diff options
| author | Karl Williamson <khw@cpan.org> | 2017-02-13 19:57:53 -0700 |
|---|---|---|
| committer | Karl Williamson <khw@cpan.org> | 2017-02-13 21:24:11 -0700 |
| commit | 7e2f38b21adec3a814f436b1c0c7e79796f5dcc5 (patch) | |
| tree | 1be361bd816726c0528205f5b28d96c633b08f2a /utf8.c | |
| parent | 6b58f9be8c82394d776908727ff4e9d582f87f12 (diff) | |
| download | perl-7e2f38b21adec3a814f436b1c0c7e79796f5dcc5.tar.gz | |
Make _byte_dump_string() usable in all of core
I found myself needing this function for development debugging, which
formerly was only usable from utf8.c. This enhances it to allow a
second format type, and makes it core-accessible.
Diffstat (limited to 'utf8.c')
| -rw-r--r-- | utf8.c | 41 |
1 files changed, 25 insertions, 16 deletions
@@ -754,11 +754,15 @@ Perl__is_utf8_char_helper(const U8 * const s, const U8 * e, const U32 flags) return UTF8SKIP(s); } -STATIC char * -S__byte_dump_string(pTHX_ const U8 * s, const STRLEN len) +char * +Perl__byte_dump_string(pTHX_ const U8 * s, const STRLEN len, const bool format) { /* Returns a mortalized C string that is a displayable copy of the 'len' - * bytes starting at 's', each in a \xXY format. */ + * bytes starting at 's'. 'format' gives how to display each byte. + * Currently, there are only two formats, so it is currently a bool: + * 0 \xab + * 1 ab (that is a space between two hex digit bytes) + */ const STRLEN output_len = 4 * len + 1; /* 4 bytes per each input, plus a trailing NUL */ @@ -776,8 +780,13 @@ S__byte_dump_string(pTHX_ const U8 * s, const STRLEN len) const unsigned high_nibble = (*s & 0xF0) >> 4; const unsigned low_nibble = (*s & 0x0F); - *d++ = '\\'; - *d++ = 'x'; + if (format) { + *d++ = ' '; + } + else { + *d++ = '\\'; + *d++ = 'x'; + } if (high_nibble < 10) { *d++ = high_nibble + '0'; @@ -827,7 +836,7 @@ S_unexpected_non_continuation_text(pTHX_ const U8 * const s, return Perl_form(aTHX_ "%s: %s (unexpected non-continuation byte 0x%02x," " %s after start byte 0x%02x; need %d bytes, got %d)", malformed_text, - _byte_dump_string(s, print_len), + _byte_dump_string(s, print_len, 0), *(s + non_cont_byte_pos), where, *s, @@ -1401,7 +1410,7 @@ Perl_utf8n_to_uvchr_error(pTHX_ const U8 *s, if (pack_warn) { message = Perl_form(aTHX_ "%s: %s (overflows)", malformed_text, - _byte_dump_string(s0, send - s0)); + _byte_dump_string(s0, send - s0, 0)); } } } @@ -1437,7 +1446,7 @@ Perl_utf8n_to_uvchr_error(pTHX_ const U8 *s, "%s: %s (unexpected continuation byte 0x%02x," " with no preceding start byte)", malformed_text, - _byte_dump_string(s0, 1), *s0); + _byte_dump_string(s0, 1, 0), *s0); } } } @@ -1452,7 +1461,7 @@ Perl_utf8n_to_uvchr_error(pTHX_ const U8 *s, message = Perl_form(aTHX_ "%s: %s (too short; %d byte%s available, need %d)", malformed_text, - _byte_dump_string(s0, send - s0), + _byte_dump_string(s0, send - s0, 0), (int)avail_len, avail_len == 1 ? "" : "s", (int)expectlen); @@ -1516,8 +1525,8 @@ Perl_utf8n_to_uvchr_error(pTHX_ const U8 *s, " should be represented with a" " different, shorter sequence)", malformed_text, - _byte_dump_string(s0, send - s0), - _byte_dump_string(s0, curlen)); + _byte_dump_string(s0, send - s0, 0), + _byte_dump_string(s0, curlen, 0)); } else { U8 tmpbuf[UTF8_MAXBYTES+1]; @@ -1527,8 +1536,8 @@ Perl_utf8n_to_uvchr_error(pTHX_ const U8 *s, "%s: %s (overlong; instead use %s to represent" " U+%0*" UVXf ")", malformed_text, - _byte_dump_string(s0, send - s0), - _byte_dump_string(tmpbuf, e - tmpbuf), + _byte_dump_string(s0, send - s0, 0), + _byte_dump_string(tmpbuf, e - tmpbuf, 0), ((uv < 256) ? 2 : 4), /* Field width of 2 for small code points */ uv); @@ -1553,7 +1562,7 @@ Perl_utf8n_to_uvchr_error(pTHX_ const U8 *s, message = Perl_form(aTHX_ "UTF-16 surrogate (any UTF-8 sequence that" " starts with \"%s\" is for a surrogate)", - _byte_dump_string(s0, curlen)); + _byte_dump_string(s0, curlen, 0)); } else { message = Perl_form(aTHX_ @@ -1583,7 +1592,7 @@ Perl_utf8n_to_uvchr_error(pTHX_ const U8 *s, "Any UTF-8 sequence that starts with" " \"%s\" is for a non-Unicode code point," " may not be portable", - _byte_dump_string(s0, curlen)); + _byte_dump_string(s0, curlen, 0)); } else { message = Perl_form(aTHX_ @@ -1622,7 +1631,7 @@ Perl_utf8n_to_uvchr_error(pTHX_ const U8 *s, "Any UTF-8 sequence that starts with" " \"%s\" is for a non-Unicode code" " point, and is not portable", - _byte_dump_string(s0, curlen)); + _byte_dump_string(s0, curlen, 0)); } else { message = Perl_form(aTHX_ |