geoff@desint.UUCP (Geoff Kuenning) (06/10/87)
This is Patch Number 1 to the beta posting of ispell. Ispell is an
interactive spell-checking program that is faster, more friendly, and
more flexible than standard UNIX spell. The beta posting itself is
available from the comp.sources.misc archives.
Well, once again it's proven that one shouldn't put a posting together
hastily in the middle of the night. I am rather embarrassed at the
number and nature of the bugs in my ispell beta posting, but I guess
that's water under the bridge at this point.
The patch below renames "fixdict.sh" to "fixdict.X" (by dint of recreating
it); you may want to remove "fixdict.sh" (make clean does this).
Bugs fixed in this patch:
(1) If CAPITALIZE mode is selected, the wrongletter() routine may fail to
properly generate all possibilities.
(2) There were several syntax errors in xgets.c if MAXINCLUDEFILES was
nonzero; also the #if test was backwards (Johan Widen).
(3) Several Makefile problems: CC was not defined as "cc", fixdict.sh
did not respect the definition of LIBDIR; icombine (and now fixdict)
was missing from make clean; and make install referred to
expand[12].sed rather than isexp[1-4].sed. (David Neves, Gary
Johnson, Don Kark)
(4) In term.c, the variables oldtt{in,ou,tstp} are undefined on BSD
systems. (Joel Shprentz, Don Kark)
(5) If CAPITALIZE was undefined, the routine toutent() still referred
to the capitalization-control fields in the dictionary structure.
(Gary Johnson) In fact, the code with CAPITALIZE undefined had
not been recently tested and was full of problems. These have
been corrected and ispell has been tested in this mode, though not
extensively.
(6) In TeX mode, some misspelled words could be missed because a left
brace was not seen as a delimiter. Also, there were still a couple
of nroff hangovers in TeX mode. (Don Kark).
(7) Buildhash.c wouldn't compile without CAPITALIZE.
To install this patch:
From rn, type "|patch -d dir", where dir is the directory where you
have ispell installed. From other newsreaders, save the article, then
type "patch -d dir <savefile" where savefile is the name of the file
you just created.
Geoff Kuenning geoff@ITcorp.com {uunet,trwrb}!desint!geoff
Index: version.h
Prereq: 2.0,
*** version.h.old Tue Jun 9 23:47:25 1987
--- version.h Tue Jun 9 23:47:30 1987
***************
*** 1,2
static char Version_ID[] =
! "@(#) Ispell Version 2.0, May 1987 Beta posting";
--- 1,2 -----
static char Version_ID[] =
! "@(#) Ispell Version 2.0.01, May 1987 Beta posting";
Index: Makefile
*** Makefile.old Wed Jun 10 00:08:29 1987
--- Makefile Wed Jun 10 00:08:33 1987
***************
*** 6,12
# MAN1EXT, MAN4EXT, and TERMLIB below;
# the Makefile will update all other files to match.
#
! # On USG systems, add -DUSG to CFLAGS.
#
# The ifdef NO8BIT may be used if 8 bit extended text characters
# cause problems, or you simply don't wish to allow the feature.
--- 6,12 -----
# MAN1EXT, MAN4EXT, and TERMLIB below;
# the Makefile will update all other files to match.
#
! # On USG systems, add -DUSG to CFLAGS. On BSD, remove it.
