Build an ASCII chart of the most commonly used words in a given text [closed]

前端未结

关注

 30  1618

Java - 886 865 756 744 742 744 752 742 714 680 chars

Updates before first 742: improved regex, removed superfluous parameterized types, removed superfluous whitespace.
Update 742 > 744 chars: fixed the fixed-length hack. It's only dependent on the 1st word, not other words (yet). Found several places to shorten the code (\\s in regex replaced by and ArrayList replaced by Vector). I'm now looking for a short way to remove the Commons IO dependency and reading from stdin.
Update 744 > 752 chars: I removed the commons dependency. It now reads from stdin. Paste the text in stdin and hit Ctrl+Z to get result.
Update 752 > 742 chars: I removed public and a space, made classname 1 char instead of 2 and it's now ignoring one-letter words.
Update 742 > 714 chars: Updated as per comments of Carl: removed redundant assignment (742 > 730), replaced m.containsKey(k) by m.get(k)!=null (730 > 728), introduced substringing of line (728 > 714).
Update 714 > 680 chars: Updated as per comments of Rotsor: improved bar size calculation to remove unnecessary casting and improved split() to remove unnecessary replaceAll().

import java.util.*;class F{public static void main(String[]a)throws Exception{StringBuffer b=new StringBuffer();for(int c;(c=System.in.read())>0;b.append((char)c));final Map<String,Integer>m=new HashMap();for(String w:b.toString().toLowerCase().split("(\\b(.|the|and|of|to|i[tns]|or)\\b|\\W)+"))m.put(w,m.get(w)!=null?m.get(w)+1:1);List<String>l=new Vector(m.keySet());Collections.sort(l,new Comparator(){public int compare(Object l,Object r){return m.get(r)-m.get(l);}});int c=76-l.get(0).length();String s=new String(new char[c]).replace('\0','_');System.out.println(" "+s);for(String w:l.subList(0,22))System.out.println("|"+s.substring(0,m.get(w)*c/m.get(l.get(0)))+"| "+w);}}

Java - 896 chars

931 chars

1233 chars made unreadable

1977 chars "uncompressed"

Update: I have aggressively reduced the character count. Omits single-letter words per updated spec.

I envy C# and LINQ so much.

import java.util.*;import java.io.*;import static java.util.regex.Pattern.*;class g{public static void main(String[] a)throws Exception{PrintStream o=System.out;Map<String,Integer> w=new HashMap();Scanner s=new Scanner(new File(a[0])).useDelimiter(compile("[^a-z]+|\\b(the|and|of|to|.|it|in|or|is)\\b",2));while(s.hasNext()){String z=s.next().trim().toLowerCase();if(z.equals(""))continue;w.put(z,(w.get(z)==null?0:w.get(z))+1);}List<Integer> v=new Vector(w.values());Collections.sort(v);List<String> q=new Vector();int i,m;i=m=v.size()-1;while(q.size()<22){for(String t:w.keySet())if(!q.contains(t)&&w.get(t).equals(v.get(i)))q.add(t);i--;}int r=80-q.get(0).length()-4;String l=String.format("%1$0"+r+"d",0).replace("0","_");o.println(" "+l);o.println("|"+l+"| "+q.get(0)+" ");for(i=m-1;i>m-22;i--){o.println("|"+l.substring(0,(int)Math.round(r*(v.get(i)*1.0)/v.get(m)))+"| "+q.get(m-i)+" ");}}}

"Readable":

import java.util.*;
import java.io.*;
import static java.util.regex.Pattern.*;
class g
{
   public static void main(String[] a)throws Exception
      {
      PrintStream o = System.out;
      Map<String,Integer> w = new HashMap();
      Scanner s = new Scanner(new File(a[0]))
         .useDelimiter(compile("[^a-z]+|\\b(the|and|of|to|.|it|in|or|is)\\b",2));
      while(s.hasNext())
      {
         String z = s.next().trim().toLowerCase();
         if(z.equals(""))
            continue;
         w.put(z,(w.get(z) == null?0:w.get(z))+1);
      }
      List<Integer> v = new Vector(w.values());
      Collections.sort(v);
      List<String> q = new Vector();
      int i,m;
      i = m = v.size()-1;
      while(q.size()<22)
      {
         for(String t:w.keySet())
            if(!q.contains(t)&&w.get(t).equals(v.get(i)))
               q.add(t);
         i--;
      }
      int r = 80-q.get(0).length()-4;
      String l = String.format("%1$0"+r+"d",0).replace("0","_");
      o.println(" "+l);
      o.println("|"+l+"| "+q.get(0)+" ");
      for(i = m-1; i > m-22; i--)
      {
         o.println("|"+l.substring(0,(int)Math.round(r*(v.get(i)*1.0)/v.get(m)))+"| "+q.get(m-i)+" ");
      }
   }
}

