Timerix/utf8proc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

rename DLLEXPORT to UTF8PROC_DLLEXPORT to prevent conflicts with other header files that define DLLEXPORT

Browse Source
This commit is contained in:
Steven G. Johnson 2015-03-30 11:05:51 -04:00
parent 0528e9cda6
commit a1c429a45b
2 changed files with 42 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
utf8proc.c
View File

@ -44,7 +44,7 @@
#include "utf8proc_data.c" #include "utf8proc_data.c"
DLLEXPORT const int8_t utf8proc_utf8class[256] = { UTF8PROC_DLLEXPORT const int8_t utf8proc_utf8class[256] = {
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
@ -87,11 +87,11 @@ DLLEXPORT const int8_t utf8proc_utf8class[256] = {
be different, being based on ABI compatibility.): */ be different, being based on ABI compatibility.): */
#define STRINGIZEx(x) #x #define STRINGIZEx(x) #x
#define STRINGIZE(x) STRINGIZEx(x) #define STRINGIZE(x) STRINGIZEx(x)
DLLEXPORT const char *utf8proc_version(void) { UTF8PROC_DLLEXPORT const char *utf8proc_version(void) {
return STRINGIZE(UTF8PROC_VERSION_MAJOR) "." STRINGIZE(UTF8PROC_VERSION_MINOR) "." STRINGIZE(UTF8PROC_VERSION_PATCH) ""; return STRINGIZE(UTF8PROC_VERSION_MAJOR) "." STRINGIZE(UTF8PROC_VERSION_MINOR) "." STRINGIZE(UTF8PROC_VERSION_PATCH) "";
} }
DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode) { UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode) {
switch (errcode) { switch (errcode) {
case UTF8PROC_ERROR_NOMEM: case UTF8PROC_ERROR_NOMEM:
return "Memory for processing UTF-8 data could not be allocated."; return "Memory for processing UTF-8 data could not be allocated.";
@ -108,7 +108,7 @@ DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode) {
} }
} }
DLLEXPORT ssize_t utf8proc_iterate( UTF8PROC_DLLEXPORT ssize_t utf8proc_iterate(
const uint8_t *str, ssize_t strlen, int32_t *dst const uint8_t *str, ssize_t strlen, int32_t *dst
) { ) {
int length; int length;
@ -148,14 +148,14 @@ DLLEXPORT ssize_t utf8proc_iterate(
return length; return length;
} }
DLLEXPORT bool utf8proc_codepoint_valid(int32_t uc) { UTF8PROC_DLLEXPORT bool utf8proc_codepoint_valid(int32_t uc) {
if (uc < 0 || uc >= 0x110000 || if (uc < 0 || uc >= 0x110000 ||
((uc & 0xFFFF) >= 0xFFFE) || (uc >= 0xD800 && uc < 0xE000) || ((uc & 0xFFFF) >= 0xFFFE) || (uc >= 0xD800 && uc < 0xE000) ||
(uc >= 0xFDD0 && uc < 0xFDF0)) return false; (uc >= 0xFDD0 && uc < 0xFDF0)) return false;
else return true; else return true;
} }
DLLEXPORT ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst) { UTF8PROC_DLLEXPORT ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst) {
if (uc < 0x00) { if (uc < 0x00) {
return 0; return 0;
} else if (uc < 0x80) { } else if (uc < 0x80) {
@ -195,7 +195,7 @@ static const utf8proc_property_t *get_property(int32_t uc) {
); );
} }
DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t uc) { UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t uc) {
return uc < 0 || uc >= 0x110000 ? utf8proc_properties : get_property(uc); return uc < 0 || uc >= 0x110000 ? utf8proc_properties : get_property(uc);
} }
@ -226,22 +226,22 @@ static bool grapheme_break(int lbc, int tbc) {
} }
/* return whether there is a grapheme break between codepoints c1 and c2 */ /* return whether there is a grapheme break between codepoints c1 and c2 */
DLLEXPORT bool utf8proc_grapheme_break(int32_t c1, int32_t c2) { UTF8PROC_DLLEXPORT bool utf8proc_grapheme_break(int32_t c1, int32_t c2) {
return grapheme_break(utf8proc_get_property(c1)->boundclass, return grapheme_break(utf8proc_get_property(c1)->boundclass,
utf8proc_get_property(c2)->boundclass); utf8proc_get_property(c2)->boundclass);
