All output is validated against the official XSDs, but no validation of profile levels
(basic, comfort, extended) is performed.
+The profile level is detected automatically based on the XML data and added to the PDF metadata.
+
Usage
-----
# Note that the existing PDF should be compliant to PDF/A-3!
# You can validate this here: https://www.pdf-online.com/osa/validate.aspx
with open("input.pdf", "rb") as original_file:
- new_pdf_bytes = attach_xml(original_file.read(), xml, 'EXTENDED')
+ new_pdf_bytes = attach_xml(original_file.read(), xml)
with open("output.pdf", "wb") as f:
f.write(new_pdf_bytes)
git clone https://github.com/ZUGFeRD/mustangproject.git
cd mustangproject
- git checkout core-2.5.1
+ git checkout core-2.9.0
./mvnw clean package
- java -jar Mustang-CLI/target/Mustang-CLI-2.5.1-SNAPSHOT.jar --action validate --source invoice.pdf
+ java -jar Mustang-CLI/target/Mustang-CLI-2.7.4-SNAPSHOT.jar --action validate --source invoice.pdf
Credits and License
-version = "2.2.2"
+version = "2.3.0"
class BaseElementMeta(type):
@classmethod
def __prepare__(self, name, bases):
+ del name, bases
return collections.OrderedDict()
def __new__(mcls, name, bases, attrs):
def to_etree(self):
node = self._etree_node()
- for k, v in self._data.items():
+ for _, v in self._data.items():
if v is not None:
v.append_to(node)
return node
self._text = root.text
try:
self._scheme_id = root.attrib["schemeID"]
- except:
+ except Exception:
root.attrib["schemeID"] = ""
self._scheme_id = root.attrib["schemeID"]
self._set_on_input = True
def from_etree(self, root):
try:
self._value = datetime.strptime(root.text, "%Y-%m-%dT%H:%M:%S").date()
- except:
+ except Exception:
self._value = ""
self._set_on_input = True
return self
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-import datetime
import logging
-import os
+from datetime import datetime, timezone
from io import BytesIO
from lxml import etree
from pypdf import PdfReader, PdfWriter
create_string_object,
)
+from drafthorse.xmp_schema import XMP_SCHEMA
+
+logging.basicConfig()
logger = logging.getLogger("drafthorse")
+logger.setLevel(logging.INFO)
-def attach_xml(original_pdf, xml_data, level="BASIC"):
+def attach_xml(original_pdf, xml_data, level=None, metadata=None, lang=None):
+ """
+ Create the ZUGFeRD invoice by attaching
+ the input XML and proper metadata
+ :param original_pdf: Input PDF
+ :param xml_data: Input XML
+ :param level: optional Factur-X profile level
+ one of ``{'MINIMUM', 'BASIC WL', 'BASIC', 'EN 16931', 'EXTENDED', 'XRECHNUNG'}``.
+ If omitted, autodetection is performed
+ :type level: string
+ :param metadata: optional dict with user defined PDF metadata
+ for fields "author", "keywords", "title" and "subject". If metadata is None (default value),
+ this lib will generate some metadata by extracting relevant info from the Factur-X/Order-X XML.
+ Here is an example for the metadata argument:
+ ```
+ pdf_metadata = {
+ 'author': 'MyCompany',
+ 'keywords': 'Factur-X, Invoice',
+ 'title': 'MyCompany: Invoice I1242',
+ 'subject':
+ 'Factur-X invoice I1242 dated 2017-08-17 issued by MyCompany',
+ }
+ ```
+ :type metadata: dict
+ :param lang: Language identifier in RFC 3066 format to specify the
+ natural language of the PDF document. Used by PDF readers for blind people.
+ Example: en-US or fr-FR
+ :type lang: string
+ :return: Output PDF containing the metadata and XML
+ """
if not isinstance(original_pdf, bytes):
raise TypeError("Please supply original PDF as bytes.")
if not isinstance(xml_data, bytes):