Output of Alice:

 _________________________________________________________________________
|_________________________________________________________________________| she
|_______________________________________________________________| you
|_____________________________________________________________| said
|_____________________________________________________| alice
|_______________________________________________| was
|____________________________________________| that
|____________________________________| as
|_________________________________| her
|______________________________| with
|______________________________| at
|___________________________| on
|__________________________| all
|________________________| this
|________________________| for
|_______________________| had
|_______________________| but
|______________________| be
|______________________| not
|____________________| they
|____________________| so
|___________________| very
|___________________| what

Output of Don Quixote (also from Gutenberg):

 ________________________________________________________________________
|________________________________________________________________________| that
|________________________________________________________| he
|______________________________________________| for
|__________________________________________| his
|________________________________________| as
|__________________________________| with
|_________________________________| not
|_________________________________| was
|________________________________| him
|______________________________| be
|___________________________| don
|_________________________| my
|_________________________| this
|_________________________| all
|_________________________| they
|________________________| said
|_______________________| have
|_______________________| me
|______________________| on
|______________________| so
|_____________________| you
|_____________________| quixote

0 讨论(0)

粉色の甜心

2020-11-30 16:45

PHP CLI version (450 chars)

This solution takes into account the last requirement which most purists have conviniently chosen to ignore. That costed 170 characters!

Usage: php.exe <this.php> <file.txt>

Minified:

<?php $a=array_count_values(array_filter(preg_split('/[^a-z]/',strtolower(file_get_contents($argv[1])),-1,1),function($x){return !preg_match("/^(.|the|and|of|to|it|in|or|is)$/",$x);}));arsort($a);$a=array_slice($a,0,22);function R($a,$F,$B){$r=array();foreach($a as$x=>$f){$l=strlen($x);$r[$x]=$b=$f*$B/$F;if($l+$b>76)return R($a,$f,76-$l);}return$r;}$c=R($a,max($a),76-strlen(key($a)));foreach($a as$x=>$f)echo '|',str_repeat('-',$c[$x]),"| $x\n";?>

Human readable:

<?php

// Read:
$s = strtolower(file_get_contents($argv[1]));

// Split:
$a = preg_split('/[^a-z]/', $s, -1, PREG_SPLIT_NO_EMPTY);

// Remove unwanted words:
$a = array_filter($a, function($x){
       return !preg_match("/^(.|the|and|of|to|it|in|or|is)$/",$x);
     });

// Count:
$a = array_count_values($a);

// Sort:
arsort($a);

// Pick top 22:
$a=array_slice($a,0,22);


// Recursive function to adjust bar widths
// according to the last requirement:
function R($a,$F,$B){
    $r = array();
    foreach($a as $x=>$f){
        $l = strlen($x);
        $r[$x] = $b = $f * $B / $F;
        if ( $l + $b > 76 )
            return R($a,$f,76-$l);
    }
    return $r;
}

// Apply the function:
$c = R($a,max($a),76-strlen(key($a)));


// Output:
foreach ($a as $x => $f)
    echo '|',str_repeat('-',$c[$x]),"| $x\n";

?>

Output:

|-------------------------------------------------------------------------| she
|---------------------------------------------------------------| you
|------------------------------------------------------------| said
|-----------------------------------------------------| alice
|-----------------------------------------------| was
|-------------------------------------------| that
|------------------------------------| as
|--------------------------------| her
|-----------------------------| at
|-----------------------------| with
|--------------------------| on
|--------------------------| all
|-----------------------| this
|-----------------------| for
|-----------------------| had
|-----------------------| but
|----------------------| be
|---------------------| not
|--------------------| they
|--------------------| so
|-------------------| very
|------------------| what

