Refactoring in preparation for .rm support:

Unify parsing of names given as roff request arguments into a new
function roff_getname(), which is rather different from the parsing
function for normal arguments, mandoc_getarg(), because names cannot
be quoted and cannot contain whitespace or escaped characters.
The new function now throws an ERROR when finding escaped characters
in a name.
"I'm fine with this." kristaps@

diff --git a/main.c b/main.c
index 941fa5e2aa70c896d057ab9a9c76844ef9cae409..b6954da2d2aef1094112b81698425ffd8c5036d6 100644 (file)
--- a/main.c
+++ b/main.c
@@ -1,4 +1,4 @@
-/*     $Id: main.c,v 1.136 2011/01/10 14:40:30 kristaps Exp $ */
+/*     $Id: main.c,v 1.137 2011/01/11 00:11:45 schwarze Exp $ */
 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010 Ingo Schwarze <schwarze@openbsd.org>
@@ -192,6 +192,7 @@ static      const char * const      mandocerrs[MANDOCERR_MAX] = {
 
        "input stack limit exceeded, infinite loop?",
        "skipping bad character",
+       "escaped character not allowed in a name",
        "skipping text before the first section header",
        "skipping unknown macro",
        "NOT IMPLEMENTED: skipping request",

diff --git a/mandoc.h b/mandoc.h
index e7c0e96af9d6f55d9615123dc2befa25c70d5236..9cfb350aa8a8dccb0648fced9232d96ffa43461d 100644 (file)
--- a/mandoc.h
+++ b/mandoc.h
@@ -1,4 +1,4 @@
-/*     $Id: mandoc.h,v 1.51 2011/01/10 15:31:00 kristaps Exp $ */
+/*     $Id: mandoc.h,v 1.52 2011/01/11 00:11:45 schwarze Exp $ */
 /*
  * Copyright (c) 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  *
@@ -114,6 +114,7 @@ enum        mandocerr {
 
        MANDOCERR_ROFFLOOP, /* input stack limit exceeded, infinite loop? */
        MANDOCERR_BADCHAR, /* skipping bad character */
+       MANDOCERR_NAMESC, /* escaped character not allowed in a name */
        MANDOCERR_NOTEXT, /* skipping text before the first section header */
        MANDOCERR_MACRO, /* skipping unknown macro */
        MANDOCERR_REQUEST, /* NOT IMPLEMENTED: skipping request */

diff --git a/roff.c b/roff.c
index 5053bef51401ff993472d83e139030327ea07a0a..561062280d3ccb94cc83b2846b2be633fa901a64 100644 (file)
--- a/roff.c
+++ b/roff.c
@@ -1,4 +1,4 @@
-/*     $Id: roff.c,v 1.120 2011/01/03 23:24:16 schwarze Exp $ */
+/*     $Id: roff.c,v 1.121 2011/01/11 00:11:45 schwarze Exp $ */
 /*
  * Copyright (c) 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010, 2011 Ingo Schwarze <schwarze@openbsd.org>
@@ -134,6 +134,7 @@ static      enum rofferr     roff_cond_sub(ROFF_ARGS);
 static enum rofferr     roff_ds(ROFF_ARGS);
 static enum roffrule    roff_evalcond(const char *, int *);
 static void             roff_freestr(struct roff *);
+static char            *roff_getname(struct roff *, char **, int, int);
 static const char      *roff_getstrn(const struct roff *, 
                                const char *, size_t);
 static enum rofferr     roff_line_ignore(ROFF_ARGS);
@@ -520,7 +521,7 @@ roff_endparse(struct roff *r)
 {
 
        if (r->last)
-               (*r->msg)(MANDOCERR_SCOPEEXIT, r->data, 
+               (*r->msg)(MANDOCERR_SCOPEEXIT, r->data,
                                r->last->line, r->last->col, NULL);
 
        if (r->tbl) {
@@ -1056,25 +1057,13 @@ roff_ds(ROFF_ARGS)
         * will have `bar  "     ' as its value.
         */
 
-       name = *bufp + pos;
+       string = *bufp + pos;
+       name = roff_getname(r, &string, ln, pos);
        if ('\0' == *name)
                return(ROFF_IGN);
 
-       string = name;
-       /* Read until end of name. */
-       while (*string && ' ' != *string)
-               string++;
-
-       /* Nil-terminate name. */
-       if (*string)
-               *(string++) = '\0';
-       
-       /* Read past spaces. */
-       while (*string && ' ' == *string)
-               string++;
-
-       /* Read passed initial double-quote. */
-       if (*string && '"' == *string)
+       /* Read past initial double-quote. */
+       if ('"' == *string)
                string++;
 
        /* The rest is the value. */
@@ -1087,31 +1076,14 @@ roff_ds(ROFF_ARGS)
 static enum rofferr
 roff_nr(ROFF_ARGS)
 {
-       const char      *key, *val;
+       const char      *key;
+       char            *val;
        struct reg      *rg;
 
-       key = &(*bufp)[pos];
+       val = *bufp + pos;
+       key = roff_getname(r, &val, ln, pos);
        rg = r->regs->regs;
 
-       /* Parse register request. */
-       while ((*bufp)[pos] && ' ' != (*bufp)[pos])
-               pos++;
-
-       /*
-        * Set our nil terminator.  Because this line is going to be
-        * ignored anyway, we can munge it as we please.
-        */
-       if ((*bufp)[pos])
-               (*bufp)[pos++] = '\0';
-
-       /* Skip whitespace to register token. */
-       while ((*bufp)[pos] && ' ' == (*bufp)[pos])
-               pos++;
-
-       val = &(*bufp)[pos];
-
-       /* Process register token. */
-
        if (0 == strcmp(key, "nS")) {
                rg[(int)REG_nS].set = 1;
                if ( ! roff_parse_nat(val, &rg[(int)REG_nS].v.u))
@@ -1250,6 +1222,41 @@ roff_userdef(ROFF_ARGS)
           ROFF_REPARSE : ROFF_APPEND);
 }
 
+
+static char *
+roff_getname(struct roff *r, char **cpp, int ln, int pos)
+{
+       char     *name, *cp;
+
+       name = *cpp;
+       if ('\0' == *name)
+               return(name);
+
+       /* Read until end of name. */
+       for (cp = name; '\0' != *cp && ' ' != *cp; cp++) {
+               if ('\\' != *cp)
+                       continue;
+               cp++;
+               if ('\\' == *cp)
+                       continue;
+               (*r->msg)(MANDOCERR_NAMESC, r->data, ln, pos, NULL);
+               *cp = '\0';
+               name = cp;
+       }
+
+       /* Nil-terminate name. */
+       if ('\0' != *cp)
+               *(cp++) = '\0';
+
+       /* Read past spaces. */
+       while (' ' == *cp)
+               cp++;
+
+       *cpp = cp;
+       return(name);
+}
+
+
 /*
  * Store *string into the user-defined string called *name.
  * In multiline mode, append to an existing entry and append '\n';