summaryrefslogtreecommitdiff
path: root/support/makeprog/src/progdoc.doc
blob: d85bd0ca9ce8f41337c4a016869585ce6183c423 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
% progdoc.doc					21 Sep 90
%------------------------------------------------------------
% (c) 1988-1990 by J.Schrod. Copyright conditions see below.

%
% Macro package for the documentation of programs (and TeX macros)
% MAKEPROG is needed
%

%
%	VERSION HISTORY   (MSCF -- most significant change first)
%
% DATE	   WHO REMARK
% 90-09-21 js  table of contents and headline added.
% 89-09-08 js  repaired initialization of \char_count.
% 89-06-30 js  Definition of \beginverbatim/\endverbatim.
% 88-12-05 js  first version (for ftp/Bitnet).

% bug reports to:
%
%	Detig$\,\cdot\,$Schrod \TeX{}sys
%	Joachim Schrod
%	Kranichweg 1
%
%	D-6074 R\"odermark-Urberach
%	FR Germany
%
%	Tel. (+6074) 1617
%	Bitnet: XITIJSCH@DDATHD21

% author:
%	js:	Joachim Schrod <xitijsch@ddathd21.bitnet>
% contributors:
%	(-: place enough for your name! :-)


% documented with itself...
\input progdoc


%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%
% local macros
%

\font\mc=cmr9		% for names like ASCII
\font\sc=cmcsc10	% caps and small caps 10pt

\def\WEB{{\tt WEB\/}}
\def\LaTeX{{\rm L\kern-.36em\raise.3ex\hbox{\sc a}\kern-.15em\TeX}}
\def\GNU{{\mc GNU}}

%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%




\title{{\tt progdoc} --- A {\tt WEB\/}-like Markup}





\chap Introduction.

\WEB{} systems allow the documentation of programs by supporting the
separation in program fragments which can be collected and rearranged
afterwards.  This allows {\it top-down\/} programming as well as the
{\it bottom-up\/} design of programs.  Each program fragment can be
documented, usually with \TeX{}.  The creation of a new \WEB{} system
has become easy with the introduction of Spider \WEB{} but even within
Spider \WEB{} the lexical analysis is bound to languages of the Algol
family. Building up \WEB{} systems for languages which are line
oriented or even for ``exotic'' programming languages like \TeX{}
(with a dynamic lexical, syntactical and semantical structure) remains
to be difficult.

This macro package was built to allow good documentation for programs
in languages for which \WEB{} does not exist.  It separates a program
text in sections that can be documented.  All sections, collected
sequentially, will result in the complete program.  In each section
begin and end of the program part are marked with |\beginprog| and
|\endprog|, this program part will be formatted as is input
(``verbatim'').

The separation of the sections is done in this version (which is
based on Plain~\TeX{}) by the macros |\chap| and |\sect|. In the
documentation part of a section text pieces, e.g.\ names of
variables, can be inserted verbatim to demonstrate the connection to
the program text.  These parts are included in vertical bars
(`{\tt\vbar}') while the vertical bar itself can be obtained by
|\origvert|. Longer text parts can be printed verbatim by enclosing
them in |\beginverbatim| and |\endverbatim| which behaves like
|\beginprog| and |\endprog| except that the text between is not
copied to the program file.

This macro package does not offer the creation of an index because it
is not known which syntactical tokens the language has that should be
mentioned in an index.	As well the creation of a table of contents
and of headings would be preferable to allow better orientation in the
document.  Some remarks about future enhancements which should be done
urgently are set in slanted type.


\sect This program is free software; you can redistribute it and/or
modify it under the terms of the \GNU{} General Public License as
published by the Free Software Foundation; either version~1, or (at your
option) any later version.

This program is distributed in the hope that it will be useful, but
{\bf without any warranty\/}; without even the implied warranty of
{\bf merchantability\/} or {\bf fitness for a particular purpose}.  See
the \GNU{} General Public License for more details.

You should have received a copy of the \GNU{} General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 675~Mass Ave, Cambridge, MA~02139, USA.


\sect We have to realize three parts:  (1)~the formatting of rather
small verbatim texts in a line, (2)~the formatting of larger parts of
program and (3)~the document structuring elements for the separation
of the sections.

