Skip to content

Commit a9ad65a

Browse files
khwilliamsonkhwilliamson
committed
utf8.h: White space only: Change tabs to blanks
1 parent 7d25166 commit a9ad65a

File tree

1 file changed

+42
-42
lines changed

1 file changed

+42
-42
lines changed

‎utf8.h

+42-42
Original file line numberDiff line numberDiff line change
@@ -215,7 +215,7 @@ typedef enum {
215215
* following header file: */
216216
# include "utfebcdic.h"
217217

218-
# else /* ! EBCDIC */
218+
# else /* ! EBCDIC */
219219

220220
START_EXTERN_C
221221

@@ -235,11 +235,11 @@ EXTCONST unsigned char PL_utf8skip[] = {
235235
/* 0x90 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus: continuation byte */
236236
/* 0xA0 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus: continuation byte */
237237
/* 0xB0 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus: continuation byte */
238-
/* 0xC0 */ 2,2, /* overlong */
238+
/* 0xC0 */ 2,2, /* overlong */
239239
/* 0xC2 */ 2,2,2,2,2,2,2,2,2,2,2,2,2,2, /* U+0080 to U+03FF */
240240
/* 0xD0 */ 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, /* U+0400 to U+07FF */
241241
/* 0xE0 */ 3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3, /* U+0800 to U+FFFF */
242-
/* 0xF0 */ 4,4,4,4,4,4,4,4,5,5,5,5,6,6, /* above BMP to 2**31 - 1 */
242+
/* 0xF0 */ 4,4,4,4,4,4,4,4,5,5,5,5,6,6, /* above BMP to 2**31 - 1 */
243243
/* Perl extended (never was official UTF-8). Up to 36 bit */
244244
/* 0xFE */ 7,
245245
/* More extended, Up to 72 bits (64-bit + reserved) */
@@ -314,21 +314,21 @@ adding no time nor space requirements to the implementation.
314314
The following table is from Unicode 3.2, plus the Perl extensions for above
315315
U+10FFFF
316316
317-
Code Points 1st Byte 2nd Byte 3rd 4th 5th 6th 7th 8th-13th
317+
Code Points 1st Byte 2nd Byte 3rd 4th 5th 6th 7th 8th-13th
318318
319-
U+0000..U+007F 00..7F
319+
U+0000..U+007F 00..7F
320320
U+0080..U+07FF * C2..DF 80..BF
321-
U+0800..U+0FFF E0 * A0..BF 80..BF
321+
U+0800..U+0FFF E0 * A0..BF 80..BF
322322
U+1000..U+CFFF E1..EC 80..BF 80..BF
323323
U+D000..U+D7FF ED 80..9F 80..BF
324324
U+D800..U+DFFF ED A0..BF 80..BF (surrogates)
325325
U+E000..U+FFFF EE..EF 80..BF 80..BF
326-
U+10000..U+3FFFF F0 * 90..BF 80..BF 80..BF
327-
U+40000..U+FFFFF F1..F3 80..BF 80..BF 80..BF
328-
U+100000..U+10FFFF F4 80..8F 80..BF 80..BF
326+
U+10000..U+3FFFF F0 * 90..BF 80..BF 80..BF
327+
U+40000..U+FFFFF F1..F3 80..BF 80..BF 80..BF
328+
U+100000..U+10FFFF F4 80..8F 80..BF 80..BF
329329
Below are above-Unicode code points
330-
U+110000..U+13FFFF F4 90..BF 80..BF 80..BF
331-
U+110000..U+1FFFFF F5..F7 80..BF 80..BF 80..BF
330+
U+110000..U+13FFFF F4 90..BF 80..BF 80..BF
331+
U+110000..U+1FFFFF F5..F7 80..BF 80..BF 80..BF
332332
U+200000..U+FFFFFF F8 * 88..BF 80..BF 80..BF 80..BF
333333
U+1000000..U+3FFFFFF F9..FB 80..BF 80..BF 80..BF 80..BF
334334
U+4000000..U+3FFFFFFF FC * 84..BF 80..BF 80..BF 80..BF 80..BF
@@ -670,7 +670,7 @@ encoded as UTF-8. C<cp> is a native (ASCII or EBCDIC) code point if less than
670670
/* Is the UTF8-encoded byte 'c' the first byte of a two byte sequence? Use
671671
* UTF8_IS_NEXT_CHAR_DOWNGRADEABLE() instead if the input isn't known to
672672
* be well-formed. */
673-
#define UTF8_IS_DOWNGRADEABLE_START(c) (__ASSERT_(FITS_IN_8_BITS(c)) \
673+
#define UTF8_IS_DOWNGRADEABLE_START(c) (__ASSERT_(FITS_IN_8_BITS(c)) \
674674
inRANGE_helper_(U8, NATIVE_UTF8_TO_I8(c), \
675675
UTF_MIN_START_BYTE, UTF_MIN_ABOVE_LATIN1_BYTE - 1))
676676

