Teacup rim text: Difference between revisions
Content added Content deleted
m (→{{header|Phix}}: added syntax colouring the hard way) |
|||
Line 1,177: | Line 1,177: | ||
=={{header|Phix}}== |
=={{header|Phix}}== |
||
Filters anagram lists |
Filters anagram lists |
||
<lang Phix> |
<!--<lang Phix>--> |
||
<span style="color: #008080;">procedure</span> <span style="color: #000000;">filter_set</span><span style="color: #0000FF;">(</span><span style="color: #004080;">sequence</span> <span style="color: #000000;">anagrams</span><span style="color: #0000FF;">)</span> |
|||
sequence used = repeat(false,length(anagrams)) |
|||
<span style="color: #000080;font-style:italic;">-- anagrams is a (small) set of words that are all anagrams of each other |
|||
for i=1 to length(anagrams) do |
|||
-- for example: {"angel","angle","galen","glean","lange"} |
|||
if not used[i] then |
|||
-- print any set(s) for which every rotation is also present (marking as |
|||
used[i] = true |
|||
-- you go to prevent the same set appearing with each word being first)</span> |
|||
<span style="color: #004080;">sequence</span> <span style="color: #000000;">used</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">repeat</span><span style="color: #0000FF;">(</span><span style="color: #004600;">false</span><span style="color: #0000FF;">,</span><span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">anagrams</span><span style="color: #0000FF;">))</span> |
|||
sequence res = {word} |
|||
<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: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">anagrams</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">do</span> |
|||
for r=2 to length(word) do |
|||
<span style="color: #008080;">if</span> <span style="color: #008080;">not</span> <span style="color: #000000;">used</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]</span> <span style="color: #008080;">then</span> |
|||
word = word[2..$]&word[1] |
|||
<span style="color: #000000;">used</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">=</span> <span style="color: #004600;">true</span> |
|||
integer k = find(word,anagrams) |
|||
<span style="color: #004080;">string</span> <span style="color: #000000;">word</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">anagrams</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]</span> |
|||
if k=0 then res = {} exit end if |
|||
<span style="color: #004080;">sequence</span> <span style="color: #000000;">res</span> <span style="color: #0000FF;">=</span> <span style="color: #0000FF;">{</span><span style="color: #000000;">word</span><span style="color: #0000FF;">}</span> |
|||
if not find(word,res) then |
|||
<span style="color: #008080;">for</span> <span style="color: #000000;">r</span><span style="color: #0000FF;">=</span><span style="color: #000000;">2</span> <span style="color: #008080;">to</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">word</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">do</span> |
|||
res = append(res,word) |
|||
<span style="color: #000000;">word</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">word</span><span style="color: #0000FF;">[</span><span style="color: #000000;">2</span><span style="color: #0000FF;">..$]&</span><span style="color: #000000;">word</span><span style="color: #0000FF;">[</span><span style="color: #000000;">1</span><span style="color: #0000FF;">]</span> |
|||
end if |
|||
<span style="color: #004080;">integer</span> <span style="color: #000000;">k</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">find</span><span style="color: #0000FF;">(</span><span style="color: #000000;">word</span><span style="color: #0000FF;">,</span><span style="color: #000000;">anagrams</span><span style="color: #0000FF;">)</span> |
|||
used[k] = true |
|||
<span style="color: #008080;">if</span> <span style="color: #000000;">k</span><span style="color: #0000FF;">=</span><span style="color: #000000;">0</span> <span style="color: #008080;">then</span> <span style="color: #000000;">res</span> <span style="color: #0000FF;">=</span> <span style="color: #0000FF;">{}</span> <span style="color: #008080;">exit</span> <span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
end for |
|||
<span style="color: #008080;">if</span> <span style="color: #008080;">not</span> <span style="color: #7060A8;">find</span><span style="color: #0000FF;">(</span><span style="color: #000000;">word</span><span style="color: #0000FF;">,</span><span style="color: #000000;">res</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">then</span> |
|||
if length(res) then ?res end if |
|||
<span style="color: #000000;">res</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">append</span><span style="color: #0000FF;">(</span><span style="color: #000000;">res</span><span style="color: #0000FF;">,</span><span style="color: #000000;">word</span><span style="color: #0000FF;">)</span> |
|||
end if |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
end for |
|||
<span style="color: #000000;">used</span><span style="color: #0000FF;">[</span><span style="color: #000000;">k</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">=</span> <span style="color: #004600;">true</span> |
|||
