Merge pull request #11 from ChristophWenk/feature/cleanup

Conda enviroment

Readme.md

@@ -24,10 +24,16 @@ General functionality should look like this:
 - pypdf2 2.4.2
 - dateparser 1.1.1
 
-Other Python or package versions might work but have not been tested.
+Other Python or package versions might work but have not been tested. 
+
+A conda environment configuration is provided in 
+the `environment.yml` file. You can set it up with `conda env create -f environment.yml`. Activate it with
+`conda activate PDFSorter`.
 
 ## Document Type Configuration
 New document types can be added by creating new configuration files. The process is described below.
+Place the files in the directory defined in `settings.config_files_dir`. 
+The default is `'../resources/config_files'`.
 ### Configuration File Name
 The configuration file name has to adhere to the scheme below. The [Company] and the [Document Type] values have both 
 to be found in the PDF text content. This will only be used to select the correct configuration file for the PDF in 
@@ -78,7 +84,7 @@ the configuration file and may include property keys generated from the regex pa
     "target_directory": "F:\\Dokumente\\Rechnungen\\Helsana\\Leistungsabrechnungen",
     "file_name_format":  "{company_name}_{date}_{document_type}_{document_id}.pdf",
     "document_id": "ABCD",
-    "date": "2022-01-01"
+    "date": "2022-12-31"
 }
 ```
 

environment.yml

@@ -0,0 +1,29 @@
+name: PDFSorter
+channels:
+  - defaults
+dependencies:
+  - bzip2=1.0.8=he774522_0
+  - ca-certificates=2022.4.26=haa95532_0
+  - certifi=2022.6.15=py310haa95532_0
+  - dateparser=1.1.1=pyhd3eb1b0_0
+  - libffi=3.4.2=hd77b12b_4
+  - openssl=1.1.1p=h2bbff1b_0
+  - pip=21.2.4=py310haa95532_0
+  - python=3.10.4=hbb2ffb3_0
+  - python-dateutil=2.8.2=pyhd3eb1b0_0
+  - pytz=2022.1=py310haa95532_0
+  - regex=2021.8.3=py310h2bbff1b_0
+  - setuptools=61.2.0=py310haa95532_0
+  - six=1.16.0=pyhd3eb1b0_1
+  - sqlite=3.38.5=h2bbff1b_0
+  - tk=8.6.12=h2bbff1b_0
+  - tzdata=2022a=hda174b7_0
+  - tzlocal=2.1=py310haa95532_0
+  - vc=14.2=h21ff451_1
+  - vs2015_runtime=14.27.29016=h5e58377_2
+  - wheel=0.37.1=pyhd3eb1b0_0
+  - wincertstore=0.2=py310haa95532_2
+  - xz=5.2.5=h8cc25b3_1
+  - zlib=1.2.12=h8cc25b3_2
+  - pip:
+    - pypdf2==2.4.2

pdf_sorter/main.py

@@ -60,10 +60,9 @@ def get_attr_from_regex(config, regex, file_name, not_processed_list, pdf_text):
 
 
 def process_files(path, config_file_path):
-    logger.info("\n"
-                "##################################\n"
-                "# Starting new PDF Sort Run      #\n"
-                "##################################")
+    logger.info("##################################")
+    logger.info("# Starting new PDF Sort Run      #")
+    logger.info("##################################")
     if settings.dry_run is True:
         logger.warning("Dry Run active: Running in preview mode. No files will be renamed or moved.")
 
@@ -118,17 +117,15 @@ def process_files(path, config_file_path):
             continue
 
     logger.info('==============================================================================================')
-    logger.info("\n"
-                "##################################\n"
-                "# PDF Sort Run completed         #\n"
-                "##################################")
+    logger.info("##################################")
+    logger.info("# PDF Sort Run completed         #")
+    logger.info("##################################")
 
     if not_processed_list:
+        logger.warning("The following PDF files could not be processed or have just been partially processed:")
         output_list = ""
         for file_name in not_processed_list:
-            output_list += "\n" + file_name
-        logger.warning("The following PDF files could not be processed or have just been partially processed:" +
-                       output_list)
+            logger.warning(file_name)
 
 
 # Main Function

pdf_sorter/settings.py

@@ -2,7 +2,7 @@
 import logging
 
 # Do (False) or do not (True) rename files and move them
-dry_run = True
+dry_run = False
 
 # Folder that contains the PDFs to process
 pdf_files_dir = 'F:/Downloads/02_pdf_sorter'