      email           = "beebe@math.utah.edu, beebe@acm.org, -->
<!--                         beebe@ieee.org  (Internet)", -->
<!--      codetable       = "ISO/ASCII", -->
<!--      keywords        = "bibliography, BibTeX, prettyprint", -->
<!--      supported       = "yes", -->
<!--      docstring       = "This file is the UNIX nroff/troff manual page -->
<!--                         documentation for bibclean, a prettyprinter -->
<!--                         and syntax checker for BibTeX bibliography -->
<!--                         data base files. -->
<!--  -->
<!--                         The checksum field above contains a CRC-16 -->
<!--                         checksum as the first value, followed by the -->
<!--                         equivalent of the standard UNIX wc (word -->
<!--                         count) utility output of lines, words, and -->
<!--                         characters.  This is produced by Robert -->
<!--                         Solovay's checksum utility.", -->
<!--   } -->
<!-- ===================================================================== -->
<!--  -->
<!-- .if t .ds Bi B\s-2IB\s+2T\h'-0.1667m'\v'0.20v'E\v'-0.20v'\h'-0.125m'X -->
<!--  -->
<!-- .if t .ds Sc S\s-2CRIBE\s+2 -->
<!--  -->
<!-- .if t .ds Te T\h'-0.1667m'\v'0.20v'E\v'-0.20v'\h'-0.125m'X -->
<!--  -->
<!-- ===================================================================== -->

<HTML>
    <HEAD>
        <TITLE>
            BIBCLEAN 1 &quot;09 May 1998&quot; &quot;Version 2.11.4
            &quot;
        </TITLE>
        <LINK REV="made" HREF="mailto:beebe@plot79.math.utah.edu">
    </HEAD>
    <BODY>
        <P>
            <!-- ===================================================================== -->
        </P>
        <H1>
            Table of contents
        </H1>
        <UL>
            <LI>
                <A HREF="#HDR.1">
                    NAME
                </A>
            </LI>
            <LI>
                <A HREF="#HDR.2">
                    SYNOPSIS
                </A>
            </LI>
            <LI>
                <A HREF="#HDR.3">
                    DESCRIPTION
                </A>
            </LI>
            <LI>
                <A HREF="#HDR.4">
                    OPTIONS
                </A>
            </LI>
            <LI>
                <A HREF="#HDR.5">
                    ERROR RECOVERY AND WARNINGS
                </A>
            </LI>
            <LI>
                <A HREF="#HDR.6">
                    INITIALIZATION FILES
                </A>
            </LI>
            <LI>
                <A HREF="#HDR.7">
                    LEXICAL ANALYSIS
                </A>
            </LI>
            <LI>
                <A HREF="#HDR.8">
                    SCRIBE BIBLIOGRAPHY FORMAT
                </A>
            </LI>
            <LI>
                <A HREF="#HDR.9">
                    ENVIRONMENT VARIABLES
                </A>
            </LI>
            <LI>
                <A HREF="#HDR.10">
                    FILES
                </A>
            </LI>
            <LI>
                <A HREF="#HDR.11">
                    SEE ALSO
                </A>
            </LI>
            <LI>
                <A HREF="#HDR.12">
                    AUTHOR
                </A>
            </LI>
        </UL>
        <HR>
        <H1>
            <A NAME="HDR.1">
                NAME
            </A>
        </H1>
        <P>
            bibclean - prettyprint and syntax check BibTeX and Scribe
            bibliography data base files
<!-- ===================================================================== -->
        </P>
        <HR>
        <H1>
            <A NAME="HDR.2">
                SYNOPSIS
            </A>
        </H1>
        <P>
            <STRONG>bibclean</STRONG> [ <STRONG>-author</STRONG> ] [
            <STRONG>-error-log</STRONG> <EM> filename</EM> ] [ <STRONG>
            -help</STRONG> ] <!-- .if n .ti +9n -->
            [ <STRONG>'-?'</STRONG> ] [ <STRONG>-init-file</STRONG> <EM>
            filename</EM> ] <!-- .if t .ti +.5i -->
            [ <STRONG>-max-width</STRONG> <EM> nnn</EM> ]
<!-- .if n .ti +9n -->
            [ <STRONG>-[no-]align-equals</STRONG> ] [ <STRONG>
            -[no-]check-values</STRONG> ] <!-- .if n .ti +9n -->
            [ <STRONG>-[no-]delete-empty-values</STRONG> ]
<!-- .if n .ti +9n -->
            <!-- .if t .ti +.5i -->
            [ <STRONG>-[no-]file-position</STRONG> ] [ <STRONG>
            -[no-]fix-font-changes</STRONG> ] <!-- .if n .ti +9n -->
            [ <STRONG>-[no-]fix-initials</STRONG> ] [ <STRONG>
            -[no-]fix-names</STRONG> ] <!-- .if n .ti +9n -->
            <!-- .if t .ti +.5i -->
            [ <STRONG>-[no-]German-style</STRONG> ] [ <STRONG>
            -[no-]keep-linebreaks</STRONG> ] <!-- .if n .ti +9n -->
            [ <STRONG>-[no-]keep-parbreaks</STRONG> ]
<!-- .if n .ti +9n -->
            <!-- .if t .ti +.5i -->
            [ <STRONG>-[no-]keep-preamble-spaces</STRONG> ]
<!-- .if n .ti +9n -->
            [ <STRONG>-[no-]keep-spaces</STRONG> ] [ <STRONG>
            -[no-]keep-string-spaces</STRONG> ] <!-- .if n .ti +9n -->
            <!-- .if t .ti +.5i -->
            [ <STRONG>-[no-]parbreaks</STRONG> ] [ <STRONG>
            -[no-]prettyprint</STRONG> ] <!-- .if n .ti +9n -->
            [ <STRONG>-[no-]print-patterns</STRONG> ]
<!-- .if t .ti +.5i -->
            [ <STRONG>-[no-]read-init-files</STRONG> ]
<!-- .if n .ti +9n -->
            [ <STRONG>-[no-]remove-OPT-prefixes</STRONG> ] [ <STRONG>
            -[no-]scribe</STRONG> ] <!-- .if n .ti +9n -->
            <!-- .if t .ti +.5i -->
            [ <STRONG>-[no-]trace-file-opening</STRONG> ] [ <STRONG>
            -[no-]warnings</STRONG> ] <!-- .if n .ti +9n -->
            [ <STRONG>-version</STRONG> ] <!-- .if n .ti +9n -->
            <!-- .if t .ti +.5i -->
            <EM>&lt;infile</EM> or <EM> bibfile1 bibfile2 bibfile3 ...
            </EM> <!-- .if n .ti +9n -->
            <!-- .if t .ti +.5i -->
            <EM>&gt;outfile</EM>
        </P>
        <P>
            All options can be abbreviated to a unique leading prefix.
        </P>
        <P>
            An explicit file name of ``-'' represents standard input; it
            is assumed if no input files are specified.
        </P>
        <P>
            On VAX VMS and IBM PC DOS, the leading ``-'' on option names
            may be replaced by a slash, ``/''; however, the ``-'' option
            prefix is always recognized.