But before we start we declare some shorthands for category codes.  By
declaring the at sign~(`|@|') as well as the underscore~`(|_|)' as
letters we can use them in our macros.	(I agree with D.~Knuth that
|\identifier_several_words_long| is more readable than
|\IdentifierSeveralWordsLong| and in every case better than |\p@@@s|.)
With the at sign we can use the ``private'' Plain macros and with the
underscore we can make our own macros more readable.  But as we have
to restore these category codes at the end of this macro file we store
their former values in the control sequences |\atcode| and |\uscode|.
This method is better than to use a group because not all macros have
to be defined global this way.

\beginprog
\chardef\escape=0
\chardef\subscript=8
\chardef\letter=11
\chardef\other=12
%\chardef\active=13		 % is defined in Plain already

\chardef\atcode=\catcode`\@
\chardef\uscode=\catcode`\_

\catcode`\@=\letter
\catcode`\_=\letter
\endprog




\chap Local Verbatim Formatting.

The main point of every verbatim formatting is the switching of the
character codes of all characters that have a special meaning for
\TeX{}. This can be done with the control sequence |\dospecials| that
applies the control sequence |\do| to all special characters.
Additionally, every line is regarded as a paragraph without
indentation.  Between two paragraphs, i.e.\ between two lines, no
extra space is set. Finally all blanks and tab characters shall be
obeyed and the inter word space after sentence terminators shall not
be enlarged. The activation of the tab character expansion with
|\obeytabs| is analog to |\obeyspaces| in {\tt plain.tex\/}.

Verbatim texts are set in monospace, we use (like in \WEB{}) the
character set with the extended {\mc ASCII}.

\beginprog
\font\tentex=cmtex10		% typewriter extended ASCII 10pt
\let\ttex=\tentex		% only for PLAIN with base size 10pt

\def\setup_verbatim{%
   \def\do##1{\catcode`##1\other}\dospecials
   \parskip\z@skip \parindent\z@
   \obeylines \obeyspaces \obeytabs \frenchspacing
   \ttex
   }

\let\tab=\space
\begingroup
   \catcode`\^^I=\active%	% Attention: no tabs!
   \gdef\obeytabs{\catcode`\^^I=\active\def^^I{\tab}}
   \global\let^^I=\tab% 	% if an active tab appears in a \write
\endgroup
\endprog

\sect After having saved the old meaning of `{\tt\vbar}' in
|\origvert| and after declaring |\vbar| as a synonym for the character
that has the code of a vertical bar in the current font, the vertical
bar can be made active.  Then we call |\setup_verbatim|.  But the
newline characters shall not be processed, they shall be treated as
blank space.  This can be done by defining |\par| as |\space|.

The next vertical bar in the input closes the group which becomes an
(unbreakable) |\hbox| then.  The old meanings of the special
characters and of the vertical bar are restored and \TeX{} is in
normal (horizontal) mode again.

\beginprog
\let\origvert=|
\chardef\vbar=`\|

\catcode`\|=\active

\def|{%
   \leavevmode
   \hbox\bgroup
      \let\par\space \setup_verbatim
      \let|\egroup
   }
\endprog




\chap  Program Fragments in Verbatim.

We need macros to format the program fragments without any
linebreaking.  Such a text area shall start with the macro
|\beginprog| resp.\ |\beginverbatim| and end with |\endprog|
resp.\ |\endverbatim|.	The end macros must stand
at the very beginning of a line and must be followed by white space
(blank, tab or newline character).  After all these macros
the rest of the line is ignored.

Two demands must be regarded:  There should be no length restrictions
for the processed text, and the tab characters should be expanded
so that this macro works on PC's and on VAXes, too.


\sect The implementation method is quite simple:  We read the next
line, test, wether the end is reached (by comparing with the end line)
and otherwise set the line actually read.  Every character is
inspected and tabular characters are expanded.

The verbatim text is started with |\begin_verbatim| which will be
either called by |\beginprog| or by |\beginverbatim|. These macros
will also define the contents of the end line.

Whether a line is set or whether the end of the processed area is
reached is indicated by the switch |\if@print|.  At the beginning of
the |\begin_verbatim| macro most settings are done with
|\setup_verbatim| (the vertical bar must be handled separately)
and the rest of the line is ignored.  As everything is done within
a group, the end of the verbatim text can be processed by simply
closing this group.

