/src/icu/source/common/ucnv_err.cpp

Source (jump to first uncovered line)
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
 *****************************************************************************
 *
 *   Copyright (C) 1998-2016, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 *
 *****************************************************************************
 *
 *  ucnv_err.c
 *  Implements error behaviour functions called by T_UConverter_{from,to}Unicode
 *
 *
*   Change history:
*
*   06/29/2000  helena      Major rewrite of the callback APIs.
*/

#include "unicode/utypes.h"

#if !UCONFIG_NO_CONVERSION

#include "unicode/ucnv_err.h"
#include "unicode/ucnv_cb.h"
#include "ucnv_cnv.h"
#include "cmemory.h"
#include "unicode/ucnv.h"
#include "ustrfmt.h"

#define VALUE_STRING_LENGTH 48
/*Magic # 32 = 4(number of char in value string) * 8(max number of bytes per char for any converter) */
#define UNICODE_PERCENT_SIGN_CODEPOINT  0x0025
#define UNICODE_U_CODEPOINT             0x0055
#define UNICODE_X_CODEPOINT             0x0058
#define UNICODE_RS_CODEPOINT            0x005C
#define UNICODE_U_LOW_CODEPOINT         0x0075
#define UNICODE_X_LOW_CODEPOINT         0x0078
#define UNICODE_AMP_CODEPOINT           0x0026
#define UNICODE_HASH_CODEPOINT          0x0023
#define UNICODE_SEMICOLON_CODEPOINT     0x003B
#define UNICODE_PLUS_CODEPOINT          0x002B
#define UNICODE_LEFT_CURLY_CODEPOINT    0x007B
#define UNICODE_RIGHT_CURLY_CODEPOINT   0x007D
#define UNICODE_SPACE_CODEPOINT         0x0020
#define UCNV_PRV_ESCAPE_ICU         0
#define UCNV_PRV_ESCAPE_C           'C'
#define UCNV_PRV_ESCAPE_XML_DEC     'D'
#define UCNV_PRV_ESCAPE_XML_HEX     'X'
#define UCNV_PRV_ESCAPE_JAVA        'J'
#define UCNV_PRV_ESCAPE_UNICODE     'U'
#define UCNV_PRV_ESCAPE_CSS2        'S'
#define UCNV_PRV_STOP_ON_ILLEGAL    'i'

/*
 * IS_DEFAULT_IGNORABLE_CODE_POINT
 * This is to check if a code point has the default ignorable unicode property.
 * As such, this list needs to be updated if the ignorable code point list ever
 * changes.
 * To avoid dependency on other code, this list is hard coded here.
 * When an ignorable code point is found and is unmappable, the default callbacks
 * will ignore them.
 * For a list of the default ignorable code points, use this link:
 * https://util.unicode.org/UnicodeJsps/list-unicodeset.jsp?a=%5B%3ADI%3A%5D&abb=on&g=&i=
 *
 * This list should be sync with the one in CharsetCallback.java
 */
#define IS_DEFAULT_IGNORABLE_CODE_POINT(c) ( \
    (c == 0x00AD) || \
    (c == 0x034F) || \
    (c == 0x061C) || \
    (c == 0x115F) || \
    (c == 0x1160) || \
    (0x17B4 <= c && c <= 0x17B5) || \
    (0x180B <= c && c <= 0x180F) || \
    (0x200B <= c && c <= 0x200F) || \
    (0x202A <= c && c <= 0x202E) || \
    (0x2060 <= c && c <= 0x206F) || \
    (c == 0x3164) || \
    (0xFE00 <= c && c <= 0xFE0F) || \
    (c == 0xFEFF) || \
    (c == 0xFFA0) || \
    (0xFFF0 <= c && c <= 0xFFF8) || \
    (0x1BCA0 <= c && c <= 0x1BCA3) || \
    (0x1D173 <= c && c <= 0x1D17A) || \
    (0xE0000 <= c && c <= 0xE0FFF))


/*Function Pointer STOPS at the ILLEGAL_SEQUENCE */
U_CAPI void    U_EXPORT2
UCNV_FROM_U_CALLBACK_STOP (
                  const void *context,
                  UConverterFromUnicodeArgs *fromUArgs,
                  const UChar* codeUnits,
                  int32_t length,
                  UChar32 codePoint,
                  UConverterCallbackReason reason,
                  UErrorCode * err)
{
    (void)context;
    (void)fromUArgs;
    (void)codeUnits;
    (void)length;
    if (reason == UCNV_UNASSIGNED && IS_DEFAULT_IGNORABLE_CODE_POINT(codePoint))
    {
        /*
         * Skip if the codepoint has unicode property of default ignorable.
         */
        *err = U_ZERO_ERROR;
    }
    /* the caller must have set the error code accordingly */
    return;
}


/*Function Pointer STOPS at the ILLEGAL_SEQUENCE */
U_CAPI void    U_EXPORT2
UCNV_TO_U_CALLBACK_STOP (
                   const void *context,
                   UConverterToUnicodeArgs *toUArgs,
                   const char* codePoints,
                   int32_t length,
                   UConverterCallbackReason reason,
                   UErrorCode * err)
{
    /* the caller must have set the error code accordingly */
    (void)context; (void)toUArgs; (void)codePoints; (void)length; (void)reason; (void)err;
    return;
}

