Adwaith-Rajesh/gperf
1
0
Fork 0
mirror of https://git.savannah.gnu.org/git/gperf.git synced 2025-12-02 13:09:22 +00:00
Code Activity

Updates from May 1998:

Browse Source 
- Improved documentation.
- Don't install gperf.dvi.
This commit is contained in:
Bruno Haible
2000-08-19 17:01:39 +00:00
parent 0c0e0ddbb4
commit f7640371df
3 changed files with 270 additions and 186 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
ChangeLog
View File

@@ -91,6 +91,28 @@
* doc/Makefile.in (MAKEINFO): Unset LANG while running makeinfo. * doc/Makefile.in (MAKEINFO): Unset LANG while running makeinfo.
1998-05-20 Bruno Haible <bruno@linuix.mathematik.uni-karlsruhe.de>
* doc/Makefile.in (gperf.dvi, clean): Remove gperf.cps.
(install, installdirs, uninstall): Don't install gperf.dvi. The
info and HTML documentations are sufficient for on-line use, and
users who wish to print the documentation (in PS or DVI format)
can do this directly off the source distribution.
(DVIPS): Use "-D600" instead of "-Pljfour", for portability.
1998-05-20 Akim Demaille <demaille@inf.enst.fr>
* doc/gperf.texi: Many modifications:
(Output Format): Declare `hash' and `in_word_set' as functions.
(Concept Index): New section.
(Title page): Use standard presentation.
(Top): Use @top instead of @unnumbered so that automatic master
update works.
(Motivation): Avoid spaces in @var.
(Options): Use the standard name ``Invoking ...''.
(Options): Declare also the long form of the options.
(Options): Remove redundant @itemize when @table is used.
1998-05-08 Andreas Schwab <schwab@issan.informatik.uni-dortmund.de> 1998-05-08 Andreas Schwab <schwab@issan.informatik.uni-dortmund.de>
* aclocal.m4 (CL_PROG_INSTALL): Set cl_cv_path_install, not * aclocal.m4 (CL_PROG_INSTALL): Set cl_cv_path_install, not

21
doc/Makefile.in
View File

@@ -33,6 +33,7 @@ mandir = @mandir@
man1dir = $(mandir)/man1 man1dir = $(mandir)/man1
docdir = $(datadir)/doc/@PACKAGE@ docdir = $(datadir)/doc/@PACKAGE@
dvidir = $(docdir) dvidir = $(docdir)
psdir = $(docdir)
htmldir = $(docdir) htmldir = $(docdir)
# Programs used by "make": # Programs used by "make":
@@ -42,7 +43,7 @@ RM = rm -f
# Programs used by "make" if you have changed the documentation files: # Programs used by "make" if you have changed the documentation files:
TEX = tex TEX = tex
TEXI2DVI = texi2dvi TEXI2DVI = texi2dvi
DVIPS = dvips -Pljfour DVIPS = dvips -D600
MAKEINFO = LANG= LANGUAGE= makeinfo MAKEINFO = LANG= LANGUAGE= makeinfo
TEXI2HTML = texi2html TEXI2HTML = texi2html
@@ -69,9 +70,9 @@ $(srcdir)/gperf.info : $(srcdir)/gperf.texi $(srcdir)/gpl.texinfo
dvi : $(srcdir)/gperf.dvi dvi : $(srcdir)/gperf.dvi
$(srcdir)/gperf.dvi : $(srcdir)/gperf.texi $(srcdir)/gpl.texinfo $(srcdir)/gperf.dvi : $(srcdir)/gperf.texi $(srcdir)/gpl.texinfo
cd $(srcdir) && $(RM) gperf.aux gperf.toc gperf.cp gperf.fn gperf.ky gperf.pg gperf.tp gperf.vr gperf.log cd $(srcdir) && $(RM) gperf.aux gperf.toc gperf.cp gperf.fn gperf.ky gperf.pg gperf.tp gperf.vr gperf.log gperf.cps
cd $(srcdir) && $(TEXI2DVI) gperf.texi cd $(srcdir) && $(TEXI2DVI) gperf.texi
cd $(srcdir) && $(RM) gperf.aux gperf.toc gperf.cp gperf.fn gperf.ky gperf.pg gperf.tp gperf.vr gperf.log cd $(srcdir) && $(RM) gperf.aux gperf.toc gperf.cp gperf.fn gperf.ky gperf.pg gperf.tp gperf.vr gperf.log gperf.cps
ps : $(srcdir)/gperf.ps ps : $(srcdir)/gperf.ps
@@ -98,8 +99,10 @@ install : all force
$(INSTALL_DATA) $(srcdir)/gperf.1 $(DESTDIR)$(man1dir)/gperf.1 $(INSTALL_DATA) $(srcdir)/gperf.1 $(DESTDIR)$(man1dir)/gperf.1
if [ ! -d $(DESTDIR)$(datadir)/doc ] ; then mkdir $(DESTDIR)$(datadir)/doc ; fi if [ ! -d $(DESTDIR)$(datadir)/doc ] ; then mkdir $(DESTDIR)$(datadir)/doc ; fi
if [ ! -d $(DESTDIR)$(docdir) ] ; then mkdir $(DESTDIR)$(docdir) ; fi if [ ! -d $(DESTDIR)$(docdir) ] ; then mkdir $(DESTDIR)$(docdir) ; fi
if [ ! -d $(DESTDIR)$(dvidir) ] ; then mkdir $(DESTDIR)$(dvidir) ; fi # if [ ! -d $(DESTDIR)$(dvidir) ] ; then mkdir $(DESTDIR)$(dvidir) ; fi
$(INSTALL_DATA) $(srcdir)/gperf.dvi $(DESTDIR)$(dvidir)/gperf.dvi # $(INSTALL_DATA) $(srcdir)/gperf.dvi $(DESTDIR)$(dvidir)/gperf.dvi
# if [ ! -d $(DESTDIR)$(psdir) ] ; then mkdir $(DESTDIR)$(psdir) ; fi
# $(INSTALL_DATA) $(srcdir)/gperf.ps $(DESTDIR)$(dvidir)/gperf.ps
if [ ! -d $(DESTDIR)$(htmldir) ] ; then mkdir $(DESTDIR)$(htmldir) ; fi if [ ! -d $(DESTDIR)$(htmldir) ] ; then mkdir $(DESTDIR)$(htmldir) ; fi
$(INSTALL_DATA) $(srcdir)/gperf.html $(DESTDIR)$(htmldir)/gperf.html $(INSTALL_DATA) $(srcdir)/gperf.html $(DESTDIR)$(htmldir)/gperf.html
@@ -109,13 +112,15 @@ installdirs : force
if [ ! -d $(DESTDIR)$(man1dir) ] ; then mkdir $(DESTDIR)$(man1dir) ; fi if [ ! -d $(DESTDIR)$(man1dir) ] ; then mkdir $(DESTDIR)$(man1dir) ; fi
if [ ! -d $(DESTDIR)$(datadir)/doc ] ; then mkdir $(DESTDIR)$(datadir)/doc ; fi if [ ! -d $(DESTDIR)$(datadir)/doc ] ; then mkdir $(DESTDIR)$(datadir)/doc ; fi
