2011-01-09 Paul Eggert <eggert@cs.ucla.edu>
- Simplify handling of '.' and '-' after unbracketed named references.
- * doc/bison.texinfo (Mid-Rule Actions): Mention that periods and
- dashes make symbol names less convenient for named references.
- * src/scan-code.l:
- (handle_action_dollar): New arg textlen. All callers changed.
- (handle_action_at): Likewise. Also, args are pointers to const.
- (ref_tail_fields): Remove; no longer used.
- (letter): Now includes '-' and '.', since this is for Bison
- identifiers.
- (id): Now the simpler traditional defn, since letters now include
- '-' and '.'.
- (c_letter, c_id): New defns.
- (ref): Use c_id for unbracketed IDs.
- (<SC_RULE_ACTION>): Simplify, now that the distinction between
- Bison and unbracketed IDs are now in the regular expressions.
- (VARIANT_BAD_BRACKETING): Remove.
- (VARIANT_NOT_VISIBLE_FROM_MIDRULE): Renumber.
- (find_prefix_end): Remove, replacing with ....
- (identifier_matches): New function.
- (variant_add): Use it. Omit EXPLICIT_BRACKETING arg; no longer
- needed. CP arg is pointer to constant. All callers changed.
- (show_sub_messages): Remove args CP, EXPLICIT_BRACKETING, DOLLAR_OR_AT.
- New arg TEXT. All callers changed. Do not worry about showing
- trailing context.
- (parse_ref): Args CP, RULE, TEXT are now pointers to const. New
- arg TEXTLEN. Remove arg DOLLAR_OR_AT. All callers changed.
- Simplify code now that the regular expressions capture the
- restrictions.
- * src/scan-gram.l (letter, id): Adjust to match scan-code.l.
- * src/symlist.c (symbol_list_null): Arg is now pointer to const.
- * src/symlist.h: Likewise.
- * tests/named-refs.at (Misleading references): These are now caught
- by the C compiler, not by Bison; that's good enough. Adjust test
- to reflect this.
- (Many kinds of errors, Unresolved references): Adjust expected
- diagnostics to match new behavior. The same errors are caught,
- though the diagnostics are not quite as fancy.
- ($ or @ followed by . or -): Likewise. Also, Make the grammar
- unambiguous, so that diagnostics are not complicated by ambiguity
- warnings.
-
Fix minor problems encountered by a fresh bootstrap.
* data/glr.c, data/yacc.c: Do not use apostrophes in '#' comments,
as they confuse xgettext, which tries to parse them as C character
#define YY_USER_ACTION location_compute (loc, &loc->end, yytext, yyleng);
-static void handle_action_dollar (symbol_list *, char *, unsigned, location);
-static void handle_action_at (symbol_list const *, char const *, unsigned,
- location);
+static void handle_action_dollar (symbol_list *rule, char *cp,
+ location dollar_loc);
+static void handle_action_at (symbol_list *rule, char *cp, location at_loc);
+
+/* A string to be pushed to obstack after dollar/at has been handled. */
+static char *ref_tail_fields;
static location the_location;
static location *loc = &the_location;
white space between the backslash and the newline. */
splice (\\[ \f\t\v]*\n)*
-/* A Bison identifier. Keep this synchronized with scan-gram.l "id". */
-letter [-.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]
-id {letter}({letter}|[0-9])*
-
-/* An identifier that can appear unbracketed in a reference.
