Verwendung von Fuzzy Search und Shiny in R: Eine umfassende Anleitung

Question

Ich versuche, dieses JS-Skript in einer DT-Datentabelle zu verwenden (von dieser Website: https://datatables.net/blog/2021-09-17):

var fsrco = $('#fuzzy-ranking').DataTable({
    fuzzySearch: {
        rankColumn: 3
    },
    sort: [[3, 'desc']]
});
 
fsrco.on('draw', function(){
    fsrco.order([3, 'desc']);
});

Verwenden Sie dieses Skript-Tag:

"//cdn.datatables.net/plug-ins/1.11.3/features/fuzzySearch/dataTables.fuzzySearch.js"

Ich möchte dies in eine DT-Datentabellenfunktion in einer Shiny-App integrieren, in der die Fuzzy-Suche anhand der Rangfolge angewendet wird (oben hat eine höhere Ähnlichkeit), ich möchte jedoch nicht, dass die Rangspalte angezeigt wird.

Ähnlich wie hier, aber ohne die Ranglistenspalte.

Einige grundlegende allgemeine Beispiele:

    library(shiny)
    library(DT)
    js <- c(
      "  var fsrco = $('#fuzzy-ranking').DataTable({",
      "    fuzzySearch: {",
      "        rankColumn: 3",
      "    },",
      "    sort: [[3, 'desc']]",
      "});",
      "fsrco.on('draw', function(){",
      "    fsrco.order([3, 'desc']);",
      "});"
)
    ui <- fluidPage(
      DTOutput("table")
    )
    server <- function(input, output, session){
      output[["table"]] <- renderDT({
        datatable(
          iris,
          selection = "none",
          editable = TRUE, 
          callback = JS(js),
          extensions = "KeyTable",
          options = list(
            keys = TRUE,
            url = "//cdn.datatables.net/plug-ins/1.11.3/features/fuzzySearch/dataTables.fuzzySearch.js"
          )
        )
      })
    }
    shinyApp(ui, server)

Answer 1

这个插件是一个旧插件，它不适用于最新版本的 DataTables。

但是我们可以采用计算相似度的 JavaScript 函数，并通过 SearchBuilder 扩展在自定义搜索中使用它。

首先，复制此 JavaScript 代码并将其保存在名称 levenshtein.js 下：

/*
BSD 2-Clause License

Copyright (c) 2018, Tadeusz Łazurski
All rights reserved.

Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:

* Redistributions of source code must retain the above copyright notice, this
  list of conditions and the following disclaimer.

* Redistributions in binary form must reproduce the above copyright notice,
  this list of conditions and the following disclaimer in the documentation
  and/or other materials provided with the distribution.

THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/

function levenshtein(__this, that, limit) {
  var thisLength = __this.length,
    thatLength = that.length,
    matrix = [];

  // If the limit is not defined it will be calculate from this and that args.
  limit = (limit || (thatLength > thisLength ? thatLength : thisLength)) + 1;

  for (var i = 0; i < limit; i++) {
    matrix[i] = [i];
    matrix[i].length = limit;
  }
  for (i = 0; i < limit; i++) {
    matrix[0][i] = i;
  }

  if (Math.abs(thisLength - thatLength) > (limit || 100)) {
    return prepare(limit || 100);
  }
  if (thisLength === 0) {
    return prepare(thatLength);
  }
  if (thatLength === 0) {
    return prepare(thisLength);
  }

  // Calculate matrix.
  var j, this_i, that_j, cost, min, t;
  for (i = 1; i <= thisLength; ++i) {
    this_i = __this[i - 1];

    // Step 4
    for (j = 1; j <= thatLength; ++j) {
      // Check the jagged ld total so far
      if (i === j && matrix[i][j] > 4) return prepare(thisLength);

      that_j = that[j - 1];
      cost = this_i === that_j ? 0 : 1; // Step 5
      // Calculate the minimum (much faster than Math.min(...)).
      min = matrix[i - 1][j] + 1; // Devarion.
      if ((t = matrix[i][j - 1] + 1) < min) min = t; // Insertion.
      if ((t = matrix[i - 1][j - 1] + cost) < min) min = t; // Substitution.

      // Update matrix.
      matrix[i][j] =
        i > 1 &&
        j > 1 &&
        this_i === that[j - 2] &&
        __this[i - 2] === that_j &&
        (t = matrix[i - 2][j - 2] + cost) < min
          ? t
          : min; // Transposition.
    }
  }

  return prepare(matrix[thisLength][thatLength]);

  function prepare(steps) {
    var length = Math.max(thisLength, thatLength);
    var relative = length === 0 ? 0 : steps / length;
    var similarity = 1 - relative;
    return {
      steps: steps,
      relative: relative,
      similarity: similarity
    };
  }
}

现在，这是 R 代码：

library(DT)

dtable <- datatable(
  iris,
  extensions = "SearchBuilder",
  options = list(
    dom = "Qlfrtip",
    searchBuilder = list(
      conditions = list(
        string = list(
          fuzzy = list(
            conditionName = "Fuzzy search",
            init = JS(
              "function (that, fn, preDefined = null) {",
              "  var el =  $('').on('input', function() { fn(that, this) });",
              "  if (preDefined !== null) {",
              "     $(el).val(preDefined[0]);",
              "  }",
              "  return el;",
              "}"
            ),
            inputValue = JS(
              "function (el) {",
              "  return [$(el[0]).val()];",
              "}"
            ),
            isInputValid = JS(
              "function (el, that) {",
              "  return $(el[0]).val().length !== 0;",
              "}"
            ),
            search = JS(
              "function (value, pattern) {",
              "  var fuzzy = levenshtein(value, pattern[0]);",
              "  return fuzzy.similarity > 0.25;",
              "}"
            )
          )
        )
      )
    )
  )
)

path <- normalizePath("path/to") # the folder containing levenshtein.js
dep <- htmltools::htmlDependency(
  "Levenshtein", "1.0.0", 
  path, script = "levenshtein.js")
dtable$dependencies <- c(dtable$dependencies, list(dep))
dtable

必须选择相似度的阈值。这里我取的是0.25：

return fuzzy.similarity > 0.25;

---

编辑

要在 Shiny 中使用，请使用 server=FALSE:

renderDT({
  dtable
}, server = FALSE)