if [ ! -d $(DESTDIR)$(docdir) ] ; then mkdir $(DESTDIR)$(docdir) ; fi if [ ! -d $(DESTDIR)$(docdir) ] ; then mkdir $(DESTDIR)$(docdir) ; fi
if [ ! -d $(DESTDIR)$(dvidir) ] ; then mkdir $(DESTDIR)$(dvidir) ; fi # if [ ! -d $(DESTDIR)$(dvidir) ] ; then mkdir $(DESTDIR)$(dvidir) ; fi
# if [ ! -d $(DESTDIR)$(psdir) ] ; then mkdir $(DESTDIR)$(psdir) ; fi
if [ ! -d $(DESTDIR)$(htmldir) ] ; then mkdir $(DESTDIR)$(htmldir) ; fi if [ ! -d $(DESTDIR)$(htmldir) ] ; then mkdir $(DESTDIR)$(htmldir) ; fi
uninstall : force uninstall : force
$(RM) $(DESTDIR)$(infodir)/gperf.info $(RM) $(DESTDIR)$(infodir)/gperf.info
$(RM) $(DESTDIR)$(man1dir)/gperf.1 $(RM) $(DESTDIR)$(man1dir)/gperf.1
$(RM) $(DESTDIR)$(dvidir)/gperf.dvi # $(RM) $(DESTDIR)$(dvidir)/gperf.dvi
# $(RM) $(DESTDIR)$(psdir)/gperf.ps
$(RM) $(DESTDIR)$(htmldir)/gperf.html $(RM) $(DESTDIR)$(htmldir)/gperf.html
check : all check : all
@@ -123,7 +128,7 @@ check : all
mostlyclean : clean mostlyclean : clean
clean : force clean : force
$(RM) *~ *.aux *.toc *.cp *.fn *.ky *.pg *.tp *.vr *.my *.log core $(RM) *~ *.aux *.toc *.cp *.fn *.ky *.pg *.tp *.vr *.my *.log *.cps core
distclean : clean distclean : clean
$(RM) config.status config.log config.cache Makefile $(RM) config.status config.log config.cache Makefile

409
doc/gperf.texi
View File

@@ -1,28 +1,42 @@
\input texinfo @c -*-texinfo-*- \input texinfo @c -*- texinfo -*-
@c %**start of header
@settitle User's Guide to @code{gperf}
@setfilename gperf.info @setfilename gperf.info
@settitle Perfect Hash Function Generator
@c @setchapternewpage odd
@c %**end of header
@ifinfo @c some day we should @include version.texi instead of defining
@format @c these values at hand.
START-INFO-DIR-ENTRY @set UPDATED 19 August 2000
@set EDITION 2.7
@set VERSION 2.7
@c ---------------------
@c remove the black boxes generated in the GPL appendix.
@finalout
@c Merge functions into the concept index
@syncodeindex fn cp
@c @synindex pg cp
@dircategory Programming Tools
@direntry
* Gperf: (gperf). Perfect Hash Function Generator. * Gperf: (gperf). Perfect Hash Function Generator.
END-INFO-DIR-ENTRY @end direntry
@end format
@end ifinfo
@ifinfo @ifinfo
This file documents the features of the GNU Perfect Hash Function Generator This file documents the features of the GNU Perfect Hash Function
Generator @value{VERSION}.
Copyright (C) 1989-2000 Free Software Foundation, Inc. Copyright @copyright{} 1989-2000 Free Software Foundation, Inc.
Permission is granted to make and distribute verbatim copies of Permission is granted to make and distribute verbatim copies of this
this manual provided the copyright notice and this permission notice manual provided the copyright notice and this permission notice are
are preserved on all copies. preserved on all copies.
@ignore @ignore
Permission is granted to process this file through @TeX{} and print the Permission is granted to process this file through TeX and print the
results, provided the printed document carries copying permission results, provided the printed document carries a copying permission
notice identical to this one except for the removal of this paragraph notice identical to this one except for the removal of this paragraph
(this paragraph not being relevant to the printed manual). (this paragraph not being relevant to the printed manual).
@@ -32,29 +46,23 @@ Permission is granted to copy and distribute modified versions of this
manual under the conditions for verbatim copying, provided also that the manual under the conditions for verbatim copying, provided also that the
section entitled ``GNU General Public License'' is included exactly as section entitled ``GNU General Public License'' is included exactly as
in the original, and provided that the entire resulting derived work is in the original, and provided that the entire resulting derived work is
distributed under the terms of a permission notice identical to this one. distributed under the terms of a permission notice identical to this
one.
Permission is granted to copy and distribute translations of this manual Permission is granted to copy and distribute translations of this manual
into another language, under the above conditions for modified versions, into another language, under the above conditions for modified versions,
except that the section entitled ``GNU @code{gperf} General Public License'' and except that the section entitled ``GNU General Public License'' and this
this permission notice may be included in translations approved by the permission notice may be included in translations approved by the Free
Free Software Foundation instead of in the original English. Software Foundation instead of in the original English.