- This happens to be the same as a C-language identifier. */
-c_letter [abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]
-c_id {c_letter}({c_letter}|[0-9])*
-
-ref -?[0-9]+|{c_id}|"["{id}"]"|"$"
+/* C style identifier. Must start with letter. Will be used for
+ named symbol references. Shall be kept synchronized with
+ scan-gram.l "letter" and "id". */
+letter [.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]
+id -*(-|{letter}({letter}|[-0-9])*)
+ref -?[0-9]+|{id}|"["{id}"]"|"$"
%%
<SC_RULE_ACTION>
{
"$"("<"{tag}">")?{ref} {
- handle_action_dollar (self->rule, yytext, yyleng, *loc);
+ ref_tail_fields = 0;
+ handle_action_dollar (self->rule, yytext, *loc);
+ if (ref_tail_fields) {
+ obstack_sgrow (&obstack_for_string, ref_tail_fields);
+ }
need_semicolon = true;
}
"@"{ref} {
- handle_action_at (self->rule, yytext, yyleng, *loc);
+ ref_tail_fields = 0;
+ handle_action_at (self->rule, yytext, *loc);
+ if (ref_tail_fields) {
+ obstack_sgrow (&obstack_for_string, ref_tail_fields);
+ }
need_semicolon = true;
}
"$" {
by an explicit symbol reference. */
#define VARIANT_HIDDEN (1 << 0)
+/* Set when the variant refers to a symbol containing
+ dots or dashes. Will require explicit bracketing. */
+#define VARIANT_BAD_BRACKETING (1 << 1)
+
/* Set when the variant refers to a symbol which is
not visible from current midrule. */
-#define VARIANT_NOT_VISIBLE_FROM_MIDRULE (1 << 1)
+#define VARIANT_NOT_VISIBLE_FROM_MIDRULE (1 << 2)
static variant *variant_table = 0;
static unsigned variant_table_size = 0;
variant_table_size = variant_count = 0;
}
-/* Return TRUE if ID matches the string from CP up to CP_END.
- The string does not contain null bytes. */
-static bool
-identifier_matches (char const *id, char const *cp, char const *cp_end)
+static char *
+find_prefix_end (const char *prefix, char *begin, char *end)
{
- while (cp != cp_end)
- if (*id++ != *cp++)
- return false;
- return !*id;
+ char *ptr = begin;
+
+ for (; *prefix && ptr != end; ++prefix, ++ptr)
+ if (*prefix != *ptr)
+ return 0;
+
+ if (*prefix)
+ return 0;
+
+ return ptr;
}
-/* If scanning ID, return a new variant with that ID, at location
- ID_LOC with index SYMBOL_INDEX. Otherwise, return NULL. The
- currently scanned identifier starts at CP and ends at CP_END. */
static variant *
variant_add (uniqstr id, location id_loc, unsigned symbol_index,
- char const *cp, char const *cp_end)
+ char *cp, char *cp_end, bool explicit_bracketing)
{
- if (identifier_matches (id, cp, cp_end))
+ char *prefix_end;
+
+ prefix_end = find_prefix_end (id, cp, cp_end);
+ if (prefix_end &&
+ (prefix_end == cp_end ||
+ (!explicit_bracketing && is_dot_or_dash (*prefix_end))))
{
variant *r = variant_table_grow ();
r->symbol_index = symbol_index;
return at_buf;
}
-/* Show a subsidiary message for a problem with a grammar rule. TEXT
- points to the problematic reference. MIDRULE_RHS_INDEX is the rhs
- index (1-origin) in the rule. If IS_WARNING, it is a warning,
- otherwise a complaint. Indent the message INDENT spaces. */
static void
-show_sub_messages (char const *text, int midrule_rhs_index,
+show_sub_messages (const char* cp, bool explicit_bracketing,
+ int midrule_rhs_index, char dollar_or_at,
bool is_warning, unsigned indent)
{
- char dollar_or_at = *text;
unsigned i;
for (i = 0; i < variant_count; ++i)
else
{
static struct obstack msg_buf;
+ const char *tail = explicit_bracketing ? "" :
+ cp + strlen (var->id);
const char *id = var->hidden_by ? var->hidden_by->id :
var->id;
location id_loc = var->hidden_by ? var->hidden_by->loc :
obstack_fgrow1 (&msg_buf, "[%s]", id);
else
obstack_sgrow (&msg_buf, id);
+ obstack_sgrow (&msg_buf, tail);
if (var->err & VARIANT_HIDDEN)
{
obstack_fgrow1 (&msg_buf, "[%s]", var->id);
else
obstack_sgrow (&msg_buf, var->id);
+ obstack_sgrow (&msg_buf, tail);
}
obstack_fgrow1 (&msg_buf, _(" at %s"), at_spec);
/* Sub-messages indent. */
#define SUB_INDENT (4)
-/* Return the index of a named or positional reference starting at CP
- for a rule RULE of length RULE_LENGTH. If MIDRULE_RHS_INDEX is
- nonzero, this is a generated midrule whose rhs index (1-origin) is
- MIDRULE_RHS_INDEX in the parent rule. The entire semantic value
- containing the reference is TEXT, of length TEXTLEN. Its location
- is TEXT_LOC.