For the user it looks as if |\endprog| or |\endverbatim|
terminates the processing, but
it just serves for the identification of the end, the true processing
is done with the internal macro |\end_verbatim|.

\beginprog
\newif\if@print

\def\begin_verbatim{%
   \endgraf
   \bigbreak
   \begingroup
      \setup_verbatim \catcode`\|\other
      \@printtrue
      \ignore_rest_line
   }
\let\end_verbatim=\endgroup		% internal command !
\endprog


\sect The first line is ignored, all the other lines are identified
with |\set_next_line| and processed with |\do_set|.  This separation
in identification and processing allows that the line end character is
active in the definition only for a short time.

When a line is to be formatted, we first check with |\check_print|
whether it contains |\endprog|, otherwise it is printed with
|\print_char|.	The printing must be done for every character
individually because we want to check for tab characters; the
exact algorithm is described below.  Here we just have to note that
|\print_char| is used with two parameters of which the second one is
terminated with the token |\end_line|.	The first parameter is the first
character of the line, the second parameter is the rest of the line.
If the line is empty, the argument of |\do_set| is empty, too; so the
activation of |\print_char| must be finished with two |\end_line|.
Then the first |\end_line| is the first argument for |\print_char| and
the second argument is empty.  But if the line did contain something,
the second |\end_line| is evaluated, for this case it is defined as
|\relax|.

Finally we call |\set_next_line| again to format the next line.  If
the end is reached, i.e.\ if a line with |\endprog| was found,
|\set_next_line| is redefined as |\relax|.  This can be done because
the original meaning is restored when the group is closed by
|\end_verbatim|.

\beginprog
\begingroup
   \obeylines%		% ^^M is active! ==> every line must end with %
   \gdef\ignore_rest_line#1^^M{\set_next_line}%
   \gdef\set_next_line#1^^M{\do_set{#1}}%
\endgroup

\def\do_set#1{%
   \endgraf
   \check_print{#1}%
   \if@print  \indent \print_char#1\end_line\end_line
   \else  \let\set_next_line\end_verbatim
   \fi
   \set_next_line
   }
\let\end_line=\relax
\endprog


\sect Before we attack the problem of formatting a line, we declare
|\check_print| that checks the end of the verbatim mode.  We have to
do two things:	we must split everything in front of the first blank
or tab character and compare it with |\endprog|. The splitting is easy
because the line which is our first argument contains blanks and
tabulators as active characters.  First we call |\cut_at_tab| that
demands a tab character as separator for its two parameters so that
everything in the line in front of the first tabulator is part of the
first parameter.  If there is no tab character in the line, we append
one so that the second parameter is empty. The same trick is used to
separate the part in front of the first blank character from the
resulting first part.

The check is done with |\do_check|.  We use a separate macro here so
that we can indent it (in the following definition blanks are active!)

\beginprog
\begingroup
\obeyspaces\obeytabs
\gdef\check_print#1{\cut_at_tab#1^^I\end_line}
\gdef\cut_at_tab#1^^I#2\end_line{\check_first_part#1 \end_line}% blank !
\gdef\check_first_part#1 #2\end_line{\do_check{#1}}
\endgroup
\endprog


\sect |\do_check| compares the line with a sample line that is
available in |\end_verbatim_line|.  This macro will be defined later.

\beginprog
\def\do_check#1{%
   \def\@line{#1}%
   \ifx \@line\end_verbatim_line  \@printfalse
   \fi
   }
\endprog


\sect Now we can set a line:  we start with the first character,
followed by the rest of the line.  Each character is counted in
|\char_count|.	At the beginning of a line |\char_count| is~0, it
is reset at the end of the line.

\beginprog
\newcount\char_count  \char_count\z@

\def\print_char#1#2\end_line{%
   \print_first_char{#1}%
   \print_rest_of_line{#2}%
   }
\endprog


\sect For each character that is set |\char_count| is incremented.
If a character is a tabulator, we set with |\print_tab| the required
amount of blank characters, otherwise the character itself.  We must
compare the character that is stored in |\@char| with a macro whose
``first-level'' expansion is an active tabulator.  For this case we
declare |\@tab|.