} }
/* return a character width analogous to wcwidth (except portable and /* return a character width analogous to wcwidth (except portable and
hopefully less buggy than most system wcwidth functions). */ hopefully less buggy than most system wcwidth functions). */
DLLEXPORT int utf8proc_charwidth(int32_t c) { UTF8PROC_DLLEXPORT int utf8proc_charwidth(int32_t c) {
return utf8proc_get_property(c)->charwidth; return utf8proc_get_property(c)->charwidth;
} }
DLLEXPORT utf8proc_category_t utf8proc_category(int32_t c) { UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(int32_t c) {
return utf8proc_get_property(c)->category; return utf8proc_get_property(c)->category;
} }
DLLEXPORT const char *utf8proc_category_string(int32_t c) { UTF8PROC_DLLEXPORT const char *utf8proc_category_string(int32_t c) {
static const char s[][3] = {"Cn","Lu","Ll","Lt","Lm","Lo","Mn","Mc","Me","Nd","Nl","No","Pc","Pd","Ps","Pe","Pi","Pf","Po","Sm","Sc","Sk","So","Zs","Zl","Zp","Cc","Cf","Cs","Co"}; static const char s[][3] = {"Cn","Lu","Ll","Lt","Lm","Lo","Mn","Mc","Me","Nd","Nl","No","Pc","Pd","Ps","Pe","Pi","Pf","Po","Sm","Sc","Sk","So","Zs","Zl","Zp","Cc","Cf","Cs","Co"};
return s[utf8proc_category(c)]; return s[utf8proc_category(c)];
} }
@ -250,7 +250,7 @@ DLLEXPORT const char *utf8proc_category_string(int32_t c) {
return utf8proc_decompose_char((replacement_uc), dst, bufsize, \ return utf8proc_decompose_char((replacement_uc), dst, bufsize, \
options & ~UTF8PROC_LUMP, last_boundclass) options & ~UTF8PROC_LUMP, last_boundclass)
DLLEXPORT ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) { UTF8PROC_DLLEXPORT ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) {
const utf8proc_property_t *property; const utf8proc_property_t *property;
utf8proc_propval_t category; utf8proc_propval_t category;
int32_t hangul_sindex; int32_t hangul_sindex;
@ -354,7 +354,7 @@ DLLEXPORT ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufs
return 1; return 1;
} }
DLLEXPORT ssize_t utf8proc_decompose( UTF8PROC_DLLEXPORT ssize_t utf8proc_decompose(
const uint8_t *str, ssize_t strlen, const uint8_t *str, ssize_t strlen,
int32_t *buffer, ssize_t bufsize, utf8proc_option_t options int32_t *buffer, ssize_t bufsize, utf8proc_option_t options
) { ) {
@ -416,7 +416,7 @@ DLLEXPORT ssize_t utf8proc_decompose(
return wpos; return wpos;
} }
DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, utf8proc_option_t options) { UTF8PROC_DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, utf8proc_option_t options) {
/* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored /* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored
ASSERT: 'buffer' has one spare byte of free space at the end! */ ASSERT: 'buffer' has one spare byte of free space at the end! */
if (options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC)) { if (options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC)) {
@ -531,7 +531,7 @@ DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, utf8proc_op
} }
} }
DLLEXPORT ssize_t utf8proc_map( UTF8PROC_DLLEXPORT ssize_t utf8proc_map(
const uint8_t *str, ssize_t strlen, uint8_t **dstptr, utf8proc_option_t options const uint8_t *str, ssize_t strlen, uint8_t **dstptr, utf8proc_option_t options
) { ) {
int32_t *buffer; int32_t *buffer;
@ -560,28 +560,28 @@ DLLEXPORT ssize_t utf8proc_map(
return result; return result;
} }
DLLEXPORT uint8_t *utf8proc_NFD(const uint8_t *str) { UTF8PROC_DLLEXPORT uint8_t *utf8proc_NFD(const uint8_t *str) {
uint8_t *retval; uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_DECOMPOSE); UTF8PROC_DECOMPOSE);
