protected LowerCaseKeywordTokenizer(AttributeFactory factory, System.IO.TextReader input)
: base(factory, input)
{
offsetAtt = AddAttribute<IOffsetAttribute>();
termAtt = AddAttribute<ITermAttribute>();
isAsciiCasingSameAsInvariant = CultureInfo.InvariantCulture.CompareInfo.Compare("abcdefghijklmnopqrstuvwxyz", "ABCDEFGHIJKLMNOPQRSTUVWXYZ", CompareOptions.IgnoreCase) == 0;
invariantTextInfo = CultureInfo.InvariantCulture.TextInfo;
}
/// <summary>
/// Construct a token stream processing the given input using the given AttributeFactory. </summary>
protected internal Tokenizer(AttributeFactory factory, TextReader input)
: base(factory)
{
if (input == null)
{
throw new System.NullReferenceException("input must not be null");
}
this.InputPending = input;
}
/// <summary>
/// Creates a new ThaiTokenizer, supplying the AttributeFactory </summary>
public ThaiTokenizer(AttributeFactory factory, Reader reader)
: base(factory, reader, (BreakIterator)sentenceProto.clone())
{
if (!DBBI_AVAILABLE)
{
throw new System.NotSupportedException("This JRE does not have support for Thai segmentation");
}
wordBreaker = (BreakIterator)proto.clone();
}
/// <summary> An AttributeSource that uses the same attributes as the supplied one.</summary>
public AttributeSource(AttributeSource input)
{
if (input == null)
{
throw new System.ArgumentException("input AttributeSource must not be null");
}
this.attributes = input.attributes;
this.attributeImpls = input.attributeImpls;
this.factory = input.factory;
}
/// <summary>
/// Creates the <seealso cref="TokenStream"/> of n-grams from the given <seealso cref="Reader"/> and <seealso cref="AttributeFactory"/>. </summary>
public override Tokenizer create(AttributeFactory factory, Reader input)
{
if (luceneMatchVersion.onOrAfter(Version.LUCENE_44))
{
return new NGramTokenizer(luceneMatchVersion, factory, input, minGramSize, maxGramSize);
}
else
{
return new Lucene43NGramTokenizer(factory, input, minGramSize, maxGramSize);
}
}
/// <summary>
/// Creates a new ThaiTokenizer, supplying the AttributeFactory </summary>
public ThaiTokenizer(AttributeFactory factory, TextReader reader)
: base(factory, reader, BreakIterator.CreateSentenceInstance(Locale.GetUS()))
{
if (!DBBI_AVAILABLE)
{
throw new System.NotSupportedException("This JRE does not have support for Thai segmentation");
}
wordBreaker = new ThaiWordBreaker(BreakIterator.CreateWordInstance(Locale.GetUS()));
termAtt = AddAttribute<ICharTermAttribute>();
offsetAtt = AddAttribute<IOffsetAttribute>();
}
/// <summary>
/// creates a new PatternTokenizer returning tokens from group (-1 for split functionality) </summary>
public PatternTokenizer(AttributeFactory factory, Reader input, Pattern pattern, int group)
: base(factory, input)
{
this.group = group;
// Use "" instead of str so don't consume chars
// (fillBuffer) from the input on throwing IAE below:
matcher = pattern.matcher("");
// confusingly group count depends ENTIRELY on the pattern but is only accessible via matcher
if (group >= 0 && group > matcher.groupCount())
{
throw new System.ArgumentException("invalid group specified: pattern only has: " + matcher.groupCount() + " capturing groups");
}
}
public PathHierarchyTokenizer(AttributeFactory factory, Reader input, int bufferSize, char delimiter, char replacement, int skip) : base(factory, input)
{
if (bufferSize < 0)
{
throw new System.ArgumentException("bufferSize cannot be negative");
}
if (skip < 0)
{
throw new System.ArgumentException("skip cannot be negative");
}
termAtt.resizeBuffer(bufferSize);
this.delimiter = delimiter;
this.replacement = replacement;
this.skip = skip;
resultToken = new StringBuilder(bufferSize);
}
/// <summary>
/// creates a new PatternTokenizer returning tokens from group (-1 for split functionality) </summary>
public PatternTokenizer(AttributeFactory factory, TextReader input, Regex pattern, int group)
: base(factory, input)
{
this.termAtt = AddAttribute<ICharTermAttribute>();
this.offsetAtt = AddAttribute<IOffsetAttribute>();
this.group = group;
// Use "" instead of str so don't consume chars
// (fillBuffer) from the input on throwing IAE below:
this.matcher = pattern.Match("");
this.pattern = pattern;
// confusingly group count depends ENTIRELY on the pattern but is only accessible via matcher
var groupCount = pattern.GetGroupNumbers().Length;
if (group >= 0 && group > groupCount)
{
throw new System.ArgumentException("invalid group specified: pattern only has: " + groupCount + " capturing groups");
}
}
/// <summary>
/// Creates a new instance of the <seealso cref="org.apache.lucene.analysis.wikipedia.WikipediaTokenizer"/>. Attaches the
/// <code>input</code> to a the newly created JFlex scanner. Uses the given <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/>.
