summaryrefslogtreecommitdiff
path: root/libguile/posix.c
diff options
context:
space:
mode:
authorMichael Gran <spk121@yahoo.com>2009-08-25 07:54:37 -0700
committerMichael Gran <spk121@yahoo.com>2009-08-25 07:54:37 -0700
commit889975e51accb80491af76fc5db980aeb3edd342 (patch)
tree43b57c4388abcf86e97f8f413abc4ebbcaeac1a8 /libguile/posix.c
parent9db8cf1634ca9a91cb88b2532f7b87f2502b4abd (diff)
downloadguile-889975e51accb80491af76fc5db980aeb3edd342.tar.gz
Add full Unicode capability to ports and the default reader
Ports are given two additional properties: a character encoding and a conversion failure strategy. These properties have getters and setters. The new properties are used to convert any locale text to/from the internal representation of strings. If unspecified, ports use a default value. The default value of these properties is held in a fluid. The default character encoding can be modified by calling setlocale. ISO-8859-1 is treated specially. Since it is a native encoding of strings, it can be processed more quickly. Source code is assumed to be ISO-8859-1 unless otherwise specified. The encoding of a source code file can be given as 'coding: XXXXX' in a magic comment at the top of a file. The C functions that deal with encoding often use a null pointer as shorthand for the native Latin-1 encoding, for efficiency's sake. * test-suite/tests/encoding-iso88591.test: new tests * test-suite/tests/encoding-iso88597.test: new tests * test-suite/tests/encoding-utf8.test: new tests * test-suite/tests/encoding-escapes.test: new tests * test-suite/tests/numbers.test: declare 'binary' encoding * test-suite/tests/ports.test: declare 'binary' encoding * test-suite/tests/r6rs-ports.test: declare 'binary' encoding * module/system/base/compile.scm (compile-file): use source-code file's self-declared encoding when compiling files * libguile/strports.c: store string ports in locale encoding (scm_strport_to_locale_u8vector, scm_call_with_output_locale_u8vector) (scm_open_input_locale_u8vector, scm_get_output_locale_u8vector): new functions * libguile/strings.h: new declaration for scm_i_string_contains_char * libguile/strings.c (scm_i_string_contains_char): new function (scm_from_stringn, scm_to_stringn): use NULL for Latin-1 (scm_from_locale_stringn, scm_to_locale_stringn): respect character encoding of input and output ports * libguile/read.h: declaration for scm_scan_for_encoding * libguile/read.c: (read_token): now takes scheme string instead of C string/length (read_complete_token): new function (scm_read_sexp, scm_read_number, scm_read_mixed_case_symbol) (scm_read_number_and_radix, scm_read_quote, scm_read_semicolon_comment) (scm_read_srfi4_vector, scm_read_bytevector, scm_read_guile_bit_vector) (scm_read_scsh_block_comment, scm_read_commented_expression) (scm_read_extended_symbol, scm_read_sharp_extension, scm_read_shart) (scm_read_expression): use scm_t_wchar for char type, use read_complete_token (scm_scan_for_encoding): new function to find a file's character encoding (scm_file_encoding): new function to find a port's character encoding * libguile/rdelim.c: don't unpack strings * libguile/print.h: declaration for modified function scm_i_charprint * libguile/print.c: use locale when printing characters and strings (scm_i_charprint): input parameter is now scm_t_wchar (scm_simple_format): don't unpack strings * libguile/posix.h: new declaration for scm_setbinary. * libguile/posix.c (scm_setlocale): set default and stdio port encodings based on the locale's character encoding (scm_setbinary): new function * libguile/ports.h (scm_t_port): add encoding and failed conversion handler to port type. Declarations for new or modified functions scm_getc, scm_unget_byte, scm_ungetc, scm_i_get_port_encoding, scm_i_set_port_encoding_x, scm_port_encoding, scm_set_port_encoding_x, scm_i_get_conversion_strategy, scm_i_set_conversion_strategy_x, scm_port_conversion_strategy, scm_set_port_conversion_strategy_x. * libguile/ports.c: assign the current ports to zero on startup so we can see if they've been