1996-07-25 22:56:11 +00:00
|
|
|
|
/* classes: h_files */
|
|
|
|
|
|
|
2001-08-31 10:42:19 +00:00
|
|
|
|
#ifndef SCM_READ_H
|
|
|
|
|
|
#define SCM_READ_H
|
|
|
|
|
|
|
2009-11-14 16:27:28 +01:00
|
|
|
|
/* Copyright (C) 1995,1996,2000, 2006, 2008, 2009 Free Software Foundation, Inc.
|
2001-08-31 10:42:19 +00:00
|
|
|
|
*
|
2003-04-05 19:15:35 +00:00
|
|
|
|
* This library is free software; you can redistribute it and/or
|
2009-06-17 00:22:09 +01:00
|
|
|
|
* modify it under the terms of the GNU Lesser General Public License
|
|
|
|
|
|
* as published by the Free Software Foundation; either version 3 of
|
|
|
|
|
|
* the License, or (at your option) any later version.
|
2001-08-31 10:42:19 +00:00
|
|
|
|
*
|
2009-06-17 00:22:09 +01:00
|
|
|
|
* This library is distributed in the hope that it will be useful, but
|
|
|
|
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
2003-04-05 19:15:35 +00:00
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
|
|
* Lesser General Public License for more details.
|
2001-08-31 10:42:19 +00:00
|
|
|
|
*
|
2003-04-05 19:15:35 +00:00
|
|
|
|
* You should have received a copy of the GNU Lesser General Public
|
|
|
|
|
|
* License along with this library; if not, write to the Free Software
|
2009-06-17 00:22:09 +01:00
|
|
|
|
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
|
|
|
|
|
|
* 02110-1301 USA
|
2003-04-05 19:15:35 +00:00
|
|
|
|
*/
|
2001-08-31 10:42:19 +00:00
|
|
|
|
|
1996-07-25 22:56:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
* alist.h, append.h, arbiters.h, async.h, boolean.h, chars.h,
continuations.h, debug.h, dynwind.h, error.h, eval.h, fdsocket.h,
feature.h, filesys.h, fports.h, gc.h, gdbint.h, genio.h, gsubr.h,
hash.h, init.h, ioext.h, kw.h, list.h, markers.h, marksweep.h,
mbstrings.h, numbers.h, objprop.h, options.h, pairs.h, ports.h,
posix.h, print.h, procprop.h, procs.h, ramap.h, read.h, root.h,
sequences.h, smob.h, socket.h, srcprop.h, stackchk.h, stime.h,
strings.h, strop.h, strorder.h, strports.h, struct.h, symbols.h,
tag.h, throw.h, unif.h, variable.h, vectors.h, version.h,
vports.h, weaks.h: #include "libguile/__scm.h", not
<libguile/__scm.h>. This allows 'gcc -MM' to determine which
dependencies are within libguile properly.
1996-09-05 21:19:08 +00:00
|
|
|
|
#include "libguile/__scm.h"
|
1996-07-25 22:56:11 +00:00
|
|
|
|
|
1996-09-10 02:29:49 +00:00
|
|
|
|
#include "libguile/options.h"
|
1996-07-25 22:56:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/* SCM_LINE_INCREMENTORS are the characters which cause the line count to
|
|
|
|
|
|
* be incremented for the purposes of error reporting. This feature
|
|
|
|
|
|
* is only used for scheme code loaded from files.
|
|
|
|
|
|
*
|
|
|
|
|
|
* SCM_WHITE_SPACES are other characters which should be treated like spaces
|
|
|
|
|
|
* in programs.
|
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
|
|
#define SCM_LINE_INCREMENTORS '\n'
|
|
|
|
|
|
|
|
|
|
|
|
#ifdef MSDOS
|
|
|
|
|
|
# define SCM_SINGLE_SPACES ' ':case '\r':case '\f': case 26
|
|
|
|
|
|
#else
|
|
|
|
|
|
# define SCM_SINGLE_SPACES ' ':case '\r':case '\f'
|
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
|
|
#define SCM_WHITE_SPACES SCM_SINGLE_SPACES: case '\t'
|
|
|
|
|
|
|
* backtrace.c, debug.c, debug.h, deprecation.c, eq.c, eval.c
eval.h, gsubr.c, init.c, macros.c, print.c, print.h, read.c,
read.h, stacks.c, symbols.c, throw.c: use private-options.h
* private-options.h: new file: contain hardcoded option
definitions.
2007-01-22 15:14:40 +00:00
|
|
|
|
|
1996-08-20 17:11:34 +00:00
|
|
|
|
|
1996-07-25 22:56:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
2003-05-06 20:17:26 +00:00
|
|
|
|
SCM_API SCM scm_sym_dot;
|
|
|
|
|
|
|
2001-11-02 00:19:12 +00:00
|
|
|
|
SCM_API SCM scm_read_options (SCM setting);
|
|
|
|
|
|
SCM_API SCM scm_read (SCM port);
|
|
|
|
|
|
SCM_API SCM scm_read_hash_extend (SCM chr, SCM proc);
|
2009-11-14 16:27:28 +01:00
|
|
|
|
SCM_INTERNAL char *scm_i_scan_for_encoding (SCM port);
|
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
2009-08-25 07:54:37 -07:00
|
|
|
|
SCM_API SCM scm_file_encoding (SCM port);
|
2004-10-26 17:00:13 +00:00
|
|
|
|
|
2008-05-14 05:20:47 +02:00
|
|
|
|
SCM_INTERNAL void scm_i_input_error (const char *func, SCM port,
|
|
|
|
|
|
const char *message, SCM arg)
|
2007-07-22 16:30:13 +00:00
|
|
|
|
SCM_NORETURN;
|
2004-10-26 17:00:13 +00:00
|
|
|
|
|
2008-05-14 05:20:47 +02:00
|
|
|
|
SCM_INTERNAL void scm_init_read (void);
|
1996-07-25 22:56:11 +00:00
|
|
|
|
|
2001-08-31 10:42:19 +00:00
|
|
|
|
#endif /* SCM_READ_H */
|
2000-03-19 19:01:16 +00:00
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
|
Local Variables:
|
|
|
|
|
|
c-file-style: "gnu"
|
|
|
|
|
|
End:
|
|
|
|
|
|
*/
|