lib/Lingua/EN/Fathom.pm

filter: Statementstmt 61.5% 104 / 169 Branchbran 55.5% 20 / 36 Conditioncond 33.3% 3 / 9 MC/DCmcdc 16.6% 1 / 6 Subroutinesub 60.7% 17 / 28 Podpod 90.0% 18 / 20 totaltotal 60.8% 163 / 268 CC 23 SCAR 18.4
CC
23
Cov
59%
analyse_file
30.0
_analyse_words
7.0
unique_words
6.0
CRAP 6.3
↑ Summary
1 =head1 NAME
2  
3 Lingua::EN::Fathom - Measure readability of English text
4
5 =head1 SYNOPSIS
6
7 use Lingua::EN::Fathom;
8
9 my $text = Lingua::EN::Fathom->new();
10
11 $text->analyse_file("sample.txt"); # Analyse contents of a text file
12
13 $accumulate = 1;
14 my $text_string = q{
15 Returns the number of words in the analysed text file or block. A word must
16 consist of letters a-z with at least one vowel sound, and optionally an
17 apostrophe or hyphen.
18
19 ##########################################
20 Items such as "&, K108, NSW" are not counted as words.
21 Common abbreviations such a U.S. or numbers like 1.23 will not denote the end of
22 a sentence.
23 };
24
25 $text->analyse_block($text_string,$accumulate); # Analyse contents of a text string
26
27 print($text->report); # Create a formatted report
28
29 Number of characters : 312
30 Number of words : 54
31 Percent of complex words : 7.41
32 Average syllables per word : 1.4259
33 Number of sentences : 4
34 Average words per sentence : 13.5000
35 Number of text lines : 6
36 Number of non-text lines : 1
37 Number of blank lines : 2
38 Number of paragraphs : 2
39
40 READABILITY INDICES
41
42 Fog : 8.3630
43 Flesch : 72.4992
44 Flesch-Kincaid : 6.5009
45
46 # Methods to return statistics on the analysed text
47 $text->num_chars;
48 $text->num_words;
49 $text->percent_complex_words;
50 $text->num_sentences;
51 $text->num_text_lines;
52 $text->num_non_text_lines;
53 $text->num_blank_lines; # trailing EOLs are ignored
54 $text->num_paragraphs;
55 $text->syllables_per_word;
56 $text->words_per_sentence;
57 $text->unique_words;
58 $text->fog;
59 $text->flesch;
60 $text->kincaid;
61
62 # get a hash of unique words, keyed by word and occurrence as the value
63 $text->unique_words
64
65 # Print a list of unique words
66 %words = $text->unique_words;
67 foreach $word ( sort keys %words )
68 {
69 print("$words{$word} :$word\n");
70 }
71
72 =head1 REQUIRES
73  
74 Lingua::EN::Syllable, Lingua::EN::Sentence
75  
76  
77 =head1 DESCRIPTION
78  
79 This module analyses English text in either a string or file. Totals are
80 then calculated for the number of characters, words, sentences, blank
81 and non blank (text) lines and paragraphs.
82  
83 Three common readability statistics are also derived, the Fog, Flesch and
84 Kincaid indices.
85  
86 All of these properties can be accessed through individual methods, or by
87 generating a text report.
88  
89 A hash of all unique words and the number of times they occur is generated.
90  
91  
92 =head1 METHODS
93  
94 =head2 new
95  
96 The C<new> method creates an instance of an text object This must be called
97 before any of the following methods are invoked. Note that the object only
98 needs to be created once, and can be reused with new input data.
99  
100 my $text = Lingua::EN::Fathom->new();
101  
102 =head2 analyse_file
103  
104 The C<analyse_file> method takes as input the name of a text file. Various
105 text based statistics are calculated for the file. This method and
106 C<analyse_block> are prerequisites for all the following methods. An optional
107 argument may be supplied to control accumulation of statistics. If set to
108 a non zero value, all statistics are accumulated with each successive call.
