From 72231250ed81e10d66bfe70701e64fa5fe50f712 Mon Sep 17 00:00:00 2001 From: Jon Bratseth Date: Wed, 15 Jun 2016 23:09:44 +0200 Subject: Publish --- fsa/doc/.gitignore | 2 + fsa/doc/Doxyfile | 1099 ++++++++++++++++++++++++++++++++++++++++++ fsa/doc/docbook/.gitignore | 4 + fsa/doc/docbook/fsadump.xml | 205 ++++++++ fsa/doc/docbook/fsainfo.xml | 177 +++++++ fsa/doc/docbook/makefsa.xml | 224 +++++++++ fsa/doc/fsa_file_format.html | 69 +++ fsa/doc/permute_query.stats | 18 + 8 files changed, 1798 insertions(+) create mode 100644 fsa/doc/.gitignore create mode 100644 fsa/doc/Doxyfile create mode 100644 fsa/doc/docbook/.gitignore create mode 100644 fsa/doc/docbook/fsadump.xml create mode 100644 fsa/doc/docbook/fsainfo.xml create mode 100644 fsa/doc/docbook/makefsa.xml create mode 100644 fsa/doc/fsa_file_format.html create mode 100644 fsa/doc/permute_query.stats (limited to 'fsa/doc') diff --git a/fsa/doc/.gitignore b/fsa/doc/.gitignore new file mode 100644 index 00000000000..2ec816f3ef2 --- /dev/null +++ b/fsa/doc/.gitignore @@ -0,0 +1,2 @@ +html +latex diff --git a/fsa/doc/Doxyfile b/fsa/doc/Doxyfile new file mode 100644 index 00000000000..6b47c186cb4 --- /dev/null +++ b/fsa/doc/Doxyfile @@ -0,0 +1,1099 @@ +# Copyright 2016 Yahoo Inc. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root. +# Doxyfile 1.3.5 + +# This file describes the settings to be used by the documentation system +# doxygen (www.doxygen.org) for a project +# +# All text after a hash (#) is considered a comment and will be ignored +# The format is: +# TAG = value [value, ...] +# For lists items can also be appended using: +# TAG += value [value, ...] +# Values that contain spaces should be placed between quotes (" ") + +#--------------------------------------------------------------------------- +# Project related configuration options +#--------------------------------------------------------------------------- + +# The PROJECT_NAME tag is a single word (or a sequence of words surrounded +# by quotes) that should identify the project. + +PROJECT_NAME = fsa + +# The PROJECT_NUMBER tag can be used to enter a project or revision number. +# This could be handy for archiving the generated documentation or +# if some version control system is used. + +PROJECT_NUMBER = 2.0.1 + +# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) +# base path where the generated documentation will be put. +# If a relative path is entered, it will be relative to the location +# where doxygen was started. If left blank the current directory will be used. + +OUTPUT_DIRECTORY = + +# The OUTPUT_LANGUAGE tag is used to specify the language in which all +# documentation generated by doxygen is written. Doxygen will use this +# information to generate all constant output in the proper language. +# The default language is English, other supported languages are: +# Brazilian, Catalan, Chinese, Chinese-Traditional, Croatian, Czech, Danish, Dutch, +# Finnish, French, German, Greek, Hungarian, Italian, Japanese, Japanese-en +# (Japanese with English messages), Korean, Norwegian, Polish, Portuguese, +# Romanian, Russian, Serbian, Slovak, Slovene, Spanish, Swedish, and Ukrainian. + +OUTPUT_LANGUAGE = English + +# This tag can be used to specify the encoding used in the generated output. +# The encoding is not always determined by the language that is chosen, +# but also whether or not the output is meant for Windows or non-Windows users. +# In case there is a difference, setting the USE_WINDOWS_ENCODING tag to YES +# forces the Windows encoding (this is the default for the Windows binary), +# whereas setting the tag to NO uses a Unix-style encoding (the default for +# all platforms other than Windows). + +USE_WINDOWS_ENCODING = NO + +# If the BRIEF_MEMBER_DESC tag is set to YES (the default) Doxygen will +# include brief member descriptions after the members that are listed in +# the file and class documentation (similar to JavaDoc). +# Set to NO to disable this. + +BRIEF_MEMBER_DESC = YES + +# If the REPEAT_BRIEF tag is set to YES (the default) Doxygen will prepend +# the brief description of a member or function before the detailed description. +# Note: if both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the +# brief descriptions will be completely suppressed. + +REPEAT_BRIEF = YES + +# This tag implements a quasi-intelligent brief description abbreviator +# that is used to form the text in various listings. Each string +# in this list, if found as the leading text of the brief description, will be +# stripped from the text and the result after processing the whole list, is used +# as the annotated text. Otherwise, the brief description is used as-is. If left +# blank, the following values are used ("$name" is automatically replaced with the +# name of the entity): "The $name class" "The $name widget" "The $name file" +# "is" "provides" "specifies" "contains" "represents" "a" "an" "the" + +ABBREVIATE_BRIEF = + +# If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then +# Doxygen will generate a detailed section even if there is only a brief +# description. + +ALWAYS_DETAILED_SEC = NO + +# If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all inherited +# members of a class in the documentation of that class as if those members were +# ordinary class members. Constructors, destructors and assignment operators of +# the base classes will not be shown. + +INLINE_INHERITED_MEMB = NO + +# If the FULL_PATH_NAMES tag is set to YES then Doxygen will prepend the full +# path before files name in the file list and in the header files. If set +# to NO the shortest path that makes the file name unique will be used. + +FULL_PATH_NAMES = NO + +# If the FULL_PATH_NAMES tag is set to YES then the STRIP_FROM_PATH tag +# can be used to strip a user-defined part of the path. Stripping is +# only done if one of the specified strings matches the left-hand part of +# the path. It is allowed to use relative paths in the argument list. + +STRIP_FROM_PATH = + +# If the SHORT_NAMES tag is set to YES, doxygen will generate much shorter +# (but less readable) file names. This can be useful is your file systems +# doesn't support long names like on DOS, Mac, or CD-ROM. + +SHORT_NAMES = NO + +# If the JAVADOC_AUTOBRIEF tag is set to YES then Doxygen +# will interpret the first line (until the first dot) of a JavaDoc-style +# comment as the brief description. If set to NO, the JavaDoc +# comments will behave just like the Qt-style comments (thus requiring an +# explicit @brief command for a brief description. + +JAVADOC_AUTOBRIEF = NO + +# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make Doxygen +# treat a multi-line C++ special comment block (i.e. a block of //! or /// +# comments) as a brief description. This used to be the default behaviour. +# The new default is to treat a multi-line C++ comment block as a detailed +# description. Set this tag to YES if you prefer the old behaviour instead. + +MULTILINE_CPP_IS_BRIEF = NO + +# If the DETAILS_AT_TOP tag is set to YES then Doxygen +# will output the detailed description near the top, like JavaDoc. +# If set to NO, the detailed description appears after the member +# documentation. + +DETAILS_AT_TOP = NO + +# If the INHERIT_DOCS tag is set to YES (the default) then an undocumented +# member inherits the documentation from any documented member that it +# re-implements. + +INHERIT_DOCS = YES + +# If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC +# tag is set to YES, then doxygen will reuse the documentation of the first +# member in the group (if any) for the other members of the group. By default +# all members of a group must be documented explicitly. + +DISTRIBUTE_GROUP_DOC = NO + +# The TAB_SIZE tag can be used to set the number of spaces in a tab. +# Doxygen uses this value to replace tabs by spaces in code fragments. + +TAB_SIZE = 8 + +# This tag can be used to specify a number of aliases that acts +# as commands in the documentation. An alias has the form "name=value". +# For example adding "sideeffect=\par Side Effects:\n" will allow you to +# put the command \sideeffect (or @sideeffect) in the documentation, which +# will result in a user-defined paragraph with heading "Side Effects:". +# You can put \n's in the value part of an alias to insert newlines. + +ALIASES = + +# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C sources +# only. Doxygen will then generate output that is more tailored for C. +# For instance, some of the names that are used will be different. The list +# of all members will be omitted, etc. + +OPTIMIZE_OUTPUT_FOR_C = NO + +# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java sources +# only. Doxygen will then generate output that is more tailored for Java. +# For instance, namespaces will be presented as packages, qualified scopes +# will look different, etc. + +OPTIMIZE_OUTPUT_JAVA = NO + +# Set the SUBGROUPING tag to YES (the default) to allow class member groups of +# the same type (for instance a group of public functions) to be put as a +# subgroup of that type (e.g. under the Public Functions section). Set it to +# NO to prevent subgrouping. Alternatively, this can be done per class using +# the \nosubgrouping command. + +SUBGROUPING = YES + +#--------------------------------------------------------------------------- +# Build related configuration options +#--------------------------------------------------------------------------- + +# If the EXTRACT_ALL tag is set to YES doxygen will assume all entities in +# documentation are documented, even if no documentation was available. +# Private class members and static file members will be hidden unless +# the EXTRACT_PRIVATE and EXTRACT_STATIC tags are set to YES + +EXTRACT_ALL = YES + +# If the EXTRACT_PRIVATE tag is set to YES all private members of a class +# will be included in the documentation. + +EXTRACT_PRIVATE = YES + +# If the EXTRACT_STATIC tag is set to YES all static members of a file +# will be included in the documentation. + +EXTRACT_STATIC = YES + +# If the EXTRACT_LOCAL_CLASSES tag is set to YES classes (and structs) +# defined locally in source files will be included in the documentation. +# If set to NO only classes defined in header files are included. + +EXTRACT_LOCAL_CLASSES = YES + +# If the HIDE_UNDOC_MEMBERS tag is set to YES, Doxygen will hide all +# undocumented members of documented classes, files or namespaces. +# If set to NO (the default) these members will be included in the +# various overviews, but no documentation section is generated. +# This option has no effect if EXTRACT_ALL is enabled. + +HIDE_UNDOC_MEMBERS = NO + +# If the HIDE_UNDOC_CLASSES tag is set to YES, Doxygen will hide all +# undocumented classes that are normally visible in the class hierarchy. +# If set to NO (the default) these classes will be included in the various +# overviews. This option has no effect if EXTRACT_ALL is enabled. + +HIDE_UNDOC_CLASSES = NO + +# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, Doxygen will hide all +# friend (class|struct|union) declarations. +# If set to NO (the default) these declarations will be included in the +# documentation. + +HIDE_FRIEND_COMPOUNDS = NO + +# If the HIDE_IN_BODY_DOCS tag is set to YES, Doxygen will hide any +# documentation blocks found inside the body of a function. +# If set to NO (the default) these blocks will be appended to the +# function's detailed documentation block. + +HIDE_IN_BODY_DOCS = NO + +# The INTERNAL_DOCS tag determines if documentation +# that is typed after a \internal command is included. If the tag is set +# to NO (the default) then the documentation will be excluded. +# Set it to YES to include the internal documentation. + +INTERNAL_DOCS = NO + +# If the CASE_SENSE_NAMES tag is set to NO then Doxygen will only generate +# file names in lower-case letters. If set to YES upper-case letters are also +# allowed. This is useful if you have classes or files whose names only differ +# in case and if your file system supports case sensitive file names. Windows +# users are advised to set this option to NO. + +CASE_SENSE_NAMES = YES + +# If the HIDE_SCOPE_NAMES tag is set to NO (the default) then Doxygen +# will show members with their full class and namespace scopes in the +# documentation. If set to YES the scope will be hidden. + +HIDE_SCOPE_NAMES = NO + +# If the SHOW_INCLUDE_FILES tag is set to YES (the default) then Doxygen +# will put a list of the files that are included by a file in the documentation +# of that file. + +SHOW_INCLUDE_FILES = YES + +# If the INLINE_INFO tag is set to YES (the default) then a tag [inline] +# is inserted in the documentation for inline members. + +INLINE_INFO = YES + +# If the SORT_MEMBER_DOCS tag is set to YES (the default) then doxygen +# will sort the (detailed) documentation of file and class members +# alphabetically by member name. If set to NO the members will appear in +# declaration order. + +SORT_MEMBER_DOCS = YES + +# The GENERATE_TODOLIST tag can be used to enable (YES) or +# disable (NO) the todo list. This list is created by putting \todo +# commands in the documentation. + +GENERATE_TODOLIST = YES + +# The GENERATE_TESTLIST tag can be used to enable (YES) or +# disable (NO) the test list. This list is created by putting \test +# commands in the documentation. + +GENERATE_TESTLIST = YES + +# The GENERATE_BUGLIST tag can be used to enable (YES) or +# disable (NO) the bug list. This list is created by putting \bug +# commands in the documentation. + +GENERATE_BUGLIST = YES + +# The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or +# disable (NO) the deprecated list. This list is created by putting +# \deprecated commands in the documentation. + +GENERATE_DEPRECATEDLIST= YES + +# The ENABLED_SECTIONS tag can be used to enable conditional +# documentation sections, marked by \if sectionname ... \endif. + +ENABLED_SECTIONS = + +# The MAX_INITIALIZER_LINES tag determines the maximum number of lines +# the initial value of a variable or define consists of for it to appear in +# the documentation. If the initializer consists of more lines than specified +# here it will be hidden. Use a value of 0 to hide initializers completely. +# The appearance of the initializer of individual variables and defines in the +# documentation can be controlled using \showinitializer or \hideinitializer +# command in the documentation regardless of this setting. + +MAX_INITIALIZER_LINES = 30 + +# Set the SHOW_USED_FILES tag to NO to disable the list of files generated +# at the bottom of the documentation of classes and structs. If set to YES the +# list will mention the files that were used to generate the documentation. + +SHOW_USED_FILES = YES + +#--------------------------------------------------------------------------- +# configuration options related to warning and progress messages +#--------------------------------------------------------------------------- + +# The QUIET tag can be used to turn on/off the messages that are generated +# by doxygen. Possible values are YES and NO. If left blank NO is used. + +QUIET = NO + +# The WARNINGS tag can be used to turn on/off the warning messages that are +# generated by doxygen. Possible values are YES and NO. If left blank +# NO is used. + +WARNINGS = YES + +# If WARN_IF_UNDOCUMENTED is set to YES, then doxygen will generate warnings +# for undocumented members. If EXTRACT_ALL is set to YES then this flag will +# automatically be disabled. + +WARN_IF_UNDOCUMENTED = YES + +# If WARN_IF_DOC_ERROR is set to YES, doxygen will generate warnings for +# potential errors in the documentation, such as not documenting some +# parameters in a documented function, or documenting parameters that +# don't exist or using markup commands wrongly. + +WARN_IF_DOC_ERROR = YES + +# The WARN_FORMAT tag determines the format of the warning messages that +# doxygen can produce. The string should contain the $file, $line, and $text +# tags, which will be replaced by the file and line number from which the +# warning originated and the warning text. + +WARN_FORMAT = "$file:$line: $text" + +# The WARN_LOGFILE tag can be used to specify a file to which warning +# and error messages should be written. If left blank the output is written +# to stderr. + +WARN_LOGFILE = + +#--------------------------------------------------------------------------- +# configuration options related to the input files +#--------------------------------------------------------------------------- + +# The INPUT tag can be used to specify the files and/or directories that contain +# documented source files. You may enter file names like "myfile.cpp" or +# directories like "/usr/src/myproject". Separate the files or directories +# with spaces. + +INPUT = ../src + +# If the value of the INPUT tag contains directories, you can use the +# FILE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp +# and *.h) to filter out the source-files in the directories. If left +# blank the following patterns are tested: +# *.c *.cc *.cxx *.cpp *.c++ *.java *.ii *.ixx *.ipp *.i++ *.inl *.h *.hh *.hxx *.hpp +# *.h++ *.idl *.odl *.cs *.php *.php3 *.inc + +FILE_PATTERNS = *.h *.cpp + +# The RECURSIVE tag can be used to turn specify whether or not subdirectories +# should be searched for input files as well. Possible values are YES and NO. +# If left blank NO is used. + +RECURSIVE = YES + +# The EXCLUDE tag can be used to specify files and/or directories that should +# excluded from the INPUT source files. This way you can easily exclude a +# subdirectory from a directory tree whose root is specified with the INPUT tag. + +EXCLUDE = + +# The EXCLUDE_SYMLINKS tag can be used select whether or not files or directories +# that are symbolic links (a Unix filesystem feature) are excluded from the input. + +EXCLUDE_SYMLINKS = NO + +# If the value of the INPUT tag contains directories, you can use the +# EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude +# certain files from those directories. + +EXCLUDE_PATTERNS = + +# The EXAMPLE_PATH tag can be used to specify one or more files or +# directories that contain example code fragments that are included (see +# the \include command). + +EXAMPLE_PATH = + +# If the value of the EXAMPLE_PATH tag contains directories, you can use the +# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp +# and *.h) to filter out the source-files in the directories. If left +# blank all files are included. + +EXAMPLE_PATTERNS = + +# If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be +# searched for input files to be used with the \include or \dontinclude +# commands irrespective of the value of the RECURSIVE tag. +# Possible values are YES and NO. If left blank NO is used. + +EXAMPLE_RECURSIVE = NO + +# The IMAGE_PATH tag can be used to specify one or more files or +# directories that contain image that are included in the documentation (see +# the \image command). + +IMAGE_PATH = + +# The INPUT_FILTER tag can be used to specify a program that doxygen should +# invoke to filter for each input file. Doxygen will invoke the filter program +# by executing (via popen()) the command , where +# is the value of the INPUT_FILTER tag, and is the name of an +# input file. Doxygen will then use the output that the filter program writes +# to standard output. + +INPUT_FILTER = + +# If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using +# INPUT_FILTER) will be used to filter the input files when producing source +# files to browse (i.e. when SOURCE_BROWSER is set to YES). + +FILTER_SOURCE_FILES = NO + +#--------------------------------------------------------------------------- +# configuration options related to source browsing +#--------------------------------------------------------------------------- + +# If the SOURCE_BROWSER tag is set to YES then a list of source files will +# be generated. Documented entities will be cross-referenced with these sources. +# Note: To get rid of all source code in the generated output, make sure also +# VERBATIM_HEADERS is set to NO. + +SOURCE_BROWSER = NO + +# Setting the INLINE_SOURCES tag to YES will include the body +# of functions and classes directly in the documentation. + +INLINE_SOURCES = NO + +# Setting the STRIP_CODE_COMMENTS tag to YES (the default) will instruct +# doxygen to hide any special comment blocks from generated source code +# fragments. Normal C and C++ comments will always remain visible. + +STRIP_CODE_COMMENTS = YES + +# If the REFERENCED_BY_RELATION tag is set to YES (the default) +# then for each documented function all documented +# functions referencing it will be listed. + +REFERENCED_BY_RELATION = YES + +# If the REFERENCES_RELATION tag is set to YES (the default) +# then for each documented function all documented entities +# called/used by that function will be listed. + +REFERENCES_RELATION = YES + +# If the VERBATIM_HEADERS tag is set to YES (the default) then Doxygen +# will generate a verbatim copy of the header file for each class for +# which an include is specified. Set to NO to disable this. + +VERBATIM_HEADERS = YES + +#--------------------------------------------------------------------------- +# configuration options related to the alphabetical class index +#--------------------------------------------------------------------------- + +# If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index +# of all compounds will be generated. Enable this if the project +# contains a lot of classes, structs, unions or interfaces. + +ALPHABETICAL_INDEX = YES + +# If the alphabetical index is enabled (see ALPHABETICAL_INDEX) then +# the COLS_IN_ALPHA_INDEX tag can be used to specify the number of columns +# in which this list will be split (can be a number in the range [1..20]) + +COLS_IN_ALPHA_INDEX = 3 + +# In case all classes in a project start with a common prefix, all +# classes will be put under the same header in the alphabetical index. +# The IGNORE_PREFIX tag can be used to specify one or more prefixes that +# should be ignored while generating the index headers. + +IGNORE_PREFIX = + +#--------------------------------------------------------------------------- +# configuration options related to the HTML output +#--------------------------------------------------------------------------- + +# If the GENERATE_HTML tag is set to YES (the default) Doxygen will +# generate HTML output. + +GENERATE_HTML = YES + +# The HTML_OUTPUT tag is used to specify where the HTML docs will be put. +# If a relative path is entered the value of OUTPUT_DIRECTORY will be +# put in front of it. If left blank `html' will be used as the default path. + +HTML_OUTPUT = html + +# The HTML_FILE_EXTENSION tag can be used to specify the file extension for +# each generated HTML page (for example: .htm,.php,.asp). If it is left blank +# doxygen will generate files with .html extension. + +HTML_FILE_EXTENSION = .html + +# The HTML_HEADER tag can be used to specify a personal HTML header for +# each generated HTML page. If it is left blank doxygen will generate a +# standard header. + +HTML_HEADER = + +# The HTML_FOOTER tag can be used to specify a personal HTML footer for +# each generated HTML page. If it is left blank doxygen will generate a +# standard footer. + +HTML_FOOTER = + +# The HTML_STYLESHEET tag can be used to specify a user-defined cascading +# style sheet that is used by each HTML page. It can be used to +# fine-tune the look of the HTML output. If the tag is left blank doxygen +# will generate a default style sheet. Note that doxygen will try to copy +# the style sheet file to the HTML output directory, so don't put your own +# stylesheet in the HTML output directory as well, or it will be erased! + +HTML_STYLESHEET = + +# If the HTML_ALIGN_MEMBERS tag is set to YES, the members of classes, +# files or namespaces will be aligned in HTML using tables. If set to +# NO a bullet list will be used. + +HTML_ALIGN_MEMBERS = NO + +# If the GENERATE_HTMLHELP tag is set to YES, additional index files +# will be generated that can be used as input for tools like the +# Microsoft HTML help workshop to generate a compressed HTML help file (.chm) +# of the generated HTML documentation. + +GENERATE_HTMLHELP = NO + +# If the GENERATE_HTMLHELP tag is set to YES, the CHM_FILE tag can +# be used to specify the file name of the resulting .chm file. You +# can add a path in front of the file if the result should not be +# written to the html output directory. + +CHM_FILE = + +# If the GENERATE_HTMLHELP tag is set to YES, the HHC_LOCATION tag can +# be used to specify the location (absolute path including file name) of +# the HTML help compiler (hhc.exe). If non-empty doxygen will try to run +# the HTML help compiler on the generated index.hhp. + +HHC_LOCATION = + +# If the GENERATE_HTMLHELP tag is set to YES, the GENERATE_CHI flag +# controls if a separate .chi index file is generated (YES) or that +# it should be included in the master .chm file (NO). + +GENERATE_CHI = NO + +# If the GENERATE_HTMLHELP tag is set to YES, the BINARY_TOC flag +# controls whether a binary table of contents is generated (YES) or a +# normal table of contents (NO) in the .chm file. + +BINARY_TOC = NO + +# The TOC_EXPAND flag can be set to YES to add extra items for group members +# to the contents of the HTML help documentation and to the tree view. + +TOC_EXPAND = NO + +# The DISABLE_INDEX tag can be used to turn on/off the condensed index at +# top of each HTML page. The value NO (the default) enables the index and +# the value YES disables it. + +DISABLE_INDEX = NO + +# This tag can be used to set the number of enum values (range [1..20]) +# that doxygen will group on one line in the generated HTML documentation. + +ENUM_VALUES_PER_LINE = 4 + +# If the GENERATE_TREEVIEW tag is set to YES, a side panel will be +# generated containing a tree-like index structure (just like the one that +# is generated for HTML Help). For this to work a browser that supports +# JavaScript, DHTML, CSS and frames is required (for instance Mozilla 1.0+, +# Netscape 6.0+, Internet explorer 5.0+, or Konqueror). Windows users are +# probably better off using the HTML help feature. + +GENERATE_TREEVIEW = NO + +# If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be +# used to set the initial width (in pixels) of the frame in which the tree +# is shown. + +TREEVIEW_WIDTH = 250 + +#--------------------------------------------------------------------------- +# configuration options related to the LaTeX output +#--------------------------------------------------------------------------- + +# If the GENERATE_LATEX tag is set to YES (the default) Doxygen will +# generate Latex output. + +GENERATE_LATEX = NO + +# The LATEX_OUTPUT tag is used to specify where the LaTeX docs will be put. +# If a relative path is entered the value of OUTPUT_DIRECTORY will be +# put in front of it. If left blank `latex' will be used as the default path. + +LATEX_OUTPUT = latex + +# The LATEX_CMD_NAME tag can be used to specify the LaTeX command name to be +# invoked. If left blank `latex' will be used as the default command name. + +LATEX_CMD_NAME = latex + +# The MAKEINDEX_CMD_NAME tag can be used to specify the command name to +# generate index for LaTeX. If left blank `makeindex' will be used as the +# default command name. + +MAKEINDEX_CMD_NAME = makeindex + +# If the COMPACT_LATEX tag is set to YES Doxygen generates more compact +# LaTeX documents. This may be useful for small projects and may help to +# save some trees in general. + +COMPACT_LATEX = NO + +# The PAPER_TYPE tag can be used to set the paper type that is used +# by the printer. Possible values are: a4, a4wide, letter, legal and +# executive. If left blank a4wide will be used. + +PAPER_TYPE = a4wide + +# The EXTRA_PACKAGES tag can be to specify one or more names of LaTeX +# packages that should be included in the LaTeX output. + +EXTRA_PACKAGES = + +# The LATEX_HEADER tag can be used to specify a personal LaTeX header for +# the generated latex document. The header should contain everything until +# the first chapter. If it is left blank doxygen will generate a +# standard header. Notice: only use this tag if you know what you are doing! + +LATEX_HEADER = + +# If the PDF_HYPERLINKS tag is set to YES, the LaTeX that is generated +# is prepared for conversion to pdf (using ps2pdf). The pdf file will +# contain links (just like the HTML output) instead of page references +# This makes the output suitable for online browsing using a pdf viewer. + +PDF_HYPERLINKS = NO + +# If the USE_PDFLATEX tag is set to YES, pdflatex will be used instead of +# plain latex in the generated Makefile. Set this option to YES to get a +# higher