gbranden pushed a commit to branch master
in repository groff.
commit dd7bf97938aa0c22b0528da85b2076a8f1e20b7b
Author: G. Branden Robinson <[email protected]>
AuthorDate: Sun Nov 23 16:31:23 2025 -0600
[troff]: Refactor new token description logic.
...into its own function, since there is a second place it can be used.
* src/roff/troff/token.h (class token): Declare new `describe_node()`
member function.
* src/roff/troff/input.cpp (token::description): Move the logic from
here...
(token::describe_node): ...to this new member function.
(token::description): Call the new member function.
Also annotate null pointers with `nullptr` comment to ease any future
transition to C++11, which defines it as a keyword.
---
ChangeLog | 12 ++++++++++++
src/roff/troff/input.cpp | 45 +++++++++++++++++++++++++++++----------------
src/roff/troff/token.h | 1 +
3 files changed, 42 insertions(+), 16 deletions(-)
diff --git a/ChangeLog b/ChangeLog
index 9d6f99894..a143ac0d8 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,15 @@
+2025-11-23 G. Branden Robinson <[email protected]>
+
+ [troff]: Refactor new token description logic into its own
+ function, since there is a second place it can be used.
+
+ * src/roff/troff/token.h (class token): Declare new
+ `describe_node()` member function.
+ * src/roff/troff/input.cpp (token::description): Move the logic
+ from here...
+ (token::describe_node): ...to this new member function.
+ (token::description): Call the new member function.
+
2025-11-23 G. Branden Robinson <[email protected]>
* src/roff/troff/input.cpp
diff --git a/src/roff/troff/input.cpp b/src/roff/troff/input.cpp
index aa06eee1b..384171204 100644
--- a/src/roff/troff/input.cpp
+++ b/src/roff/troff/input.cpp
@@ -2795,6 +2795,29 @@ static bool is_char_usable_as_delimiter(int c)
}
}
+void token::describe_node(char *buf, size_t bufsz)
+{
+ assert(nd != 0 /* nullptr */);
+ if (0 /* nullptr */ == nd) {
+ (void) snprintf(buf, bufsz, "a null(!) node");
+ return;
+ }
+ // Ah, the joys of computational natural language grammar.
+ const char *ndtype = nd->type();
+ const char initial_letter = ndtype[0];
+ bool is_vowelly = false;
+ // I wonder if Kernighan thought that the presence of set types and an
+ // "in" operator was one of Pascal's great blunders. --GBR
+ if (('a' == initial_letter)
+ || ('e' == initial_letter)
+ || ('i' == initial_letter)
+ || ('o' == initial_letter)
+ || ('u' == initial_letter))
+ is_vowelly = true;
+ (void) memset(buf, 0, bufsz);
+ (void) snprintf(buf, bufsz, "a%s %s", is_vowelly ? "n" : "", ndtype);
+}
+
// Is the token a valid delimiter (like `'`)?
bool token::is_usable_as_delimiter(bool report_error,
enum delimiter_context context)
@@ -2897,9 +2920,11 @@ const char *token::description()
// "character code XXX"
// "special character 'bracketrighttp'"
// "indexed character -2147483648"
+ // "space character horizontal motion node token"
// Future:
// "character code XXX (U+XXXX)" or similar
- const size_t maxstr = sizeof "special character 'bracketrighttp'";
+ const size_t maxstr
+ = sizeof "space character horizontal motion node token";
const size_t bufsz = maxstr + 2; // for trailing '"' and null
static char buf[bufsz];
(void) memset(buf, 0, bufsz);
@@ -2940,21 +2965,9 @@ const char *token::description()
case TOKEN_NEWLINE:
return "a newline";
case TOKEN_NODE:
- // Ah, the joys of computational natural language grammar.
{
- const char *ndtype = nd->type();
- const char initial_letter = ndtype[0];
- bool is_vowelly = false;
- // I wonder if Kernighan thought that the presence of set types
- // and an "in" operator was one of Pascal's great blunders. --GBR
- if (('a' == initial_letter)
- || ('e' == initial_letter)
- || ('i' == initial_letter)
- || ('o' == initial_letter)
- || ('u' == initial_letter))
- is_vowelly = true;
- (void) snprintf(buf, bufsz, "a%s %s token", is_vowelly ? "n" : "",
- ndtype);
+ static char nodebuf[bufsz];
+ describe_node(nodebuf, bufsz);
return buf;
}
case TOKEN_INDEXED_CHAR:
@@ -8891,7 +8904,7 @@ void token::process()
case TOKEN_NODE:
case TOKEN_HORIZONTAL_SPACE:
curenv->add_node(nd);
- nd = 0;
+ nd = 0 /* nullptr */;
break;
case TOKEN_INDEXED_CHAR:
// Optimize `curenv->add_char(get_charinfo())` for token type.
diff --git a/src/roff/troff/token.h b/src/roff/troff/token.h
index 3435cc5e6..1a5f8b4d4 100644
--- a/src/roff/troff/token.h
+++ b/src/roff/troff/token.h
@@ -115,6 +115,7 @@ public:
bool add_to_zero_width_node_list(node **);
void make_space();
void make_newline();
+ void describe_node(char * /* buf */, size_t /* bufsz */);
const char *description();
friend void process_input_stack();
_______________________________________________
groff-commit mailing list
[email protected]
https://lists.gnu.org/mailman/listinfo/groff-commit