-
- In case of positional references, this can return negative values
- for $-n "deep" stack accesses. */
+/* Parse named or positional reference. In case of positional
+ references, can return negative values for $-n "deep" stack
+ accesses. */
static long int
-parse_ref (char const *cp, symbol_list const *rule, int rule_length,
- int midrule_rhs_index, char const *text, unsigned textlen,
- location text_loc)
+parse_ref (char *cp, symbol_list *rule, int rule_length,
+ int midrule_rhs_index, char *text, location text_loc,
+ char dollar_or_at)
{
- symbol_list const *l;
- char const *cp_end;
+ symbol_list *l;
+ char *cp_end;
bool explicit_bracketing;
unsigned i;
unsigned valid_variants = 0;
if ('$' == *cp)
return LHS_REF;
- if (c_isdigit (*cp) || *cp == '-')
+ if (c_isdigit (*cp) || (*cp == '-' && c_isdigit (* (cp + 1))))
{
- long int num = strtol (cp, NULL, 10);
+ long int num = strtol (cp, &cp, 10);
if (1 - INT_MAX + rule_length <= num && num <= rule_length)
return num;
else
}
}
- explicit_bracketing = (*cp == '[');
- cp += explicit_bracketing;
- cp_end = text + textlen - explicit_bracketing;
+ if ('[' == *cp)
+ {
+ /* Ignore the brackets. */
+ char *p;
+ for (p = ++cp; *p != ']'; ++p)
+ continue;
+ cp_end = p;
+
+ explicit_bracketing = true;
+ }
+ else
+ {
+ /* Take all characters of the name. */
+ char* p;
+ for (p = cp; *p; ++p)
+ if (is_dot_or_dash (*p))
+ {
+ ref_tail_fields = p;
+ break;
+ }
+ for (p = cp; *p; ++p)
+ continue;
+ cp_end = p;
+
+ explicit_bracketing = false;
+ }
/* Add all relevant variants. */
{
continue;
var = variant_add (l->content.sym->tag, l->sym_loc,
- symbol_index, cp, cp_end);
+ symbol_index, cp, cp_end, explicit_bracketing);
if (var && l->named_ref)
var->hidden_by = l->named_ref;
if (l->named_ref)
variant_add (l->named_ref->id, l->named_ref->loc,
- symbol_index, cp, cp_end);
+ symbol_index, cp, cp_end, explicit_bracketing);
}
}
&& (symbol_index == 0 || midrule_rhs_index < symbol_index))
var->err |= VARIANT_NOT_VISIBLE_FROM_MIDRULE;
+ /* Check correct bracketing. */
+ if (!explicit_bracketing && contains_dot_or_dash (var->id))
+ var->err |= VARIANT_BAD_BRACKETING;
+
/* Check using of hidden symbols. */
if (var->hidden_by)
var->err |= VARIANT_HIDDEN;
{
case 0:
{
- unsigned len = cp_end - cp;
+ unsigned len = (explicit_bracketing || !ref_tail_fields) ?
+ cp_end - cp : ref_tail_fields - cp;
unsigned indent = 0;
complain_at_indent (text_loc, &indent, _("invalid reference: %s"),
const char *format =
_("syntax error after `%c', expecting integer, letter,"
" `_', `[', or `$'");
- complain_at_indent (sym_loc, &indent, format, *text);
+ complain_at_indent (sym_loc, &indent, format, dollar_or_at);
}
else if (midrule_rhs_index)
{
}
if (variant_count > 0)
- show_sub_messages (text, midrule_rhs_index, false, indent);
+ show_sub_messages (cp, explicit_bracketing, midrule_rhs_index,
+ dollar_or_at, false, indent);
return INVALID_REF;
}
case 1:
{
warn_at_indent (text_loc, &indent, _("misleading reference: %s"),
quote (text));
- show_sub_messages (text, midrule_rhs_index, true,
- indent + SUB_INDENT);
+ show_sub_messages (cp, explicit_bracketing, midrule_rhs_index,
+ dollar_or_at, true, indent + SUB_INDENT);
}
{
unsigned symbol_index =
unsigned indent = 0;
complain_at_indent (text_loc, &indent, _("ambiguous reference: %s"),
quote (text));
- show_sub_messages (text, midrule_rhs_index, false,
- indent + SUB_INDENT);
+ show_sub_messages (cp, explicit_bracketing, midrule_rhs_index,
+ dollar_or_at, false, indent + SUB_INDENT);
return INVALID_REF;
}
}
/*------------------------------------------------------------------.