@end ifinfo @end ifinfo
@setchapternewpage odd
@titlepage @titlepage
@center @titlefont{User's Guide} @title User's Guide to @code{gperf} @value{VERSION}
@sp 2 @subtitle The GNU Perfect Hash Function Generator
@center @titlefont{for the} @subtitle Edition @value{EDITION}, @value{UPDATED}
@sp 2 @author Douglas C. Schmidt
@center @titlefont{GNU GPERF Utility}
@sp 4
@center Douglas C. Schmidt
@sp 3
@center last updated 14 April 1998
@sp 1
@center for version 2.7
@page @page
@vskip 0pt plus 1filll @vskip 0pt plus 1filll
Copyright @copyright{} 1989-2000 Free Software Foundation, Inc. Copyright @copyright{} 1989-2000 Free Software Foundation, Inc.
@@ -66,61 +74,67 @@ are preserved on all copies.
Permission is granted to copy and distribute modified versions of this Permission is granted to copy and distribute modified versions of this
manual under the conditions for verbatim copying, provided also that the manual under the conditions for verbatim copying, provided also that the
section entitled ``GNU @code{gperf} General Public License'' is included exactly as section entitled ``GNU General Public License'' is included
in the original, and provided that the entire resulting derived work is exactly as in the original, and provided that the entire resulting
distributed under the terms of a permission notice identical to this one. derived work is distributed under the terms of a permission notice
identical to this one.
Permission is granted to copy and distribute translations of this manual Permission is granted to copy and distribute translations of this manual
into another language, under the above conditions for modified versions, into another language, under the above conditions for modified versions,
except that the section entitled ``GNU @code{gperf} General Public License'' may be except that the section entitled ``GNU General Public License'' may be
included in a translation approved by the author instead of in the original included in a translation approved by the author instead of in the
English. original English.
@end titlepage @end titlepage
@ifinfo @ifinfo
@node Top, Copying, (dir), (dir) @node Top, Copying, (dir), (dir)
@unnumbered Introduction @top Introduction
This manual documents the GNU @code{gperf} perfect hash function generator This manual documents the GNU @code{gperf} perfect hash function generator
utility, focusing on its features and how to use them, and how to report utility, focusing on its features and how to use them, and how to report
bugs. bugs.
@end ifinfo
@menu @menu
* Copying:: GNU @code{gperf} General Public License says * Copying:: GNU @code{gperf} General Public License says
how you can copy and share @code{gperf}. how you can copy and share @code{gperf}.
* Contributors:: People who have contributed to @code{gperf}. * Contributors:: People who have contributed to @code{gperf}.
* Motivation:: Static search structures and GNU GPERF. * Motivation:: Static search structures and GNU GPERF.
* Search Structures:: Static search structures and GNU @code{gperf} * Search Structures:: Static search structures and GNU @code{gperf}
* Description:: High-level discussion of how GPERF functions. * Description:: High-level discussion of how GPERF functions.
* Options:: A description of options to the program. * Options:: A description of options to the program.
* Bugs:: Known bugs and limitations with GPERF. * Bugs:: Known bugs and limitations with GPERF.
* Projects:: Things still left to do. * Projects:: Things still left to do.
* Implementation:: Implementation Details for GNU GPERF. * Implementation:: Implementation Details for GNU GPERF.
* Bibliography:: Material Referenced in this Report. * Bibliography:: Material Referenced in this Report.
--- The Detailed Node Listing --- * Concept Index::
@detailmenu --- The Detailed Node Listing ---
High-Level Description of GNU @code{gperf} High-Level Description of GNU @code{gperf}
* Input Format:: Input Format to @code{gperf} * Input Format:: Input Format to @code{gperf}
* Output Format:: Output Format for Generated C Code with @code{gperf} * Output Format:: Output Format for Generated C Code with @code{gperf}
Input Format to @code{gperf} Input Format to @code{gperf}
* Declarations:: @code{struct} Declarations and C Code Inclusion. * Declarations:: @code{struct} Declarations and C Code Inclusion.
* Keywords:: Format for Keyword Entries. * Keywords:: Format for Keyword Entries.
* Functions:: Including Additional C Functions. * Functions:: Including Additional C Functions.
Options to the @code{gperf} Utility Invoking @code{gperf}
* Input Details:: Options that affect Interpretation of the Input File * Input Details:: Options that affect Interpretation of the Input File
* Output Language:: Specifying the Language for the Output Code * Output Language:: Specifying the Language for the Output Code
* Output Details:: Fine tuning Details in the Output Code * Output Details:: Fine tuning Details in the Output Code
* Algorithmic Details:: Changing the Algorithms employed by @code{gperf} * Algorithmic Details:: Changing the Algorithms employed by @code{gperf}
* Verbosity:: Informative Output * Verbosity:: Informative Output
@end detailmenu
@end menu @end menu
@end ifinfo
@node Copying, Contributors, Top, Top @node Copying, Contributors, Top, Top
@unnumbered GNU GENERAL PUBLIC LICENSE @unnumbered GNU GENERAL PUBLIC LICENSE
@include gpl.texinfo @include gpl.texinfo
@@ -130,6 +144,7 @@ Options to the @code{gperf} Utility
@itemize @bullet @itemize @bullet
@item @item
@cindex Bugs
The GNU @code{gperf} perfect hash function generator utility was The GNU @code{gperf} perfect hash function generator utility was
originally written in GNU C++ by Douglas C. Schmidt. It is now also originally written in GNU C++ by Douglas C. Schmidt. It is now also
available in a highly-portable ``old-style'' C version. The general available in a highly-portable ``old-style'' C version. The general
@@ -153,14 +168,14 @@ that greatly helped improve the quality and functionality of @code{gperf}.
@chapter Introduction @chapter Introduction
@code{gperf} is a perfect hash function generator written in C++. It @code{gperf} is a perfect hash function generator written in C++. It
transforms an @var{n} element user-specified keyword set @var{W} into transforms an @var{n} element user-specified keyword set @var{W} into a
a perfect hash function @var{F}. @var{F} uniquely maps keywords in perfect hash function @var{F}. @var{F} uniquely maps keywords in
@var{W} onto the range 0..@var{k}, where @var{k >= n}. If @var{W} onto the range 0..@var{k}, where @var{k} >= @var{n}. If @var{k}
@var{k = n} then @var{F} is a @emph{minimal} perfect hash function. = @var{n} then @var{F} is a @emph{minimal} perfect hash function.
