cleanups from Hartmut

[lyx.git] / lib / examples / Literate.lyx

#LyX 1.4.0cvs created this file. For more info see http://www.lyx.org/
\lyxformat 243
\begin_document
\begin_header
\textclass literate-article
\language english
\inputencoding default
\fontscheme default
\graphics default
\paperfontsize default
\spacing single
\papersize default
\use_geometry false
\use_amsmath 0
\cite_engine basic
\use_bibtopic false
\paperorientation portrait
\secnumdepth 3
\tocdepth 3
\paragraph_separation indent
\defskip medskip
\quotes_language english
\quotes_times 2
\papercolumns 1
\papersides 1
\paperpagestyle default
\tracking_changes false
\output_changes true
\end_header

\begin_body

\begin_layout Title

LyX and Literate Programming
\newline
An example program
\end_layout

\begin_layout Author

Edmar Wienskoski Jr.
\newline
edmar-w-jr@technologist.com
\begin_inset Foot
status collapsed

\begin_layout Standard

Modified by Bernard Michael Hurley bernardh@westherts.ac.uk ---- Don't blame
 Edmar for any errors that have crept in!
\end_layout

\end_inset


\end_layout

\begin_layout Abstract


\series bold
Note:
\series default
 This example program is provided for educational use only.
 The functionality in this C program has been superceded by the equivalent
 Python code in 
\emph on
examples/listerrors.lyx
\emph default
 which should be installed in the LyX scripts directory.
\end_layout

\begin_layout Date


\begin_inset ERT
status collapsed

\begin_layout Standard

\backslash
today
\end_layout

\end_inset


\end_layout

\begin_layout Standard


\begin_inset LatexCommand \tableofcontents{}

\end_inset


\end_layout

\begin_layout Section

Introduction
\end_layout

\begin_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.
\end_layout

\begin_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.
 
\end_layout

\begin_layout Standard

In this document we present a filter that recognizes compilation error messages
 from noweb, gnu C, and the IBM C compiler (xlc).
\end_layout

\begin_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.
\end_layout

\begin_layout Section

Algorithm
\end_layout

\begin_layout Scrap

<<Function bodies>>=
\newline
int
\newline
main (int argc, char **argv)
\newline
{
\newline
  if (argc == 2) {
\newline
    switch (argv[1][0]) {
\newline
    case 'n':
\newline
      <<Scan input for noweb error messages>>
\newline
      break;
\newline
    case 'x':
\newline
      <<Scan input for xlc error messages>>
\newline
      break;
\newline
    case 'a':
\newline
      <<AIX system using both noweb and xlc>>
\newline
      break;
\newline
    case 's':
\newline
    case 'b':
\newline
      <<Solaris and Linux systems using both noweb and gcc>>
\newline
      break;
\newline
    case 'g':
\newline
    default:
\newline
      <<Scan input for gcc error messages>>
\newline
      break;
\newline
    }
\newline
  } else {
\newline
    <<Scan input for gcc error messages>>
\newline
  }
\newline
}
\newline
@
\end_layout

\begin_layout Scrap

<<Function prototypes>>=
\newline
int main (int argc, char **argv);
\newline
@
\end_layout

\begin_layout Section

Data Structures
\end_layout

\begin_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.
\end_layout

\begin_layout Scrap

<<Global variables>>=
\newline
char    buffer[200][200];
\newline
int     last_buf_line;
\newline
int     last_err_line;
\newline
int     err_line;
\newline
@ 
\end_layout

\begin_layout Section

The output format
\end_layout

\begin_layout Standard

The output format mimics the TeX 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.
\begin_inset Foot
status collapsed

\begin_layout Standard

This function has been slightly changed from EW's original to make scanning
 a bit easier with LaTeX::scanLogFile().
 The test has been added because LyX can crash if empty lines are allowed
 here --- I can't figure out why! --- BMH
\end_layout

\end_inset


\end_layout

\begin_layout Scrap

<<Function bodies>>=
\newline
void
\newline
output_error (int buf_size, int error_line, char *tool)
\newline
{
\newline
  int     i;
\newline
 