109  
110 $text->analyse_file("sample.txt");
111  
112  
113 =head2 analyse_block
114  
115 The C<analyse_block> method takes as input a text string. Various
116 text based statistics are calculated for the file. This method and
117 C<analyse_file> are prerequisites for all the following methods. An optional
118 argument may be supplied to control accumulation of statistics. If set to
119 a non zero value, all statistics are accumulated with each successive call.
120  
121 $text->analyse_block($text_str,$accumulate);
122  
123 =head2 num_chars
124  
125 Returns the number of characters in the analysed text file or block. This
126 includes characters such as spaces, and punctuation marks.
127  
128 =head2 num_words
129  
130 Returns the number of words in the analysed text file or block. A word must
131 consist of letters a-z with at least one vowel sound, and optionally an
132 apostrophe or hyphen. Items such as "&, K108, NW" are not counted as words.
133  
134 =head2 percent_complex_words
135  
136 Returns the percentage of complex words in the analysed text file or block. A
137 complex word must consist of three or more syllables. This statistic is used to
138 calculate the fog index.
139  
140 =head2 num_sentences
141  
142 Returns the number of sentences in the analysed text file or block. A sentence
143 is any group of words and non words terminated with a single full stop. Spaces
144 may occur before and after the full stop.
145  
146 =head2 num_text_lines
147  
148 Returns the number of lines containing some text in the analysed
149 text file or block.
150  
151 =head2 num_non_text_lines
152  
153 Returns the number of lines containing no text in the analysed
154 text file or block.
155  
156 =head2 num_blank_lines
157  
158 Returns the number of empty lines in the analysed
159 text file or block.
160  
161 =head2 num_paragraphs
162  
163 Returns the number of paragraphs in the analysed text file or block.
164  
165 =head2 syllables_per_word
166  
167 Returns the average number of syllables per word in the analysed
168 text file or block.
169  
170 =head2 words_per_sentence
171  
172 Returns the average number of words per sentence in the analysed
173 text file or block.
174  
175  
176 =head2 READABILITY
177  
178 Three indices of text readability are calculated. They all measure complexity as
179 a function of syllables per word and words per sentence. They assume the text is
180 well formed and logical. You could analyse a passage of nonsensical English and
181 find the readability is quite good, provided the words are not too complex and
182 the sentences not too long.
183  
184 For more information see: L<http://www.plainlanguage.com/Resources/readability.html>
185  
186  
187 =head2 fog
188  
189 Returns the Fog index for the analysed text file or block.
190  
191 ( words_per_sentence + percent_complex_words ) * 0.4
192  
193 The Fog index, developed by Robert Gunning, is a well known and simple
194 formula for measuring readability. The index indicates the number of years
195 of formal education a reader of average intelligence would need to read the
196 text once and understand that piece of writing with its word sentence workload.
197  
198 18 unreadable
199 14 difficult
200 12 ideal
201 10 acceptable
202 8 childish
203  
204  
205 =head2 flesch
206  
207 Returns the Flesch reading ease score for the analysed text file or block.
208  
209 206.835 - (1.015 * words_per_sentence) - (84.6 * syllables_per_word)
210  
211 This score rates text on a 100 point scale. The higher the score, the easier
212 it is to understand the text. A score of 60 to 70 is considered to be optimal.
213  
214  
215 =head2 kincaid
216  
217 Returns the Flesch-Kincaid grade level score for the analysed text
218 file or block.
219  
220 (11.8 * syllables_per_word) + (0.39 * words_per_sentence) - 15.59;
221  
222 This score rates text on U.S. grade school level. So a score of 8.0 means
223 that the document can be understood by an eighth grader. A score of 7.0 to
224 8.0 is considered to be optimal.
225  
226 =head2 unique_words
227  
228 Returns a hash of unique words. The words (in lower case) are held in
229 the hash keys while the number of occurrences are held in the hash values.
