small fix for file-lkist, pdf parse

reality · May 19, 2020 · 4dd7d9d · 4dd7d9d
1 parent 0c6d340
commit 4dd7d9d
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/src/main/groovy/komenti/Komenti.groovy b/src/main/groovy/komenti/Komenti.groovy
@@ -191,7 +191,7 @@ public class Komenti {
 
       def fList
       if(o['file-list']) {
-        fList = new File(o['file-list']).text.split('\n')
+        fList = new File(o['file-list']).text.split('\n').collect { new File(it) }
       }
 
       def outWriter = new BufferedWriter(new FileWriter(o.out))

diff --git a/src/main/groovy/komenti/klib/PDFReader.groovy b/src/main/groovy/komenti/klib/PDFReader.groovy
@@ -18,6 +18,7 @@ public class PDFReader {
 
         def text = stripper.getText(reader).toLowerCase()
 
+        text = text.replaceAll('\n\n', '. ')
         text = text.replaceAll('\u2022', '.  ')
         text = text.replaceAll('â€“', '. ')
         text = text.replaceAll('\b-', '.  ')
@@ -27,7 +28,6 @@ public class PDFReader {
         text = text.replaceAll('\\s+', ' ')
         text = text.replaceAll(', \\?', '. ?')
         text = text.replaceAll('\\.', '. ')
-        text = text.replaceAll('\n\n', '. ')
 
         pages << text
       }