/// <summary>
/// Define SurrogatePairDictionary class
/// <a href="http://www.unicode.org/charts/PDF/UE000.pdf">Newline</a>
/// </summary>
public EudcProperty(UnicodeRangeDatabase unicodeDb, Collection<UnicodeRange> expectedRanges)
{
low = 0xE000; high = 0xF8FF;
bool isValid = false;
foreach (UnicodeRange range in expectedRanges)
{
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
eudcRangeList,
"Private Use",
GroupAttributes.GroupName))
{
isValid = true;
}
}
if(!isValid)
{
throw new ArgumentOutOfRangeException("expectedRanges", "EudcProperty, EUDC ranges are beyond expected range. " +
"Refer to Private Use range.");
}
foreach (UnicodeRangeProperty data in eudcRangeList)
{
if (data.Name.Equals("Private Use Area", StringComparison.OrdinalIgnoreCase))
{
low = data.Range.StartOfUnicodeRange;
high = data.Range.EndOfUnicodeRange;
break;
}
}
}
private static void InitializeAlphabetRangeList( )
{
bool isValid = false;
foreach (UnicodeRange range in ranges)
{
UnicodeRange newRange = RangePropertyCollector.GetRange(new UnicodeRange(0x0041, 0x005A), range);
if (null != newRange)
{
alphabetRangeList.Add(newRange);
isValid = true;
}
newRange = RangePropertyCollector.GetRange(new UnicodeRange(0x0061, 0x007A), range);
if (null != newRange)
{
alphabetRangeList.Add(newRange);
isValid = true;
}
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("StringFactory, Latin alphabet ranges for Combining mark property are beyond expected. " +
"Refer to Latin Alphabet range 0x0041 - 0x005A and 0x0061 - 0x007A." + "All " + ranges.Count + " UniCodeRange is in Latin alphabet range");
}
}
/// <summary>
/// Define CombiningMarksProperty class
/// <a href="http://www.unicode.org/charts/PDF/U0300.pdf">Newline</a>
/// <a href="http://www.unicode.org/charts/PDF/U1DC0.pdf">Newline</a>
/// <a href="http://www.unicode.org/charts/PDF/UFE20.pdf">Newline</a>
/// </summary>
public CombiningMarksProperty(UnicodeRangeDatabase unicodeDb, Collection <UnicodeRange> expectedRanges)
{
bool isValid = false;
foreach (UnicodeRange range in expectedRanges)
{
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
combiningMarksPropertyRangeList,
"Combining Diacritics",
GroupAttributes.GroupName))
{
isValid = true;
}
}
if (InitializeCombiningMarksDictionary(expectedRanges))
{
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("expectedRanges", "CombiningMarksProperty, Combining mark ranges are beyond expected range. " +
"Refer to Combining Diacritics range.");
}
}
/// <summary>
/// Define CombiningMarksProperty class
/// <a href="http://www.unicode.org/charts/PDF/U0300.pdf">Newline</a>
/// <a href="http://www.unicode.org/charts/PDF/U1DC0.pdf">Newline</a>
/// <a href="http://www.unicode.org/charts/PDF/UFE20.pdf">Newline</a>
/// </summary>
public CombiningMarksProperty(UnicodeRangeDatabase unicodeDb, UnicodeRange expectedRange)
{
bool isValid = false;
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
combiningMarksPropertyRangeList,
"Combining Diacritics",
GroupAttributes.GroupName))
{
isValid = true;
}
if (InitializeCombiningMarksDictionary(expectedRange))
{
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("CombiningMarksProperty, combining mark ranges are beyond expected range, " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.StartOfUnicodeRange) + " - " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.EndOfUnicodeRange) +
". Refer to Combining Diacritics range.");
}
}
/// <summary>
/// Define NumberProperty class,
/// <a href="http://unicode.org/reports/tr13/tr13-5.html">Newline</a>
/// </summary>
public NumberProperty(UnicodeRangeDatabase unicodeDb, UnicodeRange expectedRange)
{
bool isValid = false;
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
numberDigitRangeList,
"Numbers and Digits",
GroupAttributes.GroupName))
{
isValid = true;
}
if (InitializeNumberCharDictionary(expectedRange))
{
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("NumberProperty, number ranges are beyond expected range, " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.StartOfUnicodeRange) + " - " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.EndOfUnicodeRange) +
". Refer to latin numberals and point, percent, plus, and minus signs, and comma.");
}
}
/// <summary>
/// Define LineBreakDictionary class,
/// <a href="http://www.unicode.org/reports/tr29/">Newline</a>
/// </summary>
public TextSegmentationProperty(UnicodeRangeDatabase unicodeDb, Collection <UnicodeRange> expectedRanges)
{
bool isValid = false;
foreach (UnicodeRange range in expectedRanges)
{
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
textSegmentationRangeList,
"Controls",
GroupAttributes.Name))
{
isValid = true;
}
}
if (InitializeDictionaries(expectedRanges))
{
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("expectedRanges", "TextSegmentationProperty, " +
"code points for text segmentation ranges are beyond expected range. " + "Refert to Controls ranges");
}
}
/// <summary>
/// Create a UnicodeRange instance, using the provided UnicodeChart Enum type.
