This commit is contained in:
nate smith 2024-04-30 21:52:20 -07:00
parent 4b497a8185
commit 9031c268c9
3 changed files with 12 additions and 7 deletions

View File

@ -139,7 +139,7 @@ func worker(opts CutupOpts, paths <-chan string, sources chan<- string) {
}
}
for i, r := range text {
if v := shouldBreak(phraseBuff, r); v > 0 {
if v := shouldBreak(phraseBuff, r); v >= 0 {
if len(phraseBuff) > 0 {
phraseBuff = phraseBuff[0 : len(phraseBuff)-v]
}
@ -198,7 +198,7 @@ const maxSuffixLen = 8 // magic number based on longest suffix
func shouldBreak(phraseBuff []byte, r rune) int {
if ok := phraseMarkers[r]; ok {
return 1
return 0
}
if r != ' ' {

View File

@ -82,6 +82,11 @@ func Test_shouldBreak(t *testing.T) {
args: args{[]byte("whether good or"), ' '},
expected: 2,
},
{
name: "phrase marker",
args: args{[]byte("whither good"), ';'},
expected: 1,
},
// TODO test phrasemarkers
}

View File

@ -121,18 +121,18 @@ a {
<a is="about-toggler"></a>
<a is="theme-toggler"></a>
</p>
<p id="about">
<div>
<div id="about">
<p>
HELLO. THIS IS A <a href="https://github.com/vilmibm/trunkless">SOFT WARE</a> FOR MAKING <a href="https://en.wikipedia.org/wiki/Cut-up_technique">CUT-UP POETRY</a>. THERE ARE A VARIETY OF CORPORA TO CHOOSE FROM:
</div>
</p>
<ul>
<li><code>gutenberg</code>, THE ENTIRE ENGLISH CONTENT OF <a href="https://gutenberg.org">PROJECT GUTENBERG</a>. IT IS UNABRIDGED: BE WARNED.</li>
</ul>
<div>
<p>
THE AUTHOR OF THIS SOFT WARE IS <a href="https://tilde.town/~vilmibm">~VILMIBM</a>.
</div>
</p>
</div>
<div class="controls">
<button is="poem-resetter"></button>
<form is="corpus-picker" style="display:inline">