DMS-XS-Parser
view release on metacpan or search on metacpan
vendor/dms-c/vendor/utf8proc/utf8proc.h view on Meta::CPAN
# define UTF8PROC_DLLEXPORT
#else
# ifdef _WIN32
# ifdef UTF8PROC_EXPORTS
# define UTF8PROC_DLLEXPORT __declspec(dllexport)
# else
# define UTF8PROC_DLLEXPORT __declspec(dllimport)
# endif
# elif __GNUC__ >= 4
# define UTF8PROC_DLLEXPORT __attribute__ ((visibility("default")))
# else
# define UTF8PROC_DLLEXPORT
# endif
#endif
#ifdef __cplusplus
extern "C" {
#endif
/**
* Option flags used by several functions in the library.
*/
typedef enum {
/** The given UTF-8 input is NULL terminated. */
UTF8PROC_NULLTERM = (1<<0),
/** Unicode Versioning Stability has to be respected. */
UTF8PROC_STABLE = (1<<1),
/** Compatibility decomposition (i.e. formatting information is lost). */
UTF8PROC_COMPAT = (1<<2),
/** Return a result with decomposed characters. */
UTF8PROC_COMPOSE = (1<<3),
/** Return a result with decomposed characters. */
UTF8PROC_DECOMPOSE = (1<<4),
/** Strip "default ignorable characters" such as SOFT-HYPHEN or ZERO-WIDTH-SPACE. */
UTF8PROC_IGNORE = (1<<5),
/** Return an error, if the input contains unassigned codepoints. */
UTF8PROC_REJECTNA = (1<<6),
/**
* Indicating that NLF-sequences (LF, CRLF, CR, NEL) are representing a
* line break, and should be converted to the codepoint for line
* separation (LS).
*/
UTF8PROC_NLF2LS = (1<<7),
/**
* Indicating that NLF-sequences are representing a paragraph break, and
* should be converted to the codepoint for paragraph separation
* (PS).
*/
UTF8PROC_NLF2PS = (1<<8),
/** Indicating that the meaning of NLF-sequences is unknown. */
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.
*
* E.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-". See lump.md for details.
*
* If NLF2LF is set, this includes a transformation of paragraph and
* line separators to ASCII line-feed (LF).
*/
UTF8PROC_LUMP = (1<<12),
/** Strips all character markings.
*
* This includes non-spacing, spacing and enclosing (i.e. accents).
* @note This option works only with @ref UTF8PROC_COMPOSE or
* @ref UTF8PROC_DECOMPOSE
*/
UTF8PROC_STRIPMARK = (1<<13),
/**
* Strip unassigned codepoints.
*/
UTF8PROC_STRIPNA = (1<<14),
} utf8proc_option_t;
/** @name Error codes
* Error codes being returned by almost all functions.
*/
/** @{ */
/** Memory could not be allocated. */
#define UTF8PROC_ERROR_NOMEM -1
/** The given string is too long to be processed. */
#define UTF8PROC_ERROR_OVERFLOW -2
/** The given string is not a legal UTF-8 string. */
#define UTF8PROC_ERROR_INVALIDUTF8 -3
/** The @ref UTF8PROC_REJECTNA flag was set and an unassigned codepoint was found. */
#define UTF8PROC_ERROR_NOTASSIGNED -4
/** Invalid options have been used. */
#define UTF8PROC_ERROR_INVALIDOPTS -5
/** @} */
/* @name Types */
/** Holds the value of a property. */
typedef utf8proc_int16_t utf8proc_propval_t;
/** Struct containing information about a codepoint. */
typedef struct utf8proc_property_struct {
/**
* Unicode category.
* @see utf8proc_category_t.