/// </summary>
/// <param name="chart">Group name of scripts, symbols or punctuations (e.g. "European Scripts", "Punctuation", etc.)</param>
public UnicodeRange(UnicodeChart chart)
{
UnicodeRange range = RangePropertyCollector.GetUnicodeChartRange(new UnicodeRangeDatabase(), chart);
startOfUnicodeRange = range.StartOfUnicodeRange;
endOfUnicodeRange = range.EndOfUnicodeRange;
}
/// <summary>
/// Define NumberProperty class,
/// <a href="http://unicode.org/reports/tr13/tr13-5.html">Newline</a>
/// </summary>
public NumberProperty(UnicodeRangeDatabase unicodeDb, Collection <UnicodeRange> expectedRanges)
{
bool isValid = false;
foreach (UnicodeRange range in expectedRanges)
{
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
numberDigitRangeList,
"Numbers and Digits",
GroupAttributes.GroupName))
{
isValid = true;
}
}
if (InitializeNumberCharDictionary(expectedRanges))
{
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("expectedRanges", "NumberProperty, number ranges are beyond expected range. " +
"Refer to latin numberals and point, percent, plus, and minus signs, and comma.");
}
}
/// <summary>
/// Define LineBreakDictionary class,
/// <a href="http://www.unicode.org/reports/tr29/">Newline</a>
/// </summary>
public TextSegmentationProperty(UnicodeRangeDatabase unicodeDb, UnicodeRange expectedRange)
{
bool isValid = false;
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
textSegmentationRangeList,
"Controls",
GroupAttributes.Name))
{
isValid = true;
}
if (InitializeDictionaries(expectedRange))
{
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("TextSegmentationProperty, code points for text segmentation ranges are beyond expected range, " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.StartOfUnicodeRange) + " - " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.EndOfUnicodeRange) + ". Refert to Controls ranges");
}
}
private static void InitializeAlphabetRangeList( )
{
bool isValid = false;
UnicodeRange newRange = RangePropertyCollector.GetRange(new UnicodeRange(0x0041, 0x005A), range);
if (null != newRange)
{
alphabetRangeList.Add(newRange);
isValid = true;
}
newRange = RangePropertyCollector.GetRange(new UnicodeRange(0x0061, 0x007A), range);
if (null != newRange)
{
alphabetRangeList.Add(newRange);
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("StringFactory, latin alphabet range are beyond expected " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", range.StartOfUnicodeRange) + " - " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", range.EndOfUnicodeRange) +
". Refer to latin Alphabet range 0x0041 - 0x005A and 0x0061 - 0x007A.");
}
}
/// <summary>
/// Define SurrogatePairDictionary class
/// <a href="http://www.unicode.org/charts/PDF/UE000.pdf">Newline</a>
/// </summary>
public EudcProperty(UnicodeRangeDatabase unicodeDb, UnicodeRange expectedRange)
{
low = 0xE000; high = 0xF8FF;
if (!RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
eudcRangeList,
"Private Use",
GroupAttributes.GroupName))
{
throw new ArgumentOutOfRangeException("EudcProperty, EUDC ranges are beyond expected range, " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.StartOfUnicodeRange) + " - " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.EndOfUnicodeRange) + ". Refer to Private Use range.");
}
foreach (UnicodeRangeProperty data in eudcRangeList)
{
if (data.Name.Equals("Private Use Area", StringComparison.OrdinalIgnoreCase))
{
low = data.Range.StartOfUnicodeRange;
high = data.Range.EndOfUnicodeRange;
break;
}
}
}
/// <summary>
/// Define SurrogatePairProperty class
/// <a href="http://www.unicode.org/charts/PDF/UD800.pdf">Newline</a>
/// <a href="http://www.unicode.org/charts/PDF/UDC00.pdf">Newline</a>
/// </summary>
public SurrogatePairProperty(UnicodeRangeDatabase unicodeDb, Collection <UnicodeRange> expectedRanges)
