cweave.w

模拟器提供了一个简单易用的平台

strings will not be entered into the cross reference lists since they are not
definitions of section names.

The program uses the fact that our internal code numbers satisfy
the relations |xref_roman==identifier+roman| and |xref_wildcard==identifier
+wildcard| and |xref_typewriter==identifier+typewriter|,
as well as |normal==0|.

@<Predecl...@>=
void C_xref();

@ @c
void
C_xref( spec_ctrl ) /* makes cross-references for \CEE/ identifiers */
  eight_bits spec_ctrl;
{
  name_pointer p; /* a referenced name */
  while (next_control<format_code || next_control==spec_ctrl) {
    if (next_control>=identifier && next_control<=xref_typewriter) {
      if (next_control>identifier) @<Replace |"@@@@"| by |"@@"| @>@;
      p=id_lookup(id_first, id_loc,next_control-identifier); new_xref(p);
    }
    if (next_control==section_name) {
      section_xref_switch=cite_flag;
      new_section_xref(cur_section);
    }
    next_control=get_next();
    if (next_control=='|' || next_control==begin_comment ||
        next_control==begin_short_comment) return;
  }
}

@ The |outer_xref| subroutine is like |C_xref| except that it begins
with |next_control!='|'| and ends with |next_control>=format_code|. Thus, it
handles \CEE/ text with embedded comments.

@<Predecl...@>=
void outer_xref();

@ @c
void
outer_xref() /* extension of |C_xref| */
{
  int bal; /* brace level in comment */
  while (next_control<format_code)
    if (next_control!=begin_comment && next_control!=begin_short_comment)
      C_xref(ignore);
    else {
      boolean is_long_comment=(next_control==begin_comment);
      bal=copy_comment(is_long_comment,1); next_control='|';
      while (bal>0) {
        C_xref(section_name); /* do not reference section names in comments */
        if (next_control=='|') bal=copy_comment(is_long_comment,bal);
        else bal=0; /* an error message will occur in phase two */
      }
    }
}

@ In the \TEX/ part of a section, cross-reference entries are made only for
the identifiers in \CEE/ texts enclosed in \pb, or for control texts
enclosed in \.{@@\^}$\,\ldots\,$\.{@@>} or \.{@@.}$\,\ldots\,$\.{@@>}
or \.{@@:}$\,\ldots\,$\.{@@>}.

@<Store cross-references in the \T...@>=
while (1) {
  switch (next_control=skip_TeX()) {
    case translit_code: err_print("! Use @@l in limbo only"); continue;
@.Use @@l in limbo...@>
    case underline: xref_switch=def_flag; continue;
    case trace: tracing=*(loc-1)-'0'; continue;
    case '|': C_xref(section_name); break;
    case xref_roman: case xref_wildcard: case xref_typewriter:
    case noop: case section_name:
      loc-=2; next_control=get_next(); /* scan to \.{@@>} */
      if (next_control>=xref_roman && next_control<=xref_typewriter) {
        @<Replace |"@@@@"| by |"@@"| @>@;
        new_xref(id_lookup(id_first, id_loc,next_control-identifier));
      }
      break;
  }
  if (next_control>=format_code) break;
}

@ @<Replace |"@@@@"| by |"@@"| @>=
{
  char *src=id_first,*dst=id_first;
  while(src<id_loc){
    if(*src=='@@') src++;
    *dst++=*src++;
  }
  id_loc=dst;
  while (dst<src) *dst++=' '; /* clean up in case of error message display */
}

@ During the definition and \CEE/ parts of a section, cross-references
are made for all identifiers except reserved words. However, the right
identifier in a format definition is not referenced, and the left
identifier is referenced only if it has been explicitly
underlined (preceded by \.{@@!}).
The \TEX/ code in comments is, of course, ignored, except for
\CEE/ portions enclosed in \pb; the text of a section name is skipped
entirely, even if it contains \pb\ constructions.

The variables |lhs| and |rhs| point to the respective identifiers involved
in a format definition.

@<Global...@>=
name_pointer lhs, rhs; /* pointers to |byte_start| for format identifiers */
name_pointer res_wd_end; /* pointer to the first nonreserved identifier */

@ When we get to the following code we have |next_control>=format_code|.

