Generation Script + BUGFIX, XSD für Beilagen

This commit is contained in:
Simon Martens
2024-08-15 14:22:51 +02:00
parent 913f83ba17
commit 9674030be0
10 changed files with 876 additions and 736 deletions

View File

@@ -0,0 +1,108 @@
import os
import re
import sys
from datetime import datetime, timedelta
from xml.etree.ElementTree import Element, SubElement, tostring
from xml.dom import minidom
def get_files(directory):
pattern = re.compile(r'(\d{4})-(\d+)(b\d?)?-(\d+)\.jpg')
files = {}
year = None
for filename in os.listdir(directory):
match = pattern.match(filename)
if match:
file_year, stueck, beilage_info, page = match.groups()
file_year = int(file_year)
stueck = int(stueck)
page = int(page)
if year is None:
year = file_year
elif year != file_year:
raise ValueError(f"Inconsistent years found: {year} and {file_year}")
if stueck not in files:
files[stueck] = {'main': [], 'beilage': []}
if beilage_info:
beilage_num = int(beilage_info[1:] or '1')
files[stueck]['beilage'].append((beilage_num, page))
else:
files[stueck]['main'].append(page)
return files, year
def calculate_date(year, stueck_number):
base_date = datetime(year, 1, 1) # Start from January 1st of the given year
while base_date.weekday() != 4: # Find the first Friday
base_date += timedelta(days=1)
days_to_add = (stueck_number - 1) * 3 + ((stueck_number - 1) // 2) * 1
return base_date + timedelta(days=days_to_add)
def create_xml(files, year):
root = Element('stuecke')
root.set('xmlns', 'https://www.koenigsberger-zeitungen.de')
root.set('xmlns:xsi', 'http://www.w3.org/2001/XMLSchema-instance')
root.set('xsi:schemaLocation', 'https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd')
for stueck, pages in sorted(files.items()):
stueck_elem = SubElement(root, 'stueck')
nummer = SubElement(stueck_elem, 'nummer')
nummer.text = str(stueck)
date = calculate_date(year, stueck)
datum = SubElement(stueck_elem, 'datum')
datum.set('when', date.strftime('%Y-%m-%d'))
if pages['main']:
von = SubElement(stueck_elem, 'von')
von.text = str(min(pages['main']))
bis = SubElement(stueck_elem, 'bis')
bis.text = str(max(pages['main']))
if pages['beilage']:
beilage_pages = sorted(pages['beilage'])
current_beilage = [beilage_pages[0]]
current_beilage_num = beilage_pages[0][0]
for beilage_num, page in beilage_pages[1:]:
if beilage_num == current_beilage_num and page == current_beilage[-1][1] + 1:
current_beilage.append((beilage_num, page))
else:
beilage_elem = SubElement(stueck_elem, 'beilage')
beilage_elem.set('nummer', str(current_beilage_num))
beilage_von = SubElement(beilage_elem, 'von')
beilage_von.text = str(min(page for _, page in current_beilage))
beilage_bis = SubElement(beilage_elem, 'bis')
beilage_bis.text = str(max(page for _, page in current_beilage))
current_beilage = [(beilage_num, page)]
current_beilage_num = beilage_num
# Add the last beilage
beilage_elem = SubElement(stueck_elem, 'beilage')
beilage_elem.set('nummer', str(current_beilage_num))
beilage_von = SubElement(beilage_elem, 'von')
beilage_von.text = str(min(page for _, page in current_beilage))
beilage_bis = SubElement(beilage_elem, 'bis')
beilage_bis.text = str(max(page for _, page in current_beilage))
return root
def pretty_print(elem):
rough_string = tostring(elem, 'utf-8')
reparsed = minidom.parseString(rough_string)
return reparsed.toprettyxml(indent=" ")
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: python script.py <directory_path>")
sys.exit(1)
directory = sys.argv[1]
files, year = get_files(directory)
xml_root = create_xml(files, year)
output_filename = f'{year}-stuecke.xml'
with open(output_filename, 'w', encoding='utf-8') as f:
f.write(pretty_print(xml_root))
print(f"XML file '{output_filename}' has been generated.")