U_CAPI void    U_EXPORT2
UCNV_FROM_U_CALLBACK_SKIP (                  
                  const void *context,
                  UConverterFromUnicodeArgs *fromUArgs,
                  const UChar* codeUnits,
                  int32_t length,
                  UChar32 codePoint,
                  UConverterCallbackReason reason,
                  UErrorCode * err)
{
    (void)fromUArgs;
    (void)codeUnits;
    (void)length;
    if (reason <= UCNV_IRREGULAR)
    {
        if (reason == UCNV_UNASSIGNED && IS_DEFAULT_IGNORABLE_CODE_POINT(codePoint))
        {
            /*
             * Skip if the codepoint has unicode property of default ignorable.
             */
            *err = U_ZERO_ERROR;
        }
        else if (context == NULL || (*((char*)context) == UCNV_PRV_STOP_ON_ILLEGAL && reason == UCNV_UNASSIGNED))
        {
            *err = U_ZERO_ERROR;
        }
        /* else the caller must have set the error code accordingly. */
    }
    /* else ignore the reset, close and clone calls. */
}

U_CAPI void    U_EXPORT2
UCNV_FROM_U_CALLBACK_SUBSTITUTE (
                  const void *context,
                  UConverterFromUnicodeArgs *fromArgs,
                  const UChar* codeUnits,
                  int32_t length,
                  UChar32 codePoint,
                  UConverterCallbackReason reason,
                  UErrorCode * err)
{
    (void)codeUnits;
    (void)length;
    if (reason <= UCNV_IRREGULAR)
    {
        if (reason == UCNV_UNASSIGNED && IS_DEFAULT_IGNORABLE_CODE_POINT(codePoint))
        {
            /*
             * Skip if the codepoint has unicode property of default ignorable.
             */
            *err = U_ZERO_ERROR;
        }
        else if (context == NULL || (*((char*)context) == UCNV_PRV_STOP_ON_ILLEGAL && reason == UCNV_UNASSIGNED))
        {
            *err = U_ZERO_ERROR;
            ucnv_cbFromUWriteSub(fromArgs, 0, err);
        }
        /* else the caller must have set the error code accordingly. */
    }
    /* else ignore the reset, close and clone calls. */
}

/*uses uprv_itou to get a unicode escape sequence of the offensive sequence,
 *uses a clean copy (resetted) of the converter, to convert that unicode
 *escape sequence to the target codepage (if conversion failure happens then
 *we revert to substituting with subchar)
 */
U_CAPI void    U_EXPORT2
UCNV_FROM_U_CALLBACK_ESCAPE (
                         const void *context,
                         UConverterFromUnicodeArgs *fromArgs,
                         const UChar *codeUnits,
                         int32_t length,
                         UChar32 codePoint,
                         UConverterCallbackReason reason,
                         UErrorCode * err)
{

  UChar valueString[VALUE_STRING_LENGTH];
  int32_t valueStringLength = 0;
  int32_t i = 0;

  const UChar *myValueSource = NULL;
  UErrorCode err2 = U_ZERO_ERROR;
  UConverterFromUCallback original = NULL;
  const void *originalContext;

  UConverterFromUCallback ignoredCallback = NULL;
  const void *ignoredContext;
  
  if (reason > UCNV_IRREGULAR)
  {
      return;
  }
  else if (reason == UCNV_UNASSIGNED && IS_DEFAULT_IGNORABLE_CODE_POINT(codePoint))
  {
      /*
       * Skip if the codepoint has unicode property of default ignorable.
       */
      *err = U_ZERO_ERROR;
      return;
  }

  ucnv_setFromUCallBack (fromArgs->converter,
                     (UConverterFromUCallback) UCNV_FROM_U_CALLBACK_SUBSTITUTE,
                     NULL,
                     &original,
                     &originalContext,
                     &err2);
  
  if (U_FAILURE (err2))
  {
    *err = err2;
    return;
  } 
  if(context==NULL)
  { 
      while (i < length)
      {
        valueString[valueStringLength++] = (UChar) UNICODE_PERCENT_SIGN_CODEPOINT;  /* adding % */
        valueString[valueStringLength++] = (UChar) UNICODE_U_CODEPOINT; /* adding U */
        valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[i++], 16, 4);
      }
  }
  else
  {
      switch(*((char*)context))
      {
      case UCNV_PRV_ESCAPE_JAVA:
          while (i < length)
          {
              valueString[valueStringLength++] = (UChar) UNICODE_RS_CODEPOINT;    /* adding \ */
              valueString[valueStringLength++] = (UChar) UNICODE_U_LOW_CODEPOINT; /* adding u */
              valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[i++], 16, 4);
          }
          break;

      case UCNV_PRV_ESCAPE_C:
          valueString[valueStringLength++] = (UChar) UNICODE_RS_CODEPOINT;    /* adding \ */

          if(length==2){
              valueString[valueStringLength++] = (UChar) UNICODE_U_CODEPOINT; /* adding U */
              valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, codePoint, 16, 8);