230  
231  
232 =head2 report
233  
234 print($text->report);
235  
236 Produces a text based report containing all Fathom statistics for
237 the currently analysed text block or file. For example:
238
239 Number of characters : 813
240 Number of words : 135
241 Percent of complex words : 20.00
242 Average syllables per word : 1.7704
243 Number of sentences : 12
244 Average words per sentence : 11.2500
245 Number of text lines : 13
246 Number of non text lines : 0
247 Number of blank lines : 8
248 Number of paragraphs : 4
249  
250  
251 READABILITY INDICES
252  
253 Fog : 12.5000
254 Flesch : 45.6429
255 Flesch-Kincaid : 9.6879
256  
257 The return value is a string containing the report contents
258  
259  
260 =head1 SEE ALSO
261  
262 L<Lingua::EN::Syllable>,L<Lingua::EN::Sentence>,L<B::Fathom>
263  
264  
265 =head1 POSSIBLE EXTENSIONS
266  
267 Count white space and punctuation characters
268 Allow user control over what strictly defines a word
269  
270 =head1 LIMITATIONS
271  
272 The syllable count provided in Lingua::EN::Syllable is about 90% accurate
273 Acronyms that contain vowels, like GPO, will be counted as words.
274 The fog index should exclude proper names
275  
276  
277  
278 =head1 AUTHOR
279  
280 Lingua::EN::Fathom was written by Kim Ryan <kimryan at cpan dot org>.
281  
282 =head1 COPYRIGHT AND LICENSE
283  
284 Copyright (c) 2023 Kim Ryan. All rights reserved.
285  
286 This library is free software; you can redistribute it and/or modify
287 it under the same terms as Perl itself.
288  
289 =cut
290  
291 #------------------------------------------------------------------------------
292  
293 package Lingua::EN::Fathom;
294  
295 1 ▶use Lingua::EN::Syllable;
Subroutine BEGIN: called CC=1 SCAR=0.0
296 1 ▶use Lingua::EN::Sentence;
Subroutine BEGIN: called CC=1 SCAR=0.0
297 1 ▶use strict;
Subroutine BEGIN: called CC=1 SCAR=0.0
298 1 ▶use warnings;
Subroutine BEGIN: called CC=1 SCAR=0.0
299  
300 1 our $VERSION = '1.27';
301  
302 #------------------------------------------------------------------------------
303 # Create a new instance of a text object.
304  
305 sub new
306 1 ▶{
Subroutine new: called CC=1 SCAR=0.0
Pod documented
307 1 my $class = shift;
308  
309 1 my $text = {};
310 1 bless($text,$class);
311 1 $text = &_initialize($text);
312 1 return($text);
313 }
314 #------------------------------------------------------------------------------
315 # Analyse text stored in a file, reading from the file one line at a time
316  
317 sub analyse_file
318 0 ▶{
Subroutine analyse_file: not called CC=5 SCAR=34.0
Pod documented
319 0 my $text = shift;
320 0 my ($file_name,$accumulate) = @_;
321  
322 0 ▶ unless ( $accumulate )
Branch: 1 branch
BranchTrueFalseTotal
unless ($accumulate) 0 0 0
323 {
324 0 $text = _initialize($text);
325 }
326  
327 0 $text->{file_name} = $file_name;
328  
329 # Only analyse non-empty text files
330 0 ▶ unless ( -T $file_name and -s $file_name )
Branch: 1 branch
BranchTrueFalseTotal
unless (-T $file_name and -s $file_name) 0 0 0
Condition0%0/3
-T $file_name and -s $file_name
!ll&&!rl&&r
000
MC/DC0%0/2
-T $file_name and -s $file_name
-T $file_name -s $file_name
Truth table0%0/3
A and B
A= -T $file_nameB= -s $file_name
ABresult
0X0
100
111
331 {
332 0 return($text);
333 }
334  
335 0 open(IN_FH,"<$file_name");
336  
337 0 my $in_paragraph = 0;
338 0 my $all_text;
339 0 ▶ while ( <IN_FH> )
Branch: 1 branch
BranchTrueFalseTotal
if (defined($_ = readline IN_FH)) 0 0 0
340 {
341 0 my $one_line = $_;
342 0 $all_text .= $one_line;
343 0 ($in_paragraph,$text) = _analyse_line($text,$one_line,$in_paragraph);
344 }
345 0 close(IN_FH);
346
347 0 my $sentences= Lingua::EN::Sentence::get_sentences($all_text);
348 0 $text->{num_sentences} += scalar(@$sentences);
349 0 $text->_calculate_readability;
350  
351 0 return($text);
352 }
353 #------------------------------------------------------------------------------
354 # Analyse a block of text, stored as a string. The string may contain line
355 # terminators.