\beginprog
{\obeytabs\gdef\@tab{^^I}}

\def\print_first_char#1{%
   \def\@char{#1}%
   \advance \char_count\@ne
   \ifx \@char\@tab  \print_tab
   \else  \@char
   \fi
   }
\endprog


\sect If we want to fill the line with blank spaces up to the next
column with a number that can be divided by~8, we must be able to
compute the column number modulo~8, but \TeX{} has no modulo operator.
So we define the macro |\mod_viii| that computes its argument modulo~8
and returns the result in the counter |\count_mod_viii|.  For the
computation we use the temporary counter |\count@|.

\beginprog
\newcount\count_mod_viii
\def\mod_viii#1{%
   \count@ #1\relax  \count_mod_viii\count@
   \divide \count@ 8\relax
   \multiply \count@ 8\relax
   \advance \count_mod_viii -\count@
   }
\endprog


\sect Now we can declare |\print_tab|.	We must remember that
|\char_count| was incremented already, if we set only one blank
character the counter keeps untouched.

\beginprog
\def\print_tab{%
   \loop  \space \mod_viii\char_count
      \ifnum \count_mod_viii>\z@
	 \advance \char_count\@ne
   \repeat
   }
\endprog


\sect If the rest of the line is empty, we have finished the task.
|\char_count| is reset to~0 for the next line.

Inside the |\else| part of |\ifx| |\print_char| should not be used
directly because this costs too much storage of \TeX{}.  Instead we
set a control sequence |\next| that is processed afterwards, depending
on the result of the comparison.  If there is still something to set,
we use |\print_char| again, otherwise a syntactically similar macro
that expands to |\relax|.

\beginprog
\def\print_rest_of_line#1{%
   \def\@line{#1}%
   \ifx \@line\empty  \char_count\z@
	\def\next##1\end_line{\relax}%
   \else  \let\next\print_char
   \fi
   \next#1\end_line
   }
\endprog


\sect Now we are ready to define the two ``user accessible'' macros
|\beginprog| and |\beginverbatim|. They must define the prototyp end
line |\end_verbatim_line| which will be compared against every line
in the verbatim text. During the definition of
|\end_verbatim_line| it must be cared for that the escape character~`|\|'
is a printable character:  A comparison with |\ifx| demands identical
category codes.  As a temporary escape character we use the slash.

\beginprog
{\catcode`\/=\escape  \catcode`\\=\other % / is temporary escape char
   /gdef/beginprog{%
      /gdef/end_verbatim_line{\endprog}%
      /begin_verbatim
      }
   /gdef/beginverbatim{%
      /gdef/end_verbatim_line{\endverbatim}%
      /begin_verbatim
      }
}					 % here \endgroup can't be used
\endprog




\chap Document Structuring.

The layout of the document shall be like in \WEB{}; this can be done
easily in Plain. A document -- which may have a title -- consists of
sections which are numbered. We distinguish between main sections
which start a group of sections and between normal sections within a
group. Main sections have a title, a table of contents with all
titles is output at the end.


\sect The number of the current section is stored in the counter
|\sectno|.

\beginprog
\newcount\sectno  \sectno=\@ne

\newtoks\title  \title{}
\endprog


\sect As usual, the name |\toc_file_name| of the table of contents
file |\toc_file| is built from the jobname and the extension |toc|.
We open the file and output a |\relax| so we are save that something
is in the file and it can be read in later without any difficulties.

In this file lines are written with the main section numbers, their
titles, and their page numbers, respectively. Every line is marked
with |\tocline| which is assumed to have the given three parameters.
Now we define |\tocline| to be |\relax| so that |\write| does not
expand it.

\beginprog
\def\toc_file_name{\jobname.toc }      % <--- Space!!
\newwrite\toc_file

\immediate\openout\toc_file=\toc_file_name
\immediate\write\toc_file{\relax}

\let\tocline=\relax
\endprog


\sect We want a headline with the current section number, the
document title, the last main section title, and the page number. The
footline is empty.

To realize this headline every section must |\mark| it's section
number {\it in front of\/} a potentiel page break (so the number may
be accessed by |\topmark|) and every main section must define
|\main_title| to be it's title.

\beginprog
\headline{%
   \tenrm
   \S\topmark \qquad \the\title
   \hfil
   \main_title \qquad \tenrm \folio
   }
\footline{\hfil}
\endprog


\sect But this does not work the way it should: On the first page
|\topmark| will be always empty! Here we borrow a trick from
|webmac.tex|, we insert a first garbage page which will be discarded
by the output routine.

