/// <summary>
/// 提取版本号
/// </summary>
/// <param name="result">盘古分词的结果</param>
/// <param name="vWordNode">V 这个字符的第一个出现位置</param>
/// <param name="lastNode">版本号的最后一个词</param>
/// <param name="versionBeginPosition">版本号第一个词的起始位置</param>
private void Pickup(SuperLinkedList<WordInfo> result, SuperLinkedListNode<WordInfo> vWordNode,
SuperLinkedListNode<WordInfo> lastNode, int versionBeginPosition)
{
SuperLinkedListNode<WordInfo> node = vWordNode.Next;
int lastPosition = lastNode.Value.Position + lastNode.Value.Word.Length;
SuperLinkedListNode<WordInfo> end = lastNode.Next;
while (node != end)
{
result.Remove(node);
node = vWordNode.Next;
}
if (vWordNode.Value.Word == "V")
{
vWordNode.Value.Word = "v";
}
string version = _Text.Substring(versionBeginPosition, lastPosition - versionBeginPosition);
int dotPosition = 0;
int dotCount = 0;
WordInfo verWord = null;
dotPosition = version.IndexOf('.', dotPosition);
while (dotPosition > 0)
{
verWord = null;
if (dotCount > 0) //第一个点之前的版本号不提取
{
//提取前n个子版本号
verWord = new WordInfo(version.Substring(0, dotPosition), POS.POS_D_K, 0);
verWord.Rank = 1; //这里设置子版本号的权重
verWord.Position = versionBeginPosition;
verWord.WordType = WordType.None;
}
dotCount++;
dotPosition = version.IndexOf('.', dotPosition + 1);
if (verWord != null)
{
result.AddAfter(vWordNode, verWord);
}
}
//提取完整版本号
verWord = new WordInfo(version, POS.POS_D_K, 0);
verWord.Rank = 5; //这里设置完整版本号的权重
verWord.Position = versionBeginPosition;
verWord.WordType = WordType.None;
result.AddAfter(vWordNode, verWord);
}
public void EqualityOperator()
{
WordInfo info1 = new WordInfo("word", 0, 0, WordLocation.Content);
WordInfo info2 = new WordInfo("word", 0, 0, WordLocation.Content);
WordInfo info3 = new WordInfo("word", 10, 1, WordLocation.Content);
WordInfo info4 = new WordInfo("word", 10, 1, WordLocation.Title);
WordInfo info5 = new WordInfo("word2", 0, 0, WordLocation.Content);
Assert.IsTrue(info1 == info2, "info1 should equal info2");
Assert.IsFalse(info1 == info3, "info1 should not equal info3");
Assert.IsFalse(info3 == info4, "info3 should not equal info4");
Assert.IsFalse(info1 == null, "info1 should not equal null");
Assert.IsFalse(info1 == info5, "info1 should not equal info5");
}
public void Clear()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo mi1 = new WordInfo("continuous", 0, 0, WordLocation.Content);
WordInfo mi2 = new WordInfo("taskbar", 21, 1, WordLocation.Content);
collection.Add(mi1);
collection.Add(mi2);
Assert.AreEqual(2, collection.Count, "Wrong count (collection should contain 2 items)");
collection.Clear();
Assert.AreEqual(0, collection.Count, "Wrong count (collection should be empty)");
}
public void CompareTo()
{
WordInfo info1 = new WordInfo("word", 0, 0, WordLocation.Content);
WordInfo info2 = new WordInfo("word", 0, 0, WordLocation.Content);
WordInfo info3 = new WordInfo("word", 10, 1, WordLocation.Content);
WordInfo info4 = new WordInfo("word", 10, 1, WordLocation.Title);
WordInfo info5 = new WordInfo("word2", 0, 0, WordLocation.Content);
Assert.AreEqual(0, info1.CompareTo(info2), "info1 should equal info2");
Assert.AreEqual(-3, info1.CompareTo(info3), "info1 should be smaller than info3");
Assert.AreEqual(2, info3.CompareTo(info4), "info3 should be greater than info4");
Assert.AreEqual(1, info1.CompareTo(null), "info1 should be greater than null");
Assert.AreEqual(-1, info1.CompareTo(info5), "info1 should be smaller than info5");
}
public void Tokenize()
{
string input = "Hello, there!";
WordInfo[] expectedOutput = new WordInfo[] { new WordInfo("Hello", 0, 0, WordLocation.Content), new WordInfo("there", 7, 1, WordLocation.Content) };
WordInfo[] output = Tools.Tokenize(input, WordLocation.Content);
Assert.AreEqual(expectedOutput.Length, output.Length, "Wrong output length");
for(int i = 0; i < output.Length; i++) {
Assert.AreEqual(expectedOutput[i].Text, output[i].Text, "Wrong word text at index " + i.ToString());
Assert.AreEqual(expectedOutput[i].FirstCharIndex, output[i].FirstCharIndex, "Wrong first char index at " + i.ToString());
Assert.AreEqual(expectedOutput[i].WordIndex, output[i].WordIndex, "Wrong word index at " + i.ToString());
}
}
public void Equals()
{
WordInfo info1 = new WordInfo("word", 0, 0, WordLocation.Content);
WordInfo info2 = new WordInfo("word", 0, 0, WordLocation.Content);
WordInfo info3 = new WordInfo("word", 10, 1, WordLocation.Content);
WordInfo info4 = new WordInfo("word", 10, 1, WordLocation.Title);
WordInfo info5 = new WordInfo("word2", 0, 0, WordLocation.Content);
Assert.IsTrue(info1.Equals(info2), "info1 should equal info2");
Assert.IsFalse(info1.Equals(info3), "info1 should not equal info3");
Assert.IsFalse(info3.Equals(info4), "info3 should not equal info4");
Assert.IsTrue(info1.Equals(info1), "info1 should equal itself");
Assert.IsFalse(info1.Equals(null), "info1 should not equal null");
Assert.IsFalse(info1.Equals("hello"), "info1 should not equal a string");
Assert.IsFalse(info1.Equals(info5), "info1 should not equal info5");
}
public void RemoveStopWords()
{
WordInfo[] input = new WordInfo[] { new WordInfo("I", 0, 0, WordLocation.Content), new WordInfo("like", 7, 1, WordLocation.Content),
new WordInfo("the", 15, 2, WordLocation.Content), new WordInfo("cookies", 22, 3, WordLocation.Content) };
WordInfo[] expectedOutput = new WordInfo[] { new WordInfo("I", 0, 0, WordLocation.Content), new WordInfo("like", 7, 1, WordLocation.Content),
new WordInfo("cookies", 22, 3, WordLocation.Content) };
WordInfo[] output = Tools.RemoveStopWords(input, new string[] { "the", "in", "of" });
Assert.AreEqual(expectedOutput.Length, output.Length, "Wrong output length");
for(int i = 0; i < output.Length; i++) {
Assert.AreEqual(expectedOutput[i].Text, output[i].Text, "Wrong word text at index " + i.ToString());
Assert.AreEqual(expectedOutput[i].FirstCharIndex, output[i].FirstCharIndex, "Wrong word position at index " + i.ToString());
}
}
public void RemoveStopWords()
{
WordInfo[] input = new WordInfo[] { new WordInfo("I", 0, 0, WordLocation.Content), new WordInfo("like", 7, 1, WordLocation.Content),
new WordInfo("the", 15, 2, WordLocation.Content), new WordInfo("cookies", 22, 3, WordLocation.Content) };
WordInfo[] expectedOutput = new WordInfo[] { new WordInfo("I", 0, 0, WordLocation.Content), new WordInfo("like", 7, 1, WordLocation.Content),
