Small tweaks for release.

[mandoc.git] / read.c

diff --git a/read.c b/read.c
index 8d59b23f43df751ebd8ebc10ed9a74f4d356e372..5b14e357d2bd8bfafe8f3a63f9ae8dfe3a19a976 100644 (file)
--- a/read.c
+++ b/read.c
@@ -1,4 +1,4 @@
-/*     $Id: read.c,v 1.19 2011/07/18 14:30:51 kristaps Exp $ */
+/*     $Id: read.c,v 1.28 2012/02/16 20:51:31 joerg Exp $ */

 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010, 2011 Ingo Schwarze <schwarze@openbsd.org>
 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010, 2011 Ingo Schwarze <schwarze@openbsd.org>


@@ -28,6 +28,7 @@
 #include <ctype.h>
 #include <fcntl.h>
 #include <stdarg.h>
 #include <ctype.h>
 #include <fcntl.h>
 #include <stdarg.h>

+#include <stdint.h>

 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>


@@ -37,6 +38,7 @@
 #include "libmandoc.h"
 #include "mdoc.h"
 #include "man.h"
 #include "libmandoc.h"
 #include "mdoc.h"
 #include "man.h"

+#include "main.h"

 
 #ifndef MAP_FILE
 #define        MAP_FILE        0
 
 #ifndef MAP_FILE
 #define        MAP_FILE        0


@@ -63,13 +65,13 @@ struct      mparse {
        mandocmsg         mmsg; /* warning/error message handler */
        void             *arg; /* argument to mmsg */
        const char       *file; 
        mandocmsg         mmsg; /* warning/error message handler */
        void             *arg; /* argument to mmsg */
        const char       *file; 

+       struct buf       *secondary;

 };
 
 static void      resize_buf(struct buf *, size_t);
 static void      mparse_buf_r(struct mparse *, struct buf, int);
 static void      mparse_readfd_r(struct mparse *, int, const char *, int);
 static void      pset(const char *, int, struct mparse *);
 };
 
 static void      resize_buf(struct buf *, size_t);
 static void      mparse_buf_r(struct mparse *, struct buf, int);
 static void      mparse_readfd_r(struct mparse *, int, const char *, int);
 static void      pset(const char *, int, struct mparse *);

-static void      pdesc(struct mparse *, const char *, int);

 static int       read_whole_file(const char *, int, struct buf *, int *);
 static void      mparse_end(struct mparse *);
 
 static int       read_whole_file(const char *, int, struct buf *, int *);
 static void      mparse_end(struct mparse *);
 


@@ -152,8 +154,11 @@ static     const char * const      mandocerrs[MANDOCERR_MAX] = {
        "generic error",
 
        /* related to equations */
        "generic error",
 
        /* related to equations */

-       "bad equation macro syntax",
-       "too many nested equation defines",
+       "unexpected equation scope closure",
+       "equation scope open on exit",
+       "overlapping equation scopes",
+       "unexpected end of equation",
+       "equation syntax error",

 
        /* related to tables */
        "bad table syntax",
 
        /* related to tables */
        "bad table syntax",


@@ -188,7 +193,6 @@ static      const char * const      mandocerrs[MANDOCERR_MAX] = {
        "not a manual",
        "column syntax is inconsistent",
        "NOT IMPLEMENTED: .Bd -file",
        "not a manual",
        "column syntax is inconsistent",
        "NOT IMPLEMENTED: .Bd -file",

-       "line scope broken, syntax violated",

        "argument count wrong, violates syntax",
        "child violates parent syntax",
        "argument count wrong, violates syntax",
        "argument count wrong, violates syntax",
        "child violates parent syntax",
        "argument count wrong, violates syntax",


@@ -322,9 +326,9 @@ mparse_buf_r(struct mparse *curp, struct buf blk, int start)
                         * Warn about bogus characters.  If you're using
                         * non-ASCII encoding, you're screwing your
                         * readers.  Since I'd rather this not happen,
                         * Warn about bogus characters.  If you're using
                         * non-ASCII encoding, you're screwing your
                         * readers.  Since I'd rather this not happen,

-                        * I'll be helpful and drop these characters so
-                        * we don't display gibberish.  Note to manual
-                        * writers: use special characters.
+                        * I'll be helpful and replace these characters
+                        * with "?", so we don't display gibberish.
+                        * Note to manual writers: use special characters.

