Methods and systems to fingerprint textual information using word runs

A computer implemented method for preventing unauthorized disclosure of secure information, the computer implemented method comprising:

• receiving information including a first text, by a computer system having at least a processor for executing instructions, said first text including a plurality of words;
• normalizing, by said computer system, said first text into a first canonical text expression, said first canonical text expression including a plurality of normalized words;
• generating, at said computer system, a first word hash list for said first canonical text expression, where said first word hash list is generated at a word level;
• generating, at said computer system, a first set of fingerprints for said first word hash list;
• wherein generating said first word hash list includes converting said plurality of normalized words into a plurality of word-value hashes, each specific one of said word-value hashes representing a specific normalized word;
• and
• wherein said generating said first set of fingerprints includes:
• assigning a sliding window of size W, wherein said sliding window is used for reading a W number of said word-value hashes from said first word hash list;
• using said sliding window to read said W number of said word-level hashes from said first word hash list;
• designating said word-value hash with a distinct value within said sliding window as an anchor;
• and
• generating a fingerprint using a fingerprint hash function, wherein said fingerprint hash function is applied over all said word-value hashes contained within a start of said sliding window to where said anchor resides in said sliding window.