/// <summary>
/// Construct a matcher that matches a substring of the given
/// pattern string.
/// </summary>
/// <param name="theString">The pattern to be matched, possibly containing
/// stand-ins that represent nested <see cref="IUnicodeMatcher"/> objects.</param>
/// <param name="start">First character of <paramref name="theString"/> to be matched.</param>
/// <param name="limit">Index after the last character of <paramref name="theString"/> to be matched.</param>
/// <param name="segmentNum">The segment number from 1..n, or 0 if this is not a segment.</param>
/// <param name="theData">context object mapping stand-ins to <see cref="IUnicodeMatcher"/> objects.</param>
public StringMatcher(string theString,
int start,
int limit,
int segmentNum,
RuleBasedTransliterator.Data theData)
: this(theString.Substring(start, limit - start), segmentNum, theData) // ICU4N: Corrected 2nd substring parameter
{
}
/// <summary>
/// Construct a matcher that matches the given pattern string.
/// </summary>
/// <param name="theString">The pattern to be matched, possibly containing
/// stand-ins that represent nested <see cref="IUnicodeMatcher"/> objects.</param>
/// <param name="segmentNum">The segment number from 1..n, or 0 if this is
/// not a segment.</param>
/// <param name="theData">Context object mapping stand-ins to <see cref="IUnicodeMatcher"/> objects.</param>
public StringMatcher(string theString,
int segmentNum,
RuleBasedTransliterator.Data theData)
{
data = theData;
pattern = theString;
matchStart = matchLimit = -1;
segmentNumber = segmentNum;
}
/// <summary>
/// Construct a <see cref="StringReplacer"/> that sets the emits the given output
/// text and does not modify the cursor.
/// </summary>
/// <param name="theOutput">Text that will replace input text when the
/// <see cref="Replace(IReplaceable, int, int, out int[])"/> method is called.
/// May contain stand-in characters that represent nested replacers.</param>
/// <param name="theData">Transliterator context object that translates
/// stand-in characters to <see cref="IUnicodeReplacer"/> objects.</param>
public StringReplacer(string theOutput,
RuleBasedTransliterator.Data theData)
{
output = theOutput;
cursorPos = 0;
hasCursor = false;
data = theData;
isComplex = true;
}
/// <summary>
/// Construct a matcher that matches a substring of the given
/// pattern string.
/// </summary>
/// <param name="theString">The pattern to be matched, possibly containing
/// stand-ins that represent nested <see cref="IUnicodeMatcher"/> objects.</param>
/// <param name="start">First character of <paramref name="theString"/> to be matched.</param>
/// <param name="limit">Index after the last character of <paramref name="theString"/> to be matched.</param>
/// <param name="segmentNum">The segment number from 1..n, or 0 if this is not a segment.</param>
/// <param name="theData">context object mapping stand-ins to <see cref="IUnicodeMatcher"/> objects.</param>
public StringMatcher(string theString,
int start,
int limit,
int segmentNum,
#pragma warning disable 612, 618
RuleBasedTransliterator.Data theData)
#pragma warning restore 612, 618
: this(theString.Substring(start, limit - start), segmentNum, theData) // ICU4N: Corrected 2nd substring parameter
{
}
/// <summary>
/// Construct a <see cref="StringReplacer"/> that sets the emits the given output
/// text and does not modify the cursor.
/// </summary>
/// <param name="theOutput">Text that will replace input text when the
/// <see cref="Replace(IReplaceable, int, int, int[])"/> method is called.
/// May contain stand-in characters that represent nested replacers.</param>
/// <param name="theData">Transliterator context object that translates
/// stand-in characters to <see cref="IUnicodeReplacer"/> objects.</param>
public StringReplacer(string theOutput,
#pragma warning disable 612, 618
RuleBasedTransliterator.Data theData)
#pragma warning restore 612, 618
{
output = theOutput;
cursorPos = 0;
hasCursor = false;
data = theData;
isComplex = true;
}
#pragma warning restore 612, 618
/// <summary>
/// Construct a matcher that matches the given pattern string.
