Deploying to gh-pages from @ ssciwr/AMMICO@251a31763f 🚀

build/html/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 5899cb50f8b06cc7e4e6fc49fb2f9600
+config: e9b6de766ccb900ad5baf44d5b42ad4a
 tags: 645f666f9bcd5a90fca523b33c5a78b7

build/html/_static/basic.css

@@ -4,7 +4,7 @@
  *
  * Sphinx stylesheet -- basic theme.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */

build/html/_static/doctools.js

@@ -4,7 +4,7 @@
  *
  * Base JavaScript utilities for all Sphinx HTML documentation.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */

build/html/_static/language_data.js

@@ -5,7 +5,7 @@
  * This script contains the language-specific data used by searchtools.js,
  * namely the list of stopwords, stemmer, scorer and splitter.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */
@@ -13,7 +13,7 @@
 var stopwords = ["a", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "near", "no", "not", "of", "on", "or", "such", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with"];
 
 
-/* Non-minified version is copied as a separate JS file, is available */
+/* Non-minified version is copied as a separate JS file, if available */
 
 /**
  * Porter Stemmer

build/html/_static/searchtools.js

@@ -4,7 +4,7 @@
  *
  * Sphinx JavaScript utilities for the full-text search.
  *
- * :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
+ * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */
@@ -99,7 +99,7 @@ const _displayItem = (item, searchTerms, highlightTerms) => {
       .then((data) => {
         if (data)
           listItem.appendChild(
-            Search.makeSearchSummary(data, searchTerms)
+            Search.makeSearchSummary(data, searchTerms, anchor)
           );
         // highlight search terms in the summary
         if (SPHINX_HIGHLIGHT_ENABLED)  // set in sphinx_highlight.js
@@ -116,8 +116,8 @@ const _finishSearch = (resultCount) => {
     );
   else
     Search.status.innerText = _(
-      `Search finished, found ${resultCount} page(s) matching the search query.`
-    );
+      "Search finished, found ${resultCount} page(s) matching the search query."
+    ).replace('${resultCount}', resultCount);
 };
 const _displayNextItem = (
   results,
@@ -137,6 +137,22 @@ const _displayNextItem = (
   // search finished, update title and status message
   else _finishSearch(resultCount);
 };
+// Helper function used by query() to order search results.
+// Each input is an array of [docname, title, anchor, descr, score, filename].
+// Order the results by score (in opposite order of appearance, since the
+// `_displayNextItem` function uses pop() to retrieve items) and then alphabetically.
+const _orderResultsByScoreThenName = (a, b) => {
+  const leftScore = a[4];
+  const rightScore = b[4];
+  if (leftScore === rightScore) {
+    // same score: sort alphabetically
+    const leftTitle = a[1].toLowerCase();
+    const rightTitle = b[1].toLowerCase();
+    if (leftTitle === rightTitle) return 0;
+    return leftTitle > rightTitle ? -1 : 1; // inverted is intentional
+  }
+  return leftScore > rightScore ? 1 : -1;
+};
 
 /**
  * Default splitQuery function. Can be overridden in ``sphinx.search`` with a
@@ -160,13 +176,26 @@ const Search = {
   _queued_query: null,
   _pulse_status: -1,
 
-  htmlToText: (htmlString) => {
+  htmlToText: (htmlString, anchor) => {
     const htmlElement = new DOMParser().parseFromString(htmlString, 'text/html');
-    htmlElement.querySelectorAll(".headerlink").forEach((el) => { el.remove() });
-    const docContent = htmlElement.querySelector('[role="main"]');
-    if (docContent !== undefined) return docContent.textContent;
+    for (const removalQuery of [".headerlinks", "script", "style"]) {
+      htmlElement.querySelectorAll(removalQuery).forEach((el) => { el.remove() });
+    }
+    if (anchor) {
+      const anchorContent = htmlElement.querySelector(`[role="main"] ${anchor}`);
+      if (anchorContent) return anchorContent.textContent;
+
       console.warn(
-      "Content block not found. Sphinx search tries to obtain it via '[role=main]'. Could you check your theme or template."
+        `Anchored content block not found. Sphinx search tries to obtain it via DOM query '[role=main] ${anchor}'. Check your theme or template.`
+      );
+    }
+
+    // if anchor not specified or not found, fall back to main content
+    const docContent = htmlElement.querySelector('[role="main"]');
+    if (docContent) return docContent.textContent;
+
+    console.warn(
+      "Content block not found. Sphinx search tries to obtain it via DOM query '[role=main]'. Check your theme or template."
     );
     return "";
   },
@@ -239,16 +268,7 @@ const Search = {
     else Search.deferQuery(query);
   },
 