end procedure |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">for</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: #0000FF;">?</span><span style="color: #000000;">res</span> <span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
procedure teacup(string filename, integer minlen=3, bool allow_mono=false) |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
sequence words = {}, anagrams = {}, last="", letters |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">for</span> |
|||
object word |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">procedure</span> |
|||
printf(1,"using %s",filename) |
|||
<span style="color: #008080;">procedure</span> <span style="color: #000000;">teacup</span><span style="color: #0000FF;">(</span><span style="color: #004080;">string</span> <span style="color: #000000;">filename</span><span style="color: #0000FF;">,</span> <span style="color: #004080;">integer</span> <span style="color: #000000;">minlen</span><span style="color: #0000FF;">=</span><span style="color: #000000;">3</span><span style="color: #0000FF;">,</span> <span style="color: #004080;">bool</span> <span style="color: #000000;">allow_mono</span><span style="color: #0000FF;">=</span><span style="color: #004600;">false</span><span style="color: #0000FF;">)</span> |
|||
integer fn = open(filename,"r") |
|||
<span style="color: #004080;">sequence</span> <span style="color: #000000;">letters</span><span style="color: #0000FF;">,</span> <span style="color: #000080;font-style:italic;">-- a sorted word, eg "ate" -> "aet".</span> |
|||
if fn=-1 then crash(filename&" not found") end if |
|||
<span style="color: #000000;">words</span> <span style="color: #0000FF;">=</span> <span style="color: #0000FF;">{},</span> <span style="color: #000080;font-style:italic;">-- in eg {{"aet","ate"},...} form</span> |
|||
while 1 do |
|||
<span style="color: #000000;">anagrams</span> <span style="color: #0000FF;">=</span> <span style="color: #0000FF;">{},</span> <span style="color: #000080;font-style:italic;">-- a set with same letters</span> |
|||
word = lower(trim(gets(fn))) |
|||
<span style="color: #000000;">last</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">""</span> <span style="color: #000080;font-style:italic;">-- (for building such sets)</span> |
|||
if atom(word) then exit end if |
|||
<span style="color: #004080;">object</span> <span style="color: #000000;">word</span> |
|||
if length(word)>=minlen then |
|||
letters = sort(word) |
|||
<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;">"using %s"</span><span style="color: #0000FF;">,</span><span style="color: #000000;">filename</span><span style="color: #0000FF;">)</span> |
|||
words = append(words, {letters, word}) |
|||
<span style="color: #004080;">integer</span> <span style="color: #000000;">fn</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">open</span><span style="color: #0000FF;">(</span><span style="color: #000000;">filename</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"r"</span><span style="color: #0000FF;">)</span> |
|||
end if |
|||
<span style="color: #008080;">if</span> <span style="color: #000000;">fn</span><span style="color: #0000FF;">=-</span><span style="color: #000000;">1</span> <span style="color: #008080;">then</span> <span style="color: #7060A8;">crash</span><span style="color: #0000FF;">(</span><span style="color: #000000;">filename</span><span style="color: #0000FF;">&</span><span style="color: #008000;">" not found"</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
end while |
|||
<span style="color: #008080;">while</span> <span style="color: #000000;">1</span> <span style="color: #008080;">do</span> |
|||
close(fn) |
|||
<span style="color: #000000;">word</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">lower</span><span style="color: #0000FF;">(</span><span style="color: #7060A8;">trim</span><span style="color: #0000FF;">(</span><span style="color: #7060A8;">gets</span><span style="color: #0000FF;">(</span><span style="color: #000000;">fn</span><span style="color: #0000FF;">)))</span> |
|||
printf(1,", %d words read\n",length(words)) |
|||
<span style="color: #008080;">if</span> <span style="color: #004080;">atom</span><span style="color: #0000FF;">(</span><span style="color: #000000;">word</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> |
|||
if length(words)!=0 then |
|||
<span style="color: #008080;">if</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">word</span><span style="color: #0000FF;">)>=</span><span style="color: #000000;">minlen</span> <span style="color: #008080;">then</span> |
|||
words = sort(words) |
|||
<span style="color: #000000;">letters</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">sort</span><span style="color: #0000FF;">(</span><span style="color: #000000;">word</span><span style="color: #0000FF;">)</span> |
|||
for i=1 to length(words) do |
|||
<span style="color: #000000;">words</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">append</span><span style="color: #0000FF;">(</span><span style="color: #000000;">words</span><span style="color: #0000FF;">,</span> <span style="color: #0000FF;">{</span><span style="color: #000000;">letters</span><span style="color: #0000FF;">,</span> <span style="color: #000000;">word</span><span style="color: #0000FF;">})</span> |
|||
{letters,word} = words[i] |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
