'\" '\" Generated from file 'pt_pgen\&.man' by tcllib/doctools with format 'nroff' '\" Copyright (c) 2009 Andreas Kupries '\" .TH "pt::pgen" 3tcl 1\&.1 tcllib "Parser Tools" .\" The -*- nroff -*- definitions below are for supplemental macros used .\" in Tcl/Tk manual entries. .\" .\" .AP type name in/out ?indent? .\" Start paragraph describing an argument to a library procedure. .\" type is type of argument (int, etc.), in/out is either "in", "out", .\" or "in/out" to describe whether procedure reads or modifies arg, .\" and indent is equivalent to second arg of .IP (shouldn't ever be .\" needed; use .AS below instead) .\" .\" .AS ?type? ?name? .\" Give maximum sizes of arguments for setting tab stops. Type and .\" name are examples of largest possible arguments that will be passed .\" to .AP later. If args are omitted, default tab stops are used. .\" .\" .BS .\" Start box enclosure. From here until next .BE, everything will be .\" enclosed in one large box. .\" .\" .BE .\" End of box enclosure. .\" .\" .CS .\" Begin code excerpt. .\" .\" .CE .\" End code excerpt. .\" .\" .VS ?version? ?br? .\" Begin vertical sidebar, for use in marking newly-changed parts .\" of man pages. The first argument is ignored and used for recording .\" the version when the .VS was added, so that the sidebars can be .\" found and removed when they reach a certain age. If another argument .\" is present, then a line break is forced before starting the sidebar. .\" .\" .VE .\" End of vertical sidebar. .\" .\" .DS .\" Begin an indented unfilled display. .\" .\" .DE .\" End of indented unfilled display. .\" .\" .SO ?manpage? .\" Start of list of standard options for a Tk widget. The manpage .\" argument defines where to look up the standard options; if .\" omitted, defaults to "options". The options follow on successive .\" lines, in three columns separated by tabs. .\" .\" .SE .\" End of list of standard options for a Tk widget. .\" .\" .OP cmdName dbName dbClass .\" Start of description of a specific option. cmdName gives the .\" option's name as specified in the class command, dbName gives .\" the option's name in the option database, and dbClass gives .\" the option's class in the option database. .\" .\" .UL arg1 arg2 .\" Print arg1 underlined, then print arg2 normally. .\" .\" .QW arg1 ?arg2? .\" Print arg1 in quotes, then arg2 normally (for trailing punctuation). .\" .\" .PQ arg1 ?arg2? .\" Print an open parenthesis, arg1 in quotes, then arg2 normally .\" (for trailing punctuation) and then a closing parenthesis. .\" .\" # Set up traps and other miscellaneous stuff for Tcl/Tk man pages. .if t .wh -1.3i ^B .nr ^l \n(.l .ad b .\" # Start an argument description .de AP .ie !"\\$4"" .TP \\$4 .el \{\ . ie !"\\$2"" .TP \\n()Cu . el .TP 15 .\} .ta \\n()Au \\n()Bu .ie !"\\$3"" \{\ \&\\$1 \\fI\\$2\\fP (\\$3) .\".b .\} .el \{\ .br .ie !"\\$2"" \{\ \&\\$1 \\fI\\$2\\fP .\} .el \{\ \&\\fI\\$1\\fP .\} .\} .. .\" # define tabbing values for .AP .de AS .nr )A 10n .if !"\\$1"" .nr )A \\w'\\$1'u+3n .nr )B \\n()Au+15n .\" .if !"\\$2"" .nr )B \\w'\\$2'u+\\n()Au+3n .nr )C \\n()Bu+\\w'(in/out)'u+2n .. .AS Tcl_Interp Tcl_CreateInterp in/out .\" # BS - start boxed text .\" # ^y = starting y location .\" # ^b = 1 .de BS .br .mk ^y .nr ^b 1u .if n .nf .if n .ti 0 .if n \l'\\n(.lu\(ul' .if n .fi .. .\" # BE - end boxed text (draw box now) .de BE .nf .ti 0 .mk ^t .ie n \l'\\n(^lu\(ul' .el \{\ .\" Draw four-sided box normally, but don't draw top of .\" box if the box started on an earlier page. .ie !\\n(^b-1 \{\ \h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul' .\} .el \}\ \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul' .\} .\} .fi .br .nr ^b 0 .. .\" # VS - start vertical sidebar .\" # ^Y = starting y location .\" # ^v = 1 (for troff; for nroff this doesn't matter) .de VS .if !"\\$2"" .br .mk ^Y .ie n 'mc \s12\(br\s0 .el .nr ^v 1u .. .\" # VE - end of vertical sidebar .de VE .ie n 'mc .el \{\ .ev 2 .nf .ti 0 .mk ^t \h'|\\n(^lu+3n'\L'|\\n(^Yu-1v\(bv'\v'\\n(^tu+1v-\\n(^Yu'\h'-|\\n(^lu+3n' .sp -1 .fi .ev .