<!-- ===================================================================== -->
        </P>
        <HR>
        <H1>
            <A NAME="HDR.3">
                DESCRIPTION
            </A>
        </H1>
        <P>
            <STRONG>bibclean</STRONG> prettyprints input BibTeX files to
            <EM>stdout</EM>, and checks the brace balance and
            bibliography entry syntax as well.  It can be used to detect
            problems in BibTeX files that sometimes confuse even BibTeX
            itself, and importantly, can be used to normalize the
            appearance of collections of BibTeX files.
        </P>
        <P>
            Here is a summary of the formatting actions:
        </P>
        <UL>
            <LI>
                BibTeX items are formatted into a consistent structure
                with one <EM>field = &quot;value&quot;</EM> pair per
                line, and the initial @ and trailing right brace in
                column 1.
            </LI>
            <LI>
                Tabs are expanded into blank strings; their use is
                discouraged because they inhibit portability, and can
                suffer corruption in electronic mail.
            </LI>
            <LI>
                Long string values are split at a blank and continued
                onto the next line with leading indentation.
            </LI>
            <LI>
                A single blank line separates adjacent bibliography
                entries.
            </LI>
            <LI>
                Text outside BibTeX entries is passed through verbatim.
            </LI>
            <LI>
                Outer parentheses around entries are converted to
                braces.
            </LI>
            <LI>
                Personal names in <EM>author</EM> and <EM>editor</EM>
                field values are normalized to the form ``P.  D. Q.
                Bach'', from ``P.D.Q.  Bach'' and ``Bach, P.D.Q.''.
            </LI>
            <LI>
                Hyphen sequences in page numbers are converted to
                en-dashes.
            </LI>
            <LI>
                Month values are converted to standard BibTeX string
                abbreviations.
            </LI>
            <LI>
                In titles, sequences of upper-case characters at brace
                level zero are braced to protect them from being
                converted to lower-case letters by some bibliography
                styles.
            </LI>
            <LI>
                CODEN, ISBN (International Standard Book Number) and
                ISSN (International Standard Serial Number) entry values
                are examined to verify the checksums of each listed
                number, and correct ISBN hyphenation is automatically
                supplied.
            </LI>
        </UL>
        The standardized format of the output of <STRONG>bibclean
        </STRONG> facilitates the later application of simple filters,
        such as <STRONG>bibcheck</STRONG> (1), <STRONG>bibdup</STRONG>
        (1), <STRONG>bibextract</STRONG> (1), <STRONG>bibindex</STRONG>
        (1), <STRONG>bibjoin</STRONG> (1), <STRONG>biblabel</STRONG>
        (1), <STRONG>biblook</STRONG> (1), <STRONG>biborder</STRONG>
        (1), <STRONG>bibsort</STRONG> (1), <STRONG>citefind</STRONG>
        (1), and <STRONG>citetags</STRONG> (1), to process the text, and
        also is the one expected by the GNU Emacs BibTeX support
        functions.
<!-- ===================================================================== -->
        <HR>
        <H1>
            <A NAME="HDR.4">
                OPTIONS
            </A>
        </H1>
        <P>
            Command-line switches may be abbreviated to a unique leading
            prefix, and letter case is <EM>not</EM> significant.  All
            options are parsed before any input bibliography files are
            read, no matter what their order on the command line.
            Options that correspond to a yes/no setting of a flag have a
            form with a prefix &quot;no-&quot; to set the flag to <EM>no
            </EM>. For such options, the last setting determines the
            flag value used.  This is significant when options are also
            specified in initialization files (see the <STRONG>
            INITIALIZATION FILES</STRONG> manual section).
        </P>
        <P>
            The leading hyphen that distinguishes an option from a
            filename may be doubled, for compatibility with GNU and
            POSIX conventions.  Thus, <STRONG>-author</STRONG> and
            <STRONG>--author</STRONG> are equivalent.
        </P>
        <P>
            To avoid confusion with options, if a filename begins with a
            hyphen, it must be disguised by a leading absolute or
            relative directory path, e.g., <EM>/tmp/-foo.bib</EM> or
            <EM>./-foo.bib</EM>.
<!-- ______________________________________________- -->
        </P>
        <DL>
            <DT>
                <STRONG>-author</STRONG>
            </DT>
            <DD>
                Display an author credit on the standard error unit,
                <EM>stderr</EM>, and then exit with a success return
                code. Sometimes an executable program is separated from
                its documentation and source code; this option provides
                a way to recover from that.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-error-log</STRONG> <EM> filename</EM>
            </DT>
            <DD>
                Redirect <EM>stderr</EM> to the indicated file, which
                will then contain all of the error and warning messages.
                This option is provided for those systems that have
                difficulty redirecting <EM>stderr</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-help</STRONG> or <STRONG>-?</STRONG>
            </DT>
            <DD>
                Display a help message on <EM>stderr</EM>, giving a
                usage description, similar to this section of the manual
                pages, and then exit with a success return code.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-init-file</STRONG> <EM> filename</EM>
            </DT>
            <DD>
                Provide an explicit value pattern initialization file.
                It will be processed <EM>after</EM> any system-wide and
                job-wide initialization files found on the <STRONG>PATH
                </STRONG> (for VAX VMS, <STRONG>SYS$SYSTEM</STRONG> )
                and <STRONG>BIBINPUTS</STRONG> search paths,
                respectively, and may override them. It in turn may be
                overridden by a subsequent file-specific initialization
                file.  The initialization file name can be changed at
                compile time, or at run time through a setting of the
                environment variable <STRONG>BIBCLEANINI</STRONG>, but
                defaults to <EM>.bibcleanrc</EM> on UNIX, and to <EM>
                bibclean.ini</EM> elsewhere. For further details, see
                the <STRONG>INITIALIZATION FILES</STRONG> manual
                section.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-max-width</STRONG> <EM> nnn</EM>
            </DT>
            <DD>
                <STRONG>bibclean</STRONG> normally limits output line
                widths to 72 characters, and in the interests of
                consistency, that value should not be changed.
                Occasionally, special-purpose applications may require
                different maximum line widths, so this option provides
                that capability.  The number following the option name
                can be specified in decimal, octal (starting with 0), or
                hexadecimal (starting with 0x). A zero or negative value
                is interpreted to mean unlimited, so <STRONG>-max-width
                </STRONG> <EM> 0</EM> can be used to ensure that each
                field/value pair appears on a single line.
                <P>
                    When <STRONG>-no-prettyprint</STRONG> requests
                    <STRONG>bibclean</STRONG> to act as a lexical
                    analyzer, the default line width is unlimited,
                    unless overridden by this option.
                </P>
                <P>
                    When <STRONG>bibclean</STRONG> is prettyprinting,
                    line wrapping will be done only at a space.
                    Consequently, a long non-blank character sequence
                    may result in the output exceeding the requested
                    line width.
                </P>
                <P>
                    When <STRONG>bibclean</STRONG> is lexing, line
                    wrapping is done by inserting a backslash-newline
                    pair when the specified maximum is reached, so no
                    line length will ever exceed the maximum.
