guile/libguile/print.c

1327 lines
37 KiB
C
Raw Normal View History

Remove "compiled closures" ("cclos") in favor of a simpler mechanism. The idea is to introduce `gsubrs' whose arity is encoded in their type (more precisely in the sizeof (void *) - 8 MSBs). This removes the indirection introduced by cclos and simplifies the code. * libguile/__scm.h (CCLO): Remove. * libguile/debug.c (scm_procedure_source, scm_procedure_environment): Remove references to `scm_tc7_cclo'. * libguile/eval.c (scm_trampoline_0, scm_trampoline_1, scm_trampoline_2): Replace `scm_tc7_cclo' with `scm_tc7_gsubr'. * libguile/eval.i.c (CEVAL): Likewise. No longer make PROC the first argument. Directly invoke `scm_gsubr_apply ()' instead of jump to the `evap(N+1)' label or call to `SCM_APPLY ()'. * libguile/evalext.c (scm_self_evaluating_p): Remove reference to `scm_tc7_cclo'. * libguile/gc-card.c (scm_i_sweep_card, scm_i_tag_name): Likewise. * libguile/gc-mark.c (scm_gc_mark_dependencies): Likewise. * libguile/goops.c (scm_class_of): Likewise. * libguile/print.c (iprin1): Likewise. * libguile/gsubr.c (create_gsubr): Use `unsigned int's for REQ, OPT and RST. Use `scm_tc7_gsubr' instead of `scm_makcclo ()' in the default case. (scm_gsubr_apply): Remove calls to `SCM_GSUBR_PROC ()'. (scm_f_gsubr_apply): Remove. * libguile/gsubr.h (SCM_GSUBR_TYPE): New definition. (SCM_GSUBR_MAX): Changed to 33. (SCM_SET_GSUBR_TYPE, SCM_GSUBR_PROC, SCM_SET_GSUBR_PROC, scm_f_gsubr_apply): Remove. * libguile/procprop.c (scm_i_procedure_arity): Remove reference to `scm_tc7_cclo'; add proper handling of `scm_tc7_gsubr'. * libguile/procs.c (scm_makcclo, scm_make_cclo): Remove. (scm_procedure_p): Remove reference to `scm_tc7_cclo'. (scm_thunk_p): Likewise, plus add proper `scm_tc7_gsubr' handling. * libguile/procs.h (SCM_CCLO_LENGTH, SCM_MAKE_CCLO_TAG, SCM_SET_CCLO_LENGTH, SCM_CCLO_BASE, SCM_SET_CCLO_BASE, SCM_CCLO_REF, SCM_CCLO_SET, SCM_CCLO_SUBR, SCM_SET_CCLO_SUBR, scm_makcclo, scm_make_cclo): Remove. * libguile/stacks.c (read_frames): Remove reference to `scm_f_gsubr_apply'. * libguile/tags.h (scm_tc7_cclo): Remove. (scm_tc7_gsubr): New. (scm_tcs_subrs): Add `scm_tc7_gsubr'.
2009-02-16 00:24:00 +01:00
/* Copyright (C) 1995-1999,2000,2001, 2002, 2003, 2004, 2006, 2008, 2009 Free Software Foundation, Inc.
*
* This library is free software; you can redistribute it and/or
* 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.
*
* This library is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301 USA
*/
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#include <errno.h>
#include <uniconv.h>
#include <unictype.h>
#include "libguile/_scm.h"
#include "libguile/chars.h"
#include "libguile/continuations.h"
#include "libguile/smob.h"
#include "libguile/eval.h"
#include "libguile/macros.h"
#include "libguile/procprop.h"
#include "libguile/read.h"
#include "libguile/weaks.h"
#include "libguile/programs.h"
#include "libguile/alist.h"
#include "libguile/struct.h"
#include "libguile/ports.h"
#include "libguile/root.h"
#include "libguile/strings.h"
#include "libguile/strports.h"
#include "libguile/vectors.h"
#include "libguile/lang.h"
#include "libguile/numbers.h"
#include "libguile/validate.h"
#include "libguile/print.h"
#include "libguile/private-options.h"
/* {Names of immediate symbols}
*
* This table must agree with the declarations in scm.h: {Immediate Symbols}.
*/
/* This table must agree with the list of flags in tags.h. */
static const char *iflagnames[] =
{
"#f",
the cube of lisp booleans (#f nil () #t) * Renumbers the IFLAG constants. * Adds several macros related to boolean type tests, null tests, and boolean-truth testing (including lisp-style boolean-truth tests). * Adds compile-time checks to verify the necessary IFLAG numbering properties needed for the checks to work properly. * Changes some existing code to use the new optimized macros, without changing the semantics of the code at all (except that scm_is_bool is changed from a function to a macro). I added the following macros, whose names explicitly state how %nil should be handled. See the comments in the patch for more information about these. scm_is_false_assume_not_lisp_nil scm_is_true_assume_not_lisp_nil scm_is_false_and_not_lisp_nil scm_is_true_or_lisp_nil scm_is_false_or_lisp_nil scm_is_true_and_not_lisp_nil scm_is_lisp_false scm_is_lisp_true scm_is_null_assume_not_lisp_nil scm_is_null_and_not_lisp_nil scm_is_null_or_lisp_nil scm_is_bool_and_not_lisp_nil scm_is_bool_or_lisp_nil The following already-existing macros are defined as aliases, such that their semantics is unchanged (although scm_is_bool used to be a function and is now a macro). scm_is_null --> scm_is_null_and_not_lisp_nil scm_is_false --> scm_is_false_and_not_lisp_nil scm_is_true --> scm_is_true_or_lisp_nil scm_is_bool --> scm_is_bool_and_not_lisp_nil (I still believe that these should be changed to versions that handle %nil properly, but await approval on that point, so these patches do not make those changes) Also, if the preprocessor macro SCM_ENABLE_ELISP is not true (this macro already existed and was used in lang.h), all overheads associated with %nil handling are eliminated from the above macros. * libguile/tags.h (SCM_BOOL_F, SCM_BOOL_T, SCM_UNSPECIFIED) (SCM_UNDEFINED, SCM_UNBOUND, SCM_ELISP_NIL): Renumber, so that a number of important distinctions (false versus true, end-of-list, etc) can be made by masking a single bit. Also define a number of build-time tests to assert that this condition holds. * libguile/boolean.h (scm_is_false_and_not_nil, scm_is_true_or_nil) (scm_is_false_assume_not_nil, scm_is_true_assume_not_nil): (scm_is_false_or_nil, scm_is_true_and_not_nil) (scm_is_bool_or_nil, scm_is_bool_and_not_nil): New exciting macros to test certain boolean/end-of-list properties. (scm_is_false, scm_is_true): Use a restrictive definition, where only SCM_BOOL_F is false. Should probably change in the future. (scm_is_bool): Incompatible change: changed to be a macro. Was a function before. Probably should allow nil as a boolean, but that will be for a later patch. (scm_is_lisp_false, scm_is_lisp_true): New macros, implementing the standard Lisp boolean predicates, where '() is actually false. * libguile/eval.i.c (CEVAL): Fix a number of false-or-nil and similar tests to use the new macros. * libguile/lang.h (SCM_NULL_OR_NIL_P): Use scm_is_null_or_nil. * libguile/pairs.c: Add a compile-time check that null and nil differ by only one bit. * libguile/pairs.h (scm_is_null_and_not_nil, scm_is_null_assume_not_nil) (scm_is_null_or_nil): New exciting macros! (scm_is_null): Just be scm_is_null_and_not_nil, for now. * libguile/print.c: Adapt to the reordering, and print suitably nasty things for the not-to-be-used values.