@<Store cross-references in the d...@>=
while (next_control<=definition) { /* |format_code| or |definition| */
  if (next_control==definition) {
    xref_switch=def_flag; /* implied \.{@@!} */
    next_control=get_next();
  } else @<Process a format definition@>;
  outer_xref();
}

@ Error messages for improper format definitions will be issued in phase
two. Our job in phase one is to define the |ilk| of a properly formatted
identifier, and to remove cross-references to identifiers that we now
discover should be unindexed.

@<Process a form...@>= {
  next_control=get_next();
  if (next_control==identifier) {
    lhs=id_lookup(id_first, id_loc,normal); lhs->ilk=normal;
    if (xref_switch) new_xref(lhs);
    next_control=get_next();
    if (next_control==identifier) {
      rhs=id_lookup(id_first, id_loc,normal);
      lhs->ilk=rhs->ilk;
      if (unindexed(lhs)) { /* retain only underlined entries */
        xref_pointer q,r=NULL;
        for (q=(xref_pointer)lhs->xref;q>xmem;q=q->xlink)
          if (q->num<def_flag)
            if (r) r->xlink=q->xlink;
            else lhs->xref=(char*)q->xlink;
          else r=q;
      }
      next_control=get_next();
    }
  }
}

@ A much simpler processing of format definitions occurs when the
definition is found in limbo.

@<Process simple format in limbo@>=
{
  if (get_next()!=identifier)
    err_print("! Missing left identifier of @@s");
@.Missing left identifier...@>
  else {
    lhs=id_lookup(id_first,id_loc,normal);
    if (get_next()!=identifier)
      err_print("! Missing right identifier of @@s");
@.Missing right identifier...@>
    else {
      rhs=id_lookup(id_first,id_loc,normal);
      lhs->ilk=rhs->ilk;
    }
  }
}

@ Finally, when the \TEX/ and definition parts have been treated, we have
|next_control>=begin_C|.

@<Store cross-references in the \CEE/...@>=
if (next_control<=section_name) {  /* |begin_C| or |section_name| */
  if (next_control==begin_C) section_xref_switch=0;
  else {
    section_xref_switch=def_flag;
    if(cur_section_char=='(' && cur_section!=name_dir)
      set_file_flag(cur_section);
  }
  do {
    if (next_control==section_name && cur_section!=name_dir)
      new_section_xref(cur_section);
    next_control=get_next(); outer_xref();
  } while ( next_control<=section_name);
}

@ After phase one has looked at everything, we want to check that each
section name was both defined and used.  The variable |cur_xref| will point
to cross-references for the current section name of interest.

@<Global...@>=
xref_pointer cur_xref; /* temporary cross-reference pointer */
boolean an_output; /* did |file_flag| precede |cur_xref|? */

@ The following recursive procedure
walks through the tree of section names and prints out anomalies.
@^recursion@>

@<Predecl...@>=
void section_check();

@ @c
void
section_check(p)
name_pointer p; /* print anomalies in subtree |p| */
{
  if (p) {
    section_check(p->llink);
    cur_xref=(xref_pointer)p->xref;
    if (cur_xref->num==file_flag) {an_output=1; cur_xref=cur_xref->xlink;}
    else an_output=0;
    if (cur_xref->num <def_flag) {
      printf("\n! Never defined: <"); print_section_name(p); putchar('>'); mark_harmless;
@.Never defined: <section name>@>
    }
    while (cur_xref->num >=cite_flag) cur_xref=cur_xref->xlink;
    if (cur_xref==xmem && !an_output) {
      printf("\n! Never used: <"); print_section_name(p); putchar('>'); mark_harmless;
@.Never used: <section name>@>
    }
    section_check(p->rlink);
  }
}

@ @<Print error messages about un...@>=section_check(root)

@* Low-level output routines.
The \TEX/ output is supposed to appear in lines at most |line_length|
characters long, so we place it into an output buffer. During the output
process, |out_line| will hold the current line number of the line about to
be output.

