'\" '\" Generated from file 'docstrip\&.man' by tcllib/doctools with format 'nroff' '\" Copyright (c) 2003–2010 Lars Hellström '\" .TH "docstrip" 3tcl 1\&.2 tcllib "Literate programming tool" .\" 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 docstrip \- Docstrip style source code extraction .SH SYNOPSIS package require \fBTcl 8\&.4\fR .sp package require \fBdocstrip ?1\&.2?\fR .sp \fBdocstrip::extract\fR \fItext\fR \fIterminals\fR ?\fIoption\fR \fIvalue\fR \&.\&.\&.? .sp \fBdocstrip::sourcefrom\fR \fIfilename\fR \fIterminals\fR ?\fIoption\fR \fIvalue\fR \&.\&.\&.? .sp .BE .SH DESCRIPTION \fBDocstrip\fR is a tool created to support a brand of Literate Programming\&. It is most common in the (La)TeX community, where it is being used for pretty much everything from the LaTeX core and up, but there is nothing about \fBdocstrip\fR which prevents using it for other types of software\&. .PP In short, the basic principle of literate programming is that program source should primarily be written and structured to suit the developers (and advanced users who want to peek "under the hood"), not to suit the whims of a compiler or corresponding source code consumer\&. This means literate sources often need some kind of "translation" to an illiterate form that dumb software can understand\&. The \fBdocstrip\fR Tcl package handles this translation\&. .PP Even for those who do not whole-hartedly subscribe to the philosophy behind literate programming, \fBdocstrip\fR can bring greater clarity to in particular: .IP \(bu programs employing non-obvious mathematics .IP \(bu projects where separate pieces of code, perhaps in different languages, need to be closely coordinated\&. .PP The first is by providing access to much more powerful typographical features for source code comments than are possible in plain text\&. The second is because all the separate pieces of code can be kept next to each other in the same source file\&. .PP The way it works is that the programmer edits directly only one or several "master" source code files, from which \fBdocstrip\fR generates the more traditional "source" files compilers or the like would expect\&. The master sources typically contain a large amount of documentation of the code, sometimes even in places where the code consumers would not allow any comments\&. The etymology of "docstrip" is that this \fIdoc\fRumentation was \fIstrip\fRped away (although "code extraction" might be a better description, as it has always been a matter of copying selected pieces of the master source rather than deleting text from it)\&. The \fBdocstrip\fR Tcl package contains a reimplementation of the basic extraction functionality from the \fBdocstrip\fR program, and thus makes it possible for a Tcl interpreter to read and interpret the master source files directly\&. .PP Readers who are not previously familiar with \fBdocstrip\fR but want to know more about it may consult the following sources\&. .IP [1] \fIThe tclldoc package and class\fR, \fIhttp://ctan\&.org/tex-archive/macros/latex/contrib/tclldoc/\fR\&. .IP [2] \fIThe DocStrip utility\fR, \fIhttp://ctan\&.org/tex-archive/macros/latex/base/docstrip\&.dtx\fR\&. .IP [3] \fIThe doc and shortvrb Packages\fR, \fIhttp://ctan\&.org/tex-archive/macros/latex/base/doc\&.dtx\fR\&. .IP [4] Chapter 14 of \fIThe LaTeX Companion\fR (second edition), Addison-Wesley, 2004; ISBN 0-201-36299-6\&. .PP .SH "FILE FORMAT" The basic unit \fBdocstrip\fR operates on are the \fIlines\fR of a master source file\&. Extraction consists of selecting some of these lines to be copied from input text to output text\&. The basic distinction is that between \fIcode lines\fR (which are copied and do not begin with a percent character) and \fIcomment lines\fR (which begin with a percent character and are not copied)\&. .CS docstrip::extract [join { {% comment} {% more comment !"#$%&/(} {some command} { % blah $blah "Not a comment\&."} {% abc; this is comment} {# def; this is code} {ghi} {% jkl} } \\n] {} .CE returns the same sequence of lines as .CS join { {some command} { % blah $blah "Not a comment\&."} {# def; this is code} {ghi} "" } \\n .CE It does not matter to \fBdocstrip\fR what format is used for the documentation in the comment lines, but in order to do better than plain text comments, one typically uses some markup language\&. Most commonly LaTeX is used, as that is a very established standard and also provides the best support for mathematical formulae, but the \fBdocstrip::util\fR package also gives some support for \fIdoctools\fR-like markup\&. .PP Besides the basic code and comment lines, there are also \fIguard lines\fR, which begin with the two characters '%<', and \fImeta-comment lines\fR, which begin with the two characters \'%%'\&. Within guard lines there is furthermore the distinction between \fIverbatim guard lines\fR, which begin with '%<<', and ordinary guard lines, where the '%<' is not followed by another '<'\&. The last category is by far the most