-  /**
-   * execute search (requires search index to be loaded)
-   */
-  query: (query) => {
-    const filenames = Search._index.filenames;
-    const docNames = Search._index.docnames;
-    const titles = Search._index.titles;
-    const allTitles = Search._index.alltitles;
-    const indexEntries = Search._index.indexentries;
-
+  _parseQuery: (query) => {
     // stem the search terms and add them to the correct list
     const stemmer = new Stemmer();
     const searchTerms = new Set();
@@ -284,16 +304,32 @@ const Search = {
     // console.info("required: ", [...searchTerms]);
     // console.info("excluded: ", [...excludedTerms]);
 
-    // array of [docname, title, anchor, descr, score, filename]
-    let results = [];
+    return [query, searchTerms, excludedTerms, highlightTerms, objectTerms];
+  },
+
+  /**
+   * execute search (requires search index to be loaded)
+   */
+  _performSearch: (query, searchTerms, excludedTerms, highlightTerms, objectTerms) => {
+    const filenames = Search._index.filenames;
+    const docNames = Search._index.docnames;
+    const titles = Search._index.titles;
+    const allTitles = Search._index.alltitles;
+    const indexEntries = Search._index.indexentries;
+
+    // Collect multiple result groups to be sorted separately and then ordered.
+    // Each is an array of [docname, title, anchor, descr, score, filename].
+    const normalResults = [];
+    const nonMainIndexResults = [];
+
     _removeChildren(document.getElementById("search-progress"));
 
-    const queryLower = query.toLowerCase();
+    const queryLower = query.toLowerCase().trim();
     for (const [title, foundTitles] of Object.entries(allTitles)) {
-      if (title.toLowerCase().includes(queryLower) && (queryLower.length >= title.length/2)) {
+      if (title.toLowerCase().trim().includes(queryLower) && (queryLower.length >= title.length/2)) {
         for (const [file, id] of foundTitles) {
           let score = Math.round(100 * queryLower.length / title.length)
-          results.push([
+          normalResults.push([
             docNames[file],
             titles[file] !== title ? `${titles[file]} > ${title}` : title,
             id !== null ? "#" + id : "",
@@ -308,46 +344,47 @@ const Search = {
     // search for explicit entries in index directives
     for (const [entry, foundEntries] of Object.entries(indexEntries)) {
       if (entry.includes(queryLower) && (queryLower.length >= entry.length/2)) {
-        for (const [file, id] of foundEntries) {
-          let score = Math.round(100 * queryLower.length / entry.length)
-          results.push([
+        for (const [file, id, isMain] of foundEntries) {
+          const score = Math.round(100 * queryLower.length / entry.length);
+          const result = [
             docNames[file],
             titles[file],
             id ? "#" + id : "",
             null,
             score,
             filenames[file],
-          ]);
+          ];
+          if (isMain) {
+            normalResults.push(result);
+          } else {
+            nonMainIndexResults.push(result);
+          }
         }
       }
     }
 
     // lookup as object
     objectTerms.forEach((term) =>
-      results.push(...Search.performObjectSearch(term, objectTerms))
+      normalResults.push(...Search.performObjectSearch(term, objectTerms))
     );
 
     // lookup as search terms in fulltext
-    results.push(...Search.performTermsSearch(searchTerms, excludedTerms));
+    normalResults.push(...Search.performTermsSearch(searchTerms, excludedTerms));
 
     // let the scorer override scores with a custom scoring function
-    if (Scorer.score) results.forEach((item) => (item[4] = Scorer.score(item)));
-
-    // now sort the results by score (in opposite order of appearance, since the
-    // display function below uses pop() to retrieve items) and then
-    // alphabetically
-    results.sort((a, b) => {
-      const leftScore = a[4];
-      const rightScore = b[4];
-      if (leftScore === rightScore) {
-        // same score: sort alphabetically
-        const leftTitle = a[1].toLowerCase();
-        const rightTitle = b[1].toLowerCase();
-        if (leftTitle === rightTitle) return 0;
-        return leftTitle > rightTitle ? -1 : 1; // inverted is intentional
+    if (Scorer.score) {
+      normalResults.forEach((item) => (item[4] = Scorer.score(item)));
+      nonMainIndexResults.forEach((item) => (item[4] = Scorer.score(item)));
     }
-      return leftScore > rightScore ? 1 : -1;
-    });
+
+    // Sort each group of results by score and then alphabetically by name.
+    normalResults.sort(_orderResultsByScoreThenName);
+    nonMainIndexResults.sort(_orderResultsByScoreThenName);
+
+    // Combine the result groups in (reverse) order.
+    // Non-main index entries are typically arbitrary cross-references,
+    // so display them after other results.
+    let results = [...nonMainIndexResults, ...normalResults];
 
