mirror of
				https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque.git
				synced 2025-11-04 04:12:45 +00:00 
			
		
		
		
	dynamic token visualization
This commit is contained in:
		@@ -7,20 +7,21 @@ class CorpusAnalysisStaticVisualization {
 | 
			
		||||
      stopwords: undefined,
 | 
			
		||||
      originalStopwords: {},
 | 
			
		||||
      stopwordCache: {},
 | 
			
		||||
      promises: {getStopwords: undefined}
 | 
			
		||||
      promises: {getStopwords: undefined},
 | 
			
		||||
      tokenSet: new Set()
 | 
			
		||||
    };
 | 
			
		||||
 | 
			
		||||
    this.app.registerExtension(this);
 | 
			
		||||
  }
 | 
			
		||||
 | 
			
		||||
  async init() {
 | 
			
		||||
  init() {
 | 
			
		||||
    // Init data
 | 
			
		||||
    this.data.corpus = this.app.data.corpus;
 | 
			
		||||
    this.renderGeneralCorpusInfo();
 | 
			
		||||
    this.renderTextInfoList();
 | 
			
		||||
    this.renderTextProportionsGraphic();
 | 
			
		||||
    this.renderTokenList();
 | 
			
		||||
    this.renderFrequenciesGraphic();
 | 
			
		||||
    // this.renderFrequenciesGraphic();
 | 
			
		||||
 | 
			
		||||
    // Add event listeners
 | 
			
		||||
    let frequenciesStopwordSettingModal = document.querySelector('#frequencies-stopwords-setting-modal');
 | 
			
		||||
@@ -46,7 +47,7 @@ class CorpusAnalysisStaticVisualization {
 | 
			
		||||
    let frequenciesTokenCategoryDropdownListElement = document.querySelector("#frequencies-token-category-dropdown");
 | 
			
		||||
    frequenciesTokenCategoryDropdownListElement.addEventListener('click', (event) => {
 | 
			
		||||
      frequenciesTokenCategoryDropdownElement.firstChild.textContent = event.target.innerHTML;
 | 
			
		||||
      this.renderFrequenciesGraphic();
 | 
			
		||||
      this.renderTokenList();
 | 
			
		||||
    });
 | 
			
		||||
 | 
			
		||||
    let frequenciesGraphModeButtons = document.querySelectorAll('.frequencies-graph-mode-button');
 | 
			
		||||
@@ -56,7 +57,7 @@ class CorpusAnalysisStaticVisualization {
 | 
			
		||||
          btn.classList.remove('disabled');
 | 
			
		||||
        });
 | 
			
		||||
        event.target.closest('.frequencies-graph-mode-button').classList.add('disabled');
 | 
			
		||||
        this.renderFrequenciesGraphic();
 | 
			
		||||
        this.renderFrequenciesGraphic(this.data.tokenSet);
 | 
			
		||||
      });
 | 
			
		||||
    });
 | 
			
		||||
 | 
			
		||||
@@ -64,7 +65,8 @@ class CorpusAnalysisStaticVisualization {
 | 
			
		||||
      actionButton.addEventListener('click', (event) => {
 | 
			
		||||
        let action = event.target.closest('.frequencies-stopword-setting-modal-action-buttons').dataset.action;
 | 
			
		||||
        if (action === 'submit') {
 | 
			
		||||
          this.renderFrequenciesGraphic();
 | 
			
		||||
          console.log('Stopwords changed');
 | 
			
		||||
          this.renderTokenList();
 | 
			
		||||
        } else if (action === 'cancel') {
 | 
			
		||||
          this.data.stopwords = structuredClone(this.data.stopwordCache);
 | 
			
		||||
        }
 | 
			
		||||
@@ -208,34 +210,60 @@ class CorpusAnalysisStaticVisualization {
 | 
			
		||||
  }
 | 
			
		||||
 | 
			
		||||
  async renderTokenList() {
 | 
			
		||||
    let corpusData = this.data.corpus.o.staticData;
 | 
			
		||||
    let corpusTokenListElement = document.querySelector('.corpus-token-list');
 | 
			