<!-- ______________________________________________- -->
                </P>
            </DD>
            <DT>
                <STRONG>-[no-]align-equals</STRONG>
            </DT>
            <DD>
                With the positive form, align the equals sign in
                key/value assignments at the same column, separated by a
                single space from the value string. Otherwise, the
                equals sign follows the key, separated by a single
                space. Default: <EM>no</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]check-values</STRONG>
            </DT>
            <DD>
                With the positive form, apply heuristic pattern matching
                to field values in order to detect possible errors
                (e.g., `` <EM>year = &quot;192&quot;</EM> '' instead of
                `` <EM>year = &quot;1992&quot;</EM> ''), and issue
                warnings when unexpected patterns are found.
                <P>
                    This checking is usually beneficial, but if it
                    produces too many bogus warnings for a particular
                    bibliography file, you can disable it with the
                    negative form of this option. Default: <EM>yes</EM>.
                    <!-- ______________________________________________- -->
                </P>
            </DD>
            <DT>
                <STRONG>-[no-]delete-empty-values</STRONG>
            </DT>
            <DD>
                With the positive form, remove all field/value pairs for
                which the value is an empty string.  This is helpful in
                cleaning up bibliographies generated from text editor
                templates.  Compare this option with <STRONG>
                -[no-]remove-OPT-prefixes</STRONG> described below.
                Default: <EM>no</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]file-position</STRONG>
            </DT>
            <DD>
                With the positive form, give detailed file position
                information in warning and error messages. Default: <EM>
                no</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]fix-font-changes</STRONG>
            </DT>
            <DD>
                With the positive form, supply an additional brace level
                around font changes in titles to protect against
                downcasing by some BibTeX styles.  Font changes that
                already have more than one level of braces are not
                modified.
                <P>
                    For example, if a title contains the Latin phrase
                    <EM>{\em Dictyostelium Discoideum}</EM> or <EM>{\em
                    {D}ictyostelium {D}iscoideum}</EM>, then downcasing
                    will incorrectly convert the phrase to lower-case
                    letters.  Most BibTeX users are surprised that
                    bracing the initial letters does not prevent the
                    downcase action.  The correct coding is <EM>{{\em
                    Dictyostelium Discoideum}}</EM>. However, there are
                    also legitimate cases where an extra level of
                    bracing wrongly protects from downcasing.
                    Consequently, <STRONG>bibclean</STRONG> will
                    normally <EM>not</EM> supply an extra level of
                    braces, but if you have a bibliography where the
                    extra braces are routinely missing, you can use this
                    option to supply them.
                </P>
                <P>
                    If you think that you need this option, it is <EM>
                    strongly</EM> recommended that you apply <STRONG>
                    bibclean</STRONG> to your bibliography file with and
                    without <STRONG>-fix-font-changes</STRONG>, then
                    compare the two output files to ensure that extra
                    braces are not being supplied in titles where they
                    should not be present.  You will have to decide
                    which of the two output files is the better choice,
                    then repair the incorrect title bracing by hand.
                </P>
                <P>
                    Since font changes in titles are uncommon, except
                    for cases of the type which this option is designed
                    to correct, it should do more good than harm.
                    Default: <EM>no</EM>.
<!-- ______________________________________________- -->
                </P>
            </DD>
            <DT>
                <STRONG>-[no-]fix-initials</STRONG>
            </DT>
            <DD>
                With the positive form, insert a space after a period
                following author initials. Default: <EM>yes</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]fix-names</STRONG>
            </DT>
            <DD>
                With the positive form, reorder <EM>author</EM> and <EM>
                editor</EM> name lists to remove commas at brace level
                zero, placing first names or initials before last names.
                Default: <EM>yes</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]German-style</STRONG>
            </DT>
            <DD>
                With the positive form, interpret quote characters [
                &quot;] inside <EM>braced</EM> value strings at brace
                level 1 according to the conventions of the TeX style
                file <EM>german.sty</EM>, which overloads quote to
                simplify input and representation of German umlaut
                accents, sharp-s (es-zet), ligature separators,
                invisible hyphens, raised/lowered quotes, French
                guillemets, and discretionary hyphens.  Recognized
                character combinations will be braced to prevent BibTeX
                from interpreting the quote as a string delimiter.
                <P>
                    Quoted strings receive no special handling from this
                    option, and since German nouns in titles must anyway
                    be protected from the downcasing operation of most
                    BibTeX bibliography styles, German value strings
                    that use the overloaded quote character can always
                    be entered in the form &quot;{...}&quot;, without
                    the need to specify this option at all.
                </P>
                <P>
                    Default: <EM>no</EM>.
<!-- ______________________________________________- -->
                </P>
            </DD>
            <DT>
                <STRONG>-[no-]keep-linebreaks</STRONG>
            </DT>
            <DD>
                Normally, line breaks inside value strings are collapsed
                into a single space, so that long value strings can
                later be broken to provide lines of reasonable length.
                <P>
                    With the positive form, linebreaks are preserved in
                    value strings.  If <STRONG>-max-width</STRONG> is
                    set to zero, this preserves the original line
                    breaks.  Spacing <EM>outside</EM> value strings
                    remains under <STRONG>bibclean</STRONG> 's control,
                    and is not affected by this option.
                </P>
                <P>
                    Default: <EM>no</EM>.
<!-- ______________________________________________- -->
                </P>
            </DD>
            <DT>
                <STRONG>-[no-]keep-parbreaks</STRONG>
            </DT>
            <DD>
                With the positive form, preserve paragraph breaks
                (either formfeeds, or lines containing only spaces) in
                value strings.  Normally, paragraph breaks are collapsed
                into a single space.  Spacing <EM>outside</EM> value
                strings remains under <STRONG>bibclean</STRONG> 's
                control, and is not affected by this option. Default:
                <EM>no</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]keep-preamble-spaces</STRONG>
            </DT>
            <DD>
                With the positive form, preserve all whitespace in
                @Preamble{...} entries. Default: <EM>no</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]keep-spaces</STRONG>
            </DT>
            <DD>
                With the positive form, preserve all spaces in value
                strings.  Normally, multiple spaces are collapsed into a
                single space.  This option can be used together with
                <STRONG>-keep-linebreaks</STRONG>, <STRONG>
                -keep-parbreaks</STRONG>, and <STRONG>-max-width
                </STRONG> <EM> 0</EM> to preserve the form of value
                strings while still providing syntax and value checking.
                Spacing <EM>outside</EM> value strings remains under
                <STRONG>bibclean</STRONG> 's control, and is not
                affected by this option. Default: <EM>no</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]keep-string-spaces</STRONG>
            </DT>
            <DD>
                With the positive form, preserve all whitespace in
                @String{...} entries. Default: <EM>no</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]parbreaks</STRONG>
            </DT>
            <DD>
                With the negative form, a paragraph break (either a
                formfeed, or a line containing only spaces) is not
                permitted in value strings, or between field/value
                pairs.  This may be useful to quickly trap runaway
                strings arising from mismatched delimiters. Default:
                <EM>yes</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]prettyprint</STRONG>
            </DT>
            <DD>
                Normally, <STRONG>bibclean</STRONG> functions as a
                prettyprinter.  However, with the negative form of this
                option, it acts as a lexical analyzer instead, producing
                a stream of lexical tokens.  See the <STRONG>LEXICAL
                ANALYSIS</STRONG> manual section for further details.
