lyx_mirror/lib/examples/Literate.lyx
Lars Gullik Bjønnes 27de1486ca Initial revision
git-svn-id: svn://svn.lyx.org/lyx/lyx-devel/trunk@140 a592a061-630c-0410-9148-cb99ea01b6c8
1999-09-27 18:44:28 +00:00

1803 lines
26 KiB
Plaintext

#This file was created by <wiensk> Tue Feb 23 22:25:52 1999
#LyX 1.0 (C) 1995-1999 Matthias Ettrich and the LyX Team
\lyxformat 2.15
\textclass literate-article
\language default
\inputencoding default
\fontscheme default
\graphics default
\paperfontsize default
\spacing single
\papersize Default
\paperpackage a4
\use_geometry 0
\use_amsmath 0
\paperorientation portrait
\secnumdepth 3
\tocdepth 3
\paragraph_separation indent
\defskip medskip
\quotes_language english
\quotes_times 2
\papercolumns 1
\papersides 1
\paperpagestyle default
\layout Title
LyX and Literate Programming
\newline
An example program
\layout Author
Edmar Wienskoski Jr.
\newline
edmar-w-jr@technologist.com
\layout Date
\latex latex
\backslash
today
\layout Standard
\begin_inset LatexCommand \tableofcontents
\end_inset
\layout Section
Introduction
\layout Standard
After typesetting a document, LyX scans the LaTeX log file looking for errors.
For each error found, the line number is obtained and a error box is displayed
in the LyX screen at that position.
\layout Standard
To use this feature to view compilation errors while working with literate
documents, we need a program that filters the compilation errors and puts
them in a format suitable for LyX reading it.
\layout Standard
In this document we present a filter that recognizes compilation error messages
from noweb, gnu C, and the IBM C compiler (xlc).
\layout Standard
The filter is required to read from standard input, parse for error messages
and copy the error messages to the standard output.
During the output process, the filter must present the error messages in a
format that LyX can interpret, currently, the LaTeX error message format.
Of course, nothing will prevent future LyX releases from being able to read
other formats as well (like gcc error messages for example).
This mechanism is necessary to fully explore the literate programming
tool's capabilities.
\layout Section
Algorithm
\layout Scrap
<<Function bodies>>=
\newline
int
\newline
main (int argc, char **argv)
\newline
{
\newline
\protected_separator
if (argc == 2) {
\newline
\protected_separator
\protected_separator
\protected_separator
switch (argv[1][0]) {
\newline
\protected_separator
\protected_separator
\protected_separator
case 'n':
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
<<Scan input for noweb error messages>>
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
break;
\newline
\protected_separator
\protected_separator
\protected_separator
case 'x':
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
<<Scan input for xlc error messages>>
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
break;
\newline
\protected_separator
\protected_separator
\protected_separator
case 'a':
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
<<AIX system using both noweb and xlc>>
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
break;
\newline
\protected_separator
\protected_separator
\protected_separator
case 's':
\newline
\protected_separator
\protected_separator
\protected_separator
case 'b':
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
<<Solaris and Linux systems using both noweb and gcc>>
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
break;
\newline
\protected_separator
\protected_separator
\protected_separator
case 'g':
\newline
\protected_separator
\protected_separator
\protected_separator
default:
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
<<Scan input for gcc error messages>>
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
break;
\newline
\protected_separator
\protected_separator
\protected_separator
}
\newline
\protected_separator
} else {
\newline
\protected_separator
\protected_separator
\protected_separator
<<Scan input for gcc error messages>>
\newline
\protected_separator
}
\newline
}
\newline
@
\layout Scrap
<<Function prototypes>>=
\newline
int main (int argc, char **argv);
\newline
@
\layout Section
Data Structures
\layout Standard
We resort to some global variables to allow access from several different
routines.
These are the buffer and related pointers used during the parse of the
input.