2009-10-26 23:56:03 +01:00
"#nil", /* Elisp nil value. Should print from elisp as symbol `nil'. */
"#<XXX UNUSED LISP FALSE -- DO NOT USE -- SHOULD NEVER BE SEEN XXX>",
"()",
"#t",
the cube of lisp booleans (#f nil () #t) * Renumbers the IFLAG constants. * Adds several macros related to boolean type tests, null tests, and boolean-truth testing (including lisp-style boolean-truth tests). * Adds compile-time checks to verify the necessary IFLAG numbering properties needed for the checks to work properly. * Changes some existing code to use the new optimized macros, without changing the semantics of the code at all (except that scm_is_bool is changed from a function to a macro). I added the following macros, whose names explicitly state how %nil should be handled. See the comments in the patch for more information about these. scm_is_false_assume_not_lisp_nil scm_is_true_assume_not_lisp_nil scm_is_false_and_not_lisp_nil scm_is_true_or_lisp_nil scm_is_false_or_lisp_nil scm_is_true_and_not_lisp_nil scm_is_lisp_false scm_is_lisp_true scm_is_null_assume_not_lisp_nil scm_is_null_and_not_lisp_nil scm_is_null_or_lisp_nil scm_is_bool_and_not_lisp_nil scm_is_bool_or_lisp_nil The following already-existing macros are defined as aliases, such that their semantics is unchanged (although scm_is_bool used to be a function and is now a macro). scm_is_null --> scm_is_null_and_not_lisp_nil scm_is_false --> scm_is_false_and_not_lisp_nil scm_is_true --> scm_is_true_or_lisp_nil scm_is_bool --> scm_is_bool_and_not_lisp_nil (I still believe that these should be changed to versions that handle %nil properly, but await approval on that point, so these patches do not make those changes) Also, if the preprocessor macro SCM_ENABLE_ELISP is not true (this macro already existed and was used in lang.h), all overheads associated with %nil handling are eliminated from the above macros. * libguile/tags.h (SCM_BOOL_F, SCM_BOOL_T, SCM_UNSPECIFIED) (SCM_UNDEFINED, SCM_UNBOUND, SCM_ELISP_NIL): Renumber, so that a number of important distinctions (false versus true, end-of-list, etc) can be made by masking a single bit. Also define a number of build-time tests to assert that this condition holds. * libguile/boolean.h (scm_is_false_and_not_nil, scm_is_true_or_nil) (scm_is_false_assume_not_nil, scm_is_true_assume_not_nil): (scm_is_false_or_nil, scm_is_true_and_not_nil) (scm_is_bool_or_nil, scm_is_bool_and_not_nil): New exciting macros to test certain boolean/end-of-list properties. (scm_is_false, scm_is_true): Use a restrictive definition, where only SCM_BOOL_F is false. Should probably change in the future. (scm_is_bool): Incompatible change: changed to be a macro. Was a function before. Probably should allow nil as a boolean, but that will be for a later patch. (scm_is_lisp_false, scm_is_lisp_true): New macros, implementing the standard Lisp boolean predicates, where '() is actually false. * libguile/eval.i.c (CEVAL): Fix a number of false-or-nil and similar tests to use the new macros. * libguile/lang.h (SCM_NULL_OR_NIL_P): Use scm_is_null_or_nil. * libguile/pairs.c: Add a compile-time check that null and nil differ by only one bit. * libguile/pairs.h (scm_is_null_and_not_nil, scm_is_null_assume_not_nil) (scm_is_null_or_nil): New exciting macros! (scm_is_null): Just be scm_is_null_and_not_nil, for now. * libguile/print.c: Adapt to the reordering, and print suitably nasty things for the not-to-be-used values.
2009-10-26 23:56:03 +01:00
"#<XXX UNUSED BOOLEAN -- DO NOT USE -- SHOULD NEVER BE SEEN XXX>",
"#<unspecified>",
"#<undefined>",
"#<eof>",
/* Unbound slot marker for GOOPS. For internal use in GOOPS only. */
"#<unbound>",
};
SCM_SYMBOL (sym_reader, "reader");
2001-06-14 19:50:43 +00:00
scm_t_option scm_print_opts[] = {
{ SCM_OPTION_SCM, "closure-hook", SCM_UNPACK (SCM_BOOL_F),
"Hook for printing closures (should handle macros as well)." },
{ SCM_OPTION_BOOLEAN, "source", 0,
"Print closures with source." },
{ SCM_OPTION_SCM, "highlight-prefix", (unsigned long)SCM_BOOL_F,
"The string to print before highlighted values." },
{ SCM_OPTION_SCM, "highlight-suffix", (unsigned long)SCM_BOOL_F,
"The string to print after highlighted values." },
{ SCM_OPTION_SCM, "quote-keywordish-symbols", (unsigned long)SCM_BOOL_F,
"How to print symbols that have a colon as their first or last character. "
"The value '#f' does not quote the colons; '#t' quotes them; "
"'reader' quotes them when the reader option 'keywords' is not '#f'."
},
{ 0 },
};
SCM_DEFINE (scm_print_options, "print-options-interface", 0, 1, 0,
(SCM setting),
"Option interface for the print options. Instead of using\n"
"this procedure directly, use the procedures\n"
"@code{print-enable}, @code{print-disable}, @code{print-set!}\n"
"and @code{print-options}.")
#define FUNC_NAME s_scm_print_options
{
SCM ans = scm_options (setting,
scm_print_opts,
FUNC_NAME);
return ans;
}
#undef FUNC_NAME
/* {Printing of Scheme Objects}
*/
/* Detection of circular references.
*
* Due to other constraints in the implementation, this code has bad
* time complexity (O (depth * N)), The printer code can be
* rewritten to be O(N).
*/
#define PUSH_REF(pstate, obj) \
do \
{ \
PSTATE_STACK_SET (pstate, pstate->top, obj); \
pstate->top++; \
if (pstate->top == pstate->ceiling) \
grow_ref_stack (pstate); \
} while(0)
#define ENTER_NESTED_DATA(pstate, obj, label) \
do \
{ \
register unsigned long i; \
for (i = 0; i < pstate->top; ++i) \
if (scm_is_eq (PSTATE_STACK_REF (pstate, i), (obj))) \
goto label; \
if (pstate->fancyp) \
{ \
if (pstate->top - pstate->list_offset >= pstate->level) \
{ \
scm_putc ('#', port); \
return; \
} \
} \
PUSH_REF(pstate, obj); \
} while(0)
#define EXIT_NESTED_DATA(pstate) \
do \
{ \
--pstate->top; \
PSTATE_STACK_SET (pstate, pstate->top, SCM_UNDEFINED); \
} \
while (0)
SCM scm_print_state_vtable = SCM_BOOL_F;
static SCM print_state_pool = SCM_EOL;
2005-03-02 20:42:01 +00:00
scm_i_pthread_mutex_t print_state_mutex = SCM_I_PTHREAD_MUTEX_INITIALIZER;
#ifdef GUILE_DEBUG /* Used for debugging purposes */
SCM_DEFINE (scm_current_pstate, "current-pstate", 0, 0, 0,
(),
"Return the current-pstate -- the car of the\n"
"@code{print_state_pool}. @code{current-pstate} is only\n"
"included in @code{--enable-guile-debug} builds.")