                Default: <EM>yes</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]print-patterns</STRONG>
            </DT>
            <DD>
                With the positive form, print the value patterns read
                from initialization files as they are added to internal
                tables.  Use this option to check newly-added patterns,
                or to see what patterns are being used.
                <P>
                    When <STRONG>bibclean</STRONG> is compiled with
                    native pattern-matching code (the default), these
                    patterns are the ones that will be used in checking
                    value strings for valid syntax, and all of them are
                    specified in initialization files, rather than
                    hard-coded into the program. For further details,
                    see the <STRONG>INITIALIZATION FILES</STRONG> manual
                    section. Default: <EM>no</EM>.
<!-- ______________________________________________- -->
                </P>
            </DD>
            <DT>
                <STRONG>-[no-]read-init-files</STRONG>
            </DT>
            <DD>
                With the negative form, suppress loading of system-,
                user-, and file-specific initialization files.
                Initializations will come <EM>only</EM> from those files
                explicitly given by <STRONG>-init-file</STRONG> <EM>
                filename</EM> options. Default: <EM>yes</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]remove-OPT-prefixes</STRONG>
            </DT>
            <DD>
                With the positive form, remove the ``OPT'' prefix from
                each field name where the corresponding value is <EM>not
                </EM> an empty string.  The prefix ``OPT'' must be
                entirely in upper-case to be recognized.
                <P>
                    This option is for bibliographies generated with the
                    help of the GNU Emacs BibTeX editing support, which
                    generates templates with optional fields identified
                    by the ``OPT'' prefix.  Although the function <EM>
                    M-x</EM> normally bound to the keystrokes <EM>C-c
                    </EM> does the job, users often forget, with the
                    result that BibTeX does not recognize the field
                    name, and ignores the value string.  Compare this
                    option with <STRONG>-[no-]delete-empty-values
                    </STRONG> described above. Default: <EM>no</EM>.
<!-- ______________________________________________- -->
                </P>
            </DD>
            <DT>
                <STRONG>-[no-]scribe</STRONG>
            </DT>
            <DD>
                With the positive form, accept input syntax conforming
                to the Scribe document system.  The output will be
                converted to conform to BibTeX syntax.  See the <STRONG>
                SCRIBE BIBLIOGRAPHY FORMAT</STRONG> manual section for
                further details. Default: <EM>no</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]trace-file-opening</STRONG>
            </DT>
            <DD>
                With the positive form, record in the error log file the
                names of all files which <STRONG>bibclean</STRONG>
                attempts to open.  Use this option to identify where
                initialization files are located. Default: <EM>no</EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-[no-]warnings</STRONG>
            </DT>
            <DD>
                With the positive form, allow all warning messages.  The
                negative form is <EM>not</EM> recommended since it may
                mask problems that should be repaired. Default: <EM>yes
                </EM>.
<!-- ______________________________________________- -->
            </DD>
            <DT>
                <STRONG>-version</STRONG>
            </DT>
            <DD>
                Display the program version number on <EM>stderr</EM>,
                and then exit with a success return code. This will also
                include an indication of who compiled the program, the
                host name on which it was compiled, the time of
                compilation, and the type of string-value matching code
                selected, when that information is available to the
                compiler.
<!-- ===================================================================== -->
            </DD>
        </DL>
        <HR>
        <H1>
            <A NAME="HDR.5">
                ERROR RECOVERY AND WARNINGS
            </A>
        </H1>
        <P>
            When <STRONG>bibclean</STRONG> detects an error, it issues
            an error message to both <EM>stderr</EM> and <EM>stdout</EM>
            .
            That way, the user is clearly notified, and the output
            bibliography also contains the message at the point of
            error.
        </P>
        <P>
            Error messages begin with a distinctive pair of queries, ??,
            beginning in column 1, followed by the input file name and
            line number.  If the <STRONG>-file-position</STRONG> option
            was specified, they also contain the input and output
            positions of the current file, entry, and value.  Each
            position includes the file byte number, the line number, and
            the column number. In the event of a runaway string
            argument, the entry and value positions should precisely
            pinpoint the erroneous bibliography entry, and the file
            positions will indicate where it was detected, which may be
            rather later in the files.
        </P>
        <P>
            Warning messages identify possible problems, and are
            therefore sent only to <EM>stderr</EM>, and not to <EM>
            stdout</EM>, so they never appear in the output file.  They
            are identified by a distinctive pair of percents, %%,
            beginning in column 1, and as with error messages, may be
            followed by file position messages if the <STRONG>
            -file-position</STRONG> option was specified.
        </P>
        <P>
            For convenience, the first line of each error and warning
            message sent to <EM>stderr</EM> is formatted according to
            the expectations of the GNU Emacs <EM>next-error</EM>
            command.  You can invoke <STRONG>bibclean</STRONG> with the
            Emacs <EM>M-x compile&lt;RET&gt;bibclean filename.bib &gt;
            filename.new</EM> command, then use the <EM>next-error</EM>
            command, normally bound to <EM>C-x `</EM> (that's a grave,
            or back, accent), to move to the location of the error in
            the input file.
        </P>
        <P>
            If error messages are ignored, and left in the output
            bibliography file, they will precipitate an error when the
            bibliography is next processed with BibTeX.
        </P>
        <P>
            After issuing an error message, <STRONG>bibclean</STRONG>
            then resynchronizes its input by copying it verbatim to <EM>
            stdout</EM> until a new bibliography entry is recognized on
            a line in which the first non-blank character is an at-sign
            (@).  This ensures that nothing is lost from the input
            file(s), allowing corrections to be made in either the input
            or the output files. However, if <STRONG>bibclean</STRONG>
            detects an internal error in its data structures, it will
            terminate abruptly without further input or output
            processing; this kind of error should never happen, and if
            it does, it should be reported immediately to the author of
            the program. Errors in initialization files, and running out
            of dynamic memory, will also immediately terminate <STRONG>
            bibclean</STRONG>.
<!-- ===================================================================== -->
        </P>
        <HR>
        <H1>
            <A NAME="HDR.6">
                INITIALIZATION FILES
            </A>
        </H1>
        <P>
            <STRONG>bibclean</STRONG> can be compiled with one of three
            different types of pattern matching; the choice is made by
            the installer at compile time:
        </P>
        <BLOCKQUOTE>
            <UL>
                <LI>
                    The original version uses explicit hand-coded tests
                    of value-string syntax.
                </LI>
                <LI>
                    The second version uses regular-expression
                    pattern-matching host library routines together with
                    regular-expression patterns that come entirely from
                    initialization files.