/// </summary>
/// <param name="input"> The input </param>
/// <param name="tokenOutput"> One of <seealso cref="#TOKENS_ONLY"/>, <seealso cref="#UNTOKENIZED_ONLY"/>, <seealso cref="#BOTH"/> </param>
public WikipediaTokenizer(AttributeFactory factory, Reader input, int tokenOutput, HashSet<string> untokenizedTypes)
: base(factory, input)
{
this.scanner = new WikipediaTokenizerImpl(this.input);
init(tokenOutput, untokenizedTypes);
}
/// <summary>
/// Construct a new SegmenterBase, also supplying the AttributeFactory
/// </summary>
public SegmentingTokenizerBase(AttributeFactory factory, Reader reader, BreakIterator iterator) : base(factory, reader)
{
this.iterator = iterator;
}
/// <summary>
/// clean up products, attributes, productypes and categories since provisioning the tenant
/// </summary>
/// <param name="tenantId"></param>
/// <param name="masterCatalogId"></param>
/// <param name="siteId"></param>
public static void CleanUpProducts(int tenantId, int masterCatalogId, int?catalogId = null, int?siteId = null)
{
var tenant = TenantFactory.GetTenant(ServiceClientMessageFactory.GetTestClientMessage(), tenantId);
var ApiMessageHandler = ServiceClientMessageFactory.GetTestClientMessage(tenantId: tenantId, masterCatalogId: masterCatalogId, catalogId: catalogId, siteId: siteId);
var products = ProductFactory.GetProducts(ApiMessageHandler, noCount: null, pageSize: null, q: null, qLimit: null, sortBy: null, startIndex: null, filter: "createdate gt " + SinceWhen(DateTime.Now.AddDays(-1)));
foreach (var pro in products.Items)
{
ProductFactory.DeleteProduct(ApiMessageHandler, pro.ProductCode);
}
var productTypes = ProductTypeFactory.GetProductTypes(handler: ApiMessageHandler, successCode: HttpStatusCode.OK, expectedCode: HttpStatusCode.OK);
foreach (var pt in productTypes.Items)
{
if (pt.AuditInfo.CreateDate.Value > DateTime.Now.AddDays(-1))
{
try
{
ProductTypeFactory.DeleteProductType(ApiMessageHandler, pt.Id.Value);
}
catch (TestFailException e) //getaround base product type
{
// ToDo: e.ActualReturnCode
}
}
}
var attributes = AttributeFactory.GetAttributes(handler: ApiMessageHandler, successCode: HttpStatusCode.OK, expectedCode: HttpStatusCode.OK);
if (attributes.TotalCount != 0)
{
foreach (var attr in attributes.Items)
{
if (attr.AuditInfo.CreateDate.Value > DateTime.Now.AddDays(-1))
{
//bug 18745, should return NoContent
try
{
AttributeFactory.DeleteAttribute(ApiMessageHandler, attr.AttributeFQN);
}
catch (TestFailException e) //get around the bug
{
// ToDo: e.ActualReturnCode
}
}
}
}
var cates = CategoryFactory.GetCategories(ApiMessageHandler, pageSize: null, sortBy: null, startIndex: null, filter: "createdate gt " + SinceWhen(DateTime.Now.AddDays(-1)));
foreach (var cate in cates.Items)
{
var messageHandler1 = ServiceClientMessageFactory.GetTestClientMessage(tenantId: tenantId, masterCatalogId: masterCatalogId, catalogId: catalogId, siteId: siteId);
try
{
CategoryFactory.DeleteCategoryById(handler: messageHandler1, categoryId: (int)cate.Id, cascadeDelete: true);
}
catch (TestFailException e) //work around notfound
{
// ToDo: e.ActualReturnCode
}
}
}
public TokenizerAnonymousClass(AttributeFactory factory, TextReader reader, Token[] tokens)
: base(factory, reader)
{
reusableToken = AddAttribute <ICharTermAttribute>();
this.tokens = tokens;
}
public PipeTokenizer(LuceneVersion matchVersion, AttributeFactory factory, TextReader input) :
base(matchVersion, factory, input)
{
}
/// <summary>
/// Construct a new LowerCaseTokenizer using a given
/// <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/>.