                         */
 
                        c = (unsigned char) blk.buf[i];
                         */
 
                        c = (unsigned char) blk.buf[i];


@@ -332,8 +336,11 @@ mparse_buf_r(struct mparse *curp, struct buf blk, int start)
                        if ( ! (isascii(c) && 
                                        (isgraph(c) || isblank(c)))) {
                                mandoc_msg(MANDOCERR_BADCHAR, curp,
                        if ( ! (isascii(c) && 
                                        (isgraph(c) || isblank(c)))) {
                                mandoc_msg(MANDOCERR_BADCHAR, curp,

-                                               curp->line, pos, "ignoring byte");
+                                               curp->line, pos, NULL);

                                i++;
                                i++;

+                               if (pos >= (int)ln.sz)
+                                       resize_buf(&ln, 256);
+                               ln.buf[pos++] = '?';

                                continue;
                        }
 
                                continue;
                        }
 


@@ -408,6 +415,27 @@ mparse_buf_r(struct mparse *curp, struct buf blk, int start)
 
                of = 0;
 
 
                of = 0;
 

+               /*
+                * Maintain a lookaside buffer of all parsed lines.  We
+                * only do this if mparse_keep() has been invoked (the
+                * buffer may be accessed with mparse_getkeep()).
+                */
+
+               if (curp->secondary) {
+                       curp->secondary->buf = 
+                               mandoc_realloc
+                               (curp->secondary->buf, 
+                                curp->secondary->sz + pos + 2);
+                       memcpy(curp->secondary->buf + 
+                                       curp->secondary->sz, 
+                                       ln.buf, pos);
+                       curp->secondary->sz += pos;
+                       curp->secondary->buf
+                               [curp->secondary->sz] = '\n';
+                       curp->secondary->sz++;
+                       curp->secondary->buf
+                               [curp->secondary->sz] = '\0';
+               }

 rerun:
                rr = roff_parseln
                        (curp->roff, curp->line, 
 rerun:
                rr = roff_parseln
                        (curp->roff, curp->line, 


@@ -434,6 +462,13 @@ rerun:
                        assert(MANDOCLEVEL_FATAL <= curp->file_status);
                        break;
                case (ROFF_SO):
                        assert(MANDOCLEVEL_FATAL <= curp->file_status);
                        break;
                case (ROFF_SO):

+                       /*
+                        * We remove `so' clauses from our lookaside
+                        * buffer because we're going to descend into
+                        * the file recursively.
+                        */
+                       if (curp->secondary) 
+                               curp->secondary->sz -= pos + 1;

                        mparse_readfd_r(curp, -1, ln.buf + of, 1);
                        if (MANDOCLEVEL_FATAL <= curp->file_status)
                                break;
                        mparse_readfd_r(curp, -1, ln.buf + of, 1);
                        if (MANDOCLEVEL_FATAL <= curp->file_status)
                                break;


@@ -513,38 +548,6 @@ rerun:
        free(ln.buf);
 }
 
        free(ln.buf);
 }
 

-static void
-pdesc(struct mparse *curp, const char *file, int fd)
-{
-       struct buf       blk;
-       int              with_mmap;
-
-       /*
-        * Run for each opened file; may be called more than once for
-        * each full parse sequence if the opened file is nested (i.e.,
-        * from `so').  Simply sucks in the whole file and moves into
-        * the parse phase for the file.
-        */
-
-       if ( ! read_whole_file(file, fd, &blk, &with_mmap)) {
-               curp->file_status = MANDOCLEVEL_SYSERR;
-               return;
-       }
-
-       /* Line number is per-file. */
-
-       curp->line = 1;
-
-       mparse_buf_r(curp, blk, 1);
-
-#ifdef HAVE_MMAP
-       if (with_mmap)
-               munmap(blk.buf, blk.sz);
-       else
-#endif
-               free(blk.buf);
-}
-

 static int
 read_whole_file(const char *file, int fd, struct buf *fb, int *with_mmap)
 {
 static int
 read_whole_file(const char *file, int fd, struct buf *fb, int *with_mmap)
 {


