app/static/js/corpus-analysis/query-builder/query-builder.js

@@ -99,14 +99,18 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
 
     // Ensures that metadata is always at the end of the query and if an index is given, inserts the query chip at the given index and if there is a closing tag, inserts the query chip before the closing tag.
     this.removePlaceholder();
+    let lastChild = this.elements.queryInputField.lastChild;
+    let isLastChildTextAnnotation = lastChild && lastChild.dataset.type === 'text-annotation';
     if (!index) {
       let closingTagElement = this.elements.queryInputField.querySelector('[data-closing-tag="true"]');
       if (closingTagElement) {
         index = Array.from(this.elements.queryInputField.children).indexOf(closingTagElement);
       }
     }
-    if (index) {
+    if (dataType !== 'text-annotation' && index) {
       this.elements.queryInputField.insertBefore(queryChipElement, this.elements.queryChipElements[index]);
+    } else if (dataType !== 'text-annotation' && isLastChildTextAnnotation) {
+      this.elements.queryInputField.insertBefore(queryChipElement, lastChild);
     } else {
       this.elements.queryInputField.appendChild(queryChipElement);
     }
@@ -145,6 +149,9 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
       case 'start-entity':
         this.extensions.structuralAttributeBuilderFunctions.editStartEntityChipElement(queryChipElement);
         break;
+      case 'text-annotation':
+        this.extensions.structuralAttributeBuilderFunctions.editTextAnnotationChipElement(queryChipElement);
+        break;
       case 'token':
         let queryElementsContent = this.extensions.tokenAttributeBuilderFunctions.prepareTokenQueryElementsContent(queryChipElement);
         this.extensions.tokenAttributeBuilderFunctions.editTokenChipElement(queryElementsContent);
@@ -322,7 +329,7 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
       if (dropdownId === 'corpus-analysis-concordance-token-incidence-modifiers-dropdown') {
         button.addEventListener('click', () => this.tokenIncidenceModifierHandler(button.dataset.token, button.innerHTML));
       } else if (dropdownId === 'corpus-analysis-concordance-character-incidence-modifiers-dropdown') {
-        button.addEventListener('click', () => this.extensions.tokenAttributeBuilderFunctions.characterIncidenceModifierHandler(button));
+        button.addEventListener('click', () => this.characterIncidenceModifierHandler(button));
       }
     });
   }
@@ -353,7 +360,7 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
     let expertModeInputFieldValue = document.querySelector('#corpus-analysis-concordance-form-query').value;
     let chipElements = this.parseTextToChip(expertModeInputFieldValue);
     let closingTagElements = ['end-sentence', 'end-entity'];
-    let editableElements = ['start-entity',  'token'];
+    let editableElements = ['start-entity', 'text-annotation', 'token'];
     for (let chipElement of chipElements) {
       let isClosingTag = closingTagElements.includes(chipElement['type']);
       let isEditable = editableElements.includes(chipElement['type']);
@@ -386,7 +393,11 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
         pretty: 'Entity End',
         type: 'end-entity'
       },
-      '\\[(word|lemma|pos|simple_pos)=("(?:[^"\\\\]|\\\\")*") ?(%c)? ?((\\&|\\|) ?(word|lemma|pos|simple_pos)=("(?:[^"\\\\]|\\\\")*") ?(%c)? ?)*\\]': {
+      ':: ?match\\.text_[A-Za-z]+="[^"]+"': {
+        pretty: '',
+        type: 'text-annotation'
+      },
+      '\\[(word|lemma|pos|simple_pos)=(("[^"]+")|(\\u0027[^\\u0027]+\\u0027)) ?(%c)? ?((\\&|\\|) ?(word|lemma|pos|simple_pos)=(("[^"]+")|(\\u0027[^\\u0027]+\\u0027)) ?(%c)? ?)*\\]': {
         pretty: '',
         type: 'token'
       },
@@ -439,8 +450,14 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
             case ':: ?match\\.text_[A-Za-z]+="[^"]+"':
               prettyText = stringElement.replace(/:: ?match\.text_|"|"/g, '');
               break;
-            case '\\[(word|lemma|pos|simple_pos)=("(?:[^"\\\\]|\\\\")*") ?(%c)? ?((\\&|\\|) ?(word|lemma|pos|simple_pos)=("(?:[^"\\\\]|\\\\")*") ?(%c)? ?)*\\]':
-              prettyText = stringElement.replace(/^\[|\]$|(?<!\\)"/g, '');
+            case '\\[(word|lemma|pos|simple_pos)=(("[^"]+")|(\\u0027[^\\u0027]+\\u0027)) ?(%c)? ?((\\&|\\|) ?(word|lemma|pos|simple_pos)=(("[^"]+")|(\\u0027[^\\u0027]+\\u0027)) ?(%c)? ?)*\\]':
+              let doubleQuotes = /(word|lemma|pos|simple_pos)="[^"]+"/gi;
+              let singleQuotes = /(word|lemma|pos|simple_pos)='[^']+'/gi;
+              if (doubleQuotes.exec(stringElement)) {
+                prettyText = stringElement.replace(/^\[|\]$|"/g, '');
+              } else if (singleQuotes.exec(stringElement)) {
+                prettyText = stringElement.replace(/^\[|\]$|'/g, '');
+              }
               prettyText = prettyText.replace(/\&/g, ' and ').replace(/\|/g, ' or ');
               break;
             case '(?<!\\[) ?\\{[0-9]+} ?(?![^\\]]\\])':