/// </summary>
/// <param name="matchVersion">
/// Lucene version to match See <seealso cref="<a href="#version">above</a>"/> </param>
/// <param name="factory">
/// the attribute factory to use for this <seealso cref="Tokenizer"/> </param>
/// <param name="in">
/// the input to split up into tokens </param>
public LowerCaseTokenizer(Version matchVersion, AttributeFactory factory, TextReader @in)
: base(matchVersion, factory, @in)
{
}
public NGramTokenizer(AttributeFactory factory, TextReader input,
int gramSize)
: base(factory, input)
{
Init(gramSize);
}
/// <summary>
/// Construct a new SegmenterBase, also supplying the <see cref="Lucene.Net.Util.AttributeSource.AttributeFactory"/>
/// </summary>
protected SegmentingTokenizerBase(AttributeFactory factory, TextReader reader, BreakIterator iterator) // LUCENENET: CA1012: Abstract types should not have constructors (marked protected)
: base(factory, reader)
{
offsetAtt = AddAttribute <IOffsetAttribute>();
this.iterator = iterator;
}
/// <summary> A TokenStream using the supplied AttributeFactory for creating new <see cref="IAttribute" /> instances.</summary>
protected internal TokenStream(AttributeFactory factory)
: base(factory)
{
}
public static ICollection <AttributeInfo> Get(OffnetServiceKey key, bool populateLists)
{
var config = OffnetServiceConfiguration.Get(key.Id, key.EffectiveDate);
var list = ValidValueRuleParser.GetRules(config.ValidValueRule);
var set = new ValidValueRuleSet();
set.AddRules(list);
var attributeSet = set.GetAttributes(key, SearchOptions.ALL_FALSE);
//If we have an attribute with no valid options, clear the value and try again...
var emptyAttributes = (from a in attributeSet where a.Values == null || a.Values.Count == 0 select a.Name).ToList();
if (emptyAttributes.Count > 0)
{
foreach (var a in emptyAttributes)
{
key.RemoveAttribute(a);
}
attributeSet = set.GetAttributes(key, SearchOptions.ALL_FALSE);
}
IDictionary <string, AttributeInfo> tempList = new Dictionary <string, AttributeInfo>();
foreach (var a in attributeSet)
{
tempList[a.Name] = a;
}
key.AddMissingAttributes();
//Next we need to look if there are non-list items that need to be collected.
foreach (var pair in config.Attributes)
{
AttributeInfo a = null;
if (tempList.ContainsKey(pair.Key))
{
tempList.TryGetValue(pair.Key, out a);
}
tempList[pair.Key] = AttributeFactory.CreateAttribute(pair.Value, pair.Key, a, key);
if ((pair.Value.Type == AttributeType.Parent || pair.Value.Type == AttributeType.Related) &&
key.HasAttribute(pair.Key))
{
tempList[pair.Key].SetValue(key.GetAttributeValue(pair.Key, SearchOptions.ALL_TRUE));
}
}
var ruleSet = new OffnetServiceRuleSet();
ruleSet.AddDefaults(key); // add defaults so rules such as IsApplicable can use them
//key doesn't have all the data we have generated so to use the latest we will build a ValueHolder that has what we need...
string aValue;
foreach (var a in tempList.Values)
{
aValue = a.GetValue();
if (!string.IsNullOrEmpty(aValue)) // don't add empty values
{
ruleSet.AddValue(a.Name, new RuleValue(aValue));
}
}
//Determine which attributes we don't need
var finalList = tempList.Values.Where(a => config.IsConfigurableAttribute(a.Name, ruleSet)).ToDictionary(a => a.Name);
//Last we need to try and add a description to attributes that haven't had them added yet...
