Inverted index: Difference between revisions
m
→{{header|Phix}}: added syntax colouring, marked p2js incompatible
m (→{{header|Phix}}: added syntax colouring, marked p2js incompatible) |
|||
Line 2,625:
Might be better (and almost as easy) for the dictionary values to be say
{total_count, {file nos}, {file counts}}.
<!--<lang Phix>(notonline)--
<span style="color: #000080;font-style:italic;">-- demo\rosetta\Inverted_index.exw</span>
<span style="color: #008080;">without</span> <span style="color: #008080;">js</span> <span style="color: #000080;font-style:italic;">-- (file i/o)</span>
<span style="color: #004080;">integer</span> <span style="color: #000000;">word_count</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">0</span>
<span style="color: #004080;">sequence</span> <span style="color: #000000;">filenames</span> <span style="color: #0000FF;">=</span> <span style="color: #0000FF;">{}</span>
<span style="color: #008080;">function</span> <span style="color: #000000;">is_ascii</span><span style="color: #0000FF;">(</span><span style="color: #004080;">string</span> <span style="color: #000000;">txt</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: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">txt</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">do</span>
<span style="color: #004080;">integer</span> <span style="color: #000000;">ch</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">txt</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]</span>
<span style="color: #008080;">if</span> <span style="color: #000000;">ch</span><span style="color: #0000FF;">=</span><span style="color: #008000;">'\0'</span> <span style="color: #008080;">or</span> <span style="color: #000000;">ch</span><span style="color: #0000FF;">>=</span><span style="color: #000000;">#7F</span> <span style="color: #008080;">then</span> <span style="color: #008080;">return</span> <span style="color: #000000;">0</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;">1</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">function</span>
<span style="color: #008080;">procedure</span> <span style="color: #000000;">add_words</span><span style="color: #0000FF;">(</span><span style="color: #004080;">string</span> <span style="color: #000000;">name</span><span style="color: #0000FF;">,</span> <span style="color: #004080;">sequence</span> <span style="color: #000000;">words</span><span style="color: #0000FF;">)</span>
<span style="color: #000000;">filenames</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">append</span><span style="color: #0000FF;">(</span><span style="color: #000000;">filenames</span><span style="color: #0000FF;">,</span><span style="color: #000000;">name</span><span style="color: #0000FF;">)</span>
<span style="color: #004080;">integer</span> <span style="color: #000000;">fn</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">filenames</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: #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>
<span style="color: #004080;">string</span> <span style="color: #000000;">word</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>
<span style="color: #008080;">if</span> <span style="color: #000000;">word</span><span style="color: #0000FF;">[</span><span style="color: #000000;">1</span><span style="color: #0000FF;">]>=</span><span style="color: #008000;">'a'</span> <span style="color: #000080;font-style:italic;">-- skip numbers</span>
<span style="color: #008080;">and</span> <span style="color: #000000;">word</span><span style="color: #0000FF;">[</span><span style="color: #000000;">1</span><span style="color: #0000FF;">]<=</span><span style="color: #008000;">'z'</span> <span style="color: #008080;">then</span>
<span style="color: #004080;">integer</span> <span style="color: #000000;">node</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">getd_index</span><span style="color: #0000FF;">(</span><span style="color: #000000;">word</span><span style="color: #0000FF;">)</span>
<span style="color: #008080;">if</span> <span style="color: #000000;">node</span><span style="color: #0000FF;">=</span><span style="color: #000000;">0</span> <span style="color: #008080;">then</span> <span style="color: #000080;font-style:italic;">-- not present</span>
<span style="color: #7060A8;">setd</span><span style="color: #0000FF;">(</span><span style="color: #000000;">word</span><span style="color: #0000FF;">,{</span><span style="color: #000000;">fn</span><span style="color: #0000FF;">})</span>
<span style="color: #000000;">word_count</span> <span style="color: #0000FF;">+=</span> <span style="color: #000000;">1</span>
<span
<span style="color: #004080;">sequence</span> <span style="color: #000000;">val</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">getd_by_index</span><span style="color: #0000FF;">(</span><span style="color: #000000;">node</span><span style="color: #0000FF;">)</span>