#
# The ifdef NO8BIT may be used if 8 bit extended text characters
# cause problems, or you simply don't wish to allow the feature.
***************
*** 16,22
#
# buildhash <infile> <outfile>
! CC = lcc -v -HL -HD -R tgetflag
CFLAGS = -n -O -DUSG
# BINDIR, LIBDIR, DEFHASH, DEFDICT, MAN1DIR, MAN4DIR, MAN1EXT, MAN4EXT,
# TERMLIB
--- 16,22 -----
#
# buildhash <infile> <outfile>
! CC = cc
CFLAGS = -n -O -DUSG
# BINDIR, LIBDIR, DEFHASH, DEFDICT, MAN1DIR, MAN4DIR, MAN1EXT, MAN4EXT,
# TERMLIB
***************
*** 33,39
SHELL = /bin/sh
! all: buildhash ispell icombine munchlist isexpand $(DEFHASH)
ispell.hash: buildhash $(DEFDICT)
./buildhash $(DEFDICT) $(DEFHASH)
--- 33,39 -----
SHELL = /bin/sh
! all: buildhash fixdict ispell icombine munchlist isexpand $(DEFHASH)
ispell.hash: buildhash $(DEFDICT)
./buildhash $(DEFDICT) $(DEFHASH)
***************
*** 41,47
install: all
cp ispell isexpand munchlist $(BINDIR)
cp ispell.hash $(LIBDIR)/$(DEFHASH)
! cp expand1.sed expand2.sed icombine $(LIBDIR)
chmod 755 $(BINDIR)/ispell $(BINDIR)/munchlist $(BINDIR)/isexpand \
$(LIBDIR)/icombine
chmod 644 $(LIBDIR)/$(DEFHASH) $(LIBDIR)/expand1.sed \
--- 41,47 -----
install: all
cp ispell isexpand munchlist $(BINDIR)
cp ispell.hash $(LIBDIR)/$(DEFHASH)
! cp isexp[1-4].sed icombine $(LIBDIR)
chmod 755 $(BINDIR)/ispell $(BINDIR)/munchlist $(BINDIR)/isexpand \
$(LIBDIR)/icombine
chmod 644 $(LIBDIR)/$(DEFHASH) $(LIBDIR)/isexp[1-4].sed
***************
*** 44,51
cp expand1.sed expand2.sed icombine $(LIBDIR)
chmod 755 $(BINDIR)/ispell $(BINDIR)/munchlist $(BINDIR)/isexpand \
$(LIBDIR)/icombine
! chmod 644 $(LIBDIR)/$(DEFHASH) $(LIBDIR)/expand1.sed \
! $(LIBDIR)/expand2.sed
cp ispell.1 $(MAN1DIR)/ispell$(MAN1EXT)
cp ispell.4 $(MAN4DIR)/ispell$(MAN4EXT)
--- 44,50 -----
cp isexp[1-4].sed icombine $(LIBDIR)
chmod 755 $(BINDIR)/ispell $(BINDIR)/munchlist $(BINDIR)/isexpand \
$(LIBDIR)/icombine
! chmod 644 $(LIBDIR)/$(DEFHASH) $(LIBDIR)/isexp[1-4].sed
cp ispell.1 $(MAN1DIR)/ispell$(MAN1EXT)
cp ispell.4 $(MAN4DIR)/ispell$(MAN4EXT)
***************
*** 52,57
buildhash: buildhash.o hash.o
$(CC) $(CFLAGS) -o buildhash buildhash.o hash.o
icombine: icombine.c config.h ispell.h
$(CC) $(CFLAGS) -o icombine icombine.c
--- 51,61 -----
buildhash: buildhash.o hash.o
$(CC) $(CFLAGS) -o buildhash buildhash.o hash.o
+ fixdict: fixdict.X Makefile
+ sed -e 's@!!LIBDIR!!@$(LIBDIR)@' -e 's@!!DEFDICT!!@$(DEFDICT)@' \
+ <fixdict.X >fixdict
+ chmod +x fixdict
+
icombine: icombine.c config.h ispell.h
$(CC) $(CFLAGS) -o icombine icombine.c
***************
*** 78,81
clean:
rm -f *.o buildhash ispell core a.out mon.out hash.out \
! *.stat *.cnt munchlist config.h
--- 82,85 -----
clean:
rm -f *.o buildhash ispell core a.out mon.out hash.out \
! *.stat *.cnt fixdict fixdict.sh icombine munchlist config.h
Index: buildhash.c
*** buildhash.c.old Wed Jun 10 00:05:38 1987
--- buildhash.c Wed Jun 10 00:05:45 1987
***************
*** 240,245
d.word = malloc (2 * len + 4);
else
d.word = malloc (len + 1);
#endif
if (d.word == NULL) {
fprintf (stderr, "couldn't allocate space for word %s\n", lbuf);
--- 240,247 -----
d.word = malloc (2 * len + 4);
else
d.word = malloc (len + 1);
+ #else
+ d.word = malloc (len + 1);
#endif
if (d.word == NULL) {
fprintf (stderr, "couldn't allocate space for word %s\n", lbuf);
***************
*** 339,344
hashtbl[h].next = dp;
}
}
}
printf ("\n");
}
--- 341,347 -----
hashtbl[h].next = dp;
}
}
+ #ifdef CAPITALIZE
}
#endif
printf ("\n");
***************
*** 340,345
}
}
}
printf ("\n");
}
--- 343,349 -----
}
#ifdef CAPITALIZE
}
+ #endif
printf ("\n");
}
Index: fixdict.X
0a1,79
> : Use /bin/sh
> #
> # Add capitalization information to an ispell dictionary
> #
> # Usage:
> #
> # fixdict dict-file
> #
> # Requires availability of UNIX spell. The new dictionary is
> # rewritten in place. A list of words that couldn't be
> # resolved (because spell doesn't know them) is written to
> # standard output. This list appears in lowercase in the
> # dictionary, and if there are any errors the must be edited
> # by hand.