//and flag them as optional or not. We will also set the default value if there is one.
foreach (var a in finalList.Values)
{
a.Optional = config.IsOptional(a.Name, ruleSet).ToString();
a.Label = config.GetLabel(a.Name);
if (config.HasDefault(a.Name))
{
try
{
a.DefaultValue = config.GetDefaultValue(a.Name, key);
}
catch (Exception) { }
}
a.Hidden = config.IsHidden(a.Name, key);
a.MaxRepeats = config.GetMaxRepeats(a.Name);
a.RequiresRefresh = config.GetRequiresRefresh(a.Name);
a.ReadOnly = config.IsReadOnly(a.Name, key);
a.ApplicableForChange = config.GetApplicableForChange(a.Name);
a.AffectsChildren = config.AffectsChildren(a.Name);
a.DesignImpact = config.IsDesignImpact(a.Name, key);
a.ProvisioningImpact = config.IsProvisioningImpact(a.Name, key);
var attribute = a as ListAttribute;
if (attribute != null)
{
var la = attribute;
if (populateLists && la.GetValue() != null && !la.ReadOnly && !la.Hidden)
{
//Since the value has been set, the list of options is empty. If it is asked for, we will determine
//the list of options if this was not set.
var myKey = key.Clone(false);
myKey.AddValue(la.Name, null);
var myAtts = set.GetAttributes(myKey, SearchOptions.ALL_FALSE);
foreach (var av in
from myAtt in myAtts
where myAtt.Name.Equals(la.Name)
from av in ((ListAttribute)myAtt).GetList()
select av)
{
la.AddValue(av);
}
}
}
}
return(config.SortList(finalList.Values));
}
protected LowerCaseKeywordTokenizer(AttributeFactory factory, System.IO.TextReader input)
: base(factory, input)
{
}
public override ArabicLetterTokenizer create(AttributeFactory factory, Reader input)
{
return(new ArabicLetterTokenizer(luceneMatchVersion, factory, input));
}
/// <summary>
/// Creates NGramTokenizer with given min and max n-grams. </summary>
/// <param name="factory"> <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/> to use </param>
/// <param name="input"> <seealso cref="Reader"/> holding the input to be tokenized </param>
/// <param name="minGram"> the smallest n-gram to generate </param>
/// <param name="maxGram"> the largest n-gram to generate </param>
public Lucene43NGramTokenizer(AttributeFactory factory, Reader input, int minGram, int maxGram) : base(factory, input)
{
init(minGram, maxGram);
}
protected LowerCaseKeywordTokenizer(AttributeFactory factory, System.IO.TextReader input)
: base(factory, input)
{
offsetAtt = AddAttribute <IOffsetAttribute>();
termAtt = AddAttribute <ITermAttribute>();
}
/// <summary>
/// Construct a new WhitespaceTokenizer using a given
/// <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/>.