          }
          else{
              valueString[valueStringLength++] = (UChar) UNICODE_U_LOW_CODEPOINT; /* adding u */
              valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[0], 16, 4);
          }
          break;

      case UCNV_PRV_ESCAPE_XML_DEC:

          valueString[valueStringLength++] = (UChar) UNICODE_AMP_CODEPOINT;   /* adding & */
          valueString[valueStringLength++] = (UChar) UNICODE_HASH_CODEPOINT;  /* adding # */
          if(length==2){
              valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, codePoint, 10, 0);
          }
          else{
              valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[0], 10, 0);
          }
          valueString[valueStringLength++] = (UChar) UNICODE_SEMICOLON_CODEPOINT; /* adding ; */
          break;

      case UCNV_PRV_ESCAPE_XML_HEX:

          valueString[valueStringLength++] = (UChar) UNICODE_AMP_CODEPOINT;   /* adding & */
          valueString[valueStringLength++] = (UChar) UNICODE_HASH_CODEPOINT;  /* adding # */
          valueString[valueStringLength++] = (UChar) UNICODE_X_LOW_CODEPOINT; /* adding x */
          if(length==2){
              valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, codePoint, 16, 0);
          }
          else{
              valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[0], 16, 0);
          }
          valueString[valueStringLength++] = (UChar) UNICODE_SEMICOLON_CODEPOINT; /* adding ; */
          break;

      case UCNV_PRV_ESCAPE_UNICODE:
          valueString[valueStringLength++] = (UChar) UNICODE_LEFT_CURLY_CODEPOINT;    /* adding { */
          valueString[valueStringLength++] = (UChar) UNICODE_U_CODEPOINT;    /* adding U */
          valueString[valueStringLength++] = (UChar) UNICODE_PLUS_CODEPOINT; /* adding + */
          if (length == 2) {
              valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, codePoint, 16, 4);
          } else {
              valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[0], 16, 4);
          }
          valueString[valueStringLength++] = (UChar) UNICODE_RIGHT_CURLY_CODEPOINT;    /* adding } */
          break;

      case UCNV_PRV_ESCAPE_CSS2:
          valueString[valueStringLength++] = (UChar) UNICODE_RS_CODEPOINT;    /* adding \ */
          valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, codePoint, 16, 0);
          /* Always add space character, because the next character might be whitespace,
             which would erroneously be considered the termination of the escape sequence. */
          valueString[valueStringLength++] = (UChar) UNICODE_SPACE_CODEPOINT;
          break;

      default:
          while (i < length)
          {
              valueString[valueStringLength++] = (UChar) UNICODE_PERCENT_SIGN_CODEPOINT;  /* adding % */
              valueString[valueStringLength++] = (UChar) UNICODE_U_CODEPOINT;             /* adding U */
              valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[i++], 16, 4);
          }
      }
  }  
  myValueSource = valueString;

  /* reset the error */
  *err = U_ZERO_ERROR;

  ucnv_cbFromUWriteUChars(fromArgs, &myValueSource, myValueSource+valueStringLength, 0, err);

  ucnv_setFromUCallBack (fromArgs->converter,
                         original,
                         originalContext,
                         &ignoredCallback,
                         &ignoredContext,
                         &err2);
  if (U_FAILURE (err2))
  {
      *err = err2;
      return;
  }

  return;
}



U_CAPI void  U_EXPORT2
UCNV_TO_U_CALLBACK_SKIP (
                 const void *context,
                 UConverterToUnicodeArgs *toArgs,
                 const char* codeUnits,
                 int32_t length,
                 UConverterCallbackReason reason,
                 UErrorCode * err)
{
    (void)toArgs;
    (void)codeUnits;
    (void)length;
    if (reason <= UCNV_IRREGULAR)
    {
        if (context == NULL || (*((char*)context) == UCNV_PRV_STOP_ON_ILLEGAL && reason == UCNV_UNASSIGNED))
        {
            *err = U_ZERO_ERROR;
        }
        /* else the caller must have set the error code accordingly. */
    }
    /* else ignore the reset, close and clone calls. */
}

U_CAPI void    U_EXPORT2
UCNV_TO_U_CALLBACK_SUBSTITUTE (
                 const void *context,
                 UConverterToUnicodeArgs *toArgs,
                 const char* codeUnits,
                 int32_t length,
                 UConverterCallbackReason reason,
                 UErrorCode * err)
{
    (void)codeUnits;
    (void)length;
    if (reason <= UCNV_IRREGULAR)
    {
        if (context == NULL || (*((char*)context) == UCNV_PRV_STOP_ON_ILLEGAL && reason == UCNV_UNASSIGNED))
        {
            *err = U_ZERO_ERROR;
            ucnv_cbToUWriteSub(toArgs,0,err);
        }
        /* else the caller must have set the error code accordingly. */
    }
    /* else ignore the reset, close and clone calls. */
}