     // remove duplicate search results
     // note the reversing of results, so that in the case of duplicates, the highest-scoring entry is kept
@@ -361,7 +398,12 @@ const Search = {
       return acc;
     }, []);
 
-    results = results.reverse();
+    return results.reverse();
+  },
+
+  query: (query) => {
+    const [searchQuery, searchTerms, excludedTerms, highlightTerms, objectTerms] = Search._parseQuery(query);
+    const results = Search._performSearch(searchQuery, searchTerms, excludedTerms, highlightTerms, objectTerms);
 
     // for debugging
     //Search.lastresults = results.slice();  // a copy
@@ -466,15 +508,19 @@ const Search = {
       // add support for partial matches
       if (word.length > 2) {
         const escapedWord = _escapeRegExp(word);
+        if (!terms.hasOwnProperty(word)) {
           Object.keys(terms).forEach((term) => {
-          if (term.match(escapedWord) && !terms[word])
+            if (term.match(escapedWord))
               arr.push({ files: terms[term], score: Scorer.partialTerm });
           });
+        }
+        if (!titleTerms.hasOwnProperty(word)) {
           Object.keys(titleTerms).forEach((term) => {
-          if (term.match(escapedWord) && !titleTerms[word])
-            arr.push({ files: titleTerms[word], score: Scorer.partialTitle });
+            if (term.match(escapedWord))
+              arr.push({ files: titleTerms[term], score: Scorer.partialTitle });
           });
         }
+      }
 
       // no match but word was a required one
       if (arr.every((record) => record.files === undefined)) return;
@@ -496,9 +542,8 @@ const Search = {
 
       // create the mapping
       files.forEach((file) => {
-        if (fileMap.has(file) && fileMap.get(file).indexOf(word) === -1)
-          fileMap.get(file).push(word);
-        else fileMap.set(file, [word]);
+        if (!fileMap.has(file)) fileMap.set(file, [word]);
+        else if (fileMap.get(file).indexOf(word) === -1) fileMap.get(file).push(word);
       });
     });
 
@@ -549,8 +594,8 @@ const Search = {
    * search summary for a given text. keywords is a list
    * of stemmed words.
    */
-  makeSearchSummary: (htmlText, keywords) => {
-    const text = Search.htmlToText(htmlText);
+  makeSearchSummary: (htmlText, keywords, anchor) => {
+    const text = Search.htmlToText(htmlText, anchor);
     if (text === "") return null;
 
     const textLower = text.toLowerCase();

build/html/ammico.html

@@ -16,7 +16,7 @@
         <script src="_static/jquery.js?v=5d32c60e"></script>
         <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/doctools.js?v=9a2dae69"></script>
         <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
@@ -63,6 +63,10 @@
 <li class="toctree-l4"><a class="reference internal" href="#text.PostprocessText.get_text_dict"><code class="docutils literal notranslate"><span class="pre">PostprocessText.get_text_dict()</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l3"><a class="reference internal" href="#text.TextAnalyzer"><code class="docutils literal notranslate"><span class="pre">TextAnalyzer</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#text.TextAnalyzer.read_csv"><code class="docutils literal notranslate"><span class="pre">TextAnalyzer.read_csv()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l3"><a class="reference internal" href="#text.TextDetector"><code class="docutils literal notranslate"><span class="pre">TextDetector</span></code></a><ul>
 <li class="toctree-l4"><a class="reference internal" href="#text.TextDetector.analyse_image"><code class="docutils literal notranslate"><span class="pre">TextDetector.analyse_image()</span></code></a></li>
 <li class="toctree-l4"><a class="reference internal" href="#text.TextDetector.clean_text"><code class="docutils literal notranslate"><span class="pre">TextDetector.clean_text()</span></code></a></li>
@@ -283,6 +287,24 @@
 