///
/// @param
/// matchVersion Lucene version to match See
/// <seealso cref="<a href="#version">above</a>"/> </summary>
/// <param name="factory">
/// the attribute factory to use for this <seealso cref="Tokenizer"/> </param>
/// <param name="in">
/// the input to split up into tokens </param>
public WhitespaceTokenizer(Version matchVersion, AttributeFactory factory, TextReader @in)
: base(matchVersion, factory, @in)
{
}
public ReversePathHierarchyTokenizer(AttributeFactory factory, TextReader input, int bufferSize, char delimiter, char replacement, int skip)
: base(factory, input)
{
if (bufferSize < 0)
{
throw new System.ArgumentException("bufferSize cannot be negative");
}
if (skip < 0)
{
throw new System.ArgumentException("skip cannot be negative");
}
termAtt = AddAttribute<ICharTermAttribute>();
offsetAtt = AddAttribute<IOffsetAttribute>();
posAtt = AddAttribute<IPositionIncrementAttribute>();
termAtt.ResizeBuffer(bufferSize);
this.delimiter = delimiter;
this.replacement = replacement;
this.skip = skip;
resultToken = new StringBuilder(bufferSize);
resultTokenBuffer = new char[bufferSize];
delimiterPositions = new List<int>(bufferSize / 10);
}
public PathHierarchyTokenizer(AttributeFactory factory, TextReader input, char delimiter, char replacement, int skip)
: this(factory, input, DEFAULT_BUFFER_SIZE, delimiter, replacement, skip)
{
}
protected LowerCaseKeywordTokenizer(AttributeFactory factory, System.IO.TextReader input)
: base(factory, input)
{
offsetAtt = AddAttribute<IOffsetAttribute>();
termAtt = AddAttribute<ITermAttribute>();
}
/// <summary>Construct a new LetterTokenizer using a given {@link Mono.Lucene.Net.Util.AttributeSource.AttributeFactory}. </summary>
public LetterTokenizer(AttributeFactory factory, System.IO.TextReader in_Renamed) : base(factory, in_Renamed)
{
}
public ArabicLetterTokenizer(AttributeFactory factory, TextReader @in) : base(factory, @in)
{
}
public ReplacerTokenizer(AttributeFactory factory, System.IO.TextReader input)
: base(factory, input)
{
Init();
}
/// <summary>
/// Creates <see cref="NGramTokenizer"/> with given min and max n-grams. </summary>
/// <param name="version"> the lucene compatibility version </param>
/// <param name="factory"> <see cref="AttributeSource.AttributeFactory"/> to use </param>
/// <param name="input"> <see cref="TextReader"/> holding the input to be tokenized </param>
/// <param name="minGram"> the smallest n-gram to generate </param>
/// <param name="maxGram"> the largest n-gram to generate </param>
public NGramTokenizer(LuceneVersion version, AttributeFactory factory, TextReader input, int minGram, int maxGram)
: this(version, factory, input, minGram, maxGram, false)
{
}
/// <summary>
/// Creates a new StandardTokenizer with a given <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/>
/// </summary>
public StandardTokenizer(Version matchVersion, AttributeFactory factory, Reader input)
: base(factory, input)
{
Init(matchVersion);
}
public MockTokenizer(AttributeFactory factory, StreamReader input, CharacterRunAutomaton runAutomaton, bool lowerCase)
: this(factory, input, runAutomaton, lowerCase, DEFAULT_MAX_TOKEN_LENGTH)
{
}
/// <summary>
/// Construct a new RussianLetterTokenizer using a given
/// <see cref="AttributeSource.AttributeFactory"/>.
/// </summary>
/// <param name="matchVersion"> lucene compatibility version </param>
/// <param name="factory">
/// the attribute factory to use for this <see cref="Tokenizer"/> </param>
/// <param name="in">
/// the input to split up into tokens </param>
public RussianLetterTokenizer(LuceneVersion matchVersion, AttributeFactory factory, TextReader @in)
: base(matchVersion, factory, @in)
{
}
internal NGramTokenizer(LuceneVersion version, AttributeFactory factory, TextReader input, int minGram, int maxGram, bool edgesOnly)
: base(factory, input)
{