View File

@@ -1,6 +1,7 @@
<?xml version="1.0"?>
<?xml version="1.0" ?>
<stuecke xmlns="https://www.koenigsberger-zeitungen.de" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stuecke xmlns="https://www.koenigsberger-zeitungen.de"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stueck>
<nummer>2</nummer>
<datum when="1764-01-09" />

View File

@@ -1,6 +1,7 @@
<?xml version="1.0"?>
<?xml version="1.0" ?>
<stuecke xmlns="https://www.koenigsberger-zeitungen.de" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stuecke xmlns="https://www.koenigsberger-zeitungen.de"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stueck>
<nummer>1</nummer>
<datum when="1765-01-04" />

View File

@@ -1,6 +1,7 @@
<?xml version="1.0"?>
<?xml version="1.0" ?>
<stuecke xmlns="https://www.koenigsberger-zeitungen.de" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stuecke xmlns="https://www.koenigsberger-zeitungen.de"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stueck>
<nummer>1</nummer>
<datum when="1766-01-03" />

View File

@@ -1,6 +1,7 @@
<?xml version="1.0"?>
<?xml version="1.0" ?>
<stuecke xmlns="https://www.koenigsberger-zeitungen.de" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stuecke xmlns="https://www.koenigsberger-zeitungen.de"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stueck>
<nummer>1</nummer>
<datum when="1767-01-02" />

View File

@@ -1,6 +1,7 @@
<?xml version="1.0"?>
<?xml version="1.0" ?>
<stuecke xmlns="https://www.koenigsberger-zeitungen.de" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stuecke xmlns="https://www.koenigsberger-zeitungen.de"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stueck>
<nummer>1</nummer>
<datum when="1768-01-01" />

View File

@@ -1,6 +1,7 @@
<?xml version="1.0"?>
<?xml version="1.0" ?>
<stuecke xmlns="https://www.koenigsberger-zeitungen.de" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stuecke xmlns="https://www.koenigsberger-zeitungen.de"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stueck>
<nummer>1</nummer>
<datum when="1771-01-04" />

View File

@@ -1,6 +1,7 @@
<?xml version="1.0"?>
<?xml version="1.0" ?>
<stuecke xmlns="https://www.koenigsberger-zeitungen.de" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stuecke xmlns="https://www.koenigsberger-zeitungen.de"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="https://www.koenigsberger-zeitungen.de ../../XSD/KGPZ.xsd">
<stueck>
<nummer>1</nummer>
<datum when="1772-01-03" />

View File

@@ -22,31 +22,56 @@
<xsd:element name="datum" type="kgpz:date" minOccurs="0" maxOccurs="1">
<xsd:annotation>
<xsd:documentation>Das Datum des Stücks, wie auf dem Titel angegeben, falls bekannt.</xsd:documentation>
<xsd:documentation>Das Datum des Stücks, wie auf dem Titel
angegeben, falls bekannt.</xsd:documentation>
</xsd:annotation>
</xsd:element>
<xsd:element name="von" type="xsd:positiveInteger" minOccurs="0"
maxOccurs="1">
<xsd:annotation>
<xsd:documentation>Die erste Seitenzahl des Stücks, falls bekannt.</xsd:documentation>
<xsd:documentation>Die erste Seitenzahl des Stücks, falls
bekannt.</xsd:documentation>
</xsd:annotation>
</xsd:element>
<xsd:element name="bis" type="xsd:positiveInteger" minOccurs="0"
maxOccurs="1">
<xsd:annotation>
<xsd:documentation>Die letzte Seitenzahl des Stücks, falls bekannt.</xsd:documentation>
<xsd:documentation>Die letzte Seitenzahl des Stücks, falls
bekannt.</xsd:documentation>
</xsd:annotation>
</xsd:element>
<!-- Kann von Stücke abgeleitet werden -->
<xsd:element name="beilagen" type="xsd:nonNegativeInteger" default="0"
minOccurs="0" maxOccurs="1">
<xsd:element name="beilage" minOccurs="0" maxOccurs="unbounded">
<xsd:annotation>
<xsd:documentation> Optional: Die Anzahl der Beilagen des
Stücks. </xsd:documentation>
</xsd:annotation>
<xsd:complexType>
<xsd:sequence>
<xsd:element name="von" type="xsd:positiveInteger"
minOccurs="0"
maxOccurs="1">
<xsd:annotation>
<xsd:documentation>Die erste Seitenzahl der Beilage,
falls bekannt.</xsd:documentation>
</xsd:annotation>
</xsd:element>
<xsd:element name="bis" type="xsd:positiveInteger"
minOccurs="0"
maxOccurs="1">
<xsd:annotation>
<xsd:documentation>Die letzte Seitenzahl der
Beilage, falls bekannt.</xsd:documentation>
</xsd:annotation>
</xsd:element>
</xsd:sequence>
<xsd:attribute name="nummer" type="xsd:positiveInteger"
use="required"></xsd:attribute>
</xsd:complexType>
</xsd:element>
<!-- Vielleicht nötig -->