#define FUNC_NAME s_scm_current_pstate
{
2004-09-22 17:41:37 +00:00
if (!scm_is_null (print_state_pool))
return SCM_CAR (print_state_pool);
else
return SCM_BOOL_F;
}
#undef FUNC_NAME
#endif
#define PSTATE_SIZE 50L
static SCM
make_print_state (void)
{
SCM print_state
= scm_make_struct (scm_print_state_vtable, SCM_INUM0, SCM_EOL);
scm_print_state *pstate = SCM_PRINT_STATE (print_state);
pstate->ref_vect = scm_c_make_vector (PSTATE_SIZE, SCM_UNDEFINED);
pstate->ceiling = SCM_SIMPLE_VECTOR_LENGTH (pstate->ref_vect);
pstate->highlight_objects = SCM_EOL;
return print_state;
}
SCM
scm_make_print_state ()
{
SCM answer = SCM_BOOL_F;
/* First try to allocate a print state from the pool */
2005-03-02 20:42:01 +00:00
scm_i_pthread_mutex_lock (&print_state_mutex);
2004-09-22 17:41:37 +00:00
if (!scm_is_null (print_state_pool))
{
answer = SCM_CAR (print_state_pool);
print_state_pool = SCM_CDR (print_state_pool);
}
2005-03-02 20:42:01 +00:00
scm_i_pthread_mutex_unlock (&print_state_mutex);
return scm_is_false (answer) ? make_print_state () : answer;
}
void
scm_free_print_state (SCM print_state)
{
SCM handle;
scm_print_state *pstate = SCM_PRINT_STATE (print_state);
/* Cleanup before returning print state to pool.
* It is better to do it here. Doing it in scm_prin1
* would cost more since that function is called much more
* often.
*/
pstate->fancyp = 0;
pstate->revealed = 0;
pstate->highlight_objects = SCM_EOL;
2005-03-02 20:42:01 +00:00
scm_i_pthread_mutex_lock (&print_state_mutex);
handle = scm_cons (print_state, print_state_pool);
print_state_pool = handle;
2005-03-02 20:42:01 +00:00
scm_i_pthread_mutex_unlock (&print_state_mutex);
}
SCM
scm_i_port_with_print_state (SCM port, SCM print_state)
{
if (SCM_UNBNDP (print_state))
{
if (SCM_PORT_WITH_PS_P (port))
return port;
else
print_state = scm_make_print_state ();
/* port does not need to be coerced since it doesn't have ps */
}
else
port = SCM_COERCE_OUTPORT (port);
SCM_RETURN_NEWSMOB (scm_tc16_port_with_ps,
SCM_UNPACK (scm_cons (port, print_state)));
}
static void
grow_ref_stack (scm_print_state *pstate)
{
SCM old_vect = pstate->ref_vect;
size_t old_size = SCM_SIMPLE_VECTOR_LENGTH (old_vect);
size_t new_size = 2 * pstate->ceiling;
SCM new_vect = scm_c_make_vector (new_size, SCM_UNDEFINED);
unsigned long int i;
for (i = 0; i != old_size; ++i)
SCM_SIMPLE_VECTOR_SET (new_vect, i, SCM_SIMPLE_VECTOR_REF (old_vect, i));
pstate->ref_vect = new_vect;
pstate->ceiling = new_size;
}
#define PSTATE_STACK_REF(p,i) SCM_SIMPLE_VECTOR_REF((p)->ref_vect, (i))
#define PSTATE_STACK_SET(p,i,v) SCM_SIMPLE_VECTOR_SET((p)->ref_vect, (i), (v))
static void
print_circref (SCM port, scm_print_state *pstate, SCM ref)
{
register long i;
long self = pstate->top - 1;
i = pstate->top - 1;
if (scm_is_pair (PSTATE_STACK_REF (pstate, i)))
{
while (i > 0)
{
if (!scm_is_pair (PSTATE_STACK_REF (pstate, i-1))
|| !scm_is_eq (SCM_CDR (PSTATE_STACK_REF (pstate, i-1)),
SCM_CDR (PSTATE_STACK_REF (pstate, i))))
break;
--i;
}
self = i;
}
for (i = pstate->top - 1; 1; --i)
if (scm_is_eq (PSTATE_STACK_REF(pstate, i), ref))
break;
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_putc ('#', port);
scm_intprint (i - self, 10, port);
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_putc ('#', port);
}
/* Print the name of a symbol. */
static int
quote_keywordish_symbol (SCM symbol)
{
SCM option;
if (scm_i_symbol_ref (symbol, 0) != ':'
&& scm_i_symbol_ref (symbol, scm_i_symbol_length (symbol) - 1) != ':')
return 0;
option = SCM_PRINT_KEYWORD_STYLE;
if (scm_is_false (option))
return 0;
if (scm_is_eq (option, sym_reader))
return scm_is_true (SCM_PACK (SCM_KEYWORD_STYLE));
return 1;
}
void
scm_i_print_symbol_name (SCM str, SCM port)
{
/* This points to the first character that has not yet been written to the
* port. */
size_t pos = 0;
/* This points to the character we're currently looking at. */
size_t end;
/* If the name contains weird characters, we'll escape them with
* backslashes and set this flag; it indicates that we should surround the
* name with "#{" and "}#". */
int weird = 0;
/* Backslashes are not sufficient to make a name weird, but if a name is
* weird because of other characters, backslahes need to be escaped too.
* The first time we see a backslash, we set maybe_weird, and mw_pos points
* to the backslash. Then if the name turns out to be weird, we re-process
* everything starting from mw_pos.
* We could instead make backslashes always weird. This is not necessary
* to ensure that the output is (read)-able, but it would make this code
* simpler and faster. */
int maybe_weird = 0;
size_t mw_pos = 0;
size_t len = scm_i_symbol_length (str);
scm_t_wchar str0 = scm_i_symbol_ref (str, 0);
if (len == 0 || str0 == '\'' || str0 == '`' || str0 == ','
|| quote_keywordish_symbol (str)
|| (str0 == '.' && len == 1)
|| scm_is_true (scm_i_string_to_number (scm_symbol_to_string (str), 10)))
{
scm_lfwrite ("#{", 2, port);
weird = 1;
}
for (end = pos; end < len; ++end)
switch (scm_i_symbol_ref (str, end))
{
#ifdef BRACKETS_AS_PARENS
case '[':
case ']':
#endif
case '(':
case ')':
case '"':
case ';':
case '#':
case SCM_WHITE_SPACES:
case SCM_LINE_INCREMENTORS:
weird_handler:
if (maybe_weird)
{
end = mw_pos;
maybe_weird = 0;
}
if (!weird)
{
scm_lfwrite ("#{", 2, port);
weird = 1;
}
if (pos < end)
scm_lfwrite_substr (scm_symbol_to_string (str), pos, end, port);
{
char buf[2];
buf[0] = '\\';
buf[1] = (char) (unsigned char) scm_i_symbol_ref (str, end);
scm_lfwrite (buf, 2, port);
}
pos = end + 1;
break;
case '\\':
if (weird)
goto weird_handler;
if (!maybe_weird)
{
maybe_weird = 1;
mw_pos = pos;
}
break;
default:
break;
}
if (pos < end)
scm_lfwrite_substr (scm_symbol_to_string (str), pos, end, port);
if (weird)
scm_lfwrite ("}#", 2, port);
}
void
scm_print_symbol_name (const char *str, size_t len, SCM port)
{
SCM symbol = scm_from_locale_symboln (str, len);
return scm_i_print_symbol_name (symbol, port);
}
/* Print generally. Handles both write and display according to PSTATE.
*/
SCM_GPROC(s_write, "write", 1, 1, 0, scm_write, g_write);
SCM_GPROC(s_display, "display", 1, 1, 0, scm_display, g_display);
static void iprin1 (SCM exp, SCM port, scm_print_state *pstate);
void
scm_iprin1 (SCM exp, SCM port, scm_print_state *pstate)
{
if (pstate->fancyp
&& scm_is_true (scm_memq (exp, pstate->highlight_objects)))
{
scm_display (SCM_PRINT_HIGHLIGHT_PREFIX, port);
iprin1 (exp, port, pstate);
scm_display (SCM_PRINT_HIGHLIGHT_SUFFIX, port);
}
else
iprin1 (exp, port, pstate);
}
static void
iprin1 (SCM exp, SCM port, scm_print_state *pstate)
{
switch (SCM_ITAG3 (exp))
{
case scm_tc3_closure:
case scm_tc3_tc7_1:
case scm_tc3_tc7_2:
/* These tc3 tags should never occur in an immediate value. They are
* only used in cell types of non-immediates, i. e. the value returned
* by SCM_CELL_TYPE (exp) can use these tags.
