Data update
This commit is contained in:
parent
5150844a7d
commit
4bb20c9b71
7735 changed files with 38060 additions and 199180 deletions
|
|
@ -1,63 +0,0 @@
|
|||
with Ada.Text_IO;
|
||||
|
||||
with GNATColl.Boyer_Moore;
|
||||
|
||||
procedure Boyermoore is
|
||||
|
||||
procedure Search_All (Needle : in String;
|
||||
Haystack : in String)
|
||||
is
|
||||
use Ada.Text_IO;
|
||||
use GNATColl.Boyer_Moore;
|
||||
|
||||
Found : String (Haystack'Range) := (others => ' ');
|
||||
Count : Natural := 0;
|
||||
Motif : Pattern;
|
||||
First : Positive := Haystack'First;
|
||||
Position : Integer;
|
||||
begin
|
||||
Put_Line ("Needle : " & Needle);
|
||||
Put_Line ("Haystack: " & Haystack);
|
||||
Put ("Found : ");
|
||||
|
||||
Compile (Motif => Motif,
|
||||
From_String => Needle,
|
||||
Case_Sensitive => True);
|
||||
loop
|
||||
Position := Search (Motif => Motif,
|
||||
In_String => Haystack (First .. Haystack'Last));
|
||||
exit when Position = -1;
|
||||
|
||||
Count := Count + 1;
|
||||
Found (Position .. Position + Needle'Length - 1) := (others => '^');
|
||||
First := Position + 1;
|
||||
end loop;
|
||||
|
||||
Free (Motif);
|
||||
|
||||
if Count = 0 then
|
||||
Put_Line ("<not found>");
|
||||
else
|
||||
Put_Line (Found);
|
||||
end if;
|
||||
New_Line;
|
||||
end Search_All;
|
||||
|
||||
Text_1 : constant String := "InhisbookseriesTheArtofComputerProgrammingpublishedbyAddisonWesleyDKnuthusesanimaginarycomputertheMIXanditsassociatedmachinecodeandassemblylanguagestoillustratetheconceptsandalgorithmsastheyarepresented";
|
||||
|
||||
Text_2 : constant String := "Nearby farms grew a half acre of alfalfa on the dairy's behalf, with bales of all that alfalfa exchanged for milk.";
|
||||
|
||||
Text_3 : constant String := "GCTAGCTCTACGAGTCTA";
|
||||
Text_4 : constant String := "GGCTATAATGCGTA";
|
||||
Text_5 : constant String := "there would have been a time for such a word";
|
||||
Text_6 : constant String := "needle need noodle needle";
|
||||
|
||||
begin
|
||||
Search_All ("put", Text_1);
|
||||
Search_All ("and", Text_1);
|
||||
Search_All ("alfalfa", Text_2);
|
||||
Search_All ("TCTA", Text_3);
|
||||
Search_All ("TAATAAA", Text_4);
|
||||
Search_All ("word", Text_5);
|
||||
Search_All ("needle", Text_6);
|
||||
end Boyermoore;
|
||||
|
|
@ -1,81 +0,0 @@
|
|||
(defun bm_compile_pattern (pattern)
|
||||
"Compile the pattern to a right most position map"
|
||||
(let ((patLen (length pattern))
|
||||
(rightMap (make-vector 256 -1))
|
||||
(j -1))
|
||||
(while (> patLen (setq j (1+ j)))
|
||||
(aset rightMap (elt pattern j) j) )
|
||||
rightMap
|
||||
)
|
||||
)
|
||||
;;
|
||||
(defun bm_make_suffix_table (text)
|
||||
(let ((suffix-table (make-vector (length text) -1)) (textLen (length text))
|
||||
(suffix-found nil)
|
||||
)
|
||||
(cl-loop for pos from (1- textLen) downto 1 do
|
||||
(setq suffix-found nil)
|
||||
(cl-loop for ptn from (- textLen 2) downto 0 while (not suffix-found) do
|
||||
(let ((start1 pos) (end1 (1- textLen))
|
||||
(start2 (- ptn (- (1- textLen) pos))) (end2 ptn)
|
||||
(matched 't)
|
||||
)
|
||||
(if (< start2 0) (setq start2 0))
|
||||
(cl-loop for idx1 from end1 downto start1 and idx2 from end2 downto start2 while matched do
|
||||
(if (/= (elt text idx1) (elt text idx2))
|
||||
(setq matched nil))
|
||||
)
|
||||
(when matched
|
||||
(aset suffix-table pos start2)
|
||||
(setq suffix-found 't) )
|
||||
)
|
||||
)
|
||||
)
|
||||
suffix-table
|
||||
)
|
||||
)
|
||||
;;
|
||||
;;
|
||||
(defun bm_substring_search (pattern text)
|
||||
"Boyer-Moore string search"
|
||||
(let ((patLen (length pattern))
|
||||
(txtLen (length text))
|
||||
(startPos 0)
|
||||
(result nil)
|
||||
(rightMap (bm_compile_pattern pattern))
|
||||
(suffixTable (bm_make_suffix_table pattern)))
|
||||
;; Continue this loop when no result and not exceed the text length
|
||||
(while (and (not result) (<= (+ startPos patLen) txtLen))
|
||||
|
||||
(let ((idx patLen)
|
||||
(suffixSkip 0)
|
||||
(badCharSkip 0)
|
||||
(skip 0))
|
||||
(while (and (= 0 skip) (<= 0 (setq idx (1- idx))))
|
||||
(setq suffixSkip 0)
|
||||
(setq badCharSkip 0)
|
||||
;; skip when the character at position idx is different