356  
357 sub analyse_block
358 1 ▶{
Subroutine analyse_block: called CC=5 SCAR=16.4
Pod documented
359 1 my $text = shift;
360 1 my ($block,$accumulate) = @_;
361  
362 1 ▶ unless ( $accumulate )
Branch: 1 branch
BranchTrueFalseTotal
unless ($accumulate) 1 0 1
363 {
364 1 $text = _initialize($text);
365 }
366  
367 1 ▶ unless ( $block )
Branch: 1 branch
BranchTrueFalseTotal
unless ($block) 0 1 1
368 {
369 0 return($text);
370 }
371  
372 1 my $in_paragraph = 0;
373  
374 # Split on EOL character
375 # repeating trailing line terminators are stripped
376 1 my @all_lines = split(/\n/,$block);
377 1 my $one_line;
378 1 foreach $one_line ( @all_lines )
379 {
380 9 ($in_paragraph,$text) = _analyse_line($text,$one_line,$in_paragraph);
381 }
382
383 1 my $sentences= Lingua::EN::Sentence::get_sentences($block);
384 1 ▶ if (defined($sentences))
Branch: 1 branch
BranchTrueFalseTotal
if (defined $sentences) 1 0 1
385 {
386 1 $text->{num_sentences} += scalar(@$sentences);
387 }
388
389
390 1 $text->_calculate_readability;
391
392 1 return($text);
393 }
394 #------------------------------------------------------------------------------
395 sub num_chars
396 1 ▶{
Subroutine num_chars: called CC=1 SCAR=0.0
Pod documented
397 1 my $text = shift;
398 1 return($text->{num_chars});
399 }
400 #------------------------------------------------------------------------------
401 sub num_words
402 1 ▶{
Subroutine num_words: called CC=1 SCAR=0.0
Pod documented
403 1 my $text = shift;
404 1 return($text->{num_words});
405 }
406 #------------------------------------------------------------------------------
407 sub percent_complex_words
408 0 ▶{
Subroutine percent_complex_words: not called CC=1 SCAR=6.9
Pod documented
409 0 my $text = shift;
410 0 return($text->{percent_complex_words});
411 }
412 #------------------------------------------------------------------------------
413 sub num_sentences
414 1 ▶{
Subroutine num_sentences: called CC=1 SCAR=0.0
Pod documented
415 1 my $text = shift;
416 1 return($text->{num_sentences});
417 }
418 #------------------------------------------------------------------------------
419 sub num_text_lines
420 1 ▶{
Subroutine num_text_lines: called CC=1 SCAR=0.0
Pod documented
421 1 my $text = shift;
422 1 return($text->{num_text_lines});
423 }
424 #------------------------------------------------------------------------------
425 sub num_non_text_lines
426 1 ▶{
Subroutine num_non_text_lines: called CC=1 SCAR=0.0
Pod documented
427 1 my $text = shift;
428 1 return($text->{num_non_text_lines});
429 }
430 #------------------------------------------------------------------------------
431 sub num_blank_lines
432 1 ▶{
Subroutine num_blank_lines: called CC=1 SCAR=0.0
Pod documented
433 1 my $text = shift;
434 1 return($text->{num_blank_lines});
435 }
436 #------------------------------------------------------------------------------
437 sub num_paragraphs
438 1 ▶{
Subroutine num_paragraphs: called CC=1 SCAR=0.0
Pod documented
439 1 my $text = shift;
440 1 return($text->{num_paragraphs});
441 }
442 #------------------------------------------------------------------------------
443 sub syllables_per_word
444 0 ▶{
Subroutine syllables_per_word: not called CC=1 SCAR=6.9
Pod documented
445 0 my $text = shift;
446 0 return($text->{syllables_per_word});
