[14.0][BCK][PORT] 898 from 16.0

base_ubl/models/ubl.py

@@ -14,12 +14,6 @@
 
 logger = logging.getLogger(__name__)
 
-try:
-    from PyPDF2 import PdfFileReader, PdfFileWriter
-    from PyPDF2.generic import NameObject
-except ImportError:
-    logger.debug("Cannot import PyPDF2")
-
 
 class BaseUbl(models.AbstractModel):
     _name = "base.ubl"
@@ -592,40 +586,33 @@ def _ubl_check_xml_schema(self, xml_string, document, version="2.1"):
             )
         return True
 
-    # TODO: move to pdf_helper
     @api.model
     def _ubl_add_xml_in_pdf_buffer(self, xml_string, xml_filename, buffer):
-        # Add attachment to PDF content.
-        reader = PdfFileReader(buffer)
-        writer = PdfFileWriter()
-        writer.appendPagesFromReader(reader)
-        writer.addAttachment(xml_filename, xml_string)
-        # show attachments when opening PDF
-        writer._root_object.update(
-            {NameObject("/PageMode"): NameObject("/UseAttachments")}
+        logger.warning(
+            "`_ubl_add_xml_in_pdf_buffer` deprecated: use `pdf.helper.pdf_embed_xml`"
         )
-        new_buffer = BytesIO()
-        writer.write(new_buffer)
+        pdf_content = buffer.getvalue()
+        new_content = self.env["pdf.helper"].pdf_embed_xml(
+            pdf_content, xml_filename, xml_string
+        )
+        new_buffer = BytesIO(new_content)
         return new_buffer
 
-    # TODO: move to pdf_helper
     @api.model
     def _embed_ubl_xml_in_pdf_content(self, xml_string, xml_filename, pdf_content):
         """Add the attachments to the PDF content.
         Use the pdf_content argument, which has the binary of the PDF
         -> it will return the new PDF binary with the embedded XML
         (used for qweb-pdf reports)
         """
+        logger.warning(
+            "`_embed_ubl_xml_in_pdf_content` deprecated: use `pdf.helper.pdf_embed_xml`"
+        )
         self.ensure_one()
         logger.debug("Starting to embed %s in PDF", xml_filename)
-
-        with BytesIO(pdf_content) as reader_buffer:
-            buffer = self._ubl_add_xml_in_pdf_buffer(
-                xml_string, xml_filename, reader_buffer
-            )
-        pdf_content = buffer.getvalue()
-        buffer.close()
-
+        pdf_content = self.env["pdf.helper"].pdf_embed_xml(
+            pdf_content, xml_filename, xml_string
+        )
         logger.info("%s file added to PDF content", xml_filename)
         return pdf_content
 
@@ -648,8 +635,8 @@ def embed_xml_in_pdf(
         if pdf_file:
             with open(pdf_file, "rb") as f:
                 pdf_content = f.read()
-        updated_pdf_content = self._embed_ubl_xml_in_pdf_content(
-            xml_string, xml_filename, pdf_content
+        updated_pdf_content = self.env["pdf.helper"].pdf_embed_xml(
+            pdf_content, xml_filename, xml_string
         )
         if pdf_file:
             with open(pdf_file, "wb") as f:

pdf_helper/models/helper.py

@@ -1,11 +1,13 @@
 # Copyright 2022 Camptocamp SA
 # @author: Simone Orsi <simahawk@gmail.com>
+# Copyright 2023 Jacques-Etienne Baudoux (BCIM) <je@bcim.be>
 # License LGPL-3.0 or later (http://www.gnu.org/licenses/lgpl).
-import logging
 
-from pypdf.errors import PdfReadError
+import io
+import logging
 
-from odoo import models
+from odoo import api, models
+from odoo.tools.pdf import NameObject, OdooPdfFileReader, OdooPdfFileWriter
 
 from ..utils import PDFParser
 
@@ -18,16 +20,31 @@ class PDFHelper(models.AbstractModel):
 
     _PDF_PARSER_KLASS = PDFParser
 
+    @api.model
     def pdf_get_xml_files(self, pdf_file):
+        """Extract XML attachments from pdf
+
+        :param pdf_file: binary PDF file content
+        :returns: a dict like {$filename: $parsed_xml_file_obj}.
+        """
         parser = self._PDF_PARSER_KLASS(pdf_file)
         try:
             return parser.get_xml_files()
-        except self._pdf_get_xml_files_swallable_exceptions() as err:
-            # TODO: can't we catch specific exceptions?
-            # This try/except block was added to reflect what done
-            # in base_business_document_import till now.
+        except parser.get_xml_files_swallable_exceptions() as err:
             _logger.error("PDF file parsing failed: %s", str(err))
             return {}
 