output._ID = original_pdf_id
# else : generate some ?
- _facturx_update_metadata_add_attachment(
- output, xml_data, {}, level, output_intents=_get_original_output_intents(reader)
+ # Extract metadata from XML
+ pdf_metadata, profile = _extract_xml_info(xml_data, level, metadata)
+
+ # Extract output intents from input PDF
+ output_intents = _get_original_output_intents(reader)
+
+ _update_metadata_add_attachment(
+ output, xml_data, pdf_metadata, profile, output_intents, lang
)
outbuffer = BytesIO()
def _get_original_output_intents(original_pdf):
+ """
+ Get output intents from input PDF
+ :param original_pdf: Input PDF
+ :return: Output PDF metadata information
+ """
output_intents = []
try:
pdf_root = original_pdf.trailer["/Root"]
def _prepare_pdf_metadata_txt(pdf_metadata):
- pdf_date = datetime.datetime.utcnow().strftime("D:%Y%m%d%H%M%SZ")
- info_dict = {
+ """
+ Create PDF info for the Document Properties section
+ :param pdf_metadata: Metadata
+ :return: PDF info
+ """
+ pdf_date = datetime.now(tz=timezone.utc).strftime("D:%Y%m%d%H%M%SZ")
+ return {
"/Author": pdf_metadata.get("author", ""),
"/CreationDate": pdf_date,
"/Creator": "python-drafthorse",
"/Subject": pdf_metadata.get("subject", ""),
"/Title": pdf_metadata.get("title", ""),
}
- return info_dict
-def _prepare_pdf_metadata_xml(level, pdf_metadata):
- nsmap_x = {"x": "adobe:ns:meta/"}
- nsmap_rdf = {"rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#"}
- nsmap_dc = {"dc": "http://purl.org/dc/elements/1.1/"}
- nsmap_pdf = {"pdf": "http://ns.adobe.com/pdf/1.3/"}
- nsmap_xmp = {"xmp": "http://ns.adobe.com/xap/1.0/"}
- nsmap_pdfaid = {"pdfaid": "http://www.aiim.org/pdfa/ns/id/"}
- nsmap_zf = {"zf": "urn:factur-x:pdfa:CrossIndustryDocument:invoice:1p0#"}
- ns_x = "{%s}" % nsmap_x["x"]
- ns_dc = "{%s}" % nsmap_dc["dc"]
- ns_rdf = "{%s}" % nsmap_rdf["rdf"]
- ns_pdf = "{%s}" % nsmap_pdf["pdf"]
- ns_xmp = "{%s}" % nsmap_xmp["xmp"]
- ns_pdfaid = "{%s}" % nsmap_pdfaid["pdfaid"]
- ns_zf = "{%s}" % nsmap_zf["zf"]
- ns_xml = "{http://www.w3.org/XML/1998/namespace}"
-
- root = etree.Element(ns_x + "xmpmeta", nsmap=nsmap_x)
- rdf = etree.SubElement(root, ns_rdf + "RDF", nsmap=nsmap_rdf)
- desc_pdfaid = etree.SubElement(rdf, ns_rdf + "Description", nsmap=nsmap_pdfaid)
- desc_pdfaid.set(ns_rdf + "about", "")
- etree.SubElement(desc_pdfaid, ns_pdfaid + "part").text = "3"
- etree.SubElement(desc_pdfaid, ns_pdfaid + "conformance").text = "B"
- desc_dc = etree.SubElement(rdf, ns_rdf + "Description", nsmap=nsmap_dc)
- desc_dc.set(ns_rdf + "about", "")
- dc_title = etree.SubElement(desc_dc, ns_dc + "title")
- dc_title_alt = etree.SubElement(dc_title, ns_rdf + "Alt")
- dc_title_alt_li = etree.SubElement(dc_title_alt, ns_rdf + "li")
- dc_title_alt_li.text = pdf_metadata.get("title", "")
- dc_title_alt_li.set(ns_xml + "lang", "x-default")
- dc_creator = etree.SubElement(desc_dc, ns_dc + "creator")
- dc_creator_seq = etree.SubElement(dc_creator, ns_rdf + "Seq")
- etree.SubElement(dc_creator_seq, ns_rdf + "li").text = pdf_metadata.get(
- "author", ""
+def _prepare_xmp_metadata(profile, pdf_metadata):
+ """
+ Prepare pdf metadata using the FACTUR-X XMP extension schema
+ :param profile: Invoice profile
+ :param pdf_metadata: PDF metadata
+ :return: metadata XML
+ """
+ xml_str = XMP_SCHEMA.format(
+ title=pdf_metadata.get("title", ""),
+ author=pdf_metadata.get("author", ""),
+ subject=pdf_metadata.get("subject", ""),
+ producer="pypdf",
+ creator_tool="python-drafthorse",
+ timestamp=datetime.now(tz=timezone.utc).strftime("%Y-%m-%dT%H:%M:%S+00:00"),
+ urn="urn:factur-x:pdfa:CrossIndustryDocument:invoice:1p0#",
+ documenttype="INVOICE",
+ xml_filename="factur-x.xml",