 </dd></dl>
 
+<dl class="py class">
+<dt class="sig sig-object py" id="text.TextAnalyzer">
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">text.</span></span><span class="sig-name descname"><span class="pre">TextAnalyzer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">csv_path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">column_key</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><span class="pre">None</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#text.TextAnalyzer" title="Link to this definition"></a></dt>
+<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
+<p>Used to get text from a csv and then run the TextDetector on it.</p>
+<dl class="py method">
+<dt class="sig sig-object py" id="text.TextAnalyzer.read_csv">
+<span class="sig-name descname"><span class="pre">read_csv</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">dict</span></span></span><a class="headerlink" href="#text.TextAnalyzer.read_csv" title="Link to this definition"></a></dt>
+<dd><p>Read the CSV file and return the dictionary with the text entries.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns<span class="colon">:</span></dt>
+<dd class="field-odd"><p><strong>dict</strong> – The dictionary with the text entries.</p>
+</dd>
+</dl>
+</dd></dl>
+
+</dd></dl>
+
 <dl class="py class">
 <dt class="sig sig-object py" id="text.TextDetector">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">text.</span></span><span class="sig-name descname"><span class="pre">TextDetector</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">subdict</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">analyse_text</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_names</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">list</span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><span class="pre">None</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">revision_numbers</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">list</span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><span class="pre">None</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#text.TextDetector" title="Link to this definition"></a></dt>
@@ -1056,7 +1078,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="multimodal_search.MultimodalSearch.read_img">
-<span class="sig-name descname"><span class="pre">read_img</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filepath</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">&lt;module</span> <span class="pre">'PIL.Image'</span> <span class="pre">from</span> <span class="pre">'/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/PIL/Image.py'&gt;</span></span></span><a class="headerlink" href="#multimodal_search.MultimodalSearch.read_img" title="Link to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">read_img</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filepath</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">&lt;module</span> <span class="pre">'PIL.Image'</span> <span class="pre">from</span> <span class="pre">'/opt/hostedtoolcache/Python/3.9.19/x64/lib/python3.9/site-packages/PIL/Image.py'&gt;</span></span></span><a class="headerlink" href="#multimodal_search.MultimodalSearch.read_img" title="Link to this definition"></a></dt>
 <dd><p>Load Image from filepath.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
@@ -1070,7 +1092,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="multimodal_search.MultimodalSearch.resize_img">
-<span class="sig-name descname"><span class="pre">resize_img</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">raw_img:</span> <span class="pre">&lt;module</span> <span class="pre">'PIL.Image'</span> <span class="pre">from</span> <span class="pre">'/opt/hostedtoolcache/Python/3.9.18/x64/lib/python3.9/site-packages/PIL/Image.py'&gt;</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#multimodal_search.MultimodalSearch.resize_img" title="Link to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">resize_img</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">raw_img:</span> <span class="pre">&lt;module</span> <span class="pre">'PIL.Image'</span> <span class="pre">from</span> <span class="pre">'/opt/hostedtoolcache/Python/3.9.19/x64/lib/python3.9/site-packages/PIL/Image.py'&gt;</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#multimodal_search.MultimodalSearch.resize_img" title="Link to this definition"></a></dt>
 <dd><p>Proportional resize image to 240 p width.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>

build/html/create_API_key_link.html

@@ -16,7 +16,7 @@
         <script src="_static/jquery.js?v=5d32c60e"></script>
         <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/doctools.js?v=9a2dae69"></script>
         <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>