Init(version, minGram, maxGram, edgesOnly);
}
/// <summary>
/// Calls {@link #MockTokenizer(Lucene.Net.Util.AttributeSource.AttributeFactory,Reader,CharacterRunAutomaton,boolean)
/// MockTokenizer(AttributeFactory, Reader, WHITESPACE, true)}
/// </summary>
public MockTokenizer(AttributeFactory factory, StreamReader input)
: this(input, WHITESPACE, true)
{
}
public CharJoinAbbreviationsLowerCaseExactTokenizer(AttributeFactory factory, System.IO.TextReader input)
: base(factory, input)
{
offsetAtt = AddAttribute<IOffsetAttribute>();
termAtt = AddAttribute<ITermAttribute>();
}
public override WhitespaceTokenizer create(AttributeFactory factory, Reader input)
{
return(new WhitespaceTokenizer(luceneMatchVersion, factory, input));
}
/// <summary>
/// Construct a new RussianLetterTokenizer using a given
/// <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/>. * @param
/// matchVersion Lucene version to match See
/// <seealso cref="<a href="#version">above</a>"/>
/// </summary>
/// <param name="factory">
/// the attribute factory to use for this <seealso cref="Tokenizer"/> </param>
/// <param name="in">
/// the input to split up into tokens </param>
public RussianLetterTokenizer(Version matchVersion, AttributeFactory factory, Reader @in)
: base(matchVersion, factory, @in)
{
}
/// <summary>
/// Creates a new StandardTokenizer with a given <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/>
/// </summary>
public StandardTokenizer(Version matchVersion, AttributeFactory factory, Reader input)
: base(factory, input)
{
Init(matchVersion);
}
public UpperCaseKeywordTokenizer(AttributeFactory factory, TextReader @in)
: base(factory, @in)
{
}
private Loader(Uri defaultBaseUri)
{
DefaultBaseUri = defaultBaseUri;
ElementFactory = new ElementFactory();
AttributeFactory = new AttributeFactory();
}
/// <summary>
/// Creates a new ClassicTokenizer with a given <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/>
/// </summary>
public ClassicTokenizer(LuceneVersion matchVersion, AttributeFactory factory, Reader input)
: base(factory, input)
{
Init(matchVersion);
}
/*
* Creates EdgeNGramTokenizer that can generate n-grams in the sizes of the given range
*
* <param name="factory"><see cref="AttributeSource.AttributeFactory"/> to use</param>
* <param name="input"><see cref="TextReader"/> holding the input to be tokenized</param>
* <param name="side">the <see cref="Side"/> from which to chop off an n-gram</param>
* <param name="minGram">the smallest n-gram to generate</param>
* <param name="maxGram">the largest n-gram to generate</param>
*/
public EdgeNGramTokenizer(AttributeFactory factory, TextReader input, Side side, int minGram, int maxGram)
: base(factory, input)
{
init(side, minGram, maxGram);
}
public ReversePathHierarchyTokenizer(AttributeFactory factory, TextReader input, char delimiter, char replacement, int skip)
: this(factory, input, DEFAULT_BUFFER_SIZE, delimiter, replacement, skip)
{
}
/// <summary>
/// Creates NGramTokenizer with given min and max n-grams. </summary>
/// <param name="version"> the lucene compatibility <a href="#version">version</a> </param>
/// <param name="factory"> <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/> to use </param>
/// <param name="input"> <seealso cref="Reader"/> holding the input to be tokenized </param>
/// <param name="minGram"> the smallest n-gram to generate </param>
/// <param name="maxGram"> the largest n-gram to generate </param>
public NGramTokenizer(Version version, AttributeFactory factory, Reader input, int minGram, int maxGram) : this(version, factory, input, minGram, maxGram, false)
{
}
/// <summary>
/// Creates a new instance of the <see cref="WikipediaTokenizer"/>. Attaches the
/// <paramref name="input"/> to a the newly created JFlex scanner. Uses the given <see cref="AttributeSource.AttributeFactory"/>.