447 }
448 #------------------------------------------------------------------------------
449 sub words_per_sentence
450 0 ▶{
Subroutine words_per_sentence: not called CC=1 SCAR=6.9
Pod documented
451 0 my $text = shift;
452 0 return($text->{words_per_sentence});
453 }
454 #------------------------------------------------------------------------------
455 sub num_syllables
456 0 ▶{
Subroutine num_syllables: not called CC=1 SCAR=6.9
Pod undocumented
457 0 my $text = shift;
458 0 return($text->{num_syllables});
459 }
460 #------------------------------------------------------------------------------
461 sub complex_words
462 0 ▶{
Subroutine complex_words: not called CC=1 SCAR=6.9
Pod undocumented
463 0 my $text = shift;
464 0 return($text->{num_complex_words});
465 }
466 #------------------------------------------------------------------------------
467 sub fog
468 0 ▶{
Subroutine fog: not called CC=1 SCAR=6.9
Pod documented
469 0 my $text = shift;
470 0 return($text->{fog});
471 }
472 #------------------------------------------------------------------------------
473 sub flesch
474 0 ▶{
Subroutine flesch: not called CC=1 SCAR=6.9
Pod documented
475 0 my $text = shift;
476 0 return($text->{flesch});
477 }
478 #------------------------------------------------------------------------------
479 sub kincaid
480 0 ▶{
Subroutine kincaid: not called CC=1 SCAR=6.9
Pod documented
481 0 my $text = shift;
482 0 return($text->{kincaid});
483 }
484 #------------------------------------------------------------------------------
485 # Return anonymous hash of all the unique words in analysed text. The words
486 # occurrence count is stored in the hash value.
487  
488 sub unique_words
489 0 ▶{
Subroutine unique_words: not called CC=2 SCAR=17.9
Pod documented
490 0 my $text = shift;
491 0 ▶ if ( $text->{unique_words} )
Branch: 1 branch
BranchTrueFalseTotal
if ($text->{'unique_words'}) { } 0 0 0
492 {
493 0 return( %{ $text->{unique_words} } );
494 }
495 else
496 {
497 0 return(undef);
498 }
499 }
500 #------------------------------------------------------------------------------
501 # Provide a formatted text report of all statistics for a text object.
502 # Return report as a string.
503  
504 sub report
505 0 ▶{
Subroutine report: not called CC=2 SCAR=17.9
Pod documented
506 0 my $text = shift;
507 0 my $report = '';
508
509  
510 $text->{file_name} and
511 0 ▶ $report .= sprintf("File name : %s\n",$text->{file_name} );
Branch: 1 branch
BranchTrueFalseTotal
$text->{"file_name"} and $report .= sprintf("File name : %s\n", $text->{"file_name"}) 0 0 0
512  
513 0 $report .= sprintf("Number of characters : %d\n", $text->num_chars);
514 0 $report .= sprintf("Number of words : %d\n", $text->num_words);
515 0 $report .= sprintf("Percent of complex words : %.2f\n",$text->percent_complex_words);
516 0 $report .= sprintf("Average syllables per word : %.4f\n",$text->syllables_per_word);
517 0 $report .= sprintf("Number of sentences : %d\n", $text->num_sentences);
518 0 $report .= sprintf("Average words per sentence : %.4f\n",$text->words_per_sentence);
519 0 $report .= sprintf("Number of text lines : %d\n", $text->num_text_lines);
520 0 $report .= sprintf("Number of non-text lines : %d\n", $text->num_non_text_lines);