common\&. .PP Ordinary guard lines conditions extraction of the code line(s) they guard by the value of a boolean expression; the guarded block of code lines will only be included if the expression evaluates to true\&. The syntax of an ordinary guard line is one of .CS '%' '<' STARSLASH EXPRESSION '>' '%' '<' PLUSMINUS EXPRESSION '>' CODE .CE where .CS STARSLASH ::= '*' | '/' PLUSMINUS ::= | '+' | '-' EXPRESSION ::= SECONDARY | SECONDARY ',' EXPRESSION | SECONDARY '|' EXPRESSION SECONDARY ::= PRIMARY | PRIMARY '&' SECONDARY PRIMARY ::= TERMINAL | '!' PRIMARY | '(' EXPRESSION ')' CODE ::= { any character except end-of-line } .CE Comma and vertical bar both denote 'or'\&. Ampersand denotes 'and'\&. Exclamation mark denotes 'not'\&. A TERMINAL can be any nonempty string of characters not containing '>', '&', '|', comma, '(', or ')', although the \fBdocstrip\fR manual is a bit restrictive and only guarantees proper operation for strings of letters (although even the LaTeX core sources make heavy use also of digits in TERMINALs)\&. The second argument of \fBdocstrip::extract\fR is the list of those TERMINALs that should count as having the value 'true'; all other TERMINALs count as being 'false' when guard expressions are evaluated\&. .PP In the case of a '%<*\fIEXPRESSION\fR>' guard, the lines guarded are all lines up to the next '%' guard with the same \fIEXPRESSION\fR (compared as strings)\&. The blocks of code delimited by such '*' and '/' guard lines must be properly nested\&. .CS set text [join { {begin} {%<*foo>} {1} {%<*bar>} {2} {%} {%<*!bar>} {3} {%} {4} {%} {5} {%<*bar>} {6} {%} {end} } \\n] set res [docstrip::extract $text foo] append res [docstrip::extract $text {foo bar}] append res [docstrip::extract $text bar] .CE sets $res to the result of .CS join { {begin} {1} {3} {4} {5} {end} {begin} {1} {2} {4} {5} {6} {end} {begin} {5} {6} {end} "" } \\n .CE In guard lines without a '*', '/', '+', or '-' modifier after the \'%<', the guard applies only to the CODE following the '>' on that single line\&. A '+' modifier is equivalent to no modifier\&. A '-' modifier is like the case with no modifier, but the expression is implicitly negated, i\&.e\&., the CODE of a '%<-' guard line is only included if the expression evaluates to false\&. .PP Metacomment lines are "comment lines which should not be stripped away", but be extracted like code lines; these are sometimes used for copyright notices and similar material\&. The '%%' prefix is however not kept, but substituted by the current \fB-metaprefix\fR, which is customarily set to some "comment until end of line" character (or character sequence) of the language of the code being extracted\&. .CS set text [join { {begin} {% foo} {%<+foo>plusfoo} {%<-foo>minusfoo} {middle} {%% some metacomment} {%<*foo>} {%%another metacomment} {%} {end} } \\n] set res [docstrip::extract $text foo -metaprefix {# }] append res [docstrip::extract $text bar -metaprefix {#}] .CE sets $res to the result of .CS join { {begin} { foo} {plusfoo} {middle} {# some metacomment} {# another metacomment} {end} {begin} {minusfoo} {middle} {# some metacomment} {end} "" } \\n .CE Verbatim guards can be used to force code line interpretation of a block of lines even if some of them happen to look like any other type of lines to docstrip\&. A verbatim guard has the form '%<<\fIEND-TAG\fR' and the verbatim block is terminated by the first line that is exactly '%\fIEND-TAG\fR'\&. .CS set text [join { {begin} {%<*myblock>} {some stupid()} { #computer} {%<} {%QQQ-98765} { using*strange@programming} {%} {end} } \\n] set res [docstrip::extract $text myblock -metaprefix {# }] append res [docstrip::extract $text {}] .CE sets $res to the result of .CS join { {begin} {some stupid()} { #computer} {% These three lines are copied verbatim (including percents} {%% even if -metaprefix is something different than %%)\&.} {%} { using*strange@programming} {end} {begin} {end} "" } \\n .CE The processing of verbatim guards takes place also inside blocks of lines which due to some outer block guard will not be copied\&. .PP The final piece of \fBdocstrip\fR syntax is that extraction stops at a line that is exactly "\\endinput"; this is often used to avoid copying random whitespace at the end of a file\&. In the unlikely case that one wants such a code line, one can protect it with a verbatim guard\&. .SH COMMANDS The package defines two commands\&. .TP \fBdocstrip::extract\fR \fItext\fR \fIterminals\fR ?\fIoption\fR \fIvalue\fR \&.\&.