When there is a long word, the bars are adjusted properly:

|--------------------------------------------------------| she
|---------------------------------------------------| thisisareallylongwordhere
|-------------------------------------------------| you
|-----------------------------------------------| said
|-----------------------------------------| alice
|------------------------------------| was
|---------------------------------| that
|---------------------------| as
|-------------------------| her
|-----------------------| with
|-----------------------| at
|--------------------| on
|--------------------| all
|------------------| this
|------------------| for
|------------------| had
|-----------------| but
|-----------------| be
|----------------| not
|---------------| they
|---------------| so
|--------------| very

0 讨论(0)

梦如初夏

2020-11-30 16:46

Transact SQL set based solution (SQL Server 2005) 1063 892 873 853 827 820 783 683 647 644 630 characters

Thanks to Gabe for some useful suggestions to reduce the character count.

NB: Line breaks added to avoid scrollbars only the last line break is required.

DECLARE @ VARCHAR(MAX),@F REAL SELECT @=BulkColumn FROM OPENROWSET(BULK'A',
SINGLE_BLOB)x;WITH N AS(SELECT 1 i,LEFT(@,1)L UNION ALL SELECT i+1,SUBSTRING
(@,i+1,1)FROM N WHERE i<LEN(@))SELECT i,L,i-RANK()OVER(ORDER BY i)R INTO #D
FROM N WHERE L LIKE'[A-Z]'OPTION(MAXRECURSION 0)SELECT TOP 22 W,-COUNT(*)C
INTO # FROM(SELECT DISTINCT R,(SELECT''+L FROM #D WHERE R=b.R FOR XML PATH
(''))W FROM #D b)t WHERE LEN(W)>1 AND W NOT IN('the','and','of','to','it',
'in','or','is')GROUP BY W ORDER BY C SELECT @F=MIN(($76-LEN(W))/-C),@=' '+
REPLICATE('_',-MIN(C)*@F)+' 'FROM # SELECT @=@+' 
|'+REPLICATE('_',-C*@F)+'| '+W FROM # ORDER BY C PRINT @

Readable Version

DECLARE @  VARCHAR(MAX),
        @F REAL
SELECT @=BulkColumn
FROM   OPENROWSET(BULK'A',SINGLE_BLOB)x; /*  Loads text file from path
                                             C:\WINDOWS\system32\A  */

/*Recursive common table expression to
generate a table of numbers from 1 to string length
(and associated characters)*/
WITH N AS
     (SELECT 1 i,
             LEFT(@,1)L

     UNION ALL

     SELECT i+1,
            SUBSTRING(@,i+1,1)
     FROM   N
     WHERE  i<LEN(@)
     )
  SELECT   i,
           L,
           i-RANK()OVER(ORDER BY i)R
           /*Will group characters
           from the same word together*/
  INTO     #D
  FROM     N
  WHERE    L LIKE'[A-Z]'OPTION(MAXRECURSION 0)
             /*Assuming case insensitive accent sensitive collation*/

SELECT   TOP 22 W,
         -COUNT(*)C
INTO     #
FROM     (SELECT DISTINCT R,
                          (SELECT ''+L
                          FROM    #D
                          WHERE   R=b.R FOR XML PATH('')
                          )W
                          /*Reconstitute the word from the characters*/
         FROM             #D b
         )
         T
WHERE    LEN(W)>1
AND      W NOT IN('the',
                  'and',
                  'of' ,
                  'to' ,
                  'it' ,
                  'in' ,
                  'or' ,
                  'is')
GROUP BY W
ORDER BY C

/*Just noticed this looks risky as it relies on the order of evaluation of the 
 variables. I'm not sure that's guaranteed but it works on my machine :-) */
SELECT @F=MIN(($76-LEN(W))/-C),
       @ =' '      +REPLICATE('_',-MIN(C)*@F)+' '
FROM   #

SELECT @=@+' 
|'+REPLICATE('_',-C*@F)+'| '+W
             FROM     #
             ORDER BY C

PRINT @

Output

 _________________________________________________________________________ 
|_________________________________________________________________________| she
|_______________________________________________________________| You
|____________________________________________________________| said
|_____________________________________________________| Alice
|_______________________________________________| was
|___________________________________________| that
|____________________________________| as
|________________________________| her
|_____________________________| at
|_____________________________| with
|__________________________| on
|__________________________| all
|_______________________| This
|_______________________| for
|_______________________| had
|_______________________| but
|______________________| be
|_____________________| not
|____________________| they
|____________________| So
|___________________| very
|__________________| what