build/html/genindex.html

@@ -15,7 +15,7 @@
         <script src="_static/jquery.js?v=5d32c60e"></script>
         <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/doctools.js?v=9a2dae69"></script>
         <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
@@ -420,12 +420,14 @@
 </li>
       <li><a href="ammico.html#multimodal_search.MultimodalSearch.read_and_process_images_itm">read_and_process_images_itm() (multimodal_search.MultimodalSearch method)</a>
 </li>
-      <li><a href="ammico.html#multimodal_search.MultimodalSearch.read_img">read_img() (multimodal_search.MultimodalSearch method)</a>
+      <li><a href="ammico.html#text.TextAnalyzer.read_csv">read_csv() (text.TextAnalyzer method)</a>
 </li>
-      <li><a href="ammico.html#text.TextDetector.remove_linebreaks">remove_linebreaks() (text.TextDetector method)</a>
+      <li><a href="ammico.html#multimodal_search.MultimodalSearch.read_img">read_img() (multimodal_search.MultimodalSearch method)</a>
 </li>
   </ul></td>
   <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="ammico.html#text.TextDetector.remove_linebreaks">remove_linebreaks() (text.TextDetector method)</a>
+</li>
       <li><a href="ammico.html#multimodal_search.MultimodalSearch.resize_img">resize_img() (multimodal_search.MultimodalSearch method)</a>
 </li>
       <li><a href="ammico.html#utils.DownloadResource.resources">resources (utils.DownloadResource attribute)</a>
@@ -480,11 +482,13 @@
       </ul></li>
       <li><a href="ammico.html#text.TextDetector.text_ner">text_ner() (text.TextDetector method)</a>
 </li>
-  </ul></td>
-  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="ammico.html#text.TextDetector.text_sentiment_transformers">text_sentiment_transformers() (text.TextDetector method)</a>
 </li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="ammico.html#text.TextDetector.text_summary">text_summary() (text.TextDetector method)</a>
+</li>
+      <li><a href="ammico.html#text.TextAnalyzer">TextAnalyzer (class in text)</a>
 </li>
       <li><a href="ammico.html#text.TextDetector">TextDetector (class in text)</a>
 </li>

build/html/index.html

@@ -16,9 +16,11 @@
         <script src="_static/jquery.js?v=5d32c60e"></script>
         <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/doctools.js?v=9a2dae69"></script>
         <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
+        <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
+        <script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
     <link rel="search" title="Search" href="search.html" />

build/html/license_link.html

@@ -16,7 +16,7 @@
         <script src="_static/jquery.js?v=5d32c60e"></script>
         <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/doctools.js?v=9a2dae69"></script>
         <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>

build/html/modules.html

@@ -16,7 +16,7 @@
         <script src="_static/jquery.js?v=5d32c60e"></script>
         <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/doctools.js?v=9a2dae69"></script>
         <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
@@ -104,6 +104,10 @@
 <li class="toctree-l3"><a class="reference internal" href="ammico.html#text.PostprocessText.get_text_dict"><code class="docutils literal notranslate"><span class="pre">PostprocessText.get_text_dict()</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l2"><a class="reference internal" href="ammico.html#text.TextAnalyzer"><code class="docutils literal notranslate"><span class="pre">TextAnalyzer</span></code></a><ul>
+<li class="toctree-l3"><a class="reference internal" href="ammico.html#text.TextAnalyzer.read_csv"><code class="docutils literal notranslate"><span class="pre">TextAnalyzer.read_csv()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="ammico.html#text.TextDetector"><code class="docutils literal notranslate"><span class="pre">TextDetector</span></code></a><ul>
 <li class="toctree-l3"><a class="reference internal" href="ammico.html#text.TextDetector.analyse_image"><code class="docutils literal notranslate"><span class="pre">TextDetector.analyse_image()</span></code></a></li>
 <li class="toctree-l3"><a class="reference internal" href="ammico.html#text.TextDetector.clean_text"><code class="docutils literal notranslate"><span class="pre">TextDetector.clean_text()</span></code></a></li>