                </LI>
                <LI>
                    The third version uses special patterns that come
                    entirely from initialization files.
                </LI>
            </UL>
        </BLOCKQUOTE>
        <P>
            The second and third versions are the ones of most interest
            here, because they allow the user to control what values are
            considered acceptable. However, command-line options can
            also be specified in initialization files, no matter which
            pattern matching choice was selected.
        </P>
        <P>
            When <STRONG>bibclean</STRONG> starts, it searches for
            initialization files, finding the first one in the system
            executable program search path (on UNIX and IBM PC DOS,
            <STRONG>PATH</STRONG> ) and the first one in the <STRONG>
            BIBINPUTS</STRONG> search path, and processes them in turn.
            Then, when command-line arguments are processed, any
            additional files specified by <STRONG>-init-file</STRONG>
            <EM>filename</EM> options are also processed.  Finally,
            immediately before each <EM>named</EM> bibliography file is
            processed, an attempt is made to process an initialization
            file with the same name, but with the extension changed to
            <EM>.ini</EM>. The default extension can be changed by a
            setting of the environment variable <STRONG>BIBCLEANEXT
            </STRONG>. This scheme permits system-wide, user-wide,
            session-wide, and file-specific initialization files to be
            supported.
        </P>
        <P>
            When input is taken from <EM>stdin</EM>, there is no
            file-specific initialization.
        </P>
        <P>
            For precise control, the <STRONG>-no-read-init-files
            </STRONG> option suppresses all initialization files except
            those explicitly named by <STRONG>-init-file</STRONG> <EM>
            filename</EM> options, either on the command line, or in
            requested initialization files.
        </P>
        <P>
            Recursive execution of initialization files with nested
            <STRONG>-init-file</STRONG> options is permitted; if the
            recursion is circular, <STRONG>bibclean</STRONG> will
            finally get a non-fatal initialization file open failure
            after opening too many files.  This terminates further
            initialization file processing. As the recursion unwinds,
            the files are all closed, then execution proceeds normally.
        </P>
        <P>
            An initialization file may contain empty lines, comments
            from percent to end of line (just like TeX), option
            switches, and field/pattern or field/pattern/message
            assignments.  Leading and trailing spaces are ignored.  This
            is best illustrated by a short example:
        </P>
<PRE>
% This is a small bibclean initialization file

-init-file /u/math/bib/.bibcleanrc %% departmental patterns

chapter = &quot;\&quot;D\&quot;&quot;                 %% 23

pages   = &quot;\&quot;D--D\&quot;&quot;              %% 23--27

volume  = &quot;\&quot;D \an\d D\&quot;&quot;       %% 11 and 12

year    = \
   &quot;\&quot;dddd, dddd, dddd\&quot;&quot; \
   &quot;Multiple years specified.&quot;      %% 1989, 1990, 1991

-no-fix-names   %% do not modify author/editor lists
</PRE>
        <P>
            Long logical lines can be split into multiple physical lines
            by breaking at a backslash-newline pair; the
            backslash-newline pair is discarded. This processing happens
            while characters are being read, before any further
            interpretation of the input stream.
        </P>
        <P>
            Each logical line must contain a complete option (and its
            value, if any), or a complete field/pattern pair, or a
            field/pattern/message triple.
        </P>
        <P>
            Comments are stripped during the parsing of the field,
            pattern, and message values.  The comment start symbol is
            not recognized inside quoted strings, so it can be freely
            used in such strings.
        </P>
        <P>
            Comments on logical lines that were input as multiple
            physical lines via the backslash-newline convention must
            appear on the <EM>last</EM> physical line; otherwise, the
            remaining physical lines will become part of the comment.
        </P>
        <P>
            Pattern strings must be enclosed in quotation marks; within
            such strings, a backslash starts an escape mechanism that is
            commonly used in UNIX software.  The recognized escape
            sequences are:
        </P>
        <BLOCKQUOTE>
            <DL>
                <DT>
                    <STRONG>\a</STRONG>
                </DT>
                <DD>
                    alarm bell (octal 007)
                </DD>
                <DT>
                    <STRONG>\b</STRONG>
                </DT>
                <DD>
                    backspace (octal 010)
                </DD>
                <DT>
                    <STRONG>\f</STRONG>
                </DT>
                <DD>
                    formfeed (octal 014)
                </DD>
                <DT>
                    <STRONG>\n</STRONG>
                </DT>
                <DD>
                    newline (octal 012)
                </DD>
                <DT>
                    <STRONG>\r</STRONG>
                </DT>
                <DD>
                    carriage return (octal 015)
                </DD>
                <DT>
                    <STRONG>\t</STRONG>
                </DT>
                <DD>
                    horizontal tab (octal 011)
                </DD>
                <DT>
                    <STRONG>\v</STRONG>
                </DT>
                <DD>
                    vertical tab (octal 013)
                </DD>
                <DT>
                    <STRONG>\ooo</STRONG>
                </DT>
                <DD>
                    character number octal <EM>ooo</EM> (e.g <STRONG>
                    \012</STRONG> is linefeed).  Up to 3 octal digits
                    may be used.
                </DD>
                <DT>
                    <STRONG>\0xhh</STRONG>
                </DT>
                <DD>
                    character number hexadecimal <EM>hh</EM> (e.g.,
                    <STRONG>\0x0a</STRONG> is linefeed). <EM>xhh</EM>
                    may be in either letter case. Any number of
                    hexadecimal digits may be used.
                </DD>
            </DL>
        </BLOCKQUOTE>
        <P>
            Backslash followed by any other character produces just that
            character.  Thus, \% gets a literal percent into a string
            (preventing its interpretation as a comment), \&quot;
            produces a quotation mark, and \ produces a single
            backslash.
        </P>
        <P>
            An ASCII NUL <EM>(\0)</EM> in a string will terminate it;
            this is a feature of the C programming language in which
            <STRONG>bibclean</STRONG> is implemented.
        </P>
        <P>
            Field/pattern pairs can be separated by arbitrary space, and
            optionally, either an equals sign or colon functioning as an
            assignment operator. Thus, the following are equivalent:
        </P>
<PRE>
pages=&quot;\&quot;D--D\&quot;&quot;
pages:&quot;\&quot;D--D\&quot;&quot;
pages &quot;\&quot;D--D\&quot;&quot;
  pages = &quot;\&quot;D--D\&quot;&quot;
  pages : &quot;\&quot;D--D\&quot;&quot;
pages   &quot;\&quot;D--D\&quot;&quot;
</PRE>
        <P>
            Each field name can have an arbitrary number of patterns
            associated with it; however, they must be specified in
            separate field/pattern assignments.
        </P>
        <P>
            An empty pattern string causes previously-loaded patterns
            for that field name to be forgotten.  This feature permits
            an initialization file to completely discard patterns from
            earlier initialization files.
        </P>
        <P>
            Patterns for value strings are represented in a tiny
            special-purpose language that is both convenient and
            suitable for bibliography value-string syntax checking.