And with the long string

 _______________________________________________________________ 
|_______________________________________________________________| she
|_______________________________________________________| superlongstringstring
|____________________________________________________| said
|______________________________________________| Alice
|________________________________________| was
|_____________________________________| that
|_______________________________| as
|____________________________| her
|_________________________| at
|_________________________| with
|_______________________| on
|______________________| all
|____________________| This
|____________________| for
|____________________| had
|____________________| but
|___________________| be
|__________________| not
|_________________| they
|_________________| So
|________________| very
|________________| what

0 讨论(0)

鱼传尺愫

2020-11-30 16:46

Gawk -- 336 (originally 507) characters

(after fixing the output formatting; fixing the contractions thing; tweaking; tweaking again; removing a wholly unnecessary sorting step; tweaking yet again; and again (oops this one broke the formatting); tweak some more; taking up Matt's challenge I desperately tweak so more; found another place to save a few, but gave two back to fix the bar length bug)

Heh heh! I am momentarily ahead of [Matt's JavaScript][1] solution^{counter challenge! ;)} and [AKX's python][2].

The problem seems to call out for a language that implements native associative arrays, so of course I've chosen one with a horribly deficient set of operators on them. In particular, you cannot control the order in which awk offers up the elements of a hash map, so I repeatedly scan the whole map to find the currently most numerous item, print it and delete it from the array.

It is all terribly inefficient, with all the golfifcations I've made it has gotten to be pretty awful, as well.

Minified:

{gsub("[^a-zA-Z]"," ");for(;NF;NF--)a[tolower($NF)]++}
END{split("the and of to a i it in or is",b," ");
for(w in b)delete a[b[w]];d=1;for(w in a){e=a[w]/(78-length(w));if(e>d)d=e}
for(i=22;i;--i){e=0;for(w in a)if(a[w]>e)e=a[x=w];l=a[x]/d-2;
t=sprintf(sprintf("%%%dc",l)," ");gsub(" ","_",t);if(i==22)print" "t;
print"|"t"| "x;delete a[x]}}

line breaks for clarity only: they are not necessary and should not be counted.

Output:

$ gawk -f wordfreq.awk.min < 11.txt 
 _________________________________________________________________________
|_________________________________________________________________________| she
|_______________________________________________________________| you
|____________________________________________________________| said
|____________________________________________________| alice
|______________________________________________| was
|__________________________________________| that
|___________________________________| as
|_______________________________| her
|____________________________| with
|____________________________| at
|___________________________| s
|___________________________| t
|_________________________| on
|_________________________| all
|______________________| this
|______________________| for
|______________________| had
|_____________________| but
|____________________| be
|____________________| not
|___________________| they
|__________________| so
$ sed 's/you/superlongstring/gI' 11.txt | gawk -f wordfreq.awk.min
 ______________________________________________________________________
|______________________________________________________________________| she
|_____________________________________________________________| superlongstring
|__________________________________________________________| said
|__________________________________________________| alice
|____________________________________________| was
|_________________________________________| that
|_________________________________| as
|______________________________| her
|___________________________| with
|___________________________| at
|__________________________| s
|__________________________| t
|________________________| on
|________________________| all
|_____________________| this
|_____________________| for
|_____________________| had
|____________________| but
|___________________| be
|___________________| not
|__________________| they
|_________________| so

Readable; 633 characters (originally 949):

{
    gsub("[^a-zA-Z]"," ");
    for(;NF;NF--)
    a[tolower($NF)]++
}
END{
    # remove "short" words
    split("the and of to a i it in or is",b," ");
    for (w in b) 
    delete a[b[w]];
    # Find the bar ratio
    d=1;
    for (w in a) {
    e=a[w]/(78-length(w));
    if (e>d)
        d=e
    }
    # Print the entries highest count first
    for (i=22; i; --i){               
    # find the highest count
    e=0;
    for (w in a) 
        if (a[w]>e)
        e=a[x=w];
        # Print the bar
    l=a[x]/d-2;
    # make a string of "_" the right length
    t=sprintf(sprintf("%%%dc",l)," ");
    gsub(" ","_",t);
    if (i==22) print" "t;
    print"|"t"| "x;
    delete a[x]
    }
}

0 讨论(0)

热议问题