DMS-Parser-XS
view release on metacpan or search on metacpan
parse_label|5.013007|5.013007|x
parse_listexpr|5.013008|5.013008|x
parse_lparen_question_flags|5.017009||Viu
PARSE_OPTIONAL|5.013007|5.013007|
parser_dup|5.009000|5.009000|u
parser_free|5.009005||Viu
parser_free_nexttoke_ops|5.017006||Viu
parse_stmtseq|5.013006|5.013006|x
parse_subsignature|5.031003|5.031003|x
parse_termexpr|5.013008|5.013008|x
parse_unicode_opts|5.008001||Viu
parse_uniprop_string|5.027011||Viu
PATCHLEVEL|5.003007||Viu
path_is_searchable|5.019001||Vniu
Pause|5.003007||Viu
pause|5.005000||Viu
pclose|5.003007||Viu
peep|5.003007||Viu
pending_ident|5.017004||Viu
PERL_ABS|5.008001|5.003007|p
Perl_acos|5.021004|5.021004|n
PL_threadhook|5.008000||Viu
PL_tmps_floor|5.005000||Viu
PL_tmps_ix|5.005000||Viu
PL_tmps_max|5.005000||Viu
PL_tmps_stack|5.005000||Viu
PL_tokenbuf||5.003007|ponu
PL_top_env|5.005000||Viu
PL_toptarget|5.005000||Viu
PL_TR_SPECIAL_HANDLING_UTF8|5.031006||Viu
PL_underlying_numeric_obj|5.027009||Viu
PL_unicode|5.008001||Viu
PL_unitcheckav|5.009005||Viu
PL_unitcheckav_save|5.009005||Viu
PL_unlockhook|5.007003||Viu
PL_unsafe|5.005000||Viu
PL_UpperLatin1|5.019005||Viu
PLUS|5.003007||Viu
PLUS_t8|5.035004||Viu
PLUS_t8_p8|5.033003||Viu
PLUS_t8_pb|5.033003||Viu
PLUS_tb|5.035004||Viu
#endif
#ifndef PERL_PV_PRETTY_DUMP
# define PERL_PV_PRETTY_DUMP PERL_PV_PRETTY_ELLIPSES|PERL_PV_PRETTY_QUOTE
#endif
#ifndef PERL_PV_PRETTY_REGPROP
# define PERL_PV_PRETTY_REGPROP PERL_PV_PRETTY_ELLIPSES|PERL_PV_PRETTY_LTGT|PERL_PV_ESCAPE_RE
#endif
/* Hint: pv_escape
* Note that unicode functionality is only backported to
* those perl versions that support it. For older perl
* versions, the implementation will fall back to bytes.
*/
#ifndef pv_escape
#if defined(NEED_pv_escape)
static char * DPPP_(my_pv_escape)(pTHX_ SV * dsv, char const * const str, const STRLEN count, const STRLEN max, STRLEN * const escaped, const U32 flags);
static
#else
extern char * DPPP_(my_pv_escape)(pTHX_ SV * dsv, char const * const str, const STRLEN count, const STRLEN max, STRLEN * const escaped, const U32 flags);
vendor/dms-c/dms.c view on Meta::CPAN
case '\\': buf_push(&b, '\\'); break;
case 'n': buf_push(&b, '\n'); break;
case 't': buf_push(&b, '\t'); break;
case 'r': buf_push(&b, '\r'); break;
case 'b': buf_push(&b, '\b'); break;
case 'f': buf_push(&b, '\f'); break;
case 'u':
case 'U': {
int n = (esc == 'u') ? 4 : 8;
if ((int)(p->len - p->pos) < n) {
set_err(p, "expected %d hex digits in unicode escape", n);
free(b.data); return NULL;
}
cp = 0;
for (int i = 0; i < n; i++) {
char h = p->src[p->pos + i];
int d;
if (h >= '0' && h <= '9') d = h - '0';
else if (h >= 'a' && h <= 'f') d = h - 'a' + 10;
else if (h >= 'A' && h <= 'F') d = h - 'A' + 10;
else { set_err(p, "invalid hex in unicode escape"); free(b.data); return NULL; }
cp = (cp << 4) | d;
}
p->pos += n;
/* SPEC: U+0000 is forbidden anywhere in DMS source, including via
escape decoding. `�` / `\U00000000` must not slip through. */
if (cp == 0) {
set_err(p, "\\u0000 escape forbidden"); free(b.data); return NULL;
}
/* SPEC §basic-string escapes: surrogate codepoints (U+D800..U+DFFF)
are not valid Unicode scalars and are a parse error in `\uXXXX` /
`\UXXXXXXXX` escapes. */
if (cp >= 0xD800 && cp <= 0xDFFF) {
set_err(p, "surrogate codepoint U+%04X in escape", cp); free(b.data); return NULL;
}
if (cp > 0x10FFFF) {
set_err(p, "unicode escape is not a scalar value"); free(b.data); return NULL;
}
outlen = utf8_encode(cp, out);
buf_push_str(&b, out, outlen);
break;
}
default:
set_err(p, "invalid escape '\\%c'", esc);
free(b.data); return NULL;
}
} else {
vendor/dms-c/vendor/utf8proc/LICENSE.md view on Meta::CPAN
DEALINGS IN THE SOFTWARE.
