/src/mozilla-central/intl/icu/source/common/ustr_imp.h

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) 1999-2015, International Business Machines
*   Corporation and others.  All Rights Reserved.
**********************************************************************
*   file name:  ustr_imp.h
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2001jan30
*   created by: Markus W. Scherer
*/

#ifndef __USTR_IMP_H__
#define __USTR_IMP_H__

#include "unicode/utypes.h"
#include "unicode/utf8.h"

/**
 * Internal option for unorm_cmpEquivFold() for strncmp style.
 * If set, checks for both string length and terminating NUL.
 */
#define _STRNCMP_STYLE 0x1000

/**
 * Compare two strings in code point order or code unit order.
 * Works in strcmp style (both lengths -1),
 * strncmp style (lengths equal and >=0, flag TRUE),
 * and memcmp/UnicodeString style (at least one length >=0).
 */
U_CFUNC int32_t U_EXPORT2
uprv_strCompare(const UChar *s1, int32_t length1,
                const UChar *s2, int32_t length2,
                UBool strncmpStyle, UBool codePointOrder);

U_CAPI int32_t U_EXPORT2 
ustr_hashUCharsN(const UChar *str, int32_t length);

U_CAPI int32_t U_EXPORT2 
ustr_hashCharsN(const char *str, int32_t length);

U_CAPI int32_t U_EXPORT2
ustr_hashICharsN(const char *str, int32_t length);

/**
 * NUL-terminate a UChar * string if possible.
 * If length  < destCapacity then NUL-terminate.
 * If length == destCapacity then do not terminate but set U_STRING_NOT_TERMINATED_WARNING.
 * If length  > destCapacity then do not terminate but set U_BUFFER_OVERFLOW_ERROR.
 *
 * @param dest Destination buffer, can be NULL if destCapacity==0.
 * @param destCapacity Number of UChars available at dest.
 * @param length Number of UChars that were (to be) written to dest.
 * @param pErrorCode ICU error code.
 * @return length
 */
U_CAPI int32_t U_EXPORT2
u_terminateUChars(UChar *dest, int32_t destCapacity, int32_t length, UErrorCode *pErrorCode);

/**
 * NUL-terminate a char * string if possible.
 * Same as u_terminateUChars() but for a different string type.
 */
U_CAPI int32_t U_EXPORT2
u_terminateChars(char *dest, int32_t destCapacity, int32_t length, UErrorCode *pErrorCode);

/**
 * NUL-terminate a UChar32 * string if possible.
 * Same as u_terminateUChars() but for a different string type.
 */
U_CAPI int32_t U_EXPORT2
u_terminateUChar32s(UChar32 *dest, int32_t destCapacity, int32_t length, UErrorCode *pErrorCode);

/**
 * NUL-terminate a wchar_t * string if possible.
 * Same as u_terminateUChars() but for a different string type.
 */
U_CAPI int32_t U_EXPORT2
u_terminateWChars(wchar_t *dest, int32_t destCapacity, int32_t length, UErrorCode *pErrorCode);

/**
 * Counts the bytes of any whole valid sequence for a UTF-8 lead byte.
 * Returns 1 for ASCII 0..0x7f.
 * Returns 0 for 0x80..0xc1 as well as for 0xf5..0xff.
 * leadByte might be evaluated multiple times.
 *
 * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff.
 * @return 0..4
 */
#define U8_COUNT_BYTES(leadByte) \
    (U8_IS_SINGLE(leadByte) ? 1 : U8_COUNT_BYTES_NON_ASCII(leadByte))

/**
 * Counts the bytes of any whole valid sequence for a UTF-8 lead byte.
 * Returns 0 for 0x00..0xc1 as well as for 0xf5..0xff.
 * leadByte might be evaluated multiple times.
 *
 * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff.
 * @return 0 or 2..4
 */
#define U8_COUNT_BYTES_NON_ASCII(leadByte) \
    (U8_IS_LEAD(leadByte) ? ((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)+2 : 0)

#ifdef __cplusplus

U_NAMESPACE_BEGIN

class UTF8 {
public:
    UTF8() = delete;  // all static

    /**
     * Is t a valid UTF-8 trail byte?
     *
     * @param prev Must be the preceding lead byte if i==1 and length>=3;
     *             otherwise ignored.
     * @param t The i-th byte following the lead byte.
     * @param i The index (1..3) of byte t in the byte sequence. 0<i<length
     * @param length The length (2..4) of the byte sequence according to the lead byte.
     * @return TRUE if t is a valid trail byte in this context.
     */
    static inline UBool isValidTrail(int32_t prev, uint8_t t, int32_t i, int32_t length) {
        // The first trail byte after a 3- or 4-byte lead byte
        // needs to be validated together with its lead byte.
        if (length <= 2 || i > 1) {
            return U8_IS_TRAIL(t);
        } else if (length == 3) {
            return U8_IS_VALID_LEAD3_AND_T1(prev, t);
        } else {  // length == 4
            return U8_IS_VALID_LEAD4_AND_T1(prev, t);
        }
    }
};