/// </summary>
/// <param name="factory"> The <see cref="AttributeSource.AttributeFactory"/> </param>
/// <param name="input"> The input </param>
/// <param name="tokenOutput"> One of <see cref="TOKENS_ONLY"/>, <see cref="UNTOKENIZED_ONLY"/>, <see cref="BOTH"/> </param>
/// <param name="untokenizedTypes"> Untokenized types </param>
public WikipediaTokenizer(AttributeFactory factory, TextReader input, int tokenOutput, ICollection <string> untokenizedTypes)
: base(factory, input)
{
this.scanner = new WikipediaTokenizerImpl(this.m_input);
Init(tokenOutput, untokenizedTypes);
}
public static System.Attribute ConvertPlatformAttribute(CustomAttributeData attribute, PlatformName platform)
{
var constructorArguments = new object [attribute.ConstructorArguments.Count];
for (int i = 0; i < attribute.ConstructorArguments.Count; ++i)
{
constructorArguments [i] = attribute.ConstructorArguments [i].Value;
}
Func <string> createErrorMessage = () => {
var b = new System.Text.StringBuilder(" Types { ");
for (int i = 0; i < constructorArguments.Length; ++i)
{
b.Append(constructorArguments[i].GetType().ToString() + " ");
}
b.Append("}");
return(b.ToString());
};
Func <string> unknownFormatError = () => $"Unknown format for old style availability attribute {attribute.AttributeType.FullName} {attribute.ConstructorArguments.Count} {createErrorMessage ()}";
object [] ctorValues;
System.Type [] ctorTypes;
switch (attribute.ConstructorArguments.Count)
{
case 2:
if (constructorArguments [0].GetType() == typeof(byte) &&
constructorArguments [1].GetType() == typeof(byte))
{
ctorValues = new object [] { (byte)platform, (int)(byte)constructorArguments [0], (int)(byte)constructorArguments [1], (byte)0xff, null };
ctorTypes = new System.Type [] { AttributeFactory.PlatformEnum, typeof(int), typeof(int), AttributeFactory.PlatformArch, typeof(string) };
break;
}
throw new NotImplementedException(unknownFormatError());
case 3:
if (constructorArguments [0].GetType() == typeof(byte) &&
constructorArguments [1].GetType() == typeof(byte) &&
constructorArguments [2].GetType() == typeof(byte))
{
ctorValues = new object [] { (byte)platform, (int)(byte)constructorArguments [0], (int)(byte)constructorArguments [1], (int)(byte)constructorArguments [2], (byte)0xff, null };
ctorTypes = new System.Type [] { AttributeFactory.PlatformEnum, typeof(int), typeof(int), typeof(int), AttributeFactory.PlatformArch, typeof(string) };
break;
}
if (constructorArguments [0].GetType() == typeof(byte) &&
constructorArguments [1].GetType() == typeof(byte) &&
constructorArguments [2].GetType() == typeof(bool))
{
byte arch = (bool)constructorArguments [2] ? (byte)2 : (byte)0xff;
ctorValues = new object [] { (byte)platform, (int)(byte)constructorArguments [0], (int)(byte)constructorArguments [1], arch, null };
ctorTypes = new System.Type [] { AttributeFactory.PlatformEnum, typeof(int), typeof(int), AttributeFactory.PlatformArch, typeof(string) };
break;
}
throw new NotImplementedException(unknownFormatError());
case 4:
if (constructorArguments [0].GetType() == typeof(byte) &&
constructorArguments [1].GetType() == typeof(byte) &&
constructorArguments [2].GetType() == typeof(byte) &&
constructorArguments [3].GetType() == typeof(bool))
{
byte arch = (bool)constructorArguments [3] ? (byte)2 : (byte)0xff;
ctorValues = new object [] { (byte)platform, (int)(byte)constructorArguments [0], (int)(byte)constructorArguments [1], (int)(byte)constructorArguments [2], arch, null };
ctorTypes = new System.Type [] { AttributeFactory.PlatformEnum, typeof(int), typeof(int), typeof(int), AttributeFactory.PlatformArch, typeof(string) };
break;
}
if (constructorArguments [0].GetType() == typeof(byte) &&
constructorArguments [1].GetType() == typeof(byte) &&
constructorArguments [2].GetType() == typeof(byte) &&
constructorArguments [3].GetType() == typeof(byte) /* ObjCRuntime.PlatformArchitecture */)
{
ctorValues = new object [] { (byte)platform, (int)(byte)constructorArguments [0], (int)(byte)constructorArguments [1], (int)(byte)constructorArguments [2], constructorArguments [3], null };
ctorTypes = new System.Type [] { AttributeFactory.PlatformEnum, typeof(int), typeof(int), typeof(int), AttributeFactory.PlatformArch, typeof(string) };
break;
}
throw new NotImplementedException(unknownFormatError());
default:
throw new NotImplementedException($"Unknown count {attribute.ConstructorArguments.Count} {createErrorMessage ()}");