return retval; return retval;
} }
DLLEXPORT uint8_t *utf8proc_NFC(const uint8_t *str) { UTF8PROC_DLLEXPORT uint8_t *utf8proc_NFC(const uint8_t *str) {
uint8_t *retval; uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_COMPOSE); UTF8PROC_COMPOSE);
return retval; return retval;
} }
DLLEXPORT uint8_t *utf8proc_NFKD(const uint8_t *str) { UTF8PROC_DLLEXPORT uint8_t *utf8proc_NFKD(const uint8_t *str) {
uint8_t *retval; uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT); UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT);
return retval; return retval;
} }
DLLEXPORT uint8_t *utf8proc_NFKC(const uint8_t *str) { UTF8PROC_DLLEXPORT uint8_t *utf8proc_NFKC(const uint8_t *str) {
uint8_t *retval; uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_COMPOSE | UTF8PROC_COMPAT); UTF8PROC_COMPOSE | UTF8PROC_COMPAT);

46
utf8proc.h
View File

@ -99,14 +99,14 @@ enum {false, true};
#ifdef _WIN32 #ifdef _WIN32
# ifdef UTF8PROC_EXPORTS # ifdef UTF8PROC_EXPORTS
# define DLLEXPORT __declspec(dllexport) # define UTF8PROC_DLLEXPORT __declspec(dllexport)
# else # else
# define DLLEXPORT __declspec(dllimport) # define UTF8PROC_DLLEXPORT __declspec(dllimport)
# endif # endif
#elif __GNUC__ >= 4 #elif __GNUC__ >= 4
# define DLLEXPORT __attribute__ ((visibility("default"))) # define UTF8PROC_DLLEXPORT __attribute__ ((visibility("default")))
#else #else
# define DLLEXPORT # define UTF8PROC_DLLEXPORT
#endif #endif
#ifdef __cplusplus #ifdef __cplusplus
@ -351,20 +351,20 @@ typedef enum {
* Array containing the byte lengths of a UTF-8 encoded codepoint based * Array containing the byte lengths of a UTF-8 encoded codepoint based
* on the first byte. * on the first byte.
*/ */
DLLEXPORT extern const int8_t utf8proc_utf8class[256]; UTF8PROC_DLLEXPORT extern const int8_t utf8proc_utf8class[256];
/** /**
* Returns the utf8proc API version as a string MAJOR.MINOR.PATCH * Returns the utf8proc API version as a string MAJOR.MINOR.PATCH
* (http://semver.org format), possibly with a "-dev" suffix for * (http://semver.org format), possibly with a "-dev" suffix for
* development versions. * development versions.
*/ */
DLLEXPORT const char *utf8proc_version(void); UTF8PROC_DLLEXPORT const char *utf8proc_version(void);
/** /**
* Returns an informative error string for the given utf8proc error code * Returns an informative error string for the given utf8proc error code
* (e.g. the error codes returned by @ref utf8proc_map). * (e.g. the error codes returned by @ref utf8proc_map).
*/ */
DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode); UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode);
/** /**
* Reads a single codepoint from the UTF-8 sequence being pointed to by `str`. * Reads a single codepoint from the UTF-8 sequence being pointed to by `str`.
@ -376,7 +376,7 @@ DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode);
* In case of success, the number of bytes read is returned; otherwise, a * In case of success, the number of bytes read is returned; otherwise, a
* negative error code is returned. * negative error code is returned.
*/ */
DLLEXPORT ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *codepoint_ref); UTF8PROC_DLLEXPORT ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *codepoint_ref);
/** /**
* Check if a codepoint is valid (regardless of whether it has been * Check if a codepoint is valid (regardless of whether it has been
@ -384,7 +384,7 @@ DLLEXPORT ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *
* *
* @return 1 if the given `codepoint` is valid and otherwise return 0. * @return 1 if the given `codepoint` is valid and otherwise return 0.