\newline
  fprintf(stdout, "! Build Error: ==> %s ==>
\backslash
n", tool);
\newline
  fprintf(stdout, " ...
\backslash
n
\backslash
nl.%d ...
\backslash
n", error_line);
\newline
 
\newline
  for (i=0; i<buf_size; i++)
\newline
    if (strlen(buffer[i]) != 0)
\newline
      fprintf(stdout, "%s", buffer[i]);
\newline
 
\newline
  fprintf(stdout, "
\backslash
n");
\newline
}
\newline
@
\end_layout

\begin_layout Scrap

<<Function prototypes>>=
\newline
void output_error (int buf_size, int error_line, char *tool);
\newline
@
\end_layout

\begin_layout Section

Functions Implementation
\end_layout

\begin_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.
\end_layout

\begin_layout Scrap

<<Scan input for noweb error messages>>=
\newline
{
\newline
  last_buf_line = 0;
\newline
  while (fgets(buffer[0], 200, stdin)) {
\newline
    if (noweb_try(0))
\newline
      output_error(1, err_line, "noweb");
\newline
  }
\newline
}
\newline
@
\end_layout

\begin_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.
\end_layout

\begin_layout Scrap

<<Global variables>>=
\newline
char *noweb_msgs[] = {
\newline
  "couldn't open file",
\newline
  "couldn't open temporary file",
\newline
  "error writing temporary file",
\newline
  "ill-formed option",
\newline
  "unknown option",
\newline
  "Bad format sequence",
\newline
  "Can't open output file",
\newline
  "Can't open temporary file",
\newline
  "Capacity exceeded:",
\newline
  "Ignoring unknown option -",
\newline
  "This can't happen:",
\newline
  "non-numeric line number in"
\newline
};
\newline

\newline
char *noweb_msgs_mimic_gcc[] = {
\newline
  ": unescaped << in documentation chunk"
\newline
};
\newline
@
\end_layout

\begin_layout Standard

A noweb error message can be any string that contains a matching pair of
 < <\InsetSpace ~
\InsetSpace ~
\InsetSpace ~
> >, or any of the above strings
\end_layout

\begin_layout Scrap

<<Function bodies>>=
\newline
int
\newline
noweb_try (int buf_line)
\newline
{
\newline
  char    *s, *t, *b;
\newline
  int     i; 
\newline

\newline
  b = buffer[buf_line];
\newline
  err_line = 0;
\newline

\newline
  for (i=0; i<1; i++) {
\newline
      s = (char *)strstr (b, noweb_msgs_mimic_gcc[i]);
\newline
      if (s != NULL) {
\newline
        t = (char *)strchr(buffer[buf_line], ':');
\newline
        err_line = atoi(t+1);
\newline
        t = buffer[buf_line];
\newline
        ++s;
\newline
        while (*(t++) = *(s++));
\newline
        return 1;
\newline
      }
\newline
  }
\newline
  s = (char *)strstr(b, "<<");
\newline
  if (s != NULL) {
\newline
    s = (char *)strstr(s+2, ">>");
\newline
    if (s != NULL) {
\newline
      return 1;
\newline
    }
\newline
  } else { 
\newline
     for (i = 0; i < 12; ++i) {
\newline
        s = (char *)strstr (b, noweb_msgs[i]);
\newline
        if (s != NULL) {
\newline
           return 1;
\newline
        }
\newline
    }
\newline
  }
\newline
  return 0;
\newline
}
\newline
@
\end_layout

\begin_layout Scrap

<<Function prototypes>>=
\newline
int noweb_try (int buf_line);
\newline
@
\end_layout

\begin_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.
\end_layout

\begin_layout Scrap

<<Scan input for xlc error messages>>= 
\newline
{
\newline
  last_buf_line = 0;
\newline
  while (fgets(buffer[last_buf_line], 200, stdin)) {
\newline
    if (xlc_try(0))
\newline
      output_error(1, err_line, "xlc");
\newline
  }
\newline
}
\newline
@
\end_layout

\begin_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:
\end_layout

\begin_layout Scrap

<<Function bodies>>=
\newline
int 
\newline
xlc_try (int buf_line)
\newline
{
\newline
  char    *s, *t;
\newline
 