set. (scm_current_input_port, scm_current_output_port, scm_current_error_port): return #f if the port is not yet initialized (scm_new_port_table_entry): set up a new port's encoding and illegal sequence handler based on the thread's current defaults (scm_i_remove_port): free port encoding name when port is removed (scm_i_mode_bits_n): now takes a scheme string instead of a c string and length. All callers changed. (SCM_MBCHAR_BUF_SIZE): new const (scm_getc): new function, since the scm_getc in inline.h is now scm_get_byte_or_eof. This pulls one codepoint from a port. (scm_lfwrite_substr, scm_lfwrite_str): now uses port's encoding (scm_unget_byte): new function, incorportaing the low-level functionality of scm_ungetc (scm_ungetc): uses scm_unget_byte * libguile/numbers.h (scm_t_wchar): compilation order problem with scm_t_wchar being use in functions in multiple headers. Forward declare scm_t_wchar. * libguile/load.c (scm_primitive_load): scan for file encoding at top of file and use it to set the load port's encoding * libguile/inline.h (scm_get_byte_or_eof): new function incorporating most of the functionality of scm_getc. * libguile/fports.c (fport_fill_input): now returns scm_t_wchar * libguile/chars.h (scm_t_wchar): avoid compilation order problem with declaration of scm_t_wchar
Diffstat (limited to 'libguile/posix.c')
-rw-r--r--libguile/posix.c46
1 files changed, 42 insertions, 4 deletions
diff --git a/libguile/posix.c b/libguile/posix.c
index dafc5e996..09d53f212 100644
--- a/libguile/posix.c
+++ b/libguile/posix.c
@@ -25,6 +25,7 @@
#include <stdlib.h>
#include <stdio.h>
#include <errno.h>
+#include <uniconv.h>
#include "libguile/_scm.h"
#include "libguile/dynwind.h"
@@ -1528,12 +1529,17 @@ SCM_DEFINE (scm_setlocale, "setlocale", 1, 1, 0,
"Otherwise the specified locale category is set to the string\n"
"@var{locale} and the new value is returned as a\n"
"system-dependent string. If @var{locale} is an empty string,\n"
- "the locale will be set using environment variables.")
+ "the locale will be set using environment variables.\n"
+ "\n"
+ "When the locale is changed, the character encoding of the new\n"
+ "locale (UTF-8, ISO-8859-1, etc.) is used for the current\n"
+ "input, output, and error ports\n")
#define FUNC_NAME s_scm_setlocale
{
int c_category;
char *clocale;
char *rv;
+ const char *enc;
scm_dynwind_begin (0);
@@ -1562,15 +1568,47 @@ SCM_DEFINE (scm_setlocale, "setlocale", 1, 1, 0,
SCM_SYSERROR;
}
- /* Recompute the standard SRFI-14 character sets in a locale-dependent
- (actually charset-dependent) way. */
- scm_srfi_14_compute_char_sets ();
+ enc = locale_charset ();
+ /* Set the default encoding for new ports. */
+ scm_i_set_port_encoding_x (SCM_BOOL_F, enc);
+ /* Set the encoding for the stdio ports. */
+ scm_i_set_port_encoding_x (scm_current_input_port (), enc);
+ scm_i_set_port_encoding_x (scm_current_output_port (), enc);
+ scm_i_set_port_encoding_x (scm_current_error_port (), enc);
scm_dynwind_end ();
return scm_from_locale_string (rv);
}
#undef FUNC_NAME
#endif /* HAVE_SETLOCALE */
+SCM_DEFINE (scm_setbinary, "setbinary", 0, 0, 0,
+ (void),
+ "Sets the encoding for the current input, output, and error\n"
+ "ports to ISO-8859-1. That character encoding allows\n"
+ "ports to operate on binary data.\n"
+ "\n"
+ "It also sets the default encoding for newly created ports\n"
+ "to ISO-8859-1.\n"
+ "\n"
+ "The previous default encoding for new ports is returned\n")
+#define FUNC_NAME s_scm_setbinary
+{
+ const char *enc = scm_i_get_port_encoding (SCM_BOOL_F);
+
+ /* Set the default encoding for new ports. */
+ scm_i_set_port_encoding_x (SCM_BOOL_F, NULL);
+ /* Set the encoding for the stdio ports. */
+ scm_i_set_port_encoding_x (scm_current_input_port (), NULL);
+ scm_i_set_port_encoding_x (scm_current_output_port (), NULL);
+ scm_i_set_port_encoding_x (scm_current_error_port (), NULL);
+
+ if (enc)
+ return scm_from_locale_string (enc);
+
+ return scm_from_locale_string ("ISO-8859-1");
+}
+#undef FUNC_NAME
+
#ifdef HAVE_MKNOD
SCM_DEFINE (scm_mknod, "mknod", 4, 0, 0,