<span style="color: #008080;">if</span> <span style="color: #7060A8;">find</span><span style="color: #0000FF;">(</span><span style="color: #000000;">fn</span><span style="color: #0000FF;">,</span><span style="color: #000000;">val</span><span style="color: #0000FF;">)=</span><span style="color: #000000;">0</span> <span style="color: #008080;">then</span>
<span style="color: #7060A8;">setd</span><span style="color: #0000FF;">(</span><span style="color: #000000;">word</span><span style="color: #0000FF;">,</span><span style="color: #7060A8;">append</span><span style="color: #0000FF;">(</span><span style="color: #000000;">val</span><span style="color: #0000FF;">,</span><span style="color: #000000;">fn</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;">if</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;">end</span> <span style="color: #008080;">procedure</span>
<span style="color: #008080;">procedure</span> <span style="color: #000000;">load_directory</span><span style="color: #0000FF;">()</span>
<span style="color: #004080;">sequence</span> <span style="color: #000000;">d</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">dir</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"."</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: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">d</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">do</span>
<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: #008000;">'d'</span><span style="color: #0000FF;">,</span><span style="color: #000000;">d</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">][</span><span style="color: #004600;">D_ATTRIBUTES</span><span style="color: #0000FF;">])</span> <span style="color: #000080;font-style:italic;">-- skip directories</span>
<span style="color: #008080;">and</span> <span style="color: #000000;">d</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">][</span><span style="color: #004600;">D_SIZE</span><span style="color: #0000FF;">]<</span><span style="color: #000000;">1024</span><span style="color: #0000FF;">*</span><span style="color: #000000;">1024</span><span style="color: #0000FF;">*</span><span style="color: #000000;">1024</span> <span style="color: #008080;">then</span> <span style="color: #000080;font-style:italic;">-- and files > 1GB</span>
<span style="color: #004080;">string</span> <span style="color: #000000;">name</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">d</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">][</span><span style="color: #004600;">D_NAME</span><span style="color: #0000FF;">]</span>
<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;">name</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"rb"</span><span style="color: #0000FF;">)</span>
<span style="color: #004080;">string</span> <span style="color: #000000;">txt</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">lower</span><span style="color: #0000FF;">(</span><span style="color: #7060A8;">get_text</span><span style="color: #0000FF;">(</span><span style="color: #000000;">fn</span><span style="color: #0000FF;">))</span>
<span style="color: #7060A8;">close</span><span style="color: #0000FF;">(</span><span style="color: #000000;">fn</span><span style="color: #0000FF;">)</span>
<span style="color: #008080;">if</span> <span style="color: #000000;">is_ascii</span><span style="color: #0000FF;">(</span><span style="color: #000000;">txt</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">then</span> <span style="color: #000080;font-style:italic;">-- skip any bitmaps etc</span>
<span style="color: #004080;">sequence</span> <span style="color: #000000;">words</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">split_any</span><span style="color: #0000FF;">(</span><span style="color: #000000;">txt</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"\0\r\n\t !\"#$%&\'()*+,-./:;<=>?@[\\]^`{|}~"</span><span style="color: #0000FF;">)</span>
<span style="color: #000000;">add_words</span><span style="color: #0000FF;">(</span><span style="color: #000000;">name</span><span style="color: #0000FF;">,</span><span style="color: #000000;">words</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;">if</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">for</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">procedure</span>
<span style="color: #008080;">function</span> <span style="color: #000000;">lookup</span><span style="color: #0000FF;">(</span><span style="color: #004080;">sequence</span> <span style="color: #000000;">words</span><span style="color: #0000FF;">)</span>
<span style="color: #004080;">sequence</span> <span style="color: #000000;">files</span> <span style="color: #0000FF;">=</span> <span style="color: #0000FF;">{}</span> <span style="color: #000080;font-style:italic;">-- indexes to filenames</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: #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>
<span style="color: #004080;">string</span> <span style="color: #000000;">word</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>