}
return(AttributeFactory.CreateNewAttribute(AttributeFactory.IntroducedAttributeType, ctorTypes, ctorValues));
}
/*
* Creates EdgeNGramTokenizer that can generate n-grams in the sizes of the given range
*
* <param name="factory"><see cref="AttributeSource.AttributeFactory"/> to use</param>
* <param name="input"><see cref="TextReader"/> holding the input to be tokenized</param>
* <param name="sideLabel">the name of the <see cref="Side"/> from which to chop off an n-gram</param>
* <param name="minGram">the smallest n-gram to generate</param>
* <param name="maxGram">the largest n-gram to generate</param>
*/
public EdgeNGramTokenizer(AttributeFactory factory, TextReader input, string sideLabel, int minGram, int maxGram) :
this(factory, input, SideExtensions.GetSide(sideLabel), minGram, maxGram)
{
}
public CJKTokenizer(AttributeFactory factory, TextReader @in)
: base(factory, @in)
{
Init();
}
internal NGramTokenizer(Version version, AttributeFactory factory, Reader input, int minGram, int maxGram, bool edgesOnly) : base(factory, input)
{
init(version, minGram, maxGram, edgesOnly);
}
public Lucene43EdgeNGramTokenizer(LuceneVersion version, AttributeFactory factory, TextReader input, Side side, int minGram, int maxGram)
: base(factory, input)
{
Init(version, side, minGram, maxGram);
}
public CJKTokenizer(AttributeFactory factory, TextReader _in)
: base(factory, _in)
{
Init();
}
public Lucene43EdgeNGramTokenizer(LuceneVersion version, AttributeFactory factory, TextReader input, string sideLabel, int minGram, int maxGram)
: this(version, factory, input, GetSide(sideLabel), minGram, maxGram)
{
}
/// <summary>
/// Creates NGramTokenizer with given min and max n-grams. </summary>
/// <param name="factory"> <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/> to use </param>
/// <param name="input"> <seealso cref="Reader"/> holding the input to be tokenized </param>
/// <param name="minGram"> the smallest n-gram to generate </param>
/// <param name="maxGram"> the largest n-gram to generate </param>
public Lucene43NGramTokenizer(AttributeFactory factory, Reader input, int minGram, int maxGram) : base(factory, input)
{
init(minGram, maxGram);
}
/// <summary>
/// Creates <see cref="Lucene43EdgeNGramTokenizer"/> that can generate n-grams in the sizes of the given range
/// </summary>
/// <param name="version"> the Lucene match version - See <see cref="LuceneVersion"/> </param>
/// <param name="factory"> <see cref="AttributeSource.AttributeFactory"/> to use </param>
/// <param name="input"> <see cref="TextReader"/> holding the input to be tokenized </param>
/// <param name="minGram"> the smallest n-gram to generate </param>
/// <param name="maxGram"> the largest n-gram to generate </param>
public Lucene43EdgeNGramTokenizer(LuceneVersion version, AttributeFactory factory, TextReader input, int minGram, int maxGram)
: this(version, factory, input, Side.FRONT, minGram, maxGram)
{
}
/// <summary>
/// Construct a new WhitespaceTokenizer using a given
/// <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/>.
///
/// @param
/// matchVersion Lucene version to match See
/// <seealso cref="<a href="#version">above</a>"/> </summary>
/// <param name="factory">
/// the attribute factory to use for this <seealso cref="Tokenizer"/> </param>
/// <param name="in">
/// the input to split up into tokens </param>
public WhitespaceTokenizer(Version matchVersion, AttributeFactory factory, TextReader @in) : base(matchVersion, factory, @in)
{
}
public MyAttributeFactory(AttributeFactory @delegate)
{
this.@delegate = @delegate;
}
/// <summary> An AttributeSource using the supplied {@link AttributeFactory} for creating new {@link Attribute} instances.</summary>
public AttributeSource(AttributeFactory factory)
{
this.attributes = new SupportClass.GeneralKeyedCollection<Type, SupportClass.AttributeImplItem>(delegate(SupportClass.AttributeImplItem att) { return att.Key; });
this.attributeImpls = new SupportClass.GeneralKeyedCollection<Type, SupportClass.AttributeImplItem>(delegate(SupportClass.AttributeImplItem att) { return att.Key; });
this.factory = factory;
}
/// <summary>
/// Creates a new ClassicTokenizer with a given <seealso cref="org.apache.lucene.util.AttributeSource.AttributeFactory"/>
/// </summary>
public ClassicTokenizer(LuceneVersion matchVersion, AttributeFactory factory, Reader input)
: base(factory, input)
{
Init(matchVersion);
}