| TEXT is pointing to a wannabee semantic value (i.e., a `$'). |
| |
-| Possible inputs: $(<TYPENAME>|)($|integer|c_id|[id]) |
+| Possible inputs: $[<TYPENAME>]($|integer) |
| |
| Output to OBSTACK_FOR_STRING a reference to this semantic value. |
`------------------------------------------------------------------*/
static void
-handle_action_dollar (symbol_list *rule, char *text, unsigned textlen,
- location dollar_loc)
+handle_action_dollar (symbol_list *rule, char *text, location dollar_loc)
{
char const *type_name = NULL;
char *cp = text + 1;
}
n = parse_ref (cp, effective_rule, effective_rule_length,
- rule->midrule_parent_rhs_index, text, textlen, dollar_loc);
+ rule->midrule_parent_rhs_index, text, dollar_loc, '$');
if (gt_ptr)
*gt_ptr = '\0';
`------------------------------------------------------*/
static void
-handle_action_at (symbol_list const *rule, char const *text, unsigned textlen,
- location at_loc)
+handle_action_at (symbol_list *rule, char *text, location at_loc)
{
- char const *cp = text + 1;
- symbol_list const *effective_rule;
+ char *cp = text + 1;
+ symbol_list *effective_rule;
int effective_rule_length;
int n;
muscle_percent_define_ensure("locations", at_loc, true);
n = parse_ref (cp, effective_rule, effective_rule_length,
- rule->midrule_parent_rhs_index, text, textlen, at_loc);
+ rule->midrule_parent_rhs_index, text, at_loc, '@');
switch (n)
{
case INVALID_REF:
foo: '1'
foo.bar: '2'
]])
-AT_BISON_CHECK([-o test.c test.y])
-AT_CHECK([if $CC $CFLAGS $CPPFLAGS test.c; then false; else true; fi],
- [0], [ignore], [ignore])
+AT_BISON_CHECK([-o test.c test.y], 0, [],
+[[test.y:11.22-29: warning: misleading reference: `$foo.bar'
+test.y:11.8-10: warning: refers to: $foo at $1
+test.y:11.12-18: warning: possibly meant: $[foo.bar] at $2
+]])
AT_CLEANUP
#######################################################################
AT_BISON_CHECK([-o test.c test.y], 1, [],
[[test.y:24.36-41: invalid reference: `$cond1'
test.y:23.11-24.62: symbol not found in production: cond1
-test.y:26.43-47: invalid reference: `$stmt'
+test.y:26.43-53: invalid reference: `$stmt.field'
test.y:25.11-26.60: symbol not found in production: stmt
-test.y:25.35-38: possibly meant: $then, hiding $stmt at $4
-test.y:28.43-47: invalid reference: `$stmt'
+test.y:25.35-38: possibly meant: $then.field, hiding $stmt.field at $4
+test.y:28.43-52: invalid reference: `$stmt.list'
test.y:27.11-28.59: symbol not found in production: stmt
+test.y:27.30-38: possibly meant: $[stmt.list] at $4
test.y:30.43-46: ambiguous reference: `$xyz'
test.y:29.35-37: refers to: $xyz at $4
test.y:29.50-52: refers to: $xyz at $6
-test.y:32.43-47: invalid reference: `$stmt'
+test.y:32.43-52: invalid reference: `$stmt.list'
test.y:31.11-32.63: symbol not found in production: stmt
-test.y:34.43-47: invalid reference: `$stmt'
+test.y:31.40-43: possibly meant: $then, hiding $[stmt.list] at $4
+test.y:31.61-64: possibly meant: $else, hiding $[stmt.list] at $6
+test.y:34.43-58: invalid reference: `$stmt.list.field'
test.y:33.11-34.69: symbol not found in production: stmt
+test.y:33.40-43: possibly meant: $then.field, hiding $[stmt.list].field at $4
+test.y:33.61-64: possibly meant: $else.field, hiding $[stmt.list].field at $6
test.y:36.43-54: invalid reference: `$[stmt.list]'
test.y:35.11-36.71: symbol not found in production: stmt.list
