buildpath/match_collector/item_tree.ts

type ItemTree = {
  data: number | undefined
  count: number
  children: Array<ItemTree>
}

function treeInit(): ItemTree {
  return { data: undefined, count: 0, children: [] }
}

function treeNode(data: number, count: number): ItemTree {
  return { data: data, count: count, children: [] }
}

/*
 * Merge a node with an item tree
 */
function nodeMerge(itemtree: ItemTree, node: ItemTree) {
  const item = node.data
  const count = node.count
  let next: ItemTree | null = null

  // Try to find an existing node in this tree level with same item
  for (const node of itemtree.children) {
    if (node.data == item) {
      node.count += 1
      next = node
      break
    }
  }

  // If not found, add item node at this level
  if (next == null) {
    next = treeNode(item, count)
    itemtree.children.push(next)
  }

  return next
}

/*
 * Merge a full build path with an existing item tree
 */
function treeMerge(itemtree: ItemTree, items: Array<number>) {
  let current = itemtree

  for (const item of items) {
    current = nodeMerge(current, { data: item, count: 1, children: [] })
  }
}

function treeCutBranches(itemtree: ItemTree, thresholdCount: number, thresholdPerc: number) {
  // Remove branches that are above threshold count
  while (itemtree.children.length > thresholdCount) {
    const leastUsedBranch = itemtree.children.reduce(
      (a, b) => (Math.min(a.count, b.count) == a.count ? a : b),
      { data: undefined, count: +Infinity, children: [] }
    )
    itemtree.children.splice(itemtree.children.indexOf(leastUsedBranch), 1)
  }

  // Remove branches that are of too low usage
  const toRemove: Array<ItemTree> = []
  for (const child of itemtree.children) {
    if (child.count / itemtree.count < thresholdPerc) {
      toRemove.push(child)
    }
  }
  for (const tr of toRemove) {
    itemtree.children.splice(itemtree.children.indexOf(tr), 1)
  }

  itemtree.children.map(x => treeCutBranches(x, thresholdCount, thresholdPerc))
}

function treeSort(itemtree: ItemTree) {
  itemtree.children.sort((a, b) => b.count - a.count)

  for (const item of itemtree.children) {
    treeSort(item)
  }
}

/*
 * Deep clone an ItemTree
 */
function treeClone(tree: ItemTree): ItemTree {
  return {
    data: tree.data,
    count: tree.count,
    children: tree.children.map(child => treeClone(child))
  }
}

/*
 * Merge two ItemTrees into one
 */
function treeMergeTree(t1: ItemTree, t2: ItemTree): ItemTree {
  // Merge counts for the root
  t1.count += t2.count

  // Merge children from t2 into t1
  for (const child2 of t2.children) {
    // Find matching child in t1 (same data value)
    const matchingChild = t1.children.find(child1 => child1.data === child2.data)

    if (matchingChild) {
      // Recursively merge matching children
      treeMergeTree(matchingChild, child2)
    } else {
      // Add a deep copy of child2 to t1
      t1.children.push(treeClone(child2))
    }
  }

  return t1
}

/*
 * Flatten an ItemTree into a Set of item numbers
 */
function treeToSet(itemtree: ItemTree): Set<number> {
  const items: Set<number> = new Set()

  function traverse(node: ItemTree) {
    if (node.data !== undefined) {
      items.add(node.data)
    }
    for (const child of node.children) {
      traverse(child)
    }
  }

  traverse(itemtree)
  return items
}

/*
 * Calculate similarity between two trees as item sets.
 * Returns a number between 0 and 1, where 1 means identical and 0 means completely different.
 * Uses Jaccard similarity: |A ∩ B| / |A ∪ B|
 * Sets included in one another will have similarity close to 1.
 */
function areTreeSimilars(t1: ItemTree, t2: ItemTree): number {
  const set1 = treeToSet(t1)
  const set2 = treeToSet(t2)

  // Handle empty sets
  if (set1.size === 0 && set2.size === 0) {
    return 1.0
  }

  // Calculate intersection
  const intersection = new Set<number>()
  for (const item of Array.from(set1)) {
    if (set2.has(item)) {
      intersection.add(item)
    }
  }

  // Calculate union
  const union = new Set<number>()
  for (const item of Array.from(set1)) {
    union.add(item)
  }
  for (const item of Array.from(set2)) {
    union.add(item)
  }

  // Jaccard similarity: |intersection| / |union|
  const similarity = intersection.size / Math.min(set1.size, set2.size)

  // Ensure result is between 0 and 1
  return Math.max(0, Math.min(1, similarity))
}

export { ItemTree, treeMerge, treeInit, treeCutBranches, treeSort, treeMergeTree, areTreeSimilars }