Changeset 28a5ebd in mainline for uspace/app/bdsh/tok.c

Timestamp:

2020-06-18T15:39:50Z (4 years ago)

Author:

Martin Decky <martin@…>

Branches:

lfn, master, serial, ticket/834-toolchain-update, topic/msim-upgrade, topic/simplify-dev-export

Children:

ce52c333

Parents:

4f663f3e

Message:

Use char32_t instead of wchat_t to represent UTF-32 strings

The intention of the native HelenOS string API has been always to
support Unicode in the UTF-8 and UTF-32 encodings as the sole character
representations and ignore the obsolete mess of older single-byte and
multibyte character encodings. Before C11, the wchar_t type has been
slightly misused for the purpose of the UTF-32 strings. The newer
char32_t type is obviously a much more suitable option. The standard
defines char32_t as uint_least32_t, thus we can take the liberty to fix
it to uint32_t.

To maintain compatilibity with the C Standard, the putwchar(wchar_t)
functions has been replaced by our custom putuchar(char32_t) functions
where appropriate.

File:

• uspace/app/bdsh/tok.c (modified) (6 diffs)

uspace/app/bdsh/tok.c

@@ -36 +36 @@
 
 /* Forward declarations of static functions */
-static wchar_t tok_get_char(tokenizer_t *);
-static wchar_t tok_look_char(tokenizer_t *);
-static errno_t tok_push_char(tokenizer_t *, wchar_t);
+static char32_t tok_get_char(tokenizer_t *);
+static char32_t tok_look_char(tokenizer_t *);
+static errno_t tok_push_char(tokenizer_t *, char32_t);
 static errno_t tok_push_token(tokenizer_t *);
 static bool tok_pending_chars(tokenizer_t *);
@@ -92 +92 @@
 {
         errno_t rc;
-        wchar_t next_char;
+        char32_t next_char;
 
         /* Read the input line char by char and append tokens */
@@ -182 +182 @@
 {
         errno_t rc;
-        wchar_t next_char;
+        char32_t next_char;
 
         while ((next_char = tok_look_char(tok)) != 0) {
@@ -214 +214 @@
 
 /** Get a char from input, advancing the input position */
-wchar_t tok_get_char(tokenizer_t *tok)
+char32_t tok_get_char(tokenizer_t *tok)
 {
         tok->in_char_offset++;
@@ -221 +221 @@
 
 /** Get a char from input, while staying on the same input position */
-wchar_t tok_look_char(tokenizer_t *tok)
+char32_t tok_look_char(tokenizer_t *tok)
 {
         size_t old_offset = tok->in_offset;
         size_t old_char_offset = tok->in_char_offset;
-        wchar_t ret = tok_get_char(tok);
+        char32_t ret = tok_get_char(tok);
         tok->in_offset = old_offset;
         tok->in_char_offset = old_char_offset;
@@ -232 +232 @@
 
 /** Append a char to the end of the current token */
-errno_t tok_push_char(tokenizer_t *tok, wchar_t ch)
+errno_t tok_push_char(tokenizer_t *tok, char32_t ch)
 {
         return chr_encode(ch, tok->outbuf, &tok->outbuf_offset, tok->outbuf_size);