Merge branch 'master' of https://github.com/danielquinn/paperless into feature/heuristically-extract-date-from-document-text

Dockerfile

@@ -45,3 +45,4 @@ WORKDIR /usr/src/paperless/src
 VOLUME ["/usr/src/paperless/data", "/usr/src/paperless/media", "/consume", "/export"]
 ENTRYPOINT ["/sbin/docker-entrypoint.sh"]
 CMD ["--help"]
+

requirements.txt

@@ -19,7 +19,7 @@ pdftotext>=2.0.1
 
 # For the tests
 factory-boy
-pytest
+pytest==3.3.2  # Newer versions break with pytest-sugar
 pytest-django
 pytest-sugar
 pytest-env

src/paperless/version.py

@@ -1 +1 @@
-__version__ = (1, 1, 0)
+__version__ = (1, 2, 0)

src/paperless_tesseract/parsers.py

@@ -260,6 +260,6 @@ def get_text_from_pdf(pdf_file):
         try:
             pdf = pdftotext.PDF(f)
         except pdftotext.Error:
-            return False
+            return ""
 
     return "\n".join(pdf)