{
bool isValid = false;
foreach (UnicodeRange range in expectedRanges)
{
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
surrogatePairRangeList,
"Surrogates",
GroupAttributes.GroupName))
{
foreach (UnicodeRangeProperty data in surrogatePairRangeList)
{
if (data.Name.Equals("High Surrogates", StringComparison.OrdinalIgnoreCase))
{
highMin = data.Range.StartOfUnicodeRange;
highMax = data.Range.EndOfUnicodeRange;
}
else if (data.Name.Equals("Low Surrogates", StringComparison.OrdinalIgnoreCase))
{
lowMin = data.Range.StartOfUnicodeRange;
lowMax = data.Range.EndOfUnicodeRange;
}
}
isValid = true;
}
surrogateRange = RangePropertyCollector.GetRange(new UnicodeRange(0x10000, TextUtil.MaxUnicodePoint), range);
if (null != surrogateRange)
{
isValid = true;
}
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("expectedRanges", "SurrogatePairProperty, SurrogatePair ranges are beyond expected range. " +
"Refert to Surrogates range and UTF32.");
}
}
/// <summary>
/// Define SurrogatePairDictionary class
/// <a href="http://unicode.org/reports/tr9/">Newline</a>
/// </summary>
public BidiProperty(UnicodeRangeDatabase unicodeDb, Collection <UnicodeRange> expectedRanges)
{
bool isValid = false;
foreach (UnicodeRange range in expectedRanges)
{
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
bidiPropertyRangeList,
"Arabic",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
bidiPropertyRangeList,
"Hebrew",
GroupAttributes.Name))
{
isValid = true;
}
}
if (InitializeBidiDictionary(expectedRanges))
{
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("expectedRanges", "BidiProperty, Bidi ranges are beyond expected range. " +
"Refer to Arabic and Hebrew ranges.");
}
// Reset isValid to validate Latin range
isValid = false;
foreach (UnicodeRange expectedRange in expectedRanges)
{
UnicodeRange range = RangePropertyCollector.GetRange(new UnicodeRange(0x0030, 0x0039), expectedRange);
if (null != range)
{
latinRangeList.Add(range);
isValid = true;
}
range = RangePropertyCollector.GetRange(new UnicodeRange(0x0041, 0x005A), expectedRange);
if (null != range)
{
latinRangeList.Add(range);
isValid = true;
}
range = RangePropertyCollector.GetRange(new UnicodeRange(0x0061, 0x007A), expectedRange);
if (null != range)
{
latinRangeList.Add(range);
isValid = true;
}
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("expectedRanges", "BidiProperty, Bidi ranges are beyond expected range. " +
"0x0030 - 0x0039, 0x0041 - 0x005A, and 0x0061 - 0x007A ranges are needed to construct Bidi string.");
}
}
/// <summary>
/// Define SurrogatePairDictionary class
/// <a href="http://www.unicode.org/reports/tr15/">Newline</a>
/// <a href="http://www.unicode.org/charts/normalization/">Newline</a>
/// </summary>
public TextNormalizationProperty(UnicodeRangeDatabase unicodeDb, Collection <UnicodeRange> expectedRanges)
{
bool isValid = false;
foreach (UnicodeRange range in expectedRanges)
{
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
textNormalizationRangeList,
"Latin",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
textNormalizationRangeList,
"CJK Unified Ideographs (Han)",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
textNormalizationRangeList,
"CJK Compatibility Ideographs",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
textNormalizationRangeList,
"Katakana",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
textNormalizationRangeList,
"Hangul Jamo",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
textNormalizationRangeList,
"Hangul Syllables",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
textNormalizationRangeList,
"Arabic",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
range,
textNormalizationRangeList,
"Greek",
GroupAttributes.Name))
{
isValid = true;
}
}
if (InitializeTextNormalizationPropertyDictionary(expectedRanges))