new WordInfo("cookies", 22, 3, WordLocation.Content) };
WordInfo[] output = Tools.RemoveStopWords(input, new string[] { "the", "in", "of" });
Assert.AreEqual(expectedOutput.Length, output.Length, "Wrong output length");
for (int i = 0; i < output.Length; i++)
{
Assert.AreEqual(expectedOutput[i].Text, output[i].Text, "Wrong word text at index " + i);
Assert.AreEqual(expectedOutput[i].FirstCharIndex, output[i].FirstCharIndex, "Wrong word position at index " + i);
}
}
public void Tokenize_OneWordWithSplitChar()
{
string input = "todo.";
WordInfo[] expectedOutput = new WordInfo[] { new WordInfo("todo", 0, 0, WordLocation.Content) };
WordInfo[] output = Tools.Tokenize(input, WordLocation.Content);
Assert.AreEqual(expectedOutput.Length, output.Length, "Wrong output length");
for (int i = 0; i < output.Length; i++)
{
Assert.AreEqual(expectedOutput[i].Text, output[i].Text, "Wrong word text at index " + i);
Assert.AreEqual(expectedOutput[i].FirstCharIndex, output[i].FirstCharIndex, "Wrong first char index at " + i);
Assert.AreEqual(expectedOutput[i].WordIndex, output[i].WordIndex, "Wrong word index at " + i);
}
}
private void WordsDataGridAddingNewItem(object sender, AddingNewItemEventArgs e)
{
DataGrid dataGrid = sender as DataGrid;
if (dataGrid == null)
{
return;
}
LanguageConfig nativeLang = App.CountriesConfig.FirstOrDefault(c => c.Alias.Contains("Rus"));
LanguageConfig translatedLang = App.CountriesConfig.LastOrDefault(c => c.Alias.Contains("Eng"));
if (_wordsList.Count > 0)
{
List <IGrouping <LanguageConfig, WordInfo> > nativeLangGrouping = _wordsList.GroupBy(w => w.NativeLang).ToList();
List <IGrouping <LanguageConfig, WordInfo> > translatedLangGrouping = _wordsList.GroupBy(w => w.TranslatedLang).ToList();
int nativeLangGroupingMaxElementsCount = nativeLangGrouping.Max(g => g.Count());
int translatedLangGroupingMaxElementsCount = translatedLangGrouping.Max(g => g.Count());
IGrouping <LanguageConfig, WordInfo> nativeLangusgeGroup = nativeLangGrouping.FirstOrDefault(tt => tt.Count() == nativeLangGroupingMaxElementsCount);
IGrouping <LanguageConfig, WordInfo> translatedLangusgeGroup = translatedLangGrouping.FirstOrDefault(tt => tt.Count() == translatedLangGroupingMaxElementsCount);
if (nativeLangusgeGroup != null)
{
nativeLang = nativeLangusgeGroup.Key;
}
if (translatedLangusgeGroup != null)
{
translatedLang = translatedLangusgeGroup.Key;
}
}
WordInfo lastItem = _wordsList.LastOrDefault() ?? new WordInfo();
e.NewItem = new WordInfo
{
NativeLang = nativeLang,
TranslatedLang = translatedLang,
TwoWays = lastItem.TwoWays,
Parent = lastItem.Parent,
};
}
public void DetailWord(WordInfo info)
{
DetailPanel.SetActive(true);
Debug.Log("Detail Word :" + info.data.Id);
AudioManager.I.PlayWord(info.data.Id);
MoreInfoPanel.SetActive(false);
ScoreText.text = "Score: " + info.score;
var output = "";
var splittedLetters = ArabicAlphabetHelper.SplitWordIntoLetters(info.data.Arabic);
foreach (var letter in splittedLetters)
{
output += letter.GetChar() + " ";
}
output += "\n";
output += info.data.Arabic;
//output += "\n";
//foreach (var letter in splittedLetters) {
// output += letter.GetChar();
//}
ArabicText.text = output;
LL_Isolated.Init(new LL_WordData(info.data));
LL_Initial.gameObject.SetActive(false);
LL_Final.gameObject.SetActive(false);
if (info.data.Drawing != "")
{
var drawingChar = AppManager.I.Teacher.wordHelper.GetWordDrawing(info.data);
Drawing.text = drawingChar;
//LL_Medial.gameObject.SetActive(true);
LL_Medial.Init(new LL_ImageData(info.data));
Debug.Log("Drawing: " + info.data.Drawing + " / " + ArabicAlphabetHelper.GetLetterFromUnicode(info.data.Drawing));
}
else
{
Drawing.text = "";
LL_Medial.gameObject.SetActive(false);
}
}
/// <summary>
/// Stores a document in the index.
/// </summary>
/// <param name="document">The document.</param>
/// <param name="keywords">The document keywords, if any, an empty array or <c>null</c> otherwise.</param>
/// <param name="content">The content of the document.</param>
/// <param name="state">A state object that is passed to the IndexStorer SaveDate/DeleteData function.</param>
/// <returns>The number of indexed words (including duplicates).</returns>
/// <remarks>Indexing the content of the document is <b>O(n)</b>,
/// where <b>n</b> is the total number of words in the document.</remarks>
public int StoreDocument(IDocument document, string[] keywords, string content, object state)
{
if (document == null)
{
throw new ArgumentNullException("document");
}
if (keywords == null)
{
keywords = new string[0];
}
if (content == null)
{
throw new ArgumentNullException("content");
}
RemoveDocument(document, state);
keywords = ScrewTurn.Wiki.SearchEngine.Tools.CleanupKeywords(keywords);
// Prepare content words
WordInfo[] contentWords = document.Tokenize(content);
contentWords = ScrewTurn.Wiki.SearchEngine.Tools.RemoveStopWords(contentWords, stopWords);
// Prepare title words
WordInfo[] titleWords = document.Tokenize(document.Title);
titleWords = ScrewTurn.Wiki.SearchEngine.Tools.RemoveStopWords(titleWords, stopWords);
for (int i = 0; i < titleWords.Length; i++)
{
titleWords[i] = new WordInfo(titleWords[i].Text, titleWords[i].FirstCharIndex, titleWords[i].WordIndex, WordLocation.Title);
}
// Prepare keywords
WordInfo[] words = new WordInfo[keywords.Length];
int count = 0;
for (int i = 0; i < words.Length; i++)
{
words[i] = new WordInfo(keywords[i], (ushort)count, (ushort)i, WordLocation.Keywords);
count += 1 + keywords[i].Length;
}
return(connector.SaveDataForDocument(document, contentWords, titleWords, words, state));
}
public void DetailWord(WordInfo _currentWord)
{
currentWordInfo = _currentWord;
DetailPanel.SetActive(true);
HighlightWordItem(currentWordInfo.data.Id);
PlayWord();
// empty spelling container
foreach (Transform t in SpellingContainer.transform)
{
Destroy(t.gameObject);
}
var splittedLetters = ArabicAlphabetHelper.SplitWord(AppManager.I.DB, currentWordInfo.data, false, false);
foreach (var letter in splittedLetters)
{
btnGO = Instantiate(SpellingLetterItemPrefab);
btnGO.transform.SetParent(SpellingContainer.transform, false);
btnGO.transform.SetAsFirstSibling();
btnGO.GetComponent <ItemSpellingLetter>().Init(letter.letter);
}
WordArabicText.text = currentWordInfo.data.Arabic;