@<Global...@>=
char out_buf[line_length+1]; /* assembled characters */
char *out_ptr; /* just after last character in |out_buf| */
char *out_buf_end = out_buf+line_length; /* end of |out_buf| */
int out_line; /* number of next line to be output */

@ The |flush_buffer| routine empties the buffer up to a given breakpoint,
and moves any remaining characters to the beginning of the next line.
If the |per_cent| parameter is 1 a |'%'| is appended to the line
that is being output; in this case the breakpoint |b| should be strictly
less than |out_buf_end|. If the |per_cent| parameter is |0|,
trailing blanks are suppressed.
The characters emptied from the buffer form a new line of output;
if the |carryover| parameter is true, a |"%"| in that line will be
carried over to the next line (so that \TEX/ will ignore the completion
of commented-out text).

@d c_line_write(c) fflush(active_file),fwrite(out_buf+1,sizeof(char),c,active_file)
@d tex_putc(c) putc(c,active_file)
@d tex_new_line putc('\n',active_file)
@d tex_printf(c) fprintf(active_file,c)

@c
void
flush_buffer(b,per_cent,carryover)
char *b;  /* outputs from |out_buf+1| to |b|,where |b<=out_ptr| */
boolean per_cent,carryover;
{
  char *j; j=b; /* pointer into |out_buf| */
  if (! per_cent) /* remove trailing blanks */
    while (j>out_buf && *j==' ') j--;
  c_line_write(j-out_buf);
  if (per_cent) tex_putc('%');
  tex_new_line; out_line++;
  if (carryover)
    while (j>out_buf)
      if (*j--=='%' && (j==out_buf || *j!='\\')) {
        *b--='%'; break;
      }
  if (b<out_ptr) strncpy(out_buf+1,b+1,out_ptr-b);
  out_ptr-=b-out_buf;
}

@ When we are copying \TEX/ source material, we retain line breaks
that occur in the input, except that an empty line is not
output when the \TEX/ source line was nonempty. For example, a line
of the \TEX/ file that contains only an index cross-reference entry
will not be copied. The |finish_line| routine is called just before
|get_line| inputs a new line, and just after a line break token has
been emitted during the output of translated \CEE/ text.

@c
void
finish_line() /* do this at the end of a line */
{
  char *k; /* pointer into |buffer| */
  if (out_ptr>out_buf) flush_buffer(out_ptr,0,0);
  else {
    for (k=buffer; k<=limit; k++)
      if (!(xisspace(*k))) return;
    flush_buffer(out_buf,0,0);
  }
}

@ In particular, the |finish_line| procedure is called near the very
beginning of phase two. We initialize the output variables in a slightly
tricky way so that the first line of the output file will be
`\.{\\input cwebmac}'.

@<Set init...@>=
out_ptr=out_buf+1; out_line=1; active_file=tex_file;
*out_ptr='c'; tex_printf("\\input cwebma");

@ When we wish to append one character |c| to the output buffer, we write
`|out(c)|'; this will cause the buffer to be emptied if it was already
full.  If we want to append more than one character at once, we say
|out_str(s)|, where |s| is a string containing the characters.

A line break will occur at a space or after a single-nonletter
\TEX/ control sequence.

@d out(c) {if (out_ptr>=out_buf_end) break_out(); *(++out_ptr)=c;}

@c
void
out_str(s) /* output characters from |s| to end of string */
char *s;
{
  while (*s) out(*s++);
}

@ The |break_out| routine is called just before the output buffer is about
to overflow. To make this routine a little faster, we initialize position
0 of the output buffer to `\.\\'; this character isn't really output.

@<Set init...@>=
out_buf[0]='\\';

@ A long line is broken at a blank space or just before a backslash that isn't
preceded by another backslash. In the latter case, a |'%'| is output at
the break.

@<Predecl...@>=
void break_out();

@ @c
void
break_out() /* finds a way to break the output line */
{
  char *k=out_ptr; /* pointer into |out_buf| */
  while (1) {
    if (k==out_buf) @<Print warning message, break the line, |return|@>;
    if (*k==' ') {
      flush_buffer(k,0,1); return;
    }
    if (*(k--)=='\\' && *k!='\\') { /* we've decreased |k| */
      flush_buffer(k,1,1); return;
    }
  }
}

@ We get to this section only in the unusual case that the entire output line
consists of a string of backslashes followed by a string of nonblank
non-backslashes. In such cases it is almost always safe to break the