{
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("expectedRanges", "TextNormalizationProperty, " +
"code points for text normalization ranges are beyond expected range. " + "Refert to Latin, CJK Unified Ideographs (Han) " +
"CJK Compatibility Ideographs, Katakana, Hangul Jamo, Hangul Syllables, Arabic, and Greek ranges.");
}
}
/// <summary>
/// Define SurrogatePairDictionary class
/// <a href="http://unicode.org/reports/tr9/">Newline</a>
/// </summary>
public BidiProperty(UnicodeRangeDatabase unicodeDb, UnicodeRange expectedRange)
{
bool isValid = false;
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
bidiPropertyRangeList,
"Arabic",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
bidiPropertyRangeList,
"Hebrew",
GroupAttributes.Name))
{
isValid = true;
}
if (InitializeBidiDictionary(expectedRange))
{
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("BidiProperty, Bidi ranges are beyond expected range, " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.StartOfUnicodeRange) + " - " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.EndOfUnicodeRange) +
". Refer to Arabic and Hebrew ranges.");
}
UnicodeRange range = RangePropertyCollector.GetRange(new UnicodeRange(0x0030, 0x0039), expectedRange);
if (null != range)
{
latinRangeList.Add(range);
isValid = true;
}
range = RangePropertyCollector.GetRange(new UnicodeRange(0x0041, 0x005A), expectedRange);
if (null != range)
{
latinRangeList.Add(range);
isValid = true;
}
range = RangePropertyCollector.GetRange(new UnicodeRange(0x0061, 0x007A), expectedRange);
if (null != range)
{
latinRangeList.Add(range);
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("BidiProperty, Bidi ranges are beyond expected range, " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.StartOfUnicodeRange) + " - " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.EndOfUnicodeRange) +
". 0x0030 - 0x0039, 0x0041 - 0x005A, and 0x0061 - 0x007A ranges are needed to construct Bidi string.");
}
}
/// <summary>
/// Define SurrogatePairDictionary class
/// <a href="http://www.unicode.org/reports/tr15/">Newline</a>
/// <a href="http://www.unicode.org/charts/normalization/">Newline</a>
/// </summary>
public TextNormalizationProperty(UnicodeRangeDatabase unicodeDb, UnicodeRange expectedRange)
{
bool isValid = false;
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
textNormalizationRangeList,
"Latin",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
textNormalizationRangeList,
"CJK Unified Ideographs (Han)",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
textNormalizationRangeList,
"CJK Compatibility Ideographs",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
textNormalizationRangeList,
"Katakana",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
textNormalizationRangeList,
"Hangul Jamo",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
textNormalizationRangeList,
"Hangul Syllables",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
textNormalizationRangeList,
"Arabic",
GroupAttributes.Name))
{
isValid = true;
}
if (RangePropertyCollector.BuildPropertyDataList(
unicodeDb,
expectedRange,
textNormalizationRangeList,
"Greek",
GroupAttributes.Name))
{
isValid = true;
}
if (InitializeTextNormalizationPropertyDictionary(expectedRange))
{
isValid = true;
}
if (!isValid)
{
throw new ArgumentOutOfRangeException("TextNormalizationProperty, code points for text normalization ranges are beyond expected range, " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.StartOfUnicodeRange) + " - " +
String.Format(CultureInfo.InvariantCulture, "0x{0:X}", expectedRange.EndOfUnicodeRange) + ". Refert to Latin, CJK Unified Ideographs (Han) " +
"CJK Compatibility Ideographs, Katakana, Hangul Jamo, Hangul Syllables, Arabic, and Greek ranges.");
}
}
