From a2ecd6aa857d7f3d95b3ad5e68822a679ef058c5 Mon Sep 17 00:00:00 2001
From: Kai Chappell <git@kschappell.com>
Date: Mon, 28 Apr 2025 23:19:49 +0100
Subject: [PATCH] hard questions

---
 .../median-of-two-sorted-arrays.yaml          | 122 ++++++++++++++
 .../data/questions/merge-k-sorted-lists.yaml  | 149 ++++++++++++++++++
 .../data/questions/trapping-rain-water.yaml   | 129 +++++++++++++++
 3 files changed, 400 insertions(+)
 create mode 100644 backend/data/questions/median-of-two-sorted-arrays.yaml
 create mode 100644 backend/data/questions/merge-k-sorted-lists.yaml
 create mode 100644 backend/data/questions/trapping-rain-water.yaml

diff --git a/backend/data/questions/median-of-two-sorted-arrays.yaml b/backend/data/questions/median-of-two-sorted-arrays.yaml
new file mode 100644
index 0000000..c3813f2
--- /dev/null
+++ b/backend/data/questions/median-of-two-sorted-arrays.yaml
@@ -0,0 +1,122 @@
+title: Median of Two Sorted Arrays
+slug: median-of-two-sorted-arrays
+difficulty: hard
+leetcode_id: 4
+leetcode_url: https://leetcode.com/problems/median-of-two-sorted-arrays/
+categories:
+  - arrays
+  - binary-search
+patterns:
+  - binary-search
+
+description: |
+  Given two sorted arrays `nums1` and `nums2` of size m and n respectively, return the median
+  of the two sorted arrays.
+
+  The overall run time complexity should be O(log(m+n)).
+
+constraints: |
+  - nums1.length == m
+  - nums2.length == n
+  - 0 <= m <= 1000
+  - 0 <= n <= 1000
+  - 1 <= m + n <= 2000
+  - -10^6 <= nums1[i], nums2[i] <= 10^6
+
+examples:
+  - input: "nums1 = [1,3], nums2 = [2]"
+    output: "2.0"
+    explanation: "Merged array is [1,2,3]. Median is 2."
+  - input: "nums1 = [1,2], nums2 = [3,4]"
+    output: "2.5"
+    explanation: "Merged array is [1,2,3,4]. Median is (2+3)/2 = 2.5."
+
+explanation:
+  approach: |
+    1. Binary search on the smaller array for partition point
+    2. Partition both arrays such that left half has (m+n+1)//2 elements
+    3. Check if partition is valid: max(left) <= min(right)
+    4. If valid, compute median from boundary elements
+    5. Adjust binary search bounds based on comparison
+
+  intuition: |
+    The median divides the combined array into two halves of equal size. We don't need to
+    actually merge; we just need to find the correct partition.
+
+    If we choose i elements from nums1 for the left half, we need (m+n+1)//2 - i from nums2.
+    Binary search on i (0 to m) to find where nums1[i-1] <= nums2[j] and nums2[j-1] <= nums1[i].
+
+    This is O(log min(m,n)) since we binary search on the smaller array.
+
+  common_pitfalls:
+    - title: Not handling edge cases at partition
+      description: |
+        When partition is at array boundary (i=0 or i=m), use -inf or inf for boundary values.
+      wrong_approach: "Accessing nums1[i-1] when i=0"
+      correct_approach: "Use float('-inf') if i == 0"
+
+    - title: Binary searching on the longer array
+      description: |
+        Always binary search on the shorter array to ensure valid partition exists
+        and for better efficiency.
+
+    - title: Odd vs even total length
+      description: |
+        For odd total, median is max of left half.
+        For even, it's average of max(left) and min(right).
+
+  key_takeaways:
+    - Binary search on partition, not on values
+    - Partition both arrays to have equal halves
+    - Handle boundary conditions with infinity
+    - O(log min(m,n)) is achievable
+
+  time_complexity: "O(log min(m,n))"
+  space_complexity: "O(1)"
+  complexity_explanation: |
+    Time: Binary search on the smaller array.
+    Space: Only constant extra variables.
+
+solutions:
+  - approach_name: Binary Search on Partition (Optimal)
+    is_optimal: true
+    code: |
+      def find_median_sorted_arrays(nums1: list[int], nums2: list[int]) -> float:
+          # Ensure nums1 is the smaller array
+          if len(nums1) > len(nums2):
+              nums1, nums2 = nums2, nums1
+
+          m, n = len(nums1), len(nums2)
+          left, right = 0, m
+          half_len = (m + n + 1) // 2
+
+          while left <= right:
+              i = (left + right) // 2  # Partition in nums1
+              j = half_len - i          # Partition in nums2
+
+              # Handle edge cases with infinity
+              nums1_left = float('-inf') if i == 0 else nums1[i - 1]
+              nums1_right = float('inf') if i == m else nums1[i]
+              nums2_left = float('-inf') if j == 0 else nums2[j - 1]
+              nums2_right = float('inf') if j == n else nums2[j]
+
+              if nums1_left <= nums2_right and nums2_left <= nums1_right:
+                  # Found valid partition
+                  if (m + n) % 2 == 1:
+                      return max(nums1_left, nums2_left)
+                  else:
+                      return (max(nums1_left, nums2_left) +
+                              min(nums1_right, nums2_right)) / 2
+
+              elif nums1_left > nums2_right:
+                  # Too many elements from nums1 in left half
+                  right = i - 1
+              else:
+                  # Too few elements from nums1 in left half
+                  left = i + 1
+
+          return 0.0  # Should never reach here
+    explanation: |
+      Binary search to find correct partition point in the smaller array.
