APPROVE COMMIT NOTE: This patch has been committed # HG changeset patch # User Aidan Kehoe <kehoea(a)parhasard.net&gt; # Date 1507158497 -3600 # Thu Oct 05 00:08:17 2017 +0100 # Node ID 19876e056bb7630f1854719c8b037a1f2fb691e8 # Parent 8df05e6e201fbbd618c7127c762bf954028ceec3 Be more realistic, #'char-to-unicode, #'make-char 2017-10-04 Aidan Kehoe <kehoea(a)parhasard.net&gt; * text.c (old_mule_ichar_to_unicode): Assert we haven't been handed an Ichar less than 256 in value. * text.c (unicode_internal_handle_bad_ichar_to_unicode): New. Handle a value passed to the inline ichar_to_unicode(), if CHR is not an official Unicode character and FAIL is not CONVERR_USE_PRIVATE. * text.c (Fmake_char): Make this API compatible with GNU and with pre-unicode-internal, return a private character by default if HANDLE-ERROR is nil. * text.c (Fchar_to_unicode): Return nil if HANDLE-ERROR is FAIL or nil here. * text.c (Funicode_to_char): * text.c (Fchar_to_charset_codepoint): * text.c (Fchar_charset): * text.c (Fsplit_char): Update the docstrings in this three functions. * text.h (ichar_to_unicode): Make the implementation of this a bit more realistic with UNICODE_INTERNAL, use the new unicode_internal_handle_bad_ichar_to_unicode(). diff -r 8df05e6e201f -r 19876e056bb7 src/ChangeLog --- a/src/ChangeLog Sat Sep 30 16:16:08 2017 +0100 +++ b/src/ChangeLog Thu Oct 05 00:08:17 2017 +0100 ＠＠ -1,3 +1,26 ＠＠ +2017-10-04 Aidan Kehoe <kehoea(a)parhasard.net&gt; + + * text.c (old_mule_ichar_to_unicode): + Assert we haven't been handed an Ichar less than 256 in value. + * text.c (unicode_internal_handle_bad_ichar_to_unicode): New. + Handle a value passed to the inline ichar_to_unicode(), if CHR is + not an official Unicode character and FAIL is not + CONVERR_USE_PRIVATE. + * text.c (Fmake_char): + Make this API compatible with GNU and with pre-unicode-internal, + return a private character by default if HANDLE-ERROR is nil. + * text.c (Fchar_to_unicode): + Return nil if HANDLE-ERROR is FAIL or nil here. + * text.c (Funicode_to_char): + * text.c (Fchar_to_charset_codepoint): + * text.c (Fchar_charset): + * text.c (Fsplit_char): + Update the docstrings in this three functions. + * text.h (ichar_to_unicode): + Make the implementation of this a bit more realistic with + UNICODE_INTERNAL, use the new + unicode_internal_handle_bad_ichar_to_unicode(). + 2017-09-30 Aidan Kehoe <kehoea(a)parhasard.net&gt; * text.c (old_mule_non_ascii_valid_ichar_p): diff -r 8df05e6e201f -r 19876e056bb7 src/text.c --- a/src/text.c Sat Sep 30 16:16:08 2017 +0100 +++ b/src/text.c Thu Oct 05 00:08:17 2017 +0100 ＠＠ -1703,11 +1703,7 ＠＠ old_mule_ichar_to_unicode (Ichar chr, enum converr fail) { ASSERT_VALID_ICHAR (chr); - - /* This shortcut depends on the representation of an Ichar, see text.c. */ - if (chr < 256) - return (int) chr; - + text_checking_assert (chr < 256); { int c1, c2; Lisp_Object charset; ＠＠ -1862,6 +1858,39 ＠＠ #endif /* not UNICODE_INTERNAL */ +int +unicode_internal_handle_bad_ichar_to_unicode (Ichar chr, enum converr fail) +{ + ASSERT_VALID_ICHAR (chr); + text_checking_assert (fail != CONVERR_USE_PRIVATE); + text_checking_assert (!valid_unicode_codepoint_p (chr, + UNICODE_OFFICIAL_ONLY)); + switch (fail) + { + case CONVERR_FAIL: + return -1; + case CONVERR_ERROR: + if (chr > UNICODE_OFFICIAL_MAX) + { + args_out_of_range_3 (make_fixnum (chr), Qzero, + make_fixnum (UNICODE_OFFICIAL_MAX)); + } + if (chr >= FIRST_UTF_16_SURROGATE) + { + args_out_of_range_3 (make_fixnum (chr), Qzero, + make_fixnum (FIRST_UTF_16_SURROGATE)); + } + /* FALLTHROUGH */ + case CONVERR_ABORT: + case CONVERR_USE_PRIVATE: + default: + ABORT (); + case CONVERR_SUCCEED: + case CONVERR_SUBSTITUTE: + return 0xFFFD; + } +} + #endif /* MULE */ /* Take a possibly invalid Ichar value (must be >= 0) and move upwards as ＠＠ -5422,11 +5451,11 ＠＠ to translate. Currently, this happens only with Unicode-internal (see below): -nil or `fail' Return nil -`abort' Signal an error -`succeed' Same as `substitute' -`substitute' Substitute the Unicode replacement char (0xFFFD) -`use-private' Encode using private Unicode space +`use-private' or `nil' Encode using private Unicode space +`fail' Return nil +`error' Signal an error +`succeed' Same as `substitute' +`substitute' Substitute