introduced starts_with_matnum

encrypt.py

@@ -16,7 +16,7 @@ import argparse
 import sys
 import time
 
-import utils.matnum as utils
+import utils.matnum as matnum_utils
 
 
 def encrypt(pdf_file, enc_file, password):
@@ -90,8 +90,8 @@ Files in output folder {} will be overwritten during this process.
     enc_files = []
     for pdf_file in pdf_files:
         # File ID for password storage
-        if utils.check_matnum(pdf_file[0:6]):  # PDF file is linked to matnum
-            pdf_id = utils.get_matnum(pdf_file)
+        if matnum_utils.starts_with_matnum(pdf_file):  # PDF linked to matnum
+            pdf_id = matnum_utils.get_matnum(pdf_file)
         else:  # PDF file does not start with matnum
             pdf_id = pdf_file
 

preparemoodle.py

@@ -6,7 +6,7 @@ import time
 import shutil  # copyfile, make_archive
 import argparse
 import sys
-import utils.matnum as utils
+import utils.matnum as matnum_utils
 
 
 def find_unmatched_pdfs(infolder, matnums, nowarn):
@@ -26,7 +26,7 @@ def find_unmatched_pdfs(infolder, matnums, nowarn):
         for pdffile in files:
             if pdffile.endswith(".pdf"):
                 # Get matriculation number from file
-                matnum = utils.get_matnum(pdffile)
+                matnum = matnum_utils.get_matnum(pdffile)
 
                 # Search matriculation number in CSV
                 if matnum not in matnums:
@@ -125,7 +125,7 @@ Processing {} lines
             # If pdf files for current student exists, create a directory and
             # copy the pdf files to it. The resulting directories can be
             # uploaded to Moodle
-            longpdffiles = utils.find_file(matnum + "*.pdf", infolder)
+            longpdffiles = matnum_utils.find_file(matnum + "*.pdf", infolder)
             if len(longpdffiles) > 0:  # Found some file(s)
                 numfoundpdfs += 1
 

supplements.py

@@ -15,7 +15,7 @@ import argparse  # handle command line arguments
 import shutil  # copy
 import csv  # handle CSV files
 
-import utils.matnum as utils
+import utils.matnum as matnum_utils
 
 
 def copy_supplements(supp_dir, supp_files, prefixes, output_dir, dry=False):
@@ -127,7 +127,8 @@ Files in output folder {} will be overwritten during this process.
     if pdf_dir != "":  # Take prefixes from pdf directory
         pdf_folder = os.listdir(pdf_dir)
         pdf_files = [_ for _ in pdf_folder
-                     if _.endswith(".pdf") and utils.check_matnum(_.split('_', 1)[0])]
+                     if _.endswith(".pdf") and
+                     matnum_utils.starts_with_matnum(_)]
         prefixes = []
         for pdf_file in pdf_files:
             prefix = os.path.splitext(pdf_file)[0]  # take file name as prefix
@@ -144,7 +145,7 @@ Files in output folder {} will be overwritten during this process.
                 name = row[1]  # [Lastname], [Firstname]
                 name = name[0]  # Take only first letter of lastname
                 matnum = row[2]  # matriculation number (6-digit)
-                if not utils.check_matnum(matnum):
+                if not matnum_utils.check_matnum(matnum):
                     raise Exception("Invalid matriculation number found")
 
                 prefix = matnum + "_" + name

tests/test_watermark.py

@@ -23,8 +23,9 @@ class MainTest(unittest.TestCase):
 
         # Prepare parameter
         in_dir = './pdfs'
-        dpi = 250
+        dpi = 150
         quality = 75
+        fontsize = 75
         pdf_file = '123456_Nachname.pdf'
 
         tmp_dir = os.path.join(self.test_dir, 'tmp')
@@ -34,8 +35,9 @@ class MainTest(unittest.TestCase):
         os.mkdir(out_dir)
 
         # Call function
-        watermark.watermark_pdf(in_dir, tmp_dir, out_dir,
-                                dpi, quality, pdf_file)
+        watermark.watermark_pdf(input_dir=in_dir, tmp_dir=tmp_dir,
+                                output_dir=out_dir, fontsize=fontsize, dpi=dpi,
+                                quality=quality, pdf_file=pdf_file)
 
         self.assertTrue(os.listdir(out_dir)[0], '123456_Nachname_w.pdf')
 
@@ -48,7 +50,7 @@ class MainTest(unittest.TestCase):
 
         # Prepare parameter
         in_dir = './pdfs'
-        dpi = 250
+        dpi = 150
 
         tmp_dir = os.path.join(self.test_dir, 'tmp')
         os.mkdir(tmp_dir)

utils/matnum.py

@@ -23,31 +23,64 @@ def find_file(pattern, path):
     return result
 
 
+def _extract_matnum(s):
+    """Internal wrapper for splitting string
+
+    Args:
+        s (string): string
+
+    Returns:
+        string: all characters in string until first occurence of '_'.
+    """
+    # Has to be separated by "_" from the rest of the file name
+    return s.split('_', 1)[0]
+
+
 def check_matnum(matnum):
     """Checks for valid matriculation number
 
+    * All characters have to be digits
+    * Either five or six digits
+
     Args:
         matnum (str): matriculation number
 
     Returns:
         bool: valid
     """
+
     return (len(matnum) == 6 or len(matnum) == 5) and matnum.isdigit()
 
 
+def starts_with_matnum(s):
+    """Checks string for starting with valid matriculation number
+
+    Args:
+        s (str): file name with first 5 to 6 characters matriculation number
+
+    Returns:
+        bool: valid
+    """
+
+    matnum = _extract_matnum(s)
+    return check_matnum(matnum)
+
+
 def get_matnum(s):
-    """Extracts matriculation number from string
+    """Extracts matriculation number from string and checks if valid
 
     Args:
     s (str): file name with first 6 characters matriculation number
 
     Returns:
     str: 6-digit matriculation number
+
+    Throws:
+    Error (ValueError) if file does not start with propper matriculation number
     """
 
     # Get matriculation number
-    # Has to be separated by "_" from the rest of the file name
-    matnum = s.split('_', 1)[0]
+    matnum = _extract_matnum(s)
 
     # Sanity check
     if not check_matnum(matnum):

watermark.py

@@ -16,10 +16,9 @@ from multiprocessing import Pool  # multi processing
 from functools import partial
 from wand.image import Image as wi  # PDF to images
 from PIL import Image, ImageDraw, ImageFont  # Image handling
-from pikepdf import Pdf #combining PDFs
-from glob import glob   #combining PDFs
+from pikepdf import Pdf  # combining PDFs
 
-import utils.matnum as utils
+import utils.matnum as matnum_utils
 
 
 def convert_pdf_to_img(pdf_file, input_dir, tmp_dir, dpi):
@@ -108,17 +107,20 @@ def create_watermark_template(img_file, matnum, fontsize, dpi):
 
     return template
 
+
 def remove_transparency(im, bg_colour=(255, 255, 255)):
     """
     Correct transparent image turning black issue
     Args:
-        pdf page image
-        background color white code
+        im (PIL.Image.Image): pdf page image
+        bg_colour (tuple): background color white code
     Returns:
-        corrected image when the image is transparent
-        else just retuirn the pdf page image
+        PIL.Image.Image: corrected image when the image is transparent
+        else just return the pdf page image
     """
-    if im.mode in ('RGBA', 'LA') or (im.mode == 'P' and 'transparency' in im.info):
+
+    if (im.mode in ('RGBA', 'LA')) or (im.mode == 'P' and
+                                       'transparency' in im.info):
         alpha = im.convert('RGBA').split()[-1]
         # Create a new background image of our matt color.
         # Must be RGBA because paste requires both images have the same format
@@ -211,7 +213,7 @@ def watermark_pdf(input_dir, tmp_dir, output_dir,
     img_files = convert_pdf_to_img(pdf_file, input_dir, tmp_dir, dpi)
 
     # Extracting matriculation numebers
-    matnum = utils.get_matnum(pdf_file)
+    matnum = matnum_utils.get_matnum(pdf_file)
 
     # Watermarking PDF page images
     # Create template for first page
@@ -250,19 +252,23 @@ def main(args):
       Watermarked PDFs are stored in folder 'out'
       ''')
     parser.add_argument("-i", "--infolder", default="./pdfs",
-        help="Input folder with PDFs. Default: ./pdfs")
+                        help="Input folder with PDFs. Default: ./pdfs")
     parser.add_argument("-o", "--outfolder", default="./pdfs_watermarked",
-        help="Output folder of the PDFs. Default: ./pdfs_watermarked")
+                        help="Output folder of the PDFs. " +
+                        "Default: ./pdfs_watermarked")
     parser.add_argument("-f", "--fontsize", default="75",
-        help="Font size of watermark text in points. Default: 75")
+                        help="Font size of watermark text in points. " +
+                        "Default: 75")
     parser.add_argument("-c", "--cores", default="1",
-        help="Number of cores for parallel processing. Default: 1")
+                        help="Number of cores for parallel processing. " +
+                        "Default: 1")
     parser.add_argument("-t", "--tmp", default="./tmp",
-        help="tmp folder. Default: ./tmp/")
-    parser.add_argument("-d", "--dpi", default="250",
-        help="dpi parameter for conversion from pdf to images. Default: 250")
+                        help="tmp folder. Default: ./tmp/")
+    parser.add_argument("-d", "--dpi", default="150",
+                        help="DPI parameter for PDF to image conversion. " +
+                        "Default: 150")
     parser.add_argument("-q", "--quality", default="75",
-        help="quality parameter for jpeg. Default: 75")
+                        help="quality parameter for jpeg. Default: 75")
 
     args = parser.parse_args(args)
     infolder = args.infolder
@@ -277,7 +283,7 @@ def main(args):
     starttime = time.time()
     pdf_folder = os.listdir(infolder)
     pdf_files = [_ for _ in pdf_folder
-                 if _.endswith(".pdf") and utils.check_matnum(_.split('_', 1)[0])]
+                 if _.endswith(".pdf") and matnum_utils.starts_with_matnum(_)]
     print("""
 Available PDFs to be watermarked:
 - {}