> #
> # The final dictionary appears in expanded form and must be
> # passed through munchlist to regenerate suffixes.
> #
> LIBDIR=!!LIBDIR!!
> EXPAND1=${LIBDIR}/isexp1.sed
> EXPAND2=${LIBDIR}/isexp2.sed
> EXPAND3=${LIBDIR}/isexp3.sed
> EXPAND4=${LIBDIR}/isexp4.sed
> TDIR=${TMPDIR:-/tmp}
> TMP=${TDIR}/fix$$
>
> trap "/bin/rm -f ${TMP}*; exit 1" 1 2 15
> sed -f ${EXPAND1} $1 | sed -f ${EXPAND2} \
> | sed -f ${EXPAND3} | sed -f ${EXPAND4} \
> | tr '[A-Z]' '[a-z]' \
> | spell \
> | sort > ${TMP}a
> #
> # ${TMP}a contains all the words that spell doesn't like.
> # Now figure out which of those are because spell doesn't know them at
> # all, and leave those in ${TMP}b.
> #
> tr '[a-z]' '[A-Z]' < ${TMP}a | spell | tr '[A-Z]' '[a-z]' > ${TMP}b
> #
> # The wrongly-capitalized words are those that spell didn't object to
> # in the last step. Produce a list of them in, and capitalize the
> # first letter of each. Save this list in ${TMP}c.
> #
> comm -23 ${TMP}a ${TMP}b \
> | sed 's/^a/A/;s/^b/B/;s/^c/C/;s/^d/D/;s/^e/E/;s/^f/F/;s/^g/G/;s/^h/H/
> s/^i/I/;s/^j/J/;s/^k/K/;s/^l/L/;s/^m/M/;s/^n/N/;s/^o/O/;s/^p/P/
> s/^q/Q/;s/^r/R/;s/^s/S/;s/^t/T/;s/^u/U/;s/^v/V/;s/^w/W/;s/^x/X/
> s/^y/Y/;s/^z/Z/' > ${TMP}c
> #
> # Find out which of those spell objects to, saving the failures in ${TMP}d.
> #
> spell ${TMP}c > ${TMP}d
> #
> # Extract the words which were correctly capitalized at the first letter,
> # combine them with an all-capitals version of the ones that weren't, and
> # put the result into ${TMP}e.
> #
> (comm -23 ${TMP}c ${TMP}d; tr '[a-z]' '[A-Z]' < ${TMP}d) \
> | sort -o ${TMP}e
> #
> # At this point, ${TMP}b contains the words that spell just plain doesn't
> # like, and ${TMP}e contains the words that are now capitalized correctly.
> #
> /bin/rm ${TMP}[cd]
> #
> # Put it all together, rewriting the dictionary in place.
> #
> sed -f ${EXPAND1} $1 | sed -f ${EXPAND2} \
> | sed -f ${EXPAND3} | sed -f ${EXPAND4} \
> | tr '[A-Z]' '[a-z]' \
> | sort \
> | comm -23 - ${TMP}a \
> | sort -f -o $1 - ${TMP}b ${TMP}e
> #
> # Finally, write the list of words that have questionable capitalization
> # to the standard output.