\beginprog
\vbox to \vsize{}

\output={%
   \setbox\z@ \vbox{\unvbox\@cclv}%    % throw away the first page
   \global\output{\plainoutput}%       % restore Plain output routine
   }
\endprog


\sect The main sections are started with the macro |\chap|. It has
one parameter, the title of the section group.	This parameter must
be terminated by a dot.  We start a new page, typeset the title in
bold face and separate it from the section text with a |\medskip|. 
This text, the first paragraph of the documentation part of the
section, is formatted without paragraph indentation.

At the beginning of the new page we output the section number, the
title, and the page number to the contents file. We must take care to
expand the section number right now because it will be incremented
and would not be the correct value during the output routine.

The deletion of the paragraph indentation is done with |\everypar|.
We do not care if |\everypar| is used for something else and delete it
after usage.

\beginprog
\def\chap#1.{%
   \endgraf
   \mark{\number\sectno}%        % gather information for headline
   \vfill\supereject
   \begingroup
      \def\protect##1{\string ##1 }%   % <--- Space!!
      \edef\write_toc_sectno{\write\toc_file{\tocline{\number\sectno}}}%
      \write_toc_sectno
      \write\toc_file{{#1}{\folio}}%
   \endgroup
   \gdef\main_title{#1}%         % more information for headline
   \noindent {\bf \number\sectno.\quad #1.}%
   \global\advance \sectno\@ne
   \endgraf
   \medskip  \nobreak
   \everypar{%                         % remove next parindent
      \setbox0\lastbox
      \global\everypar{}%
      }%
   }
\endprog


\sect Normal sections are started with |\sect|.  This macro has no
parameter.  Between two paragraphs we set 2~pica space (if possible)
and prefer the page breaking.  Between the section number and the text
one quad of space is set.

\begingroup \sl
The page break manipulation should be more sophisticated.
\endgroup

\beginprog
\def\sect{%
   \endgraf
   \mark{\number\sectno}%        % gather information for headline
   \vskip 2pc plus 1pc minus 6dd  \goodbreak
   \noindent {\bf \number\sectno.}\quad \ignorespaces
   \global\advance \sectno\@ne
   }
\endprog


\sect At the end we add a page with the table of contents. This is
triggered by |\bye|. If the user does not want this table he may use
|\byebye|.

\beginprog
\def\byebye{\par\vfil\supereject\end}    % original definition of \bye
\def\bye{%
   \endgraf
   \vfill \supereject
   \immediate\closeout\toc_file
   \message{Table of contents:}%
   \leftskip\z@skip  \rightskip\z@skip
   \parskip\z@skip  \parindent\z@  \parfillskip\z@skip
   \normalbaselines
   \headline{\hfil}%
   \footline{\hfil \folio \hfil}%
   \def\HeaderToc{\rightline{Section\hbox to\thr@@ em{\hss Page}}}%
   \def\tocline##1##2##3{%
      \line{%
	 \ignorespaces ##2%
	 \leaders\hbox to .5em{.\hfil}\hfil
	 \ ##1%
	 \hbox to \thr@@ em{\hss ##3}%
	 }%
       }
   \pageno\m@ne        % table of contents gets roman page numbers
   \topofcontents      % may redefine \HeaderToc and \tocline!
   \HeaderToc
   \catcode`\@\letter  % @ and _ are letters (for reading private macros)
   \catcode`\_\letter
   \input \toc_file_name
   \catcode`\@\atcode  % @ and _ are no more letters
   \catcode`\_\uscode
   \botofcontents
   \byebye		       % print the contents page(s) and terminate
   }

\font\titlefont=cmr7 scaled\magstep4	% title on the contents page
\font\ttitlefont=cmtt10 scaled\magstep2 % typewriter type in title
\def\topofcontents{
   \null \vfill
   \centerline{\let\tt\ttitlefont \titlefont \the\title}
   \vskip 1cm
   }
\def\botofcontents{
   \vfill\vfill
   }
\endprog


\sect We are finished and just have to restore the category codes.

\beginprog
\catcode`\@=\atcode
\catcode`\_=\uscode

\endinput
\endprog





\bye