/*uses uprv_itou to get a unicode escape sequence of the offensive sequence,
 *and uses that as the substitution sequence
 */
U_CAPI void   U_EXPORT2
UCNV_TO_U_CALLBACK_ESCAPE (
                 const void *context,
                 UConverterToUnicodeArgs *toArgs,
                 const char* codeUnits,
                 int32_t length,
                 UConverterCallbackReason reason,
                 UErrorCode * err)
{
    UChar uniValueString[VALUE_STRING_LENGTH];
    int32_t valueStringLength = 0;
    int32_t i = 0;

    if (reason > UCNV_IRREGULAR)
    {
        return;
    }

    if(context==NULL)
    {    
        while (i < length)
        {
            uniValueString[valueStringLength++] = (UChar) UNICODE_PERCENT_SIGN_CODEPOINT; /* adding % */
            uniValueString[valueStringLength++] = (UChar) UNICODE_X_CODEPOINT;    /* adding X */
            valueStringLength += uprv_itou (uniValueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint8_t) codeUnits[i++], 16, 2);
        }
    }
    else
    {
        switch(*((char*)context))
        {
        case UCNV_PRV_ESCAPE_XML_DEC:
            while (i < length)
            {
                uniValueString[valueStringLength++] = (UChar) UNICODE_AMP_CODEPOINT;   /* adding & */
                uniValueString[valueStringLength++] = (UChar) UNICODE_HASH_CODEPOINT;  /* adding # */
                valueStringLength += uprv_itou (uniValueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint8_t)codeUnits[i++], 10, 0);
                uniValueString[valueStringLength++] = (UChar) UNICODE_SEMICOLON_CODEPOINT; /* adding ; */
            }
            break;

        case UCNV_PRV_ESCAPE_XML_HEX:
            while (i < length)
            {
                uniValueString[valueStringLength++] = (UChar) UNICODE_AMP_CODEPOINT;   /* adding & */
                uniValueString[valueStringLength++] = (UChar) UNICODE_HASH_CODEPOINT;  /* adding # */
                uniValueString[valueStringLength++] = (UChar) UNICODE_X_LOW_CODEPOINT; /* adding x */
                valueStringLength += uprv_itou (uniValueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint8_t)codeUnits[i++], 16, 0);
                uniValueString[valueStringLength++] = (UChar) UNICODE_SEMICOLON_CODEPOINT; /* adding ; */
            }
            break;
        case UCNV_PRV_ESCAPE_C:
            while (i < length)
            {
                uniValueString[valueStringLength++] = (UChar) UNICODE_RS_CODEPOINT;    /* adding \ */
                uniValueString[valueStringLength++] = (UChar) UNICODE_X_LOW_CODEPOINT; /* adding x */
                valueStringLength += uprv_itou (uniValueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint8_t)codeUnits[i++], 16, 2);
            }
            break;
        default:
            while (i < length)
            {
                uniValueString[valueStringLength++] = (UChar) UNICODE_PERCENT_SIGN_CODEPOINT; /* adding % */
                uniValueString[valueStringLength++] = (UChar) UNICODE_X_CODEPOINT;    /* adding X */
                uprv_itou (uniValueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint8_t) codeUnits[i++], 16, 2);
                valueStringLength += 2;
            }
        }
    }
    /* reset the error */
    *err = U_ZERO_ERROR;