> #
> cat ${TMP}b
> /bin/rm ${TMP}*
Index: ispell.c
*** ispell.c.old Wed Jun 10 00:25:46 1987
--- ispell.c Wed Jun 10 00:26:14 1987
***************
*** 37,42
#include "ispell.h"
#include "version.h"
FILE *infile;
FILE *outfile;
--- 37,47 -----
#include "ispell.h"
#include "version.h"
+ #define ISTEXTERM(c) (((c) == '{') || \
+ ((c) == '}') || \
+ ((c) == '[') || \
+ ((c) == ']'))
+
FILE *infile;
FILE *outfile;
***************
*** 437,449
len = strlen (secondbuf) - 1;
! /* skip over .if */
! if (strncmp(currentchar,".if t",5) == 0
! || strncmp(currentchar,".if n",5) == 0) {
! copyout(¤tchar,5);
! while (*currentchar && isspace(*currentchar))
! copyout(¤tchar, 1);
! }
/* skip over .ds XX or .nr XX */
if (strncmp(currentchar,".ds ",4) == 0
--- 442,455 -----
len = strlen (secondbuf) - 1;
! if(!tflag) {
! /* skip over .if */
! if (strncmp(currentchar,".if t",5) == 0
! || strncmp(currentchar,".if n",5) == 0) {
! copyout(¤tchar,5);
! while (*currentchar && isspace(*currentchar))
! copyout(¤tchar, 1);
! }
/* skip over .ds XX or .nr XX */
if (strncmp(currentchar,".ds ",4) == 0
***************
*** 445,463
copyout(¤tchar, 1);
}
! /* skip over .ds XX or .nr XX */
! if (strncmp(currentchar,".ds ",4) == 0
! || strncmp(currentchar,".de ",4) == 0
! || strncmp(currentchar,".nr ",4) == 0) {
! copyout(¤tchar, 3);
! while (*currentchar && isspace(*currentchar))
! copyout(¤tchar, 1);
! while (*currentchar && !isspace(*currentchar))
! copyout(¤tchar, 1);
! if (*currentchar == 0) {
! if (!lflag) putc ('\n', outfile);
! continue;
! }
}
if (secondbuf [ len ] == '\n')
--- 451,470 -----
copyout(¤tchar, 1);
}
! /* skip over .ds XX or .nr XX */
! if (strncmp(currentchar,".ds ",4) == 0
! || strncmp(currentchar,".de ",4) == 0
! || strncmp(currentchar,".nr ",4) == 0) {
! copyout(¤tchar, 3);
! while (*currentchar && isspace(*currentchar))
! copyout(¤tchar, 1);
! while (*currentchar && !isspace(*currentchar))
! copyout(¤tchar, 1);
! if (*currentchar == 0) {
! if (!lflag) putc ('\n', outfile);
! continue;
! }
! }
}
if (secondbuf [ len ] == '\n')
***************
*** 484,490
if (*currentchar == '\\') {
/* skip till whitespace */
while (*currentchar &&
! !isspace(*currentchar)) {
if (!lflag)
putc(*currentchar, outfile);
currentchar++;
--- 491,498 -----
if (*currentchar == '\\') {
/* skip till whitespace */
while (*currentchar &&
! (!isspace(*currentchar) &&
! !ISTEXTERM(*currentchar))) {
if (!lflag)
putc(*currentchar, outfile);
currentchar++;
***************
*** 960,965
return;
}
}
newword[i] = word[i];
}
}
--- 968,980 -----
return;
}
}
+ #ifdef CAPITALIZE
+ c = word[i];
+ if (islower (c))
+ newword[i] = toupper (c);
+ else
+ newword[i] = c;
+ #else
newword[i] = word[i];
#endif
}
***************
*** 961,966
}
}
newword[i] = word[i];
}
}
--- 976,982 -----
newword[i] = c;
#else
newword[i] = word[i];
+ #endif
}
}
Index: ispell.1
*** ispell.1.old Wed Jun 10 00:28:13 1987
--- ispell.1 Wed Jun 10 00:28:21 1987
***************
*** 376,384
.I ispell
to read in the hash table.
.sp
! Perhaps more than ten choices should be allowed for near misses.
! .sp
! The hash table is stored as a quarter-megabyte array, so a PDP-11
version does not seem likely.
.sp
.I Ispell
--- 376,382 -----
.I ispell
to read in the hash table.
.sp
! The hash table is stored as a quarter-megabyte (or larger) array, so a PDP-11
version does not seem likely.