@code{gperf} generates a 0..@var{k} element static lookup table and a @code{gperf} generates a 0..@var{k} element static lookup table and a
pair of C functions. These functions determine whether a given pair of C functions. These functions determine whether a given
character string @var{s} occurs in @var{W}, using at most one probe character string @var{s} occurs in @var{W}, using at most one probe into
into the lookup table. the lookup table.
@code{gperf} currently generates the reserved keyword recognizer for @code{gperf} currently generates the reserved keyword recognizer for
lexical analyzers in several production and research compilers and lexical analyzers in several production and research compilers and
@@ -176,6 +191,7 @@ in the Second USENIX C++ Conference proceedings.
@node Search Structures, Description, Motivation, Top @node Search Structures, Description, Motivation, Top
@chapter Static search structures and GNU @code{gperf} @chapter Static search structures and GNU @code{gperf}
@cindex Static search structure
A @dfn{static search structure} is an Abstract Data Type with certain A @dfn{static search structure} is an Abstract Data Type with certain
fundamental operations, e.g., @emph{initialize}, @emph{insert}, fundamental operations, e.g., @emph{initialize}, @emph{insert},
@@ -201,7 +217,7 @@ proportional to log @var{n}. Conversely, hash table implementations
often locate a table entry in constant time, but typically impose often locate a table entry in constant time, but typically impose
additional memory overhead and exhibit poor worst case performance. additional memory overhead and exhibit poor worst case performance.
@cindex Minimal perfect hash functions
@emph{Minimal perfect hash functions} provide an optimal solution for a @emph{Minimal perfect hash functions} provide an optimal solution for a
particular class of static search sets. A minimal perfect hash particular class of static search sets. A minimal perfect hash
function is defined by two properties: function is defined by two properties:
@@ -245,8 +261,8 @@ efficiently identify their respective reserved keywords.
@chapter High-Level Description of GNU @code{gperf} @chapter High-Level Description of GNU @code{gperf}
@menu @menu
* Input Format:: Input Format to @code{gperf} * Input Format:: Input Format to @code{gperf}
* Output Format:: Output Format for Generated C Code with @code{gperf} * Output Format:: Output Format for Generated C Code with @code{gperf}
@end menu @end menu
The perfect hash function generator @code{gperf} reads a set of The perfect hash function generator @code{gperf} reads a set of
@@ -277,7 +293,10 @@ Experimentation is the key to getting the most from @code{gperf}.
@node Input Format, Output Format, Description, Description @node Input Format, Output Format, Description, Description
@section Input Format to @code{gperf} @section Input Format to @code{gperf}
@cindex Format
@cindex Declaration section
@cindex Keywords section
@cindex Functions section
You can control the input keyfile format by varying certain command-line You can control the input keyfile format by varying certain command-line
arguments, in particular the @samp{-t} option. The input's appearance arguments, in particular the @samp{-t} option. The input's appearance
is similar to GNU utilities @code{flex} and @code{bison} (or UNIX is similar to GNU utilities @code{flex} and @code{bison} (or UNIX
@@ -294,14 +313,14 @@ functions
@end group @end group
@end example @end example
@emph{Unlike} @code{flex} or @code{bison}, all sections of @code{gperf}'s input @emph{Unlike} @code{flex} or @code{bison}, all sections of
are optional. The following sections describe the input format for each @code{gperf}'s input are optional. The following sections describe the
section. input format for each section.
@menu @menu
* Declarations:: @code{struct} Declarations and C Code Inclusion. * Declarations:: @code{struct} Declarations and C Code Inclusion.
* Keywords:: Format for Keyword Entries. * Keywords:: Format for Keyword Entries.
* Functions:: Including Additional C Functions. * Functions:: Including Additional C Functions.
@end menu @end menu
@node Declarations, Keywords, Input Format, Input Format @node Declarations, Keywords, Input Format, Input Format
@@ -316,7 +335,7 @@ field in this struct must be a @code{char *} identifier called @samp{name},
although it is possible to modify this field's name with the @samp{-K} although it is possible to modify this field's name with the @samp{-K}
option described below. option described below.
Here is simple example, using months of the year and their attributes as Here is a simple example, using months of the year and their attributes as
input: input:
@example @example
@@ -338,15 +357,18 @@ december, 12, 31, 31
@end group @end group
@end example @end example
Separating the @code{struct} declaration from the list of key words and @cindex @samp{%%}
other fields are a pair of consecutive percent signs, @code{%%}, Separating the @code{struct} declaration from the list of keywords and
other fields are a pair of consecutive percent signs, @samp{%%},
appearing left justified in the first column, as in the UNIX utility appearing left justified in the first column, as in the UNIX utility
@code{lex}. @code{lex}.
@cindex @samp{%@{}
@cindex @samp{%@}}
Using a syntax similar to GNU utilities @code{flex} and @code{bison}, it Using a syntax similar to GNU utilities @code{flex} and @code{bison}, it
is possible to directly include C source text and comments verbatim into is possible to directly include C source text and comments verbatim into
the generated output file. This is accomplished by enclosing the region the generated output file. This is accomplished by enclosing the region
inside left-justified surrounding @code{%@{}, @code{%@}} pairs. Here is inside left-justified surrounding @samp{%@{}, @samp{%@}} pairs. Here is
an input fragment based on the previous example that illustrates this an input fragment based on the previous example that illustrates this
feature: feature:
@@ -410,7 +432,7 @@ return
@end group @end group
@end example @end example
Note that unlike @code{flex} or @code{bison} the first @code{%%} marker Note that unlike @code{flex} or @code{bison} the first @samp{%%} marker
may be elided if the declaration section is empty. may be elided if the declaration section is empty.
Additional fields may optionally follow the leading keyword. Fields Additional fields may optionally follow the leading keyword. Fields
@@ -426,38 +448,40 @@ one contain keyword attributes.