|
||||
(when (/= (elt pattern idx) (elt text (+ startPos idx)))
|
||||
(when (< idx (1- (length pattern)))
|
||||
(setq suffixSkip (aref suffixTable (1+ idx))) )
|
||||
(setq badCharSkip (- idx (aref rightMap (elt text (+ startPos idx)))))
|
||||
;; looking up the right most position in pattern
|
||||
|
||||
(setq skip (max 1 badCharSkip suffixSkip))
|
||||
)
|
||||
)
|
||||
(if (< 0 skip)
|
||||
(setq startPos (+ startPos skip))
|
||||
(setq result startPos)
|
||||
)
|
||||
)
|
||||
)
|
||||
result
|
||||
)
|
||||
)
|
||||
;;
|
||||
(let ((pattern "alfalfa")
|
||||
(full_text "Nearby farms grew a half acre of alfalfa on the dairy's behalf, with bales of all that alfalfa exchanged for milk."))
|
||||
(bm_substring_search pattern full_text) )
|
||||
|
||||
)
|
||||
|
|
@ -1,108 +1,102 @@
|
|||
(phixonline)-->
|
||||
<span style="color: #000080;font-style:italic;">--
|
||||
-- demo\rosetta\BoyerMoore.exw
|
||||
-- ===========================
|
||||
--
|
||||
-- based on https://www-igm.univ-mlv.fr/~lecroq/string/node14.html
|
||||
--</span>
|
||||
<span style="color: #008080;">with</span> <span style="color: #008080;">javascript_semantics</span>
|
||||
<span style="color: #008080;">function</span> <span style="color: #000000;">preBmBc</span><span style="color: #0000FF;">(</span><span style="color: #004080;">string</span> <span style="color: #000000;">pat</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #004080;">integer</span> <span style="color: #000000;">m</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">pat</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #004080;">sequence</span> <span style="color: #000000;">bmBc</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">repeat</span><span style="color: #0000FF;">(</span><span style="color: #000000;">m</span><span style="color: #0000FF;">,</span><span style="color: #000000;">255</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #008080;">for</span> <span style="color: #000000;">i</span><span style="color: #0000FF;">=</span><span style="color: #000000;">1</span> <span style="color: #008080;">to</span> <span style="color: #000000;">m</span><span style="color: #0000FF;">-</span><span style="color: #000000;">1</span> <span style="color: #008080;">do</span>
|
||||
<span style="color: #000000;">bmBc</span><span style="color: #0000FF;">[</span><span style="color: #000000;">pat</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]]</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">m</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">i</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">for</span>
|
||||
<span style="color: #008080;">return</span> <span style="color: #000000;">bmBc</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">function</span>
|
||||
-- demo\rosetta\BoyerMoore.exw
|
||||
-- based on https://www-igm.univ-mlv.fr/~lecroq/string/node14.html
|
||||
with javascript_semantics
|
||||
function preBmBc(string pat)
|
||||
integer m = length(pat)
|
||||
sequence bmBc = repeat(m,255)
|
||||
for i=1 to m-1 do
|
||||
bmBc[pat[i]] = m - i
|
||||
end for
|
||||
return bmBc
|
||||
end function
|
||||
|
||||
<span style="color: #008080;">function</span> <span style="color: #000000;">suffixes</span><span style="color: #0000FF;">(</span><span style="color: #004080;">string</span> <span style="color: #000000;">pat</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #004080;">integer</span> <span style="color: #000000;">m</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">pat</span><span style="color: #0000FF;">),</span> <span style="color: #000000;">g</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">m</span><span style="color: #0000FF;">,</span> <span style="color: #000000;">f</span>
|
||||
<span style="color: #004080;">sequence</span> <span style="color: #000000;">suff</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">repeat</span><span style="color: #0000FF;">(</span><span style="color: #000000;">0</span><span style="color: #0000FF;">,</span><span style="color: #000000;">m</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #000000;">suff</span><span style="color: #0000FF;">[</span><span style="color: #000000;">m</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">m</span><span style="color: #0000FF;">;</span>
