Removed .pdf from document title in pdf_converter (#315)

* removed .pdf from document title in pdf_converter * bump version
cdqa-suite · Nov 29, 2019 · 424e450 · 424e450
1 parent 7919dad
commit 424e450
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/cdqa/utils/converters.py b/cdqa/utils/converters.py
@@ -168,7 +168,7 @@ def pdf_converter(directory_path, min_length=200, include_line_breaks=False):
     df = pd.DataFrame(columns=["title", "paragraphs"])
     for i, pdf in enumerate(list_pdf):
         try:
-            df.loc[i] = [pdf, None]
+            df.loc[i] = [pdf.replace(".pdf",''), None]
             raw = parser.from_file(os.path.join(directory_path, pdf))
             s = raw["content"]
             paragraphs = re.split("\n(?=\u2028|[A-Z-0-9])", s)

diff --git a/setup.py b/setup.py
@@ -8,7 +8,7 @@ def read(file):
 
 setup(
     name="cdqa",
-    version="1.3.7",
+    version="1.3.8",
     author="Félix MIKAELIAN, André FARIAS, Matyas AMROUCHE, Olivier SANS, Théo NAZON",
     description="An End-To-End Closed Domain Question Answering System",
     long_description=read("README.md"),