/// </summary>
/// <param name="theString">The pattern to be matched, possibly containing
/// stand-ins that represent nested <see cref="IUnicodeMatcher"/> objects.</param>
/// <param name="segmentNum">The segment number from 1..n, or 0 if this is
/// not a segment.</param>
/// <param name="theData">Context object mapping stand-ins to <see cref="IUnicodeMatcher"/> objects.</param>
public StringMatcher(string theString,
int segmentNum,
#pragma warning disable 612, 618
RuleBasedTransliterator.Data theData)
#pragma warning restore 612, 618
{
data = theData;
pattern = theString;
matchStart = matchLimit = -1;
segmentNumber = segmentNum;
}
#pragma warning restore 612, 618
/**
* Construct a new rule with the given input, output text, and other
* attributes. A cursor position may be specified for the output text.
* @param input input string, including key and optional ante and
* post context
* @param anteContextPos offset into input to end of ante context, or -1 if
* none. Must be <= input.length() if not -1.
* @param postContextPos offset into input to start of post context, or -1
* if none. Must be <= input.length() if not -1, and must be >=
* anteContextPos.
* @param output output string
* @param cursorPos offset into output at which cursor is located, or -1 if
* none. If less than zero, then the cursor is placed after the
* <code>output</code>; that is, -1 is equivalent to
* <code>output.length()</code>. If greater than
* <code>output.length()</code> then an exception is thrown.
* @param cursorOffset an offset to be added to cursorPos to position the
* cursor either in the ante context, if < 0, or in the post context, if >
* 0. For example, the rule "abc{def} > | @@@ xyz;" changes "def" to
* "xyz" and moves the cursor to before "a". It would have a cursorOffset
* of -3.
* @param segs array of UnicodeMatcher corresponding to input pattern
* segments, or null if there are none
* @param anchorStart true if the the rule is anchored on the left to
* the context start
* @param anchorEnd true if the rule is anchored on the right to the
* context limit
*/
public TransliterationRule(string input,
int anteContextPos, int postContextPos,
string output,
int cursorPos, int cursorOffset,
IUnicodeMatcher[] segs,
bool anchorStart, bool anchorEnd,
#pragma warning disable 612, 618
RuleBasedTransliterator.Data theData)
#pragma warning restore 612, 618
{
data = theData;
// Do range checks only when warranted to save time
if (anteContextPos < 0)
{
anteContextLength = 0;
}
else
{
if (anteContextPos > input.Length)
{
throw new ArgumentException("Invalid ante context");
}
anteContextLength = anteContextPos;
}
if (postContextPos < 0)
{
keyLength = input.Length - anteContextLength;
}
else
{
if (postContextPos < anteContextLength ||
postContextPos > input.Length)
{
throw new ArgumentException("Invalid post context");
}
keyLength = postContextPos - anteContextLength;
}
if (cursorPos < 0)
{
cursorPos = output.Length;
}
else if (cursorPos > output.Length)
{
throw new ArgumentException("Invalid cursor position");
}
// We don't validate the segments array. The caller must
// guarantee that the segments are well-formed (that is, that
// all $n references in the output refer to indices of this
// array, and that no array elements are null).
this.segments = segs;
pattern = input;
flags = 0;
if (anchorStart)
{
flags |= (byte)ANCHOR_START;
}
if (anchorEnd)
{
flags |= (byte)ANCHOR_END;
}
anteContext = null;
if (anteContextLength > 0)
{
anteContext = new StringMatcher(pattern.Substring(0, anteContextLength), // ICU4N: Checked 2nd parameter
0, data);
}
key = null;
if (keyLength > 0)
{
key = new StringMatcher(pattern.Substring(anteContextLength, keyLength), // ICU4N: (anteContextLength + keyLength) - anteContextLength == keyLength
0, data);
}
int postContextLength = pattern.Length - keyLength - anteContextLength;
postContext = null;
if (postContextLength > 0)
{
postContext = new StringMatcher(pattern.Substring(anteContextLength + keyLength),
0, data);
}
this.output = new StringReplacer(output, cursorPos + cursorOffset, data);
}