    ucnv_cbToUWriteUChars(toArgs, uniValueString, valueStringLength, 0, err);
}

#endif

Coverage Report

Created: 2024-04-24 06:23

Line	Count	Source (jump to first uncovered line)
1		// © 2016 and later: Unicode, Inc. and others.
2		// License & terms of use: http://www.unicode.org/copyright.html
3		/*
4		*****************************************************************************
5		*
6		* Copyright (C) 1998-2016, International Business Machines
7		* Corporation and others. All Rights Reserved.
8		*
9		*****************************************************************************
10		*
11		* ucnv_err.c
12		* Implements error behaviour functions called by T_UConverter_{from,to}Unicode
13		*
14		*
15		* Change history:
16		*
17		* 06/29/2000 helena Major rewrite of the callback APIs.
18		*/
19
20		#include "unicode/utypes.h"
21
22		#if !UCONFIG_NO_CONVERSION
23
24		#include "unicode/ucnv_err.h"
25		#include "unicode/ucnv_cb.h"
26		#include "ucnv_cnv.h"
27		#include "cmemory.h"
28		#include "unicode/ucnv.h"
29		#include "ustrfmt.h"
30
31	0	#define VALUE_STRING_LENGTH 48
32		/Magic # 32 = 4(number of char in value string) 8(max number of bytes per char for any converter) */
33	0	#define UNICODE_PERCENT_SIGN_CODEPOINT 0x0025
34	0	#define UNICODE_U_CODEPOINT 0x0055
35	0	#define UNICODE_X_CODEPOINT 0x0058
36	0	#define UNICODE_RS_CODEPOINT 0x005C
37	0	#define UNICODE_U_LOW_CODEPOINT 0x0075
38	0	#define UNICODE_X_LOW_CODEPOINT 0x0078
39	0	#define UNICODE_AMP_CODEPOINT 0x0026
40	0	#define UNICODE_HASH_CODEPOINT 0x0023
41	0	#define UNICODE_SEMICOLON_CODEPOINT 0x003B
42	0	#define UNICODE_PLUS_CODEPOINT 0x002B
43	0	#define UNICODE_LEFT_CURLY_CODEPOINT 0x007B
44	0	#define UNICODE_RIGHT_CURLY_CODEPOINT 0x007D
45	0	#define UNICODE_SPACE_CODEPOINT 0x0020
46		#define UCNV_PRV_ESCAPE_ICU 0
47	0	#define UCNV_PRV_ESCAPE_C 'C'
48	0	#define UCNV_PRV_ESCAPE_XML_DEC 'D'
49	0	#define UCNV_PRV_ESCAPE_XML_HEX 'X'
50	0	#define UCNV_PRV_ESCAPE_JAVA 'J'
51	0	#define UCNV_PRV_ESCAPE_UNICODE 'U'
52	0	#define UCNV_PRV_ESCAPE_CSS2 'S'
53	0	#define UCNV_PRV_STOP_ON_ILLEGAL 'i'
54
55		/*
56		* IS_DEFAULT_IGNORABLE_CODE_POINT
57		* This is to check if a code point has the default ignorable unicode property.
58		* As such, this list needs to be updated if the ignorable code point list ever
59		* changes.
60		* To avoid dependency on other code, this list is hard coded here.
61		* When an ignorable code point is found and is unmappable, the default callbacks
62		* will ignore them.
63		* For a list of the default ignorable code points, use this link:
64		* https://util.unicode.org/UnicodeJsps/list-unicodeset.jsp?a=%5B%3ADI%3A%5D&abb=on&g=&i=
65		*
66		* This list should be sync with the one in CharsetCallback.java
67		*/
68	0	#define IS_DEFAULT_IGNORABLE_CODE_POINT(c) ( \
69	0	(c == 0x00AD) \|\| \
70	0	(c == 0x034F) \|\| \
71	0	(c == 0x061C) \|\| \
72	0	(c == 0x115F) \|\| \
73	0	(c == 0x1160) \|\| \
74	0	(0x17B4 <= c && c <= 0x17B5) \|\| \
75	0	(0x180B <= c && c <= 0x180F) \|\| \
76	0	(0x200B <= c && c <= 0x200F) \|\| \
77	0	(0x202A <= c && c <= 0x202E) \|\| \
78	0	(0x2060 <= c && c <= 0x206F) \|\| \
79	0	(c == 0x3164) \|\| \
80	0	(0xFE00 <= c && c <= 0xFE0F) \|\| \
81	0	(c == 0xFEFF) \|\| \
82	0	(c == 0xFFA0) \|\| \
83	0	(0xFFF0 <= c && c <= 0xFFF8) \|\| \
84	0	(0x1BCA0 <= c && c <= 0x1BCA3) \|\| \
85	0	(0x1D173 <= c && c <= 0x1D17A) \|\| \
86	0	(0xE0000 <= c && c <= 0xE0FFF))
87
88
89		/Function Pointer STOPS at the ILLEGAL_SEQUENCE /
90		U_CAPI void U_EXPORT2
91		UCNV_FROM_U_CALLBACK_STOP (
92		const void *context,
93		UConverterFromUnicodeArgs *fromUArgs,
94		const UChar* codeUnits,
95		int32_t length,
96		UChar32 codePoint,
97		UConverterCallbackReason reason,
98		UErrorCode * err)
99	0	{
100	0	(void)context;
101	0	(void)fromUArgs;
102	0	(void)codeUnits;
103	0	(void)length;
104	0	if (reason == UCNV_UNASSIGNED && IS_DEFAULT_IGNORABLE_CODE_POINT(codePoint))
105	0	{
106		/*
107		* Skip if the codepoint has unicode property of default ignorable.
108		*/
109	0	*err = U_ZERO_ERROR;
110	0	}
111		/* the caller must have set the error code accordingly */
112	0	return;
113	0	}
114
115
116		/Function Pointer STOPS at the ILLEGAL_SEQUENCE /