test.y:35.40-43: possibly meant: $then, hiding $[stmt.list] at $4
test.y:35.61-64: possibly meant: $else, hiding $[stmt.list] at $6
-test.y:38.43-47: invalid reference: `$then'
+test.y:38.43-49: invalid reference: `$then.1'
test.y:37.11-38.60: symbol not found in production: then
-test.y:40.43-47: invalid reference: `$then'
+test.y:37.40-45: possibly meant: $[then.1] at $4
+test.y:40.43-55: invalid reference: `$then.1.field'
test.y:39.11-40.66: symbol not found in production: then
-test.y:42.44-48: invalid reference: `$stmt'
+test.y:39.40-45: possibly meant: $[then.1].field at $4
+test.y:42.44-50: invalid reference: `$stmt.x'
test.y:41.12-42.57: symbol not found in production: stmt
-test.y:41.36-41: possibly meant: $[stmt.x], hiding $stmt at $4
-test.y:44.13-15: invalid reference: `$if'
+test.y:41.36-41: possibly meant: $[stmt.x].x, hiding $stmt.x at $4
+test.y:41.36-41: possibly meant: $[stmt.x] at $4
+test.y:44.13-22: invalid reference: `$if-stmt-a'
test.y:43.12-44.59: symbol not found in production: if
-test.y:46.46-50: invalid reference: `$then'
+test.y:43.1-9: possibly meant: $[if-stmt-a] at $$
+test.y:46.46-54: invalid reference: `$then-a.f'
test.y:45.12-46.65: symbol not found in production: then
+test.y:45.41-46: possibly meant: $[then-a].f at $4
]])
AT_CLEANUP
sym_b : 'b';
]])
AT_BISON_CHECK([-o test.c test.y], 1, [],
-[[test.y:13.8-11: invalid reference: `$sym'
+[[test.y:13.8-17: invalid reference: `$sym.field'
test.y:12.1-13.21: symbol not found in production: sym
-test.y:16.8-15: invalid reference: `$<aa>sym'
+test.y:16.8-21: invalid reference: `$<aa>sym.field'
test.y:15.1-16.25: symbol not found in production: sym
test.y:19.8-19: invalid reference: `$[sym.field]'
test.y:18.1-19.23: symbol not found in production: sym.field
test.y:30.1-33.21: symbol not found in production before $3: sym
test.y:33.8-17: invalid reference: `$<aa>[sym]'
test.y:30.1-33.21: symbol not found in production: sym
-test.y:37.8-11: invalid reference: `$sym'
+test.y:37.8-17: invalid reference: `$sym-field'
test.y:36.1-37.21: symbol not found in production: sym
-test.y:40.8-15: invalid reference: `$<aa>sym'
+test.y:40.8-21: invalid reference: `$<aa>sym-field'
test.y:39.1-40.25: symbol not found in production: sym
test.y:43.8-19: invalid reference: `$[sym-field]'
test.y:42.1-43.23: symbol not found in production: sym-field
.field { $.field; }
| -field { @-field; }
| 'a' { @.field; }
-| 'b' { $-field; }
+| 'a' { $-field; }
;
-.field: 'c' ;
--field: 'd' ;
+.field: ;
+-field: ;
]])
-AT_BISON_CHECK([[test.y]], [], [],
-[[test.y:4.12: warning: stray `$'
-test.y:5.12: warning: stray `@'
-test.y:6.12: warning: stray `@'
-test.y:7.12: warning: stray `$'
+AT_BISON_CHECK([[test.y]], [[1]], [],
+[[test.y:4.12-18: invalid reference: `$.field'
+test.y:4.13: syntax error after `$', expecting integer, letter, `_', `@<:@', or `$'
+test.y:4.3-8: possibly meant: $[.field] at $1
+test.y:5.12-18: invalid reference: `@-field'
+test.y:5.13: syntax error after `@', expecting integer, letter, `_', `@<:@', or `$'
+test.y:5.3-8: possibly meant: @[-field] at $1
+test.y:6.12-18: invalid reference: `@.field'
+test.y:6.13: syntax error after `@', expecting integer, letter, `_', `@<:@', or `$'
+test.y:7.12-18: invalid reference: `$-field'
+test.y:7.13: syntax error after `$', expecting integer, letter, `_', `@<:@', or `$'
]])
AT_CLEANUP
projects / bison.git / commitdiff
