Cleanup code, formatting & replaced pdftk stuff by fillpdf & pdfrw2

goodbye external dependencys, this is now python-native code

.gitignore

@@ -1,4 +1 @@
-output*.pdf
 teilnehmendenliste*.pdf
-
-data_fdf.bin

generate_bmbf_list.py

@@ -1,103 +1,107 @@
 #!/usr/bin/env python3
-from fdfgen import forge_fdf
-import sh
-from math import ceil
 import csv
+import os
+import tempfile
+from math import ceil
 from operator import itemgetter
-from pathlib import Path
+
+from fillpdf import fillpdfs
+from pdfrw import PdfReader, PdfWriter
+
+# Change to your needs
+event_period = "25.05. - 29.05.22"
+event_org = "Verein der Freunde und Förderer der Bundesfachschaftentagung Elektrotechnik e.V."
+event_name = "90. Bundesfachschaftentagung Elektrotechnik"
+attendees_csv = "teilnehmer_innen.csv"
+empty_sheets = 1
+template_form = "210705_Teilnehmendenliste_abgestimmt.pdf"
+date_list = ["25.05.22", "26.05.22", "27.05.22", "28.05.22", "29.05.22"]
+
+# Nothing to change below here
+
+form_mapping = [("6", "20", "21"), ("19", "40", "41"), ("18", "39", "22"),
+                ("17", "42", "23"), ("16", "43", "24"), ("15", "44", "25"), ("14", "45", "26"),
+                ("13", "46", "27"), ("12", "Text7", "28"), ("11", "29", "34"), ("10", "30", "35"),
+                ("9", "31", "36"), ("8", "32", "37"), ("7", "33", "38")]
 
 
-
+def read_csv(csv_path):
-######## Bitte hier Anpassen ##########################################
-maßnahmenzeitraum = "25.05. - 29.05.22"
-datum="25.05.22"
-kif_ev= "Verein der Freunde und Förderer der Bundesfachschaftentagung Elektrotechnik e.V."
-maßname="90. Bundesfachschaftentagung Elektrotechnik"
-csv_file_name="teilnehmer_innen.csv"
-leer_blaetter=1
-vorlage = "210705_Teilnehmendenliste_abgestimmt.pdf"
-datum_list = ["25.05.22","26.05.22","27.05.22","28.05.22","29.05.22",]
-
-
-######## Nothing to change below here ##########################################
-
-form_mapping = [("6","20","21"),("19","40","41"),("18","39","22"),
-            ("17","42","23"),("16","43","24"),("15","44","25"),("14","45","26"),
-            ("13","46","27"),("12","Text7","28"),("11","29","34"),("10","30","35"),
-            ("9","31","36"),("8","32","37"),("7","33","38")]
-
-
-def readcsv(csv_file_name):
     persons = []
     try:
-        csvfile = open(csv_file_name,newline='')
+        csvfile = open(csv_path, newline='')
     except FileNotFoundError:
-        print("[X] File {} not found!".format(csv_file_name))
+        print("[X] File {} not found!".format(csv_path))
         exit(-1)
     else:
         with csvfile:
             reader = csv.DictReader(csvfile, delimiter=",")
-            persons = [{"Name": f"{t['Vorname']} {t['Nachname']}", "Hochschule": f"{t['Standort']}"} for t in reader if t['Status'] == "Student"]
+            persons = [{"Name": f"{t['Vorname']} {t['Nachname']}", "Hochschule": f"{t['Standort']}"} for t in reader if
-            persons.sort(key=itemgetter("Hochschule","Name"))
+                       t['Status'] == "Student"]
+            persons.sort(key=itemgetter("Hochschule", "Name"))
 
     return persons
 
 
-def generate_pdfs(persons, maßnahmenzeitraum, datum, kif_ev, maßname, leer_blaetter):
+def fill_pdf_form(working_directory, form, persons, zeitraum, form_date, org_name, name, add_sheets):
-    seite = 1
+    page = 1
-    data_file="data_fdf.bin"
+    output_file_name = "output"
-    output_file_name="output"
     personen_pro_seite = 14
 
-    #check if vorlage exits
+    anzahl_seiten = ceil(len(persons) / personen_pro_seite)
-    test_file = Path(vorlage)
-    if not test_file.is_file():
-        print("[X] File {} not found!".format(vorlage))
-        exit(-1)
-
-    anzahl_seiten = ceil(len(persons)/personen_pro_seite)
     pdfs = []
 
-    for j in range(anzahl_seiten+leer_blaetter):
+    for j in range(anzahl_seiten + add_sheets):
-        felder = []
+        felder = {}
-        i=0
+        i = 0
         for item in form_mapping:
-            if personen_pro_seite*j+i < len(persons):
+            if personen_pro_seite * j + i < len(persons):
-                felder.append((item[0],str(j*personen_pro_seite+i+1)))
+                felder[item[0]] = str(j * personen_pro_seite + i + 1)
-                felder.append((item[1], persons[j*personen_pro_seite+i]["Name"]))
+                felder[item[1]] = persons[j * personen_pro_seite + i]["Name"]
-                felder.append((item[2], persons[j*personen_pro_seite+i]["Hochschule"]))
+                felder[item[2]] = persons[j * personen_pro_seite + i]["Hochschule"]
-            i+=1
+            i += 1
 
             if i == personen_pro_seite:
-                output_file = output_file_name + str(seite) +".pdf"
+                output_file_path = os.path.join(working_directory, f'{output_file_name}{page}.pdf')
 
-                headers = [("1", seite), ("2", maßnahmenzeitraum), ("3", datum), ("4", kif_ev), ("5", maßname)]
+                headers = {"1": page, "2": zeitraum, "3": form_date, "4": org_name, "5": name}
 
-                fields = felder + headers
+                fields = {**headers, **felder}
-
-
-                fdf = forge_fdf("",fields,[],[],[])
-                fdf_file = open(data_file,"wb")
-                fdf_file.write(fdf)
-                fdf_file.close()
-
-                sh.pdftk(vorlage,"fill_form", data_file,"output",output_file,"flatten")
-
-                pdfs.append(output_file)
-
-                seite+=1
 
+                fillpdfs.write_fillable_pdf(input_pdf_path=form, output_pdf_path=output_file_path, data_dict=fields,
+                                            flatten=True)
+                pdfs.append(output_file_path)
+                page += 1
 
     return pdfs
 
 
+def concat_pdfs(file_list: list, output_pdf: str):
+    writer = PdfWriter()
+    for input_file in file_list:
+        reader = PdfReader(input_file)
+        writer.addpages(reader.pages)
+        writer.trailer.Info = reader.Info
+
+    writer.write(output_pdf)
+
 
 if __name__ == "__main__":
-    person_list = readcsv(csv_file_name)
+    workdir = tempfile.mkdtemp()
-    for datum in datum_list:
+    cwd = os.getcwd()
-        final_pdf_name = "teilnehmendenliste_{}.pdf".format(datum.replace(". ", "_"))
+    csv_file_path = os.path.join(cwd, attendees_csv)
-        output_files = generate_pdfs(person_list, maßnahmenzeitraum, datum, kif_ev, maßname, leer_blaetter)
+    person_list = read_csv(csv_file_path)
-        sh.pdftk(output_files, "cat","output",final_pdf_name )
+    form_path = os.path.join(cwd, template_form)
-
 
+    # check if form exits
+    if not os.path.exists(form_path):
+        print("[X] File {} not found!".format(form_path))
+        exit(1)
 
+    for date in date_list:
+        final_pdf_name = f'teilnehmendenliste_{date.replace(". ", "_")}.pdf'
+        print(f'Creating {final_pdf_name}... ', end='')
+        final_pdf_path = os.path.join(cwd, final_pdf_name)
+        output_files = fill_pdf_form(workdir, form_path, person_list, event_period, date, event_org, event_name,
+                                     empty_sheets)
+        concat_pdfs(file_list=output_files, output_pdf=final_pdf_path)
+        print('done!')

requirements.txt

@@ -1,3 +1,2 @@
-fdfgen
+fillpdf~=0.7.1
-sh
+pdfrw2~=0.5.0
-pathlib