*/
scm_ipruk ("immediate", exp, port);
break;
case scm_tc3_int_1:
case scm_tc3_int_2:
scm_intprint (SCM_I_INUM (exp), 10, port);
break;
case scm_tc3_imm24:
if (SCM_CHARP (exp))
{
scm_t_wchar i = SCM_CHAR (exp);
const char *name;
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
if (SCM_WRITINGP (pstate))
{
scm_puts ("#\\", port);
name = scm_i_charname (exp);
if (name != NULL)
scm_puts (name, port);
else if (uc_is_general_category_withtable (i, UC_CATEGORY_MASK_L
| UC_CATEGORY_MASK_M
| UC_CATEGORY_MASK_N
| UC_CATEGORY_MASK_P
| UC_CATEGORY_MASK_S))
/* Print the character if is graphic character. */
{
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_t_wchar *wbuf;
SCM wstr;
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
char *buf;
size_t len;
const char *enc;
enc = scm_i_get_port_encoding (port);
if (uc_combining_class (i) == UC_CCC_NR)
{
wstr = scm_i_make_wide_string (1, &wbuf);
wbuf[0] = i;
}
else
{
/* Character is a combining character: print it connected
to a dotted circle instead of connecting it to the
backslash in '#\' */
wstr = scm_i_make_wide_string (2, &wbuf);
wbuf[0] = SCM_CODEPOINT_DOTTED_CIRCLE;
wbuf[1] = i;
}
if (enc == NULL)
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
{
if (i <= 0xFF)
/* Character is graphic and Latin-1. Print it */
scm_lfwrite_str (wstr, port);
else
/* Character is graphic but unrepresentable in
this port's encoding. */
scm_intprint (i, 8, 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
}
else
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
{
buf = u32_conv_to_encoding (enc,
iconveh_error,
(scm_t_uint32 *) wbuf,
1,
NULL,
NULL, &len);
if (buf != NULL)
{
/* Character is graphic. Print it. */
scm_lfwrite_str (wstr, port);
free (buf);
}
else
/* Character is graphic but unrepresentable in
this port's encoding. */
scm_intprint (i, 8, port);
}
}
else
/* Character is a non-graphical character. */
scm_intprint (i, 8, port);
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
}
else
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_i_charprint (i, port);
}
else if (SCM_IFLAGP (exp)
&& ((size_t) SCM_IFLAGNUM (exp) < (sizeof iflagnames / sizeof (char *))))
{
scm_puts (iflagnames [SCM_IFLAGNUM (exp)], port);
}
else
{
/* unknown immediate value */
scm_ipruk ("immediate", exp, port);
}
break;
case scm_tc3_cons:
switch (SCM_TYP7 (exp))
{
case scm_tcs_struct:
{
ENTER_NESTED_DATA (pstate, exp, circref);
if (SCM_OBJ_CLASS_FLAGS (exp) & SCM_CLASSF_GOOPS)
{
SCM pwps, print = pstate->writingp ? g_write : g_display;
if (!print)
goto print_struct;
pwps = scm_i_port_with_print_state (port, pstate->handle);
pstate->revealed = 1;
scm_call_generic_2 (print, exp, pwps);
}
else
{
print_struct:
scm_print_struct (exp, port, pstate);
}
EXIT_NESTED_DATA (pstate);
}
break;
case scm_tcs_cons_imcar:
case scm_tcs_cons_nimcar:
ENTER_NESTED_DATA (pstate, exp, circref);
scm_iprlist ("(", exp, ')', port, pstate);
EXIT_NESTED_DATA (pstate);
break;
circref:
print_circref (port, pstate, exp);
break;
case scm_tcs_closures:
if (scm_is_false (scm_procedure_p (SCM_PRINT_CLOSURE))
|| scm_is_false (scm_printer_apply (SCM_PRINT_CLOSURE,
exp, port, pstate)))
{
scm_puts ("#<procedure", port);
scm_putc (' ', port);
scm_iprin1 (scm_procedure_name (exp), port, pstate);
scm_putc (' ', port);
new evaluator, y'all * libguile/eval.c: So, ladies & gents, a new evaluator. It's similar to the old one, in that we memoize and then evaluate, but in this incarnation, memoization of an expression happens before evaluation, not lazily as the expression is evaluated. This makes the evaluation itself much cleaner, in addition to being threadsafe. In addition, since this C evaluator will in the future just serve to bootstrap the Scheme evaluator, we don't have to pay much concern for debugging conveniences. So the environment is just a list of values, and the memoizer pre-computes where it's going to find each individual value in the environment. Interface changes are commented below, with eval.h. (scm_evaluator_traps): No need to reset the debug mode after rnning te traps thing. But really, the whole traps system needs some love. * libguile/memoize.h: * libguile/memoize.c: New memoizer, which runs before evaluation, checking all syntax before evaluation begins. Significantly, no debugging information is left for lexical variables, which is not so great for interactive debugging; perhaps we should change this to have a var list in the future as per the classic interpreters. But it's quite fast, and the resulting code is quite good. Also note that it doesn't produce ilocs, memoized code is a smob whose type is in the first word of the smob itself. * libguile/eval.h (scm_sym_and, scm_sym_begin, scm_sym_case) (scm_sym_cond, scm_sym_define, scm_sym_do, scm_sym_if, scm_sym_lambda) (scm_sym_let, scm_sym_letstar, scm_sym_letrec, scm_sym_quote) (scm_sym_quasiquote, scm_sym_unquote, scm_sym_uq_splicing, scm_sym_at) (scm_sym_atat, scm_sym_atapply, scm_sym_atcall_cc) (scm_sym_at_call_with_values, scm_sym_delay, scm_sym_eval_when) (scm_sym_arrow, scm_sym_else, scm_sym_apply, scm_sym_set_x) (scm_sym_args): Remove public declaration of these symbols. (scm_ilookup, scm_lookupcar, scm_eval_car, scm_eval_body) (scm_eval_args, scm_i_eval_x, scm_i_eval): Remove public declaration of these functions. (scm_ceval, scm_deval, scm_ceval_ptr): Remove declarations of these deprecated functions. (scm_i_print_iloc, scm_i_print_isym, scm_i_unmemocopy_expr) (scm_i_unmemocopy_body): Remove declarations of these internal functions. (scm_primitive_eval_x, scm_eval_x): Redefine as macros for their less destructive siblings. * libguile/Makefile.am: Add memoize.[ch] to the build. * libguile/debug.h (scm_debug_mode_p, scm_check_entry_p) (scm_check_apply_p, scm_check_exit_p, scm_check_memoize_p) (scm_debug_eframe_size): Remove these vars that were tied to the old evaluator's execution model. (SCM_RESET_DEBUG_MODE): Remove, no more need for this. (SCM_MEMOIZEDP, SCM_MEMOIZED_EXP, SCM_MEMOIZED_ENV): Remove macros referring to old memoized code representation. (scm_local_eval, scm_procedure_environment, scm_memoized_environment) (scm_make_memoized, scm_memoized_p): Remove functions operating on old memoized code representation. (scm_memcons, scm_mem_to_proc, scm_proc_to_mem): Remove debug-only code for old evaluator. * libguile/debug.c: Remove code to correspond with debug.h removals. (scm_debug_options): No need to set the debug mode or frame limit here, as we don't have C stack limits any more. Perhaps this is a bug, but as long as we can compile eval.scm, we should be fine. * libguile/init.c (scm_i_init_guile): Init memoize.c. * libguile/modules.c (scm_top_level_env, scm_env_top_level) (scm_env_module, scm_system_module_env_p): Remove these functions. * libguile/print.c (iprin1): No more need to handle isyms. Adapt to new form of interpreted procedures. * libguile/procprop.c (scm_i_procedure_arity): Adapt to new form of interpreted procedures. * libguile/procs.c (scm_thunk_p): Adapt to new form of interpreted procedures. * libguile/procs.h (SCM_CLOSURE_FORMALS): Removed, this exists no more. (SCM_CLOSURE_NUM_REQUIRED_ARGS, SCM_CLOSURE_HAS_REST_ARGS): New accessors. * libguile/srcprop.c (scm_source_properties, scm_source_property) (scm_set_source_property_x): Remove special cases for memoized code. * libguile/stacks.c (read_frame): Remove a source-property case for interpreted code. (NEXT_FRAME): Remove a case that I don't fully understand, that seems to be designed to skip over apply frames. Will be obsolete in the futures. (read_frames): Default source value for interpreted frames to #f. (narrow_stack): Don't pay attention to the system_module thing. * libguile/tags.h: Remove isyms and ilocs. Whee! * libguile/validate.h (SCM_VALIDATE_MEMOIZED): Fix to use the new MEMOIZED_P formulation. * module/ice-9/psyntax-pp.scm (do, quasiquote, case): Adapt for these no longer being primitive macros. * module/ice-9/boot-9.scm: Whitespace change, but just a poke to force a rebuild due to and/or/cond/... not being primitives any more. * module/ice-9/deprecated.scm (unmemoize-expr): Deprecate, it's unmemoize-expression now. * test-suite/tests/eval.test ("define set procedure-name"): XFAIL a couple of tests here; I don't know what to do about them. I reckon the expander should ensure that defined values are named. * test-suite/tests/chars.test ("basic char handling"): Fix expected exception when trying to apply a char.
2009-11-28 01:19:50 +01:00
scm_iprin1
(scm_cons (SCM_I_MAKINUM (SCM_CLOSURE_NUM_REQUIRED_ARGS (exp)),
scm_from_bool (SCM_CLOSURE_HAS_REST_ARGS (exp))),
port, pstate);
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_putc ('>', port);
}
break;
case scm_tc7_number:
switch SCM_TYP16 (exp) {
case scm_tc16_big:
scm_bigprint (exp, port, pstate);
break;
case scm_tc16_real:
scm_print_real (exp, port, pstate);
break;
case scm_tc16_complex:
scm_print_complex (exp, port, pstate);
break;
* print.c (scm_iprin1): Handle fractions. * objects.h (scm_class_fraction): New. * objects.c (scm_class_fraction): New. (scm_class_of): Handle fractions. * hash.c (scm_hasher): Handle fractions. * numbers.c: New code for handling fraction all over the place. (scm_odd_p, scm_even_p): Handle inexact integers. (scm_rational_p): New function, same as scm_real_p. (scm_round_number, scm_truncate_number, scm_ceiling, scm_floor): New exact functions that replace the inexact 'dsubr' implementations. (scm_numerator, scm_denominator): New. * numbers.h (SCM_NUMP): Recognize fractions. (SCM_FRACTIONP, SCM_SLOPPY_FRACTIONP, SCM_FRACTION_NUMERATOR, SCM_FRACTION_DENOMINATOR, SCM_FRACTION_SET_NUMERATOR, SCM_FRACTION_SET_DENOMINATOR, SCM_FRACTION_REDUCED_BIT, SCM_FRACTION_REDUCED_SET, SCM_FRACTION_REDUCED_CLEAR, SCM_FRACTION_REDUCED): New. (scm_floor, scm_ceiling, scm_truncate_number, scm_round_number): New prototypes. (scm_make_ratio, scm_rationalize, scm_numerator, scm_denominator, scm_rational_p): New prototypes. (scm_i_dbl2num, scm_i_fraction2double, scm_i_fraction_equalp, scm_i_print_fraction): New prototypes. * goops.c (create_standard_classes): Create "<fraction>" class. * gc-mark.c (scm_gc_mark_dependencies): Handle fractions. * gc-card.c (scm_i_sweep_card): Include scm_tc16_fraction as a case in the switch, but do nothing for now. * eval.c (SCM_CEVAL, SCM_APPLY, call_dsubr_1): Convert fractions to doubles when calling 'dsubr' functions. * eq.c (scm_eqv_p, scm_equal_p): Handle fractions.
2003-11-18 19:59:53 +00:00
case scm_tc16_fraction:
scm_i_print_fraction (exp, port, pstate);
break;
}
break;
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
2009-08-08 02:35:00 -07:00
case scm_tc7_string:
if (SCM_WRITINGP (pstate))
{
size_t i, j, len;
static char const hex[] = "0123456789abcdef";
char buf[8];
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
2009-08-08 02:35:00 -07:00
scm_putc ('"', port);
len = scm_i_string_length (exp);
for (i = 0; i < len; ++i)
{
scm_t_wchar ch = scm_i_string_ref (exp, i);
int printed = 0;
if (ch == ' ' || ch == '\n')
{
scm_putc (ch, port);
printed = 1;
}
else if (ch == '"' || ch == '\\')
{
scm_putc ('\\', port);
scm_i_charprint (ch, port);
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
2009-08-08 02:35:00 -07:00
printed = 1;
}
else
if (uc_is_general_category_withtable
(ch,
UC_CATEGORY_MASK_L | UC_CATEGORY_MASK_M |
UC_CATEGORY_MASK_N | UC_CATEGORY_MASK_P |
UC_CATEGORY_MASK_S))
{
/* Print the character since it is a graphic
character. */
scm_t_wchar *wbuf;
SCM wstr = scm_i_make_wide_string (1, &wbuf);
char *buf;
size_t len;
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
if (scm_i_get_port_encoding (port))
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
2009-08-08 02:35:00 -07:00
{
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
wstr = scm_i_make_wide_string (1, &wbuf);
wbuf[0] = ch;
buf = u32_conv_to_encoding (scm_i_get_port_encoding (port),
iconveh_error,
(scm_t_uint32 *) wbuf,
1 ,
NULL,
NULL, &len);
if (buf != NULL)
{
/* Character is graphic and representable in
this encoding. Print it. */
scm_lfwrite_str (wstr, port);
free (buf);
printed = 1;
}
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
2009-08-08 02:35:00 -07:00
}
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
else
if (ch <= 0xFF)
{
scm_putc (ch, port);
printed = 1;
}
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
2009-08-08 02:35:00 -07:00
}
if (!printed)
{
/* Character is graphic but unrepresentable in
this port's encoding or is not graphic. */
if (ch <= 0xFF)
{
buf[0] = '\\';
buf[1] = 'x';
buf[2] = hex[ch / 16];
buf[3] = hex[ch % 16];
scm_lfwrite (buf, 4, port);
}
else if (ch <= 0xFFFF)
{
buf[0] = '\\';
buf[1] = 'u';
buf[2] = hex[(ch & 0xF000) >> 12];
buf[3] = hex[(ch & 0xF00) >> 8];
buf[4] = hex[(ch & 0xF0) >> 4];
buf[5] = hex[(ch & 0xF)];
scm_lfwrite (buf, 6, port);
j = i + 1;
}
else if (ch > 0xFFFF)
{
buf[0] = '\\';
buf[1] = 'U';
buf[2] = hex[(ch & 0xF00000) >> 20];
buf[3] = hex[(ch & 0xF0000) >> 16];
buf[4] = hex[(ch & 0xF000) >> 12];
buf[5] = hex[(ch & 0xF00) >> 8];
buf[6] = hex[(ch & 0xF0) >> 4];
buf[7] = hex[(ch & 0xF)];
scm_lfwrite (buf, 8, port);
j = i + 1;
}
}
}
scm_putc ('"', port);
scm_remember_upto_here_1 (exp);
}
else
scm_lfwrite_str (exp, port);
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
2009-08-08 02:35:00 -07:00
scm_remember_upto_here_1 (exp);
break;
case scm_tc7_symbol:
if (scm_i_symbol_is_interned (exp))
{
scm_i_print_symbol_name (exp, port);
scm_remember_upto_here_1 (exp);
}
else
{
scm_puts ("#<uninterned-symbol ", port);
scm_i_print_symbol_name (exp, port);
scm_putc (' ', port);
scm_uintprint (SCM_UNPACK (exp), 16, port);
scm_putc ('>', port);
}
break;
case scm_tc7_variable:
scm_i_variable_print (exp, port, pstate);
break;
case scm_tc7_program:
scm_i_program_print (exp, port, pstate);
break;
case scm_tc7_wvect:
ENTER_NESTED_DATA (pstate, exp, circref);
if (SCM_IS_WHVEC (exp))
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts ("#wh(", port);
else
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts ("#w(", port);
goto common_vector_printer;
case scm_tc7_bytevector:
scm_i_print_bytevector (exp, port, pstate);
break;
case scm_tc7_vector:
ENTER_NESTED_DATA (pstate, exp, circref);
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts ("#(", port);
common_vector_printer:
{
register long i;
long last = SCM_SIMPLE_VECTOR_LENGTH (exp) - 1;
int cutp = 0;
if (pstate->fancyp
&& SCM_SIMPLE_VECTOR_LENGTH (exp) > pstate->length)
{
last = pstate->length - 1;
cutp = 1;
}
if (SCM_I_WVECTP (exp))
{
/* Elements of weak vectors may not be accessed via the
`SIMPLE_VECTOR_REF ()' macro. */
for (i = 0; i < last; ++i)
{
scm_iprin1 (scm_c_vector_ref (exp, i),
port, pstate);
scm_putc (' ', port);
}
}
else
{
for (i = 0; i < last; ++i)
{
scm_iprin1 (SCM_SIMPLE_VECTOR_REF (exp, i), port, pstate);
scm_putc (' ', port);
}
}
if (i == last)
{
/* CHECK_INTS; */
scm_iprin1 (scm_c_vector_ref (exp, i), port, pstate);
}
if (cutp)
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts (" ...", port);
scm_putc (')', port);
}
EXIT_NESTED_DATA (pstate);
break;
case scm_tcs_subrs:
{
SCM name = scm_symbol_to_string (SCM_SUBR_NAME (exp));
scm_puts (SCM_SUBR_GENERIC (exp)
? "#<primitive-generic "
: "#<primitive-procedure ",
port);
scm_lfwrite_str (name, port);
scm_putc ('>', port);
break;
}
case scm_tc7_pws:
scm_puts ("#<procedure-with-setter", port);
{
SCM name = scm_procedure_name (exp);
if (scm_is_true (name))
{
scm_putc (' ', port);
scm_display (name, port);
}
}
scm_putc ('>', port);
break;
case scm_tc7_port:
{
register long i = SCM_PTOBNUM (exp);
if (i < scm_numptob
&& scm_ptobs[i].print
&& (scm_ptobs[i].print) (exp, port, pstate))
break;
goto punk;
}
case scm_tc7_smob:
ENTER_NESTED_DATA (pstate, exp, circref);
SCM_SMOB_DESCRIPTOR (exp).print (exp, port, pstate);
EXIT_NESTED_DATA (pstate);
break;
default:
punk:
scm_ipruk ("type", exp, port);
}
}
}
/* Print states are necessary for circular reference safe printing.
* They are also expensive to allocate. Therefore print states are
* kept in a pool so that they can be reused.
*/
/* The PORT argument can also be a print-state/port pair, which will
* then be used instead of allocating a new print state. This is
* useful for continuing a chain of print calls from Scheme. */
void
scm_prin1 (SCM exp, SCM port, int writingp)
{
SCM handle = SCM_BOOL_F; /* Will GC protect the handle whilst unlinked */
SCM pstate_scm;
scm_print_state *pstate;
int old_writingp;
/* If PORT is a print-state/port pair, use that. Else create a new
print-state. */
if (SCM_PORT_WITH_PS_P (port))
{
1999-08-24 02:23:02 +00:00
pstate_scm = SCM_PORT_WITH_PS_PS (port);
port = SCM_PORT_WITH_PS_PORT (port);
}
else
{
/* First try to allocate a print state from the pool */
2005-03-02 20:42:01 +00:00
scm_i_pthread_mutex_lock (&print_state_mutex);
2004-09-22 17:41:37 +00:00
if (!scm_is_null (print_state_pool))
{
handle = print_state_pool;
print_state_pool = SCM_CDR (print_state_pool);
}
2005-03-02 20:42:01 +00:00
scm_i_pthread_mutex_unlock (&print_state_mutex);
if (scm_is_false (handle))
handle = scm_list_1 (make_print_state ());
pstate_scm = SCM_CAR (handle);
}
pstate = SCM_PRINT_STATE (pstate_scm);
old_writingp = pstate->writingp;
pstate->writingp = writingp;
scm_iprin1 (exp, port, pstate);
pstate->writingp = old_writingp;
/* Return print state to pool if it has been created above and
hasn't escaped to Scheme. */
if (scm_is_true (handle) && !pstate->revealed)
{
2005-03-02 20:42:01 +00:00
scm_i_pthread_mutex_lock (&print_state_mutex);
SCM_SETCDR (handle, print_state_pool);
print_state_pool = handle;
2005-03-02 20:42:01 +00:00
scm_i_pthread_mutex_unlock (&print_state_mutex);
}
}
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
2009-08-08 02:35:00 -07:00
/* Print a character.
*/
void
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_i_charprint (scm_t_wchar ch, SCM port)
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
2009-08-08 02:35:00 -07:00
{
scm_t_wchar *wbuf;
SCM wstr = scm_i_make_wide_string (1, &wbuf);
wbuf[0] = ch;
scm_lfwrite_str (wstr, port);
}
/* Print an integer.
*/
void
scm_intprint (scm_t_intmax n, int radix, SCM port)
{
char num_buf[SCM_INTBUFLEN];
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_lfwrite (num_buf, scm_iint2str (n, radix, num_buf), port);
}
void
scm_uintprint (scm_t_uintmax n, int radix, SCM port)
{
char num_buf[SCM_INTBUFLEN];
scm_lfwrite (num_buf, scm_iuint2str (n, radix, num_buf), port);
}
/* Print an object of unrecognized type.
*/
void
scm_ipruk (char *hdr, SCM ptr, SCM port)
{
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts ("#<unknown-", port);
scm_puts (hdr, port);
if (1) /* (scm_in_heap_p (ptr)) */ /* FIXME */
{
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts (" (0x", port);
scm_uintprint (SCM_CELL_WORD_0 (ptr), 16, port);
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts (" . 0x", port);
scm_uintprint (SCM_CELL_WORD_1 (ptr), 16, port);
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts (") @", port);
}
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts (" 0x", port);
scm_uintprint (SCM_UNPACK (ptr), 16, port);
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_putc ('>', port);
}
/* Print a list.