117		U_CAPI void U_EXPORT2
118		UCNV_TO_U_CALLBACK_STOP (
119		const void *context,
120		UConverterToUnicodeArgs *toUArgs,
121		const char* codePoints,
122		int32_t length,
123		UConverterCallbackReason reason,
124		UErrorCode * err)
125	0	{
126		/* the caller must have set the error code accordingly */
127	0	(void)context; (void)toUArgs; (void)codePoints; (void)length; (void)reason; (void)err;
128	0	return;
129	0	}
130
131		U_CAPI void U_EXPORT2
132		UCNV_FROM_U_CALLBACK_SKIP (
133		const void *context,
134		UConverterFromUnicodeArgs *fromUArgs,
135		const UChar* codeUnits,
136		int32_t length,
137		UChar32 codePoint,
138		UConverterCallbackReason reason,
139		UErrorCode * err)
140	0	{
141	0	(void)fromUArgs;
142	0	(void)codeUnits;
143	0	(void)length;
144	0	if (reason <= UCNV_IRREGULAR)
145	0	{
146	0	if (reason == UCNV_UNASSIGNED && IS_DEFAULT_IGNORABLE_CODE_POINT(codePoint))
147	0	{
148		/*
149		* Skip if the codepoint has unicode property of default ignorable.
150		*/
151	0	*err = U_ZERO_ERROR;
152	0	}
153	0	else if (context == NULL \|\| (((char)context) == UCNV_PRV_STOP_ON_ILLEGAL && reason == UCNV_UNASSIGNED))
154	0	{
155	0	*err = U_ZERO_ERROR;
156	0	}
157		/* else the caller must have set the error code accordingly. */
158	0	}
159		/* else ignore the reset, close and clone calls. */
160	0	}
161
162		U_CAPI void U_EXPORT2
163		UCNV_FROM_U_CALLBACK_SUBSTITUTE (
164		const void *context,
165		UConverterFromUnicodeArgs *fromArgs,
166		const UChar* codeUnits,
167		int32_t length,
168		UChar32 codePoint,
169		UConverterCallbackReason reason,
170		UErrorCode * err)
171	0	{
172	0	(void)codeUnits;
173	0	(void)length;
174	0	if (reason <= UCNV_IRREGULAR)
175	0	{
176	0	if (reason == UCNV_UNASSIGNED && IS_DEFAULT_IGNORABLE_CODE_POINT(codePoint))
177	0	{
178		/*
179		* Skip if the codepoint has unicode property of default ignorable.
180		*/
181	0	*err = U_ZERO_ERROR;
182	0	}
183	0	else if (context == NULL \|\| (((char)context) == UCNV_PRV_STOP_ON_ILLEGAL && reason == UCNV_UNASSIGNED))
184	0	{
185	0	*err = U_ZERO_ERROR;
186	0	ucnv_cbFromUWriteSub(fromArgs, 0, err);
187	0	}
188		/* else the caller must have set the error code accordingly. */
189	0	}
190		/* else ignore the reset, close and clone calls. */
191	0	}
192
193		/*uses uprv_itou to get a unicode escape sequence of the offensive sequence,
194		*uses a clean copy (resetted) of the converter, to convert that unicode
195		*escape sequence to the target codepage (if conversion failure happens then
196		*we revert to substituting with subchar)
197		*/
198		U_CAPI void U_EXPORT2
199		UCNV_FROM_U_CALLBACK_ESCAPE (
200		const void *context,
201		UConverterFromUnicodeArgs *fromArgs,
202		const UChar *codeUnits,
203		int32_t length,
204		UChar32 codePoint,
205		UConverterCallbackReason reason,
206		UErrorCode * err)
207	0	{
208
209	0	UChar valueString[VALUE_STRING_LENGTH];
210	0	int32_t valueStringLength = 0;
211	0	int32_t i = 0;
212
213	0	const UChar *myValueSource = NULL;
214	0	UErrorCode err2 = U_ZERO_ERROR;
215	0	UConverterFromUCallback original = NULL;
216	0	const void *originalContext;
217
218	0	UConverterFromUCallback ignoredCallback = NULL;
219	0	const void *ignoredContext;
220
221	0	if (reason > UCNV_IRREGULAR)
222	0	{
223	0	return;
224	0	}
225	0	else if (reason == UCNV_UNASSIGNED && IS_DEFAULT_IGNORABLE_CODE_POINT(codePoint))
226	0	{
227		/*
228		* Skip if the codepoint has unicode property of default ignorable.
229		*/
230	0	*err = U_ZERO_ERROR;
231	0	return;
232	0	}
233
234	0	ucnv_setFromUCallBack (fromArgs->converter,
235	0	(UConverterFromUCallback) UCNV_FROM_U_CALLBACK_SUBSTITUTE,
236	0	NULL,
237	0	&original,
238	0	&originalContext,
239	0	&err2);
240
241	0	if (U_FAILURE (err2))
242	0	{
243	0	*err = err2;
244	0	return;
245	0	}
246	0	if(context==NULL)
247	0	{
248	0	while (i < length)
249	0	{
250	0	valueString[valueStringLength++] = (UChar) UNICODE_PERCENT_SIGN_CODEPOINT; /* adding % */
251	0	valueString[valueStringLength++] = (UChar) UNICODE_U_CODEPOINT; /* adding U */
252	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[i++], 16, 4);
253	0	}
254	0	}
255	0	else
256	0	{
257	0	switch(((char)context))
