Merge pull request #41 from VikParuchuri/dev

Dev

Author: VikParuchuri

pdftext/pdf/pages.py

@@ -107,8 +107,8 @@ def span_break():
             span_break()
             continue
 
-        # we also break on hyphenation
-        if span['text'].endswith("\x02"):
+        # we break on hyphenation or newline
+        if span['text'].endswith("\x02") or span['text'].endswith("\n"):
             span_break()
             continue
 

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pdftext"
-version = "0.6.1"
+version = "0.6.2"
 description = "Extract structured text from pdfs quickly"
 authors = ["Vik Paruchuri <vik.paruchuri@gmail.com>"]
 license = "Apache-2.0"