The optional third section also corresponds closely with conventions The optional third section also corresponds closely with conventions
found in @code{flex} and @code{bison}. All text in this section, found in @code{flex} and @code{bison}. All text in this section,
starting at the final @code{%%} and extending to the end of the input starting at the final @samp{%%} and extending to the end of the input
file, is included verbatim into the generated output file. Naturally, file, is included verbatim into the generated output file. Naturally,
it is your responsibility to ensure that the code contained in this it is your responsibility to ensure that the code contained in this
section is valid C. section is valid C.
@node Output Format, , Input Format, Description @node Output Format, , Input Format, Description
@section Output Format for Generated C Code with @code{gperf} @section Output Format for Generated C Code with @code{gperf}
@cindex @code{hash_table}
Several options control how the generated C code appears on the standard Several options control how the generated C code appears on the standard
output. Two C function are generated. They are called @code{hash} and output. Two C function are generated. They are called @code{hash} and
@code{in_word_set}, although you may modify the name for @code{in_word_set}, although you may modify their names with a command-line
@code{in_word_set} with a command-line option. Both functions require option. Both functions require two arguments, a string, @code{char *}
two arguments, a string, @code{char *} @var{str}, and a length @var{str}, and a length parameter, @code{int} @var{len}. Their default
parameter, @code{int} @var{len}. Their default function prototypes are function prototypes are as follows:
as follows:
@example
@group
static int hash (char *str, int len);
int in_word_set (char *str, int len);
@end group
@end example
@deftypefun {unsigned int} hash (const char * @var{str}, unsigned int @var{len})
By default, the generated @code{hash} function returns an integer value By default, the generated @code{hash} function returns an integer value
created by adding @var{len} to several user-specified @var{str} key created by adding @var{len} to several user-specified @var{str} key
positions indexed into an @dfn{associated values} table stored in a positions indexed into an @dfn{associated values} table stored in a
local static array. The associated values table is constructed local static array. The associated values table is constructed
internally by @code{gperf} and later output as a static local C array called internally by @code{gperf} and later output as a static local C array
@var{hash_table}; its meaning and properties are described below. called @samp{hash_table}; its meaning and properties are described below
@xref{Implementation}. The relevant key positions are specified via the (@pxref{Implementation}). The relevant key positions are specified via
@samp{-k} option when running @code{gperf}, as detailed in the @emph{Options} the @samp{-k} option when running @code{gperf}, as detailed in the
section below. @xref{Options}. @emph{Options} section below(@pxref{Options}).
@end deftypefun
@deftypefun {} in_word_set (const char * @var{str}, unsigned int @var{len})
If @var{str} is in the keyword set, returns a pointer to that
keyword. More exactly, if the option @samp{-t} was given, it returns
a pointer to the matching keyword's structure. Otherwise it returns
@code{NULL}.
@end deftypefun
Two options, @samp{-g} (assume you are compiling with GNU C and its Two options, @samp{-g} (assume you are compiling with GNU C and its
@code{inline} feature) and @samp{-a} (assume ANSI C-style function @code{inline} feature) and @samp{-a} (assume ANSI C-style function
@@ -466,49 +490,51 @@ prototypes), alter the content of both the generated @code{hash} and
be modified more extensively, in response to your option settings. The be modified more extensively, in response to your option settings. The
options that affect the @code{in_word_set} structure are: options that affect the @code{in_word_set} structure are:
@itemize @bullet
@table @samp @table @samp
@item -t @item -t
@itemx --struct-type
Make use of the user-defined @code{struct}. Make use of the user-defined @code{struct}.
@item -S @var{total switch statements} @item -S @var{total-switch-statements}
@itemx --switch=@var{total-switch-statements}
@cindex @code{switch}
Generate 1 or more C @code{switch} statement rather than use a large, Generate 1 or more C @code{switch} statement rather than use a large,
(and potentially sparse) static array. Although the exact time and (and potentially sparse) static array. Although the exact time and
space savings of this approach vary according to your C compiler's space savings of this approach vary according to your C compiler's
degree of optimization, this method often results in smaller and faster degree of optimization, this method often results in smaller and faster
code. code.
@end table @end table
@end itemize
If the @samp{-t} and @samp{-S} options are omitted, the If the @samp{-t} and @samp{-S} options are omitted, the default action
default action is to generate a @code{char *} array containing the keys, is to generate a @code{char *} array containing the keys, together with
together with additional null strings used for padding the array. By additional null strings used for padding the array. By experimenting
experimenting with the various input and output options, and timing the with the various input and output options, and timing the resulting C
resulting C code, you can determine the best option choices for code, you can determine the best option choices for different keyword
different keyword set characteristics. set characteristics.
@node Options, Input Details, Description, Top @node Options, Bugs, Description, Top
@chapter Options to the @code{gperf} Utility @chapter Invoking @code{gperf}
There are @emph{many} options to @code{gperf}. They were added to make There are @emph{many} options to @code{gperf}. They were added to make
the program more convenient for use with real applications. ``On-line'' the program more convenient for use with real applications. ``On-line''
help is readily available via the @samp{-h} option. Here is the complete help is readily available via the @samp{-h} option. Here is the
list of options. complete list of options.
@menu @menu
* Input Details:: Options that affect Interpretation of the Input File * Input Details:: Options that affect Interpretation of the Input File
* Output Language:: Specifying the Language for the Output Code * Output Language:: Specifying the Language for the Output Code
* Output Details:: Fine tuning Details in the Output Code * Output Details:: Fine tuning Details in the Output Code
* Algorithmic Details:: Changing the Algorithms employed by @code{gperf} * Algorithmic Details:: Changing the Algorithms employed by @code{gperf}
* Verbosity:: Informative Output * Verbosity:: Informative Output
@end menu @end menu
@node Input Details, Output Language, Options, Options @node Input Details, Output Language, Options, Options
@section Options that affect Interpretation of the Input File @section Options that affect Interpretation of the Input File
@itemize @bullet
@table @samp @table @samp
@item -e @var{keyword delimiter list} @item -e @var{keyword-delimiter-list}
@itemx --delimiters=@var{keyword-delimiter-list}
@cindex Delimiters
Allows the user to provide a string containing delimiters used to Allows the user to provide a string containing delimiters used to
separate keywords from their attributes. The default is ",\n". This separate keywords from their attributes. The default is ",\n". This
option is essential if you want to use keywords that have embedded option is essential if you want to use keywords that have embedded
@@ -516,25 +542,24 @@ commas or newlines. One useful trick is to use -e'TAB', where TAB is
the literal tab character. the literal tab character.