## Unicode data license ##
This software contains data (`utf8proc_data.c`) derived from processing
the Unicode data files. The following license applies to that data:
**COPYRIGHT AND PERMISSION NOTICE**
*Copyright (c) 1991-2007 Unicode, Inc. All rights reserved. Distributed
under the Terms of Use in http://www.unicode.org/copyright.html.*
Permission is hereby granted, free of charge, to any person obtaining a
copy of the Unicode data files and any associated documentation (the "Data
Files") or Unicode software and any associated documentation (the
"Software") to deal in the Data Files or Software without restriction,
including without limitation the rights to use, copy, modify, merge,
publish, distribute, and/or sell copies of the Data Files or Software, and
to permit persons to whom the Data Files or Software are furnished to do
so, provided that (a) the above copyright notice(s) and this permission
notice appear with all copies of the Data Files or Software, (b) both the
vendor/dms-c/vendor/utf8proc/utf8proc.c view on Meta::CPAN
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*/
/*
* This library contains derived data from a modified version of the
* Unicode data files.
*
* The original data files are available at
* https://www.unicode.org/Public/UNIDATA/
*
* Please notice the copyright statement in the file "utf8proc_data.c".
*/
/*
* File name: utf8proc.c
*
* Description:
* Implementation of libutf8proc.
vendor/dms-c/vendor/utf8proc/utf8proc.c view on Meta::CPAN
/* Should follow semantic-versioning rules (semver.org) based on API
compatibility. (Note that the shared-library version number will
be different, being based on ABI compatibility.): */
#define STRINGIZEx(x) #x
#define STRINGIZE(x) STRINGIZEx(x)
UTF8PROC_DLLEXPORT const char *utf8proc_version(void) {
return STRINGIZE(UTF8PROC_VERSION_MAJOR) "." STRINGIZE(UTF8PROC_VERSION_MINOR) "." STRINGIZE(UTF8PROC_VERSION_PATCH) "";
}
UTF8PROC_DLLEXPORT const char *utf8proc_unicode_version(void) {
return "16.0.0";
}
UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode) {
switch (errcode) {
case UTF8PROC_ERROR_NOMEM:
return "Memory for processing UTF-8 data could not be allocated.";
case UTF8PROC_ERROR_OVERFLOW:
return "UTF-8 string is too long to be processed.";
case UTF8PROC_ERROR_INVALIDUTF8:
vendor/dms-c/vendor/utf8proc/utf8proc.c view on Meta::CPAN
}
UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int32_t uc) {
return uc < 0 || uc >= 0x110000 ? utf8proc_properties : unsafe_get_property(uc);
}
/* return whether there is a grapheme break between boundclasses lbc and tbc
(according to the definition of extended grapheme clusters)
Rule numbering refers to TR29 Version 29 (Unicode 9.0.0):
http://www.unicode.org/reports/tr29/tr29-29.html
CAVEATS:
Please note that evaluation of GB10 (grapheme breaks between emoji zwj sequences)
and GB 12/13 (regional indicator code points) require knowledge of previous characters
and are thus not handled by this function. This may result in an incorrect break before
an E_Modifier class codepoint and an incorrectly missing break between two
REGIONAL_INDICATOR class code points if such support does not exist in the caller.
See the special support in grapheme_break_extended, for required bookkeeping by the caller.
*/
vendor/dms-c/vendor/utf8proc/utf8proc.h view on Meta::CPAN
UTF8PROC_NLF2LF = (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS),
/** Strips and/or convers control characters.
*
* NLF-sequences are transformed into space, except if one of the
* NLF2LS/PS/LF options is given. HorizontalTab (HT) and FormFeed (FF)
* are treated as a NLF-sequence in this case. All other control
* characters are simply removed.
*/
UTF8PROC_STRIPCC = (1<<9),
/**
* Performs unicode case folding, to be able to do a case-insensitive
* string comparison.
*/
UTF8PROC_CASEFOLD = (1<<10),
/**
* Inserts 0xFF bytes at the beginning of each sequence which is
* representing a single grapheme cluster (see UAX#29).
*/
UTF8PROC_CHARBOUND = (1<<11),
/** Lumps certain characters together.
