tommy/libpostal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Removing EXPORT statements from all source files and most header files, leaving only the exports for the main API in libpostal.h. Modified Makefiles so that all the test apps build without having extra functions exported from libpostal.

Browse Source
This commit is contained in:
AeroXuk
2017-11-25 04:35:28 +00:00
parent f0246e7333
commit 26ac9ab5c2
26 changed files with 186 additions and 211 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
src/utf8proc/utf8proc.c
View File

@@ -44,7 +44,7 @@
#include "utf8proc_data.c"
UTF8PROC_DLLEXPORT const utf8proc_int8_t utf8proc_utf8class[256] = {
const utf8proc_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,
@@ -87,11 +87,11 @@ UTF8PROC_DLLEXPORT const utf8proc_int8_t utf8proc_utf8class[256] = {
be different, being based on ABI compatibility.): */
#define STRINGIZEx(x) #x
#define STRINGIZE(x) STRINGIZEx(x)
UTF8PROC_DLLEXPORT const char *utf8proc_version(void) {
const char *utf8proc_version(void) {
return STRINGIZE(UTF8PROC_VERSION_MAJOR) "." STRINGIZE(UTF8PROC_VERSION_MINOR) "." STRINGIZE(UTF8PROC_VERSION_PATCH) "";
}
UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode) {
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.";
@@ -109,7 +109,7 @@ UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode) {
}
#define utf_cont(ch) (((ch) & 0xc0) == 0x80)
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(
utf8proc_ssize_t utf8proc_iterate(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_int32_t *dst
) {
utf8proc_uint32_t uc;
@@ -157,11 +157,11 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(
return 4;
}
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t uc) {
utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t uc) {
return (((utf8proc_uint32_t)uc)-0xd800 > 0x07ff) && ((utf8proc_uint32_t)uc < 0x110000);
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t uc, utf8proc_uint8_t *dst) {
utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t uc, utf8proc_uint8_t *dst) {
if (uc < 0x00) {
return 0;
} else if (uc < 0x80) {
@@ -228,7 +228,7 @@ static const utf8proc_property_t *unsafe_get_property(utf8proc_int32_t uc) {
);
}
UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int32_t uc) {
const utf8proc_property_t *utf8proc_get_property(utf8proc_int32_t uc) {
return uc < 0 || uc >= 0x110000 ? utf8proc_properties : unsafe_get_property(uc);
}
@@ -259,18 +259,18 @@ static utf8proc_bool grapheme_break(int lbc, int tbc) {
}
/* return whether there is a grapheme break between codepoints c1 and c2 */
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(utf8proc_int32_t c1, utf8proc_int32_t c2) {
utf8proc_bool utf8proc_grapheme_break(utf8proc_int32_t c1, utf8proc_int32_t c2) {
return grapheme_break(utf8proc_get_property(c1)->boundclass,
utf8proc_get_property(c2)->boundclass);
}
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_tolower(utf8proc_int32_t c)
utf8proc_int32_t utf8proc_tolower(utf8proc_int32_t c)
{
utf8proc_int32_t cl = utf8proc_get_property(c)->lowercase_mapping;
return cl >= 0 ? cl : c;
}
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c)
utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c)
{
utf8proc_int32_t cu = utf8proc_get_property(c)->uppercase_mapping;
return cu >= 0 ? cu : c;
@@ -278,15 +278,15 @@ UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c)
/* return a character width analogous to wcwidth (except portable and
hopefully less buggy than most system wcwidth functions). */
UTF8PROC_DLLEXPORT int utf8proc_charwidth(utf8proc_int32_t c) {
int utf8proc_charwidth(utf8proc_int32_t c) {
return utf8proc_get_property(c)->charwidth;
}
UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(utf8proc_int32_t c) {
utf8proc_category_t utf8proc_category(utf8proc_int32_t c) {
return utf8proc_get_property(c)->category;
}
UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t c) {
const char *utf8proc_category_string(utf8proc_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"};
return s[utf8proc_category(c)];
}
@@ -295,7 +295,7 @@ UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t c) {
return utf8proc_decompose_char((replacement_uc), dst, bufsize, \
options & ~UTF8PROC_LUMP, last_boundclass)
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(utf8proc_int32_t uc, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) {
utf8proc_ssize_t utf8proc_decompose_char(utf8proc_int32_t uc, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) {
const utf8proc_property_t *property;
utf8proc_propval_t category;
utf8proc_int32_t hangul_sindex;
@@ -399,7 +399,7 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(utf8proc_int32_t uc,
return 1;
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
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
) {
@@ -461,7 +461,7 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
return wpos;
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options) {
utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options) {
/* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored
ASSERT: 'buffer' has one spare byte of free space at the end! */
if (options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC)) {
@@ -583,7 +583,7 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t *buffer,
}
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(
utf8proc_ssize_t utf8proc_map(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options
) {
utf8proc_int32_t *buffer;
@@ -612,28 +612,28 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(
return result;
}
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFD(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *utf8proc_NFD(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_DECOMPOSE);
return retval;
}
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFC(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *utf8proc_NFC(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_COMPOSE);
return retval;
}
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKD(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *utf8proc_NFKD(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT);
return retval;
}
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *utf8proc_NFKC(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_COMPOSE | UTF8PROC_COMPAT);

