mirror of
https://git.savannah.gnu.org/git/guile.git
synced 2025-06-19 02:00:26 +02:00
889975e51a
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
105 lines
2.7 KiB
Scheme
105 lines
2.7 KiB
Scheme
;;;; strings.test --- test suite for Guile's string functions -*- mode: scheme; coding: utf-8 -*-
|
|
;;;;
|
|
;;;; Copyright (C) 2009 Free Software Foundation, Inc.
|
|
;;;;
|
|
;;;; This program is free software; you can redistribute it and/or modify
|
|
;;;; it under the terms of the GNU General Public License as published by
|
|
;;;; the Free Software Foundation; either version 2, or (at your option)
|
|
;;;; any later version.
|
|
;;;;
|
|
;;;; This program 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 General Public License for more details.
|
|
;;;;
|
|
;;;; You should have received a copy of the GNU General Public License
|
|
;;;; along with this software; see the file COPYING. If not, write to
|
|
;;;; the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
|
|
;;;; Boston, MA 02110-1301 USA
|
|
|
|
(define-module (test-strings)
|
|
#:use-module (test-suite lib)
|
|
#:use-module (srfi srfi-1))
|
|
|
|
(define exception:conversion
|
|
(cons 'misc-error "^cannot convert to output locale"))
|
|
|
|
;; Create a string from integer char values, eg. (string-ints 65) => "A"
|
|
(define (string-ints . args)
|
|
(apply string (map integer->char args)))
|
|
|
|
(setlocale LC_ALL "")
|
|
|
|
(define s1 "última")
|
|
(define s2 "cédula")
|
|
(define s3 "años")
|
|
(define s4 "羅生門")
|
|
|
|
(with-test-prefix "string length"
|
|
|
|
(pass-if "última"
|
|
(eq? (string-length s1) 6))
|
|
|
|
(pass-if "cédula"
|
|
(eq? (string-length s2) 6))
|
|
|
|
(pass-if "años"
|
|
(eq? (string-length s3) 4))
|
|
|
|
(pass-if "羅生門"
|
|
(eq? (string-length s4) 3)))
|
|
|
|
(with-test-prefix "internal encoding"
|
|
|
|
(pass-if "última"
|
|
(string=? s1 (string-ints #xfa #x6c #x74 #x69 #x6d #x61)))
|
|
|
|
(pass-if "cédula"
|
|
(string=? s2 (string-ints #x63 #xe9 #x64 #x75 #x6c #x61)))
|
|
|
|
(pass-if "años"
|
|
(string=? s3 (string-ints #x61 #xf1 #x6f #x73)))
|
|
|
|
(pass-if "羅生門"
|
|
(string=? s4 (string-ints #x7f85 #x751f #x9580))))
|
|
|
|
(with-test-prefix "chars"
|
|
|
|
(pass-if "última"
|
|
(list= eqv? (string->list s1)
|
|
(list #\ú #\l #\t #\i #\m #\a)))
|
|
|
|
(pass-if "cédula"
|
|
(list= eqv? (string->list s2)
|
|
(list #\c #\é #\d #\u #\l #\a)))
|
|
|
|
(pass-if "años"
|
|
(list= eqv? (string->list s3)
|
|
(list #\a #\ñ #\o #\s)))
|
|
|
|
(pass-if "羅生門"
|
|
(list= eqv? (string->list s4)
|
|
(list #\羅 #\生 #\門))))
|
|
|
|
(with-test-prefix "symbols == strings"
|
|
|
|
(pass-if "última"
|
|
(eq? (string->symbol s1) 'última))
|
|
|
|
(pass-if "cédula"
|
|
(eq? (string->symbol s2) 'cédula))
|
|
|
|
(pass-if "años"
|
|
(eq? (string->symbol s3) 'años))
|
|
|
|
(pass-if "羅生門"
|
|
(eq? (string->symbol s4) '羅生門)))
|
|
|
|
(with-test-prefix "non-ascii variable names"
|
|
|
|
(pass-if "1"
|
|
(let ((芥川龍之介 1)
|
|
(ñ 2))
|
|
(eq? (+ 芥川龍之介 ñ) 3))))
|
|
|
|
|