{
    "api": "YAML JSON TOON Database",
    "version": "1.0.0",
    "format": "json",
    "dataset": {
        "id": 58,
        "slug": "string-algorithms",
        "title": "String Algorithms and Pattern Matching",
        "description": "String processing algorithms: KMP, Rabin-Karp, Z-algorithm, suffix trees/arrays, Aho-Corasick, and edit distance (Levenshtein).",
        "category": "Data Structures",
        "category_slug": "data-structures",
        "tags": "strings,pattern-matching,kmp,rabin-karp,z-algorithm,suffix-tree,aho-corasick,levenshtein",
        "view_count": 0,
        "created_at": 1778695229,
        "updated_at": 1778695229
    },
    "data": {
        "algorithms": [
            {"name": "Knuth-Morris-Pratt (KMP)", "type": "Pattern Matching", "time": "O(n + m) preprocessing + search", "space": "O(m)", "description": "Uses failure function (longest proper prefix that is also suffix) to skip redundant comparisons", "use_cases": ["Text search in editors", "DNA sequence matching", "Intrusion detection (signature matching)"], "notes": "Preprocessing builds π (pi) table; search never backtracks in text"},
            {"name": "Rabin-Karp", "type": "Pattern Matching (Rolling Hash)", "time": "O(n + m) average, O(nm) worst", "space": "O(1)", "description": "Uses hash of pattern and rolling hash of text windows; matches hash before character-by-character verify", "use_cases": ["Plagiarism detection", "Multiple pattern matching", "Fingerprinting", "Duplicate detection"], "notes": "Extendable to 2D pattern matching; collision probability managed with double hashing"},
            {"name": "Z-Algorithm", "type": "Pattern Matching", "time": "O(n + m)", "space": "O(n + m)", "description": "Computes Z-array: length of longest substring starting at each position that matches a prefix", "use_cases": ["String matching", "Period detection", "Longest common prefix queries"], "notes": "Concatenate pattern$text with sentinel; Z-values ≥ pattern length indicate matches"},
            {"name": "Suffix Tree", "type": "String Index", "build_time": "O(n)", "space": "O(n)", "description": "Compressed trie of all suffixes; enables O(m) pattern search, longest repeated substring, etc.", "use_cases": ["Genomic sequence analysis", "Full-text search", "Longest common substring", "Palindrome detection"], "notes": "Ukkonen's algorithm builds in linear time; high constant factor and memory usage in practice"},
            {"name": "Suffix Array", "type": "String Index", "build_time": "O(n log n) or O(n)", "space": "O(n)", "description": "Sorted array of all suffixes; with LCP array enables most suffix tree operations with less memory", "use_cases": ["Compressed text indexing", "Bioinformatics", "Data compression (BWT)"], "notes": "Binary search for pattern in O(m log n); with LCP array can achieve O(m + log n)"},
            {"name": "Aho-Corasick", "type": "Multi-pattern Matching", "time": "O(n + m + z) where z = number of matches", "space": "O(m)", "description": "Builds automaton from dictionary of patterns; finds all occurrences of all patterns in one text pass", "use_cases": ["Virus/malware signature scanning", "Keyword highlighting", "Content filtering", "Aho-Corasick automaton"], "notes": "Extends KMP failure function to a trie; failure links point to longest proper suffix that is a dictionary prefix"},
            {"name": "Levenshtein Distance (Edit Distance)", "type": "String Similarity", "time": "O(m * n)", "space": "O(min(m,n)) with optimization", "description": "Minimum number of single-character edits (insert, delete, substitute) to transform one string into another", "use_cases": ["Spell checking", "Fuzzy search", "DNA sequence alignment", "Plagiarism detection", "OCR error correction"], "notes": "Dynamic programming; can be optimized with Ukkonen's cutoff for bounded distance queries"}
        ]
    }
}