.sp
.I Ispell
***************
*** 425,430
Stewart Clamen,
Mark Davies,
Steve Dum,
Don Kark,
Steve Kelem,
Jim Knutson,
--- 423,429 -----
Stewart Clamen,
Mark Davies,
Steve Dum,
+ Gary Johnson,
Don Kark,
Steve Kelem,
Jim Knutson,
***************
*** 441,446
Marc Ries,
Rich Salz,
Greg Schaffer,
George Sipe,
Perry Smith,
Stefan Taxhet,
--- 440,446 -----
Marc Ries,
Rich Salz,
Greg Schaffer,
+ Joel Shprentz,
George Sipe,
Perry Smith,
Stefan Taxhet,
***************
*** 445,449
Perry Smith,
Stefan Taxhet,
Andrew Vignaux,
James Woods,
and Ken Yap.
--- 445,450 -----
Perry Smith,
Stefan Taxhet,
Andrew Vignaux,
+ Johan Widen,
James Woods,
and Ken Yap.
Index: term.c
*** term.c.old Wed Jun 10 00:29:35 1987
--- term.c Wed Jun 10 00:29:39 1987
***************
*** 68,73
static termchanged = 0;
static int (*oldint) ();
static int (*oldterm) ();
terminit ()
{
--- 68,78 -----
static termchanged = 0;
static int (*oldint) ();
static int (*oldterm) ();
+ #ifdef SIGTTIN
+ static int (*oldttin) ();
+ static int (*oldttou) ();
+ static int (*oldtstp) ();
+ #endif
terminit ()
{
***************
*** 228,236
signal (SIGINT, oldint);
signal (SIGTERM, oldterm);
#ifdef SIGTTIN
! signal(SIGTTIN, SIG_DFL);
! signal(SIGTTOU, SIG_DFL);
! signal(SIGTSTP, SIG_DFL);
#endif
system (buf);
--- 233,241 -----
signal (SIGINT, oldint);
signal (SIGTERM, oldterm);
#ifdef SIGTTIN
! oldttin = signal(SIGTTIN, SIG_DFL);
! oldttou = signal(SIGTTOU, SIG_DFL);
! oldtstp = signal(SIGTSTP, SIG_DFL);
#endif
system (buf);
Index: tree.c
*** tree.c.old Wed Jun 10 00:31:23 1987
--- tree.c Wed Jun 10 00:31:34 1987
***************
*** 632,637
toutent (cent)
register struct dent *cent;
{
register char *cp;
int len;
register int wcount;
--- 632,638 -----
toutent (cent)
register struct dent *cent;
{
+ #ifdef CAPITALIZE
register char *cp;
int len;
register int wcount;
***************
*** 659,664
cent->word[0] = toupper (cent->word[0]);
toutword (cent->word, cent);
}
}
static
--- 660,668 -----
cent->word[0] = toupper (cent->word[0]);
toutword (cent->word, cent);
}
+ #else
+ toutword (cent->word, cent);
+ #endif
}
static
Index: xgets.c
*** xgets.c.old Wed Jun 10 00:33:05 1987
--- xgets.c Wed Jun 10 00:33:08 1987
***************
*** 22,28
xgets (str)
char str [];
{
! #if MAXINCLUDFILES == 0
return gets (str);
#else
static char * Include_File = DEFINCSTR;
--- 22,28 -----
xgets (str)
char str [];
{
! #if MAXINCLUDEFILES == 0
return gets (str);
#else
static char * Include_File = DEFINCSTR;
***************
*** 35,41
if (Include_Len == 0) {
char * env_variable, * getenv ();
! if ((env_variable = getenv (INCSTRVAR) != NULL)
Include_File = env_variable;
Include_Len = strlen (Include_File);
--- 35,41 -----
if (Include_Len == 0) {
char * env_variable, * getenv ();
! if ((env_variable = getenv (INCSTRVAR)) != NULL)
Include_File = env_variable;
Include_Len = strlen (Include_File);
***************
*** 59,65
if (incfileflag != 0 && strncmp (str, Include_File, Include_Len) == 0) {
char * file_name = str + Include_Len;
! if (current_F - F < MAX_FILES && strlen (file_name) > 0) {
FILE * f;
if (f = fopen (file_name, "r"))
*(++current_F) = f;
--- 59,65 -----
if (incfileflag != 0 && strncmp (str, Include_File, Include_Len) == 0) {
char * file_name = str + Include_Len;
! if (current_F - F < MAXINCLUDEFILES && strlen (file_name) > 0) {
FILE * f;
if (f = fopen (file_name, "r"))
*(++current_F) = f;