|
||||
<span style="color: #008080;">for</span> <span style="color: #000000;">i</span><span style="color: #0000FF;">=</span><span style="color: #000000;">m</span><span style="color: #0000FF;">-</span><span style="color: #000000;">1</span> <span style="color: #008080;">to</span> <span style="color: #000000;">1</span> <span style="color: #008080;">by</span> <span style="color: #0000FF;">-</span><span style="color: #000000;">1</span> <span style="color: #008080;">do</span>
|
||||
<span style="color: #008080;">if</span> <span style="color: #000000;">i</span> <span style="color: #0000FF;">></span> <span style="color: #000000;">g</span> <span style="color: #008080;">and</span> <span style="color: #000000;">suff</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span> <span style="color: #0000FF;">+</span> <span style="color: #000000;">m</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">f</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;"><</span> <span style="color: #000000;">i</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">g</span> <span style="color: #008080;">then</span>
|
||||
<span style="color: #000000;">suff</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">suff</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span> <span style="color: #0000FF;">+</span> <span style="color: #000000;">m</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">f</span><span style="color: #0000FF;">]</span>
|
||||
<span style="color: #008080;">else</span>
|
||||
<span style="color: #008080;">if</span> <span style="color: #000000;">i</span> <span style="color: #0000FF;"><</span> <span style="color: #000000;">g</span> <span style="color: #008080;">then</span> <span style="color: #000000;">g</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">i</span> <span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
|
||||
<span style="color: #000000;">f</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">i</span>
|
||||
<span style="color: #008080;">while</span> <span style="color: #000000;">g</span> <span style="color: #0000FF;">>=</span> <span style="color: #000000;">1</span> <span style="color: #008080;">and</span> <span style="color: #000000;">pat</span><span style="color: #0000FF;">[</span><span style="color: #000000;">g</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">==</span> <span style="color: #000000;">pat</span><span style="color: #0000FF;">[</span><span style="color: #000000;">g</span> <span style="color: #0000FF;">+</span> <span style="color: #000000;">m</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">f</span><span style="color: #0000FF;">]</span> <span style="color: #008080;">do</span>
|
||||
<span style="color: #000000;">g</span> <span style="color: #0000FF;">-=</span> <span style="color: #000000;">1</span><span style="color: #0000FF;">;</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">while</span>
|
||||
<span style="color: #000000;">suff</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">f</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">g</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">for</span>
|
||||
<span style="color: #008080;">return</span> <span style="color: #000000;">suff</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">function</span>
|
||||
function suffixes(string pat)
|
||||
integer m = length(pat), g = m, f
|
||||
sequence suff = repeat(0,m)
|
||||
suff[m] = m;
|
||||
for i=m-1 to 1 by -1 do
|
||||
if i > g and suff[i + m - f] < i - g then
|
||||
suff[i] = suff[i + m - f]
|
||||
else
|
||||
if i < g then g = i end if
|
||||
f = i
|
||||
while g >= 1 and pat[g] == pat[g + m - f] do
|
||||
g -= 1;
|
||||
end while
|
||||
suff[i] = f - g
|
||||
end if
|
||||
end for
|
||||
return suff
|
||||
end function
|
||||
|
||||