*/
utf8proc_propval_t category;
utf8proc_propval_t combining_class;
/**
* Bidirectional class.
vendor/dms-c/vendor/utf8proc/utf8proc.h view on Meta::CPAN
UTF8PROC_BOUNDCLASS_START = 0, /**< Start */
UTF8PROC_BOUNDCLASS_OTHER = 1, /**< Other */
UTF8PROC_BOUNDCLASS_CR = 2, /**< Cr */
UTF8PROC_BOUNDCLASS_LF = 3, /**< Lf */
UTF8PROC_BOUNDCLASS_CONTROL = 4, /**< Control */
UTF8PROC_BOUNDCLASS_EXTEND = 5, /**< Extend */
UTF8PROC_BOUNDCLASS_L = 6, /**< L */
UTF8PROC_BOUNDCLASS_V = 7, /**< V */
UTF8PROC_BOUNDCLASS_T = 8, /**< T */
UTF8PROC_BOUNDCLASS_LV = 9, /**< Lv */
UTF8PROC_BOUNDCLASS_LVT = 10, /**< Lvt */
UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR = 11, /**< Regional indicator */
UTF8PROC_BOUNDCLASS_SPACINGMARK = 12, /**< Spacingmark */
UTF8PROC_BOUNDCLASS_PREPEND = 13, /**< Prepend */
UTF8PROC_BOUNDCLASS_ZWJ = 14, /**< Zero Width Joiner */
/* the following are no longer used in Unicode 11, but we keep
the constants here for backward compatibility */
UTF8PROC_BOUNDCLASS_E_BASE = 15, /**< Emoji Base */
UTF8PROC_BOUNDCLASS_E_MODIFIER = 16, /**< Emoji Modifier */
UTF8PROC_BOUNDCLASS_GLUE_AFTER_ZWJ = 17, /**< Glue_After_ZWJ */
UTF8PROC_BOUNDCLASS_E_BASE_GAZ = 18, /**< E_BASE + GLUE_AFTER_ZJW */
/* the Extended_Pictographic property is used in the Unicode 11
grapheme-boundary rules, so we store it in the boundclass field */
UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC = 19,
UTF8PROC_BOUNDCLASS_E_ZWG = 20, /* UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC + ZWJ */
} utf8proc_boundclass_t;
/** Indic_Conjunct_Break property. (TR44) */
typedef enum {
UTF8PROC_INDIC_CONJUNCT_BREAK_NONE = 0,
UTF8PROC_INDIC_CONJUNCT_BREAK_LINKER = 1,
UTF8PROC_INDIC_CONJUNCT_BREAK_CONSONANT = 2,
UTF8PROC_INDIC_CONJUNCT_BREAK_EXTEND = 3,
} utf8proc_indic_conjunct_break_t;
/**
* Function pointer type passed to utf8proc_map_custom() and
* utf8proc_decompose_custom(), which is used to specify a user-defined
* mapping of codepoints to be applied in conjunction with other mappings.
*/
typedef utf8proc_int32_t (*utf8proc_custom_func)(utf8proc_int32_t codepoint, void *data);
/**
* Array containing the byte lengths of a UTF-8 encoded codepoint based
* on the first byte.
*/
UTF8PROC_DLLEXPORT extern const utf8proc_int8_t utf8proc_utf8class[256];
/**
* 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
* negative (in which case up to 4 bytes are read).
*
* If a valid codepoint could be read, it is stored in the variable
* pointed to by `codepoint_ref`, otherwise that variable will be set to -1.
* In case of success, the number of bytes read is returned; otherwise, a
* negative error code is returned.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_int32_t *codepoint_ref);
/**
* Check if a codepoint is valid (regardless of whether it has been
* assigned a value by the current Unicode standard).
*
* @return 1 if the given `codepoint` is valid and otherwise return 0.
*/
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t codepoint);
/**
* Encodes the codepoint as an UTF-8 string in the byte array pointed
* to by `dst`. This array must be at least 4 bytes long.
*
* In case of success the number of bytes written is returned, and
* otherwise 0 is returned.
*
* This function does not check whether `codepoint` is valid Unicode.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t codepoint, utf8proc_uint8_t *dst);
/**
* Look up the properties for a given codepoint.
*
* @param codepoint The Unicode codepoint.
*
* @returns
* A pointer to a (constant) struct containing information about
* the codepoint.