\layout Scrap
<<Global variables>>=
\newline
char
\protected_separator
\protected_separator
\protected_separator
buffer[200][200];
\newline
int
\protected_separator
\protected_separator
\protected_separator
\protected_separator
last_buf_line;
\newline
int
\protected_separator
\protected_separator
\protected_separator
\protected_separator
last_err_line;
\newline
int
\protected_separator
\protected_separator
\protected_separator
\protected_separator
err_line;
\newline
@
\layout Section
The output format
\layout Standard
The output format mimics the LaTeX error messages format.
This function prints a number of lines residing in the global variable
\family typewriter
buffer
\family default
, a program name and line number.
There is no special requirement on the input strings, they can be anything.
\layout Scrap
<<Function bodies>>=
\newline
void
\newline
output_error (int buf_size, int error_line, char *tool)
\newline
{
\newline
\protected_separator
int
\protected_separator
\protected_separator
\protected_separator
\protected_separator
i;
\newline
\protected_separator
\newline
\protected_separator
fprintf(stdout, "! Build Error: ==> %s ==>
\backslash
n", tool);
\newline
\protected_separator
for (i=0; i<buf_size; i++)
\newline
\protected_separator
\protected_separator
\protected_separator
fprintf(stdout, "%s", buffer[i]);
\newline
\protected_separator
fprintf(stdout, " ...
\backslash
n
\backslash
nl.%d ...
\backslash
n
\backslash
n", error_line);
\newline
}
\newline
@
\layout Scrap
<<Function prototypes>>=
\newline
void output_error (int buf_size, int error_line, char *tool);
\newline
@
\layout Section
Functions Implementation
\layout Standard
Both noweave and notangle routines, always output one single line for each
error found, thus to scan the buffer for noweb error messages is enough
to exam one input line at a time.
Note that the noweb software does not provide a line error number, so all
errors boxes related to noweb messages will be displayed at the beginning
of the file.
\layout Scrap
<<Scan input for noweb error messages>>=
\newline
{
\newline
\protected_separator
last_buf_line = 0;
\newline
\protected_separator
while (fgets(buffer[0], 200, stdin)) {
\newline
\protected_separator
\protected_separator
\protected_separator
if (noweb_try(0))
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
output_error(1, 0, "noweb");
\newline
\protected_separator
}
\newline
}
\newline
@
\layout Standard
The examination itself is very inefficient.
Unfortunately noweb doesn't have any characteristic that would help to
identify one of its error messages.
The solution is to collect all possible output messages in an array of
strings, and turn the examination process into a linear search in this
array.
\layout Scrap
<<Global variables>>=
\newline
char *noweb_msgs[] = {
\newline
\protected_separator
"couldn't open file",
\newline
\protected_separator
"couldn't open temporary file",
\newline
\protected_separator
"error writing temporary file",
\newline
\protected_separator
"ill-formed option",
\newline
\protected_separator
"unknown option",
\newline
\protected_separator
"Bad format sequence",
\newline
\protected_separator
"Can't open output file",
\newline
\protected_separator
"Can't open temporary file",
\newline
\protected_separator
"Capacity exceeded:",
\newline
\protected_separator
"Ignoring unknown option -",
\newline
\protected_separator
"This can't happen:",
\newline
\protected_separator
"non-numeric line number in"
\newline
};
\newline
@
\layout Standard
A noweb error message can be any string that contains a matching pair of
< <
\protected_separator
\protected_separator
\protected_separator
> >, or any of the above strings.