258	0	{
259	0	case UCNV_PRV_ESCAPE_JAVA:
260	0	while (i < length)
261	0	{
262	0	valueString[valueStringLength++] = (UChar) UNICODE_RS_CODEPOINT; /* adding \ */
263	0	valueString[valueStringLength++] = (UChar) UNICODE_U_LOW_CODEPOINT; /* adding u */
264	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[i++], 16, 4);
265	0	}
266	0	break;
267
268	0	case UCNV_PRV_ESCAPE_C:
269	0	valueString[valueStringLength++] = (UChar) UNICODE_RS_CODEPOINT; /* adding \ */
270
271	0	if(length==2){
272	0	valueString[valueStringLength++] = (UChar) UNICODE_U_CODEPOINT; /* adding U */
273	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, codePoint, 16, 8);
274
275	0	}
276	0	else{
277	0	valueString[valueStringLength++] = (UChar) UNICODE_U_LOW_CODEPOINT; /* adding u */
278	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[0], 16, 4);
279	0	}
280	0	break;
281
282	0	case UCNV_PRV_ESCAPE_XML_DEC:
283
284	0	valueString[valueStringLength++] = (UChar) UNICODE_AMP_CODEPOINT; /* adding & */
285	0	valueString[valueStringLength++] = (UChar) UNICODE_HASH_CODEPOINT; /* adding # */
286	0	if(length==2){
287	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, codePoint, 10, 0);
288	0	}
289	0	else{
290	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[0], 10, 0);
291	0	}
292	0	valueString[valueStringLength++] = (UChar) UNICODE_SEMICOLON_CODEPOINT; /* adding ; */
293	0	break;
294
295	0	case UCNV_PRV_ESCAPE_XML_HEX:
296
297	0	valueString[valueStringLength++] = (UChar) UNICODE_AMP_CODEPOINT; /* adding & */
298	0	valueString[valueStringLength++] = (UChar) UNICODE_HASH_CODEPOINT; /* adding # */
299	0	valueString[valueStringLength++] = (UChar) UNICODE_X_LOW_CODEPOINT; /* adding x */
300	0	if(length==2){
301	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, codePoint, 16, 0);
302	0	}
303	0	else{
304	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[0], 16, 0);
305	0	}
306	0	valueString[valueStringLength++] = (UChar) UNICODE_SEMICOLON_CODEPOINT; /* adding ; */
307	0	break;
308
309	0	case UCNV_PRV_ESCAPE_UNICODE:
310	0	valueString[valueStringLength++] = (UChar) UNICODE_LEFT_CURLY_CODEPOINT; /* adding { */
311	0	valueString[valueStringLength++] = (UChar) UNICODE_U_CODEPOINT; /* adding U */
312	0	valueString[valueStringLength++] = (UChar) UNICODE_PLUS_CODEPOINT; /* adding + */
313	0	if (length == 2) {
314	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, codePoint, 16, 4);
315	0	} else {
316	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[0], 16, 4);
317	0	}
318	0	valueString[valueStringLength++] = (UChar) UNICODE_RIGHT_CURLY_CODEPOINT; /* adding } */
319	0	break;
320
321	0	case UCNV_PRV_ESCAPE_CSS2:
322	0	valueString[valueStringLength++] = (UChar) UNICODE_RS_CODEPOINT; /* adding \ */
323	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, codePoint, 16, 0);
324		/* Always add space character, because the next character might be whitespace,
325		which would erroneously be considered the termination of the escape sequence. */
326	0	valueString[valueStringLength++] = (UChar) UNICODE_SPACE_CODEPOINT;
327	0	break;
328
329	0	default:
330	0	while (i < length)
331	0	{
332	0	valueString[valueStringLength++] = (UChar) UNICODE_PERCENT_SIGN_CODEPOINT; /* adding % */
333	0	valueString[valueStringLength++] = (UChar) UNICODE_U_CODEPOINT; /* adding U */
334	0	valueStringLength += uprv_itou (valueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint16_t)codeUnits[i++], 16, 4);
335	0	}
336	0	}
337	0	}
338	0	myValueSource = valueString;
339
340		/* reset the error */
341	0	*err = U_ZERO_ERROR;
342
343	0	ucnv_cbFromUWriteUChars(fromArgs, &myValueSource, myValueSource+valueStringLength, 0, err);
344
345	0	ucnv_setFromUCallBack (fromArgs->converter,
346	0	original,
347	0	originalContext,
348	0	&ignoredCallback,
349	0	&ignoredContext,
350	0	&err2);
351	0	if (U_FAILURE (err2))
352	0	{
353	0	*err = err2;
354	0	return;
355	0	}
356
357	0	return;
358	0	}
359
360
361
362		U_CAPI void U_EXPORT2
363		UCNV_TO_U_CALLBACK_SKIP (
364		const void *context,
365		UConverterToUnicodeArgs *toArgs,
366		const char* codeUnits,
367		int32_t length,
368		UConverterCallbackReason reason,
369		UErrorCode * err)
370	0	{
