Not logged in.  Login/Logout/Register | List snippets | | Create snippet | Upload image | Upload data

211
LINES

< > BotCompany Repo | #1028128 // Suffix Tree Spike v1 [seems OK]

JavaX source code (Dynamic Module) [tags: use-pretranspiled] - run with: Stefan's OS

Uses 911K of libraries. Click here for Pure Java version (3756L/20K).

!7

// adapted from https://github.com/eugenp/tutorials/tree/master/algorithms-searching/src/main/java/com/baeldung/algorithms/suffixtree

cmodule SuffixTreeSpike > DynPrintLog {
  switchable S text = "hello world what is up in the world";
  switchable S pattern = "world";
  transient SuffixTree tree;
  
  sclass Node {
    S text;
    new L<Node> children;
    int position;

    *(S *text, int *position) {}

    S getText() { ret text; }
    void setText(S text) { this.text = text; }

    int getPosition() { ret position; }
    void setPosition(int position) { this.position = position; }
    L<Node> getChildren() { ret children; }
    void setChildren(L<Node> children) { this.children = children; }

    S printTree(String depthIndicator) {
        S str = "";
        S positionStr = position > -1 ? "[" + position + "]" : "";
        str += depthIndicator + text + positionStr + "\n";

        for (int i = 0; i < children.size(); i++)
          str += children.get(i).printTree(depthIndicator + "\t");
        return str;
    }

    toString { ret printTree(""); }
  }
  
  sclass SuffixTree {
    private static final String WORD_TERMINATION = "$";
    private static final int POSITION_UNDEFINED = -1;
    Node root;
    S fullText;
  
    *(S text) {
        root = new Node("", POSITION_UNDEFINED);
        for (int i = 0; i < text.length(); i++) {
            addSuffix(text.substring(i) + WORD_TERMINATION, i);
        }
        fullText = text;
    }

    public LS searchText(S pattern) {
        //LOGGER.info("Searching for pattern \"{}\"", pattern);
        List<String> result = new ArrayList<>();
        List<Node> nodes = getAllNodesInTraversePath(pattern, root, false);

        if (nodes.size() > 0) {
            Node lastNode = nodes.get(nodes.size() - 1);
            if (lastNode != null) {
                List<Integer> positions = getPositions(lastNode);
                /*positions = positions.stream()
                    .sorted()
                    .collect(Collectors.toList());*/
                sortInPlace(positions);
                positions.forEach(m -> result.add((markPatternInText(m, pattern))));
            }
        }
        return result;
    }

    private void addSuffix(String suffix, int position) {
        //LOGGER.info(">>>>>>>>>>>> Adding new suffix {}", suffix);
        List<Node> nodes = getAllNodesInTraversePath(suffix, root, true);
        if (nodes.size() == 0) {
            addChildNode(root, suffix, position);
            //LOGGER.info("{}", printTree());
        } else {
            Node lastNode = nodes.remove(nodes.size() - 1);
            String newText = suffix;
            if (nodes.size() > 0) {
                String existingSuffixUptoLastNode = nodes.stream()
                    .map(a -> a.getText())
                    .reduce("", String::concat);

                // Remove prefix from newText already included in parent
                newText = newText.substring(existingSuffixUptoLastNode.length());
            }
            extendNode(lastNode, newText, position);
            //LOGGER.info("{}", printTree());
        }
    }

    private List<Integer> getPositions(Node node) {
        List<Integer> positions = new ArrayList<>();
        if (node.getText()
            .endsWith(WORD_TERMINATION)) {
            positions.add(node.getPosition());
        }
        for (int i = 0; i < node.getChildren()
            .size(); i++) {
            positions.addAll(getPositions(node.getChildren()
                .get(i)));
        }
        return positions;
    }

    private String markPatternInText(Integer startPosition, String pattern) {
        String matchingTextLHS = fullText.substring(0, startPosition);
        String matchingText = fullText.substring(startPosition, startPosition + pattern.length());
        String matchingTextRHS = fullText.substring(startPosition + pattern.length());
        return matchingTextLHS + "[" + matchingText + "]" + matchingTextRHS;
    }

    private void addChildNode(Node parentNode, String text, int position) {
        parentNode.getChildren()
            .add(new Node(text, position));
    }

    private void extendNode(Node node, String newText, int position) {
        String currentText = node.getText();
        String commonPrefix = getLongestCommonPrefix(currentText, newText);

        if (commonPrefix != currentText) {
            String parentText = currentText.substring(0, commonPrefix.length());
            String childText = currentText.substring(commonPrefix.length());
            splitNodeToParentAndChild(node, parentText, childText);
        }