\newline
  t = buffer[buf_line];
\newline
  s = t+1;
\newline
  while (*s != '"' && *s != ' ' && *s != '
\backslash
0')
\newline
    s++;
\newline
  if (*t != '"' || *s != '"' || strncmp(s+1, ", line ", 7) != 0)
\newline
    return 0;
\newline
  s += 8;
\newline
  err_line = atoi(s);
\newline
  return 1;
\newline
}
\newline
@
\end_layout

\begin_layout Scrap

<<Function prototypes>>=
\newline
int xlc_try (int buf_line);
\newline
@
\end_layout

\begin_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.
\end_layout

\begin_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

.
\end_layout

\begin_layout Scrap

<<Scan input for gcc error messages>>=
\newline
{
\newline
  char    *s, *t;
\newline
 
\newline
  last_buf_line = 0;
\newline
  while (fgets(buffer[last_buf_line], 200, stdin)) {
\newline
    /****** Skip lines until I find an error */
\newline
    s = (char *)strpbrk(buffer[last_buf_line], " :");
\newline
    if (s == NULL || *s == ' ')
\newline
      continue; /* No gcc error found here */
\newline
    do {
\newline
      <<gcc error message criteria is to find a "...:999:" or a "...: ">>
\newline
      /****** OK It is an error message, get line number */
\newline
      err_line = atoi(s+1);
\newline
      if (last_err_line == 0 || last_err_line == err_line) {
\newline
        last_err_line = err_line;
\newline
        continue; /* It's either a header or a continuation, don't output
 yet */
\newline
      }
\newline
      /****** Completed the scan of one error message, output it to LyX
 */
\newline
      discharge_buffer(1);
\newline
      break;
\newline
    } while (fgets(buffer[last_buf_line], 200, stdin));
\newline
  }
\newline
  /****** EOF completes the scan of whatever was being scanned */
\newline
  discharge_buffer(0);
\newline
}
\newline
@
\end_layout

\begin_layout Scrap

<<gcc error message criteria is to find a "...:999:" or a "...: ">>=
\newline
/****** Search first ":" in the error number */
\newline
s = (char *)strpbrk(buffer[last_buf_line], " :");
\newline
last_buf_line++;
\newline
if (s == NULL || *s == ' ') 
\newline
  <<No gcc error found here, but it might terminate the scanning of a previous
 one>>
\newline
/****** Search second ":" in the error number */
\newline
t = (char *)strpbrk(s+1, " :");
\newline
if (t == NULL || *t == ' ')
\newline
  <<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
  <<No gcc error found here, but it might terminate the scanning of a previous
 one>>
\newline
@
\end_layout

\begin_layout Scrap

<<No gcc error found here, but it might terminate the scanning of a previous
 one>>=
\newline
{
\newline
  err_line = 0;
\newline
  discharge_buffer(1);
\newline
  continue;
\newline
}
\newline
@
\end_layout

\begin_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.
\end_layout

\begin_layout Scrap

<<Function bodies>>=
\newline
void
\newline
discharge_buffer (int save_last)
\newline
{
\newline
 if (last_err_line != 0) { 
\newline
   clean_gcc_messages();
\newline
   if (save_last != 0) {
\newline
      output_error(last_buf_line-1, last_err_line, "gcc");
\newline
      strcpy (buffer[0], buffer[last_buf_line-1]);
\newline
      last_err_line = err_line;
\newline
      last_buf_line = 1;
\newline
    } else { 
\newline
      ++last_buf_line;
\newline
      clean_gcc_messages();
\newline
      output_error(last_buf_line-1, last_err_line, "gcc");
\newline
      last_err_line = 0;
\newline
      last_buf_line = 0;
\newline
    }
\newline
  }
\newline
}
\newline
@
\end_layout

\begin_layout Scrap

<<Function prototypes>>=
\newline
void discharge_buffer (int save_last);
\newline
@
\end_layout

\begin_layout Standard

The next function 
\begin_inset Quotes eld
\end_inset

cleans
\begin_inset Quotes erd
\end_inset

 superfluous information from gcc messages, namely the name of the noweb
 file and the line number of the Error.
\begin_inset Foot
status collapsed

\begin_layout Standard

More could be done.
 For instance, some way of distinguishing between gcc Errors and Warnings
 should be devised.
\end_layout