521 0 $report .= sprintf("Number of blank lines : %d\n", $text->num_blank_lines);
522 0 $report .= sprintf("Number of paragraphs : %d\n", $text->num_paragraphs);
523  
524 0 $report .= "\n\nREADABILITY INDICES\n\n";
525 0 $report .= sprintf("Fog : %.4f\n",$text->fog);
526 0 $report .= sprintf("Flesch : %.4f\n",$text->flesch);
527 0 $report .= sprintf("Flesch-Kincaid : %.4f\n",$text->kincaid);
528  
529 0 return($report);
530 }
531  
532 #------------------------------------------------------------------------------
533 # PRIVATE METHODS
534 #------------------------------------------------------------------------------
535 sub _initialize
536 2 ▶{
Subroutine _initialize: called CC=1 SCAR=0.0
537 2 my $text = shift;
538  
539 2 $text->{num_chars} = 0;
540 2 $text->{num_syllables} = 0;
541 2 $text->{num_words} = 0;
542 2 $text->{num_complex_words} = 0;
543 2 $text->{syllables_per_word} = 0;
544 2 $text->{words_per_sentence} = 0;
545 2 $text->{percent_complex_words} = 0;
546 2 $text->{num_text_lines} = 0;
547 2 $text->{num_non_text_lines} = 0;
548 2 $text->{num_blank_lines} = 0;
549 2 $text->{num_paragraphs} = 0;
550 2 $text->{num_sentences} = 0;
551 2 $text->{unique_words} = ();
552 2 $text->{file_name} = '';
553  
554 2 $text->{fog} = 0;
555 2 $text->{flesch} = 0;
556 2 $text->{kincaid} = 0;
557  
558 2 return($text);
559 }
560 #------------------------------------------------------------------------------
561 # Increment number of text lines, blank lines and paragraphs
562  
563 sub _analyse_line
564 9 ▶{
Subroutine _analyse_line: called CC=5 SCAR=16.1
565 9 my $text = shift;
566
567 9 my ($one_line,$in_paragraph) = @_;
568 9 ▶ if ( $one_line =~ /\w/ )
Branch: 3 branches
BranchTrueFalseTotal
if ($one_line =~ /\w/) { } 6 3 9
elsif ($one_line eq '') { } 2 1 3
elsif ($one_line =~ /^\W+$/) { } 1 0 1
569 {
570 6 chomp($one_line);
571 6 $text = _analyse_words($text,$one_line);
572 6 $text->{num_text_lines}++;
573
574 6 ▶ unless ( $in_paragraph )
Branch: 1 branch
BranchTrueFalseTotal
unless ($in_paragraph) 2 4 6
575 {
576 2 $text->{num_paragraphs}++;
577 2 $in_paragraph = 1;
578 }
579 }
580 elsif ($one_line eq '' ) # empty line
581 {
582 2 $text->{num_blank_lines}++;
583 2 $in_paragraph = 0;
584 }
585 elsif ($one_line =~ /^\W+$/ ) # non text
586 {
587 1 $text->{num_non_text_lines}++;
588 1 $in_paragraph = 0;
589 }
590 9 return($in_paragraph,$text);
591 }
592 #------------------------------------------------------------------------------
593 # Try to detect real words in line. Increment syllable, word, and complex word counters.
594  
595 sub _analyse_words
596 6 ▶{
Subroutine _analyse_words: called CC=7 SCAR=19.5
597 6 my $text = shift;
598 6 my ($one_line) = @_;
599  
600 6 $text->{num_chars} += length($one_line);
601  
602 # Word found, such as: twice, BOTH, a, I'd, non-plussed ..
603
604 # Ignore words like 'Mr.', K12, &, X.Y.Z ...
605 # It could be argued that Mr. is a word, but this approach should detect most of the non words
606 # which have punctuation or numbers in them
607
608 6 ▶ while ( $one_line =~ /\b([a-z][-'a-z]*)\b/ig )
Branch: 1 branch
BranchTrueFalseTotal
if ($one_line =~ /\b([a-z][-'a-z]*)\b/gi) 57 6 63
609 {
610 57 my $one_word = $1;
611  
612 # Try to filter out acronyms and abbreviations by accepting
613 # words with a vowel sound. This won't work for GPO etc.
