@article{oai:ipsj.ixsq.nii.ac.jp:00081778,
 author = {Mohammed, Sahli and Tetsuo, Shibuya and Mohammed, Sahli and Tetsuo, Shibuya},
 issue = {4},
 journal = {情報処理学会論文誌},
 month = {Apr},
 note = {Exact string matching is the problem of finding all occurrences of a pattern P in a text T. The problem is well-known and many sophisticated algorithms have been proposed. Some fast exact string matching algorithms have been described since the 80s (e.g., the Boyer-Moore algorithm and its simplified version the Boyer-Moore-Horspool algorithm). They have been regarded as the standard benchmarks for the practical exact string search literature. In this paper, we propose two algorithms MSBM (Max-Shift BM) and MSH (Max-Shift BMH) both based on the combination of the bad-character rule of the right-most character used in the Boyer-Moore-Horspool algorithm, the extended bad-character rule and the good-suffix rule used in the Gusfield algorithm, which is a modification of the Boyer-Moore algorithm. Only a small extra space and preprocessing time are needed with respect to the BM and BMH algorithms. Nonetheless, empirical results on different data (DNA, Protein and Text Web) with different pattern lengths show that both MSBM and MSH are very fast in practice. MSBM algorithm usually won against other algorithms.
------------------------------ 
This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.20(2012) No.2 (online) 
DOI　http://dx.doi.org/10.2197/ipsjjip.20.419
------------------------------, Exact string matching is the problem of finding all occurrences of a pattern P in a text T. The problem is well-known and many sophisticated algorithms have been proposed. Some fast exact string matching algorithms have been described since the 80s (e.g., the Boyer-Moore algorithm and its simplified version the Boyer-Moore-Horspool algorithm). They have been regarded as the standard benchmarks for the practical exact string search literature. In this paper, we propose two algorithms MSBM (Max-Shift BM) and MSH (Max-Shift BMH) both based on the combination of the bad-character rule of the right-most character used in the Boyer-Moore-Horspool algorithm, the extended bad-character rule and the good-suffix rule used in the Gusfield algorithm, which is a modification of the Boyer-Moore algorithm. Only a small extra space and preprocessing time are needed with respect to the BM and BMH algorithms. Nonetheless, empirical results on different data (DNA, Protein and Text Web) with different pattern lengths show that both MSBM and MSH are very fast in practice. MSBM algorithm usually won against other algorithms.
------------------------------ 
This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.20(2012) No.2 (online) 
DOI　http://dx.doi.org/10.2197/ipsjjip.20.419
------------------------------},
 title = {Max-Shift BM and Max-Shift Horspool: Practical Fast Exact String Matching Algorithms},
 volume = {53},
 year = {2012}
}