*
vendor/dms-c/vendor/utf8proc/utf8proc.h view on Meta::CPAN
/**
* Returns the utf8proc API version as a string MAJOR.MINOR.PATCH
* (http://semver.org format), possibly with a "-dev" suffix for
* development versions.
*/
UTF8PROC_DLLEXPORT const char *utf8proc_version(void);
/**
* Returns the utf8proc supported Unicode version as a string MAJOR.MINOR.PATCH.
*/
UTF8PROC_DLLEXPORT const char *utf8proc_unicode_version(void);
/**
* Returns an informative error string for the given utf8proc error code
* (e.g. the error codes returned by utf8proc_map()).
*/
UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode);
/**
* Reads a single codepoint from the UTF-8 sequence being pointed to by `str`.
* The maximum number of bytes read is `strlen`, unless `strlen` is
vendor/dms-c/vendor/utf8proc/utf8proc.h view on Meta::CPAN
utf8proc_int32_t codepoint, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize,
utf8proc_option_t options, int *last_boundclass
);
/**
* The same as utf8proc_decompose_char(), but acts on a whole UTF-8
* string and orders the decomposed sequences correctly.
*
* If the @ref UTF8PROC_NULLTERM flag in `options` is set, processing
* will be stopped, when a NULL byte is encountered, otherwise `strlen`
* bytes are processed. The result (in the form of 32-bit unicode
* codepoints) is written into the buffer being pointed to by
* `buffer` (which must contain at least `bufsize` entries). In case of
* success, the number of codepoints written is returned; in case of an
* error, a negative error code is returned (utf8proc_errmsg()).
* See utf8proc_decompose_custom() to supply additional transformations.
*
* If the number of written codepoints would be bigger than `bufsize`, the
* required buffer size is returned, while the buffer will be overwritten with
* undefined data.
*/
vendor/dms-c/vendor/utf8proc/utf8proc.h view on Meta::CPAN
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_custom(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options,
utf8proc_custom_func custom_func, void *custom_data
);
/**
* Normalizes the sequence of `length` codepoints pointed to by `buffer`
* in-place (i.e., the result is also stored in `buffer`).
*
* @param buffer the (native-endian UTF-32) unicode codepoints to re-encode.
* @param length the length (in codepoints) of the buffer.
* @param options a bitwise or (`|`) of one or more of the following flags:
* - @ref UTF8PROC_NLF2LS - convert LF, CRLF, CR and NEL into LS
* - @ref UTF8PROC_NLF2PS - convert LF, CRLF, CR and NEL into PS
* - @ref UTF8PROC_NLF2LF - convert LF, CRLF, CR and NEL into LF
* - @ref UTF8PROC_STRIPCC - strip or convert all non-affected control characters
* - @ref UTF8PROC_COMPOSE - try to combine decomposed codepoints into composite
* codepoints
* - @ref UTF8PROC_STABLE - prohibit combining characters that would violate
* the unicode versioning stability
*
* @return
* In case of success, the length (in codepoints) of the normalized UTF-32 string is
* returned; otherwise, a negative error code is returned (utf8proc_errmsg()).
*
* @warning The entries of the array pointed to by `str` have to be in the
* range `0x0000` to `0x10FFFF`. Otherwise, the program might crash!
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_normalize_utf32(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options);
/**
* Reencodes the sequence of `length` codepoints pointed to by `buffer`
* UTF-8 data in-place (i.e., the result is also stored in `buffer`).
* Can optionally normalize the UTF-32 sequence prior to UTF-8 conversion.
*
* @param buffer the (native-endian UTF-32) unicode codepoints to re-encode.
* @param length the length (in codepoints) of the buffer.
* @param options a bitwise or (`|`) of one or more of the following flags:
* - @ref UTF8PROC_NLF2LS - convert LF, CRLF, CR and NEL into LS
* - @ref UTF8PROC_NLF2PS - convert LF, CRLF, CR and NEL into PS
* - @ref UTF8PROC_NLF2LF - convert LF, CRLF, CR and NEL into LF
* - @ref UTF8PROC_STRIPCC - strip or convert all non-affected control characters
* - @ref UTF8PROC_COMPOSE - try to combine decomposed codepoints into composite
* codepoints
* - @ref UTF8PROC_STABLE - prohibit combining characters that would violate
* the unicode versioning stability
* - @ref UTF8PROC_CHARBOUND - insert 0xFF bytes before each grapheme cluster
*
* @return
* In case of success, the length (in bytes) of the resulting nul-terminated
* UTF-8 string is returned; otherwise, a negative error code is returned
* (utf8proc_errmsg()).
*
* @warning The amount of free space pointed to by `buffer` must
* exceed the amount of the input data by one byte, and the
* entries of the array pointed to by `str` have to be in the
( run in 1.131 second using v1.01-cache-2.11-cpan-c966e8aa7e8 )