+ version="1.0",
+ xmp_level=profile,
)
- dc_desc = etree.SubElement(desc_dc, ns_dc + "description")
- dc_desc_alt = etree.SubElement(dc_desc, ns_rdf + "Alt")
- dc_desc_alt_li = etree.SubElement(dc_desc_alt, ns_rdf + "li")
- dc_desc_alt_li.text = pdf_metadata.get("subject", "")
- dc_desc_alt_li.set(ns_xml + "lang", "x-default")
- desc_adobe = etree.SubElement(rdf, ns_rdf + "Description", nsmap=nsmap_pdf)
- desc_adobe.set(ns_rdf + "about", "")
- producer = etree.SubElement(desc_adobe, ns_pdf + "Producer")
- producer.text = "pypdf"
- desc_xmp = etree.SubElement(rdf, ns_rdf + "Description", nsmap=nsmap_xmp)
- desc_xmp.set(ns_rdf + "about", "")
- creator = etree.SubElement(desc_xmp, ns_xmp + "CreatorTool")
- creator.text = "python-drafthorse"
- xmp_date = datetime.datetime.utcnow().replace(microsecond=0).isoformat() + "+00:00"
- etree.SubElement(desc_xmp, ns_xmp + "CreateDate").text = xmp_date
- etree.SubElement(desc_xmp, ns_xmp + "ModifyDate").text = xmp_date
+ return xml_str.encode("utf-8")
- # Now is the ZUGFeRD description tag
- zugferd_desc = etree.SubElement(rdf, ns_rdf + "Description", nsmap=nsmap_zf)
- zugferd_desc.set(ns_rdf + "about", "")
- fx_doc_type = etree.SubElement(zugferd_desc, ns_zf + "DocumentType", nsmap=nsmap_zf)
- fx_doc_type.text = "INVOICE"
- fx_doc_filename = etree.SubElement(
- zugferd_desc, ns_zf + "DocumentFileName", nsmap=nsmap_zf
- )
- fx_doc_filename.text = "factur-x.xml"
- fx_doc_version = etree.SubElement(zugferd_desc, ns_zf + "Version", nsmap=nsmap_zf)
- fx_doc_version.text = "1.0"
- fx_conformance_level = etree.SubElement(
- zugferd_desc, ns_zf + "ConformanceLevel", nsmap=nsmap_zf
- )
- fx_conformance_level.text = level
- xmp_file = os.path.join(
- os.path.dirname(__file__),
- "schema",
- "ZUGFeRD2p2_extension_schema.xmp",
- )
- # Reason for defining a parser below:
- # http://lxml.de/FAQ.html#why-doesn-t-the-pretty-print-option-reformat-my-xml-output
- parser = etree.XMLParser(remove_blank_text=True)
- facturx_ext_schema_root = etree.parse(open(xmp_file), parser)
- # The Factur-X extension schema must be embedded into each PDF document
- facturx_ext_schema_desc_xpath = facturx_ext_schema_root.xpath(
- "//rdf:Description", namespaces=nsmap_rdf
- )
- rdf.append(facturx_ext_schema_desc_xpath[1])
-
- # TODO: should be UTF-16be ??
- xml_str = etree.tostring(
- root, pretty_print=True, encoding="UTF-8", xml_declaration=False
- )
- head = '<?xpacket begin="\ufeff" id="W5M0MpCehiHzreSzNTczkc9d"?>'.encode("utf-8")
- tail = '<?xpacket end="w"?>'.encode("utf-8")
- xml_final_str = head + xml_str + tail
- return xml_final_str
-
-
-def _facturx_update_metadata_add_attachment(
- pdf_filestream, facturx_xml_str, pdf_metadata, facturx_level, output_intents
+def _update_metadata_add_attachment(
+ pdf_filestream,
+ facturx_xml_str,
+ pdf_metadata,
+ facturx_level,
+ output_intents,
+ lang=None,
):
+ """
+ Update PDF metadata and attach XML file
+ :param pdf_filestream: PDF data
+ :param facturx_xml_str: XML data
+ :param pdf_metadata: PDF metadata
+ :param facturx_level: Invoice profile
+ :param output_intents: Output intents from input PDF
+ :param lang: Language identifier in RFC 3066 format
+ """
+ # Disable encoding
# md5sum = hashlib.md5(facturx_xml_str).hexdigest()
# md5sum_obj = create_string_object(md5sum)
- pdf_date = datetime.datetime.utcnow().strftime("D:%Y%m%d%H%M%SZ")
+ pdf_date = datetime.now(tz=timezone.utc).strftime("D:%Y%m%d%H%M%SZ")
params_dict = DictionaryObject(
{
# NameObject('/CheckSum'): md5sum_obj,
}
)
file_entry = DecodedStreamObject()
- file_entry.set_data(facturx_xml_str) # here we integrate the file itself
+ file_entry.set_data(facturx_xml_str)
file_entry.update(
{