app/static/js/corpus-analysis/query-builder/token-attribute-builder-functions.js

@@ -285,8 +285,8 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
   }
 
   prepareTokenQueryElementsContent(queryChipElement) {
-    //this regex searches for word or lemma or pos or simple_pos="any string (also quotation marks escaped by backslash) within double quotes" followed by one or no ignore case markers, followed by one or no condition characters.
-    let regex = new RegExp('(word|lemma|pos|simple_pos)=("(?:[^"\\\\]|\\\\")*") ?(%c)? ?(\\&|\\|)?', 'gm');
+    //this regex searches for word or lemma or pos or simple_pos="any string within single or double quotes" followed by one or no ignore case markers, followed by one or no condition characters.
+    let regex = new RegExp('(word|lemma|pos|simple_pos)=(("[^"]+")|(\\\\u0027[^\\\\u0027]+\\\\u0027)) ?(%c)? ?(\\&|\\|)?', 'gm');
     let m;
     let queryElementsContent = [];
     while ((m = regex.exec(queryChipElement.dataset.query)) !== null) {
@@ -299,7 +299,7 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
       if (tokenAttr === 'pos') {
         tokenAttr = 'english-pos';
       }
-      let tokenValue = m[2].replace(/(?<!\\)"/g, '');
+      let tokenValue = m[2].replace(/"|'/g, '');
       let ignoreCase = false;
       let condition = undefined;
       m.forEach((match) => {

migrations/versions/31dd42e5ea6f_.py

@@ -20,7 +20,6 @@ depends_on = None
 
 
 def upgrade():
-    # TODO: Add error handling for sqlalchemy.exc.ProgrammingError
     for user in User.query.all():
         spacy_nlp_pipeline_models_dir = os.path.join(user.path, 'spacy_nlp_pipeline_models')
         if os.path.exists(spacy_nlp_pipeline_models_dir):

migrations/versions/63b2cc26a01f_.py

@@ -17,7 +17,6 @@ depends_on = None
 
 
 def upgrade():
-    # TODO: Add error handling for sqlalchemy.exc.ProgrammingError
     for user in User.query.all():
         old_tesseract_ocr_pipeline_model_path = os.path.join(user.path, 'tesseract_ocr_models')
         new_tesseract_ocr_pipeline_model_path = os.path.join(user.path, 'tesseract_ocr_pipeline_models')