<span style="color: #008080;">function</span> <span style="color: #000000;">preBmGs</span><span style="color: #0000FF;">(</span><span style="color: #004080;">string</span> <span style="color: #000000;">pat</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #004080;">integer</span> <span style="color: #000000;">m</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">pat</span><span style="color: #0000FF;">),</span> <span style="color: #000000;">j</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">1</span>
|
||||
<span style="color: #004080;">sequence</span> <span style="color: #000000;">suff</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">suffixes</span><span style="color: #0000FF;">(</span><span style="color: #000000;">pat</span><span style="color: #0000FF;">),</span>
|
||||
<span style="color: #000000;">bmGs</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">repeat</span><span style="color: #0000FF;">(</span><span style="color: #000000;">m</span><span style="color: #0000FF;">,</span><span style="color: #000000;">m</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #008080;">for</span> <span style="color: #000000;">i</span><span style="color: #0000FF;">=</span><span style="color: #000000;">m</span> <span style="color: #008080;">to</span> <span style="color: #000000;">1</span> <span style="color: #008080;">by</span> <span style="color: #0000FF;">-</span><span style="color: #000000;">1</span> <span style="color: #008080;">do</span>
|
||||
<span style="color: #008080;">if</span> <span style="color: #0000FF;">(</span><span style="color: #000000;">suff</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">==</span> <span style="color: #000000;">i</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">then</span>
|
||||
<span style="color: #008080;">while</span> <span style="color: #000000;">j</span> <span style="color: #0000FF;"><</span> <span style="color: #000000;">m</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">i</span> <span style="color: #008080;">do</span>
|
||||
<span style="color: #008080;">if</span> <span style="color: #0000FF;">(</span><span style="color: #000000;">bmGs</span><span style="color: #0000FF;">[</span><span style="color: #000000;">j</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">==</span> <span style="color: #000000;">m</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">then</span>
|
||||
<span style="color: #000000;">bmGs</span><span style="color: #0000FF;">[</span><span style="color: #000000;">j</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">m</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">i</span><span style="color: #0000FF;">;</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
|
||||
<span style="color: #000000;">j</span> <span style="color: #0000FF;">+=</span> <span style="color: #000000;">1</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">while</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">for</span>
|
||||
<span style="color: #008080;">for</span> <span style="color: #000000;">i</span><span style="color: #0000FF;">=</span><span style="color: #000000;">1</span> <span style="color: #008080;">to</span> <span style="color: #000000;">m</span><span style="color: #0000FF;">-</span><span style="color: #000000;">1</span> <span style="color: #008080;">do</span>
|
||||
<span style="color: #000000;">bmGs</span><span style="color: #0000FF;">[</span><span style="color: #000000;">m</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">suff</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]]</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">m</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">i</span><span style="color: #0000FF;">;</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">for</span>
|
||||
<span style="color: #008080;">return</span> <span style="color: #000000;">bmGs</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">function</span>
|
||||
function preBmGs(string pat)
|
||||
integer m = length(pat), j = 1
|
||||
sequence suff = suffixes(pat),
|
||||
bmGs = repeat(m,m)
|
||||
for i=m to 1 by -1 do
|
||||
if (suff[i] == i) then
|
||||
while j < m - i do
|
||||
if (bmGs[j] == m) then
|
||||
bmGs[j] = m - i;
|
||||
end if
|
||||
j += 1
|
||||
end while
|
||||
end if
|
||||
end for
|
||||
for i=1 to m-1 do
|
||||
bmGs[m - suff[i]] = m - i;
|
||||
end for
|
||||
return bmGs
|
||||
end function
|
||||
|
||||