if letters=last then |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">while</span> |
|||
anagrams = append(anagrams,word) |
|||
<span style="color: #7060A8;">close</span><span style="color: #0000FF;">(</span><span style="color: #000000;">fn</span><span style="color: #0000FF;">)</span> |
|||
else |
|||
<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;">", %d words read\n"</span><span style="color: #0000FF;">,</span><span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">words</span><span style="color: #0000FF;">))</span> |
|||
if allow_mono or length(anagrams)>=length(last) then |
|||
<span style="color: #008080;">if</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">words</span><span style="color: #0000FF;">)!=</span><span style="color: #000000;">0</span> <span style="color: #008080;">then</span> |
|||
filter(anagrams) |
|||
<span style="color: #000000;">words</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">sort</span><span style="color: #0000FF;">(</span><span style="color: #000000;">words</span><span style="color: #0000FF;">)</span> <span style="color: #000080;font-style:italic;">-- group by anagram</span> |
|||
end if |
|||
<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: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">words</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">do</span> |
|||
last = letters |
|||
<span style="color: #0000FF;">{</span><span style="color: #000000;">letters</span><span style="color: #0000FF;">,</span><span style="color: #000000;">word</span><span style="color: #0000FF;">}</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">words</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]</span> |
|||
anagrams = {word} |
|||
<span style="color: #008080;">if</span> <span style="color: #000000;">letters</span><span style="color: #0000FF;">=</span><span style="color: #000000;">last</span> <span style="color: #008080;">then</span> |
|||
end if |
|||
<span style="color: #000000;">anagrams</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">append</span><span style="color: #0000FF;">(</span><span style="color: #000000;">anagrams</span><span style="color: #0000FF;">,</span><span style="color: #000000;">word</span><span style="color: #0000FF;">)</span> |
|||
end for |
|||
<span style="color: #008080;">else</span> |
|||
if allow_mono or length(anagrams)>=length(last) then |
|||
<span style="color: #008080;">if</span> <span style="color: #000000;">allow_mono</span> <span style="color: #008080;">or</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">anagrams</span><span style="color: #0000FF;">)>=</span><span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">last</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">then</span> |
|||
filter(anagrams) |
|||
<span style="color: #000000;">filter_set</span><span style="color: #0000FF;">(</span><span style="color: #000000;">anagrams</span><span style="color: #0000FF;">)</span> |
|||
end if |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
end if |
|||
<span style="color: #000000;">last</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">letters</span> |
|||
end procedure |
|||
<span style="color: #000000;">anagrams</span> <span style="color: #0000FF;">=</span> <span style="color: #0000FF;">{</span><span style="color: #000000;">word</span><span style="color: #0000FF;">}</span> |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
teacup(join_path({"demo","unixdict.txt"})) |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">for</span> |
|||
-- These match output from other entries: |
|||
<span style="color: #008080;">if</span> <span style="color: #000000;">allow_mono</span> <span style="color: #008080;">or</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">anagrams</span><span style="color: #0000FF;">)>=</span><span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">last</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">then</span> |
|||
--teacup(join_path({"demo","unixdict.txt"}),allow_mono:=true) |
|||
<span style="color: #000000;">filter_set</span><span style="color: #0000FF;">(</span><span style="color: #000000;">anagrams</span><span style="color: #0000FF;">)</span> |
|||
--teacup(join_path({"demo","rosetta","mit.wordlist.10000.txt"})) |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
--teacup(join_path({"demo","rosetta","words.txt"}),4,true) |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
-- Note that allow_mono is needed to display eg {"agag","gaga"}</lang> |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">procedure</span> |
|||
<span style="color: #000000;">teacup</span><span style="color: #0000FF;">(</span><span style="color: #7060A8;">join_path</span><span style="color: #0000FF;">({</span><span style="color: #008000;">"demo"</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"unixdict.txt"</span><span style="color: #0000FF;">}))</span> |
|||
<span style="color: #000080;font-style:italic;">-- These match output from other entries: |
|||
--teacup(join_path({"demo","unixdict.txt"}),allow_mono:=true) |
|||
--teacup(join_path({"demo","rosetta","mit.wordlist.10000.txt"})) |
|||
--teacup(join_path({"demo","rosetta","words.txt"}),4,true) |
|||
-- Note that allow_mono is needed to display eg {"agag","gaga"}</span> |
|||
<!--</lang>--> |
|||
{{out}} |
{{out}} |
||
<pre> |
<pre> |