/**
* Searches the provided SemanticNode for the keyword and creates an Entity for each occurrence.
* @param keyword the string to search for
* @param type The type of the RedactionEntity to be created
* @param entityType The EntityType of the RedactionEntity to be created
* @param node The SemanticNode to search in
* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
*/
public Stream<RedactionEntity> byString(String keyword, String type, EntityType entityType, SemanticNode node)
/**
* Same as byString, but case insensitive.
*/
public Stream<RedactionEntity> byStringIgnoreCase(String keyword, String type, EntityType entityType, SemanticNode node)
/**
* Searches the provided SemanticNode with the regexPattern and creates a new RedactionEntity with the provided group for each occurrence.
* @param regexPattern The regexPattern
* @param type The type of the RedactionEntity to be created
* @param entityType The EntityType of the RedactionEntity to be created
* @param group the regexPattern group, that should be the entity
* @param node The SemanticNode to search in
* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
*/
public Stream<RedactionEntity> byRegex(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
/**
* Same as byRegex, but case insensitive.
*/
public Stream<RedactionEntity> byRegexIgnoreCase(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
/**
* Same as byRegex, but can handle patterns with linebreaks.
*/
public Stream<RedactionEntity> byRegexWithLineBreaksIgnoreCase(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
/**
* Same as byRegexWithLineBreaks, but case insensitive.
*/
public Stream<RedactionEntity> byRegexWithLineBreaksIgnoreCase(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
/**
* Finds the provided string, and creates a new RedactionEntity from the text after until the end of the line it is found in.
* @param string The keyword to search for
* @param type The type of the RedactionEntity to be created
* @param entityType The EntityType of the RedactionEntity to be created
* @param node The SemanticNode to search in
* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
*/
public Stream<RedactionEntity> lineAfterString(String string, String type, EntityType entityType, SemanticNode node)
/**
* Same as lineAfterString, but with multiple keywords
*/
public Stream<RedactionEntity> lineAfterStrings(List<String> strings, String type, EntityType entityType, SemanticNode node)
/**
* Finds the provided string in a TableCell, and creates a new RedactionEntity in the same line but adjacent table cells to the right.
* @param string The keyword to search for
* @param type The type of the RedactionEntity to be created
* @param entityType The EntityType of the RedactionEntity to be created
* @param table The TableNode to search in
* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
*/
public Stream<RedactionEntity> lineAfterStringAcrossColumns(String string, String type, EntityType entityType, TableNode table)
/**
* Creates a redaction entity based on the given boundary, type, entity type, and semantic node.
*
* @param boundary   The boundary of the redaction entity.
* @param type       The type of the redaction entity.
* @param entityType The entity type of the redaction entity.
* @param node       The semantic node where the boundary is.
* @return An Optional containing the new redaction entity.
*/
public Optional<RedactionEntity> byBoundary(Boundary boundary, String type, EntityType entityType, SemanticNode node)
/**
* Creates new RedactionEntities between the provided start and stop boundaries. The start and stop boundaries are excluded.
* If any boundaries of the new RedactionEntities overlap, only the shortest boundary will be used.
* @param startBoundaries List of start boundaries
* @param stopBoundaries List of stop boundaries
* @param type       The type of the redaction entity.
* @param entityType The entity type of the redaction entity.
* @param node       The semantic node where the boundaries are.
* @return A Stream of new RedactionEntities between the start and stop boundaries
*/
public Stream<RedactionEntity> betweenBoundaries(List<Boundary> startBoundaries, List<Boundary> stopBoundaries, String type, EntityType entityType, SemanticNode node)
/**
* Same as betweenBoundaries, but it creates the start and stop boundaries by performing a text search on the provided SemanticNode.
*/
public Stream<RedactionEntity> betweenStrings(String start, String stop, String type, EntityType entityType, SemanticNode node)
/**
* Same as betweenStrings, but case insensitive.
*/
public Stream<RedactionEntity> betweenStringsIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
/**
* These 6 functions work the same as betweenStrings, but they also include the start and/or stop strings or are case insensitive, depending on their name.
*/
public Stream<RedactionEntity> betweenStringsIncludeStart(String start, String stop, String type, EntityType entityType, SemanticNode node)
public Stream<RedactionEntity> betweenStringsIncludeStartIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
public Stream<RedactionEntity> betweenStringsIncludeEnd(String start, String stop, String type, EntityType entityType, SemanticNode node)
public Stream<RedactionEntity> betweenStringsIncludeEndIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
public Stream<RedactionEntity> betweenStringsIncludeStartAndEnd(String start, String stop, String type, EntityType entityType, SemanticNode node)
public Stream<RedactionEntity> betweenStringsIncludeStartAndEndIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
/**
* Same as betweenBoundaries, but it creates the start and stop boundaries by performing a regex search on the provided SemanticNode.
*/
public Stream<RedactionEntity> betweenRegexes(String regexStart, String regexStop, String type, EntityType entityType, SemanticNode node)
/**
* Same as betweenRegexes, but case insensitive.
*/
public Stream<RedactionEntity> betweenRegexesIgnoreCase(String regexStart, String regexStop, String type, EntityType entityType, SemanticNode node)
/**
* Creates a new RedactionEntity which has the same boundary as the provided SemanticNode.
* @param node The SemanticNode to create a new RedactionEntity from.
* @param type       The type of the redaction entity.
* @param entityType The entity type of the redaction entity.
* @return An optional RedactionEntity. Is empty, if the provided SemanticNode is empty.
*/
public Optional<RedactionEntity> bySemanticNode(SemanticNode node, String type, EntityType entityType)
/**
* Same as bySemanticNode, but ignores the SemanticNode, if its not a Paragraph and all its child SemanticNodes, that are not Paragraphs.
*/
public Stream<RedactionEntity> bySemanticNodeParagraphsOnly(SemanticNode node, String type, EntityType entityType)
/**
* Searches the provided SemanticNode for the provided string, and creates a new RedactionEntity, from the end of the first occurrence of the string until the end of the SemanticNode.
* @param string The string to search for
* @param type       The type of the redaction entity.
* @param entityType The entity type of the redaction entity.
* @param node The SemanticNode to use and search in
* @return An optional RedactionEntity, is empty, if the SemanticNode is empty, or the string isn't found in the SemanticNode.
*/
public Optional<RedactionEntity> semanticNodeAfterString(String string, String type, EntityType entityType, SemanticNode node)