*/ */
DLLEXPORT bool utf8proc_codepoint_valid(int32_t codepoint); UTF8PROC_DLLEXPORT bool utf8proc_codepoint_valid(int32_t codepoint);
/** /**
* Encodes the codepoint as an UTF-8 string in the byte array pointed * Encodes the codepoint as an UTF-8 string in the byte array pointed
@ -395,7 +395,7 @@ DLLEXPORT bool utf8proc_codepoint_valid(int32_t codepoint);
* *
* This function does not check whether `codepoint` is valid Unicode. * This function does not check whether `codepoint` is valid Unicode.
*/ */
DLLEXPORT ssize_t utf8proc_encode_char(int32_t codepoint, uint8_t *dst); UTF8PROC_DLLEXPORT ssize_t utf8proc_encode_char(int32_t codepoint, uint8_t *dst);
/** /**
* Look up the properties for a given codepoint. * Look up the properties for a given codepoint.
@ -409,7 +409,7 @@ DLLEXPORT ssize_t utf8proc_encode_char(int32_t codepoint, uint8_t *dst);
* If the codepoint is unassigned or invalid, a pointer to a special struct is * If the codepoint is unassigned or invalid, a pointer to a special struct is
* returned in which `category` is 0 (@ref UTF8PROC_CATEGORY_CN). * returned in which `category` is 0 (@ref UTF8PROC_CATEGORY_CN).
*/ */
DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t codepoint); UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t codepoint);
/** Decompose a codepoint into an array of codepoints. /** Decompose a codepoint into an array of codepoints.
* *
@ -438,7 +438,7 @@ DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t codepoint);
* required buffer size is returned, while the buffer will be overwritten with * required buffer size is returned, while the buffer will be overwritten with
* undefined data. * undefined data.
*/ */
DLLEXPORT ssize_t utf8proc_decompose_char( UTF8PROC_DLLEXPORT ssize_t utf8proc_decompose_char(
int32_t codepoint, int32_t *dst, ssize_t bufsize, int32_t codepoint, int32_t *dst, ssize_t bufsize,
utf8proc_option_t options, int *last_boundclass utf8proc_option_t options, int *last_boundclass
); );
@ -459,7 +459,7 @@ DLLEXPORT ssize_t utf8proc_decompose_char(
* required buffer size is returned, while the buffer will be overwritten with * required buffer size is returned, while the buffer will be overwritten with
* undefined data. * undefined data.
*/ */
DLLEXPORT ssize_t utf8proc_decompose( UTF8PROC_DLLEXPORT ssize_t utf8proc_decompose(
const uint8_t *str, ssize_t strlen, const uint8_t *str, ssize_t strlen,
int32_t *buffer, ssize_t bufsize, utf8proc_option_t options int32_t *buffer, ssize_t bufsize, utf8proc_option_t options
); );
@ -489,13 +489,13 @@ DLLEXPORT ssize_t utf8proc_decompose(
* entries of the array pointed to by `str` have to be in the * entries of the array pointed to by `str` have to be in the
* range `0x0000` to `0x10FFFF`. Otherwise, the program might crash! * range `0x0000` to `0x10FFFF`. Otherwise, the program might crash!
*/ */
DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, utf8proc_option_t options); UTF8PROC_DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, utf8proc_option_t options);
/** /**
* Given a pair of consecutive codepoints, return whether a grapheme break is * 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). * permitted between them (as defined by the extended grapheme clusters in UAX#29).
