Word frequency: Difference between revisions

Line 2,359:

=={{header|FutureBasic}}==

Task said: "Feel free to explicitly state the thoughts behind the program decisions." Thus the heavy comments.

include "NSLog.incl"

include "Tlbx CFCharacterSet.incl"

local fn WordFrequency( textStr as CFStringRef, caseSensitive as Boolean, ascendingOrder as Boolean ) as CFStringRef

'~'1

CFStringRef ~~wrd,~~ ~~resultStr~~ = ~~NULL~~

CFStringRef wrd

CFDictionaryRef dict

// Break out capitalized words during seaarch or not as determined by the caseSensitive Boolean function input parameter

if caseSensitive == NO then textStr = fn StringLowercaseString( textStr )

// Trim non-alphabetic characters from string and separate individual words with a space

CFStringRef tempStr = fn ArrayComponentsJoinedByString( fn StringComponentsSeparatedByCharactersInSet( textStr, fn CharacterSetInvertedSet( fn CharacterSetLetterSet ) ), @" " )

⚫

CFMutableCharacterSetRef separators = fn ~~CFCharacterSetCreateMutable( 0 )~~

// Prepare separators to parse string into array

MutableCharacterSetFormUnionWithCharacterSet( separators, fn CharacterSetPuntuationSet )

⚫

CFMutableCharacterSetRef separators = fn MutableCharacterSetInit

MutableCharacterSetFormUnionWithCharacterSet( separators, fn CharacterSetWhitespaceAndNewlineSet )

MutableCharacterSetFormUnionWithCharacterSet( separators, fn CharacterSetPuntuationSet ) // Informally, this set is the set of all non-whitespace characters used to separate linguistic units in scripts, such as periods, dashes, parentheses, and so on.

MutableCharacterSetFormUnionWithCharacterSet( separators, fn CharacterSetWhitespaceAndNewlineSet ) // A character set containing all the whitespace and newline characters. A character set containing characters in Unicode General Category Z*, U+000A ~ U+000D, and U+0085.

// Create array of separated words

CFArrayRef tempArr = fn StringComponentsSeparatedByCharactersInSet( tempStr, separators )

CFRelease( separators )

// Create a counted set with each word and its frequency

CountedSetRef freqencies = fn CountedSetWithArray( tempArr )

⚫

EnumeratorRef enumRef = fn CountedSetObjectEnumerator( freqencies )

⚫

CFArrayRef array = fn EnumeratorAllObjects( enumRef )

// Enumerate each word-frequeny pain in the counted set...

⚫

EnumeratorRef enumRef = fn CountedSetObjectEnumerator( freqencies )

// .. and use it to create array of words in counted set

⚫

CFArrayRef array = fn EnumeratorAllObjects( enumRef )

// Create an empty mutable array

CFMutableArrayRef wordArr = fn MutableArrayWithCapacity( 0 )

// Create word couter

NSInteger totalWords = 0

// Enumerate each word, get its frequency, create its own key/value pair dictionary, add each dictionary into master array

for wrd in array

totalWords++

// Create dictionary with frequency and matching word

dict = @{ @"count":fn NumberWithUnsignedInteger( fn CountedSetCountForObject( freqencies, wrd ) ), @"object":wrd }

// Add each dictionary to the master mutable array, checking for a valid word by length

if ( fn StringLength( wrd ) != 0 )

MutableArrayAddObject( wordArr, dict )

Line 2,389:

Line 2,407:

// Store the total words as a global application property

AppSetProperty( @"totalWords", fn StringWithFormat( @"%d", totalWords ) )

AppSetProperty( @"totalWords", fn StringWithFormat( @"%d", totalWords - 1 ) )

// Sort the array in ascending or descending order as determined by the ascendingOrder Boolean function input parameter

SortDescriptorRef descriptors = fn SortDescriptorWithKey( @"count", ascendingOrder )

CFArrayRef sortedArray = fn ArraySortedArrayUsingDescriptors( wordArr, @[descriptors] )

⚫

CFMutableStringRef mutStr = fn MutableStringWithCapacity( 0 )

// Create an empty mutable string

⚫

CFMutableStringRef mutStr = fn MutableStringWithCapacity( 0 )

// Use each dictionary in sorted array to build the formatted output string

NSInteger count = 1

for dict in sortedArray

Line 2,400:

Line 2,424:

// Create output string from mutable

resultStr = fn StringWithFormat( @"%@", mutStr )

CFStringRef resultStr = fn StringWithFormat( @"%@", mutStr )

end fn = resultStr

local fn ParseTextFromWebsite( webSite as CFStringRef )

⚫

CFAbsoluteTime startTime

// Convert incoming string to URL

CFURLRef textURL

CFURLRef textURL = fn URLWithString( webSite )

CFStringRef textStr, frequencyStr

// Read contents of URL into a string

⚫

CFStringRef textStr = fn StringWithContentsOfURL( textURL, NSUTF8StringEncoding, NULL )

// Start timer

⚫

~~textURL =~~ fn ~~URLWithString~~( @"https://www.gutenberg.org/files/135/135-0.txt" )

⚫

CFAbsoluteTime startTime = fn CFAbsoluteTimeGetCurrent

⚫

textStr = fn StringWithContentsOfURL( textURL, NSUTF8StringEncoding, NULL )

// Calculate frequency of words in text and sort by occurrence

⚫

CFStringRef frequencyStr = fn WordFrequency( textStr, NO, NO )

startTime = fn CFAbsoluteTimeGetCurrent

// Log results and post post processing time

⚫

frequencyStr = fn WordFrequency( textStr, NO, NO )

NSLog( @"%@", frequencyStr )

NSLog( @"Total words in document: %@", fn AppProperty( @"totalWords" ) )

// Stop timer and log elapsed processing time

NSLog( @"Elapsed time: %f milliseconds.", ( fn CFAbsoluteTimeGetCurrent - startTime ) * 1000.0 )

end fn

// Pass url for Les Misérables on Project Gutenberg

⚫

fn ParseTextFromWebsite( @"https://www.gutenberg.org/files/135/135-0.txt" )

HandleEvents

Line 2,447:

Line 2,479:

22910 1 isabella

Total words in document: ~~22911~~

Total words in document: 22910

Elapsed time: 595.407963 milliseconds.

</pre>

=={{header|Go}}==