\&.? The \fBextract\fR command docstrips the \fItext\fR and returns the extracted lines of code, as a string with each line terminated with a newline\&. The \fIterminals\fR is the list of those guard expression terminals which should evaluate to true\&. The available options are: .RS .TP \fB-annotate\fR \fIlines\fR Requests the specified number of lines of annotation to follow each extracted line in the result\&. Defaults to 0\&. Annotation lines are mostly useful when the extracted lines are to undergo some further transformation\&. A first annotation line is a list of three elements: line type, prefix removed in extraction, and prefix inserted in extraction\&. The line type is one of: 'V' (verbatim), \'M' (metacomment), '+' (+ or no modifier guard line), '-' (- modifier guard line), '\&.' (normal line)\&. A second annotation line is the source line number\&. A third annotation line is the current stack of block guards\&. Requesting more than three lines of annotation is currently not supported\&. .TP \fB-metaprefix\fR \fIstring\fR The string by which the '%%' prefix of a metacomment line will be replaced\&. Defaults to '%%'\&. For Tcl code this would typically be '#'\&. .TP \fB-onerror\fR \fIkeyword\fR Controls what will be done when a format error in the \fItext\fR being processed is detected\&. The settings are: .RS .TP \fBignore\fR Just ignore the error; continue as if nothing happened\&. .TP \fBputs\fR Write an error message to \fBstderr\fR, then continue processing\&. .TP \fBthrow\fR Throw an error\&. The \fB-errorcode\fR is set to a list whose first element is \fBDOCSTRIP\fR, second element is the type of error, and third element is the line number where the error is detected\&. This is the default\&. .RE .TP \fB-trimlines\fR \fIboolean\fR Controls whether \fIspaces\fR at the end of a line should be trimmed away before the line is processed\&. Defaults to true\&. .RE .IP It should be remarked that the \fIterminals\fR are often called "options" in the context of the \fBdocstrip\fR program, since these specify which optional code fragments should be included\&. .TP \fBdocstrip::sourcefrom\fR \fIfilename\fR \fIterminals\fR ?\fIoption\fR \fIvalue\fR \&.\&.\&.? The \fBsourcefrom\fR command is a docstripping emulation of \fBsource\fR\&. It opens the file \fIfilename\fR, reads it, closes it, docstrips the contents as specified by the \fIterminals\fR, and evaluates the result in the local context of the caller, during which time the \fBinfo\fR \fBscript\fR value will be the \fIfilename\fR\&. The options are passed on to \fBfconfigure\fR to configure the file before its contents are read\&. The \fB-metaprefix\fR is set to '#', all other \fBextract\fR options have their default values\&. .PP .SH "DOCUMENT STRUCTURE" The file format (as described above) determines whether a master source code file can be processed correctly by \fBdocstrip\fR, but the usefulness of the format is to no little part also dependent on that the code and comment lines together constitute a well-formed document\&. .PP For a document format that does not require any non-Tcl software, see the \fBddt2man\fR command in the \fBdocstrip::util\fR package\&. It is suggested that files employing that document format are given the suffix "\fI\&.ddt\fR", to distinguish them from the more traditional LaTeX-based "\fI\&.dtx\fR" files\&. .PP Master source files with "\fI\&.dtx\fR" extension are usually set up so that they can be typeset directly by \fBlatex\fR without any support from other files\&. This is achieved by beginning the file with the lines .CS % \\iffalse %<*driver> \\documentclass{tclldoc} \\begin{document} \\DocInput{\fIfilename\&.dtx\fR} \\end{document} % % \\fi .CE or some variation thereof\&. The trick is that the file gets read twice\&. With normal LaTeX reading rules, the first two lines are comments and therefore ignored\&. The third line is the document preamble, the fourth line begins the document body, and the sixth line ends the document, so LaTeX stops there — non-comments below that point in the file are never subjected to the normal LaTeX reading rules\&. Before that, however, the \\DocInput command on the fifth line is processed, and that does two things: it changes the interpretation of '%' from "comment" to "ignored", and it inputs the file specified in the argument (which is normally the name of the file the command is in)\&. It is this second time that the file is being read that the comments and code in it are typeset\&. .PP The function of the \\iffalse \&.\&.\&. \\fi is to skip lines two to seven on this second time through; this is similar to the "if 0 { \&.\&.\&. }" idiom for block comments in Tcl code, and it is needed here because (amongst other things) the \\documentclass command may only be executed once\&. The function of the guards is to prevent this short piece of LaTeX code from being extracted by \fBdocstrip\fR\&. The total effect is that the file can function both as a LaTeX document and as a \fBdocstrip\fR master source code file\&. .PP It is not necessary to use the tclldoc document class, but that does provide a number of features that are convenient for "\fI\&.dtx\fR" files containing Tcl code\&. More information on this matter can be found in the references above\&. .SH "SEE ALSO" docstrip_util .SH KEYWORDS \\\&.dtx, LaTeX, docstrip, documentation, literate programming, source .SH CATEGORY Documentation tools .SH COPYRIGHT .nf Copyright (c) 2003–2010 Lars Hellström .fi