NameObject("/Type"): NameObject("/EmbeddedFile"),
"/Data" if facturx_level in ("BASIC-WL", "MINIMUM") else "/Alternative"
),
NameObject("/Desc"): create_string_object(
- "Invoice metadata conforming to ZUGFeRD standard (http://www.ferd-net.de/front_content.php?idcat=231&lang=4)"
+ "Invoice metadata conforming to ZUGFeRD standard (http://www.ferd-net.de/)"
),
NameObject("/Type"): NameObject("/Filespec"),
NameObject("/F"): fname_obj,
)
filespec_obj = pdf_filestream._add_object(filespec_dict)
name_arrayobj_cdict = {fname_obj: filespec_obj}
- name_arrayobj_content_sort = list(
- sorted(name_arrayobj_cdict.items(), key=lambda x: x[0])
- )
+ name_arrayobj_content_sort = sorted(name_arrayobj_cdict.items(), key=lambda x: x[0])
name_arrayobj_content_final = []
af_list = []
for fname_obj, filespec_obj in name_arrayobj_content_sort:
output_intent_obj = pdf_filestream._add_object(output_intent_dict)
res_output_intents.append(output_intent_obj)
# Update the root
- metadata_xml_str = _prepare_pdf_metadata_xml(facturx_level, pdf_metadata)
+ metadata_xml_str = _prepare_xmp_metadata(facturx_level, pdf_metadata)
metadata_file_entry = DecodedStreamObject()
metadata_file_entry.set_data(metadata_xml_str)
metadata_file_entry.update(
pdf_filestream._root_object.update(
{NameObject("/OutputIntents"): ArrayObject(res_output_intents)}
)
+ if lang:
+ pdf_filestream._root_object.update(
+ {
+ NameObject("/Lang"): create_string_object(lang.replace("_", "-")),
+ }
+ )
metadata_txt_dict = _prepare_pdf_metadata_txt(pdf_metadata)
pdf_filestream.add_metadata(metadata_txt_dict)
+
+
+def _extract_xml_info(xml_data, level=None, metadata=None):
+ """
+ Extract metadata and profile from XML further added to the PDF
+ :param xml_data: XML data
+ :param level: optional Factur-X profile level
+ one of {MINIMUM, BASIC WL, BASIC, EN 16931, EXTENDED, XRECHNUNG}
+ if omitted autodetection is performed
+ :param metadata: optional dict with user defined pdf_metadata
+ for fields "author", "keywords", "title" and "subject"
+ :return: Metadata and profile
+ """
+
+ xml_etree = etree.fromstring(xml_data)
+ namespaces = xml_etree.nsmap
+
+ # get metadata
+ number_xpath = xml_etree.xpath(
+ "//rsm:ExchangedDocument/ram:ID", namespaces=namespaces
+ )
+ number = number_xpath[0].text
+ seller_xpath = xml_etree.xpath(
+ "//ram:ApplicableHeaderTradeAgreement/ram:SellerTradeParty/ram:Name",
+ namespaces=namespaces,
+ )
+ seller = seller_xpath[0].text
+
+ if metadata is None:
+ metadata = {}
+ pdf_metadata = {
+ "author": metadata.get("author", seller),
+ "keywords": metadata.get("keywords", "Factur-X"),
+ "title": metadata.get("title", number),
+ "subject": metadata.get("subject", number),
+ }
+
+ # get profile
+ doc_id_xpath = xml_etree.xpath(
+ "//rsm:ExchangedDocumentContext"
+ "/ram:GuidelineSpecifiedDocumentContextParameter"
+ "/ram:ID",
+ namespaces=namespaces,
+ )
+ doc_id = doc_id_xpath[0].text
+
+ if level is None:
+ # autodetection of Factur-X profile
+ profile = doc_id.split(":")[-1]
+ if doc_id.split(":")[-1] in ["basic", "extended"]:
+ profile = doc_id.split(":")[-1]
+ elif doc_id.split(":")[-1].startswith("xrechnung"):
+ profile = "xrechnung"
+ elif doc_id.split(":")[-2] == "en16931":
+ profile = doc_id.split(":")[-2]
+ profile = profile[:2] + " " + profile[2:]
+ else:
+ raise Exception("Invalid XML profile!")
+ else:
+ profile = level
+
+ profile = profile.upper()
+ logger.info("Factur-X profile detected from XML: %s", profile)
+
+ return pdf_metadata, profile
+++ /dev/null
-<!--
-(c) PDFlib GmbH 2019
-
-Sample Factur-X XMP with the required PDF/A extension schema description
-for the XMP properties of the Factur-X schema and the actual Factur-X properties.
