On Wed, Mar 19, 2025 at 06:03:24PM -0400, James K. Lowden wrote:
> Elsewhere in the parser where there was a conflict like that, I renamed
> the token. For example, the COBOL word TRUE uses a token named
> TRUE_kw. I don't mind either way; your solution has less impact on the
> parser.
I think consistency is good and when it is a suffix rather than prefix,
it also sorts alphabetically together with the actual keywords.
Ok for trunk?
2025-03-21 Jakub Jelinek <ja...@redhat.com>
* parse.y: Rename COB_BLOCK to BLOCK_kw, COB_SIGNED to SIGNED_kw and
COB_UNSIGNED to UNSIGNED_kw.
* scan.l: Likewise.
* token_names.h: Regenerate.
--- gcc/cobol/scan.l.jj 2025-03-21 10:09:38.903966677 +0100
+++ gcc/cobol/scan.l 2025-03-21 10:12:07.079914108 +0100
@@ -374,7 +374,7 @@ ROUNDING { return ROUNDING; }
SECONDS { return SECONDS; }
SECURE { return SECURE; }
SHORT { return SHORT; }
-SIGNED { return COB_SIGNED; }
+SIGNED { return SIGNED_kw; }
STANDARD-BINARY { return STANDARD_BINARY; }
STANDARD-DECIMAL { return STANDARD_DECIMAL; }
STATEMENT { return STATEMENT; }
@@ -394,7 +394,7 @@ TOWARD-LESSER { return TOWARD_LESSER;
TRUNCATION { return TRUNCATION; }
UCS-4 { return UCS_4; }
UNDERLINE { return UNDERLINE; }
-UNSIGNED { return COB_UNSIGNED; }
+UNSIGNED { return UNSIGNED_kw; }
UTF-16 { return UTF_16; }
UTF-8 { return UTF_8; }
@@ -837,7 +837,7 @@ CALL { return CALL; }
BY { return BY; }
BOTTOM { return BOTTOM; }
BEFORE { return BEFORE; }
-BLOCK { return COB_BLOCK; }
+BLOCK { return BLOCK_kw; }
BACKWARD { return BACKWARD; }
AT { return AT; }
@@ -1042,7 +1042,7 @@ USE({SPC}FOR)? { return USE; }
AS { return AS; }
ASCENDING { return ASCENDING; }
BLANK { return BLANK; }
- BLOCK { return COB_BLOCK; }
+ BLOCK { return BLOCK_kw; }
BY { return BY; }
BYTE-LENGTH { return BYTE_LENGTH; }
CHARACTER { return CHARACTER; }
@@ -2164,7 +2164,7 @@ BASIS { yy_push_state(basis); return BA
BINARY { return BINARY; }
BIT { return BIT; }
BLANK { return BLANK; }
- BLOCK { return COB_BLOCK; }
+ BLOCK { return BLOCK_kw; }
BOTTOM { return BOTTOM; }
BY { return BY; }
CALL { return CALL; }
--- gcc/cobol/parse.y.jj 2025-03-21 10:09:38.902966690 +0100
+++ gcc/cobol/parse.y 2025-03-21 10:11:12.178674614 +0100
@@ -408,7 +408,7 @@
BASED BASECONVERT
BEFORE BINARY BIT BIT_OF "BIT-OF" BIT_TO_CHAR
"BIT-TO-CHAR"
- BLANK COB_BLOCK
+ BLANK BLOCK_kw
BOOLEAN_OF_INTEGER "BOOLEAN-OF-INTEGER"
BOTTOM BY
BYTE BYTE_LENGTH "BYTE-LENGTH"
@@ -613,7 +613,7 @@
NONE NORMAL NUMBERS
PREFIXED PREVIOUS PROHIBITED RELATION REQUIRED
REVERSE_VIDEO ROUNDING
- SECONDS SECURE SHORT COB_SIGNED
+ SECONDS SECURE SHORT SIGNED_kw
STANDARD_BINARY "STANDARD-BINARY"
STANDARD_DECIMAL "STANDARD-DECIMAL"
STATEMENT STEP STRUCTURE
@@ -621,7 +621,7 @@
TOWARD_LESSER "TOWARD-LESSER"
TRUNCATION
UCS_4 "UCS-4"
- UNDERLINE COB_UNSIGNED
+ UNDERLINE UNSIGNED_kw
