From 9c44cd4559a5d04ba70bbd9ff47f41bfdfebd09d Mon Sep 17 00:00:00 2001 From: Michael Gran Date: Sat, 8 Aug 2009 02:35:00 -0700 Subject: Add Unicode strings and symbols 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 --- libguile/socket.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'libguile/socket.c') diff --git a/libguile/socket.c b/libguile/socket.c index 553a1a185..2e02e9082 100644 --- a/libguile/socket.c +++ b/libguile/socket.c @@ -1438,6 +1438,7 @@ SCM_DEFINE (scm_recv, "recv!", 2, 1, 0, fd = SCM_FPORT_FDES (sock); len = scm_i_string_length (buf); + buf = scm_i_string_start_writing (buf); dest = scm_i_string_writable_chars (buf); SCM_SYSCALL (rv = recv (fd, dest, len, flg)); scm_i_string_stop_writing (); @@ -1482,6 +1483,7 @@ SCM_DEFINE (scm_send, "send", 2, 1, 0, fd = SCM_FPORT_FDES (sock); len = scm_i_string_length (message); + message = scm_i_string_start_writing (message); src = scm_i_string_writable_chars (message); SCM_SYSCALL (rv = send (fd, src, len, flg)); scm_i_string_stop_writing (); @@ -1550,6 +1552,7 @@ SCM_DEFINE (scm_recvfrom, "recvfrom!", 2, 3, 0, /* recvfrom will not necessarily return an address. usually nothing is returned for stream sockets. */ + str = scm_i_string_start_writing (str); buf = scm_i_string_writable_chars (str); ((struct sockaddr *) &addr)->sa_family = AF_UNSPEC; SCM_SYSCALL (rv = recvfrom (fd, buf + offset, -- cgit v1.2.3