U_NAMESPACE_END

#endif  // __cplusplus

#endif

Coverage Report

Created: 2018-09-25 14:53

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		* Copyright (C) 1999-2015, International Business Machines
6		* Corporation and others. All Rights Reserved.
7		**********************************************************************
8		* file name: ustr_imp.h
9		* encoding: UTF-8
10		* tab size: 8 (not used)
11		* indentation:4
12		*
13		* created on: 2001jan30
14		* created by: Markus W. Scherer
15		*/
16
17		#ifndef __USTR_IMP_H__
18		#define __USTR_IMP_H__
19
20		#include "unicode/utypes.h"
21		#include "unicode/utf8.h"
22
23		/**
24		* Internal option for unorm_cmpEquivFold() for strncmp style.
25		* If set, checks for both string length and terminating NUL.
26		*/
27	0	#define _STRNCMP_STYLE 0x1000
28
29		/**
30		* Compare two strings in code point order or code unit order.
31		* Works in strcmp style (both lengths -1),
32		* strncmp style (lengths equal and >=0, flag TRUE),
33		* and memcmp/UnicodeString style (at least one length >=0).
34		*/
35		U_CFUNC int32_t U_EXPORT2
36		uprv_strCompare(const UChar *s1, int32_t length1,
37		const UChar *s2, int32_t length2,
38		UBool strncmpStyle, UBool codePointOrder);
39
40		U_CAPI int32_t U_EXPORT2
41		ustr_hashUCharsN(const UChar *str, int32_t length);
42
43		U_CAPI int32_t U_EXPORT2
44		ustr_hashCharsN(const char *str, int32_t length);
45
46		U_CAPI int32_t U_EXPORT2
47		ustr_hashICharsN(const char *str, int32_t length);
48
49		/**
50		* NUL-terminate a UChar * string if possible.
51		* If length < destCapacity then NUL-terminate.
52		* If length == destCapacity then do not terminate but set U_STRING_NOT_TERMINATED_WARNING.
53		* If length > destCapacity then do not terminate but set U_BUFFER_OVERFLOW_ERROR.
54		*
55		* @param dest Destination buffer, can be NULL if destCapacity==0.
56		* @param destCapacity Number of UChars available at dest.
57		* @param length Number of UChars that were (to be) written to dest.
58		* @param pErrorCode ICU error code.
59		* @return length
60		*/
61		U_CAPI int32_t U_EXPORT2
62		u_terminateUChars(UChar dest, int32_t destCapacity, int32_t length, UErrorCode pErrorCode);
63
64		/**
65		* NUL-terminate a char * string if possible.
66		* Same as u_terminateUChars() but for a different string type.
67		*/
68		U_CAPI int32_t U_EXPORT2
69		u_terminateChars(char dest, int32_t destCapacity, int32_t length, UErrorCode pErrorCode);
70
71		/**
72		* NUL-terminate a UChar32 * string if possible.
73		* Same as u_terminateUChars() but for a different string type.
74		*/
75		U_CAPI int32_t U_EXPORT2
76		u_terminateUChar32s(UChar32 dest, int32_t destCapacity, int32_t length, UErrorCode pErrorCode);
77
78		/**
79		* NUL-terminate a wchar_t * string if possible.
80		* Same as u_terminateUChars() but for a different string type.
81		*/
82		U_CAPI int32_t U_EXPORT2
83		u_terminateWChars(wchar_t dest, int32_t destCapacity, int32_t length, UErrorCode pErrorCode);
84
85		/**
86		* Counts the bytes of any whole valid sequence for a UTF-8 lead byte.
87		* Returns 1 for ASCII 0..0x7f.
88		* Returns 0 for 0x80..0xc1 as well as for 0xf5..0xff.
89		* leadByte might be evaluated multiple times.
90		*
91		* @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff.
92		* @return 0..4
93		*/
94		#define U8_COUNT_BYTES(leadByte) \
95	0	(U8_IS_SINGLE(leadByte) ? 1 : U8_COUNT_BYTES_NON_ASCII(leadByte))
96
97		/**
98		* Counts the bytes of any whole valid sequence for a UTF-8 lead byte.
99		* Returns 0 for 0x00..0xc1 as well as for 0xf5..0xff.
100		* leadByte might be evaluated multiple times.
101		*
102		* @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff.
103		* @return 0 or 2..4
104		*/
105		#define U8_COUNT_BYTES_NON_ASCII(leadByte) \
106	0	(U8_IS_LEAD(leadByte) ? ((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)+2 : 0)
107
108		#ifdef __cplusplus
109
110		U_NAMESPACE_BEGIN
111
112		class UTF8 {
113		public:
114		UTF8() = delete; // all static
115
116		/**
117		* Is t a valid UTF-8 trail byte?
118		*
119		* @param prev Must be the preceding lead byte if i==1 and length>=3;
120		* otherwise ignored.
121		* @param t The i-th byte following the lead byte.
122		* @param i The index (1..3) of byte t in the byte sequence. 0<i<length
123		* @param length The length (2..4) of the byte sequence according to the lead byte.
124		* @return TRUE if t is a valid trail byte in this context.
125		*/
126	0	static inline UBool isValidTrail(int32_t prev, uint8_t t, int32_t i, int32_t length) {
127	0	// The first trail byte after a 3- or 4-byte lead byte
128	0	// needs to be validated together with its lead byte.
129	0	if (length <= 2 \|\| i > 1) {
130	0	return U8_IS_TRAIL(t);
131	0	} else if (length == 3) {
132	0	return U8_IS_VALID_LEAD3_AND_T1(prev, t);
133	0	} else { // length == 4
134	0	return U8_IS_VALID_LEAD4_AND_T1(prev, t);
135	0	}
136	0	}
137		};
138
139		U_NAMESPACE_END
140
141		#endif // __cplusplus
142
143		#endif