\} .nr ^v 0 .. .\" # Special macro to handle page bottom: finish off current .\" # box/sidebar if in box/sidebar mode, then invoked standard .\" # page bottom macro. .de ^B .ev 2 'ti 0 'nf .mk ^t .if \\n(^b \{\ .\" Draw three-sided box if this is the box's first page, .\" draw two sides but no top otherwise. .ie !\\n(^b-1 \h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c .el \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c .\} .if \\n(^v \{\ .nr ^x \\n(^tu+1v-\\n(^Yu \kx\h'-\\nxu'\h'|\\n(^lu+3n'\ky\L'-\\n(^xu'\v'\\n(^xu'\h'|0u'\c .\} .bp 'fi .ev .if \\n(^b \{\ .mk ^y .nr ^b 2 .\} .if \\n(^v \{\ .mk ^Y .\} .. .\" # DS - begin display .de DS .RS .nf .sp .. .\" # DE - end display .de DE .fi .RE .sp .. .\" # SO - start of list of standard options .de SO 'ie '\\$1'' .ds So \\fBoptions\\fR 'el .ds So \\fB\\$1\\fR .SH "STANDARD OPTIONS" .LP .nf .ta 5.5c 11c .ft B .. .\" # SE - end of list of standard options .de SE .fi .ft R .LP See the \\*(So manual entry for details on the standard options. .. .\" # OP - start of full description for a single option .de OP .LP .nf .ta 4c Command-Line Name: \\fB\\$1\\fR Database Name: \\fB\\$2\\fR Database Class: \\fB\\$3\\fR .fi .IP .. .\" # CS - begin code excerpt .de CS .RS .nf .ta .25i .5i .75i 1i .. .\" # CE - end code excerpt .de CE .fi .RE .. .\" # UL - underline word .de UL \\$1\l'|0\(ul'\\$2 .. .\" # QW - apply quotation marks to word .de QW .ie '\\*(lq'"' ``\\$1''\\$2 .\"" fix emacs highlighting .el \\*(lq\\$1\\*(rq\\$2 .. .\" # PQ - apply parens and quotation marks to word .de PQ .ie '\\*(lq'"' (``\\$1''\\$2)\\$3 .\"" fix emacs highlighting .el (\\*(lq\\$1\\*(rq\\$2)\\$3 .. .\" # QR - quoted range .de QR .ie '\\*(lq'"' ``\\$1''\\-``\\$2''\\$3 .\"" fix emacs highlighting .el \\*(lq\\$1\\*(rq\\-\\*(lq\\$2\\*(rq\\$3 .. .\" # MT - "empty" string .de MT .QW "" .. .BS .SH NAME pt::pgen \- Parser Generator .SH SYNOPSIS package require \fBTcl 8\&.5\fR .sp package require \fBpt::pgen ?1\&.1?\fR .sp \fB::pt::pgen\fR \fIinputformat\fR \fItext\fR \fIresultformat\fR ?\fIoptions\&.\&.\&.\fR? .sp .BE .SH DESCRIPTION .PP Are you lost ? Do you have trouble understanding this document ? In that case please read the overview provided by the \fIIntroduction to Parser Tools\fR\&. This document is the entrypoint to the whole system the current package is a part of\&. .PP This package provides a command implementing a \fIparser generator\fR taking parsing expression grammars as input\&. .PP It is the implementation of method \fBgenerate\fR of \fBpt\fR, the \fIParser Tools Application\fR\&. .PP As such the intended audience of this document are people wishing to modify and/or extend this part of \fBpt\fR's functionality\&. Users of \fBpt\fR on the other hand are hereby refered to the applications' manpage, i\&.e\&. \fIParser Tools Application\fR\&. .PP It resides in the User Package Layer of Parser Tools\&. .PP IMAGE: arch_user_pkg .PP .SH API .TP \fB::pt::pgen\fR \fIinputformat\fR \fItext\fR \fIresultformat\fR ?\fIoptions\&.\&.\&.\fR? This command takes the parsing expression grammar in \fItext\fR (in the format specified by \fIinputformat\fR), and returns the same grammar in the format \fIresultformat\fR as the result of the command\&. .sp The two known input formats are \fBpeg\fR and \fBjson\fR\&. Introductions to them, including their formal specifications, can be found in the \fIPEG Language Tutorial\fR and \fIThe JSON Grammar Exchange Format\fR\&. The packages used to parse these formats are .RS .TP \fBpeg\fR \fBpt::peg::from::peg\fR .TP \fBjson\fR \fBpt::peg::from::json\fR .RE .sp On the output side the known formats, and the packages used to generate them are .RS .TP \fBc\fR \fBpt::peg::to::cparam\fR .TP \fBcontainer\fR \fBpt::peg::to::container\fR .TP \fBcritcl\fR \fBpt::peg::to::cparam\fR + \fBpt::cparam::configuration::critcl\fR .TP \fBjson\fR \fBpt::peg::to::json\fR .TP \fBoo\fR \fBpt::peg::to::tclparam\fR + \fBpt::tclparam::configuration::tcloo\fR .TP \fBpeg\fR \fBpt::peg::to::peg\fR .TP \fBsnit\fR \fBpt::peg::to::tclparam\fR + \fBpt::tclparam::configuration::snit\fR .RE .IP The options supported by each of these formats are documented with their respective packages\&. .PP .SH EXAMPLE In this section we are working a complete example, starting with a PEG grammar and ending with running the parser generated from it over some input, following the outline shown in the figure below: .PP IMAGE: flow .PP Our grammar, assumed to the stored in the file "\fIcalculator\&.peg\fR" is .CS PEG calculator (Expression) Digit <- '0'/'1'/'2'/'3'/'4'/'5'/'6'/'7'/'8'/'9' ; Sign <- '-' / '+' ; Number <- Sign? Digit+ ; Expression <- Term (AddOp Term)* ; MulOp <- '*' / '/' ; Term <- Factor (MulOp Factor)* ; AddOp <- '+'/'-' ; Factor <- '(' Expression ')' / Number ; END; .CE From this we create a snit-based parser using the script "\fIgen\fR" .CS package require Tcl 8\&.5 package require fileutil package require pt::pgen lassign $argv name set grammar [fileutil::cat $name\&.peg] set pclass [pt::pgen peg $gr snit -class $name -file $name\&.peg -name $name] fileutil::writeFile $name\&.tcl $pclass exit 0 .CE calling it like .CS tclsh8\&.5 gen calculator .CE which leaves us with the parser package and class written to the file "\fIcalculator\&.tcl\fR"\&. Assuming that this package is then properly installed in a place where Tcl can find it we can now use this class via a script like .CS package require calculator lassign $argv input set channel [open $input r] set parser [calculator] set ast [$parser parse $channel] $parser destroy close $channel \&.\&.\&. now process the returned abstract syntax tree \&.\&.\&. .CE where the abstract syntax tree stored in the variable will look like .PP .CS set ast {Expression 0 4 {Factor 0 4 {Term 0 2 {Number 0 2 {Digit 0 0} {Digit 1 1} {Digit 2 2} } } {AddOp 3 3} {Term 4 4 {Number 4 4 {Digit 4 4} } } } } .CE .PP assuming that the input file and channel contained the text .CS 120+5 .CE A more graphical representation of the tree would be .PP .PS \&.nf +- Digit 0 0 | 1 | | +- Term 0 2 --- Number 0 2 -+- Digit 1 1 | 2 | | | | +- Digit 2 2 | 0 | | Expression 0 4 --- Factor 0 4 -+----------------------------- AddOp 3 3 | + | | +- Term 4 4 --- Number 4 4 --- Digit 4 4 | 5 \&.fi .PE .PP Regardless, at this point it is the user's responsibility to work with the tree to reach whatever goal she desires\&. I\&.e\&. analyze it, transform it, etc\&. The package \fBpt::ast\fR should be of help here, providing commands to walk such ASTs structures in various ways\&. .PP One important thing to note is that the parsers used here return a data structure representing the structure of the input per the grammar underlying the parser\&. There are \fIno\fR callbacks during the parsing process, i\&.e\&. no \fIparsing actions\fR, as most other parsers will have\&. .PP Going back to the last snippet of code, the execution of the parser for some input, note how the parser instance follows the specified \fIParser API\fR\&. .SH "BUGS, IDEAS, FEEDBACK" This document, and the package it describes, will undoubtedly contain bugs and other problems\&. Please report such in the category \fIpt\fR of the \fITcllib Trackers\fR [http://core\&.tcl\&.tk/tcllib/reportlist]\&. Please also report any ideas for enhancements you may have for either package and/or documentation\&. .PP When proposing code changes, please provide \fIunified diffs\fR, i\&.e the output of \fBdiff -u\fR\&. .PP Note further that \fIattachments\fR are strongly preferred over inlined patches\&. Attachments can be made by going to the \fBEdit\fR form of the ticket immediately after its creation, and then using the left-most button in the secondary navigation bar\&. .SH KEYWORDS EBNF, LL(k), PEG, TDPL, context-free languages, expression, grammar, matching, parser, parsing expression, parsing expression grammar, push down automaton, recursive descent, state, top-down parsing languages, transducer .SH CATEGORY Parsing and Grammars .SH COPYRIGHT .nf Copyright (c) 2009 Andreas Kupries .fi