Added first working solution.

2025/02/cracking_code_interview_17_26_sparse_similarity/.gitignore

@@ -0,0 +1 @@
+bin

2025/02/cracking_code_interview_17_26_sparse_similarity/Makefile

@@ -0,0 +1,19 @@
+BIN_DIR=bin
+SRC_DIR=src
+DEST=bin/program
+SRC=$(wildcard $(SRC_DIR)/*.cpp)
+BIN=$(patsubst $(SRC_DIR)/%.cpp,$(BIN_DIR)/%.cpp.o,$(SRC))
+
+all: $(DEST)
+
+.PHONY: clean
+
+$(DEST): $(BIN)
+	${CXX} $(LDFLAGS) -o $@ $^
+
+$(BIN_DIR)/%.cpp.o: $(SRC_DIR)/%.cpp
+	@mkdir -p $(BIN_DIR)
+	$(CXX) $(CFLAGS) -c -o $@ $<
+
+clean:
+	rm -rf $(BIN_DIR)

2025/02/cracking_code_interview_17_26_sparse_similarity/input.txt

@@ -0,0 +1,4 @@
+13: {14, 15, 100, 9, 3}
+16: {32, 1, 9, 3, 5}
+19: {15, 29, 2, 6, 8, 7}
+24: {7, 10}

2025/02/cracking_code_interview_17_26_sparse_similarity/src/main.cpp

@@ -0,0 +1,101 @@
+#include <algorithm>
+#include <cstdio>
+#include <cstdlib>
+#include <cstring>
+#include <iterator>
+#include <set>
+#include <map>
+
+const int MAX_BUFFER = 0x1000;
+
+using namespace std;
+
+void process_data(map<int,set<int>> &documents) {
+  fprintf(stderr, "Processing data\n");
+  for (auto it1 = documents.begin(); it1 != documents.end(); it1++) {
+    for (auto it2 = documents.begin(); it2 != documents.end(); it2++) {
+      if (it1->first >= it2->first) {
+        continue;
+      }
+
+      set<int> union_set;
+      set<int> intersection_set;
+
+      for (auto el = it1->second.begin(); el != it1->second.end(); el++) {
+        union_set.insert(*el);
+        if (auto search = it2->second.find(*el); search != it2->second.end()) {
+          intersection_set.insert(*el);
+        }
+      }
+
+      for (auto el = it2->second.begin(); el != it2->second.end(); el++) {
+        union_set.insert(*el);
+      }
+
+      auto common_count = intersection_set.size();
+      auto union_count = union_set.size();
+
+      if (common_count) {
+        
+        fprintf(stderr, "Documents %d and %d have %.2f sparse\n",
+            it1->first, it2->first, (double)common_count / (double)union_count);
+      }
+    }
+  }
+}
+
+void process_input(map<int,set<int>> &documents, char *buffer) {
+  char *it = buffer;
+  set<int> items;
+
+  int doc_id = atoi(it);
+  fprintf(stderr, "Got document id: %d\n", doc_id);
+
+  while (*it && *it != '{') {
+    it++;
+  }
+
+  ++it;
+  
+  do {
+    auto nr = atoi(it);
+    fprintf(stderr, "Got number: %d\n", nr);
+    items.insert(nr);
+    while (*it && *it != ',' && *it != '}') {
+      ++it;
+    }
+
+    if (*it == '}') {
+      break;
+    }
+
+    ++it;
+
+  } while(true);
+
+  fprintf(stderr, "The set contains %d elements\n", items.size());
+
+  documents[doc_id] = items;
+}
+
+int main() {
+  char buffer[MAX_BUFFER];
+  map<int, set<int>> documents;
+  fprintf(stderr, "Provide input: \n");
+  while(1) {
+    if (!fgets(buffer, MAX_BUFFER, stdin)) {
+      fprintf(stderr, "End of file or error\n");
+      break;
+    }
+
+    if (strlen(buffer) <= 0 || buffer[0] == '\n') {
+      break;
+    }
+
+    process_input(documents, buffer);
+  }
+
+  process_data(documents);
+  fprintf(stderr, "Execution finished\n");
+	return 0;
+}