@item -t @item -t
@itemx --struct-type
Allows you to include a @code{struct} type declaration for generated Allows you to include a @code{struct} type declaration for generated
code. Any text before a pair of consecutive %% is considered part of the code. Any text before a pair of consecutive @samp{%%} is considered
type declaration. Key words and additional fields may follow this, one part of the type declaration. Keywords and additional fields may follow
group of fields per line. A set of examples for generating perfect hash this, one group of fields per line. A set of examples for generating
tables and functions for Ada, C, and G++, Pascal, and Modula 2 and 3 perfect hash tables and functions for Ada, C, C++, Pascal, Modula 2,
reserved words are distributed with this release. Modula 3 and JavaScript reserved words are distributed with this release.
@end table @end table
@end itemize
@node Output Language, Output Details, Input Details, Options @node Output Language, Output Details, Input Details, Options
@section Options to specify the Language for the Output Code @section Options to specify the Language for the Output Code
@itemize @bullet
@table @samp @table @samp
@item -L @var{generated language name} @item -L @var{generated-language-name}
@itemx --language=@var{generated-language-name}
Instructs @code{gperf} to generate code in the language specified by the Instructs @code{gperf} to generate code in the language specified by the
option's argument. Languages handled are currently: option's argument. Languages handled are currently:
@itemize @bullet
@table @samp @table @samp
@item KR-C @item KR-C
Old-style K&R C. This language is understood by old-style C compilers and Old-style K&R C. This language is understood by old-style C compilers and
@@ -552,7 +577,6 @@ ANSI C. This language is understood by ANSI C compilers and C++ compilers.
@item C++ @item C++
C++. This language is understood by C++ compilers. C++. This language is understood by C++ compilers.
@end table @end table
@end itemize
The default is C. The default is C.
@@ -564,14 +588,14 @@ This option is supported for compatibility with previous releases of
This option is supported for compatibility with previous releases of This option is supported for compatibility with previous releases of
@code{gperf}. It does not do anything. @code{gperf}. It does not do anything.
@end table @end table
@end itemize
@node Output Details, Algorithmic Details, Output Language, Options @node Output Details, Algorithmic Details, Output Language, Options
@section Options for fine tuning Details in the Output Code @section Options for fine tuning Details in the Output Code
@itemize @bullet
@table @samp @table @samp
@item -K @var{key name} @item -K @var{key-name}
@itemx --slot-name=@var{key-name}
@cindex Slot name
This option is only useful when option @samp{-t} has been given. This option is only useful when option @samp{-t} has been given.
By default, the program assumes the structure component identifier for By default, the program assumes the structure component identifier for
the keyword is @samp{name}. This option allows an arbitrary choice of the keyword is @samp{name}. This option allows an arbitrary choice of
@@ -579,29 +603,36 @@ identifier for this component, although it still must occur as the first
field in your supplied @code{struct}. field in your supplied @code{struct}.
@item -F @var{initializers} @item -F @var{initializers}
@itemx --initializer-suffix=@var{initializers}
@cindex Initializers
This option is only useful when option @samp{-t} has been given. This option is only useful when option @samp{-t} has been given.
It permits to specify initializers for the structure members following It permits to specify initializers for the structure members following
@var{key name} in empty hash table entries. The list of initializers @var{key name} in empty hash table entries. The list of initializers
should start with a comma. By default, the emitted code will should start with a comma. By default, the emitted code will
zero-initialize structure members following @var{key name}. zero-initialize structure members following @var{key name}.
@item -H @var{hash function name} @item -H @var{hash-function-name}
@itemx --hash-fn-name=@var{hash-function-name}
Allows you to specify the name for the generated hash function. Default Allows you to specify the name for the generated hash function. Default
name is @samp{hash}. This option permits the use of two hash tables in the name is @samp{hash}. This option permits the use of two hash tables in
same file. the same file.
@item -N @var{lookup function name} @item -N @var{lookup-function-name}
@itemx --lookup-fn-name=@var{lookup-function-name}
Allows you to specify the name for the generated lookup function. Allows you to specify the name for the generated lookup function.
Default name is @samp{in_word_set}. This option permits completely automatic Default name is @samp{in_word_set}. This option permits completely
generation of perfect hash functions, especially when multiple generated automatic generation of perfect hash functions, especially when multiple
hash functions are used in the same application. generated hash functions are used in the same application.
@item -Z @var{class name} @item -Z @var{class-name}
This option is only useful when option @samp{-L C++} has been given. @itemx --class-name=@var{class-name}
It allows you to specify the name of generated C++ class. Default name is @cindex Class name
This option is only useful when option @samp{-L C++} has been given. It
allows you to specify the name of generated C++ class. Default name is
@code{Perfect_Hash}. @code{Perfect_Hash}.
@item -7 @item -7
@itemx --seven-bit
This option specifies that all strings that will be passed as arguments This option specifies that all strings that will be passed as arguments
to the generated hash function and the generated lookup function will to the generated hash function and the generated lookup function will
solely consist of 7-bit ASCII characters (characters in the range 0..127). solely consist of 7-bit ASCII characters (characters in the range 0..127).
@@ -612,36 +643,45 @@ default in earlier versions of @code{gperf}; now the default is to assume
8-bit characters. 8-bit characters.
@item -c @item -c
@itemx --compare-strncmp
Generates C code that uses the @code{strncmp} function to perform Generates C code that uses the @code{strncmp} function to perform
string comparisons. The default action is to use @code{strcmp}. string comparisons. The default action is to use @code{strcmp}.
@item -C @item -C
@itemx --readonly-tables
Makes the contents of all generated lookup tables constant, i.e., Makes the contents of all generated lookup tables constant, i.e.,
``readonly''. Many compilers can generate more efficient code for this ``readonly''. Many compilers can generate more efficient code for this
by putting the tables in readonly memory. by putting the tables in readonly memory.