build/html/notebooks/DemoNotebook_ammico.html

@@ -17,7 +17,7 @@
         <script src="../_static/jquery.js?v=5d32c60e"></script>
         <script src="../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="../_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="../_static/doctools.js?v=888ff710"></script>
+        <script src="../_static/doctools.js?v=9a2dae69"></script>
         <script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
         <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
@@ -390,7 +390,7 @@ directly on the right next to the image. This way, the user can directly inspect
 <section id="The-detector-modules">
 <h1>The detector modules<a class="headerlink" href="#The-detector-modules" title="Link to this heading"></a></h1>
 <p>The different detector modules with their options are explained in more detail in this section. ## Text detector Text on the images can be extracted using the <code class="docutils literal notranslate"><span class="pre">TextDetector</span></code> class (<code class="docutils literal notranslate"><span class="pre">text</span></code> module). The text is initally extracted using the Google Cloud Vision API and then translated into English with googletrans. The translated text is cleaned of whitespace, linebreaks, and numbers using Python syntax and spaCy.</p>
-<p><img alt="19be893e1a8b438bb04555d1ae58848e" class="no-scaled-link" src="../_images/text_detector.png" style="width: 800px;" /></p>
+<p><img alt="75ebf2c2a5044568a5af13e792d45319" class="no-scaled-link" src="../_images/text_detector.png" style="width: 800px;" /></p>
 <p>The user can set if the text should be further summarized, and analyzed for sentiment and named entity recognition, by setting the keyword <code class="docutils literal notranslate"><span class="pre">analyse_text</span></code> to <code class="docutils literal notranslate"><span class="pre">True</span></code> (the default is <code class="docutils literal notranslate"><span class="pre">False</span></code>). If set, the transformers pipeline is used for each of these tasks, with the default models as of 03/2023. Other models can be selected by setting the optional keyword <code class="docutils literal notranslate"><span class="pre">model_names</span></code> to a list of selected models, on for each task:
 <code class="docutils literal notranslate"><span class="pre">model_names=[&quot;sshleifer/distilbart-cnn-12-6&quot;,</span> <span class="pre">&quot;distilbert-base-uncased-finetuned-sst-2-english&quot;,</span> <span class="pre">&quot;dbmdz/bert-large-cased-finetuned-conll03-english&quot;]</span></code> for summary, sentiment, and ner. To be even more specific, revision numbers can also be selected by specifying the optional keyword <code class="docutils literal notranslate"><span class="pre">revision_numbers</span></code> to a list of revision numbers for each model, for example <code class="docutils literal notranslate"><span class="pre">revision_numbers=[&quot;a4f8f3e&quot;,</span> <span class="pre">&quot;af0f99b&quot;,</span> <span class="pre">&quot;f2482bf&quot;]</span></code>.</p>
 <p>Please note that for the Google Cloud Vision API (the TextDetector class) you need to set a key in order to process the images. This key is ideally set as an environment variable using for example</p>
@@ -472,7 +472,7 @@ directly on the right next to the image. This way, the user can directly inspect
 <section id="Image-summary-and-query">
 <h2>Image summary and query<a class="headerlink" href="#Image-summary-and-query" title="Link to this heading"></a></h2>
 <p>The <code class="docutils literal notranslate"><span class="pre">SummaryDetector</span></code> can be used to generate image captions (<code class="docutils literal notranslate"><span class="pre">summary</span></code>) as well as visual question answering (<code class="docutils literal notranslate"><span class="pre">VQA</span></code>).</p>
-<p><img alt="a732a7b033cd457cb8aff189e4fc8ef9" class="no-scaled-link" src="../_images/summary_detector.png" style="width: 800px;" /></p>
+<p><img alt="34686721ef3a4244bcb429faf8862f75" class="no-scaled-link" src="../_images/summary_detector.png" style="width: 800px;" /></p>
 <p>This module is based on the <a class="reference external" href="https://github.com/salesforce/LAVIS">LAVIS</a> library. Since the models can be quite large, an initial object is created which will load the necessary models into RAM/VRAM and then use them in the analysis. The user can specify the type of analysis to be performed using the <code class="docutils literal notranslate"><span class="pre">analysis_type</span></code> keyword. Setting it to <code class="docutils literal notranslate"><span class="pre">summary</span></code> will generate a caption (summary), <code class="docutils literal notranslate"><span class="pre">questions</span></code> will prepare answers (VQA) to a list of questions as set by the user,
 <code class="docutils literal notranslate"><span class="pre">summary_and_questions</span></code> will do both. Note that the desired analysis type needs to be set here in the initialization of the detector object, and not when running the analysis for each image; the same holds true for the selected model.</p>
 <p>The implemented models are listed below.</p>
@@ -725,7 +725,7 @@ directly on the right next to the image. This way, the user can directly inspect
 <section id="Detection-of-faces-and-facial-expression-analysis">
 <h2>Detection of faces and facial expression analysis<a class="headerlink" href="#Detection-of-faces-and-facial-expression-analysis" title="Link to this heading"></a></h2>