UTF_16 "UTF-16"
UTF_8 "UTF-8"
@@ -1014,7 +1014,7 @@
BACKWARD BASED BASECONVERT
BEFORE BINARY BIT BIT_OF BIT_TO_CHAR
- BLANK COB_BLOCK
+ BLANK BLOCK_kw
BOOLEAN_OF_INTEGER
BOTTOM BY
BYTE BYTE_LENGTH
@@ -1228,7 +1228,7 @@
NONE NORMAL NUMBERS
PREFIXED PREVIOUS PROHIBITED RELATION REQUIRED
REVERSE_VIDEO ROUNDING
- SECONDS SECURE SHORT COB_SIGNED
+ SECONDS SECURE SHORT SIGNED_kw
STANDARD_BINARY
STANDARD_DECIMAL
STATEMENT STEP STRUCTURE
@@ -1236,7 +1236,7 @@
TOWARD_LESSER
TRUNCATION
UCS_4
- UNDERLINE COB_UNSIGNED
+ UNDERLINE UNSIGNED_kw
UTF_16
UTF_8
@@ -2907,7 +2907,7 @@ fd_clause: record_desc
}
;
-block_desc: COB_BLOCK contains rec_contains chars_recs
+block_desc: BLOCK_kw contains rec_contains chars_recs
;
rec_contains: NUMSTR[min] {
ssize_t n;
@@ -6528,7 +6528,7 @@ context_word: APPLY
$$ = s; } // screen description entry
| SHORT { static char s[] ="SHORT";
$$ = s; } // DYNAMIC LENGTH STRUCTURE
clause
- | COB_SIGNED { static char s[] ="SIGNED";
+ | SIGNED_kw { static char s[] ="SIGNED";
$$ = s; } // DYNAMIC LENGTH STRUCTURE
clause and USAGE clause
| STANDARD_BINARY { static char s[] ="STANDARD-BINARY";
$$ = s; } // ARITHMETIC clause
@@ -6554,7 +6554,7 @@ context_word: APPLY
$$ = s; } // ALPHABET clause
| UNDERLINE { static char s[] ="UNDERLINE";
$$ = s; } // screen description entry
and SET attribute statement
- | COB_UNSIGNED { static char s[] ="UNSIGNED";
+ | UNSIGNED_kw { static char s[] ="UNSIGNED";
$$ = s; } // USAGE clause
| UTF_8 { static char s[] ="UTF-8";
$$ = s; } // ALPHABET clause
--- gcc/cobol/token_names.h.jj 2025-03-21 10:09:38.963965845 +0100
+++ gcc/cobol/token_names.h 2025-03-21 10:13:54.077431954 +0100
@@ -1,5 +1,5 @@
// generated by ./token_names.h.gen ../../build/gcc/cobol/parse.h
-// Fri Jan 31 05:52:10 EST 2025
+// Fri Mar 21 10:13:54 CET 2025
tokens = {
{ "identification", IDENTIFICATION_DIV }, // 258
{ "environment", ENVIRONMENT_DIV }, // 259
@@ -219,7 +219,7 @@ tokens = {
{ "bit-of", BIT_OF }, // 470
{ "bit-to-char", BIT_TO_CHAR }, // 471
{ "blank", BLANK }, // 472
- { "block", COB_BLOCK }, // 473
+ { "block", BLOCK_kw }, // 473
{ "boolean-of-integer", BOOLEAN_OF_INTEGER }, // 474
{ "bottom", BOTTOM }, // 475
{ "by", BY }, // 476
@@ -642,7 +642,7 @@ tokens = {
{ "seconds", SECONDS }, // 891
{ "secure", SECURE }, // 892
{ "short", SHORT }, // 893
- { "signed", COB_SIGNED }, // 894
+ { "signed", SIGNED_kw }, // 894
{ "standard-binary", STANDARD_BINARY }, // 895
{ "standard-decimal", STANDARD_DECIMAL }, // 896
{ "statement", STATEMENT }, // 897
@@ -653,7 +653,7 @@ tokens = {
{ "truncation", TRUNCATION }, // 902
{ "ucs-4", UCS_4 }, // 903
{ "underline", UNDERLINE }, // 904
- { "unsigned", COB_UNSIGNED }, // 905
+ { "unsigned", UNSIGNED_kw }, // 905
{ "utf-16", UTF_16 }, // 906
{ "utf-8", UTF_8 }, // 907
{ "address", ADDRESS }, // 908
Jakub