		||||
    let corpusTokenList = new CorpusTokenList(corpusTokenListElement);
 | 
			
		||||
    let filteredData = this.filterData();
 | 
			
		||||
    let stopwords = this.data.stopwords;
 | 
			
		||||
    if (this.data.stopwords === undefined) {
 | 
			
		||||
      stopwords = await this.getStopwords();
 | 
			
		||||
    }
 | 
			
		||||
    stopwords = Object.values(stopwords).flat();
 | 
			
		||||
    let mostFrequent = Object.entries(corpusData.corpus.freqs.word)
 | 
			
		||||
      .sort((a, b) => b[1] - a[1])
 | 
			
		||||
      .filter(item => !stopwords.includes(corpusData.values.p_attrs.word[item[0]].toLowerCase()))
 | 
			
		||||
    let mostFrequent = Object.entries(filteredData)
 | 
			
		||||
      .sort((a, b) => b[1].count - a[1].count)
 | 
			
		||||
      .filter(item => !stopwords.includes(item[0].toLowerCase()))
 | 
			
		||||
      .slice(0, 4)
 | 
			
		||||
      .map(item => parseInt(item[0]));
 | 
			
		||||
      .map(item => item[0])
 | 
			
		||||
 | 
			
		||||
    let tokenData = [];
 | 
			
		||||
    for (let i = 0; i < Object.values(corpusData.corpus.freqs.word).length; i++) {
 | 
			
		||||
    Object.entries(filteredData).forEach(item => {
 | 
			
		||||
      let resource = {
 | 
			
		||||
        term: corpusData.values.p_attrs.word[i].toLowerCase(),
 | 
			
		||||
        count: corpusData.corpus.freqs.word[i],
 | 
			
		||||
        mostFrequent: mostFrequent.includes(i)
 | 
			
		||||
        term: item[0],
 | 
			
		||||
        count: item[1].count,
 | 
			
		||||
        mostFrequent: mostFrequent.includes(item[0])
 | 
			
		||||
      };
 | 
			
		||||
      if (!Object.values(stopwords).includes(resource.term)) {
 | 
			
		||||
        tokenData.push(resource);
 | 
			
		||||
      }
 | 
			
		||||
    }
 | 
			
		||||
    });
 | 
			
		||||
    corpusTokenList.add(tokenData);
 | 
			
		||||
  }
 | 
			
		||||
 | 
			
		||||
  async renderFrequenciesGraphic() {
 | 
			
		||||
  filterData() {
 | 
			
		||||
    let frequenciesTokenCategoryDropdownElement = document.querySelector('[data-target="frequencies-token-category-dropdown"]');
 | 
			
		||||
    let tokenCategory = frequenciesTokenCategoryDropdownElement.firstChild.textContent.toLowerCase();
 | 
			
		||||
    let corpusData = this.data.corpus.o.staticData;
 | 
			
		||||
    let filteredData = {};
 | 
			
		||||
 | 
			
		||||
    for (let i = 0; i < Object.values(corpusData.corpus.freqs[tokenCategory]).length; i++) {
 | 
			
		||||
      let term = corpusData.values.p_attrs[tokenCategory][i].toLowerCase();
 | 
			
		||||
      let count = corpusData.corpus.freqs[tokenCategory][i];
 | 
			
		||||
 | 
			
		||||
      if (filteredData[term]) {
 | 
			
		||||
        filteredData[term].count += count;
 | 
			
		||||
        filteredData[term].originalIds.push(i);
 | 
			
		||||
      } else {
 | 
			
		||||
        filteredData[term] = {
 | 
			
		||||
          count: count,
 | 
			
		||||
          originalIds: [i]
 | 
			
		||||
        };
 | 
			
		||||
      }
 | 
			
		||||
    }
 | 
			
		||||
    return filteredData;
 | 
			
		||||
  }
 | 
			
		||||
  
 | 
			
		||||
 | 
			
		||||
  renderFrequenciesGraphic(tokenSet) {
 | 
			
		||||
    this.data.tokenSet = tokenSet;
 | 
			
		||||
    let corpusData = this.data.corpus.o.staticData;
 | 
			
		||||
    let frequenciesTokenCategoryDropdownElement = document.querySelector('[data-target="frequencies-token-category-dropdown"]');
 | 
			