 <p>Faces and facial expressions are detected and analyzed using the <code class="docutils literal notranslate"><span class="pre">EmotionDetector</span></code> class from the <code class="docutils literal notranslate"><span class="pre">faces</span></code> module. Initially, it is detected if faces are present on the image using RetinaFace, followed by analysis if face masks are worn (Face-Mask-Detection). The detection of age, gender, race, and emotions is carried out with deepface.</p>
-<p><img alt="b76db59fd4454f0eaf0935641e072dc5" class="no-scaled-link" src="../_images/emotion_detector.png" style="width: 800px;" /></p>
+<p><img alt="48617c903b5d4f0e8d8dca8bd812ca7c" class="no-scaled-link" src="../_images/emotion_detector.png" style="width: 800px;" /></p>
 <p>Depending on the features found on the image, the face detection module returns a different analysis content: If no faces are found on the image, all further steps are skipped and the result <code class="docutils literal notranslate"><span class="pre">&quot;face&quot;:</span> <span class="pre">&quot;No&quot;,</span> <span class="pre">&quot;multiple_faces&quot;:</span> <span class="pre">&quot;No&quot;,</span> <span class="pre">&quot;no_faces&quot;:</span> <span class="pre">0,</span> <span class="pre">&quot;wears_mask&quot;:</span> <span class="pre">[&quot;No&quot;],</span> <span class="pre">&quot;age&quot;:</span> <span class="pre">[None],</span> <span class="pre">&quot;gender&quot;:</span> <span class="pre">[None],</span> <span class="pre">&quot;race&quot;:</span> <span class="pre">[None],</span> <span class="pre">&quot;emotion&quot;:</span> <span class="pre">[None],</span> <span class="pre">&quot;emotion</span> <span class="pre">(category)&quot;:</span> <span class="pre">[None]</span></code> is returned. If one or several faces are found, up to three faces are analyzed if they are partially concealed by a face mask. If
 yes, only age and gender are detected; if no, also race, emotion, and dominant emotion are detected. In case of the latter, the output could look like this: <code class="docutils literal notranslate"><span class="pre">&quot;face&quot;:</span> <span class="pre">&quot;Yes&quot;,</span> <span class="pre">&quot;multiple_faces&quot;:</span> <span class="pre">&quot;Yes&quot;,</span> <span class="pre">&quot;no_faces&quot;:</span> <span class="pre">2,</span> <span class="pre">&quot;wears_mask&quot;:</span> <span class="pre">[&quot;No&quot;,</span> <span class="pre">&quot;No&quot;],</span> <span class="pre">&quot;age&quot;:</span> <span class="pre">[27,</span> <span class="pre">28],</span> <span class="pre">&quot;gender&quot;:</span> <span class="pre">[&quot;Man&quot;,</span> <span class="pre">&quot;Man&quot;],</span> <span class="pre">&quot;race&quot;:</span> <span class="pre">[&quot;asian&quot;,</span> <span class="pre">None],</span> <span class="pre">&quot;emotion&quot;:</span> <span class="pre">[&quot;angry&quot;,</span> <span class="pre">&quot;neutral&quot;],</span> <span class="pre">&quot;emotion</span> <span class="pre">(category)&quot;:</span> <span class="pre">[&quot;Negative&quot;,</span> <span class="pre">&quot;Neutral&quot;]</span></code>, where for the two faces that are detected (given by <code class="docutils literal notranslate"><span class="pre">no_faces</span></code>), some of the values are returned as a list
 with the first item for the first (largest) face and the second item for the second (smaller) face (for example, <code class="docutils literal notranslate"><span class="pre">&quot;emotion&quot;</span></code> returns a list <code class="docutils literal notranslate"><span class="pre">[&quot;angry&quot;,</span> <span class="pre">&quot;neutral&quot;]</span></code> signifying the first face expressing anger, and the second face having a neutral expression).</p>

build/html/notebooks/Example cropposts.html

@@ -17,7 +17,7 @@
         <script src="../_static/jquery.js?v=5d32c60e"></script>
         <script src="../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="../_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="../_static/doctools.js?v=888ff710"></script>
+        <script src="../_static/doctools.js?v=9a2dae69"></script>
         <script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
         <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>

build/html/py-modindex.html

@@ -15,7 +15,7 @@
         <script src="_static/jquery.js?v=5d32c60e"></script>
         <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/doctools.js?v=9a2dae69"></script>
         <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>

build/html/readme_link.html

@@ -16,7 +16,7 @@
         <script src="_static/jquery.js?v=5d32c60e"></script>
         <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/doctools.js?v=9a2dae69"></script>
         <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>

build/html/search.html

@@ -16,7 +16,7 @@
         <script src="_static/jquery.js?v=5d32c60e"></script>
         <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/doctools.js?v=9a2dae69"></script>
         <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>

build/html/set_up_credentials.html

@@ -16,7 +16,7 @@
         <script src="_static/jquery.js?v=5d32c60e"></script>
         <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
         <script src="_static/documentation_options.js?v=d45e8c67"></script>
-        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/doctools.js?v=9a2dae69"></script>
         <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>