\layout Scrap
<<Function bodies>>=
\newline
int
\newline
noweb_try (int buf_line)
\newline
{
\newline
\protected_separator
char
\protected_separator
\protected_separator
\protected_separator
*s, *b;
\newline
\protected_separator
int
\protected_separator
\protected_separator
\protected_separator
\protected_separator
i;
\newline
\protected_separator
\newline
\protected_separator
b = buffer[buf_line];
\newline
\protected_separator
s = strstr(b, "<<");
\newline
\protected_separator
if (s != NULL) {
\newline
\protected_separator
\protected_separator
\protected_separator
s = strstr(s+2, ">>");
\newline
\protected_separator
\protected_separator
\protected_separator
if (s != NULL)
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
return 1;
\newline
\protected_separator
} else {
\newline
\protected_separator
\protected_separator
\protected_separator
for (i=0; i<12; i++) {
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
s = strstr (b, noweb_msgs[i]);
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
if (s != NULL)
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
break;
\newline
\protected_separator
\protected_separator
\protected_separator
}
\newline
\protected_separator
\protected_separator
\protected_separator
if (s != NULL)
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
return 1;
\newline
\protected_separator
}
\newline
\protected_separator
return 0;
\newline
}
\newline
@
\layout Scrap
<<Function prototypes>>=
\newline
int noweb_try (int buf_line);
\newline
@
\layout Standard
The xlc compiler always outputs one single line for each error found, thus
to scan the buffer for xlc error messages it is enough to exam one input
line at a time.
\layout Scrap
<<Scan input for xlc error messages>>=
\protected_separator
\newline
{
\newline
\protected_separator
last_buf_line = 0;
\newline
\protected_separator
while (fgets(buffer[last_buf_line], 200, stdin)) {
\newline
\protected_separator
\protected_separator
\protected_separator
if (xlc_try(0))
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
output_error(1, err_line, "xlc");
\newline
\protected_separator
}
\newline
}
\newline
@
\layout Standard
A xlc error message is easy to identify.
Every error message starts with a quoted string with no spaces, a comma,
a space, the word
\begin_inset Quotes eld
\end_inset
line
\begin_inset Quotes erd
\end_inset
, a space, and some variable text.
The following routine tests if a given buffer line matches this criteria:
\layout Scrap
<<Function bodies>>=
\newline
int
\newline
xlc_try (int buf_line)
\newline
{
\newline
\protected_separator
char
\protected_separator
\protected_separator
\protected_separator
*s, *t;
\newline
\protected_separator
\newline
\protected_separator
t = buffer[buf_line];
\newline
\protected_separator
s = t+1;
\newline
\protected_separator
while (*s != '"' && *s != ' ' && *s != '
\backslash
0')
\newline
\protected_separator
\protected_separator
\protected_separator
s++;
\newline
\protected_separator
if (*t != '"' || *s != '"' || strncmp(s+1, ", line ", 7) != 0)
\newline
\protected_separator
\protected_separator
\protected_separator
return 0;
\newline
\protected_separator
s += 8;
\newline
\protected_separator
err_line = atoi(s);
\newline
\protected_separator
return 1;
\newline
}
\newline
@
\layout Scrap
<<Function prototypes>>=
\newline
int xlc_try (int buf_line);
\newline
@
\layout Standard
The gcc compiler error messages are more complicated to scan.
Each error can span more than one line in the buffer.
The good news is that every buffer line on each error has the same pattern,
and share the same line number.
Thus the strategy will be to accumulate lines in the buffer while the reported
line number is still the same.
At the time they differ, all the accumulated lines, except the last one,
will belong to one single error message, which now can be output-ed to
LyX.
\layout Standard
Every gcc error message contains a string with no space followed by a
\begin_inset Quotes eld
\end_inset
:
\begin_inset Quotes eld
\end_inset
.
If the next character is a space, then this line is a header of a error
message and the next line will detail the line number of the source code
where the error was found.
Otherwise, the next thing is a integer number followed by another
\begin_inset Quotes eld
\end_inset
:
\begin_inset Quotes eld
\end_inset
.