371	0	(void)toArgs;
372	0	(void)codeUnits;
373	0	(void)length;
374	0	if (reason <= UCNV_IRREGULAR)
375	0	{
376	0	if (context == NULL \|\| (((char)context) == UCNV_PRV_STOP_ON_ILLEGAL && reason == UCNV_UNASSIGNED))
377	0	{
378	0	*err = U_ZERO_ERROR;
379	0	}
380		/* else the caller must have set the error code accordingly. */
381	0	}
382		/* else ignore the reset, close and clone calls. */
383	0	}
384
385		U_CAPI void U_EXPORT2
386		UCNV_TO_U_CALLBACK_SUBSTITUTE (
387		const void *context,
388		UConverterToUnicodeArgs *toArgs,
389		const char* codeUnits,
390		int32_t length,
391		UConverterCallbackReason reason,
392		UErrorCode * err)
393	0	{
394	0	(void)codeUnits;
395	0	(void)length;
396	0	if (reason <= UCNV_IRREGULAR)
397	0	{
398	0	if (context == NULL \|\| (((char)context) == UCNV_PRV_STOP_ON_ILLEGAL && reason == UCNV_UNASSIGNED))
399	0	{
400	0	*err = U_ZERO_ERROR;
401	0	ucnv_cbToUWriteSub(toArgs,0,err);
402	0	}
403		/* else the caller must have set the error code accordingly. */
404	0	}
405		/* else ignore the reset, close and clone calls. */
406	0	}
407
408		/*uses uprv_itou to get a unicode escape sequence of the offensive sequence,
409		*and uses that as the substitution sequence
410		*/
411		U_CAPI void U_EXPORT2
412		UCNV_TO_U_CALLBACK_ESCAPE (
413		const void *context,
414		UConverterToUnicodeArgs *toArgs,
415		const char* codeUnits,
416		int32_t length,
417		UConverterCallbackReason reason,
418		UErrorCode * err)
419	0	{
420	0	UChar uniValueString[VALUE_STRING_LENGTH];
421	0	int32_t valueStringLength = 0;
422	0	int32_t i = 0;
423
424	0	if (reason > UCNV_IRREGULAR)
425	0	{
426	0	return;
427	0	}
428
429	0	if(context==NULL)
430	0	{
431	0	while (i < length)
432	0	{
433	0	uniValueString[valueStringLength++] = (UChar) UNICODE_PERCENT_SIGN_CODEPOINT; /* adding % */
434	0	uniValueString[valueStringLength++] = (UChar) UNICODE_X_CODEPOINT; /* adding X */
435	0	valueStringLength += uprv_itou (uniValueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint8_t) codeUnits[i++], 16, 2);
436	0	}
437	0	}
438	0	else
439	0	{
440	0	switch(((char)context))
441	0	{
442	0	case UCNV_PRV_ESCAPE_XML_DEC:
443	0	while (i < length)
444	0	{
445	0	uniValueString[valueStringLength++] = (UChar) UNICODE_AMP_CODEPOINT; /* adding & */
446	0	uniValueString[valueStringLength++] = (UChar) UNICODE_HASH_CODEPOINT; /* adding # */
447	0	valueStringLength += uprv_itou (uniValueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint8_t)codeUnits[i++], 10, 0);
448	0	uniValueString[valueStringLength++] = (UChar) UNICODE_SEMICOLON_CODEPOINT; /* adding ; */
449	0	}
450	0	break;
451
452	0	case UCNV_PRV_ESCAPE_XML_HEX:
453	0	while (i < length)
454	0	{
455	0	uniValueString[valueStringLength++] = (UChar) UNICODE_AMP_CODEPOINT; /* adding & */
456	0	uniValueString[valueStringLength++] = (UChar) UNICODE_HASH_CODEPOINT; /* adding # */
457	0	uniValueString[valueStringLength++] = (UChar) UNICODE_X_LOW_CODEPOINT; /* adding x */
458	0	valueStringLength += uprv_itou (uniValueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint8_t)codeUnits[i++], 16, 0);
459	0	uniValueString[valueStringLength++] = (UChar) UNICODE_SEMICOLON_CODEPOINT; /* adding ; */
460	0	}
461	0	break;
462	0	case UCNV_PRV_ESCAPE_C:
463	0	while (i < length)
464	0	{
465	0	uniValueString[valueStringLength++] = (UChar) UNICODE_RS_CODEPOINT; /* adding \ */
466	0	uniValueString[valueStringLength++] = (UChar) UNICODE_X_LOW_CODEPOINT; /* adding x */
467	0	valueStringLength += uprv_itou (uniValueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint8_t)codeUnits[i++], 16, 2);
468	0	}
469	0	break;
470	0	default:
471	0	while (i < length)
472	0	{
473	0	uniValueString[valueStringLength++] = (UChar) UNICODE_PERCENT_SIGN_CODEPOINT; /* adding % */
474	0	uniValueString[valueStringLength++] = (UChar) UNICODE_X_CODEPOINT; /* adding X */
475	0	uprv_itou (uniValueString + valueStringLength, VALUE_STRING_LENGTH - valueStringLength, (uint8_t) codeUnits[i++], 16, 2);
476	0	valueStringLength += 2;
477	0	}
478	0	}
479	0	}
480		/* reset the error */
481	0	*err = U_ZERO_ERROR;
482
483	0	ucnv_cbToUWriteUChars(toArgs, uniValueString, valueStringLength, 0, err);
484	0	}
485
486		#endif