if (currentWordInfo.data.Drawing != "")
{
WordDrawingText.text = AppManager.I.VocabularyHelper.GetWordDrawing(currentWordInfo.data);
if (currentWordInfo.data.Category == WordDataCategory.Color)
{
WordDrawingText.SetColor(GenericHelper.GetColorFromString(currentWordInfo.data.Value));
}
}
else
{
WordDrawingText.text = "";
}
if (AppConfig.DebugLogEnabled)
{
Debug.Log("Detail Word(): " + currentWordInfo.data.Id);
Debug.Log("word unicodes: " + ArabicAlphabetHelper.GetStringUnicodes(currentWordInfo.data.Arabic));
Debug.Log("word unicodes forms: " + ArabicAlphabetHelper.GetStringUnicodes(WordArabicText.RenderedText));
}
//ScoreText.text = "Score: " + currentWord.score;
}
public void DetailWord(WordInfo _currentWord)
{
currentWordInfo = _currentWord;
DetailPanel_Inner.SetActive(true);
HighlightWordItem(currentWordInfo.data.Id);
PlayWord();
// empty spelling container
foreach (Transform t in SpellingContainer.transform)
{
Destroy(t.gameObject);
}
var splittedLetters = LanguageSwitcher.I.GetHelper(LanguageUse.Learning).SplitWord(AppManager.I.DB, currentWordInfo.data, false, false);
foreach (var letter in splittedLetters)
{
btnGO = Instantiate(SpellingLetterItemPrefab);
btnGO.transform.SetParent(SpellingContainer.transform, false);
if (LanguageSwitcher.I.IsLearningLanguageRTL())
{
btnGO.transform.SetAsFirstSibling();
}
btnGO.GetComponent <ItemSpellingLetter>().Init(letter.letter);
}
WordArabicText.text = currentWordInfo.data.Text;
if (currentWordInfo.data.Drawing != "")
{
WordDrawingText.SetLetterData(new LL_ImageData(currentWordInfo.data));
}
else
{
WordDrawingText.text = "";
}
if (ApplicationConfig.I.DebugLogEnabled)
{
Debug.Log("Detail Word(): " + currentWordInfo.data.Id);
Debug.Log("drawing code: " + currentWordInfo.data.Drawing);
Debug.Log("word unicodes: " + LanguageSwitcher.I.GetHelper(LanguageUse.Learning).GetStringUnicodes(currentWordInfo.data.Text));
Debug.Log("word unicodes forms: " + LanguageSwitcher.I.GetHelper(LanguageUse.Learning).GetStringUnicodes(WordArabicText.RenderedText));
}
//ScoreText.text = "Score: " + currentWord.score;
}
public void RtlWordsInLtrContentTest()
{
var content = "This is a test content for use متن تستی راست به چپ in ltr content";
var ltrPara = new Paragraph(0);
var ltrLine = ltrPara.AddLine(new Line(new Point(0, 0)));
var offset = 0;
var wordCounter = 0;
foreach (var word in content.Split(" "))
{
var wordInfo = new WordInfo(word, offset, WordType.Normal);
wordInfo.Styles.SetDirection(Paragraph.IsRtl(word));
wordInfo.SetFormattedText(_arial, _fontSize, 1, _lineHeight);
offset += word.Length;
var space = new SpaceWord(offset++);
space.Styles.SetDirection(wordInfo.Styles.IsRtl);
space.SetFormattedText(_arial, _fontSize, 1, _lineHeight);
ltrLine.AddWord(wordInfo);
Assert.AreEqual(++wordCounter, ltrLine.Words.Count);
ltrLine.AddWord(space);
Assert.AreEqual(++wordCounter, ltrLine.Words.Count);
}
ltrLine.Build(false);
for (var i = 0; i < ltrLine.Words.Count - 1; i++)
{
Debug.WriteLine($"Word {i}'th");
var word = ltrLine.Words[i];
var nextWord = ltrLine.Words[i + 1];
if (word.Styles.IsRtl && nextWord.Styles.IsRtl) // 0X <--2-- <--1-- NX
{
Assert.IsTrue(word.Area.X > nextWord.Area.X);
}
else if (word.Styles.IsLtr && nextWord.Styles.IsLtr) // 0X --1--> --2--> NX
{
Assert.IsTrue(word.Area.X < nextWord.Area.X);
}
else
{
Assert.IsTrue(word.Area.X < nextWord.Area.X);
}
}
}
/// <summary>
/// Spawn word and non verbal object
/// </summary>
/// <param name="sound">Wordinfo. Spawn as non verbal if sound.word equals ""</param>
/// <param name="isNewObject">Will have authority if it is newly generated.</param>
public void spawnSoundObject(WordInfo sound, bool isNewObject)
{
GameObject soundobj;
if (string.IsNullOrEmpty(sound.word))
{
soundobj = (GameObject)Instantiate(nonVerbalPrefab);
}
else
{
soundobj = (GameObject)Instantiate(wordPrefab);
}
soundobj.transform.position = sound.pos;
soundobj.transform.rotation = sound.rot;
SoundObjectActs soundscript = soundobj.GetComponent <SoundObjectActs> ();
if (soundscript is WordActs)
{
((WordActs)soundscript).m_wordstr = sound.word;
((WordActs)soundscript).m_scale = sound.scale;
}
soundscript.m_serverFileName = sound.clipfn;
if (sound.looping)
{
soundscript.m_looping = true;
soundscript.m_sequencer.playtriggers = sound.playerTriggers;
soundscript.m_sequencer.loadedFromScene = true;
if (sound.scrubs != null)
{
soundscript.m_sequencer.scrubs = sound.scrubs;
}
soundscript.m_sequencer.path = sound.path;
}
if (isNewObject)
{
soundscript.m_newSpawn = true;
soundscript.m_creator = netId.Value;
Debug.Log(connectionToClient.connectionId);
NetworkServer.SpawnWithClientAuthority(soundobj, connectionToClient);
}
else
{
NetworkServer.Spawn(soundobj);
}
}
public void ContainsOccurrence()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo mi1 = new WordInfo("continuous", 7, 0, WordLocation.Content);
collection.Add(mi1);
Assert.IsTrue(collection.ContainsOccurrence("continuous", 7), "Collection should contain occurrence");
Assert.IsFalse(collection.ContainsOccurrence("continuous2", 7), "Collection should not contain occurrence");
Assert.IsFalse(collection.ContainsOccurrence("continuous", 6), "Collection should not contain occurrence");
Assert.IsFalse(collection.ContainsOccurrence("continuous", 8), "Collection should not contain occurrence");
Assert.IsFalse(collection.ContainsOccurrence("continuous2", 6), "Collection should not contain occurrence");
Assert.IsFalse(collection.ContainsOccurrence("continuous2", -1), "Contains should return false");
Assert.IsFalse(collection.ContainsOccurrence("", 7), "Contains should return false");
Assert.IsFalse(collection.ContainsOccurrence(null, 7), "Contains should return false");
}
public void ContainsOccurrence()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo mi1 = new WordInfo("continuous", 7, 0, WordLocation.Content);
collection.Add(mi1);
Assert.IsTrue(collection.ContainsOccurrence("continuous", 7), "Collection should contain occurrence");
Assert.IsFalse(collection.ContainsOccurrence("continuous2", 7), "Collection should not contain occurrence");
Assert.IsFalse(collection.ContainsOccurrence("continuous", 6), "Collection should not contain occurrence");
Assert.IsFalse(collection.ContainsOccurrence("continuous", 8), "Collection should not contain occurrence");