@item -E @item -E
@itemx --enum
Define constant values using an enum local to the lookup function rather Define constant values using an enum local to the lookup function rather
than with #defines. This also means that different lookup functions can than with #defines. This also means that different lookup functions can
reside in the same file. Thanks to James Clark @code{<jjc@@ai.mit.edu>}. reside in the same file. Thanks to James Clark @code{<jjc@@ai.mit.edu>}.
@item -I @item -I
@itemx --includes
Include the necessary system include file, @code{<string.h>}, at the Include the necessary system include file, @code{<string.h>}, at the
beginning of the code. By default, this is not done; the user must beginning of the code. By default, this is not done; the user must
include this header file himself to allow compilation of the code. include this header file himself to allow compilation of the code.
@item -G @item -G
@itemx --global
Generate the static table of keywords as a static global variable, Generate the static table of keywords as a static global variable,
rather than hiding it inside of the lookup function (which is the rather than hiding it inside of the lookup function (which is the
default behavior). default behavior).
@item -W @var{hash table array name} @item -W @var{hash-table-array-name}
@itemx --word-array-name=@var{hash-table-array-name}
@cindex Array name
Allows you to specify the name for the generated array containing the Allows you to specify the name for the generated array containing the
hash table. Default name is @samp{wordlist}. This option permits the hash table. Default name is @samp{wordlist}. This option permits the
use of two hash tables in the same file, even when the option @samp{-G} use of two hash tables in the same file, even when the option @samp{-G}
is given. is given.
@item -S @var{total switch statements} @item -S @var{total-switch-statements}
@itemx --switch=@var{total-switch-statements}
@cindex @code{switch}
Causes the generated C code to use a @code{switch} statement scheme, Causes the generated C code to use a @code{switch} statement scheme,
rather than an array lookup table. This can lead to a reduction in both rather than an array lookup table. This can lead to a reduction in both
time and space requirements for some keyfiles. The argument to this time and space requirements for some keyfiles. The argument to this
@@ -653,6 +693,7 @@ correctly generate code for large @code{switch} statements. This option
was inspired in part by Keith Bostic's original C program. was inspired in part by Keith Bostic's original C program.
@item -T @item -T
@itemx --omit-struct-type
Prevents the transfer of the type declaration to the output file. Use Prevents the transfer of the type declaration to the output file. Use
this option if the type is already defined elsewhere. this option if the type is already defined elsewhere.
@@ -660,14 +701,13 @@ this option if the type is already defined elsewhere.
This option is supported for compatibility with previous releases of This option is supported for compatibility with previous releases of
@code{gperf}. It does not do anything. @code{gperf}. It does not do anything.
@end table @end table
@end itemize
@node Algorithmic Details, Verbosity, Output Details, Options @node Algorithmic Details, Verbosity, Output Details, Options
@section Options for changing the Algorithms employed by @code{gperf} @section Options for changing the Algorithms employed by @code{gperf}
@itemize @bullet
@table @samp @table @samp
@item -k @var{keys} @item -k @var{keys}
@itemx --key-positions=@var{keys}
Allows selection of the character key positions used in the keywords' Allows selection of the character key positions used in the keywords'
hash function. The allowable choices range between 1-126, inclusive. hash function. The allowable choices range between 1-126, inclusive.
The positions are separated by commas, e.g., @samp{-k 9,4,13,14}; The positions are separated by commas, e.g., @samp{-k 9,4,13,14};
@@ -686,6 +726,7 @@ selected key positions exceeding the key length are simply not
referenced in the hash function. referenced in the hash function.
@item -l @item -l
@itemx --compare-strlen
Compare key lengths before trying a string comparison. This might cut Compare key lengths before trying a string comparison. This might cut
down on the number of string comparisons made during the lookup, since down on the number of string comparisons made during the lookup, since
keys with different lengths are never compared via @code{strcmp}. keys with different lengths are never compared via @code{strcmp}.
@@ -695,6 +736,8 @@ the switch option @samp{-S} is not enabled), since the length table
contains as many elements as there are entries in the lookup table. contains as many elements as there are entries in the lookup table.
@item -D @item -D
@itemx --duplicates
@cindex Duplicates
Handle keywords whose key position sets hash to duplicate values. Handle keywords whose key position sets hash to duplicate values.
Duplicate hash values occur for two reasons: Duplicate hash values occur for two reasons:
@@ -704,11 +747,12 @@ Since @code{gperf} does not backtrack it is possible for it to process
all your input keywords without finding a unique mapping for each word. all your input keywords without finding a unique mapping for each word.
However, frequently only a very small number of duplicates occur, and However, frequently only a very small number of duplicates occur, and
the majority of keys still require one probe into the table. the majority of keys still require one probe into the table.
@item @item
Sometimes a set of keys may have the same names, but possess different Sometimes a set of keys may have the same names, but possess different
attributes. With the -D option @code{gperf} treats all these keys as part of attributes. With the -D option @code{gperf} treats all these keys as
an equivalence class and generates a perfect hash function with multiple part of an equivalence class and generates a perfect hash function with
comparisons for duplicate keys. It is up to you to completely multiple comparisons for duplicate keys. It is up to you to completely
disambiguate the keywords by modifying the generated C code. However, disambiguate the keywords by modifying the generated C code. However,
@code{gperf} helps you out by organizing the output. @code{gperf} helps you out by organizing the output.
@end itemize @end itemize
@@ -719,33 +763,39 @@ Using this option usually means that the generated hash function is no
longer perfect. On the other hand, it permits @code{gperf} to work on longer perfect. On the other hand, it permits @code{gperf} to work on
keyword sets that it otherwise could not handle. keyword sets that it otherwise could not handle.
@item -f @var{iteration amount} @item -f @var{iteration-amount}
Generate the perfect hash function ``fast''. This decreases @code{gperf}'s @itemx --fast=@var{iteration-amount}
running time at the cost of minimizing generated table-size. The Generate the perfect hash function ``fast''. This decreases
iteration amount represents the number of times to iterate when @code{gperf}'s running time at the cost of minimizing generated
resolving a collision. `0' means iterate by the number of keywords. table-size. The iteration amount represents the number of times to
This option is probably most useful when used in conjunction with options iterate when resolving a collision. `0' means iterate by the number of
@samp{-D} and/or @samp{-S} for @emph{large} keyword sets. keywords. This option is probably most useful when used in conjunction
with options @samp{-D} and/or @samp{-S} for @emph{large} keyword sets.
