fingerprint.dox

/**
 * @file fingerprint.cpp
 * Computing fingerprint of a passage and mathematical distances of two passages.
 */

// Set the number of characters in the a-y alphabet.
#define N 25

/// Number of 2-shingles for a text, called "fingerprint" in this program.
typedef struct Fingerprint {
  unsigned short int data [N][N];
} Fingerprint;

/// Compute the fingerprint of a passage.
Fingerprint getFingerprint(Book book, int start, int length) {
 /// @param book A book in a Bible edition.
 /// @param start Start of the passage in characters.
 /// @param length Length of the passage in characters.
};

/// Compute the fingerprint of a passage.
Fingerprint getFingerprint(string text);

/// Compute the distance of two fingerprints by counting the number of different 2-shingles.
int dist(Fingerprint f1, Fingerprint f2);

/// Compute the fingerprint distance of two passages by counting the number of different 2-shingles.
int dist(const string& text1, const string& text2);

/// Print the distance of two fingerprints by counting the number of different 2-shingles (for debugging).
void printDist(Fingerprint f1, Fingerprint f2);

/// Compute the Jaccard similirity for bags. See Leskovec-Rajamaran-Ullman: Mining of massive datasets,
/// Cambridge University Press, 2014, p. 77-78 (see footnote 2 on page 77).
double jaccard_dist(const string& text1, const string& text2);