1
  +   ˆl–äY>””†»€jà€¦-ÿÁ„u—^k_†I|¥+ÁÀ ?÷     // Â© 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
*   Copyright (C) 2004-2016, International Business Machines
*   Corporation and others.  All Rights Reserved.
**********************************************************************
*   file name:  uregex.h
*   encoding:   UTF-8
*   indentation:4
*
*   created on: 2004mar09
*   created by: Andy Heninger
*
*   ICU Regular Expressions, API for C
*/

/**
 * \file
 * \brief C API: Regular Expressions
 *
 * <p>This is a C wrapper around the C++ RegexPattern and RegexMatcher classes.</p>
 */

#ifndef UREGEX_H
#define UREGEX_H

#include "unicode/utext.h"
#include "unicode/utypes.h"

#if !UCONFIG_NO_REGULAR_EXPRESSIONS

#include "unicode/localpointer.h"
#include "unicode/parseerr.h"

struct URegularExpression;
/**
  * Structure representing a compiled regular expression, plus the results
  *    of a match operation.
  * @stable ICU 3.0
  */
typedef struct URegularExpression URegularExpression;


/**
 * Constants for Regular Expression Match Modes.
 * @stable ICU 2.4
 */
typedef enum URegexpFlag{

#ifndef U_HIDE_DRAFT_API 
    /** Forces normalization of pattern and strings. 
    Not implemented yet, just a placeholder, hence draft. 
    @draft ICU 2.4 */
    UREGEX_CANON_EQ         = 128,
#endif /* U_HIDE_DRAFT_API */
    /**  Enable case insensitive matching.  @stable ICU 2.4 */
    UREGEX_CASE_INSENSITIVE = 2,

    /**  Allow white space and comments within patterns  @stable ICU 2.4 */
    UREGEX_COMMENTS         = 4,

    /**  If set, '.' matches line terminators,  otherwise '.' matching stops at line end.
      *  @stable ICU 2.4 */
    UREGEX_DOTALL           = 32,
    
    /**  If set, treat the entire pattern as a literal string.  
      *  Metacharacters or escape sequences in the input sequence will be given 
      *  no special meaning. 
      *
      *  The flag UREGEX_CASE_INSENSITIVE retains its impact
      *  on matching when used in conjunction with this flag.
      *  The other flags become superfluous.
      *
      * @stable ICU 4.0
      */
    UREGEX_LITERAL = 16,

    /**   Control behavior of "$" and "^"
      *    If set, recognize line terminators within string,
      *    otherwise, match only at start and end of input string.
      *   @stable ICU 2.4 */
    UREGEX_MULTILINE        = 8,
    
    /**   Unix-only line endings.
      *   When this mode is enabled, only \\u000a is recognized as a line ending
      *    in the behavior of ., ^, and $.
      *   @stable ICU 4.0
      */
    UREGEX_UNIX_LINES = 1,

    /**  Unicode word boundaries.
      *     If set, \b uses the Unicode TR 29 definition of word boundaries.
      *     Warning: Unicode word boundaries are quite different from
      *     traditional regular expression word boundaries.  See
      *     http://unicode.org/reports/tr29/#Word_Boundaries
      *     @stable ICU 2.8
      */
    UREGEX_UWORD            = 256,

     /**  Error on Unrecognized backslash escapes.
       *     If set, fail with an error on patterns that contain
       *     backslash-escaped ASCII letters without a known special
       *     meaning.  If this flag is not set, these
       *     escaped letters represent themselves.
       *     @stable ICU 4.0
       */
     UREGEX_ERROR_ON_UNKNOWN_ESCAPES = 512

}  URegexpFlag;

/**
  *  Open (compile) an ICU regular expression.  Compiles the regular expression in
  *  string form into an internal representation using the specified match mode flags.
  *  The resulting regular expression handle can then be used to perform various
  *   matching operations.
  * 
  *
  * @param pattern        The Regular Expression pattern to be compiled. 
  * @param patternLength  The length of the pattern, or -1 if the pattern is
  *                       NUL terminated.
  * @param flags          Flags that alter the default matching behavior for
  *                       the regular expres