		||||
    let frequenciesGraphicElement = document.querySelector('#frequencies-graphic');
 | 
			
		||||
@@ -243,12 +271,16 @@ class CorpusAnalysisStaticVisualization {
 | 
			
		||||
    let graphtype = document.querySelector('.frequencies-graph-mode-button.disabled').dataset.graphType;
 | 
			
		||||
    let tokenCategory = frequenciesTokenCategoryDropdownElement.firstChild.textContent.toLowerCase();
 | 
			
		||||
    
 | 
			
		||||
    let graphData = await this.createFrequenciesGraphData(tokenCategory, texts, graphtype);
 | 
			
		||||
    let graphData = this.createFrequenciesGraphData(tokenCategory, texts, graphtype, tokenSet);
 | 
			
		||||
    let graphLayout = {
 | 
			
		||||
      barmode: graphtype === 'bar' ? 'stack' : '',
 | 
			
		||||
      yaxis: {
 | 
			
		||||
        showticklabels: graphtype === 'markers' ? false : true
 | 
			
		||||
      },
 | 
			
		||||
      height: 627,
 | 
			
		||||
      margin: {
 | 
			
		||||
        l: 17
 | 
			
		||||
      }
 | 
			
		||||
    };
 | 
			
		||||
    let config = {
 | 
			
		||||
      responsive: true,
 | 
			
		||||
@@ -258,31 +290,28 @@ class CorpusAnalysisStaticVisualization {
 | 
			
		||||
    Plotly.newPlot(frequenciesGraphicElement, graphData, graphLayout, config);
 | 
			
		||||
  }
 | 
			
		||||
 | 
			
		||||
  async createFrequenciesGraphData(tokenCategory, texts, graphtype) {
 | 
			
		||||
  createFrequenciesGraphData(tokenCategory, texts, graphtype, tokenSet) {
 | 
			
		||||
    let corpusData = this.data.corpus.o.staticData;
 | 
			
		||||
    let stopwords = this.data.stopwords;
 | 
			
		||||
    if (this.data.stopwords === undefined) {
 | 
			
		||||
      stopwords = await this.getStopwords();
 | 
			
		||||
    }
 | 
			
		||||
    let stopwordList = Object.values(stopwords).flat();
 | 
			
		||||
    let graphData = [];
 | 
			
		||||
    let filteredData = Object.entries(corpusData.corpus.freqs[tokenCategory])
 | 
			
		||||
      .sort((a, b) => b[1] - a[1])
 | 
			
		||||
      .filter(item => !stopwordList.includes(corpusData.values.p_attrs[tokenCategory][item[0]].toLowerCase()))
 | 
			
		||||
      .slice(0, 5);
 | 
			
		||||
 | 
			
		||||
    let filteredData = this.filterData();
 | 
			
		||||
    switch (graphtype) {
 | 
			
		||||
      case 'markers':
 | 
			
		||||
        for (let item of filteredData) {
 | 
			
		||||
          let size = texts.map(text => text[1].freqs[tokenCategory][item[0]] || 0);
 | 
			
		||||
        for (let item of tokenSet) {
 | 
			
		||||
          let textTitles = texts.map(text => `${corpusData.values.s_attrs.text[text[0]].title} (${corpusData.values.s_attrs.text[text[0]].publishing_year})`);
 | 
			