Assert.IsFalse(collection.ContainsOccurrence("continuous2", 6), "Collection should not contain occurrence");
Assert.IsFalse(collection.ContainsOccurrence("continuous2", -1), "Contains should return false");
Assert.IsFalse(collection.ContainsOccurrence("", 7), "Contains should return false");
Assert.IsFalse(collection.ContainsOccurrence(null, 7), "Contains should return false");
}
public void Setup()
{
_maker = new XHtmlMaker();
_kanjiWithReading = new WordInfo {
Text = "見世物", Reading = "ミセモノ", Translation = "Unreal"
};
_kanjiWithoutReading = new WordInfo {
Text = "見世物"
};
_hiraganaWord = new WordInfo {
Text = "すべて", Reading = "スベテ"
};
_katakanaWord = new WordInfo {
Text = "スベテ", Reading = "スベテ"
};
_hiraganaWordWithDifferentPronunciation = new WordInfo {
Text = "は", Reading = "ハ", Pronunciation = "ワ"
};
}
public WordVM(WordInfo wordInfo, IKanjiProperties lang, IKanaProperties kanaProperties, IRelated related)
{
var s = wordInfo.RawWord;
StringForm = s;
codePoints.AddRange(s.AsCodePoints().Select(rawCp =>
{
var cp = CodePoint.FromInt(rawCp);
var vm = new CodePointVM(
cp,
related.FindRelated(cp).SelectMany(g => g),
cp is Kanji k
? lang.LookupRadicalsByKanji(k).ValueOr(Enumerable.Empty <CodePoint>())
: Enumerable.Empty <CodePoint>(),
cp is Kana kana ? kanaProperties.LookupRomaji(kana.ToString()) : null);
return(vm);
}));
WordInfo = wordInfo;
}
public WordInfo SearchWord(string text)
{
if (!ContainsWord(text))
{
return(null);
}
ZType ztype = SearchZTypeOne(text);
WordInfo info0 = null;
if (ztype != null)
{
info0 = new WordInfo(text, WordKind.TypeName, ztype);
}
WordInfo info1 = IWordDictionaryHelper.EnumerableSearchWord(text, EnumTypes);
WordInfo info2 = IWordDictionaryHelper.EnumerableSearchWord(text, ClassTypes);
WordInfo newWord = WordInfo.Merge(info0, info1, info2);
return(newWord);
}
private SplitResult SplitOne(string src)
{
//Console.WriteLine("WordSegmenter.SplitOne: "+src);
if (src.Length == 1)
{
WordInfo result = GetFromTree(src);
if (result == null)
{
result = new WordInfo(src, WordKind.Unkown);
}
SplitResult splitResult = new SplitResult();
splitResult.UnSplitText = "";
splitResult.ResultWord = result;
return(splitResult);
}
else
{
SplitResult splitResult = null;
WordInfo result = null;
int i = 0;
for (; i < src.Length; i++)
{
string newsrc = src.Substring(i);
//Console.WriteLine("WordSegmenter.SplitOne: " + newsrc);
result = GetFromTree(newsrc);
if (result != null)
{
splitResult = new SplitResult();
splitResult.UnSplitText = src.Substring(0, i);
splitResult.ResultWord = result;
return(splitResult);
}
}
if (splitResult == null)
{
splitResult = new SplitResult();
splitResult.UnSplitText = src.Substring(0, src.Length - 1);
WordInfo info = new WordInfo(src.Substring(src.Length - 1), WordKind.Unkown);
splitResult.ResultWord = info;
}
return(splitResult);
}
}
private void AddWordsUsingLingualeo(object sender, RoutedEventArgs args)
{
long addedWordsCount = 0;
IEnumerable <WordInfo> allWordsFromLingualeo = GetWordsListFromLingualeo();
foreach (WordInfo justAddedWord in allWordsFromLingualeo)
{
WordInfo existedWord = _wordsList.FirstOrDefault(w => w.NativeLang == justAddedWord.NativeLang && w.TranslatedLang == justAddedWord.TranslatedLang && w.NativeWord == justAddedWord.NativeWord && w.TranslatedWord == justAddedWord.TranslatedWord);
if (existedWord != null)
{
continue;
}
_wordsList.Add(justAddedWord);
addedWordsCount++;
}
MessageBox.Show(addedWordsCount + " new words successfully added.", addedWordsCount + " words added", MessageBoxButton.OK, MessageBoxImage.Information);
}
public WordVM(WordInfo wordInfo, ILanguageService lang)
{
var s = wordInfo.RawWord;
StringForm = s;
codePoints.AddRange(s.AsCodePoints().Select(rawCp =>
{
var cp = CodePoint.FromInt(rawCp);
var vm = new CodePointVM(
cp,
lang.LookupRelatedCharacters(cp),
cp is Kanji k
? lang.LookupRadicals(k).ValueOr(Enumerable.Empty <CodePoint>())
: Enumerable.Empty <CodePoint>(),
cp is Kana kana ? lang.LookupRomaji(kana) : null);
return(vm);
}));
WordInfo = wordInfo;
}
[AuthFilter]//身份认证，不带token或者token错误会被拦截器拦截进不来这个接口
public IActionResult WordsUpLoad(WordDto body)
{
string token = _httpContext.HttpContext.Request.Headers["Authorization"];
AuthRedis.GetUserByToken(token, out UserInfo userInfo);
using EFCoreContextWrite context = new EFCore.EFCoreContextWrite();
if (body.Eid == null)
{
int count = context.WordInfo.Where(x => x.PictureID == body.id).Count();
if (count > 0)
{
return(Ok(new ApiResponse(code: CodeAndMessage.已存在对应的资讯文档)));
}
WordInfo WordInfos = new WordInfo()
{
Id = SequenceID.GetSequenceID(),
CreateTime = DateTime.Now,
Disable = false,
HtmlContent = body.HtmlContent,
PictureID = body.id,
LastModifiedTime = DateTime.Now,
HtmlExplain = body.HtmlExplain,
HtmlTitle = body.HtmlTitle,
AttachedPath = body.AttachedPath
};
context.Add(WordInfos);
context.SaveChanges();
WordRedis.Del();
}
else
{
var WordInfo = context.WordInfo.Single(x => x.Id == body.Eid);
WordInfo.LastModifiedTime = DateTime.Now;
WordInfo.HtmlContent = body.HtmlContent;
WordInfo.HtmlExplain = body.HtmlExplain;
WordInfo.HtmlTitle = body.HtmlTitle;
WordInfo.AttachedPath = body.AttachedPath;
context.SaveChanges();
WordRedis.Del();
}
return(Ok(new ApiResponse()));
}
/// <summary>Простое изменение слов</summary>
static void test2()
{
Console.Write("{0, -55} | ", "Test 2 - простое изменение слов ");
SaveResourceFile("test2_resoult", "test2_resoult.xml");
SaveResourceFile("source_empty_dic", "dic.xml");
Testing.Clear();
DB db = DB.GetInstance();
//Добавляем одно слово
WordInfo info1 = new WordInfo();
info1.En = "testing...";
info1.Ru = "апробирование";
db.Push(info1);
db.Commit();
//Изменяем слово
WordInfo info2 = new WordInfo();
info2.Word = db.Words[0];
info2.Ru = "EnWord2";
info2.En = "EnWord1";
db.Push(info2);
db.Commit();
int wrongIndex;
if (!CompareFiles2("dic.xml", "test2_resoult.xml", out wrongIndex))
{
Console.WriteLine("false (line " + wrongIndex + ")");
}
else
{
Console.WriteLine("true");
}
}
private string GetPartOfSpeechText(WordInfo info)
{
if (info != null)
{
if (info.flex == null && info.indent != null && info.nom != null)
{
info.flex = context.Flexes.FirstOrDefault(x => x.type == info.nom.type && x.flex == info.nom.reestr.Substring(info.nom.reestr.Length - info.indent.indent));
}
if (info.flex != null)
{