+      Partition is valid when all left elements <= all right elements.
+      Compute median from the four boundary elements.
diff --git a/backend/data/questions/merge-k-sorted-lists.yaml b/backend/data/questions/merge-k-sorted-lists.yaml
new file mode 100644
index 0000000..d0ba9a1
--- /dev/null
+++ b/backend/data/questions/merge-k-sorted-lists.yaml
@@ -0,0 +1,149 @@
+title: Merge k Sorted Lists
+slug: merge-k-sorted-lists
+difficulty: hard
+leetcode_id: 23
+leetcode_url: https://leetcode.com/problems/merge-k-sorted-lists/
+categories:
+  - linked-lists
+  - heap
+patterns:
+  - heap
+
+description: |
+  You are given an array of k linked-lists `lists`, each linked-list is sorted in ascending order.
+
+  Merge all the linked-lists into one sorted linked-list and return it.
+
+constraints: |
+  - k == lists.length
+  - 0 <= k <= 10^4
+  - 0 <= lists[i].length <= 500
+  - -10^4 <= lists[i][j] <= 10^4
+  - lists[i] is sorted in ascending order
+  - The sum of lists[i].length will not exceed 10^4
+
+examples:
+  - input: "lists = [[1,4,5],[1,3,4],[2,6]]"
+    output: "[1,1,2,3,4,4,5,6]"
+    explanation: "Merge three sorted lists into one."
+  - input: "lists = []"
+    output: "[]"
+    explanation: "No lists to merge."
+  - input: "lists = [[]]"
+    output: "[]"
+    explanation: "Single empty list."
+
+explanation:
+  approach: |
+    1. Use a min-heap to track the smallest element among all list heads
+    2. Add the first node from each non-empty list to the heap
+    3. Pop the smallest node, add it to the result
+    4. If that node has a next, add it to the heap
+    5. Continue until heap is empty
+
+  intuition: |
+    At each step, we need to find the minimum among k candidates (the heads of each list).
+    A min-heap gives us this minimum in O(log k) time.
+
+    Since each node is pushed and popped from the heap exactly once, and we have N total nodes,
+    the overall complexity is O(N log k).
+
+  common_pitfalls:
+    - title: Not handling empty lists
+      description: |
+        Some lists might be empty (null). Filter them out or check before adding to heap.
+      wrong_approach: "Adding null to heap"
+      correct_approach: "if node: heappush(...)"
+
+    - title: Heap comparison with ListNode
+      description: |
+        Python's heapq can't compare ListNode objects directly.
+        Either use a tuple (value, index, node) or define __lt__ on ListNode.
+
+    - title: Not advancing the list pointer
+      description: |
+        After adding a node to result, push its next node to the heap, not the same node.
+
+  key_takeaways:
+    - Min-heap efficiently finds minimum among k elements
+    - This is a k-way merge algorithm
+    - Total work is O(N log k) where N is total nodes
+    - Same pattern works for merging k sorted arrays
+
+  time_complexity: "O(N log k)"
+  space_complexity: "O(k)"
+  complexity_explanation: |
+    Time: Each of N nodes is pushed and popped once, each operation is O(log k).
+    Space: Heap holds at most k nodes at any time.
+
+solutions:
+  - approach_name: Min-Heap (Optimal)
+    is_optimal: true
+    code: |
+      import heapq
+
+      class ListNode:
+          def __init__(self, val=0, next=None):
+              self.val = val
+              self.next = next
+
+      def merge_k_lists(lists: list[ListNode | None]) -> ListNode | None:
+          heap = []
+
+          # Add first node from each list with index for tie-breaking
+          for i, node in enumerate(lists):
+              if node:
+                  heapq.heappush(heap, (node.val, i, node))
+
+          dummy = ListNode()
+          current = dummy
+
+          while heap:
+              val, i, node = heapq.heappop(heap)
+              current.next = node
+              current = current.next
+
+              if node.next:
+                  heapq.heappush(heap, (node.next.val, i, node.next))
+
+          return dummy.next
+    explanation: |
+      Use heap to always get the smallest current head.
+      Push next node when popping to maintain k candidates.
+      Index in tuple handles equal values (tie-breaking).