54
src/utf8proc/utf8proc.h
View File

@@ -111,18 +111,6 @@ typedef bool utf8proc_bool;
#endif
#include <limits.h>
#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
#ifdef __cplusplus
extern "C" {
#endif
@@ -365,20 +353,20 @@ typedef enum {
* 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];
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);
const char *utf8proc_version(void);
/**
* Returns an informative error string for the given utf8proc error code
* (e.g. the error codes returned by @ref utf8proc_map).
*/
UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode);
const char *utf8proc_errmsg(utf8proc_ssize_t errcode);
/**
* Reads a single codepoint from the UTF-8 sequence being pointed to by `str`.
@@ -390,7 +378,7 @@ UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode);
* 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);
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
@@ -398,7 +386,7 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(const utf8proc_uint8_t *str
*
* @return 1 if the given `codepoint` is valid and otherwise return 0.
*/
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t codepoint);
utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t codepoint);
/**
* Encodes the codepoint as an UTF-8 string in the byte array pointed
@@ -409,7 +397,7 @@ UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t codep
*
* 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);
utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t codepoint, utf8proc_uint8_t *dst);
/**
* Look up the properties for a given codepoint.
@@ -423,7 +411,7 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t codepo
* 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);
const utf8proc_property_t *utf8proc_get_property(utf8proc_int32_t codepoint);
/** Decompose a codepoint into an array of codepoints.
*
@@ -452,7 +440,7 @@ UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int
* required buffer size is returned, while the buffer will be overwritten with
* undefined data.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(
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
);
@@ -473,7 +461,7 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(
* required buffer size is returned, while the buffer will be overwritten with
* undefined data.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
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
);
@@ -503,13 +491,13 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
* 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);
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).
*/
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(utf8proc_int32_t codepoint1, utf8proc_int32_t codepoint2);
utf8proc_bool utf8proc_grapheme_break(utf8proc_int32_t codepoint1, utf8proc_int32_t codepoint2);
/**
@@ -517,14 +505,14 @@ UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(utf8proc_int32_t codepo
* 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);
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);
utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c);
/**
* Given a codepoint, return a character width analogous to `wcwidth(codepoint)`,
@@ -534,19 +522,19 @@ UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c);
* @note
* If you want to check for particular types of non-printable characters,
* (analogous to `isprint` or `iscntrl`), use @ref utf8proc_category. */
UTF8PROC_DLLEXPORT int utf8proc_charwidth(utf8proc_int32_t codepoint);
int utf8proc_charwidth(utf8proc_int32_t codepoint);
/**
* Return the Unicode category for the codepoint (one of the
* @ref utf8proc_category_t constants.)
*/
UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(utf8proc_int32_t codepoint);
utf8proc_category_t utf8proc_category(utf8proc_int32_t codepoint);
/**
* Return the two-letter (nul-terminated) Unicode category string for
* the codepoint (e.g. `"Lu"` or `"Co"`).
*/
UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t codepoint);
const char *utf8proc_category_string(utf8proc_int32_t codepoint);
/**
* Maps the given UTF-8 string pointed to by `str` to a new UTF-8
@@ -566,7 +554,7 @@ UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t codepoi
* @note The memory of the new UTF-8 string will have been allocated
* with `malloc`, and should therefore be deallocated with `free`.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(
utf8proc_ssize_t utf8proc_map(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options
);
@@ -579,13 +567,13 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(
*/
/** @{ */
/** NFD normalization (@ref UTF8PROC_DECOMPOSE). */
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFD(const utf8proc_uint8_t *str);
utf8proc_uint8_t *utf8proc_NFD(const utf8proc_uint8_t *str);
/** NFC normalization (@ref UTF8PROC_COMPOSE). */
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFC(const utf8proc_uint8_t *str);
utf8proc_uint8_t *utf8proc_NFC(const utf8proc_uint8_t *str);
/** NFD normalization (@ref UTF8PROC_DECOMPOSE and @ref UTF8PROC_COMPAT). */
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKD(const utf8proc_uint8_t *str);
utf8proc_uint8_t *utf8proc_NFKD(const utf8proc_uint8_t *str);
/** NFD normalization (@ref UTF8PROC_COMPOSE and @ref UTF8PROC_COMPAT). */
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC(const utf8proc_uint8_t *str);
utf8proc_uint8_t *utf8proc_NFKC(const utf8proc_uint8_t *str);
/** @} */
#ifdef __cplusplus