-
-Schema name: Factur-X PDFA Extension Schema
-Preferred schema namespace prefix: fx
-Schema namespace URI: urn:factur-x:pdfa:CrossIndustryDocument:invoice:1p0#
-
-Based on the Factur-X specification published at http://fnfe-mpe.org/factur-x/factur-x_en/
--->
-
-<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
-
- <!-- The actual Factur-X properties; adjust if required -->
- <rdf:Description rdf:about="" xmlns:fx="urn:factur-x:pdfa:CrossIndustryDocument:invoice:1p0#">
- <fx:ConformanceLevel>BASIC</fx:ConformanceLevel>
- <fx:DocumentFileName>factur-x.xml</fx:DocumentFileName>
- <fx:DocumentType>INVOICE</fx:DocumentType>
- <fx:Version>1.0</fx:Version>
- </rdf:Description>
-
- <!-- PDF/A extension schema description for the Factur-X schema. -->
- <rdf:Description rdf:about=""
- xmlns:pdfaExtension="http://www.aiim.org/pdfa/ns/extension/"
- xmlns:pdfaSchema="http://www.aiim.org/pdfa/ns/schema#"
- xmlns:pdfaProperty="http://www.aiim.org/pdfa/ns/property#">
-
- <pdfaExtension:schemas>
- <rdf:Bag>
- <rdf:li rdf:parseType="Resource">
- <pdfaSchema:schema>Factur-X PDF/A Extension Schema</pdfaSchema:schema>
- <pdfaSchema:namespaceURI>urn:factur-x:pdfa:CrossIndustryDocument:invoice:1p0#</pdfaSchema:namespaceURI>
- <pdfaSchema:prefix>fx</pdfaSchema:prefix>
- <pdfaSchema:property>
- <rdf:Seq>
- <rdf:li rdf:parseType="Resource">
- <pdfaProperty:name>DocumentFileName</pdfaProperty:name>
- <pdfaProperty:valueType>Text</pdfaProperty:valueType>
- <pdfaProperty:category>external</pdfaProperty:category>
- <pdfaProperty:description>name of the embedded XML invoice file</pdfaProperty:description>
- </rdf:li>
- <rdf:li rdf:parseType="Resource">
- <pdfaProperty:name>DocumentType</pdfaProperty:name>
- <pdfaProperty:valueType>Text</pdfaProperty:valueType>
- <pdfaProperty:category>external</pdfaProperty:category>
- <pdfaProperty:description>INVOICE</pdfaProperty:description>
- </rdf:li>
- <rdf:li rdf:parseType="Resource">
- <pdfaProperty:name>Version</pdfaProperty:name>
- <pdfaProperty:valueType>Text</pdfaProperty:valueType>
- <pdfaProperty:category>external</pdfaProperty:category>
- <pdfaProperty:description>The actual version of the Factur-X XML schema</pdfaProperty:description>
- </rdf:li>
- <rdf:li rdf:parseType="Resource">
- <pdfaProperty:name>ConformanceLevel</pdfaProperty:name>
- <pdfaProperty:valueType>Text</pdfaProperty:valueType>
- <pdfaProperty:category>external</pdfaProperty:category>
- <pdfaProperty:description>The conformance level of the embedded Factur-X data</pdfaProperty:description>
- </rdf:li>
- </rdf:Seq>
- </pdfaSchema:property>
- </rdf:li>
- </rdf:Bag>
- </pdfaExtension:schemas>
- </rdf:Description>
-</rdf:RDF>
\ No newline at end of file
--- /dev/null
+"""
+FACTUR-X XMP with the required PDF/A extension schema description
+"""
+
+XMP_SCHEMA = """
+<?xpacket begin="\ufeff" id="W5M0MpCehiHzreSzNTczkc9d"?>
+<x:xmpmeta xmlns:x="adobe:ns:meta/">
+ <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+ <rdf:Description xmlns:pdfaid="http://www.aiim.org/pdfa/ns/id/" rdf:about="">
+ <pdfaid:part>3</pdfaid:part>
+ <pdfaid:conformance>B</pdfaid:conformance>
+ </rdf:Description>
+ <rdf:Description xmlns:dc="http://purl.org/dc/elements/1.1/" rdf:about="">
+ <dc:title>
+ <rdf:Alt>
+ <rdf:li xml:lang="x-default">{title}</rdf:li>
+ </rdf:Alt>
+ </dc:title>
+ <dc:creator>
+ <rdf:Seq>
+ <rdf:li>{author}</rdf:li>
+ </rdf:Seq>
+ </dc:creator>
+ <dc:description>
+ <rdf:Alt>
+ <rdf:li xml:lang="x-default">{subject}</rdf:li>
+ </rdf:Alt>
+ </dc:description>
+ </rdf:Description>
+ <rdf:Description xmlns:pdf="http://ns.adobe.com/pdf/1.3/" rdf:about="">
+ <pdf:Producer>{producer}</pdf:Producer>
+ </rdf:Description>
+ <rdf:Description xmlns:xmp="http://ns.adobe.com/xap/1.0/" rdf:about="">
+ <xmp:CreatorTool>{creator_tool}</xmp:CreatorTool>
+ <xmp:CreateDate>{timestamp}</xmp:CreateDate>
+ <xmp:ModifyDate>{timestamp}</xmp:ModifyDate>
+ </rdf:Description>
+ <rdf:Description xmlns:pdfaExtension="http://www.aiim.org/pdfa/ns/extension/" xmlns:pdfaSchema="http://www.aiim.org/pdfa/ns/schema#" xmlns:pdfaProperty="http://www.aiim.org/pdfa/ns/property#" rdf:about="">