<span style="color: #008080;">procedure</span> <span style="color: #000000;">BM</span><span style="color: #0000FF;">(</span><span style="color: #004080;">string</span> <span style="color: #000000;">pat</span><span style="color: #0000FF;">,</span> <span style="color: #000000;">s</span><span style="color: #0000FF;">,</span> <span style="color: #004080;">bool</span> <span style="color: #000000;">case_insensitive</span> <span style="color: #0000FF;">=</span> <span style="color: #004600;">false</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #004080;">string</span> <span style="color: #000000;">pins</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">sprintf</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"`%s` in `%s`"</span><span style="color: #0000FF;">,{</span><span style="color: #000000;">pat</span><span style="color: #0000FF;">,</span><span style="color: #7060A8;">shorten</span><span style="color: #0000FF;">(</span><span style="color: #000000;">s</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"characters"</span><span style="color: #0000FF;">,</span><span style="color: #000000;">10</span><span style="color: #0000FF;">)})</span>
|
||||
<span style="color: #008080;">if</span> <span style="color: #000000;">case_insensitive</span> <span style="color: #008080;">then</span>
|
||||
<span style="color: #000000;">pat</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">lower</span><span style="color: #0000FF;">(</span><span style="color: #000000;">pat</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #000000;">s</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">lower</span><span style="color: #0000FF;">(</span><span style="color: #000000;">s</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
|
||||
<span style="color: #000080;font-style:italic;">/* Preprocessing */</span>
|
||||
<span style="color: #004080;">sequence</span> <span style="color: #000000;">bmGs</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">preBmGs</span><span style="color: #0000FF;">(</span><span style="color: #000000;">pat</span><span style="color: #0000FF;">),</span>
|
||||
<span style="color: #000000;">bmBc</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">preBmBc</span><span style="color: #0000FF;">(</span><span style="color: #000000;">pat</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #000080;font-style:italic;">/* Searching */</span>
|
||||
<span style="color: #004080;">sequence</span> <span style="color: #000000;">res</span> <span style="color: #0000FF;">=</span> <span style="color: #0000FF;">{}</span>
|
||||
<span style="color: #004080;">integer</span> <span style="color: #000000;">i</span><span style="color: #0000FF;">,</span> <span style="color: #000000;">j</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">0</span><span style="color: #0000FF;">,</span>
|
||||
<span style="color: #000000;">n</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">s</span><span style="color: #0000FF;">),</span>
|
||||
<span style="color: #000000;">m</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">pat</span><span style="color: #0000FF;">),</span>
|
||||
<span style="color: #000000;">cc</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">0</span>
|
||||
<span style="color: #008080;">while</span> <span style="color: #000000;">j</span> <span style="color: #0000FF;"><=</span> <span style="color: #000000;">n</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">m</span> <span style="color: #008080;">do</span>
|
||||
<span style="color: #008080;">for</span> <span style="color: #000000;">i</span><span style="color: #0000FF;">=</span><span style="color: #000000;">m</span> <span style="color: #008080;">to</span> <span style="color: #000000;">1</span> <span style="color: #008080;">by</span> <span style="color: #0000FF;">-</span><span style="color: #000000;">1</span> <span style="color: #008080;">do</span>
|
||||
<span style="color: #000000;">cc</span> <span style="color: #0000FF;">+=</span> <span style="color: #000000;">1</span>
|
||||