            While not as powerful as the language of regular-expression
            patterns, its parsing can be portably implemented in less
            than 3% of the code in a widely-used regular-expression
            parser (the GNU <STRONG>regexp</STRONG> package).
        </P>
        <P>
            The patterns are represented by the following special
            characters:
        </P>
        <BLOCKQUOTE>
            <DL>
                <DT>
                    <STRONG>&lt;space&gt;</STRONG>
                </DT>
                <DD>
                    one or more spaces
                </DD>
                <DT>
                    <STRONG>a</STRONG>
                </DT>
                <DD>
                    exactly one letter
                </DD>
                <DT>
                    <STRONG>A</STRONG>
                </DT>
                <DD>
                    one or more letters
                </DD>
                <DT>
                    <STRONG>d</STRONG>
                </DT>
                <DD>
                    exactly one digit
                </DD>
                <DT>
                    <STRONG>D</STRONG>
                </DT>
                <DD>
                    one or more digits
                </DD>
                <DT>
                    <STRONG>r</STRONG>
                </DT>
                <DD>
                    exactly one Roman numeral
                </DD>
                <DT>
                    <STRONG>R</STRONG>
                </DT>
                <DD>
                    one or more Roman numerals (i.e. a Roman number)
                </DD>
                <DT>
                    <STRONG>w</STRONG>
                </DT>
                <DD>
                    exactly one word (one or more letters and digits)
                </DD>
                <DT>
                    <STRONG>W</STRONG>
                </DT>
                <DD>
                    one or more space-separated words, beginning and
                    ending with a word
                </DD>
                <DT>
                    <STRONG>.</STRONG>
                </DT>
                <DD>
                    one `special' character, one of the characters &lt;
                    space&gt;!#()*+,-./:;?[]~, a subset of punctuation
                    characters that are typically used in string values
                </DD>
                <DT>
                    <STRONG>:</STRONG>
                </DT>
                <DD>
                    one or more `special' characters
                </DD>
                <DT>
                    <STRONG>X</STRONG>
                </DT>
                <DD>
                    one or more `special'-separated words, beginning and
                    ending with a word
                </DD>
                <DT>
                    <STRONG>\x</STRONG>
                </DT>
                <DD>
                    exactly one x (x is any character), possibly with an
                    escape sequence interpretation given earlier
                </DD>
                <DT>
                    <STRONG>x</STRONG>
                </DT>
                <DD>
                    exactly the character x (x is anything but one of
                    these pattern characters: aAdDrRwW.:&lt;space&gt;\)
                </DD>
            </DL>
        </BLOCKQUOTE>
        <P>
            The <STRONG>X</STRONG> pattern character is very powerful,
            but generally inadvisable, since it will match almost
            anything likely to be found in a BibTeX value string. The
            reason for providing pattern matching on the value strings
            is to uncover possible errors, not mask them.
        </P>
        <P>
            There is no provision for specifying ranges or repetitions
            of characters, but this can usually be done with separate
            patterns.  It is a good idea to accompany the pattern with a
            comment showing the kind of thing it is expected to match.
            Here is a portion of an initialization file giving a few of
            the patterns used to match <EM>number</EM> value strings:
        </P>
<PRE>
number  =       &quot;\&quot;D\&quot;&quot;         %% 23
number  =       &quot;\&quot;A AD\&quot;&quot;      %% PN LPS5001
number  =       &quot;\&quot;A D(D)\&quot;&quot;    %% RJ 34(49)
number  =       &quot;\&quot;A D\&quot;&quot;       %% XNSS 288811
number  =       &quot;\&quot;A D\.D\&quot;&quot;   %% Version 3.20
number  =       &quot;\&quot;A-A-D-D\&quot;&quot;   %% UMIAC-TR-89-11
number  =       &quot;\&quot;A-A-D\&quot;&quot;     %% CS-TR-2189
number  =       &quot;\&quot;A-A-D\.D\&quot;&quot; %% CS-TR-21.7
</PRE>
        <P>
            For a bibliography that contains only <EM>article</EM>
            entries, this list should probably be reduced to just the
            first pattern, so that anything other than a digit string
            fails the pattern-match test. This is easily done by keeping
            bibliography-specific patterns in a corresponding file with
            extension <EM>.ini</EM>, since that file is read
            automatically.
        </P>
        <P>
            You should be sure to use empty pattern strings in this
            pattern file to discard patterns from earlier initialization
            files.
        </P>
        <P>
            The value strings passed to the pattern matcher contain
            surrounding quotes, so the patterns should also.  However,
            you could use a pattern specification like &quot;\&quot;D
            &quot; to match an initial digit string followed by anything
            else; the omission of the final quotation mark \&quot; in
            the pattern allows the match to succeed without checking
            that the next character in the value string is a quotation
            mark.
        </P>
        <P>
            Because the value strings are intended to be processed by
            TeX, the pattern matching ignores braces, and TeX control
            sequences, together with any space following those control
            sequences. Spaces around braces are preserved.  This
            convention allows the pattern fragment <EM>A-AD-D</EM> to
            match the value string <EM>TN-K\slash</EM> 27-70 <EM>,</EM>
            because the value is implicitly collapsed to <EM>TN-K27-70
            </EM> during the matching operation.
        </P>
        <P>
            <STRONG>bibclean</STRONG> 's normal action when a string
            value fails to match any of the corresponding patterns is to
            issue a <EM>warning</EM> message something like this: <EM>
            &quot;Unexpected value in ``year = &quot;192&quot;''</EM>.
            In most cases, that is sufficient to alert the user to a
            problem.  In some cases, however, it may be desirable to
            associate a different message with a particular pattern.
            This can be done by supplying a message string following the
            pattern string.  Format items <EM>%%</EM> (single percent),
            <EM>%e</EM> (entry name), <EM>%f</EM> (field name), <EM>%k
            </EM> (citation key), and <EM>%v</EM> (string value) are
            available to get current values expanded in the messages.
            Here is an example:
        </P>
<PRE>
chapter = &quot;\&quot;D:D\&quot;&quot; &quot;Colon found in ``%f = %v''&quot; %% 23:2
</PRE>
        <P>
            To be consistent with other messages output by <STRONG>
            bibclean</STRONG>, the message string should <EM>not</EM>
            end with punctuation.
        </P>
        <P>
            If you wish to make the message an error, rather than just a
            warning, begin it with a query (?), like this:
        </P>
<PRE>
chapter = &quot;\&quot;D:D\&quot;&quot; &quot;?Colon found in ``%f = %v''&quot; %% 23:2
</PRE>
        <P>
            The query will not be included in the output message.
        </P>
        <P>
            Escape sequences are supported in message strings, just as
            they are in pattern strings.  You can use this to advantage
            for fancy things, such as terminal display mode control.  If
            you rewrite the previous example as
        </P>
<PRE>
chapter = &quot;\&quot;D:D\&quot;&quot; \
          &quot;?\033[7mColon found in ``%f = %v''\033[0m&quot; %% 23:2
</PRE>
        <P>
            the error message will appear in inverse video on display
            screens that support ANSI terminal control sequences.  Such
            practice is not normally recommended, since it may have
            undesirable effects on some output devices.  Nevertheless,
            you may find it useful for restricted applications.