the Unicode replacement char (0xFFFD) Each octet should be in the range corresponding to the offset and size for that dimension, as defined in the charset. For a typical one-dimensional ＠＠ -5602,10 +5631,16 ＠＠ */ (charset, octet1, octet2, handle_error)) { - enum converr fail = decode_handle_error (handle_error, 1); + enum converr fail; int a1, a2; Ichar ch; + if (NILP (handle_error)) + { + handle_error = Quse_private; + } + + fail = decode_handle_error (handle_error, 1); charset = get_external_charset_codepoint (charset, octet1, octet2, &a1, &a2, 1); ch = charset_codepoint_to_ichar (charset, a1, a2, fail); ＠＠ -5622,7 +5657,7 ＠＠ HANDLE-ERROR controls error behavior: nil or `fail' Return nil -`abort' Signal an error +`error' Signal an error `succeed' Same as `substitute' `substitute' Substitute the Unicode replacement char (0xFFFD) `use-private' Encode using private Unicode space ＠＠ -5630,9 +5665,18 ＠＠ (character, handle_error)) { enum converr fail = decode_handle_error (handle_error, 1); + INT_32_BIT result; CHECK_CHAR_COERCE_INT (character); - return make_fixnum (ichar_to_unicode (XCHAR (character), fail)); + + result = ichar_to_unicode (XCHAR (character), fail); + + if (result < 0) + { + return Qnil; + } + + return make_fixnum (result); } DEFUN ("unicode-to-char", Funicode_to_char, 1, 3, 0, /* ＠＠ -5684,7 +5728,7 ＠＠ HANDLE-ERROR controls error behavior: nil or `fail' Return nil -`abort' Signal an error +`error' Signal an error `succeed' Same as `substitute' `substitute' Substitute a '?' character */ ＠＠ -5727,7 +5771,7 ＠＠ HANDLE-ERROR controls error behavior: nil or `fail' Return nil -`abort' Signal an error +`error' Signal an error `succeed' Same as `substitute' `substitute' Substitute a '?' character */ ＠＠ -5761,7 +5805,7 ＠＠ HANDLE-ERROR controls error behavior: nil or `fail' Return nil -`abort' Signal an error +`error' Signal an error `succeed' Same as `substitute' `substitute' Substitute the Unicode replacement char (0xFFFD) `use-private' Encode using private Unicode space ＠＠ -5799,7 +5843,7 ＠＠ HANDLE-ERROR controls error behavior: nil or `fail' Return nil -`abort' Signal an error +`error' Signal an error `succeed' Same as `substitute' `substitute' Substitute a '?' character */ ＠＠ -5849,7 +5893,7 ＠＠ HANDLE-ERROR controls error behavior: nil or `fail' Return nil -`abort' Signal an error +`error' Signal an error `succeed' Same as `substitute' `substitute' Substitute a '?' character */ ＠＠ -5928,7 +5972,7 ＠＠ HANDLE-ERROR controls error behavior: nil or `fail' Return nil -`abort' Signal an error +`error' Signal an error `succeed' Same as `substitute' `substitute' Substitute a '?' character */ diff -r 8df05e6e201f -r 19876e056bb7 src/text.h --- a/src/text.h Sat Sep 30 16:16:08 2017 +0100 +++ b/src/text.h Thu Oct 05 00:08:17 2017 +0100 ＠＠ -522,15 +522,17 ＠＠ #define LAST_TRAILING_BYTE 0xFF #endif -#ifndef UNICODE_INTERNAL -MODULE_API int old_mule_non_ascii_valid_ichar_p (Ichar ch); +#ifdef UNICODE_INTERNAL +MODULE_API INT_32_BIT unicode_internal_handle_bad_ichar_to_unicode (Ichar, + enum + converr); +#elif defined (MULE) +MODULE_API INT_32_BIT old_mule_non_ascii_valid_ichar_p (Ichar ch); #endif -/* Return whether the given Ichar is valid. - */ - +/* Return whether the given Ichar is valid. */ DECLARE_INLINE_HEADER ( -int +Boolint valid_ichar_p (Ichar ch) ) { ＠＠ -826,12 +828,30 ＠＠ Return value will be -1 if cannot convert. */ DECLARE_INLINE_HEADER ( int -ichar_to_unicode (Ichar chr, enum converr USED_IF_OLD_MULE (fail)) +ichar_to_unicode (Ichar chr, enum converr USED_IF_MULE (fail)) ) { ASSERT_VALID_ICHAR (chr); -#if defined (MULE) && !defined (UNICODE_INTERNAL) + /* This shortcut depends on the representation of an Ichar, see text.c. */ + if (chr < 256) + { + return (int) chr; + } + +#ifdef UNICODE_INTERNAL + if (fail == CONVERR_USE_PRIVATE) + { + return (int) chr; + } + + if (valid_unicode_codepoint_p (chr, UNICODE_OFFICIAL_ONLY)) + { + return (int) chr; + } + + return unicode_internal_handle_bad_ichar_to_unicode (chr, fail); +#elif defined (MULE) return old_mule_ichar_to_unicode (chr, fail); #else /* Unicode-internal or non-Mule */ -- ‘As I sat looking up at the Guinness ad, I could never figure out / How your man stayed up on the surfboard after forty pints of stout’ (C. Moore)