@@ -711,7 +711,7 @@ uppercase/lowercase/titlecase/fold into.
711711
*
712712
=cut
713713
*/
714-
#define UTF8_MAXBYTES_CASE \
714+
#define UTF8_MAXBYTES_CASE \
715715
MAX(UTF8_MAXBYTES, UTF8_MAX_FOLD_CHAR_EXPAND * UNISKIP_BY_MSB_(20))
716716

717717
/* Rest of these are attributes of Unicode and perl's internals rather than the
@@ -859,11 +859,11 @@ that it returns TRUE in each for the exact same set of bit patterns. It is
859859
valid on a subset of what UVCHR_IS_INVARIANT is valid on, so can just use that;
860860
and the compiler should optimize out anything extraneous given the
861861
implementation of the latter. */
862-
#define UTF8_IS_INVARIANT(c) UVCHR_IS_INVARIANT(ASSERT_NOT_PTR(c))
862+
#define UTF8_IS_INVARIANT(c) UVCHR_IS_INVARIANT(ASSERT_NOT_PTR(c))
863863

864864
/* Like the above, but its name implies a non-UTF8 input, which as the comments
865865
* above show, doesn't matter as to its implementation */
866-
#define NATIVE_BYTE_IS_INVARIANT(c) UVCHR_IS_INVARIANT(c)
866+
#define NATIVE_BYTE_IS_INVARIANT(c) UVCHR_IS_INVARIANT(c)
867867

868868
/* Misleadingly named: is the UTF8-encoded byte 'c' part of a variant sequence
869869
* in UTF-8? This is the inverse of UTF8_IS_INVARIANT. */
@@ -967,8 +967,8 @@ case any call to string overloading updates the internal UTF-8 encoding flag.
967967
&& is_in_locale_category_(FALSE, -1))) \
968968
&& (! IN_BYTES))
969969

970-
#define UNICODE_SURROGATE_FIRST 0xD800
971-
#define UNICODE_SURROGATE_LAST 0xDFFF
970+
#define UNICODE_SURROGATE_FIRST 0xD800
971+
#define UNICODE_SURROGATE_LAST 0xDFFF
972972

973973
/*
974974
=for apidoc Am|bool|UNICODE_IS_SURROGATE|const UV uv
@@ -1012,7 +1012,7 @@ representation.
10121012
10131013
=cut
10141014
*/
1015-
#define UNICODE_REPLACEMENT 0xFFFD
1015+
#define UNICODE_REPLACEMENT 0xFFFD
10161016
#define UNICODE_IS_REPLACEMENT(uv) UNLIKELY((UV) (uv) == UNICODE_REPLACEMENT)
10171017
#define UTF8_IS_REPLACEMENT(s, send) \
10181018
UNLIKELY( \
@@ -1021,7 +1021,7 @@ representation.
10211021
sizeof(REPLACEMENT_CHARACTER_UTF8) - 1))
10221022

10231023
/* Max legal code point according to Unicode */
1024-
#define PERL_UNICODE_MAX 0x10FFFF
1024+
#define PERL_UNICODE_MAX 0x10FFFF
10251025

10261026
/*
10271027
@@ -1057,10 +1057,10 @@ this macro matches
10571057
10581058
=cut
10591059
1060-
* ASCII EBCDIC I8
1061-
* U+10FFFF: \xF4\x8F\xBF\xBF \xF9\xA1\xBF\xBF\xBF max legal Unicode
1062-
* U+110000: \xF4\x90\x80\x80 \xF9\xA2\xA0\xA0\xA0
1063-
* U+110001: \xF4\x90\x80\x81 \xF9\xA2\xA0\xA0\xA1
1060+
* ASCII EBCDIC I8
1061+
* U+10FFFF: \xF4\x8F\xBF\xBF \xF9\xA1\xBF\xBF\xBF max legal Unicode
1062+
* U+110000: \xF4\x90\x80\x80 \xF9\xA2\xA0\xA0\xA0
1063+
* U+110001: \xF4\x90\x80\x81 \xF9\xA2\xA0\xA0\xA1
10641064
*/
10651065
#define UTF_START_BYTE_110000_ UTF_START_BYTE(PERL_UNICODE_MAX + 1, 21)
10661066
#define UTF_FIRST_CONT_BYTE_110000_ \
@@ -1255,10 +1255,10 @@ point's representation.
12551255
#define UTF8_ALLOW_ANYUV 0
12561256
#define UTF8_ALLOW_DEFAULT UTF8_ALLOW_ANYUV
12571257

1258-
#define UNICODE_WARN_SURROGATE 0x0001 /* UTF-16 surrogates */
1259-
#define UNICODE_WARN_NONCHAR 0x0002 /* Non-char code points */
1260-
#define UNICODE_WARN_SUPER 0x0004 /* Above 0x10FFFF */
1261-
#define UNICODE_WARN_PERL_EXTENDED 0x0008 /* Above 0x7FFF_FFFF */
1258+
#define UNICODE_WARN_SURROGATE 0x0001 /* UTF-16 surrogates */
1259+
#define UNICODE_WARN_NONCHAR 0x0002 /* Non-char code points */
1260+
#define UNICODE_WARN_SUPER 0x0004 /* Above 0x10FFFF */
1261+
#define UNICODE_WARN_PERL_EXTENDED 0x0008 /* Above 0x7FFF_FFFF */
12621262
#define UNICODE_WARN_ABOVE_31_BIT UNICODE_WARN_PERL_EXTENDED
12631263
#define UNICODE_DISALLOW_SURROGATE 0x0010
12641264
#define UNICODE_DISALLOW_NONCHAR 0x0020
@@ -1286,11 +1286,11 @@ point's representation.
12861286

12871287
/* For backward source compatibility, as are now the default */
12881288
#define UNICODE_ALLOW_SURROGATE 0
1289-
#define UNICODE_ALLOW_SUPER 0
1290-
#define UNICODE_ALLOW_ANY 0
1289+
#define UNICODE_ALLOW_SUPER 0
1290+
#define UNICODE_ALLOW_ANY 0
12911291

1292-
#define UNICODE_BYTE_ORDER_MARK 0xFEFF
1293-
#define UNICODE_IS_BYTE_ORDER_MARK(uv) UNLIKELY((UV) (uv) \
1292+
#define UNICODE_BYTE_ORDER_MARK 0xFEFF
1293+
#define UNICODE_IS_BYTE_ORDER_MARK(uv) UNLIKELY((UV) (uv) \
12941294
== UNICODE_BYTE_ORDER_MARK)
12951295

12961296
#define LATIN_SMALL_LETTER_SHARP_S LATIN_SMALL_LETTER_SHARP_S_NATIVE
@@ -1301,15 +1301,15 @@ point's representation.
13011301
LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE_NATIVE
13021302
#define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE \
13031303
LATIN_SMALL_LETTER_A_WITH_RING_ABOVE_NATIVE
1304-
#define UNICODE_GREEK_CAPITAL_LETTER_SIGMA 0x03A3
1305-
#define UNICODE_GREEK_SMALL_LETTER_FINAL_SIGMA 0x03C2
1306-
#define UNICODE_GREEK_SMALL_LETTER_SIGMA 0x03C3
1304+
#define UNICODE_GREEK_CAPITAL_LETTER_SIGMA 0x03A3
1305+
#define UNICODE_GREEK_SMALL_LETTER_FINAL_SIGMA 0x03C2
1306+
#define UNICODE_GREEK_SMALL_LETTER_SIGMA 0x03C3
13071307
#define GREEK_SMALL_LETTER_MU 0x03BC
1308-
#define GREEK_CAPITAL_LETTER_MU 0x039C /* Upper and title case
1308+
#define GREEK_CAPITAL_LETTER_MU 0x039C /* Upper and title case
13091309
of MICRON */
1310-
#define LATIN_CAPITAL_LETTER_Y_WITH_DIAERESIS 0x0178 /* Also is title case */
1310+
#define LATIN_CAPITAL_LETTER_Y_WITH_DIAERESIS 0x0178 /* Also is title case */
13111311
#ifdef LATIN_CAPITAL_LETTER_SHARP_S_UTF8
1312-
# define LATIN_CAPITAL_LETTER_SHARP_S 0x1E9E
1312+
# define LATIN_CAPITAL_LETTER_SHARP_S 0x1E9E
13131313
#endif
13141314
#define LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE 0x130
13151315
#define LATIN_SMALL_LETTER_DOTLESS_I 0x131
@@ -1319,16 +1319,16 @@ point's representation.
13191319
#define KELVIN_SIGN 0x212A
13201320
#define ANGSTROM_SIGN 0x212B
13211321

1322-
#define UNI_DISPLAY_ISPRINT 0x0001
1323-
#define UNI_DISPLAY_BACKSLASH 0x0002
1324-
#define UNI_DISPLAY_BACKSPACE 0x0004 /* Allow \b when also
1322+
#define UNI_DISPLAY_ISPRINT 0x0001
1323+
#define UNI_DISPLAY_BACKSLASH 0x0002
1324+
#define UNI_DISPLAY_BACKSPACE 0x0004 /* Allow \b when also
13251325
UNI_DISPLAY_BACKSLASH */
1326-
#define UNI_DISPLAY_QQ (UNI_DISPLAY_ISPRINT \
1326+
#define UNI_DISPLAY_QQ (UNI_DISPLAY_ISPRINT \
13271327
|UNI_DISPLAY_BACKSLASH \
13281328
|UNI_DISPLAY_BACKSPACE)
13291329

13301330
/* Character classes could also allow \b, but not patterns in general */
1331-
#define UNI_DISPLAY_REGEX (UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH)
1331+
#define UNI_DISPLAY_REGEX (UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH)
13321332

13331333
/* Should be removed; maybe deprecated, but not used in CPAN */
13341334
#define SHARP_S_SKIP 2

0 commit comments

Comments
 (0)