\layout Scrap
<<Scan input for gcc error messages>>=
\newline
{
\newline
\protected_separator
char
\protected_separator
\protected_separator
\protected_separator
*s, *t;
\newline
\protected_separator
\newline
\protected_separator
last_buf_line = 0;
\newline
\protected_separator
while (fgets(buffer[last_buf_line], 200, stdin)) {
\newline
\protected_separator
\protected_separator
\protected_separator
/****** Skip lines until I find an error */
\newline
\protected_separator
\protected_separator
\protected_separator
s = strpbrk(buffer[last_buf_line], " :");
\newline
\protected_separator
\protected_separator
\protected_separator
if (s == NULL || *s == ' ')
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
continue; /* No gcc error found here */
\newline
\protected_separator
\protected_separator
\protected_separator
do {
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
<<gcc error message criteria is to find a "...:999:" or a "...: ">>
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
/****** OK It is an error message, get line number */
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
err_line = atoi(s+1);
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
if (last_err_line == 0 || last_err_line == err_line) {
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
last_err_line = err_line;
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
continue; /* It's either a header or a continuation, don't output yet */
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
}
\newline
\protected_separator
\protected_separator
\protected_separator
/****** Completed the scan of one error message, output it to LyX */
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
discharge_buffer(1);
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
break;
\newline
\protected_separator
\protected_separator
\protected_separator
} while (fgets(buffer[last_buf_line], 200, stdin));
\newline
\protected_separator
}
\newline
\protected_separator
\protected_separator
/****** EOF completes the scan of whatever was being scanned */
\newline
\protected_separator
discharge_buffer(0);
\newline
}
\newline
@
\layout Scrap
<<gcc error message criteria is to find a "...:999:" or a "...: ">>=
\newline
/****** Search first ":" in the error number */
\newline
s = strpbrk(buffer[last_buf_line], " :");
\newline
last_buf_line++;
\newline
if (s == NULL || *s == ' ')
\newline
\protected_separator
<<No gcc error found here, but it might terminate the scanning of a previous
one>>
\newline
/****** Search second ":" in the error number */
\newline
t = strpbrk(s+1, " :");
\newline
if (t == NULL || *t == ' ')
\newline
\protected_separator
<<No gcc error found here, but it might terminate the scanning of a previous
one>>
\newline
/****** Verify if is all digits between ":" */
\newline
if (t != s+1+strspn(s+1, "0123456789"))
\newline
\protected_separator
<<No gcc error found here, but it might terminate the scanning of a previous
one>>
\newline
@
\layout Scrap
<<No gcc error found here, but it might terminate the scanning of a previous
one>>=
\newline
{
\newline
\protected_separator
\protected_separator
err_line = 0;
\newline
\protected_separator
\protected_separator
discharge_buffer(1);
\newline
\protected_separator
\protected_separator
continue;
\newline
}
\newline
@
\layout Standard
As we mentioned, when the scan of one gcc error message is completed everything
in the buffer except the last line is one single error message.
But if the scan terminates with a EOF or through finding one line that
does not match the gcc error message criteria, then there is no
\begin_inset Quotes eld
\end_inset
last line
\begin_inset Quotes erd
\end_inset
in the buffer to be concerned with.
In those cases we empty the buffer completely.
\layout Scrap
<<Function bodies>>=
\newline
void
\newline
discharge_buffer (int save_last)
\newline
{
\newline
\protected_separator
if (last_err_line != 0) {
\newline
\protected_separator
\protected_separator
\protected_separator
if (save_last != 0) {
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
output_error(last_buf_line-1, last_err_line, "gcc");
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
strcpy (buffer[0], buffer[last_buf_line-1]);
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
last_err_line = err_line;
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
last_buf_line = 1;
\newline
\protected_separator
\protected_separator
\protected_separator
} else {
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
output_error (last_buf_line, last_err_line, "gcc");
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
last_err_line = 0;
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
last_buf_line = 0;
\newline
\protected_separator
\protected_separator
\protected_separator
}
\newline
\protected_separator
}
\newline
}
\newline
@
\layout Scrap
<<Function prototypes>>=
\newline
void discharge_buffer (int save_last);
\newline
@
\layout Standard
To combine the scan of noweb error messages and xlc error messages is very
simple.
