linebreakdef.h

Go to the documentation of this file.

/* vim: set expandtab tabstop=4 softtabstop=4 shiftwidth=4: */
 
/*
 * Line breaking in a Unicode sequence.  Designed to be used in a
 * generic text renderer.
 *
 * Copyright (C) 2008-2026 Wu Yongwei <wuyongwei at gmail dot com>
 * Copyright (C) 2013 Petr Filipsky <philodej at gmail dot com>
 *
 * This software is provided 'as-is', without any express or implied
 * warranty.  In no event will the author be held liable for any damages
 * arising from the use of this software.
 *
 * Permission is granted to anyone to use this software for any purpose,
 * including commercial applications, and to alter it and redistribute
 * it freely, subject to the following restrictions:
 *
 * 1. The origin of this software must not be misrepresented; you must
 *    not claim that you wrote the original software.  If you use this
 *    software in a product, an acknowledgement in the product
 *    documentation would be appreciated but is not required.
 * 2. Altered source versions must be plainly marked as such, and must
 *    not be misrepresented as being the original software.
 * 3. This notice may not be removed or altered from any source
 *    distribution.
 *
 * The main reference is Unicode Standard Annex 14 (UAX #14):
 *      <URL:http://www.unicode.org/reports/tr14/>
 *
 * When this library was designed, this annex was at Revision 19, for
 * Unicode 5.0.0:
 *      <URL:http://www.unicode.org/reports/tr14/tr14-19.html>
 *
 * This library has been updated according to Revision 55, for
 * Unicode 17.0.0:
 *      <URL:http://www.unicode.org/reports/tr14/tr14-55.html>
 *
 * The Unicode Terms of Use are available at
 *      <URL:http://www.unicode.org/copyright.html>
 */

 
#ifndef LINEBREAKDEF_H
#define LINEBREAKDEF_H
 
#include "unibreakdef.h"

enum LineBreakClass
{
    /* This is used to signal an error condition. */
    LBP_Undefined,  
 
    /* The following break classes are treated in the pair table. */
    LBP_OP,         
    LBP_CL,         
    LBP_CP,         
    LBP_QU,         
    LBP_GL,         
    LBP_NS,         
    LBP_EX,         
    LBP_SY,         
    LBP_IS,         
    LBP_PR,         
    LBP_PO,         
    LBP_NU,         
    LBP_AL,         
    LBP_HL,         
    LBP_ID,         
    LBP_IN,         
    LBP_HY,         
    LBP_BA,         
    LBP_BB,         
    LBP_B2,         
    LBP_ZW,         
    LBP_CM,         
    LBP_WJ,         
    LBP_H2,         
    LBP_H3,         
    LBP_JL,         
    LBP_JV,         
    LBP_JT,         
    LBP_RI,         
    LBP_EB,         
    LBP_EM,         
    LBP_ZWJ,        
 
    /* The following break classes are treated in the pair table, but
     * they are not part of Table 2 of UAX #14-37. */
    LBP_AK,         
    LBP_AP,         
    LBP_AS,         
    LBP_VF,         
    LBP_VI,         
    LBP_HH,         
    LBP_CB,         
 
    /* The following break classes are not treated in the pair table */
    LBP_AI,         
    LBP_BK,         
    LBP_CJ,         
    LBP_CR,         
    LBP_LF,         
    LBP_NL,         
    LBP_SA,         
    LBP_SG,         
    LBP_SP,         
    LBP_XX          
};

enum Lb25State
{
    LB25_NONE,       
    LB25_PREFIX,     
    LB25_PREFIXOP,   
    LB25_NUM,        
    LB25_NUMCLOSE,   
};

enum PendingRule
{
    PENDING_NONE,       
    PENDING_LB15B,      
    PENDING_LB15C,      
    PENDING_LB19A,      
    PENDING_LB28A4,     
};
 
enum BreakOutputType
{
    LBOT_PER_CODE_UNIT,
    LBOT_PER_CODE_POINT
};

struct LineBreakProperties
{
    utf32_t start;              
    utf32_t end;                
    enum LineBreakClass prop;   
};

struct LineBreakAuxRange
{
    utf32_t start;              
    utf32_t end;                
};

struct LineBreakPropertiesLang
{
    const char *lang;                      
    size_t namelen;                        
    const struct LineBreakProperties *lbp; 
};

struct LineBreakContext
{
    /* --- Hot state (touched on every character) --- */
    const struct LineBreakProperties *lbpLang; 
    size_t posLast;                 
    enum LineBreakClass lbcCur;     
    enum LineBreakClass lbcNew;     
    enum LineBreakClass lbcLast;    
    enum PendingRule ePending;      
    enum Lb25State eLb25;           
    int cLb30aRI;                   
 
    bool fLb8aZwj;                  
    bool fLb21aHebrew;              
    bool fLb20aWordInit;            
    bool fLb28aPrevAksara;          
    bool fLb28aAkVi;                
 
    bool fLangCjk;                  
    bool fLangStrict;               
    bool fPrevPotentialEmoji;       
    bool fQuPiInitial;              
    bool fPrevQuPi;                 
    bool fPrevQuPf;                 
    bool fPrevEA;                   
    bool fQuPrevEA;                 
 
    /* --- Lookahead-fixup state (rarely used) --- */
    size_t posPending;              
    size_t posLb25Fixup;            
    bool fLb25Mark;                 
    char cPendingOrigBrk;           
    bool fPendingRevert;            
};
 
/* Declarations */
extern const struct LineBreakProperties lb_prop_supplementary[];
extern const unsigned int lb_prop_supplementary_len;
extern const char lb_prop_bmp[];
extern const struct LineBreakPropertiesLang lb_prop_lang_map[];
 
#endif /* LINEBREAKDEF_H */