mirror/guile
mirror/guile
1
Fork 0
mirror of https://git.savannah.gnu.org/git/guile.git synced 2025-06-16 00:30:21 +02:00
Code Activity

Add Unicode strings and symbols

Browse source 
This adds full Unicode strings as a datatype, and it adds some
minimal functionality.  The terminal and port encoding is assumed
to be ISO-8859-1.  Non-ISO-8859-1 characters are written or
input as string character escapes.

The string character escapes now have 3 forms: \xXX \uXXXX and
\UXXXXXX, for unprintable characters that have 2, 4 or 6 hex digits.

The process for writing to strings has been modified.  There is now a
function scm_i_string_start_writing that does the copy-on-write
conversion if necessary.

To compile strings that may be wide, the VM storage of strings and
string-likes has changed.

Most string-using functions have not yet been updated and may break
when used with wide strings.


        * module/language/assembly/compile-bytecode.scm (write-bytecode):
        use variable width string bytecode format

        * module/language/assembly.scm (byte-length): use variable width
        bytecode format

        * libguile/vm-i-loader.c (load-string, load-symbol):
        (load-keyword, define): use variable-width bytecode format

        * libguile/vm-engine.h (FETCH_WIDTH): new macro

        * libguile/strings.h: new declarations

        * libguile/strings.c (make_wide_stringbuf): new function
        (widen_stringbuf): new function
        (scm_i_make_wide_string): new function
        (scm_i_is_narrow_string): new function
        (scm_i_string_wide_chars): new function
        (scm_i_string_start_writing): new function
        (scm_i_string_ref): new function
        (scm_i_string_set_x): new function
        (scm_i_is_narrow_symbol): new function
        (scm_i_symbol_wide_chars, scm_i_symbol_ref): new function
        (scm_string_width): new function
        (unistring_escapes_to_guile_escapes): new function
        (scm_to_stringn): new function
        (scm_i_stringbuf_free): modify for wide strings
        (scm_i_substring_copy): modify for wide strings
        (scm_i_string_chars, scm_string_append): modify for wide strings
        (scm_i_make_symbol, scm_to_locale_stringn): modify for wide strings
        (scm_string_dump, scm_symbol_dump, scm_to_locale_stringbuf):
        (scm_string, scm_i_deprecated_string_chars): modify for wide strings
        (scm_from_locale_string, scm_from_locale_stringn): add null test

        * libguile/srfi-13.c: add calls for scm_i_string_start_writing for
        each call of scm_i_string_stop_writing
        (scm_string_for_each): modify for wide strings

        * libguile/socket.c: add calls for scm_i_string_start_writing for each
        call of scm_i_string_stop_writing

        * libguile/rw.c: add calls for scm_i_string_start_writing for each
        call of scm_i_string_stop_writing

        * libguile/read.c (scm_read_string): allow reading of wide strings

        * libguile/print.h: add declaration for scm_charprint

        * libguile/print.c (iprin1): print wide strings and add new string
        escapes
        (scm_charprint): new function

        * libguile/ports.h: new declarations for scm_lfwrite_substr and
        scm_lfwrite_str

        * libguile/ports.c (update_port_lf): new function
        (scm_lfwrite): use update_port_lf
        (scm_lfwrite_substr): new function
        (scm_lfwrite_str): new function

        * test-suite/tests/asm-to-bytecode.test ("compiler"): add string
        width byte to sting-like asm tests
This commit is contained in:
Michael Gran 2009-08-08 02:35:00 -07:00
parent a876e7dcea
commit 9c44cd4559
15 changed files with 1046 additions and 306 deletions
Download patch file Download diff file Expand all files Collapse all files

87
libguile/vm-i-loader.c
View file

@ -72,31 +72,82 @@ VM_DEFINE_LOADER (82, load_number, "load-number")
VM_DEFINE_LOADER (83, load_string, "load-string")
{
size_t len;
int width;
SCM str;
FETCH_LENGTH (len);
FETCH_WIDTH (width);
SYNC_REGISTER ();
PUSH (scm_from_locale_stringn ((char *)ip, len));
/* Was: scm_makfromstr (ip, len, 0) */
ip += len;
if (width == 1)
{
char *buf;
str = scm_i_make_string (len, &buf);
memcpy (buf, (char *) ip, len);
}
else if (width == 4)
{
scm_t_wchar *wbuf;
str = scm_i_make_wide_string (len, &wbuf);
memcpy ((char *) wbuf, (char *) ip, len * width);
}
else
SCM_MISC_ERROR ("load-string: invalid character width", SCM_EOL);
PUSH (str);
ip += len * width;
NEXT;
}
VM_DEFINE_LOADER (84, load_symbol, "load-symbol")
{
size_t len;
int width;
SCM str;
FETCH_LENGTH (len);
FETCH_WIDTH (width);
SYNC_REGISTER ();
PUSH (scm_from_locale_symboln ((char *)ip, len));
ip += len;
if (width == 1)
{
char *buf;
str = scm_i_make_string (len, &buf);
memcpy (buf, (char *) ip, len);
}
else if (width == 4)
{
scm_t_wchar *wbuf;
str = scm_i_make_wide_string (len, &wbuf);
memcpy ((char *) wbuf, (char *) ip, len * width);
}
else
SCM_MISC_ERROR ("load-symbol: invalid character width", SCM_EOL);
PUSH (scm_string_to_symbol (str));
ip += len * width;
NEXT;
}
VM_DEFINE_LOADER (85, load_keyword, "load-keyword")
{
size_t len;
int width;
SCM str;
FETCH_LENGTH (len);
FETCH_WIDTH (width);
SYNC_REGISTER ();
PUSH (scm_from_locale_keywordn ((char *)ip, len));
ip += len;
if (width == 1)
{
char *buf;
str = scm_i_make_string (len, &buf);
memcpy (buf, (char *) ip, len);
}
else if (width == 4)
{
scm_t_wchar *wbuf;
str = scm_i_make_wide_string (len, &wbuf);
memcpy ((char *) wbuf, (char *) ip, len * width);
}
else
SCM_MISC_ERROR ("load-keyword: invalid character width", SCM_EOL);
PUSH (scm_symbol_to_keyword (scm_string_to_symbol (str)));
ip += len * width;
NEXT;
}
@ -132,13 +183,29 @@ VM_DEFINE_INSTRUCTION (87, link_now, "link-now", 0, 1, 1)
VM_DEFINE_LOADER (88, define, "define")
{
SCM sym;
SCM str, sym;
size_t len;
int width;
FETCH_LENGTH (len);
FETCH_WIDTH (width);
SYNC_REGISTER ();
sym = scm_from_locale_symboln ((char *)ip, len);
ip += len;
if (width == 1)
{
char *buf;
str = scm_i_make_string (len, &buf);
memcpy (buf, (char *) ip, len);
}
else if (width == 4)
{
scm_t_wchar *wbuf;
str = scm_i_make_wide_string (len, &wbuf);
memcpy ((char *) wbuf, (char *) ip, len * width);
}
else
SCM_MISC_ERROR ("load define: invalid character width", SCM_EOL);
sym = scm_string_to_symbol (str);
ip += len * width;
SYNC_REGISTER ();
PUSH (scm_sym2var (sym, scm_current_module_lookup_closure (), SCM_BOOL_T));