614 57 ▶ next unless $one_word =~ /[aeiouy]/i;
Branch: 1 branch
BranchTrueFalseTotal
unless $one_word =~ /[aeiouy]/i 2 55 57
615  
616 # Test for valid hyphenated word like be-bop
617 55 ▶ if ( $one_word =~ /-/ )
Branch: 1 branch
BranchTrueFalseTotal
if ($one_word =~ /-/) 1 54 55
618 {
619 1 ▶ next unless $one_word =~ /[a-z]{2,}-[a-z]{2,}/i;
Branch: 1 branch
BranchTrueFalseTotal
unless $one_word =~ /[a-z]{2,}-[a-z]{2,}/i 1 0 1
620 }
621  
622 # word frequency count
623 54 $text->{unique_words}{lc($one_word)}++;
624
625 54 $text->{num_words}++;
626  
627 # Use subroutine from Lingua::EN::Syllable
628 54 my $num_syllables_current_word = syllable($one_word);
629 54 $text->{num_syllables} += $num_syllables_current_word;
630  
631 # Required for Fog index, count non hyphenated words of 3 or more
632 # syllables. Should add check for proper names in here as well
633 54 ▶ if ( $num_syllables_current_word > 2 and $one_word !~ /-/ )
Branch: 1 branch
BranchTrueFalseTotal
if ($num_syllables_current_word > 2 and not $one_word =~ /-/) 4 50 54
Condition66%2/3
$num_syllables_current_word > 2 and not $one_word =~ /-/
!ll&&!rl&&r
5004
MC/DC50%1/2
$num_syllables_current_word > 2 and not $one_word =~ /-/
$num_syllables_current_word > 2 not $one_word =~ /-/
Truth table66%2/3
A and not(B)
A= $num_syllables_current_word > 2B= not $one_word =~ /-/
ABresult
0X0
100
111
634 {
635 4 $text->{num_complex_words}++;
636 }
637 }
638  
639 6 return($text);
640 }
641 #------------------------------------------------------------------------------
642 # Determine the three readability indices
643  
644 sub _calculate_readability
645 1 ▶{
Subroutine _calculate_readability: called CC=3 SCAR=13.8
646 1 my $text = shift;
647  
648 1 ▶ if ( $text->{num_sentences} and $text->{num_words} )
Branch: 1 branch
BranchTrueFalseTotal
if ($text->{'num_sentences'} and $text->{'num_words'}) { } 1 0 1
Condition33%1/3
$text->{"num_sentences"} and $text->{"num_words"}
!ll&&!rl&&r
001
MC/DC0%0/2
$text->{"num_sentences"} and $text->{"num_words"}
$text->{"num_sentences"} $text->{"num_words"}
Truth table33%1/3
A and B
A= $text->{"num_sentences"}B= $text->{"num_words"}
ABresult
0X0
100
111
649 {
650 1 $text->{words_per_sentence} = $text->{num_words} / $text->{num_sentences};
651 1 $text->{syllables_per_word} = $text->{num_syllables} / $text->{num_words};
652 $text->{percent_complex_words} =
653 1 ( $text->{num_complex_words} / $text->{num_words} ) * 100;
654  
655 1 $text->{fog} = ( $text->{words_per_sentence} + $text->{percent_complex_words} ) * 0.4;
656  
657 $text->{flesch} = 206.835 - (1.015 * $text->{words_per_sentence}) -
658 1 (84.6 * $text->{syllables_per_word});
659  
660 $text->{kincaid} = (11.8 * $text->{syllables_per_word}) +
661 1 (0.39 * $text->{words_per_sentence}) - 15.59;
662 }
663 else
664 {
665 0 $text->{words_per_sentence} = 0;
666 0 $text->{syllables_per_word} = 0;
667 0 $text->{num_complex_words} = 0;
668 0 $text->{fog} = 0;
669 0 $text->{flesch} = 0;
670 0 $text->{kincaid} = 0;
671 }
672 }
673 #------------------------------------------------------------------------------
674 1 return(1);
↑ Summary