We just try each one for every input line:
\layout Scrap
<<AIX system using both noweb and xlc>>=
\newline
{
\newline
\protected_separator
last_buf_line = 0;
\newline
\protected_separator
while (fgets(buffer[0], 200, stdin)) {
\newline
\protected_separator
\protected_separator
\protected_separator
if (noweb_try(0))
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
output_error(1, 0, "noweb");
\newline
\protected_separator
\protected_separator
\protected_separator
else if (xlc_try(0))
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
output_error(1, err_line, "xlc");
\newline
\protected_separator
}
\newline
}
\newline
@
\layout Standard
To combine the scan of noweb error messages and gcc error messages is simple
if we realize that it is not possible to find a noweb error message
in the middle of a gcc error message.
So we just repeat the gcc procedure and test for noweb error messages in
the beginning of the scan:
\layout Scrap
<<Solaris and Linux systems using both noweb and gcc>>=
\newline
{
\newline
\protected_separator
char
\protected_separator
\protected_separator
\protected_separator
*s, *t;
\newline
\protected_separator
\newline
\protected_separator
last_buf_line = 0;
\newline
\protected_separator
while (fgets(buffer[last_buf_line], 200, stdin)) {
\newline
\protected_separator
\protected_separator
\protected_separator
/****** Skip lines until I find an error */
\newline
\protected_separator
\protected_separator
\protected_separator
if (last_buf_line == 0 && noweb_try(0)) {
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
output_error(1, 0, "noweb");
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
continue;
\newline
\protected_separator
\protected_separator
\protected_separator
}
\newline
\protected_separator
\protected_separator
\protected_separator
s = strpbrk(buffer[last_buf_line], " :");
\newline
\protected_separator
\protected_separator
\protected_separator
if (s == NULL || *s == ' ')
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
continue; /* No gcc error found here */
\newline
\protected_separator
\protected_separator
\protected_separator
do {
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
<<gcc error message criteria is to find a "...:999:" or a "...: ">>
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
/****** OK It is an error, get line number */
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
err_line = atoi(s+1);
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
if (last_err_line == 0 || last_err_line == err_line) {
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
last_err_line = err_line;
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
continue; /* It's either a header or a continuation, don't output yet */
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
}
\newline
\protected_separator
\protected_separator
\protected_separator
/****** Completed the scan of one error message, output it to LyX */
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
discharge_buffer(1);
\newline
\protected_separator
\protected_separator
\protected_separator
\protected_separator
\protected_separator
break;
\newline
\protected_separator
\protected_separator
\protected_separator
} while (fgets(buffer[last_buf_line], 200, stdin));
\newline
\protected_separator
}
\newline
\protected_separator
\protected_separator
/****** EOF completes the scan of whatever was being scanned */
\newline
\protected_separator
discharge_buffer(0);
\newline
}
\newline
@
\layout Section
Wrapping the code into a file
\layout Scrap
<<listerrors.c>>=
\newline
#include <stdio.h>
\newline
#include <strings.h>
\protected_separator
\protected_separator
\protected_separator
\newline
\protected_separator
\newline
<<Global variables>>
\newline
<<Function prototypes>>
\newline
<<Function bodies>>
\newline
@
\layout Standard
To build this program, we want to add the
\begin_inset Quotes eld
\end_inset
-L
\begin_inset Quotes erd
\end_inset
option in the tangle command to force gdb to load the file
\family typewriter
Literate.nw
\family default
instead of
\family typewriter
listerrors.c
\family default
.
In accordance with this, we pass the
\begin_inset Quotes eld
\end_inset
-g
\begin_inset Quotes erd
\end_inset
option to gcc.
\layout Scrap
<<build-script>>=
\newline
#!/usr/local/bin/bash
\newline
notangle -L -Rlisterrors.c Literate.nw > listerrors.c
\newline
gcc -g -o listerrors listerrors.c
\newline
@
\layout Standard
This project can be tangled and compiled from LyX if you set
\family typewriter
\backslash
build_command
\family default
to call a generic script that always extracts a scrap named
\family typewriter
build-script
\family default
and executes it.
Here is a example of such generic script:
\layout LyX-Code
#!/bin/sh
\newline
notangle -Rbuild-script $1 | sh
\the_end