* @par
* If the codepoint is unassigned or invalid, a pointer to a special struct is
* returned in which `category` is 0 (@ref UTF8PROC_CATEGORY_CN).
*/
UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int32_t codepoint);
/** Decompose a codepoint into an array of codepoints.
*
* @param codepoint the codepoint.
* @param dst the destination buffer.
* @param bufsize the size of the destination buffer.
* @param options one or more of the following flags:
* - @ref UTF8PROC_REJECTNA - return an error `codepoint` is unassigned
* - @ref UTF8PROC_IGNORE - strip "default ignorable" codepoints
* - @ref UTF8PROC_CASEFOLD - apply Unicode casefolding
* - @ref UTF8PROC_COMPAT - replace certain codepoints with their
* compatibility decomposition
* - @ref UTF8PROC_CHARBOUND - insert 0xFF bytes before each grapheme cluster
* - @ref UTF8PROC_LUMP - lump certain different codepoints together
* - @ref UTF8PROC_STRIPMARK - remove all character marks
* - @ref UTF8PROC_STRIPNA - remove unassigned codepoints
* @param last_boundclass
* Pointer to an integer variable containing
* the previous codepoint's (boundclass + indic_conjunct_break << 1) if the @ref UTF8PROC_CHARBOUND
* option is used. If the string is being processed in order, this can be initialized to 0 for
* the beginning of the string, and is thereafter updated automatically. Otherwise, this parameter is ignored.
*
* @return
* In case of success, the number of codepoints written is returned; in case
* of an error, a negative error code is returned (utf8proc_errmsg()).
* @par
* 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.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(
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.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options
);
/**
* The same as utf8proc_decompose(), but also takes a `custom_func` mapping function
* that is called on each codepoint in `str` before any other transformations
* (along with a `custom_data` pointer that is passed through to `custom_func`).
* The `custom_func` argument is ignored if it is `NULL`. See also utf8proc_map_custom().
*/
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
* range `0x0000` to `0x10FFFF`. Otherwise, the program might crash!
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options);
/**
* Given a pair of consecutive codepoints, return whether a grapheme break is
* permitted between them (as defined by the extended grapheme clusters in UAX#29).
*
* @param codepoint1 The first codepoint.
* @param codepoint2 The second codepoint, occurring consecutively after `codepoint1`.
* @param state Beginning with Version 29 (Unicode 9.0.0), this algorithm requires
* state to break graphemes. This state can be passed in as a pointer
* in the `state` argument and should initially be set to 0. If the
* state is not passed in (i.e. a null pointer is passed), UAX#29 rules
* GB10/12/13 which require this state will not be applied, essentially
* matching the rules in Unicode 8.0.0.
*
* @warning If the state parameter is used, `utf8proc_grapheme_break_stateful` must
* be called IN ORDER on ALL potential breaks in a string. However, it
* is safe to reset the state to zero after a grapheme break.
*/
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break_stateful(
utf8proc_int32_t codepoint1, utf8proc_int32_t codepoint2, utf8proc_int32_t *state);
/**
* Same as utf8proc_grapheme_break_stateful(), except without support for the
* Unicode 9 additions to the algorithm. Supported for legacy reasons.
*/
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(
utf8proc_int32_t codepoint1, utf8proc_int32_t codepoint2);
/**
* Given a codepoint `c`, return the codepoint of the corresponding
* lower-case character, if any; otherwise (if there is no lower-case
* variant, or if `c` is not a valid codepoint) return `c`.
*/
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_tolower(utf8proc_int32_t c);
/**
* Given a codepoint `c`, return the codepoint of the corresponding
* upper-case character, if any; otherwise (if there is no upper-case
* variant, or if `c` is not a valid codepoint) return `c`.
*/
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c);
/**
* Given a codepoint `c`, return the codepoint of the corresponding
* title-case character, if any; otherwise (if there is no title-case
* variant, or if `c` is not a valid codepoint) return `c`.
( run in 0.807 second using v1.01-cache-2.11-cpan-9581c071862 )