fixed get_raw_def method and bumped version in Pipfile.lock (#29)

Pipfile

@@ -8,6 +8,7 @@ ipykernel = "*"
 tabula-py = "*"
 pikepdf = "*"
 click = "*"
+pdf-statement-reader = {editable = true, path = "."}
 
 [dev-packages]
 setuptools = "*"

README.md

@@ -127,6 +127,8 @@ The configuration file itself is in JSON format. Here's the Absa cheque account
 
 These were the configuration options that were required for the default format. It is envisaged that as more formats are added, the list of options will grow.
 
+A key part in setting up a new configuration is getting the page coordinates for the area and columns. The easiest way to do this is to run the [tabula GUI](https://tabula.technology/), autodetect the page areas, save the settings as a template, then download and inspect json template file. It's not a one-to-one mapping to the psr config but hopefully it will be a good starting point.
+
 ## CLI API
 
 ### decrypt

data/.gitignore

@@ -0,0 +1,2 @@
+*
+!.gitignore

pdf_statement_reader/parse.py

@@ -28,9 +28,8 @@ def get_raw_df(filename, num_pages, config):
                 "-Dorg.apache.commons.logging.Log=org.apache.commons.logging.impl.NoOpLog"
             ]
         )
-        if df is not None:
-            dfs.append(df)
-
+        if df is not None and len(df) > 0:
+            dfs.extend(df)
     statement = pd.concat(dfs, sort=False).reset_index(drop=True)
     return statement
 

setup.py

@@ -5,7 +5,7 @@
 
 setup(
     name="pdf_statement_reader",
-    version="0.2.1",
+    version="0.2.2",
     description="PDF Statement Reader",
     long_description=long_description,
     long_description_content_type="text/markdown",