Gr gr = context.Gr.FirstOrDefault(x => x.id == info.indent.gr_id);
if (gr != null)
{
var grInfo = gr.GetType().GetProperty($"field{info.flex.field2 + 3}").GetValue(gr, null);
return(grInfo.ToString());
}
}
}
return("");
}
private WordInfo SplitOneChar(string src)
{
//string src = tok.GetText();
if (src.Length != 1)
{
throw new CompileException("SplitOneChar的内容'" + src + "'长度不为1");
}
WordInfo word = GetFromTree(src);
if (word != null)
{
return(word);
}
else
{
WordInfo info2 = new WordInfo(src, WordKind.Unkown);
return(info2);
}
}
public void AfterSegment(SuperLinkedList <WordInfo> result)
{
SuperLinkedListNode <WordInfo> node = result.First;
while (node != null)
{
if (node.Value.WordType == WordType.English)
{
int position = node.Value.Word.IndexOf("Nokia", 0, StringComparison.CurrentCultureIgnoreCase);
if (position >= 0 &&
!node.Value.Word.Equals("Nokia", StringComparison.CurrentCultureIgnoreCase))
{
WordInfo wordinfo = new WordInfo("Nokia", node.Value.Position + position, node.Value.Pos,
node.Value.Frequency, node.Value.Rank, node.Value.WordType, node.Value.OriginalWordType);
node = result.AddAfter(node, wordinfo);
}
}
node = node.Next;
}
}
public void AfterSegment(SuperLinkedList<WordInfo> result)
{
SuperLinkedListNode<WordInfo> node = result.First;
while (node != null)
{
if (node.Value.WordType == WordType.English)
{
int position = node.Value.Word.IndexOf("Nokia", 0, StringComparison.CurrentCultureIgnoreCase);
if (position >= 0 &&
!node.Value.Word.Equals("Nokia", StringComparison.CurrentCultureIgnoreCase))
{
WordInfo wordinfo = new WordInfo("Nokia", node.Value.Position + position, node.Value.Pos,
node.Value.Frequency, node.Value.Rank, node.Value.WordType, node.Value.OriginalWordType);
node = result.AddAfter(node, wordinfo);
}
}
node = node.Next;
}
}
/// <summary>
/// 获取特定字符串在整个字符串位置集合
/// </summary>
/// <param name="wordInfo"></param>
/// <returns></returns>
private static List <int> GetStrIndexsFromAllText(WordInfo wordInfo)
{
List <int> subIndex = new List <int>();
try
{
if (wordInfo != null && !string.IsNullOrEmpty(wordInfo.AllText) && !string.IsNullOrEmpty(wordInfo.UnValidText))
{
int ii = wordInfo.AllText.IndexOf(wordInfo.UnValidText);
while (ii >= 0 && ii < wordInfo.AllText.Length)
{
subIndex.Add(ii);
ii = wordInfo.AllText.IndexOf(wordInfo.UnValidText, ii + 1);
}
}
}
catch (Exception ex)
{
}
return(subIndex);
}
public void UpdateWordInfo(WordInfo word)
{
currentCharacter = 0;
pinYinArray = word.Pinyin.Split(' ');
characterArray = word.Content.Split(' ');
AndroidUtil.Log(
"拼音: " + GeneralUtils.printArray(pinYinArray) +
"\n内容: " + GeneralUtils.printArray(characterArray) +
"\n详细: " + word.detail);
for (var i = 0; i < pinYinArray.Length; i++)
{
characterGrids[i].pinyin.text = pinYinArray[i];
characterGrids[i].content.text = "";
}
currentPinYin.text = pinYinArray[0];
characterGrids[0].toggle.isOn = true;
tipPinYin.text = infos[currentWord].Pinyin;
tipDetail.text = "释义:" + infos[currentWord].Detail;
}
/// <summary>
/// 图片生成WORD、PDF文件
/// </summary>
/// <returns></returns>
public Dictionary <string, string> ImagesToWordPDF(string docname, string abspath, string FilePath, Dictionary <string, string> imgdic)
{
DateTime dt = DateTime.Now;
if (!Directory.Exists(FilePath))
{
Directory.CreateDirectory(FilePath);
}
string OriginalPathYear = FilePath + "\\" + dt.Year;
if (!Directory.Exists(OriginalPathYear))
{
Directory.CreateDirectory(OriginalPathYear);
}
string OriginalPathdate = OriginalPathYear + "\\" + dt.ToString("yyyyMMdd");
if (!Directory.Exists(OriginalPathdate))
{
Directory.CreateDirectory(OriginalPathdate);
}
string wordtimeStr = dt.ToString("yyyyMMddHHmmssffff") + new Random().Next(10000, 99999);
string wordfileName = docname + wordtimeStr + ".docx";
string wordPath = Path.Combine(OriginalPathdate, wordfileName);
string pdftimeStr = dt.ToString("yyyyMMddHHmmssffff") + new Random().Next(10000, 99999);
string pdffileName = docname + pdftimeStr + ".pdf";
string pdfPath = Path.Combine(OriginalPathdate, pdffileName);
WordInfo info = new WordInfo(abspath, wordPath, pdfPath);
info.AddPictures(imgdic);
info.WordToPdf();
info.Dispose();
Dictionary <string, string> doc = new Dictionary <string, string>();
doc.Add("WordPath", dt.Year + "/" + dt.ToString("yyyyMMdd") + "/" + wordfileName);
doc.Add("PDFPath", dt.Year + "/" + dt.ToString("yyyyMMdd") + "/" + pdffileName);
return(doc);
}
//I have to optimise this.
public static List <WordInfo> GetSelectedWords(int startSelectionIndex, string selectedText, string fullText)
{
_selectedWords.Clear();
var charIndex = 0;
var selectedSplitted = selectedText.Split(SplitPattern, StringSplitOptions.RemoveEmptyEntries);
for (int i = 0; i < selectedSplitted.Length; i++)
{
for (int j = startSelectionIndex; j < startSelectionIndex + selectedText.Length; j++)
{
if (fullText[j].IsValidChar())
{
charIndex = j;
while (fullText.ElementAtOrDefault(j).IsValidChar())
{
j++;
}
startSelectionIndex = j;
break;
}
}
var pair = GetWordIndexPair(fullText, charIndex);
var info = new WordInfo()
{
GlobalCharIndex = charIndex,
WordIndex = pair.Item1,
Word = pair.Item2
};
_selectedWords.Add(info);
}
return(_selectedWords);
}
public WordInfo SearchWord(string text)
{
List <WordInfo> words = new List <WordInfo>();
foreach (IWordDictionary dict in this)
{
WordInfo word = dict.SearchWord(text);
if (word != null)
{
words.Add(word);
}
}
if (words != null)
{
WordInfo newWord = WordInfo.Merge(words.ToArray());
return(newWord);
}
else
{
return(null);
}
}
{/// <summary>
/// Создание документа
/// </summary>
/// <param name="info"></param>
public static void CreateDoc(WordInfo info)
{
using (WordprocessingDocument wordDocument =
WordprocessingDocument.Create(info.FileName, WordprocessingDocumentType.Document))
{
MainDocumentPart mainPart = wordDocument.AddMainDocumentPart();
mainPart.Document = new Document();
Body docBody = mainPart.Document.AppendChild(new Body());
docBody.AppendChild(CreateParagraph(new WordParagraph
{
Texts = new List <string> {
info.Title
},
TextProperties = new WordParagraphProperties
{
Bold = true,
Size = "24",
JustificationValues = JustificationValues.Center
}
}));
foreach (var component in info.Komlects)
{
docBody.AppendChild(CreateParagraph(new WordParagraph
{
Texts = new List <string> {
component.KomlectName + " - " + component.Price.ToString() + " р."
