1// © 2016 and later: Unicode, Inc. and others.
2// License & terms of use: http://www.unicode.org/copyright.html
3/*
4**********************************************************************
5* Copyright (C) 1999-2011, International Business Machines
6* Corporation and others. All Rights Reserved.
7**********************************************************************
8*
9* File USC_IMPL.H
10*
11* Modification History:
12*
13* Date Name Description
14* 07/08/2002 Eric Mader Creation.
15******************************************************************************
16*/
17
18#ifndef USC_IMPL_H
19#define USC_IMPL_H
20#include "unicode/utypes.h"
21#include "unicode/uscript.h"
22
23/**
24 * <code>UScriptRun</code> is used to find runs of characters in
25 * the same script. It implements a simple iterator over an array
26 * of characters. The iterator will resolve script-neutral characters
27 * like punctuation into the script of the surrounding characters.
28 *
29 * The iterator will try to match paired punctuation. If it sees an
30 * opening punctuation character, it will remember the script that
31 * was assigned to that character, and assign the same script to the
32 * matching closing punctuation.
33 *
34 * Scripts are chosen based on the <code>UScriptCode</code> enumeration.
35 * No attempt is made to combine related scripts into a single run. In
36 * particular, Hiragana, Katakana, and Han characters will appear in separate
37 * runs.
38
39 * Here is an example of how to iterate over script runs:
40 * <pre>
41 * \code
42 * void printScriptRuns(const UChar *text, int32_t length)
43 * {
44 * UErrorCode error = U_ZERO_ERROR;
45 * UScriptRun *scriptRun = uscript_openRun(text, testLength, &error);
46 * int32_t start = 0, limit = 0;
47 * UScriptCode code = USCRIPT_INVALID_CODE;
48 *
49 * while (uscript_nextRun(&start, &limit, &code)) {
50 * printf("Script '%s' from %d to %d.\n", uscript_getName(code), start, limit);
51 * }
52 *
53 * uscript_closeRun(scriptRun);
54 * }
55 * </pre>
56 */
57struct UScriptRun;
58
59typedef struct UScriptRun UScriptRun;
60
61/**
62 * Create a <code>UScriptRun</code> object for iterating over the given text. This object must
63 * be freed using <code>uscript_closeRun()</code>. Note that this object does not copy the source text,
64 * only the pointer to it. You must make sure that the pointer remains valid until you call
65 * <code>uscript_closeRun()</code> or <code>uscript_setRunText()</code>.
66 *
67 * @param src is the address of the array of characters over which to iterate.
68 * if <code>src == NULL</code> and <code>length == 0</code>,
69 * an empty <code>UScriptRun</code> object will be returned.
70 *
71 * @param length is the number of characters over which to iterate.
72 *
73 * @param pErrorCode is a pointer to a valid <code>UErrorCode</code> value. If this value
74 * indicates a failure on entry, the function will immediately return.
75 * On exit the value will indicate the success of the operation.
76 *
77 * @return the address of <code>UScriptRun</code> object which will iterate over the text,
78 * or <code>NULL</code> if the operation failed.
79 */
80U_CAPI UScriptRun * U_EXPORT2
81uscript_openRun(const UChar *src, int32_t length, UErrorCode *pErrorCode);
82
83/**
84 * Frees the given <code>UScriptRun</code> object and any storage associated with it.
85 * On return, scriptRun no longer points to a valid <code>UScriptRun</code> object.
86 *
87 * @param scriptRun is the <code>UScriptRun</code> object which will be freed.
88 */
89U_CAPI void U_EXPORT2
90uscript_closeRun(UScriptRun *scriptRun);
91
92/**
93 * Reset the <code>UScriptRun</code> object so that it will start iterating from
94 * the beginning.
95 *
96 * @param scriptRun is the address of the <code>UScriptRun</code> object to be reset.
97 */
98U_CAPI void U_EXPORT2
99uscript_resetRun(UScriptRun *scriptRun);
100
101/**
102 * Change the text over which the given <code>UScriptRun</code> object iterates.
103 *
104 * @param scriptRun is the <code>UScriptRun</code> object which will be changed.
105 *
106 * @param src is the address of the new array of characters over which to iterate.
107 * If <code>src == NULL</code> and <code>length == 0</code>,
108 * the <code>UScriptRun</code> object will become empty.
109 *
110 * @param length is the new number of characters over which to iterate
111 *
112 * @param pErrorCode is a pointer to a valid <code>UErrorCode</code> value. If this value
113 * indicates a failure on entry, the function will immediately return.
114 * On exit the value will indicate the success of the operation.
115 */
116U_CAPI void U_EXPORT2
117uscript_setRunText(UScriptRun *scriptRun, const UChar *src, int32_t length, UErrorCode *pErrorCode);
118
119/**
120 * Advance the <code>UScriptRun</code> object to the next script run, return the start and limit
121 * offsets, and the script of the run.
122 *
123 * @param scriptRun is the address of the <code>UScriptRun</code> object.
124 *
125 * @param pRunStart is a pointer to the variable to receive the starting offset of the next run.
126 * This pointer can be <code>NULL</code> if the value is not needed.
127 *
128 * @param pRunLimit is a pointer to the variable to receive the limit offset of the next run.
129 * This pointer can be <code>NULL</code> if the value is not needed.
130 *
131 * @param pRunScript is a pointer to the variable to receive the UScriptCode for the
132 * script of the current run. This pointer can be <code>NULL</code> if the value is not needed.
133 *
134 * @return true if there was another script run.
135 */
136U_CAPI UBool U_EXPORT2
137uscript_nextRun(UScriptRun *scriptRun, int32_t *pRunStart, int32_t *pRunLimit, UScriptCode *pRunScript);
138
139#endif
140