+ <pdfaExtension:schemas>
+ <rdf:Bag>
+ <rdf:li rdf:parseType="Resource">
+ <pdfaSchema:schema>Factur-X PDFA Extension Schema</pdfaSchema:schema>
+ <pdfaSchema:namespaceURI>{urn}</pdfaSchema:namespaceURI>
+ <pdfaSchema:prefix>fx</pdfaSchema:prefix>
+ <pdfaSchema:property>
+ <rdf:Seq>
+ <rdf:li rdf:parseType="Resource">
+ <pdfaProperty:name>DocumentFileName</pdfaProperty:name>
+ <pdfaProperty:valueType>Text</pdfaProperty:valueType>
+ <pdfaProperty:category>external</pdfaProperty:category>
+ <pdfaProperty:description>The name of the embedded XML document</pdfaProperty:description>
+ </rdf:li>
+ <rdf:li rdf:parseType="Resource">
+ <pdfaProperty:name>DocumentType</pdfaProperty:name>
+ <pdfaProperty:valueType>Text</pdfaProperty:valueType>
+ <pdfaProperty:category>external</pdfaProperty:category>
+ <pdfaProperty:description>The type of the hybrid document in capital letters, e.g. INVOICE or ORDER</pdfaProperty:description>
+ </rdf:li>
+ <rdf:li rdf:parseType="Resource">
+ <pdfaProperty:name>Version</pdfaProperty:name>
+ <pdfaProperty:valueType>Text</pdfaProperty:valueType>
+ <pdfaProperty:category>external</pdfaProperty:category>
+ <pdfaProperty:description>The actual version of the standard applying to the embedded XML document</pdfaProperty:description>
+ </rdf:li>
+ <rdf:li rdf:parseType="Resource">
+ <pdfaProperty:name>ConformanceLevel</pdfaProperty:name>
+ <pdfaProperty:valueType>Text</pdfaProperty:valueType>
+ <pdfaProperty:category>external</pdfaProperty:category>
+ <pdfaProperty:description>The conformance level of the embedded XML document</pdfaProperty:description>
+ </rdf:li>
+ </rdf:Seq>
+ </pdfaSchema:property>
+ </rdf:li>
+ </rdf:Bag>
+ </pdfaExtension:schemas>
+ </rdf:Description>
+ <rdf:Description xmlns:fx="{urn}" rdf:about="">
+ <fx:DocumentFileName>{xml_filename}</fx:DocumentFileName>
+ <fx:DocumentType>{documenttype}</fx:DocumentType>
+ <fx:Version>{version}</fx:Version>
+ <fx:ConformanceLevel>{xmp_level}</fx:ConformanceLevel>
+ </rdf:Description>
+ </rdf:RDF>
+</x:xmpmeta>
+<?xpacket end="w"?>
+"""
--- /dev/null
+import os
+import pytest
+from datetime import date, datetime, timezone
+from decimal import Decimal
+
+from drafthorse.models.accounting import ApplicableTradeTax
+from drafthorse.models.document import Document
+from drafthorse.models.note import IncludedNote
+from drafthorse.models.tradelines import LineItem
+
+
+@pytest.fixture
+def invoice_document(request):
+ doc = Document()
+ doc.context.guideline_parameter.id = (
+ "urn:cen.eu:en16931:2017#conformant#urn:factur-x.eu:1p0:extended"
+ )
+ doc.header.id = "RE1337"
+ doc.header.type_code = request.param
+ doc.header.name = "RECHNUNG"
+ doc.header.issue_date_time = date.today()
+ doc.header.languages.add("de")
+
+ note = IncludedNote()
+ note.content.add("Test Node 1")
+ doc.header.notes.add(note)
+
+ doc.trade.agreement.seller.name = "Lieferant GmbH"
+ doc.trade.settlement.payee.name = "Kunde GmbH"
+
+ doc.trade.agreement.buyer.name = "Kunde GmbH"
+ doc.trade.settlement.invoicee.name = "Kunde GmbH"
+
+ doc.trade.settlement.currency_code = "EUR"
+ doc.trade.settlement.payment_means.type_code = "ZZZ"
+
+ doc.trade.agreement.seller.address.country_id = "DE"
+ doc.trade.agreement.seller.address.country_subdivision = "Bayern"
+
+ doc.trade.agreement.seller_order.issue_date_time = datetime.now(timezone.utc)
+ doc.trade.agreement.buyer_order.issue_date_time = datetime.now(timezone.utc)
+ doc.trade.settlement.advance_payment.received_date = datetime.now(timezone.utc)
+ doc.trade.agreement.customer_order.issue_date_time = datetime.now(timezone.utc)
+
+ li = LineItem()
+ li.document.line_id = "1"
+ li.product.name = "Rainbow"
+ li.agreement.gross.amount = Decimal("999.00")
+ li.agreement.gross.basis_quantity = (Decimal("1.0000"), "C62") # C62 == pieces
+ li.agreement.net.amount = Decimal("999.00")
+ li.agreement.net.basis_quantity = (Decimal("999.00"), "EUR")
+ li.delivery.billed_quantity = (Decimal("1.0000"), "C62") # C62 == pieces