<span style="color: #004080;">integer</span> <span style="color: #000000;">node</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">getd_index</span><span style="color: #0000FF;">(</span><span style="color: #000000;">word</span><span style="color: #0000FF;">)</span>
<span style="color: #008080;">if</span> <span style="color: #000000;">node</span><span style="color: #0000FF;">=</span><span style="color: #000000;">0</span> <span style="color: #008080;">then</span> <span style="color: #008080;">return</span> <span style="color: #0000FF;">{}</span> <span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
<span style="color: #004080;">sequence</span> <span style="color: #000000;">val</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">getd_by_index</span><span style="color: #0000FF;">(</span><span style="color: #000000;">node</span><span style="color: #0000FF;">)</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;">files</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">val</span>
<span style="color: #008080;">else</span>
<span style="color: #008080;">for</span> <span style="color: #000000;">j</span><span style="color: #0000FF;">=</span><span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">files</span><span style="color: #0000FF;">)</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: #008080;">not</span> <span style="color: #7060A8;">find</span><span style="color: #0000FF;">(</span><span style="color: #000000;">files</span><span style="color: #0000FF;">[</span><span style="color: #000000;">j</span><span style="color: #0000FF;">],</span><span style="color: #000000;">val</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">then</span>
<span style="color: #000000;">files</span><span style="color: #0000FF;">[</span><span style="color: #000000;">j</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: #0000FF;">{}</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: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">files</span><span style="color: #0000FF;">)=</span><span style="color: #000000;">0</span> <span style="color: #008080;">then</span> <span style="color: #008080;">return</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;">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: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">files</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">do</span>
<span style="color: #000000;">files</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;">filenames</span><span style="color: #0000FF;">[</span><span style="color: #000000;">files</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;">files</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">function</span>
<span style="color: #000000;">load_directory</span><span style="color: #0000FF;">()</span>
<span style="color: #0000FF;">?</span><span style="color: #000000;">word_count</span>
<span style="color: #0000FF;">?</span><span style="color: #000000;">lookup</span><span style="color: #0000FF;">({</span><span style="color: #008000;">"load_directory"</span><span style="color: #0000FF;">})</span> <span style="color: #000080;font-style:italic;">-- should only be this file</span>
<span style="color: #0000FF;">?</span><span style="color: #000000;">lookup</span><span style="color: #0000FF;">({</span><span style="color: #008000;">"dir"</span><span style="color: #0000FF;">})</span> <span style="color: #000080;font-style:italic;">-- currently two use this</span>
<span style="color: #0000FF;">?</span><span style="color: #000000;">lookup</span><span style="color: #0000FF;">({</span><span style="color: #008000;">"lower"</span><span style="color: #0000FF;">})</span> <span style="color: #000080;font-style:italic;">-- currently four use this</span>
<span style="color: #0000FF;">?</span><span style="color: #000000;">lookup</span><span style="color: #0000FF;">({</span><span style="color: #008000;">"lower"</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"dir"</span><span style="color: #0000FF;">})</span> <span style="color: #000080;font-style:italic;">-- currently two use both</span>
<span style="color: #0000FF;">?</span><span style="color: #000000;">lookup</span><span style="color: #0000FF;">({</span><span style="color: #008000;">"dir"</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"lower"</span><span style="color: #0000FF;">})</span> <span style="color: #000080;font-style:italic;">-- should be the same two</span>
<span style="color: #0000FF;">?</span><span style="color: #000000;">lookup</span><span style="color: #0000FF;">({</span><span style="color: #008000;">"ban"</span><span style="color: #0000FF;">&</span><span style="color: #008000;">"anafish"</span><span style="color: #0000FF;">})</span> <span style="color: #000080;font-style:italic;">-- should be none ({})</span>
<!--</lang>-->
{{out}}
Note the distributed version has been modified and is occasionally used for real, so the output will likely differ.
<pre>
3365
|