        </P>
        <P>
            For some types of bibliography fields, <STRONG>bibclean
            </STRONG> contains special-purpose code to supplement or
            replace the pattern matching:
        </P>
        <BLOCKQUOTE>
            <UL>
                <LI>
                    <EM>CODEN</EM>, <EM>ISBN</EM> and <EM>ISSN</EM>
                    field values are handled this way because their
                    validation requires evaluation of checksums that
                    cannot be expressed by simple patterns; no patterns
                    are even used in these three cases.
                </LI>
                <LI>
                    When <STRONG>bibclean</STRONG> is compiled with
                    pattern-matching code support, <EM>chapter</EM>,
                    <EM>number</EM>, <EM>pages</EM>, and <EM>volume</EM>
                    values are checked only by pattern matching.
                </LI>
                <LI>
                    <EM>month</EM> values are first checked against the
                    standard BibTeX month abbreviations, and only if no
                    match is found are patterns then used.
                </LI>
                <LI>
                    <EM>year</EM> values are first checked against
                    patterns, then if no match is found, the year
                    numbers are found and converted to integer values
                    for testing against reasonable bounds.
                </LI>
            </UL>
        </BLOCKQUOTE>
        <P>
            Values for other fields are checked only against patterns.
            You can provide patterns for <EM>any</EM> field you like,
            even ones <STRONG>bibclean</STRONG> does not already know
            about.  New ones are simply added to an internal table that
            is searched for each string to be validated.
        </P>
        <P>
            The special field, <EM>key</EM>, represents the
            bibliographic citation key.  It can be given patterns, like
            any other field.  Here is an initialization file pattern
            assignment that will match an author name, a colon, an
            alphabetic string, and a two-digit year:
        </P>
<PRE>
key = &quot;A:Add&quot;                     %% Knuth:TB86
</PRE>
        <P>
            Notice that no quotation marks are included in the pattern,
            because the citation keys are not quoted. You can use such
            patterns to help enforce uniform naming conventions for
            citation keys, which is increasingly important as your
            bibliography data base grows.
<!-- ===================================================================== -->
        </P>
        <HR>
        <H1>
            <A NAME="HDR.7">
                LEXICAL ANALYSIS
            </A>
        </H1>
        <P>
            When <STRONG>-no-prettyprint</STRONG> is specified, <STRONG>
            bibclean</STRONG> acts as a lexical analyzer instead of a
            prettyprinter, producing output in lines of the form
        </P>
        <BLOCKQUOTE>
<PRE>
&lt;token-number&gt;&lt;tab&gt;&lt;token-name&gt;&lt;tab&gt;&quot;&lt;token-value&gt;&quot;
</PRE>
        </BLOCKQUOTE>
        <P>
            Each output line contains a single complete token,
            identified by a small integer number for use by a computer
            program, a token type name for human readers, and a string
            value in quotes.
        </P>
        <P>
            Special characters in the token value string are represented
            with ANSI/ISO Standard C escape sequences, so all characters
            other than NUL are representable, and multi-line values can
            be represented in a single line.
        </P>
        <P>
            Here are the token numbers and token type names that can
            appear in the output when <STRONG>-prettyprint</STRONG> is
            specified:
        </P>
        <BLOCKQUOTE>
<PRE>
 0   UNKNOWN
 1   ABBREV
 2   AT
 3   COMMA
 4   COMMENT
 5   ENTRY
 6   EQUALS
 7   FIELD
 8   INCLUDE
 9   INLINE
10   KEY
11   LBRACE
12   LITERAL
13   NEWLINE
14   PREAMBLE
15   RBRACE
16   SHARP
17   SPACE
18   STRING
19   VALUE
</PRE>
        </BLOCKQUOTE>
        <P>
            Programs that parse such output should also be prepared for
            lines beginning with the warning prefix, %%, or the error
            prefix, ??, and for ANSI/ISO Standard C line number
            directives of the form
        </P>
        <BLOCKQUOTE>
            # line 273 &quot;texbook1.bib&quot;
        </BLOCKQUOTE>
        which record the line number and file name of the current input
        file.
        <P>
            If a <STRONG>-max-width</STRONG> <EM> nnn</EM> command-line
            option was specified, long output lines will be wrapped at a
            backslash-newline pair, and consequently, software that
            processes the lexical token stream should be prepared to
            collapse such wrapped lines back into single lines.
        </P>
        <P>
            As an example of the use of <STRONG>-no-prettyprint</STRONG>
            ,
            the UNIX command pipeline
        </P>
        <BLOCKQUOTE>
<PRE>
<STRONG>bibclean -no-prettyprint</STRONG> <EM>mylib.bib</EM> | \
    <STRONG>awk</STRONG> '$2 == &quot;KEY&quot; {print $3}' | \
    <STRONG>sed</STRONG> -e 's/&quot;//g' | \
    <STRONG>sort</STRONG>
</PRE>
        </BLOCKQUOTE>
        will extract a sorted list of all citation keys in the file <EM>
        mylib.bib</EM>.
        <P>
            A certain amount of processing will have been done on the
            tokens.  In particular, delimiters equivalent to braces will
            have been replaced by braces, and braced strings will have
            become quoted strings.
        </P>
        <P>
            The LITERAL token type is used for arbitrary text that
            <STRONG>bibclean</STRONG> does not examine further, such as
            the contents of a @Preamble{...} or a @Comment{...}.
        </P>
        <P>
            The UNKNOWN token type should never appear in the output
            stream.  It is used internally to initialize token type
            variables.
<!-- ===================================================================== -->
        </P>
        <HR>
        <H1>
            <A NAME="HDR.8">
                SCRIBE BIBLIOGRAPHY FORMAT
            </A>
        </H1>
        <P>
            <STRONG>bibclean</STRONG> 's support for the Scribe
            bibliography format is based on the syntax description in
            the Scribe Introductory User's Manual, 3rd Edition, May
            1980. Scribe was originally developed by Brian Reid at
            Carnegie-Mellon University, and is now marketed by Unilogic,
            Ltd.
        </P>
        <P>
            The BibTeX bibliography format was strongly influenced by
            Scribe, and indeed, with care, it is possible to share
            bibliography files between the two systems.  Nevertheless,
            there are some differences, so here is a summary of features
            of the Scribe bibliography file format:
        </P>
        <DL>
            <DT>
                (1)
            </DT>
            <DD>
                Letter case is not significant in field names and entry
                names, but case is preserved in value strings.
            </DD>
            <DT>
                (2)
            </DT>
            <DD>
                In field/value pairs, the field and value may be
                separated by one of three characters:  =, /, or space.
                Space may optionally surround these separators.
            </DD>
            <DT>
                (3)
            </DT>
            <DD>
                Value delimiters are any of these seven pairs:  { } [ ]
                ( ) &lt; &gt; ' ' &quot; &quot; ` `
            </DD>
            <DT>
                (4)
            </DT>
            <DD>
                Value delimiters may not be nested, even though with the
                first four delimiter pairs, nested balanced delimiters
                would be unambiguous.
            </DD>
            <DT>
                (5)
            </DT>
            <DD>
                Delimiters can be omitted around values that contain
                only letters, digits, sharp (#), ampersand (&amp;),
                period (.), and percent (%).
            </DD>
            <DT>
                (6)
            </DT>
            <DD>
                Outside of delimited values, a literal at-sign (@) is
                represented by doubled at-signs (@@).
            </DD>
            <DT>
                (7)
            </DT>
            <DD>
                Bibliography entries begin with @name, as for BibTeX,
                but any of the seven Scribe value delimiter pairs may be
                used to surround the values in field/value pairs.  As in
                (4), nested delimiters are forbidden.
            </DD>
            <DT>
                (8)
            </DT>
            <DD>
                Arbitrary space may separate entry names from the
                following delimiters.
            </DD>
            <DT>
                (9)
            </DT>
            <DD>
                @Comment is a special command whose delimited value is
                discarded.  As in (4), nested delimiters are forbidden.
            </DD>
            <DT>
                (10)
            </DT>
            <DD>
                The special form
<PRE>
@Begin{comment}
 ...
@End{comment}
</PRE>
                <P>
                    permits encapsulating arbitrary text containing any
                    characters or delimiters, other than
                    ``@End{comment}''.  Any of the seven delimiter pairs
                    may be used around the word ``comment'' following
                    the ``@Begin'' or ``@End''; the delimiters in the
                    two cases need not be the same, and consequently,
                    ``@Begin{comment}''/``@End{comment}'' pairs may <EM>
                    not</EM> be nested.
                </P>
            </DD>
            <DT>
                (11)
            </DT>
            <DD>
                The <EM>key</EM> field is required in each bibliography
                entry.
            </DD>
            <DT>
                (12)
            </DT>
            <DD>
                A backslashed quote in a string will be assumed to be a
                TeX accent, and braced appropriately. While such accents
                do not conform to Scribe syntax, Scribe-format
                bibliographies have been found that appear to be
                intended for TeX processing.
            </DD>
        </DL>
        Because of this loose syntax, <STRONG>bibclean</STRONG> 's
        normal error detection heuristics are less effective, and
        consequently, Scribe mode input is not the default; it must be
        explicitly requested.
<!-- ===================================================================== -->
        <HR>
        <H1>
            <A NAME="HDR.9">
                ENVIRONMENT VARIABLES
            </A>
        </H1>
        <DL>
            <DT>
                <STRONG>BIBCLEANEXT</STRONG>
            </DT>
            <DD>
                File extension of bibliography-specific initialization
                files.  Default: <EM>.ini</EM>.
            </DD>
            <DT>
                <STRONG>BIBCLEANINI</STRONG>
            </DT>
            <DD>
                Name of <STRONG>bibclean</STRONG> initialization files.
                Default: <EM>.bibcleanrc</EM> (UNIX), <EM>bibclean.ini
                </EM> (non-UNIX).
            </DD>
            <DT>
                <STRONG>BIBINPUTS</STRONG>
            </DT>
            <DD>
                Search path for <STRONG>bibclean</STRONG> and BibTeX
                input files.  On UNIX, this is a colon-separated list of
                directories that are searched in order from first to
                last.  It is not an error for a specified directory to
                not exist.
                <P>
                    On other operating systems, the directory names
                    should be separated by whatever character is used in
                    system search path specifications, such as a
                    semicolon on IBM PC DOS.
                </P>
            </DD>
            <DT>
                <STRONG>PATH</STRONG>
            </DT>
            <DD>
                On Atari TOS, IBM PC DOS, IBM PC OS/2, Microsoft NT, and
                UNIX, search path for system executable files.  The
                system-wide <STRONG>bibclean</STRONG> initialization
                file is searched for in this path.
            </DD>
            <DT>
                <STRONG>SYS$SYSTEM</STRONG>
            </DT>
            <DD>
                On VAX VMS, search path for system executable files and
                the system-wide <STRONG>bibclean</STRONG> initialization
                file.
<!-- ===================================================================== -->
            </DD>
        </DL>
        <HR>
        <H1>
            <A NAME="HDR.10">
                FILES
            </A>
        </H1>
        <DL>
            <DT>
                <EM>*.bib</EM>
            </DT>
            <DD>
                BibTeX and Scribe bibliography data base files.
            </DD>
            <DT>
                <EM>*.ini</EM>
            </DT>
            <DD>
                File-specific initialization files.
            </DD>
            <DT>
                <EM>.bibcleanrc</EM>
            </DT>
            <DD>
                UNIX system-wide and user-specific initialization files.
            </DD>
            <DT>
                <EM>bibclean.ini</EM>
            </DT>
            <DD>
                Non-UNIX system-wide and user-specific initialization
                files.
<!-- ===================================================================== -->
            </DD>
        </DL>
        <HR>
        <H1>
            <A NAME="HDR.11">
                SEE ALSO
            </A>
        </H1>
        <P>
            <STRONG>bibcheck</STRONG> (1), <STRONG>bibdup</STRONG> (1),
            <STRONG>bibextract</STRONG> (1), <STRONG>bibindex</STRONG>
            (1), <STRONG>bibjoin</STRONG> (1), <STRONG>biblabel</STRONG>
            (1), <STRONG>biblex</STRONG> (1), <STRONG>biblook</STRONG>
            (1), <STRONG>biborder</STRONG> (1), <STRONG>bibparse
            </STRONG> (1), <STRONG>bibsort</STRONG> (1), <STRONG>bibtex
            </STRONG> (1), <STRONG>bibunlex</STRONG> (1), <STRONG>
            citefind</STRONG> (1), <STRONG>citesub</STRONG> (1),
            <STRONG>citetags</STRONG> (1), <STRONG>latex</STRONG> (1),
            <STRONG>scribe</STRONG> (1), <STRONG>tex</STRONG> (1).
<!-- ===================================================================== -->
        </P>
        <HR>
        <H1>
            <A NAME="HDR.12">
                AUTHOR
            </A>
        </H1>
<PRE>
Nelson H. F. Beebe
Center for Scientific Computing
University of Utah
Department of Mathematics, 322 INSCC
155 S 1400 E RM 233
Salt Lake City, UT 84112-0090
USA
Tel: +1 801 581 5254
FAX: +1 801 585 1640, +1 801 581 4148
Email: <A HREF="mailto:beebe@math.utah.edu">beebe@math.utah.edu</A>, <A HREF="mailto:beebe@acm.org">beebe@acm.org</A>, <A HREF="mailto:beebe@ieee.org">beebe@ieee.org</A> (Internet)
URL: <A HREF="http://www.math.utah.edu/~beebe">http://www.math.utah.edu/~beebe</A>
</PRE>
        <!-- ===================================================================== -->
        <!--  This is for GNU Emacs file-specific customization: -->
        <!--  Local Variables: -->
        <!--  fill-column: 50 -->
        <!--  End: -->
    </BODY>
</HTML>