+ li.settlement.trade_tax.type_code = "VAT"
+ li.settlement.trade_tax.category_code = "E"
+ li.settlement.trade_tax.rate_applicable_percent = Decimal("0.00")
+ li.settlement.monetary_summation.total_amount = Decimal("999.00")
+ doc.trade.items.add(li)
+
+ trade_tax = ApplicableTradeTax()
+ trade_tax.calculated_amount = Decimal("0.00")
+ trade_tax.basis_amount = Decimal("999.00")
+ trade_tax.type_code = "VAT"
+ trade_tax.category_code = "E"
+ trade_tax.rate_applicable_percent = Decimal("0.00")
+ doc.trade.settlement.trade_tax.add(trade_tax)
+
+ doc.trade.settlement.monetary_summation.line_total = Decimal("999.00")
+ doc.trade.settlement.monetary_summation.charge_total = Decimal("0.00")
+ doc.trade.settlement.monetary_summation.allowance_total = Decimal("0.00")
+ doc.trade.settlement.monetary_summation.tax_basis_total = Decimal("999.00")
+ doc.trade.settlement.monetary_summation.tax_total = Decimal("0.00")
+ doc.trade.settlement.monetary_summation.grand_total = Decimal("999.00")
+ doc.trade.settlement.monetary_summation.due_amount = Decimal("999.00")
+
+ return doc
+
+
+@pytest.fixture
+def empty_pdf16_bytes():
+ pdf_file = open(
+ os.path.join(os.path.dirname(__file__), "samples", "empty_pdf16.pdf"), "rb"
+ ).read()
+
+ return pdf_file
+
+
+@pytest.fixture
+def invoice_pdf17_bytes():
+ pdf_file = open(
+ os.path.join(os.path.dirname(__file__), "samples", "invoice_pdf17.pdf"),
+ "rb",
+ ).read()
+
+ return pdf_file
-import os
-from datetime import date, datetime, timezone
-from decimal import Decimal
-
-from drafthorse.models.accounting import ApplicableTradeTax
-from drafthorse.models.document import Document
-from drafthorse.models.note import IncludedNote
-from drafthorse.models.tradelines import LineItem
+import pytest
+
from drafthorse.pdf import attach_xml
-def test_readme_construction_example():
- doc = Document()
+@pytest.mark.parametrize("invoice_document", ["380"], indirect=True)
+def test_readme_construction_example_pdf16(invoice_document, empty_pdf16_bytes):
+ """
+ Test using a PDF 1.6 version
+ """
+ xml = invoice_document.serialize(schema="FACTUR-X_EXTENDED")
+ output_pdf = attach_xml(empty_pdf16_bytes, xml)
+
+ assert output_pdf
+
+
+@pytest.mark.parametrize("invoice_document", ["380"], indirect=True)
+def test_readme_construction_example_pdf17(invoice_document, invoice_pdf17_bytes):
+ """
+ Test using a PDF 1.7 version in order to cover the output intents handling
+ """
+ xml = invoice_document.serialize(schema="FACTUR-X_EXTENDED")
+ output_pdf = attach_xml(invoice_pdf17_bytes, xml)
+
+ assert output_pdf
+
+
+@pytest.mark.parametrize("invoice_document", ["380"], indirect=True)
+def test_readme_construction_example_pdf17_en16931(
+ invoice_document, invoice_pdf17_bytes
+):
+ """
+ Test using a PDF 1.7 version in order to cover the output intents handling
+ """
+ doc = invoice_document
+ doc.context.guideline_parameter.id = "urn:cen.eu:en16931:2017"
+ xml = doc.serialize(schema="FACTUR-X_EXTENDED")
+ output_pdf = attach_xml(invoice_pdf17_bytes, xml)
+
+ assert output_pdf
+
+
+@pytest.mark.parametrize("invoice_document", ["380"], indirect=True)
+def test_readme_construction_example_pdf17_xrechnung2(
+ invoice_document, invoice_pdf17_bytes
+):
+ """
+ Test using a PDF 1.7 version in order to cover the output intents handling
+ """
+ doc = invoice_document
doc.context.guideline_parameter.id = (
- "urn:cen.eu:en16931:2017#conformant#urn:factur-x.eu:1p0:extended"
+ "urn:cen.eu:en16931:2017#compliant#urn:xoev-de:kosit:standard:xrechnung_2.3"
)
- doc.header.id = "RE1337"
- doc.header.type_code = "380"
- doc.header.name = "RECHNUNG"
- doc.header.issue_date_time = date.today()
- doc.header.languages.add("de")
-
- note = IncludedNote()
- note.content.add("Test Node 1")
- doc.header.notes.add(note)
-
- doc.trade.agreement.seller.name = "Lieferant GmbH"
- doc.trade.settlement.payee.name = "Kunde GmbH"
-
- doc.trade.agreement.buyer.name = "Kunde GmbH"
- doc.trade.settlement.invoicee.name = "Kunde GmbH"
-
- doc.trade.settlement.currency_code = "EUR"
- doc.trade.settlement.payment_means.type_code = "ZZZ"