@@ -640,29 +643,72 @@ mparse_end(struct mparse *curp)
 }
 
 static void
 }
 
 static void

-mparse_readfd_r(struct mparse *curp, int fd, const char *file, int re)
+mparse_parse_buffer(struct mparse *curp, struct buf blk, const char *file,
+               int re)

 {
        const char      *svfile;
 
 {
        const char      *svfile;
 

+       /* Line number is per-file. */
+       svfile = curp->file;
+       curp->file = file;
+       curp->line = 1;
+
+       mparse_buf_r(curp, blk, 1);
+
+       if (0 == re && MANDOCLEVEL_FATAL > curp->file_status)
+               mparse_end(curp);
+
+       curp->file = svfile;
+}
+
+enum mandoclevel
+mparse_readmem(struct mparse *curp, const void *buf, size_t len,
+               const char *file)
+{
+       struct buf blk;
+
+       blk.buf = UNCONST(buf);
+       blk.sz = len;
+
+       mparse_parse_buffer(curp, blk, file, 0);
+       return(curp->file_status);
+}
+
+static void
+mparse_readfd_r(struct mparse *curp, int fd, const char *file, int re)
+{
+       struct buf       blk;
+       int              with_mmap;
+

        if (-1 == fd)
                if (-1 == (fd = open(file, O_RDONLY, 0))) {
                        perror(file);
                        curp->file_status = MANDOCLEVEL_SYSERR;
                        return;
                }
        if (-1 == fd)
                if (-1 == (fd = open(file, O_RDONLY, 0))) {
                        perror(file);
                        curp->file_status = MANDOCLEVEL_SYSERR;
                        return;
                }

+       /*
+        * Run for each opened file; may be called more than once for
+        * each full parse sequence if the opened file is nested (i.e.,
+        * from `so').  Simply sucks in the whole file and moves into
+        * the parse phase for the file.
+        */

 
 

-       svfile = curp->file;
-       curp->file = file;
+       if ( ! read_whole_file(file, fd, &blk, &with_mmap)) {
+               curp->file_status = MANDOCLEVEL_SYSERR;
+               return;
+       }

 
 

-       pdesc(curp, file, fd);
+       mparse_parse_buffer(curp, blk, file, re);

 
 

-       if (0 == re && MANDOCLEVEL_FATAL > curp->file_status)
-               mparse_end(curp);
+#ifdef HAVE_MMAP
+       if (with_mmap)
+               munmap(blk.buf, blk.sz);
+       else
+#endif
+               free(blk.buf);

 
        if (STDIN_FILENO != fd && -1 == close(fd))
                perror(file);
 
        if (STDIN_FILENO != fd && -1 == close(fd))
                perror(file);

-
-       curp->file = svfile;

 }
 
 enum mandoclevel
 }
 
 enum mandoclevel


@@ -701,6 +747,8 @@ mparse_reset(struct mparse *curp)
                mdoc_reset(curp->mdoc);
        if (curp->man)
                man_reset(curp->man);
                mdoc_reset(curp->mdoc);
        if (curp->man)
                man_reset(curp->man);

+       if (curp->secondary)
+               curp->secondary->sz = 0;

 
        curp->file_status = MANDOCLEVEL_OK;
        curp->mdoc = NULL;
 
        curp->file_status = MANDOCLEVEL_OK;
        curp->mdoc = NULL;


@@ -717,7 +765,10 @@ mparse_free(struct mparse *curp)
                man_free(curp->pman);
        if (curp->roff)
                roff_free(curp->roff);
                man_free(curp->pman);
        if (curp->roff)
                roff_free(curp->roff);

+       if (curp->secondary)
+               free(curp->secondary->buf);

 
 

+       free(curp->secondary);

        free(curp);
 }
 
        free(curp);
 }
 


@@ -777,3 +828,19 @@ mparse_strlevel(enum mandoclevel lvl)
 {
        return(mandoclevels[lvl]);
 }
 {
        return(mandoclevels[lvl]);
 }

+
+void
+mparse_keep(struct mparse *p)
+{
+
+       assert(NULL == p->secondary);
+       p->secondary = mandoc_calloc(1, sizeof(struct buf));
+}
+
+const char *
+mparse_getkeep(const struct mparse *p)
+{
+
+       assert(p->secondary);
+       return(p->secondary->sz ? p->secondary->buf : NULL);
+}