        String remainingText = newText.substring(commonPrefix.length());
        addChildNode(node, remainingText, position);
    }

    private void splitNodeToParentAndChild(Node parentNode, String parentNewText, String childNewText) {
        Node childNode = new Node(childNewText, parentNode.getPosition());

        if (parentNode.getChildren()
            .size() > 0) {
            while (parentNode.getChildren()
                .size() > 0) {
                childNode.getChildren()
                    .add(parentNode.getChildren()
                        .remove(0));
            }
        }

        parentNode.getChildren()
            .add(childNode);
        parentNode.setText(parentNewText);
        parentNode.setPosition(POSITION_UNDEFINED);
    }

    private String getLongestCommonPrefix(String str1, String str2) {
        int compareLength = Math.min(str1.length(), str2.length());
        for (int i = 0; i < compareLength; i++) {
            if (str1.charAt(i) != str2.charAt(i)) {
                return str1.substring(0, i);
            }
        }
        return str1.substring(0, compareLength);
    }

    private List<Node> getAllNodesInTraversePath(String pattern, Node startNode, boolean isAllowPartialMatch) {
        List<Node> nodes = new ArrayList<>();
        for (int i = 0; i < startNode.getChildren()
            .size(); i++) {
            Node currentNode = startNode.getChildren()
                .get(i);
            String nodeText = currentNode.getText();
            if (pattern.charAt(0) == nodeText.charAt(0)) {
                if (isAllowPartialMatch && pattern.length() <= nodeText.length()) {
                    nodes.add(currentNode);
                    return nodes;
                }

                int compareLength = Math.min(nodeText.length(), pattern.length());
                for (int j = 1; j < compareLength; j++) {
                    if (pattern.charAt(j) != nodeText.charAt(j)) {
                        if (isAllowPartialMatch) {
                            nodes.add(currentNode);
                        }
                        return nodes;
                    }
                }

                nodes.add(currentNode);
                if (pattern.length() > compareLength) {
                    List<Node> nodes2 = getAllNodesInTraversePath(pattern.substring(compareLength), currentNode, isAllowPartialMatch);
                    if (nodes2.size() > 0) {
                        nodes.addAll(nodes2);
                    } else if (!isAllowPartialMatch) {
                        nodes.add(null);
                    }
                }
                return nodes;
            }
        }
        return nodes;
    }

    S printTree() { ret root.printTree(""); }
  }

  start-thread {
    tree = new SuffixTree(text);
    print(tree.printTree());
    print("Estimated tree size: " + nBytes(guessObjectSize(tree)));
    print(+text);
    print(+pattern);
    pnl(tree.searchText(pattern));
  }
}

download  show line numbers  debug dex  old transpilations   

Travelled to 7 computer(s): bhatertpkbcr, mqqgnosmbjvj, pyentgdyhuwx, pzhvpgtvlbxg, tvejysmllsmz, vouqrxazstgt, xrpafgyirdlv

No comments. add comment

Snippet ID: #1028128
Snippet name: Suffix Tree Spike v1 [seems OK]
Eternal ID of this version: #1028128/7
Text MD5: 203020476937643ad2d171e987647b5e
Transpilation MD5: 3c6e660a3ace1f8d2035233f68cf00b8
Author: stefan
Category: javax / text searching
Type: JavaX source code (Dynamic Module)
Public (visible to everyone): Yes
Archived (hidden from active list): No
Created/modified: 2020-05-23 12:01:48
Source code size: 7805 bytes / 211 lines
Pitched / IR pitched: No / No
Views / Downloads: 233 / 415
Version history: 6 change(s)
Referenced in: [show references]