<span style="color: #008080;">if</span> <span style="color: #000000;">pat</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]!=</span><span style="color: #000000;">s</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">+</span><span style="color: #000000;">j</span><span style="color: #0000FF;">]</span> <span style="color: #008080;">then</span> <span style="color: #008080;">exit</span> <span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">for</span>
|
||||
<span style="color: #008080;">if</span> <span style="color: #000000;">i</span><span style="color: #0000FF;"><</span><span style="color: #000000;">1</span> <span style="color: #008080;">then</span>
|
||||
<span style="color: #000000;">res</span> <span style="color: #0000FF;">&=</span> <span style="color: #000000;">j</span><span style="color: #0000FF;">+</span><span style="color: #000000;">1</span>
|
||||
<span style="color: #000000;">j</span> <span style="color: #0000FF;">+=</span> <span style="color: #000000;">bmGs</span><span style="color: #0000FF;">[</span><span style="color: #000000;">1</span><span style="color: #0000FF;">];</span>
|
||||
<span style="color: #008080;">else</span>
|
||||
<span style="color: #000000;">j</span> <span style="color: #0000FF;">+=</span> <span style="color: #7060A8;">max</span><span style="color: #0000FF;">(</span><span style="color: #000000;">bmGs</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">],</span> <span style="color: #000000;">bmBc</span><span style="color: #0000FF;">[</span><span style="color: #000000;">s</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span> <span style="color: #0000FF;">+</span> <span style="color: #000000;">j</span><span style="color: #0000FF;">]]</span> <span style="color: #0000FF;">-</span> <span style="color: #000000;">m</span> <span style="color: #0000FF;">+</span> <span style="color: #000000;">i</span><span style="color: #0000FF;">);</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">while</span>
|
||||
<span style="color: #004080;">string</span> <span style="color: #000000;">ccs</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">sprintf</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"(%d character comparisons)"</span><span style="color: #0000FF;">,</span><span style="color: #000000;">cc</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #008080;">if</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">res</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">then</span>
|
||||
<span style="color: #004080;">string</span> <span style="color: #000000;">many</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">ordinant</span><span style="color: #0000FF;">(</span><span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">res</span><span style="color: #0000FF;">))</span>
|
||||
<span style="color: #7060A8;">printf</span><span style="color: #0000FF;">(</span><span style="color: #000000;">1</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"Found %s %s at %v %s\n"</span><span style="color: #0000FF;">,{</span><span style="color: #000000;">pins</span><span style="color: #0000FF;">,</span><span style="color: #000000;">many</span><span style="color: #0000FF;">,</span><span style="color: #000000;">res</span><span style="color: #0000FF;">,</span><span style="color: #000000;">ccs</span><span style="color: #0000FF;">})</span>
|
||||
<span style="color: #008080;">else</span>
|
||||
<span style="color: #7060A8;">printf</span><span style="color: #0000FF;">(</span><span style="color: #000000;">1</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"No %s %s\n"</span><span style="color: #0000FF;">,{</span><span style="color: #000000;">pins</span><span style="color: #0000FF;">,</span><span style="color: #000000;">ccs</span><span style="color: #0000FF;">})</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
|
||||
<span style="color: #008080;">end</span> <span style="color: #008080;">procedure</span>
|
||||
procedure BM(string pat, s, bool case_insensitive = false)
|
||||
string pins = sprintf("`%s` in `%s`",{pat,shorten(s,"characters",10)})
|
||||
if case_insensitive then
|
||||
pat = lower(pat)
|
||||
s = lower(s)
|
||||
end if
|
||||
/* Preprocessing */
|
||||
sequence bmGs = preBmGs(pat),
|
||||
bmBc = preBmBc(pat)
|
||||
/* Searching */
|
||||
sequence res = {}
|
||||
integer i, j = 0,
|
||||
n = length(s),