quality PDF documentation. + +USE_PDFLATEX = NO + +# If the LATEX_BATCHMODE tag is set to YES, doxygen will add the \\batchmode. +# command to the generated LaTeX files. This will instruct LaTeX to keep +# running if errors occur, instead of asking the user for help. +# This option is also used when generating formulas in HTML. + +LATEX_BATCHMODE = NO + +# If LATEX_HIDE_INDICES is set to YES then doxygen will not +# include the index chapters (such as File Index, Compound Index, etc.) +# in the output. + +LATEX_HIDE_INDICES = NO + +#--------------------------------------------------------------------------- +# configuration options related to the RTF output +#--------------------------------------------------------------------------- + +# If the GENERATE_RTF tag is set to YES Doxygen will generate RTF output +# The RTF output is optimized for Word 97 and may not look very pretty with +# other RTF readers or editors. + +GENERATE_RTF = NO + +# The RTF_OUTPUT tag is used to specify where the RTF docs will be put. +# If a relative path is entered the value of OUTPUT_DIRECTORY will be +# put in front of it. If left blank `rtf' will be used as the default path. + +RTF_OUTPUT = rtf + +# If the COMPACT_RTF tag is set to YES Doxygen generates more compact +# RTF documents. This may be useful for small projects and may help to +# save some trees in general. + +COMPACT_RTF = NO + +# If the RTF_HYPERLINKS tag is set to YES, the RTF that is generated +# will contain hyperlink fields. The RTF file will +# contain links (just like the HTML output) instead of page references. +# This makes the output suitable for online browsing using WORD or other +# programs which support those fields. +# Note: wordpad (write) and others do not support links. + +RTF_HYPERLINKS = NO + +# Load stylesheet definitions from file. Syntax is similar to doxygen's +# config file, i.e. a series of assignments. You only have to provide +# replacements, missing definitions are set to their default value. + +RTF_STYLESHEET_FILE = + +# Set optional variables used in the generation of an rtf document. +# Syntax is similar to doxygen's config file. + +RTF_EXTENSIONS_FILE = + +#--------------------------------------------------------------------------- +# configuration options related to the man page output +#--------------------------------------------------------------------------- + +# If the GENERATE_MAN tag is set to YES (the default) Doxygen will +# generate man pages + +GENERATE_MAN = NO + +# The MAN_OUTPUT tag is used to specify where the man pages will be put. +# If a relative path is entered the value of OUTPUT_DIRECTORY will be +# put in front of it. If left blank `man' will be used as the default path. + +MAN_OUTPUT = man + +# The MAN_EXTENSION tag determines the extension that is added to +# the generated man pages (default is the subroutine's section .3) + +MAN_EXTENSION = .3 + +# If the MAN_LINKS tag is set to YES and Doxygen generates man output, +# then it will generate one additional man file for each entity +# documented in the real man page(s). These additional files +# only source the real man page, but without them the man command +# would be unable to find the correct page. The default is NO. + +MAN_LINKS = NO + +#--------------------------------------------------------------------------- +# configuration options related to the XML output +#--------------------------------------------------------------------------- + +# If the GENERATE_XML tag is set to YES Doxygen will +# generate an XML file that captures the structure of +# the code including all documentation. + +GENERATE_XML = NO + +# The XML_OUTPUT tag is used to specify where the XML pages will be put. +# If a relative path is entered the value of OUTPUT_DIRECTORY will be +# put in front of it. If left blank `xml' will be used as the default path. + +XML_OUTPUT = xml + +# The XML_SCHEMA tag can be used to specify an XML schema, +# which can be used by a validating XML parser to check the +# syntax of the XML files. + +XML_SCHEMA = + +# The XML_DTD tag can be used to specify an XML DTD, +# which can be used by a validating XML parser to check the +# syntax of the XML files. + +XML_DTD = + +# If the XML_PROGRAMLISTING tag is set to YES Doxygen will +# dump the program listings (including syntax highlighting +# and cross-referencing information) to the XML output. Note that +# enabling this will significantly increase the size of the XML output. + +XML_PROGRAMLISTING = YES + +#--------------------------------------------------------------------------- +# configuration options for the AutoGen Definitions output +#--------------------------------------------------------------------------- + +# If the GENERATE_AUTOGEN_DEF tag is set to YES Doxygen will +# generate an AutoGen Definitions (see autogen.sf.net) file +# that captures the structure of the code including all +# documentation. Note that this feature is still experimental +# and incomplete at the moment. + +GENERATE_AUTOGEN_DEF = NO + +#--------------------------------------------------------------------------- +# configuration options related to the Perl module output +#--------------------------------------------------------------------------- + +# If the GENERATE_PERLMOD tag is set to YES Doxygen will +# generate a Perl module file that captures the structure of +# the code including all documentation. Note that this +# feature is still experimental and incomplete at the +# moment. + +GENERATE_PERLMOD = NO + +# If the PERLMOD_LATEX tag is set to YES Doxygen will generate +# the necessary Makefile rules, Perl scripts and LaTeX code to be able +# to generate PDF and DVI output from the Perl module output. + +PERLMOD_LATEX = NO + +# If the PERLMOD_PRETTY tag is set to YES the Perl module output will be +# nicely formatted so it can be parsed by a human reader. This is useful +# if you want to understand what is going on. On the other hand, if this +# tag is set to NO the size of the Perl module output will be much smaller +# and Perl will parse it just the same. + +PERLMOD_PRETTY = YES + +# The names of the make variables in the generated doxyrules.make file +# are prefixed with the string contained in PERLMOD_MAKEVAR_PREFIX. +# This is useful so different doxyrules.make files included by the same +# Makefile don't overwrite each other's variables. + +PERLMOD_MAKEVAR_PREFIX = + +#--------------------------------------------------------------------------- +# Configuration options related to the preprocessor +#--------------------------------------------------------------------------- + +# If the ENABLE_PREPROCESSING tag is set to YES (the default) Doxygen will +# evaluate all C-preprocessor directives found in the sources and include +# files. + +ENABLE_PREPROCESSING = YES + +# If the MACRO_EXPANSION tag is set to YES Doxygen will expand all macro +# names in the source code. If set to NO (the default) only conditional +# compilation will be performed. Macro expansion can be done in a controlled +# way by setting EXPAND_ONLY_PREDEF to YES. + +MACRO_EXPANSION = NO + +# If the EXPAND_ONLY_PREDEF and MACRO_EXPANSION tags are both set to YES +# then the macro expansion is limited to the macros specified with the +# PREDEFINED and EXPAND_AS_PREDEFINED tags. + +EXPAND_ONLY_PREDEF = NO + +# If the SEARCH_INCLUDES tag is set to YES (the default) the includes files +# in the INCLUDE_PATH (see below) will be search if a #include is found. + +SEARCH_INCLUDES = YES + +# The INCLUDE_PATH tag can be used to specify one or more directories that +# contain include files that are not input files but should be processed by +# the preprocessor. + +INCLUDE_PATH = + +# You can use the INCLUDE_FILE_PATTERNS tag to specify one or more wildcard +# patterns (like *.h and *.hpp) to filter out the header-files in the +# directories. If left blank, the patterns specified with FILE_PATTERNS will +# be used. + +INCLUDE_FILE_PATTERNS = + +# The PREDEFINED tag can be used to specify one or more macro names that +# are defined before the preprocessor is started (similar to the -D option of +# gcc). The argument of the tag is a list of macros of the form: name +# or name=definition (no spaces). If the definition and the = are +# omitted =1 is assumed. + +PREDEFINED = + +# If the MACRO_EXPANSION and EXPAND_ONLY_PREDEF tags are set to YES then +# this tag can be used to specify a list of macro names that should be expanded. +# The macro definition that is found in the sources will be used. +# Use the PREDEFINED tag if you want to use a different macro definition. + +EXPAND_AS_DEFINED = + +# If the SKIP_FUNCTION_MACROS tag is set to YES (the default) then +# doxygen's preprocessor will remove all function-like macros that are alone +# on a line, have an all uppercase name, and do not end with a semicolon. Such +# function macros are typically used for boiler-plate code, and will confuse the +# parser if not removed. + +SKIP_FUNCTION_MACROS = YES + +#--------------------------------------------------------------------------- +# Configuration::addtions related to external references +#--------------------------------------------------------------------------- + +# The TAGFILES option can be used to specify one or more tagfiles. +# Optionally an initial location of the external documentation +# can be added for each tagfile. The format of a tag file without +# this location is as follows: +# TAGFILES = file1 file2 ... +# Adding location for the tag files is done as follows: +# TAGFILES = file1=loc1 "file2 = loc2" ... +# where "loc1" and "loc2" can be relative or absolute paths or +# URLs. If a location is present for each tag, the installdox tool +# does not have to be run to correct the links. +# Note that each tag file must have a unique name +# (where the name does NOT include the path) +# If a tag file is not located in the directory in which doxygen +# is run, you must also specify the path to the tagfile here. + +TAGFILES = + +# When a file name is specified after GENERATE_TAGFILE, doxygen will create +# a tag file that is based on the input files it reads. + +GENERATE_TAGFILE = + +# If the ALLEXTERNALS tag is set to YES all external classes will be listed +# in the class index. If set to NO only the inherited external classes +# will be listed. + +ALLEXTERNALS = NO + +# If the EXTERNAL_GROUPS tag is set to YES all external groups will be listed +# in the modules index. If set to NO, only the current project's groups will +# be listed. + +EXTERNAL_GROUPS = YES + +# The PERL_PATH should be the absolute path and name of the perl script +# interpreter (i.e. the result of `which perl'). + +PERL_PATH = /usr/bin/perl + +#--------------------------------------------------------------------------- +# Configuration options related to the dot tool +#--------------------------------------------------------------------------- + +# If the CLASS_DIAGRAMS tag is set to YES (the default) Doxygen will +# generate a inheritance diagram (in HTML, RTF and LaTeX) for classes with base or +# super classes. Setting the tag to NO turns the diagrams off. Note that this +# option is superseded by the HAVE_DOT option below. This is only a fallback. It is +# recommended to install and use dot, since it yields more powerful graphs. + +CLASS_DIAGRAMS = YES + +# If set to YES, the inheritance and collaboration graphs will hide +# inheritance and usage relations if the target is undocumented +# or is not a class. + +HIDE_UNDOC_RELATIONS = YES + +# If you set the HAVE_DOT tag to YES then doxygen will assume the dot tool is +# available from the path. This tool is part of Graphviz, a graph visualization +# toolkit from AT&T and Lucent Bell Labs. The other options in this section +# have no effect if this option is set to NO (the default) + +HAVE_DOT = YES + +# If the CLASS_GRAPH and HAVE_DOT tags are set to YES then doxygen +# will generate a graph for each documented class showing the direct and +# indirect inheritance relations. Setting this tag to YES will force the +# the CLASS_DIAGRAMS tag to NO. + +CLASS_GRAPH = YES + +# If the COLLABORATION_GRAPH and HAVE_DOT tags are set to YES then doxygen +# will generate a graph for each documented class showing the direct and +# indirect implementation dependencies (inheritance, containment, and +# class references variables) of the class with other documented classes. + +COLLABORATION_GRAPH = YES + +# If the UML_LOOK tag is set to YES doxygen will generate inheritance and +# collaboration diagrams in a style similar to the OMG's Unified Modeling +# Language. + +UML_LOOK = YES + +# If set to YES, the inheritance and collaboration graphs will show the +# relations between templates and their instances. + +TEMPLATE_RELATIONS = NO + +# If the ENABLE_PREPROCESSING, SEARCH_INCLUDES, INCLUDE_GRAPH, and HAVE_DOT +# tags are set to YES then doxygen will generate a graph for each documented +# file showing the direct and indirect include dependencies of the file with +# other documented files. + +INCLUDE_GRAPH = YES + +# If the ENABLE_PREPROCESSING, SEARCH_INCLUDES, INCLUDED_BY_GRAPH, and +# HAVE_DOT tags are set to YES then doxygen will generate a graph for each +# documented header file showing the documented files that directly or +# indirectly include this file. + +INCLUDED_BY_GRAPH = YES + +# If the CALL_GRAPH and HAVE_DOT tags are set to YES then doxygen will +# generate a call dependency graph for every global function or class method. +# Note that enabling this option will significantly increase the time of a run. +# So in most cases it will be better to enable call graphs for selected +# functions only using the \callgraph command. + +CALL_GRAPH = YES + +# If the GRAPHICAL_HIERARCHY and HAVE_DOT tags are set to YES then doxygen +# will graphical hierarchy of all classes instead of a textual one. + +GRAPHICAL_HIERARCHY = YES + +# The DOT_IMAGE_FORMAT tag can be used to set the image format of the images +# generated by dot. Possible values are png, jpg, or gif +# If left blank png will be used. + +DOT_IMAGE_FORMAT = png + +# The tag DOT_PATH can be used to specify the path where the dot tool can be +# found. If left blank, it is assumed the dot tool can be found on the path. + +DOT_PATH = + +# The DOTFILE_DIRS tag can be used to specify one or more directories that +# contain dot files that are included in the documentation (see