usprep.cpp | Explore in Territory

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
 *******************************************************************************
 *
 *   Copyright (C) 2003-2016, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 *
 *******************************************************************************
 *   file name:  usprep.cpp
 *   encoding:   UTF-8
 *   tab size:   8 (not used)
 *   indentation:4
 *
 *   created on: 2003jul2
 *   created by: Ram Viswanadha
 */

#include "unicode/utypes.h"

#if !UCONFIG_NO_IDNA

#include "unicode/usprep.h"

#include "unicode/normalizer2.h"
#include "unicode/ustring.h"
#include "unicode/uchar.h"
#include "unicode/uversion.h"
#include "umutex.h"
#include "cmemory.h"
#include "sprpimpl.h"
#include "ustr_imp.h"
#include "uhash.h"
#include "cstring.h"
#include "udataswp.h"
#include "ucln_cmn.h"
#include "ubidi_props.h"
#include "uprops.h"

U_NAMESPACE_USE

U_CDECL_BEGIN

/*
Static cache for already opened StringPrep profiles
*/
static UHashtable *SHARED_DATA_HASHTABLE = …;
static icu::UInitOnce gSharedDataInitOnce { … };

static UMutex usprepMutex;
/* format version of spp file */
//static uint8_t formatVersion[4]={ 0, 0, 0, 0 };

/* the Unicode version of the sprep data */
static UVersionInfo dataVersion= …;

/* Profile names must be aligned to UStringPrepProfileType */
static const char * const PROFILE_NAMES[] = …;

static UBool U_CALLCONV
isSPrepAcceptable(void * /* context */,
             const char * /* type */, 
             const char * /* name */,
             const UDataInfo *pInfo) { … }

static int32_t U_CALLCONV
getSPrepFoldingOffset(uint32_t data) { … }

/* hashes an entry  */
static int32_t U_CALLCONV 
hashEntry(const UHashTok parm) { … }

/* compares two entries */
static UBool U_CALLCONV 
compareEntries(const UHashTok p1, const UHashTok p2) { … }

static void 
usprep_unload(UStringPrepProfile* data){ … }

static int32_t 
usprep_internal_flushCache(UBool noRefCount){ … }

/* Works just like ucnv_flushCache() 
static int32_t 
usprep_flushCache(){
    return usprep_internal_flushCache(false);
}
*/

static UBool U_CALLCONV usprep_cleanup(){ … }
U_CDECL_END


/** Initializes the cache for resources */
static void U_CALLCONV
createCache(UErrorCode &status) { … }

static void 
initCache(UErrorCode *status) { … }

static UBool U_CALLCONV
loadData(UStringPrepProfile* profile, 
         const char* path, 
         const char* name, 
         const char* type, 
         UErrorCode* errorCode) { … }

static UStringPrepProfile* 
usprep_getProfile(const char* path, 
                  const char* name,
                  UErrorCode *status){ … }

U_CAPI UStringPrepProfile* U_EXPORT2
usprep_open(const char* path, 
            const char* name,
            UErrorCode* status){ … }

U_CAPI UStringPrepProfile* U_EXPORT2
usprep_openByType(UStringPrepProfileType type,
				  UErrorCode* status) { … }

U_CAPI void U_EXPORT2
usprep_close(UStringPrepProfile* profile){ … }

U_CFUNC void 
uprv_syntaxError(const char16_t* rules,
                 int32_t pos,
                 int32_t rulesLen,
                 UParseError* parseError){ … }


static inline UStringPrepType
getValues(uint16_t trieWord, int16_t& value, UBool& isIndex){ … }

// TODO: change to writing to UnicodeString not char16_t *
static int32_t 
usprep_map(  const UStringPrepProfile* profile, 
             const char16_t* src, int32_t srcLength,
             char16_t* dest, int32_t destCapacity,
             int32_t options,
             UParseError* parseError,
             UErrorCode* status ){ … }

/*
   1) Map -- For each character in the input, check if it has a mapping
      and, if so, replace it with its mapping.  

   2) Normalize -- Possibly normalize the result of step 1 using Unicode
      normalization. 

   3) Prohibit -- Check for any characters that are not allowed in the
      output.  If any are found, return an error.  

   4) Check bidi -- Possibly check for right-to-left characters, and if
      any are found, make sure that the whole string satisfies the
      requirements for bidirectional strings.  If the string does not
      satisfy the requirements for bidirectional strings, return an
      error.  
      [Unicode3.2] defines several bidirectional categories; each character
       has one bidirectional category assigned to it.  For the purposes of
       the requirements below, an "RandALCat character" is a character that
       has Unicode bidirectional categories "R" or "AL"; an "LCat character"
       is a character that has Unicode bidirectional category "L".  Note


       that there are many characters which fall in neither of the above
       definitions; Latin digits (<U+0030> through <U+0039>) are examples of
       this because they have bidirectional category "EN".

       In any profile that specifies bidirectional character handling, all
       three of the following requirements MUST be met:

       1) The characters in section 5.8 MUST be prohibited.

       2) If a string contains any RandALCat character, the string MUST NOT
          contain any LCat character.

       3) If a string contains any RandALCat character, a RandALCat
          character MUST be the first character of the string, and a
          RandALCat character MUST be the last character of the string.
*/
U_CAPI int32_t U_EXPORT2
usprep_prepare(   const UStringPrepProfile* profile,
                  const char16_t* src, int32_t srcLength,
                  char16_t* dest, int32_t destCapacity,
                  int32_t options,
                  UParseError* parseError,
                  UErrorCode* status ){ … }


/* data swapping ------------------------------------------------------------ */

U_CAPI int32_t U_EXPORT2
usprep_swap(const UDataSwapper *ds,
            const void *inData, int32_t length, void *outData,
            UErrorCode *pErrorCode) { … }

#endif /* #if !UCONFIG_NO_IDNA */
chromium/third_party/icu/source/common/usprep.cpp