},
TextProperties = new WordParagraphProperties
{
Bold = true,
Size = "24",
JustificationValues = JustificationValues.Both
}
}));
}
docBody.AppendChild(CreateSectionProperties());
wordDocument.MainDocumentPart.Document.Save();
}
}
private void imageButton_Click(object sender, EventArgs e)
{
Button senderButton = (Button)sender;
int position = tblLayout.GetColumn(senderButton);
WordInfo wordInfo = m_Settings.Words[position];
if (wordInfo.IsHidden)
{
wordInfo.IsHidden = false;
if (wordInfo.IsBadWord)
{
//senderButton.BackgroundImage = GuessTheSong.Properties.Resources.Minus;
senderButton.BackgroundImage = GuessTheSong.Properties.Resources.MinusTall;
}
else
{
//senderButton.BackgroundImage = GuessTheSong.Properties.Resources.Plus;
senderButton.BackgroundImage = GuessTheSong.Properties.Resources.PlusTall;
}
senderButton.Text = wordInfo.Word;
}
ShowSongTextIfGuessed();
}
/// <summary>
///
/// </summary>
protected void GetAndCreateWords()
{
//string[] wordsFromXml = GameFunctions.GetTextXML(challengeTypeString, "WORDS", "word");
//string[] lettersFromXml = GameFunctions.GetTextXML(challengeTypeString, "LETTERS", "letter");
char[] lettersToFilter = challengeTypeString.ToCharArray();
string[] lettersToFilterString = new string[lettersToFilter.Length];
for (int i = 0; i < lettersToFilterString.Length; i++)
{
lettersToFilterString[i] = lettersToFilter[i].ToString();
}
Debug.Log(lettersToFilterString[0]);
//WordsWithLetters wordsWithLetters = GetWords(lettersToFilterString);
//WordsWithLetters wordsWithLetters = GetWords2(lettersToFilterString, (int)gameManager.infoType[ChallengeType.ZCS].Difficulty);
WordsWithLetters wordsWithLetters = GetWords2(lettersToFilterString, 10);
string[] wordsToUse = wordsWithLetters.words;
string[] lettersToUse = wordsWithLetters.letters;
int auxInt = 0;
wordObjects = new List <WordInfo>();
wordsInScreen = new Queue <WordInfo>(4);
foreach (string s in wordsToUse)
{
WordInfo aux = Instantiate(wordPrefab).GetComponent <WordInfo>();
aux.Word = s;
aux.Letter = lettersToUse[auxInt];
aux.GetComponent <TextMesh>().text = aux.Word;
aux.gameObject.SetActive(false);
wordObjects.Add(aux);
auxInt++;
}
AddWordInScreen();
}
public static void SaveWord(EnglishWordSqliteHelper englishWordSource,
EnglishWordSqliteHelper englishWordOutput, EnglishWordTranslationData wordData)
{
if (string.IsNullOrEmpty(wordData.Word))
{
return;
}
//var transformToWordSaveInfo = TransformToWordSaveInfo(wordData);
var previousWord = englishWordSource.GetWord(wordData.Word);
WordInfo newWord = new WordInfo();
newWord.Word = wordData.Word;
if (previousWord != null)
{
newWord.Pronounce = previousWord.Pronounce;
newWord.PronounceFileName = previousWord.PronounceFileName;
}
else
{
newWord.Word = wordData.Word;
}
SetWordPronounceInfo(newWord, wordData);
var newSemanticList = GetSemanticSaveInfos(wordData);
if (newSemanticList.Count > 0)
{
newWord.Semantic = JsonConvert.SerializeObject(GetSemanticSaveInfos(wordData));
}
newWord.Sentence = JsonConvert.SerializeObject(GetSentenceSaveInfos(wordData));
newWord.Phrase = JsonConvert.SerializeObject(GetPhraseSaveInfos(wordData));
newWord.Synonym = JsonConvert.SerializeObject(GetSynonymInfos(wordData));
newWord.Cognate = JsonConvert.SerializeObject(GetCognateInfos(wordData));
englishWordOutput.SaveWord(newWord);
}
private SuperLinkedList<WordInfo> PreSegment(String text)
{
SuperLinkedList<WordInfo> result = GetInitSegment(text);
SuperLinkedListNode<WordInfo> cur = result.First;
while (cur != null)
{
if (_Options.IgnoreSpace)
{
if (cur.Value.WordType == WordType.Space)
{
SuperLinkedListNode<WordInfo> lst = cur;
cur = cur.Next;
result.Remove(lst);
continue;
}
}
switch (cur.Value.WordType)
{
case WordType.SimplifiedChinese:
string inputText = cur.Value.Word;
WordType originalWordType = WordType.SimplifiedChinese;
if (_Options.TraditionalChineseEnabled)
{
string simplified = Microsoft.VisualBasic.Strings.StrConv(cur.Value.Word, Microsoft.VisualBasic.VbStrConv.SimplifiedChinese, 0);
if (simplified != cur.Value.Word)
{
originalWordType = WordType.TraditionalChinese;
inputText = simplified;
}
}
PanGu.Framework.AppendList<Dict.PositionLength> pls = _WordDictionary.GetAllMatchs(inputText, _Options.ChineseNameIdentify);
PanGu.Match.ChsFullTextMatch chsMatch = new PanGu.Match.ChsFullTextMatch(_WordDictionary);
chsMatch.Options = _Options;
chsMatch.Parameters = _Parameters;
SuperLinkedList<WordInfo> chsMatchWords = chsMatch.Match(pls.Items, cur.Value.Word, pls.Count);
SuperLinkedListNode<WordInfo> curChsMatch = chsMatchWords.First;
while (curChsMatch != null)
{
WordInfo wi = curChsMatch.Value;
wi.Position += cur.Value.Position;
wi.OriginalWordType = originalWordType;
wi.WordType = originalWordType;
if (_Options.OutputSimplifiedTraditional)
{
if (_Options.TraditionalChineseEnabled)
{
string newWord;
WordType wt;
if (originalWordType == WordType.SimplifiedChinese)
{
newWord = Microsoft.VisualBasic.Strings.StrConv(wi.Word,
Microsoft.VisualBasic.VbStrConv.TraditionalChinese, 0);
wt = WordType.TraditionalChinese;
}
else
{
newWord = Microsoft.VisualBasic.Strings.StrConv(wi.Word,
Microsoft.VisualBasic.VbStrConv.SimplifiedChinese, 0);
wt = WordType.SimplifiedChinese;
}
if (newWord != wi.Word)
{
WordInfo newWordInfo = new WordInfo(wi);
newWordInfo.Word = newWord;
newWordInfo.OriginalWordType = originalWordType;
newWordInfo.WordType = wt;
newWordInfo.Rank = _Parameters.SimplifiedTraditionalRank;
newWordInfo.Position = wi.Position;
chsMatchWords.AddBefore(curChsMatch, newWordInfo);
}
}
}
curChsMatch = curChsMatch.Next;
}
SuperLinkedListNode<WordInfo> lst = result.AddAfter(cur, chsMatchWords);
SuperLinkedListNode<WordInfo> removeItem = cur;
cur = lst.Next;
result.Remove(removeItem);
break;
case WordType.English:
cur.Value.Rank = _Parameters.EnglishRank;
List<string> output;
cur.Value.Word = ConvertChineseCapitalToAsiic(cur.Value.Word);
if (_Options.IgnoreCapital)
{
cur.Value.Word = cur.Value.Word.ToLower();
}
if (_Options.EnglishSegment)
{
string lower = cur.Value.Word.ToLower();
if (lower != cur.Value.Word)
{
result.AddBefore(cur, new WordInfo(lower, cur.Value.Position, POS.POS_A_NX, 1,
_Parameters.EnglishLowerRank, WordType.English, WordType.English));
}
string stem = GetStem(lower);
if (!string.IsNullOrEmpty(stem))
{
if (lower != stem)
{
result.AddBefore(cur, new WordInfo(stem, cur.Value.Position, POS.POS_A_NX, 1,
_Parameters.EnglishStemRank, WordType.English, WordType.English));
}
}
}
if (_Options.MultiDimensionality)
{
if (Framework.Regex.GetMatchStrings(cur.Value.Word, PATTERNS, true, out output))
{
int outputCount = 0;
foreach (string str in output)
{
if (!string.IsNullOrEmpty(str))
{
outputCount++;
if (outputCount > 1)
{
break;
}
}
}
if (outputCount > 1)
{
int position = cur.Value.Position;
foreach (string splitWord in output)
{
if (string.IsNullOrEmpty(splitWord))
{
continue;
}
WordInfo wi;
if (splitWord[0] >= '0' && splitWord[0] <= '9')
{
wi = new WordInfo(splitWord, POS.POS_A_M, 1);
wi.Position = position;
wi.Rank = _Parameters.NumericRank;
wi.OriginalWordType = WordType.English;
wi.WordType = WordType.Numeric;
}
else
{
wi = new WordInfo(splitWord, POS.POS_A_NX, 1);
wi.Position = position;
wi.Rank = _Parameters.EnglishRank;
wi.OriginalWordType = WordType.English;
wi.WordType = WordType.English;
}
result.AddBefore(cur, wi);
position += splitWord.Length;
}
}
}
}
if (!MergeEnglishSpecialWord(text, result, ref cur))
{
cur = cur.Next;
}
break;
case WordType.Numeric:
cur.Value.Word = ConvertChineseCapitalToAsiic(cur.Value.Word);
cur.Value.Rank = _Parameters.NumericRank;
if (!MergeEnglishSpecialWord(text, result, ref cur))
{
cur = cur.Next;
}
//cur = cur.Next;
break;
case WordType.Symbol:
cur.Value.Rank = _Parameters.SymbolRank;
cur = cur.Next;
break;
default:
cur = cur.Next;
break;
}
}
return result;
}
public void Contains_String()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo mi1 = new WordInfo("continuous", 0, 0, WordLocation.Content);
collection.Add(mi1);
Assert.IsTrue(collection.Contains("continuous"), "Collection should contain string");
Assert.IsFalse(collection.Contains("taskbar"), "Collection should not contain string");
Assert.IsFalse(collection.Contains(null as string), "Contains should return false");
Assert.IsFalse(collection.Contains(""), "Contains should return false");
}
public void Constructor_EmptyText()
{
WordInfo info = new WordInfo("", 0, 0, WordLocation.Content);
}
public void Remove()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo mi1 = new WordInfo("goose", 1, 0, WordLocation.Content);
WordInfo mi2 = new WordInfo("hello", 12, 0, WordLocation.Content);
collection.Add(mi1);
Assert.IsTrue(collection.Contains(mi1), "Collection should contain item");
Assert.IsFalse(collection.Contains(mi2), "Collection should not contain item");
Assert.IsFalse(collection.Contains(null as WordInfo), "Contains should return false");
}
public void UnderlineWord(Graphics g, WordInfo wi)
{
if(TextLength<=1) return;
UnderlineWord(g, wi.start, wi.word.Length);
}
public void Constructor_NullText()
{
WordInfo info = new WordInfo(null, 0, 0, WordLocation.Content);
}
public void CopyTo_InvalidIndex_TooBig()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo[] results = new WordInfo[10];
collection.CopyTo(results, 10);
}
public void CopyTo_NoSpaceAtIndex()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo mi1 = new WordInfo("home", 0, 0, WordLocation.Content);
WordInfo mi2 = new WordInfo("taskbar", 100, 0, WordLocation.Content);
collection.Add(mi1);
collection.Add(mi2);
WordInfo[] matches = new WordInfo[2];
collection.CopyTo(matches, 1);
}
public void CopyTo_ArrayTooSmall()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo mi1 = new WordInfo("home", 0, 0, WordLocation.Content);
WordInfo mi2 = new WordInfo("taskbar", 100, 0, WordLocation.Content);
collection.Add(mi1);
collection.Add(mi2);
WordInfo[] matches = new WordInfo[1];
collection.CopyTo(matches, 0);
}
public void CopyTo_InvalidIndex_Negative()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo[] results = new WordInfo[10];
collection.CopyTo(results, -1);
}
public void CopyTo()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo mi1 = new WordInfo("continuous", 0, 0, WordLocation.Content);
WordInfo mi2 = new WordInfo("goose", 34, 0, WordLocation.Content);
collection.Add(mi1);
collection.Add(mi2);
WordInfo[] matches = new WordInfo[2];
collection.CopyTo(matches, 0);
Assert.AreEqual(mi1, matches[0], "Wrong match item");
Assert.AreEqual(mi2, matches[1], "Wrong match item");
matches = new WordInfo[3];
collection.CopyTo(matches, 0);
Assert.AreEqual(mi1, matches[0], "Wrong match item");
Assert.AreEqual(mi2, matches[1], "Wrong match item");
Assert.IsNull(matches[2], "Non-null item");
matches = new WordInfo[3];
collection.CopyTo(matches, 1);
Assert.IsNull(matches[0], "Non-null item");
Assert.AreEqual(mi1, matches[1], "Wrong match item");
Assert.AreEqual(mi2, matches[2], "Wrong match item");
}
public void Contains_WordInfo()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo mi1 = new WordInfo("continuous", 0, 0, WordLocation.Content);
WordInfo mi2 = new WordInfo("taskbar", 21, 0, WordLocation.Content);
collection.Add(mi1);
Assert.IsTrue(collection.Contains(mi1), "Collection should contain item");
Assert.IsFalse(collection.Contains(mi2), "Collection should not contain item");
Assert.IsFalse(collection.Contains(null as WordInfo), "Contains should return false");
}
/// <summary>
/// Stores a document in the index.
/// </summary>
/// <param name="document">The document.</param>
/// <param name="keywords">The document keywords, if any, an empty array or <c>null</c> otherwise.</param>
/// <param name="content">The content of the document.</param>
/// <param name="state">A state object that is passed to the IndexStorer SaveDate/DeleteData function.</param>
/// <returns>The number of indexed words (including duplicates).</returns>
/// <remarks>Indexing the content of the document is <b>O(n)</b>,
/// where <b>n</b> is the total number of words in the document.</remarks>
public int StoreDocument(IDocument document, string[] keywords, string content, object state) {
if(document == null) throw new ArgumentNullException("document");
if(keywords == null) keywords = new string[0];
if(content == null) throw new ArgumentNullException("content");
RemoveDocument(document, state);
keywords = ScrewTurn.Wiki.SearchEngine.Tools.CleanupKeywords(keywords);
// Prepare content words
WordInfo[] contentWords = document.Tokenize(content);
contentWords = ScrewTurn.Wiki.SearchEngine.Tools.RemoveStopWords(contentWords, stopWords);
// Prepare title words
WordInfo[] titleWords = document.Tokenize(document.Title);
titleWords = ScrewTurn.Wiki.SearchEngine.Tools.RemoveStopWords(titleWords, stopWords);
for(int i = 0; i < titleWords.Length; i++) {
titleWords[i] = new WordInfo(titleWords[i].Text, titleWords[i].FirstCharIndex, titleWords[i].WordIndex, WordLocation.Title);
}
// Prepare keywords
WordInfo[] words = new WordInfo[keywords.Length];
int count = 0;
for(int i = 0; i < words.Length; i++) {
words[i] = new WordInfo(keywords[i], (ushort)count, (ushort)i, WordLocation.Keywords);
count += 1 + keywords[i].Length;
}
return connector.SaveDataForDocument(document, contentWords, titleWords, words, state);
}
private void OnIdle(object sender, EventArgs e)
{
if(_spellUpdateNeeded)
{
string str=Text;
string []words=str.Split(new char[]{' ', ',' , '\'' , '.', ':', '-', '!', '?'});
ArrayList wrongWordList=new ArrayList();
int l=0;
for(int i=0; i<str.Length; i++)
{
if(char.IsLetterOrDigit(str[i]))
{
l++;
}
else
{
if(l>0)
{
string word=str.Substring(i-l, l);
if(word.Length>0 && _spell.TestWord(word)==false )
{
WordInfo wi=new WordInfo();
wi.start=i-l;
wi.word=word;
wrongWordList.Add(wi);
}
}
l=0;
}
}
/* foreach(string word in words)
{
if(word.Length>0 && wrongWordList.Contains(word)==false
&& _spell.TestWord(word)==false )
{
wrongWordList.Add(word);
}
}*/
WrongWord=wrongWordList;
Invalidate();
}
_spellUpdateNeeded=false;
}
public void GetEnumerator()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo mi1 = new WordInfo("goose", 1, 0, WordLocation.Content);
WordInfo mi2 = new WordInfo("hello", 12, 0, WordLocation.Content);
collection.Add(mi2);
collection.Add(mi1);
int count = 0;
foreach(WordInfo r in collection) {
if(count == 0) Assert.AreEqual(mi1, r, "Wrong item at position 0");
if(count == 1) Assert.AreEqual(mi2, r, "Wrong item at position 1");
count++;
}
Assert.AreEqual(2, count, "Wrong count - enumerator does not work");
}
public WordInfo WordFromPos(Point pt)
{
int charpos=CharFromPos(pt);
string str=Text;
if(!char.IsLetterOrDigit(str[charpos])) return WordInfo.Zero;
int start=charpos;
int end=charpos;
while(start>0 && char.IsLetterOrDigit(str[start-1]))
{
start--;
}
while(end<str.Length && char.IsLetterOrDigit(str[end]))
{
end++;
}
WordInfo wi=new WordInfo();
wi.word=str.Substring(start, end-start).Trim();
wi.start=start;
return wi;
}
public void Indexer()
{
WordInfoCollection collection = new WordInfoCollection();
WordInfo mi1 = new WordInfo("taskbar", 1, 0, WordLocation.Content);
WordInfo mi2 = new WordInfo("goose", 12, 0, WordLocation.Content);
collection.Add(mi2);
collection.Add(mi1);
Assert.AreEqual(mi1, collection[0], "Wrong item at position 0");
Assert.AreEqual(mi2, collection[1], "Wrong item at position 0");
}
/// <summary>
/// Saves data for a new document.