the +# \dotfile command). + +DOTFILE_DIRS = + +# The MAX_DOT_GRAPH_WIDTH tag can be used to set the maximum allowed width +# (in pixels) of the graphs generated by dot. If a graph becomes larger than +# this value, doxygen will try to truncate the graph, so that it fits within +# the specified constraint. Beware that most browsers cannot cope with very +# large images. + +MAX_DOT_GRAPH_WIDTH = 1024 + +# The MAX_DOT_GRAPH_HEIGHT tag can be used to set the maximum allows height +# (in pixels) of the graphs generated by dot. If a graph becomes larger than +# this value, doxygen will try to truncate the graph, so that it fits within +# the specified constraint. Beware that most browsers cannot cope with very +# large images. + +MAX_DOT_GRAPH_HEIGHT = 1024 + +# The MAX_DOT_GRAPH_DEPTH tag can be used to set the maximum depth of the +# graphs generated by dot. A depth value of 3 means that only nodes reachable +# from the root by following a path via at most 3 edges will be shown. Nodes that +# lay further from the root node will be omitted. Note that setting this option to +# 1 or 2 may greatly reduce the computation time needed for large code bases. Also +# note that a graph may be further truncated if the graph's image dimensions are +# not sufficient to fit the graph (see MAX_DOT_GRAPH_WIDTH and MAX_DOT_GRAPH_HEIGHT). +# If 0 is used for the depth value (the default), the graph is not depth-constrained. + +MAX_DOT_GRAPH_DEPTH = 0 + +# If the GENERATE_LEGEND tag is set to YES (the default) Doxygen will +# generate a legend page explaining the meaning of the various boxes and +# arrows in the dot generated graphs. + +GENERATE_LEGEND = YES + +# If the DOT_CLEANUP tag is set to YES (the default) Doxygen will +# remove the intermediate dot files that are used to generate +# the various graphs. + +DOT_CLEANUP = YES + +#--------------------------------------------------------------------------- +# Configuration::addtions related to the search engine +#--------------------------------------------------------------------------- + +# The SEARCHENGINE tag specifies whether or not a search engine should be +# used. If set to NO the values of all tags below this one will be ignored. + +SEARCHENGINE = NO diff --git a/fsa/doc/docbook/.gitignore b/fsa/doc/docbook/.gitignore new file mode 100644 index 00000000000..56d5bd4fda9 --- /dev/null +++ b/fsa/doc/docbook/.gitignore @@ -0,0 +1,4 @@ +*.1 +*.html +manpage.links +manpage.refs diff --git a/fsa/doc/docbook/fsadump.xml b/fsa/doc/docbook/fsadump.xml new file mode 100644 index 00000000000..c4a72a157a2 --- /dev/null +++ b/fsa/doc/docbook/fsadump.xml @@ -0,0 +1,205 @@ + + + + + +fsadump +1 + + + +fsadump +dump the contents of finite state automata files + + + + + fsadump + OPTIONS + fsa_file + + + + +Description + +fsadump dumps the contents of fsa files to standard +out in one of several different formats (some of which can be directly +used as input for makefsa). + +Options + + + + + + +text output format, with empty meta info (default) + + + + + + + +text output format + + + + + + + +binary output format, with base64 encoded meta info + + + + + + + +binary output format with raw meta info + + + + + + + +text ouptut with numerical meta info + + + + + + + +text output format, with the perfect hash value instead of meta info + + + + + + + +dot output format (for visualization using graphviz) + + + + + + + +display usage help + + + + + + + +display version number + + + + + + + + + +Output formats + + + +Text output format with empty meta info () + + +The input strings are terminated with '\n', and may not contain '\0', +'\0xff' or '\n' characters. This is the default. + + + + +Text output format () + + +Lines are terminated with '\n', input string and meta info are +separated by '\t'. Input and meta strings may not contain '\0', +'\0xff', '\n' or '\t' characters. A terminating '\0' (if found) is +removed from the end of the meta info. + + + + +Text output format with numerical info () + + +Lines are terminated with '\n', input string and meta info are +separated by '\t'. Input strings may not contain '\0', '\0xff', '\n' +or '\t' characters. Meta strings are unsigned integers ([0-9]+), which +will be are retrieved from the binary representation in the +automaton. Valid data sizes are 1, 2 or 4 bytes, for sizes other than +these only the first 2 or 4 bytes are used. + + + + +Binary output format, with base64 encoded meta info () + + +Both the input string and meta info are terminated by '\0'. The input +string must not contain the reserved characters '\0' and '\0xff'. The +meta info is base64 encoded, as it may contain any character. + + + + +Binary output format with raw meta info () + + +Both the input string and meta info are terminated by '\0'. The input +string must not contain the reserved characters '\0' and '\0xff'. The +meta info must not contain '\0'. + + + + +Text output format, with the perfect hash value instead of meta +info () + + +The format is the same as for text output with numerical info, but the +perfect hash value for each string is used instead of meta info. + + + + +Dot output format for visualization using GraphViz () + + +Output a dot format graph, with the start and final states marked and +edges labeled with transition symbols. The dot tool +can be used to generate graphical output (e.g. PostScript) of the +graph. Use this format for small automata only (a few hundred states +or less), as the graph soon becomes quite complex. + + + + + + + +See also + +makefsa, fsainfo. + + + +Author + +Written by Peter Boros. + + + + diff --git a/fsa/doc/docbook/fsainfo.xml b/fsa/doc/docbook/fsainfo.xml new file mode 100644 index 00000000000..d0315b112ba --- /dev/null +++ b/fsa/doc/docbook/fsainfo.xml @@ -0,0 +1,177 @@ + + + + + +fsainfo +1 + + + +fsainfo +display information about finite state automata files + + + + + fsainfo + OPTIONS + fsa_file + + + + +Description + +fsainfo displays information about fsa files, +mainly based on the fsa header. In addition, +fsainfo tries to load the fsa file and reports +whether loading succeeded. The following information is presented: + + + + +Header size + + +Size of the fsa header (usually 256 bytes). + + + + +Magic + + +Magic number identifying fsa files (2038637673). Files with wrong +magic will not be attempted to load. + + + + +Version + + +Version of the fsa library used for building the fsa file (e.g. 1.0.2). + + + + +Serial number + + +Serial number of the fsa file. + + + + +Checksum + + +Checksum for verifying the integrity of the fsa file. If the checksum +verification fails, the fsa file will refuse to load. + + + + +FSA size + + +Size of the automaton (in number of cells and bytes). + + + + +Start state + + +Index of the start state. + + + + +Data size + + +Size of data storage used for storing meta information for final states. + + + + +Data item type + + +Type of meta data items (fixed or variable size). + + + + +Fixed item size + + +Size of meta data items, if fixed size. + + + + +Perfect hash + + +Indication whether the fsa was built with perfect hash (yes/no). + + + + +Perfect hash size + + +Perfect hash size, if the fsa was built with perfect