+
+  - approach_name: Divide and Conquer
+    is_optimal: true
+    code: |
+      def merge_k_lists(lists: list[ListNode | None]) -> ListNode | None:
+          if not lists:
+              return None
+
+          def merge_two(l1: ListNode | None, l2: ListNode | None) -> ListNode | None:
+              dummy = ListNode()
+              current = dummy
+
+              while l1 and l2:
+                  if l1.val <= l2.val:
+                      current.next = l1
+                      l1 = l1.next
+                  else:
+                      current.next = l2
+                      l2 = l2.next
+                  current = current.next
+
+              current.next = l1 or l2
+              return dummy.next
+
+          while len(lists) > 1:
+              merged = []
+              for i in range(0, len(lists), 2):
+                  l1 = lists[i]
+                  l2 = lists[i + 1] if i + 1 < len(lists) else None
+                  merged.append(merge_two(l1, l2))
+              lists = merged
+
+          return lists[0]
+    explanation: |
+      Pair up lists and merge, reducing k to k/2 each round.
+      Same complexity as heap approach but iterative merge logic.
diff --git a/backend/data/questions/trapping-rain-water.yaml b/backend/data/questions/trapping-rain-water.yaml
new file mode 100644
index 0000000..10ab08c
--- /dev/null
+++ b/backend/data/questions/trapping-rain-water.yaml
@@ -0,0 +1,129 @@
+title: Trapping Rain Water
+slug: trapping-rain-water
+difficulty: hard
+leetcode_id: 42
+leetcode_url: https://leetcode.com/problems/trapping-rain-water/
+categories:
+  - arrays
+  - two-pointers
+  - stack
+patterns:
+  - two-pointers
+  - monotonic-stack
+
+description: |
+  Given n non-negative integers representing an elevation map where the width of each bar is 1,
+  compute how much water it can trap after raining.
+
+constraints: |
+  - n == height.length
+  - 1 <= n <= 2 * 10^4
+  - 0 <= height[i] <= 10^5
+
+examples:
+  - input: "height = [0,1,0,2,1,0,1,3,2,1,2,1]"
+    output: "6"
+    explanation: "6 units of water are trapped between the bars."
+  - input: "height = [4,2,0,3,2,5]"
+    output: "9"
+    explanation: "9 units of water are trapped."
+
+explanation:
+  approach: |
+    1. Use two pointers from left and right
+    2. Track maximum height seen from each side
+    3. Move the pointer with smaller max height
+    4. Water at current position = max_height - current_height
+    5. Add to total and continue until pointers meet
+
+  intuition: |
+    Water at any position is determined by the minimum of the maximum heights to its left
+    and right, minus the current height.
+
+    With two pointers, we track left_max and right_max. If left_max < right_max, water at
+    the left pointer is limited by left_max (the right side is guaranteed to be at least
+    as tall). We process and move the pointer with the smaller maximum.
+
+  common_pitfalls:
+    - title: Only considering one side
+      description: |
+        Water level is determined by BOTH sides. You need to track maximum from left AND right.
+      wrong_approach: "Only tracking left_max"
+      correct_approach: "Track both left_max and right_max"
+
+    - title: Counting bars instead of water
+      description: |
+        Water trapped at position i is max_height - height[i], not max_height.
+        The bar itself takes up space.
+
+    - title: Not updating max heights
+      description: |
+        Update left_max or right_max before calculating water, not after.
+
+  key_takeaways:
+    - Two pointers eliminate need for O(n) precomputation
+    - Water level = min(left_max, right_max) - current_height
+    - Always process the side with smaller max (guaranteed bound)
+    - This can also be solved with monotonic stack or DP
+
+  time_complexity: "O(n)"
+  space_complexity: "O(1)"
+  complexity_explanation: |
+    Time: Single pass with two pointers.
+    Space: Only a few variables for pointers and max values.
+
+solutions:
+  - approach_name: Two Pointers (Optimal)
+    is_optimal: true
+    code: |
+      def trap(height: list[int]) -> int:
+          if not height:
+              return 0
+
+          left, right = 0, len(height) - 1
+          left_max, right_max = 0, 0
+          water = 0
+
+          while left < right:
+              if height[left] < height[right]:
+                  if height[left] >= left_max:
+                      left_max = height[left]
+                  else:
+                      water += left_max - height[left]
+                  left += 1
+              else:
+                  if height[right] >= right_max:
+                      right_max = height[right]
+                  else:
+                      water += right_max - height[right]
+                  right -= 1
+
+          return water
+    explanation: |
+      Process from both ends. Move the pointer with smaller max height.
+      Add water based on the difference between max height and current height.
+
+  - approach_name: Monotonic Stack
+    is_optimal: false
+    code: |
+      def trap(height: list[int]) -> int:
+          stack = []  # stores indices
+          water = 0
+
+          for i, h in enumerate(height):
+              while stack and h > height[stack[-1]]:
+                  top = stack.pop()
+
+                  if not stack:
+                      break
+
+                  width = i - stack[-1] - 1
+                  bounded_height = min(h, height[stack[-1]]) - height[top]
+                  water += width * bounded_height
+
+              stack.append(i)
+
+          return water
+    explanation: |
+      Stack stores indices of bars in decreasing height order.
+      When a taller bar is found, calculate water trapped in the "valley".