*/ */
DLLEXPORT bool utf8proc_grapheme_break(int32_t codepoint1, int32_t codepoint2); UTF8PROC_DLLEXPORT bool utf8proc_grapheme_break(int32_t codepoint1, int32_t codepoint2);
/** /**
* Given a codepoint, return a character width analogous to `wcwidth(codepoint)`, * Given a codepoint, return a character width analogous to `wcwidth(codepoint)`,
@ -505,19 +505,19 @@ DLLEXPORT bool utf8proc_grapheme_break(int32_t codepoint1, int32_t codepoint2);
* @note * @note
* If you want to check for particular types of non-printable characters, * If you want to check for particular types of non-printable characters,
* (analogous to `isprint` or `iscntrl`), use @ref utf8proc_category. */ * (analogous to `isprint` or `iscntrl`), use @ref utf8proc_category. */
DLLEXPORT int utf8proc_charwidth(int32_t codepoint); UTF8PROC_DLLEXPORT int utf8proc_charwidth(int32_t codepoint);
/** /**
* Return the Unicode category for the codepoint (one of the * Return the Unicode category for the codepoint (one of the
* @ref utf8proc_category_t constants.) * @ref utf8proc_category_t constants.)
*/ */
DLLEXPORT utf8proc_category_t utf8proc_category(int32_t codepoint); UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(int32_t codepoint);
/** /**
* Return the two-letter (nul-terminated) Unicode category string for * Return the two-letter (nul-terminated) Unicode category string for
* the codepoint (e.g. `"Lu"` or `"Co"`). * the codepoint (e.g. `"Lu"` or `"Co"`).
*/ */
DLLEXPORT const char *utf8proc_category_string(int32_t codepoint); UTF8PROC_DLLEXPORT const char *utf8proc_category_string(int32_t codepoint);
/** /**
* Maps the given UTF-8 string pointed to by `str` to a new UTF-8 * Maps the given UTF-8 string pointed to by `str` to a new UTF-8
@ -537,7 +537,7 @@ DLLEXPORT const char *utf8proc_category_string(int32_t codepoint);
* @note The memory of the new UTF-8 string will have been allocated * @note The memory of the new UTF-8 string will have been allocated
* with `malloc`, and should therefore be deallocated with `free`. * with `malloc`, and should therefore be deallocated with `free`.
*/ */
DLLEXPORT ssize_t utf8proc_map( UTF8PROC_DLLEXPORT ssize_t utf8proc_map(
const uint8_t *str, ssize_t strlen, uint8_t **dstptr, utf8proc_option_t options const uint8_t *str, ssize_t strlen, uint8_t **dstptr, utf8proc_option_t options
); );
@ -550,13 +550,13 @@ DLLEXPORT ssize_t utf8proc_map(
*/ */
/** @{ */ /** @{ */
/** NFD normalization (@ref UTF8PROC_DECOMPOSE). */ /** NFD normalization (@ref UTF8PROC_DECOMPOSE). */
DLLEXPORT uint8_t *utf8proc_NFD(const uint8_t *str); UTF8PROC_DLLEXPORT uint8_t *utf8proc_NFD(const uint8_t *str);
/** NFC normalization (@ref UTF8PROC_COMPOSE). */ /** NFC normalization (@ref UTF8PROC_COMPOSE). */
DLLEXPORT uint8_t *utf8proc_NFC(const uint8_t *str); UTF8PROC_DLLEXPORT uint8_t *utf8proc_NFC(const uint8_t *str);
/** NFD normalization (@ref UTF8PROC_DECOMPOSE and @ref UTF8PROC_COMPAT). */ /** NFD normalization (@ref UTF8PROC_DECOMPOSE and @ref UTF8PROC_COMPAT). */
DLLEXPORT uint8_t *utf8proc_NFKD(const uint8_t *str); UTF8PROC_DLLEXPORT uint8_t *utf8proc_NFKD(const uint8_t *str);
/** NFD normalization (@ref UTF8PROC_COMPOSE and @ref UTF8PROC_COMPAT). */ /** NFD normalization (@ref UTF8PROC_COMPOSE and @ref UTF8PROC_COMPAT). */
DLLEXPORT uint8_t *utf8proc_NFKC(const uint8_t *str); UTF8PROC_DLLEXPORT uint8_t *utf8proc_NFKC(const uint8_t *str);
/** @} */ /** @} */
#ifdef __cplusplus #ifdef __cplusplus