@item -i @var{initial value} @item -i @var{initial-value}
@itemx --initial-asso=@var{initial-value}
Provides an initial @var{value} for the associate values array. Default Provides an initial @var{value} for the associate values array. Default
is 0. Increasing the initial value helps inflate the final table size, is 0. Increasing the initial value helps inflate the final table size,
possibly leading to more time efficient keyword lookups. Note that this possibly leading to more time efficient keyword lookups. Note that this
option is not particularly useful when @samp{-S} is used. Also, option is not particularly useful when @samp{-S} is used. Also,
@samp{-i} is overriden when the @samp{-r} option is used. @samp{-i} is overridden when the @samp{-r} option is used.
@item -j @var{jump value} @item -j @var{jump-value}
Affects the ``jump value'', i.e., how far to advance the @itemx --jump=@var{jump-value}
associated character value upon collisions. @var{Jump value} is rounded @cindex Jump value
up to an odd number, the default is 5. If the @var{jump value} is 0 Affects the ``jump value'', i.e., how far to advance the associated
@code{gperf} jumps by random amounts. character value upon collisions. @var{Jump-value} is rounded up to an
odd number, the default is 5. If the @var{jump-value} is 0 @code{gperf}
jumps by random amounts.
@item -n @item -n
@itemx --no-strlen
Instructs the generator not to include the length of a keyword when Instructs the generator not to include the length of a keyword when
computing its hash value. This may save a few assembly instructions in computing its hash value. This may save a few assembly instructions in
the generated lookup table. the generated lookup table.
@item -o @item -o
@itemx --occurrence-sort
Reorders the keywords by sorting the keywords so that frequently Reorders the keywords by sorting the keywords so that frequently
occuring key position set components appear first. A second reordering occuring key position set components appear first. A second reordering
pass follows so that keys with ``already determined values'' are placed pass follows so that keys with ``already determined values'' are placed
@@ -755,12 +805,13 @@ produce more minimal perfect hash functions. The reason for this is
that the reordering helps prune the search time by handling inevitable that the reordering helps prune the search time by handling inevitable
collisions early in the search process. On the other hand, if the collisions early in the search process. On the other hand, if the
number of keywords is @emph{very} large using @samp{-o} may number of keywords is @emph{very} large using @samp{-o} may
@emph{increase} @code{gperf}'s execution time, since collisions will begin @emph{increase} @code{gperf}'s execution time, since collisions will
earlier and continue throughout the remainder of keyword processing. begin earlier and continue throughout the remainder of keyword
See Cichelli's paper from the January 1980 Communications of the ACM for processing. See Cichelli's paper from the January 1980 Communications
details. of the ACM for details.
@item -r @item -r
@itemx --random
Utilizes randomness to initialize the associated values table. This Utilizes randomness to initialize the associated values table. This
frequently generates solutions faster than using deterministic frequently generates solutions faster than using deterministic
initialization (which starts all associated values at 0). Furthermore, initialization (which starts all associated values at 0). Furthermore,
@@ -769,6 +820,7 @@ table. If @code{gperf} has difficultly with a certain keyword set try using
@samp{-r} or @samp{-D}. @samp{-r} or @samp{-D}.
@item -s @var{size-multiple} @item -s @var{size-multiple}
@itemx --size-multiple=@var{size-multiple}
Affects the size of the generated hash table. The numeric argument for Affects the size of the generated hash table. The numeric argument for
this option indicates ``how many times larger or smaller'' the maximum this option indicates ``how many times larger or smaller'' the maximum
associated value range should be, in relationship to the number of keys. associated value range should be, in relationship to the number of keys.
@@ -797,21 +849,22 @@ heuristic. In particular, setting this value too high slows down
of values. Judicious use of the @samp{-f} option helps alleviate this of values. Judicious use of the @samp{-f} option helps alleviate this
overhead, however. overhead, however.
@end table @end table
@end itemize
@node Verbosity, Bugs, Algorithmic Details, Options @node Verbosity, , Algorithmic Details, Options
@section Informative Output @section Informative Output
@itemize @bullet
@table @samp @table @samp
@item -h @item -h
@itemx --help
Prints a short summary on the meaning of each program option. Aborts Prints a short summary on the meaning of each program option. Aborts
further program execution. further program execution.
@item -v @item -v
@itemx --version
Prints out the current version number. Prints out the current version number.
@item -d @item -d
@itemx --debug
Enables the debugging option. This produces verbose diagnostics to Enables the debugging option. This produces verbose diagnostics to
``standard error'' when @code{gperf} is executing. It is useful both for ``standard error'' when @code{gperf} is executing. It is useful both for
maintaining the program and for determining whether a given set of maintaining the program and for determining whether a given set of
@@ -819,9 +872,8 @@ options is actually speeding up the search for a solution. Some useful
information is dumped at the end of the program when the @samp{-d} information is dumped at the end of the program when the @samp{-d}
option is enabled. option is enabled.
@end table @end table
@end itemize
@node Bugs, Projects, Verbosity, Top @node Bugs, Projects, Options, Top
@chapter Known Bugs and Limitations with @code{gperf} @chapter Known Bugs and Limitations with @code{gperf}
The following are some limitations with the current release of The following are some limitations with the current release of
@@ -913,7 +965,7 @@ determining both the minimum and maximum elements in a list.
@page @page
@node Bibliography, , Implementation, Top @node Bibliography, Concept Index, Implementation, Top
@chapter Bibliography @chapter Bibliography
[1] Chang, C.C.: @i{A Scheme for Constructing Ordered Minimal Perfect [1] Chang, C.C.: @i{A Scheme for Constructing Ordered Minimal Perfect
@@ -960,5 +1012,10 @@ Retrieving Method for Static Sets} Communications of the ACM, 20
[14] Tiemann, Michael D. @i{User's Guide to GNU C++} Free Software [14] Tiemann, Michael D. @i{User's Guide to GNU C++} Free Software
Foundation, 1989. Foundation, 1989.
@node Concept Index, , Bibliography, Top
@unnumbered Concept Index
@printindex cp
@contents @contents
@bye @bye