/// </summary>
/// <param name="document">The document.</param>
/// <param name="content">The content words.</param>
/// <param name="title">The title words.</param>
/// <param name="keywords">The keywords.</param>
/// <param name="state">A state object passed from the index (can be <c>null</c> or a <see cref="T:DbTransaction" />).</param>
/// <returns>The number of stored occurrences.</returns>
private int SaveDataForDocument(IDocument document, WordInfo[] content, WordInfo[] title, WordInfo[] keywords, object state)
{
// 1. Insert document
// 2. Insert all new words
// 3. Load all word IDs
// 4. Insert mappings
// On error, return without rolling back if state != null, rollback otherwise
// On completion, commit if state == null
ICommandBuilder builder = GetCommandBuilder();
QueryBuilder queryBuilder = new QueryBuilder(builder);
DbTransaction transaction = null;
if(state != null) transaction = (DbTransaction)state;
else {
DbConnection connection = builder.GetConnection(connString);
transaction = BeginTransaction(connection);
}
uint freeDocumentId = GetFreeElementId(IndexElementType.Documents, transaction);
uint freeWordId = GetFreeElementId(IndexElementType.Words, transaction);
// Insert the document
string query = queryBuilder.InsertInto("IndexDocument",
new string[] { "Id", "Name", "Title", "TypeTag", "DateTime" },
new string[] { "Id", "Name", "Title", "TypeTag", "DateTime" });
List<Parameter> parameters = new List<Parameter>(5);
parameters.Add(new Parameter(ParameterType.Int32, "Id", (int)freeDocumentId));
parameters.Add(new Parameter(ParameterType.String, "Name", document.Name));
parameters.Add(new Parameter(ParameterType.String, "Title", document.Title));
parameters.Add(new Parameter(ParameterType.String, "TypeTag", document.TypeTag));
parameters.Add(new Parameter(ParameterType.DateTime, "DateTime", document.DateTime));
DbCommand command = builder.GetCommand(transaction, query, parameters);
if(ExecuteNonQuery(command, false) != 1) {
if(state == null) RollbackTransaction(transaction);
return -1;
}
document.ID = freeDocumentId;
List<WordInfo> allWords = new List<WordInfo>(content.Length + title.Length + keywords.Length);
allWords.AddRange(content);
allWords.AddRange(title);
allWords.AddRange(keywords);
List<WordInfo> existingWords = new List<WordInfo>(allWords.Count / 2);
Dictionary<string, uint> wordIds = new Dictionary<string, uint>(1024);
// Try to blindly insert all words (assumed to be lowercase and clean from diacritics)
query = queryBuilder.InsertInto("IndexWord", new string[] { "Id", "Text" }, new string[] { "Id", "Text" });
parameters = new List<Parameter>(2);
parameters.Add(new Parameter(ParameterType.Int32, "Id", 0));
parameters.Add(new Parameter(ParameterType.String, "Text", ""));
foreach(WordInfo word in allWords) {
parameters[0].Value = (int)freeWordId;
parameters[1].Value = word.Text;
command = builder.GetCommand(transaction, query, parameters);
if(ExecuteNonQuery(command, false, false) == 1) {
wordIds.Add(word.Text, freeWordId);
freeWordId++;
}
else {
existingWords.Add(word);
}
}
// Load IDs of all existing words
query = queryBuilder.SelectFrom("IndexWord", new string[] { "Id" });
query = queryBuilder.Where(query, "Text", WhereOperator.Equals, "Text");
parameters = new List<Parameter>(1);
parameters.Add(new Parameter(ParameterType.String, "Text", ""));
foreach(WordInfo word in existingWords) {
parameters[0].Value = word.Text;
command = builder.GetCommand(transaction, query, parameters);
int id = ExecuteScalar<int>(command, -1, false);
if(id == -1) {
if(state == null) RollbackTransaction(transaction);
return -1;
}
if(!wordIds.ContainsKey(word.Text)) {
wordIds.Add(word.Text, (uint)id);
}
else if(wordIds[word.Text] != (uint)id) throw new InvalidOperationException("Word ID mismatch");
}
// Insert all mappings
query = queryBuilder.InsertInto("IndexWordMapping",
new string[] { "Word", "Document", "FirstCharIndex", "WordIndex", "Location" },
new string[] { "Word", "Document", "FirstCharIndex", "WordIndex", "Location" });
parameters = new List<Parameter>(5);
parameters.Add(new Parameter(ParameterType.Int32, "Word", 0));
parameters.Add(new Parameter(ParameterType.Int32, "Document", (int)freeDocumentId));
parameters.Add(new Parameter(ParameterType.Int16, "FirstCharIndex", 0));
parameters.Add(new Parameter(ParameterType.Int16, "WordIndex", 0));
parameters.Add(new Parameter(ParameterType.Byte, "Location", 0));
foreach(WordInfo word in allWords) {
parameters[0].Value = (int)wordIds[word.Text];
parameters[1].Value = (int)freeDocumentId;
parameters[2].Value = (short)word.FirstCharIndex;
parameters[3].Value = (short)word.WordIndex;
parameters[4].Value = word.Location.Location;
command = builder.GetCommand(transaction, query, parameters);
if(ExecuteNonQuery(command, false) != 1) {
if(state == null) RollbackTransaction(transaction);
return -1;
}
}
if(state == null) CommitTransaction(transaction);
return allWords.Count;
}
private IEnumerable<WordInfo> Optimize(List<WordInfo> selection, int start, int end)
{
int maxRank = 0;
WordInfo lst = null;
for(int i = start; i < end; i++)
{
if (selection[i].Rank > maxRank)
{
maxRank = selection[i].Rank;
}
}
int rankSum = 0;
int endPosition = selection[start].GetEndPositon();
for (int i = start; i < end; i++)
{
if (endPosition < selection[i].GetEndPositon())
{
endPosition = selection[i].GetEndPositon();
}
if (selection[i].Rank == maxRank)
{
if (lst == null)
{
rankSum += (int)Math.Pow(3, selection[i].Rank);
//yield return selection[i];
}
else if (selection[i].Position >= lst.Position + lst.Word.Length)
{
rankSum += (int)Math.Pow(3, selection[i].Rank);
//yield return selection[i];
}
lst = selection[i];
}
}
WordInfo word = new WordInfo();
word.Position = selection[start].Position;
word.Word = _Content.Substring(word.Position, endPosition - word.Position);
word.Rank = rankSum == 0 ? (int)Math.Pow(3, maxRank) : rankSum;
yield return word;
}
private void BuildWordList(string s, int lineWidth)
{
Debug.Assert(!s.Contains("\n"));
ArrayList<WordInfo> mWordListAL = new ArrayList<WordInfo>();
bool lookingForWs = false;
WordInfo we = new WordInfo();
we.pos = 0;
int spaces = 0;
int totalLength = 0;
for (int i = 0; i < s.Length; i++)
{
char ch = s[i];
if (lookingForWs && ch == ' ')
{
spaces++;
if (we.pos != i)
mWordListAL.Add(we);
we = new WordInfo();
we.spacesBefore = spaces;
we.pos = i + 1;
lookingForWs = false;
continue;
}
else if (ch != ' ')
{
lookingForWs = true;
}
we.length++;
totalLength++;
we.totalLength = totalLength;
if (we.length == lineWidth)
{
mWordListAL.Add(we);
we = new WordInfo();
we.spacesBefore = spaces;
we.pos = i + 1;
}
}
mWordListAL.Add(we);
mWordList = mWordListAL.ToArray();
}
public void Constructor()
{
WordInfo info = new WordInfo("continuous", 2, 0, WordLocation.Content);
Assert.AreEqual(2, info.FirstCharIndex, "Wrong start index");
Assert.AreEqual(10, info.Text.Length, "Wrong length");
}