|
||||
m = length(pat),
|
||||
cc = 0
|
||||
while j <= n - m do
|
||||
for i=m to 1 by -1 do
|
||||
cc += 1
|
||||
if pat[i]!=s[i+j] then exit end if
|
||||
end for
|
||||
if i<1 then
|
||||
res &= j+1
|
||||
j += bmGs[1];
|
||||
else
|
||||
j += max(bmGs[i], bmBc[s[i + j]] - m + i);
|
||||
end if
|
||||
end while
|
||||
string ccs = sprintf("(%d character comparisons)",cc)
|
||||
if length(res) then
|
||||
string many = ordinant(length(res))
|
||||
printf(1,"Found %s %s at %v %s\n",{pins,many,res,ccs})
|
||||
else
|
||||
printf(1,"No %s %s\n",{pins,ccs})
|
||||
end if
|
||||
end procedure
|
||||
|
||||
<span style="color: #000000;">BM</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"GCAGAGAG"</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"GCATCGCAGAGAGTATACAGTACG"</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #000000;">BM</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"TCTA"</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"GCTAGCTCTACGAGTCTA"</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #000000;">BM</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"TAATAAA"</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"GGCTATAATGCGTA"</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #000000;">BM</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"word"</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"there would have been a time for such a word"</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #000000;">BM</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"needle"</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"needle need noodle needle"</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #008080;">constant</span> <span style="color: #000000;">book</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">"InhisbookseriesTheArtofComputerProgrammingpublishedbyAddisonWesley"</span><span style="color: #0000FF;">&</span>
|
||||
<span style="color: #008000;">"DKnuthusesanimaginarycomputertheMIXanditsassociatedmachinecodeand"</span><span style="color: #0000FF;">&</span>
|
||||
<span style="color: #008000;">"assemblylanguagestoillustratetheconceptsandalgorithmsastheyarepresented"</span>
|
||||
<span style="color: #000000;">BM</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"put"</span><span style="color: #0000FF;">,</span><span style="color: #000000;">book</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #000000;">BM</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"and"</span><span style="color: #0000FF;">,</span><span style="color: #000000;">book</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #008080;">constant</span> <span style="color: #000000;">farm</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">"Nearby farms grew a half acre of alfalfa on the dairy's behalf, with "</span><span style="color: #0000FF;">&</span>
|
||||
<span style="color: #008000;">"bales of all that alfalfa exchanged for milk."</span>
|
||||
<span style="color: #000000;">BM</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"alfalfa"</span><span style="color: #0000FF;">,</span><span style="color: #000000;">farm</span><span style="color: #0000FF;">)</span>
|
||||
<span style="color: #000080;font-style:italic;">--BM("aLfAlfa",farm) -- none
|
||||
--BM("aLfAlfa",farm,true) -- as -2</span>
|
||||
<!--
|
||||
BM("GCAGAGAG","GCATCGCAGAGAGTATACAGTACG")
|
||||
BM("TCTA","GCTAGCTCTACGAGTCTA")
|
||||
BM("TAATAAA","GGCTATAATGCGTA")
|
||||
BM("word","there would have been a time for such a word")
|
||||
BM("needle","needle need noodle needle")
|
||||
constant book = "InhisbookseriesTheArtofComputerProgrammingpublishedbyAddisonWesley"&
|
||||
"DKnuthusesanimaginarycomputertheMIXanditsassociatedmachinecodeand"&
|
||||
"assemblylanguagestoillustratetheconceptsandalgorithmsastheyarepresented"
|
||||
BM("put",book)
|
||||
BM("and",book)
|
||||
constant farm = "Nearby farms grew a half acre of alfalfa on the dairy's behalf, with "&
|
||||
"bales of all that alfalfa exchanged for milk."
|
||||
BM("alfalfa",farm)
|
||||
--BM("aLfAlfa",farm) -- none
|
||||
--BM("aLfAlfa",farm,true) -- as -2
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue