From b9fa82f82b943cd1675ccc04835432e6f91a9cc2 Mon Sep 17 00:00:00 2001
From: AntonObersteiner <anton.obersteiner@gmail.com>
Date: Mon, 3 Jun 2024 11:02:01 +0200
Subject: [PATCH] integrate the hidden data

---
 generate.py | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/generate.py b/generate.py
index 06b4192..c748306 100755
--- a/generate.py
+++ b/generate.py
@@ -38,6 +38,13 @@ Maybe you can filter it with regular expressions? Good luck.
 # fünf Tatverdächtige
 # Uhrzeiten, siehe Infos von Verantwortlichen
 # Groß-Klein-Schreibung
+hidden_data = [
+	"Anna Bartel hat den Zweitversuch nicht bestanden.",
+	"Student Boris Parsch mit Matrikelnummer hat den Zweitversuch nicht bestanden.",
+	"Studentin Carola Winter mit Matrikel-Nr. 4940456 hat den 2. Versuch nicht bestanden.",
+	"Student:in Dennis Meier hat den 2. Versuch nicht bestanden.",
+	"Elisa Menniz, MatrNr. 5143424 hat den Zweitversuch nicht bestanden.",
+]
 
 network = Network(
 	start = Choice(
@@ -51,7 +58,7 @@ network = Network(
 		student_mit = get_names("nachnamen.csv"),
 	),
 	student_mit = Choice(
-		matr_nr = ["mit "],
+		matr_nr = ["mit ", ", "],
 	),
 	matr_nr = Choice(
 		matr_number = ["Matrikelnummer ", "Matrikel-Nummer ", "MatrNr. ", "Matrikel-Nr. "],
@@ -77,12 +84,19 @@ network = Network(
 	),
 )
 
-def generate_text(number_of_lines = 100):
+def pop_hidden_data():
+	global hidden_data
+	index = randint(0, len(hidden_data) - 1)
+	return hidden_data.pop(index)
+
+def generate_text(number_of_lines = 200):
 	result = ""
-	for i in range(200):
+	for i in range(number_of_lines):
 		emissions, _ = network.choose()
 		line = ''.join(emissions)
 		result += line + "\n"
+		if random() < len(hidden_data) / (number_of_lines - i):
+			result += pop_hidden_data() + "\n"
 	return result
 
 def read_template(filename = "./template.html"):