		||||
          let tokenCountPerText = [];
 | 
			
		||||
          for (let originalId of filteredData[item].originalIds) {
 | 
			
		||||
            for (let i = 0; i < texts.length; i++) {
 | 
			
		||||
              tokenCountPerText[i] = (tokenCountPerText[i] || 0) + (texts[i][1].freqs[tokenCategory][originalId] || 0);
 | 
			
		||||
            }
 | 
			
		||||
          }
 | 
			
		||||
          let data = {
 | 
			
		||||
            x: texts.map(text => `${corpusData.values.s_attrs.text[text[0]].title} (${corpusData.values.s_attrs.text[text[0]].publishing_year})`),
 | 
			
		||||
            y: texts.map(text => corpusData.values.p_attrs[tokenCategory][item[0]]),
 | 
			
		||||
            name: corpusData.values.p_attrs[tokenCategory][item[0]],
 | 
			
		||||
            text: texts.map(text => `${corpusData.values.p_attrs[tokenCategory][item[0]]}<br>${text[1].freqs[tokenCategory][item[0]] || 0}`),
 | 
			
		||||
            x: textTitles,
 | 
			
		||||
            y: texts.map(text => item),
 | 
			
		||||
            name: item,
 | 
			
		||||
            text: texts.map(text => `${item}<br>${tokenCountPerText || 0}`),
 | 
			
		||||
            mode: 'markers',
 | 
			
		||||
            marker: {
 | 
			
		||||
              size: size,
 | 
			
		||||
              size: tokenCountPerText,
 | 
			
		||||
              sizeref: 0.4
 | 
			
		||||
            }
 | 
			
		||||
          };
 | 
			
		||||
@@ -290,11 +319,18 @@ class CorpusAnalysisStaticVisualization {
 | 
			
		||||
        }
 | 
			
		||||
        break;
 | 
			
		||||
      default:
 | 
			
		||||
        for (let item of filteredData) {
 | 
			
		||||
        for (let item of tokenSet) {
 | 
			
		||||
          let textTitles = texts.map(text => `${corpusData.values.s_attrs.text[text[0]].title} (${corpusData.values.s_attrs.text[text[0]].publishing_year})`);
 | 
			
		||||
          let tokenCountPerText = [];
 | 
			
		||||
          for (let originalId of filteredData[item].originalIds) {
 | 
			
		||||
            for (let i = 0; i < texts.length; i++) {
 | 
			
		||||
              tokenCountPerText[i] = (tokenCountPerText[i] || 0) + (texts[i][1].freqs[tokenCategory][originalId] || 0);
 | 
			
		||||
            }
 | 
			
		||||
          } 
 | 
			
		||||
          let data = {
 | 
			
		||||
            x: texts.map(text => `${corpusData.values.s_attrs.text[text[0]].title} (${corpusData.values.s_attrs.text[text[0]].publishing_year})`),
 | 
			
		||||
            y: texts.map(text => text[1].freqs[tokenCategory][item[0]] || 0),
 | 
			
		||||
            name: corpusData.values.p_attrs[tokenCategory][item[0]],
 | 
			
		||||
            x: textTitles,
 | 
			
		||||
            y: tokenCountPerText,
 | 
			
		||||
            name: item,
 | 
			
		||||
            type: graphtype
 | 
			
		||||
          };
 | 
			
		||||
          graphData.push(data);
 | 
			
		||||
 
 | 
			
		||||
@@ -296,7 +296,7 @@ class ConcordanceQueryBuilder {
 | 
			
		||||
      this.elements.entity.innerHTML = 'Entity';
 | 
			
		||||
    }
 | 
			
		||||
    this.elements.counter -= 1;
 | 
			
		||||
    if (this.elements.counter <= 0) {
 | 
			
		||||
    if (this.elements.counter === 0) {
 | 
			
		||||
      this.elements.queryContainer.classList.add('hide');
 | 
			
		||||
    }
 | 
			
		||||
    this.queryPreviewBuilder();
 | 
			
		||||
 
 | 
			
		||||
		Reference in New Issue
	
	Block a user