-
- doc.trade.agreement.seller.address.country_id = "DE"
- doc.trade.agreement.seller.address.country_subdivision = "Bayern"
-
- doc.trade.agreement.seller_order.issue_date_time = datetime.now(timezone.utc)
- doc.trade.agreement.buyer_order.issue_date_time = datetime.now(timezone.utc)
- doc.trade.settlement.advance_payment.received_date = datetime.now(timezone.utc)
- doc.trade.agreement.customer_order.issue_date_time = datetime.now(timezone.utc)
-
- li = LineItem()
- li.document.line_id = "1"
- li.product.name = "Rainbow"
- li.agreement.gross.amount = Decimal("999.00")
- li.agreement.gross.basis_quantity = (Decimal("1.0000"), "C62") # C62 == pieces
- li.agreement.net.amount = Decimal("999.00")
- li.agreement.net.basis_quantity = (Decimal("999.00"), "EUR")
- li.delivery.billed_quantity = (Decimal("1.0000"), "C62") # C62 == pieces
- li.settlement.trade_tax.type_code = "VAT"
- li.settlement.trade_tax.category_code = "E"
- li.settlement.trade_tax.rate_applicable_percent = Decimal("0.00")
- li.settlement.monetary_summation.total_amount = Decimal("999.00")
- doc.trade.items.add(li)
-
- trade_tax = ApplicableTradeTax()
- trade_tax.calculated_amount = Decimal("0.00")
- trade_tax.basis_amount = Decimal("999.00")
- trade_tax.type_code = "VAT"
- trade_tax.category_code = "AE"
- trade_tax.exemption_reason_code = "VATEX-EU-AE"
- trade_tax.rate_applicable_percent = Decimal("0.00")
- doc.trade.settlement.trade_tax.add(trade_tax)
-
- doc.trade.settlement.monetary_summation.line_total = Decimal("999.00")
- doc.trade.settlement.monetary_summation.charge_total = Decimal("0.00")
- doc.trade.settlement.monetary_summation.allowance_total = Decimal("0.00")
- doc.trade.settlement.monetary_summation.tax_basis_total = Decimal("999.00")
- doc.trade.settlement.monetary_summation.tax_total = Decimal("0.00")
- doc.trade.settlement.monetary_summation.grand_total = Decimal("999.00")
- doc.trade.settlement.monetary_summation.due_amount = Decimal("999.00")
+ xml = doc.serialize(schema="FACTUR-X_EXTENDED")
+ output_pdf = attach_xml(invoice_pdf17_bytes, xml)
+ assert output_pdf
+
+
+@pytest.mark.parametrize("invoice_document", ["380"], indirect=True)
+def test_readme_construction_example_pdf17_xrechnung3(
+ invoice_document, invoice_pdf17_bytes
+):
+ """
+ Test using a PDF 1.7 version in order to cover the output intents handling
+ """
+ doc = invoice_document
+ doc.context.guideline_parameter.id = (
+ "urn:cen.eu:en16931:2017#compliant#urn:xeinkauf.de:kosit:xrechnung_3.0"
+ )
+ xml = doc.serialize(schema="FACTUR-X_EXTENDED")
+ output_pdf = attach_xml(invoice_pdf17_bytes, xml)
+
+ assert output_pdf
+
+
+@pytest.mark.parametrize("invoice_document", ["380"], indirect=True)
+def test_invalid_invoice_XML_profile_exceptions(invoice_document, invoice_pdf17_bytes):
+ """
+ Test using a PDF 1.7 version in order to cover the output intents handling
+ """
+ doc = invoice_document
+ doc.context.guideline_parameter.id = (
+ "urn:cen.eu:en16932:2017#conformant#urn:factur-x.eu:1p0:wrong"
+ )
xml = doc.serialize(schema="FACTUR-X_EXTENDED")
- with open(
- os.path.join(os.path.dirname(__file__), "samples", "Empty.pdf"), "rb"
- ) as original_file:
- assert attach_xml(original_file.read(), xml, "EXTENDED")
+ # invalid pdf type
+ with pytest.raises(Exception) as exc_info:
+ attach_xml(invoice_pdf17_bytes, xml)
+
+ assert str(exc_info.value) == "Invalid XML profile!"
+
+
+@pytest.mark.parametrize("invoice_document", ["220"], indirect=True)
+def test_invalid_invoice_exceptions(invoice_document, invoice_pdf17_bytes):
+ """
+ Test invalid cases
+ """
+ xml = invoice_document.serialize(schema="FACTUR-X_EXTENDED")
+
+ # invalid pdf type
+ with pytest.raises(Exception) as exc_info:
+ attach_xml("invalid_pdf_type", xml)
+
+ assert str(exc_info.value) == "Please supply original PDF as bytes."
+
+ # invalid xml type
+ with pytest.raises(Exception) as exc_info:
+ attach_xml(invoice_pdf17_bytes, "invalid_xml_type")
+
+ assert str(exc_info.value) == "Please supply XML data as bytes."
projects / thirdparty / python-drafthorse.git / commitdiff