*/
void
scm_iprlist (char *hdr, SCM exp, int tlr, SCM port, scm_print_state *pstate)
{
register SCM hare, tortoise;
long floor = pstate->top - 2;
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts (hdr, port);
/* CHECK_INTS; */
if (pstate->fancyp)
goto fancy_printing;
/* Run a hare and tortoise so that total time complexity will be
O(depth * N) instead of O(N^2). */
hare = SCM_CDR (exp);
tortoise = exp;
2004-09-22 17:41:37 +00:00
while (scm_is_pair (hare))
{
if (scm_is_eq (hare, tortoise))
goto fancy_printing;
hare = SCM_CDR (hare);
2004-09-22 17:41:37 +00:00
if (!scm_is_pair (hare))
break;
hare = SCM_CDR (hare);
tortoise = SCM_CDR (tortoise);
}
/* No cdr cycles intrinsic to this list */
scm_iprin1 (SCM_CAR (exp), port, pstate);
2004-09-22 17:41:37 +00:00
for (exp = SCM_CDR (exp); scm_is_pair (exp); exp = SCM_CDR (exp))
{
register long i;
for (i = floor; i >= 0; --i)
if (scm_is_eq (PSTATE_STACK_REF(pstate, i), exp))
goto circref;
PUSH_REF (pstate, exp);
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_putc (' ', port);
/* CHECK_INTS; */
scm_iprin1 (SCM_CAR (exp), port, pstate);
}
if (!SCM_NULL_OR_NIL_P (exp))
{
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts (" . ", port);
scm_iprin1 (exp, port, pstate);
}
end:
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_putc (tlr, port);
pstate->top = floor + 2;
return;
fancy_printing:
{
long n = pstate->length;
scm_iprin1 (SCM_CAR (exp), port, pstate);
exp = SCM_CDR (exp); --n;
2004-09-22 17:41:37 +00:00
for (; scm_is_pair (exp); exp = SCM_CDR (exp))
{
register unsigned long i;
for (i = 0; i < pstate->top; ++i)
if (scm_is_eq (PSTATE_STACK_REF(pstate, i), exp))
goto fancy_circref;
if (pstate->fancyp)
{
if (n == 0)
{
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts (" ...", port);
goto skip_tail;
}
else
--n;
}
PUSH_REF(pstate, exp);
++pstate->list_offset;
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_putc (' ', port);
/* CHECK_INTS; */
scm_iprin1 (SCM_CAR (exp), port, pstate);
}
}
if (!SCM_NULL_OR_NIL_P (exp))
{
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts (" . ", port);
scm_iprin1 (exp, port, pstate);
}
skip_tail:
pstate->list_offset -= pstate->top - floor - 2;
goto end;
fancy_circref:
pstate->list_offset -= pstate->top - floor - 2;
circref:
* Makefile.in: Rebuilt. * Makefile.am (libguile_la_SOURCES): Removed extchrs.c, mbstrings.c. (modinclude_HEADERS): Removed extchrs.h, mbstrings.h. * unif.c (scm_vector_set_length_x): Don't handle multibyte strings. * tag.c (scm_utag_mb_string, scm_utag_mb_substring): Removed. (scm_tag): Don't handle multibyte strings. * read.c: Don't include mbstrings.h. (scm_lreadr): Don't handle multibyte ports. * kw.c: Don't include mbstrings.h. * init.c: Don't include mbstrings.h. (scm_boot_guile_1): Don't init mbstrings module. * hash.c (scm_hasher): Don't handle mbstrings. * gscm.c (gscm_run_scm): Don't init mbstrings module. * gc.c (scm_gc_mark): Don't handle mbstrings. (scm_gc_sweep): Likewise. * eval.c (SCM_CEVAL): Don't handle mbstrings. * eq.c (scm_equal_p): Use SCM_TYP7S, not SCM_TYP7SD. * tags.h (SCM_TYP7SD): Removed. (SCM_TYP7D): Removed. (scm_tc7_mb_string): Removed. (scm_tc7_mb_substring): Removed. * print.c (scm_iprin1): Handle char printing directly. Don't handle mbstrings. Don't include "mbstrings.h". * symbols.c (scm_intern_obarray_soft, scm_string_to_symbol, scm_string_to_obarray_symbol, msymbolize): Don't set symbol's multi-byte flag. Don't include "mbstrings.h". * symbols.h (SCM_SYMBOL_MULTI_BYTE_STRINGP): Removed. (SCM_SYMBOL_SLOTS): Define as 4. (SCM_ROSTRINGP): Use SCM_TYP7S, not SCM_TYP7SD. * arbiters.c, backtrace.c, debug.c, dynl.c, eval.c, fluids.c, gc.c, gsubr.c, ioext.c, kw.c, mallocs.c, numbers.c, ports.c, print.c, read.c, regex-posix.c, root.c, srcprop.c, stackchk.c, struct.c, threads.c, throw.c, unif.c, variable.c: Use new ("gen"-less) I/O function names. * ports.c (scm_add_to_port_table): Don't set port's representation. * ports.h (scm_port_representation_type): Removed. (scm_string_representation_type): Removed. (struct scm_port_table ): Removed representation field. (SCM_PORT_REPRESENTATION): Removed. (SCM_SET_PORT_REPRESENTATION): Removed. * genio.h: Use new function names. * genio.c: Don't include "extchrs.h". (scm_gen_putc, scm_gen_puts, scm_gen_write, scm_get_getc): Removed. (scm_putc, scm_puts, scm_lfwrite): No longer static. (scm_getc): No longer static; handle line and column changes. (scm_ungetc): Renamed from scm_gen_ungetc. (scm_do_read_line): Renamed from scm_gen_read_line. * libguile.h: Don't include "extchrs.h" or "mbstrings.h" * extchrs.h, extchrs.c, mbstrings.h, mbstrings.c: Removed.
1997-10-15 17:18:32 +00:00
scm_puts (" . ", port);
print_circref (port, pstate, exp);
goto end;
}
int
scm_valid_oport_value_p (SCM val)
{
return (SCM_OPOUTPORTP (val)
|| (SCM_PORT_WITH_PS_P (val)
&& SCM_OPOUTPORTP (SCM_PORT_WITH_PS_PORT (val))));
}
/* SCM_GPROC(s_write, "write", 1, 1, 0, scm_write, g_write); */
SCM
scm_write (SCM obj, SCM port)
{
if (SCM_UNBNDP (port))
2005-03-02 20:42:01 +00:00
port = scm_current_output_port ();
SCM_ASSERT (scm_valid_oport_value_p (port), port, SCM_ARG2, s_write);
scm_prin1 (obj, port, 1);
2007-01-15 23:42:45 +00:00
#if 0
#ifdef HAVE_PIPE
# ifdef EPIPE
if (EPIPE == errno)
scm_close_port (port);
# endif
2007-01-15 23:42:45 +00:00
#endif
#endif
return SCM_UNSPECIFIED;
}
/* SCM_GPROC(s_display, "display", 1, 1, 0, scm_display, g_display); */
SCM
scm_display (SCM obj, SCM port)
{
if (SCM_UNBNDP (port))
2005-03-02 20:42:01 +00:00
port = scm_current_output_port ();
SCM_ASSERT (scm_valid_oport_value_p (port), port, SCM_ARG2, s_display);
scm_prin1 (obj, port, 0);
2007-01-15 23:42:45 +00:00
#if 0
#ifdef HAVE_PIPE
# ifdef EPIPE
if (EPIPE == errno)
scm_close_port (port);
# endif
2007-01-15 23:42:45 +00:00
#endif
#endif
return SCM_UNSPECIFIED;
}
SCM_DEFINE (scm_simple_format, "simple-format", 2, 0, 1,
(SCM destination, SCM message, SCM args),
"Write @var{message} to @var{destination}, defaulting to\n"
"the current output port.\n"
"@var{message} can contain @code{~A} (was @code{%s}) and\n"
"@code{~S} (was @code{%S}) escapes. When printed,\n"
"the escapes are replaced with corresponding members of\n"
"@var{ARGS}:\n"
"@code{~A} formats using @code{display} and @code{~S} formats\n"
"using @code{write}.\n"
"If @var{destination} is @code{#t}, then use the current output\n"
"port, if @var{destination} is @code{#f}, then return a string\n"
"containing the formatted text. Does not add a trailing newline.")