hash. + + + + +Total size + + +Full size of the fsa file (header + automaton + meta data + perfect hash). + + + + + +Options + + + + + + +display usage help + + + + + + + +display version number + + + + + + + + +See also + +makefsa, fsadump. + + + +Author + +Written by Peter Boros. + + + + diff --git a/fsa/doc/docbook/makefsa.xml b/fsa/doc/docbook/makefsa.xml new file mode 100644 index 00000000000..4673b06f78d --- /dev/null +++ b/fsa/doc/docbook/makefsa.xml @@ -0,0 +1,224 @@ + + + + + +makefsa +1 + + + +makefsa +create finite state automata files from text or binary input + + + + + makefsa + OPTIONS + input_file + fsa_file + + + + +Description + +makefsa creates a finite state automaton file from +text or binary input. If is not specified, +standard input is used. The input must be sorted and must not contain +duplicate input strings (unsorted or duplicate entries will be +ignored). + +Options + + + + + + +use text input format, with empty meta info (default) + + + + + + + +use text input format + + + + + + + +use binary input format, with base64 encoded meta info + + + + + + + +use binary input format with raw meta info + + + + + + + +use text input with numerical meta info + + + + + + + +data size for numerical meta info (default=4) + + + + + + + +ignore meta info regardless of input format + + + + + + + +build the automaton with a perfect hash + + + + + + + +set serial number of automaton (default=0) + + + + + + + +be verbose, display progress information and statistics + + + + + + + +display usage help + + + + + + + +display version number + + + + + + + + + +Input formats + + + +Text input format with empty meta info () + + +The input strings are terminated with '\n', and may not contain '\0', +'\0xff' or '\n' characters. This is the default. + + + + +Text input format () + + +Input lines are terminated with '\n', input string and meta info are +separated by '\t'. Input and meta strings may not contain '\0', +'\0xff', '\n' or '\t' characters. A terminating '\0' is added to the +meta info when stored in the automaton. + + + + +Text input format with numerical info () + + +Input lines are terminated with '\n', input string and meta info are +separated by '\t'. Input strings may not contain '\0', '\0xff', '\n' +or '\t' characters. Meta strings are unsigned integers ([0-9]+), which +will be stored in binary representation in the automaton. The size of +the data can be controlled by the option, valid +values are 1, 2 or 4 bytes, correcponding to uint8_t, uint16_t and +uint32_t, respectively. (Default is 4 bytes.) + + + + +Binary input format, with base64 encoded meta info () + + +Both the input string and meta info are terminated by '\0'. The input +string must not contain the reserved characters '\0' and '\0xff'. The +meta info is base64 encoded, as it may contain any character. + + + + +Binary input format with raw meta info () + + +Both the input string and meta info are terminated by '\0'. The input +string must not contain the reserved characters '\0' and '\0xff'. The +meta info must not contain '\0'. + + + + + + + +Perfect hashes + +Automata built with perfect hash (() will contain +an additional data structure which provides a mapping from the strings +stored in the automaton to unique integers in the range [0,n-1] where +n is the number of accepted strings. The size of the fsa file will +increase by up to 80%. Lookup time is slightly longer if the hash +value needs to be retrieved (but still O(m), where m is the length of +the input). Reverse lookup is also possible, though it is more +expensive (also O(m), but with a much higher constant). + + + +See also + +fsainfo, fsadump. + + + +Author + +Written by Peter Boros. + + + + diff --git a/fsa/doc/fsa_file_format.html b/fsa/doc/fsa_file_format.html new file mode 100644 index 00000000000..077edd627c3 --- /dev/null +++ b/fsa/doc/fsa_file_format.html @@ -0,0 +1,69 @@ + + + +fsa file format + + +

fsa file format

+ + + + + + +
header256 bytes
symbol tablesize bytes
state tablesize*4 bytes
data tabledata_size bytes
perfect hahs table (optional)size*4 bytes
+ +

header

+ + + + + + + + + + + + + +
fieldoffsetsizedescrption
magic04 (uint32)Magic number (0x79832469)
version44 (uint32)Version number of +the fsa library used for building this fsa
checksum84 (uint32)Checksum
size124 (uint32)Size of fsa (cells)
start164 (uint32)Start state
data_size204 (uint32)Size of data (bytes)
data_type244 (uint32)Type of data +items (0=variable size, 1=fixed size)
fixed_data_size284 (uint32)Data item size if fixed
has_perfect_hash324 +(uint32)Indicator for perfect hash (0=no, 1=yes)
serial364 (uint32)Serial number
reserved40216 (54*uint32)Reserved (pads size to 256 bytes)
+ +

symbol table and state table

+The symbol table and state table contain the transitions of the +automaton, each 1-byte entry in the symbol table corresponds to an +uint32 entry in the state table. For each state, a list of at most 254 +transistions is stored, as the symbol set is 8-bit characters, with +0x00 and 0xff reserved. Each state id is in fact an offset into these +tables. For a given state state, there exists a valid +transition for symbol sym if the symbol table contains +sym at offset state+sym. 0x00 means the +cell is empty, 0xff is a special symbol meaning that the given state +is a final state, anything else means invalid transition (i.e. the +cell is in use by some other state). For valid transitions, the +corresponding entry in the state table yields the next state. For 0xff +transitions, the state table entry contains the offset of the date +item within the data store. + +

data store

+The data store contains the data items for the final states. The 'new +state' entry of a final state transition in the state table (corresponding to the +special final state symbol 0xff) contains the data store offset of the data item +corresponding to that final state. If fixed size items are used, each +item takes fixed_data_size bytes as defined in the header. Variable +size items take 4 bytes (uint32 item_size) plus item_size +bytes. The size of the data store is given in the header. + +

perfect hash table

+The perfect hash table has one uint32 entry for each transition in the +symbol/state table, thus the size of the perfect hash table equals the +size of the state table. The perfect hash value for a final state is +calculated by adding all values in this table for the transitions +along the path from the start state to the final state. + + + + diff --git a/fsa/doc/permute_query.stats b/fsa/doc/permute_query.stats new file mode 100644 index 00000000000..3515bb9a631 --- /dev/null +++ b/fsa/doc/permute_query.stats @@ -0,0 +1,18 @@ + +Statistics: + + Empty or single term: 6815022 5.6768% + Too long: 864794 0.7204% + Length 2 (grams 1): 27184017 22.6438% + Length 3 (grams 4): 32461067 27.0395% + Length 4 (grams 11): 24369083 20.2990% + Length 5 (grams 26): 14157811 11.7932% + Length 6 (grams 57): 7269208 6.0551% + Length 7 (grams 119): 3612039 3.0088% + Length 8 (grams 238): 1822986 1.5185% + Length 9 (grams 456): 962163 0.8015% + Length 10 (grams 837): 532530 0.4436% + Total: 120050720 + +Average number of grams per query: 24.62 + -- cgit v1.2.3