\end_inset


\end_layout

\begin_layout Scrap

<<Function bodies>>=
\newline
void
\newline
clean_gcc_messages ()
\newline
{
\newline
  int index;
\newline
  char search [30]; 
\newline
  char *tail, *head; 
\newline
  int search_len = sprintf(search, ".nw:%d:", last_err_line);
\newline
  
\newline
  for (index = 0; index < last_buf_line-1; index++) {
\newline
    tail = (char *)strstr (buffer[index], search);
\newline
    if ( tail == NULL) {
\newline
       tail = (char *) strstr (buffer[index], ".nw:");
\newline
       if (tail) {
\newline
          tail += 4;
\newline
       }
\newline
    } else {
\newline
       tail += search_len;
\newline
    }
\newline
    if (tail != NULL) {
\newline
       head = buffer[index];
\newline
       while (*(head++) = *(tail++));
\newline
    }
\newline
  }
\newline
}
\newline
@
\end_layout

\begin_layout Scrap

<<Function prototypes>>=
\newline
void clean_gcc_messages ();
\newline
@
\end_layout

\begin_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:
\end_layout

\begin_layout Scrap

<<AIX system using both noweb and xlc>>=
\newline
{
\newline
  last_buf_line = 0;
\newline
  while (fgets(buffer[0], 200, stdin)) {
\newline
    if (noweb_try(0))
\newline
      output_error(1, err_line, "noweb");
\newline
    else if (xlc_try(0))
\newline
      output_error(1, err_line, "xlc");
\newline
  }
\newline
}
\newline
@
\end_layout

\begin_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:
\end_layout

\begin_layout Scrap

<<Solaris and Linux systems using both noweb and gcc>>=
\newline
{
\newline
  char    *s, *t;
\newline
 
\newline
  last_buf_line = 0;
\newline
  while (fgets(buffer[last_buf_line], 200, stdin)) {
\newline
    /****** Skip lines until I find an error */
\newline
    if (last_buf_line == 0 && noweb_try(0)) {
\newline
      output_error(1, err_line, "noweb");
\newline
      continue;
\newline
    }
\newline
    s = (char *)strpbrk(buffer[last_buf_line], " :");
\newline
    if (s == NULL || *s == ' ')
\newline
      continue; /* No gcc error found here */
\newline
    do {
\newline
      <<gcc error message criteria is to find a "...:999:" or a "...: ">>
\newline
      /****** OK It is an error, get line number */
\newline
      err_line = atoi(s+1);
\newline
      if (last_err_line == 0 || last_err_line == err_line) {
\newline
        last_err_line = err_line;
\newline
        continue; /* It's either a header or a continuation, don't output
 yet */
\newline
      }
\newline
      /****** Completed the scan of one error message, output it to LyX
 */
\newline
      discharge_buffer(1);
\newline
      break;
\newline
    } while (fgets(buffer[last_buf_line], 200, stdin));
\newline
  }
\newline
  /****** EOF completes the scan of whatever was being scanned */
\newline
  discharge_buffer(0);
\newline
}
\newline
@
\end_layout

\begin_layout Section

Wrapping the code into a file
\end_layout

\begin_layout Scrap

<<listerrors.c>>=
\newline
#include <stdio.h>
\newline
#include <strings.h>       
\newline
 
\newline
<<Global variables>>
\newline
<<Function prototypes>>
\newline
<<Function bodies>>
\newline
@
\end_layout

\begin_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.
\end_layout

\begin_layout Scrap

<<build-script>>=
\newline
#!/bin/sh
\newline
if [ -z "$NOWEB_SOURCE" ]; then NOWEB_SOURCE=Literate.nw; fi
\newline
notangle -L -Rlisterrors.c ${NOWEB_SOURCE} > listerrors.c
\newline
gcc -g -o listerrors listerrors.c
\newline
@
\end_layout

\begin_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:
\end_layout

\begin_layout LyX-Code

#!/bin/sh
\newline
notangle -Rbuild-script $1 | env NOWEB_SOURCE=$1 sh
\end_layout

\begin_layout LyX-Code

\end_layout

\end_body
\end_document