#define FUNC_NAME s_scm_simple_format
{
SCM port, answer = SCM_UNSPECIFIED;
int fReturnString = 0;
int writingp;
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
size_t start, p, end;
if (scm_is_eq (destination, SCM_BOOL_T))
{
2005-03-02 20:42:01 +00:00
destination = port = scm_current_output_port ();
}
else if (scm_is_false (destination))
{
fReturnString = 1;
port = scm_mkstrport (SCM_INUM0,
scm_make_string (SCM_INUM0, SCM_UNDEFINED),
SCM_OPN | SCM_WRTNG,
FUNC_NAME);
destination = port;
}
else
{
SCM_VALIDATE_OPORT_VALUE (1, destination);
port = SCM_COERCE_OUTPORT (destination);
}
SCM_VALIDATE_STRING (2, message);
SCM_VALIDATE_REST_ARGUMENT (args);
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
p = 0;
start = 0;
end = scm_i_string_length (message);
for (p = start; p != end; ++p)
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
if (scm_i_string_ref (message, p) == '~')
{
if (++p == end)
break;
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
switch (scm_i_string_ref (message, p))
{
case 'A': case 'a':
writingp = 0;
break;
case 'S': case 's':
writingp = 1;
break;
case '~':
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_lfwrite_substr (message, start, p, port);
start = p + 1;
continue;
case '%':
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_lfwrite_substr (message, start, p - 1, port);
scm_newline (port);
start = p + 1;
continue;
default:
SCM_MISC_ERROR ("FORMAT: Unsupported format option ~~~A - use (ice-9 format) instead",
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_list_1 (SCM_MAKE_CHAR (scm_i_string_ref (message, p))));
}
2004-09-22 17:41:37 +00:00
if (!scm_is_pair (args))
SCM_MISC_ERROR ("FORMAT: Missing argument for ~~~A",
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_list_1 (SCM_MAKE_CHAR (scm_i_string_ref (message, p))));
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_lfwrite_substr (message, start, p - 1, port);
/* we pass destination here */
scm_prin1 (SCM_CAR (args), destination, writingp);
args = SCM_CDR (args);
start = p + 1;
}
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_lfwrite_substr (message, start, p, port);
if (!scm_is_eq (args, SCM_EOL))
SCM_MISC_ERROR ("FORMAT: ~A superfluous arguments",
scm_list_1 (scm_length (args)));
if (fReturnString)
answer = scm_strport_to_string (destination);
return scm_return_first (answer, message);
}
#undef FUNC_NAME
SCM_DEFINE (scm_newline, "newline", 0, 1, 0,
(SCM port),
"Send a newline to @var{port}.\n"
"If @var{port} is omitted, send to the current output port.")
#define FUNC_NAME s_scm_newline
{
if (SCM_UNBNDP (port))
2005-03-02 20:42:01 +00:00
port = scm_current_output_port ();
SCM_VALIDATE_OPORT_VALUE (1, port);
scm_putc ('\n', SCM_COERCE_OUTPORT (port));
return SCM_UNSPECIFIED;
}
#undef FUNC_NAME
SCM_DEFINE (scm_write_char, "write-char", 1, 1, 0,
(SCM chr, SCM port),
"Send character @var{chr} to @var{port}.")
#define FUNC_NAME s_scm_write_char
{
if (SCM_UNBNDP (port))
2005-03-02 20:42:01 +00:00
port = scm_current_output_port ();
SCM_VALIDATE_CHAR (1, chr);
SCM_VALIDATE_OPORT_VALUE (2, port);
scm_i_charprint (SCM_CHAR (chr), SCM_COERCE_OUTPORT (port));
2007-01-15 23:42:45 +00:00
#if 0
#ifdef HAVE_PIPE
# ifdef EPIPE
if (EPIPE == errno)
scm_close_port (port);
# endif
2007-01-15 23:42:45 +00:00
#endif
#endif
return SCM_UNSPECIFIED;
}
#undef FUNC_NAME
/* Call back to Scheme code to do the printing of special objects
* (like structs). SCM_PRINTER_APPLY applies PROC to EXP and a smob
* containing PORT and PSTATE. This object can be used as the port for
* display/write etc to continue the current print chain. The REVEALED
* field of PSTATE is set to true to indicate that the print state has
* escaped to Scheme and thus has to be freed by the GC.
*/
2001-06-14 19:50:43 +00:00
scm_t_bits scm_tc16_port_with_ps;
/* Print exactly as the port itself would */
static int
2000-12-08 17:32:56 +00:00
port_with_ps_print (SCM obj, SCM port, scm_print_state *pstate)
{
obj = SCM_PORT_WITH_PS_PORT (obj);
return scm_ptobs[SCM_PTOBNUM (obj)].print (obj, port, pstate);
}
SCM
scm_printer_apply (SCM proc, SCM exp, SCM port, scm_print_state *pstate)
{
pstate->revealed = 1;
return scm_call_2 (proc, exp,
scm_i_port_with_print_state (port, pstate->handle));
}
SCM_DEFINE (scm_port_with_print_state, "port-with-print-state", 1, 1, 0,
(SCM port, SCM pstate),
"Create a new port which behaves like @var{port}, but with an\n"
"included print state @var{pstate}. @var{pstate} is optional.\n"
"If @var{pstate} isn't supplied and @var{port} already has\n"
"a print state, the old print state is reused.")
#define FUNC_NAME s_scm_port_with_print_state
{
SCM_VALIDATE_OPORT_VALUE (1, port);
if (!SCM_UNBNDP (pstate))
SCM_VALIDATE_PRINTSTATE (2, pstate);
return scm_i_port_with_print_state (port, pstate);
}
#undef FUNC_NAME
SCM_DEFINE (scm_get_print_state, "get-print-state", 1, 0, 0,
(SCM port),
"Return the print state of the port @var{port}. If @var{port}\n"
"has no associated print state, @code{#f} is returned.")
#define FUNC_NAME s_scm_get_print_state
{
if (SCM_PORT_WITH_PS_P (port))
return SCM_PORT_WITH_PS_PS (port);
if (SCM_OUTPUT_PORT_P (port))
return SCM_BOOL_F;
SCM_WRONG_TYPE_ARG (1, port);
}
#undef FUNC_NAME
void
scm_init_print ()
{
SCM vtable, layout, type;
scm_init_opts (scm_print_options, scm_print_opts);
scm_print_options (scm_list_4 (scm_from_locale_symbol ("highlight-prefix"),
scm_from_locale_string ("{"),
scm_from_locale_symbol ("highlight-suffix"),
scm_from_locale_string ("}")));
scm_gc_register_root (&print_state_pool);
scm_gc_register_root (&scm_print_state_vtable);
vtable = scm_make_vtable_vtable (scm_nullstr, SCM_INUM0, SCM_EOL);
layout =
scm_make_struct_layout (scm_from_locale_string (SCM_PRINT_STATE_LAYOUT));
type = scm_make_struct (vtable, SCM_INUM0, scm_list_1 (layout));
scm_set_struct_vtable_name_x (type, scm_from_locale_symbol ("print-state"));
scm_print_state_vtable = type;
/* Don't want to bind a wrapper class in GOOPS, so pass 0 as arg1. */
scm_tc16_port_with_ps = scm_make_smob_type (0, 0);
2000-12-08 17:32:56 +00:00
scm_set_smob_print (scm_tc16_port_with_ps, port_with_ps_print);
#include "libguile/print.x"
scm_print_opts[SCM_PRINT_KEYWORD_STYLE_I].val = SCM_UNPACK (sym_reader);
}
/*
Local Variables:
c-file-style: "gnu"
End:
*/