-    def _pdf_get_xml_files_swallable_exceptions(self):
-        return (KeyError, PdfReadError)
+    @api.model
+    def pdf_embed_xml(self, pdf_content, xml_filename, xml_string):
+        """Add an XML attachment in a pdf"""
+        with io.BytesIO(pdf_content) as reader_buffer, io.BytesIO() as new_pdf_stream:
+            reader = OdooPdfFileReader(reader_buffer, strict=False)
+            writer = OdooPdfFileWriter()
+            writer.cloneReaderDocumentRoot(reader)
+            writer.addAttachment(xml_filename, xml_string, subtype="text/xml")
+            # show attachments when opening PDF
+            writer._root_object.update(
+                {NameObject("/PageMode"): NameObject("/UseAttachments")}
+            )
+            writer.write(new_pdf_stream)
+            return new_pdf_stream.getvalue()

pdf_helper/readme/CONTRIBUTORS.rst

@@ -1,2 +1,3 @@
 * Simone Orsi <simone.orsi@camptocamp.com>
 * Alexis de Lattre <alexis.delattre@akretion.com>
+* Jacques-Etienne Baudoux (BCIM) <je@bcim.be>

pdf_helper/readme/USAGE.rst

@@ -2,6 +2,8 @@ Inside Odoo env::
 
     res = env["pdf.helper"].pdf_get_xml_files(pdf_filecontent)
 
+    new_pdf_filecontent = env["pdf.helper"].pdf_embed_xml(pdf_filecontent, filename, xml)
+
 Outside Odoo env::
 
     from odoo.addons.pdf_helper.utils import PDFParser

pdf_helper/tests/test_helper.py

@@ -28,14 +28,14 @@ def test_parse_xml(self):
 
 
 class TestPDFHelper(TransactionCase):
-    def test_parse_xml(self):
+    def test_get_xml(self):
         pdf_content = read_test_file("pdf_with_xml_test.pdf", mode="rb")
         res = self.env["pdf.helper"].pdf_get_xml_files(pdf_content)
         fname, xml_root = tuple(res.items())[0]
         self.assertEqual(fname, "factur-x.xml")
         self.assertTrue(isinstance(xml_root, etree._Element))
 
-    def test_parse_xml_fail(self):
+    def test_get_xml_fail(self):
         with self.assertLogs(
             "odoo.addons.pdf_helper.models.helper", level="ERROR"
         ) as log_catcher:
@@ -44,3 +44,15 @@ def test_parse_xml_fail(self):
                 "PDF file parsing failed: Cannot read an empty file",
                 log_catcher.output[0],
             )
+
+    def test_embed_xml(self):
+        pdf_content = read_test_file("pdf_with_xml_test.pdf", mode="rb")
+        filename = "test"
+        xml = b"<root>test</root>"
+        newpdf_content = self.env["pdf.helper"].pdf_embed_xml(
+            pdf_content, filename, xml
+        )
+        attachments = self.env["pdf.helper"].pdf_get_xml_files(newpdf_content)
+        self.assertTrue(filename in attachments)
+        etree_content = attachments[filename]
+        self.assertEqual(xml, etree.tostring(etree_content))

pdf_helper/utils.py

@@ -5,17 +5,19 @@
 # License LGPL-3.0 or later (http://www.gnu.org/licenses/lgpl).
 
 import logging
-import mimetypes
 from io import BytesIO
+from struct import error as StructError
 
 from lxml import etree
 
-_logger = logging.getLogger(__name__)
-
 try:
-    import pypdf
+    from PyPDF2.errors import PdfReadError
 except ImportError:
-    _logger.debug("Cannot import pypdf")
+    from PyPDF2.utils import PdfReadError
+
+from odoo.tools.pdf import OdooPdfFileReader
+
+_logger = logging.getLogger(__name__)
 
 
 class PDFParser:
@@ -35,25 +37,19 @@ def get_xml_files(self):
             _logger.debug("Valid XML files found in PDF: %s", list(res.keys()))
         return res
 
-    def _extract_xml_files(self, fd):
-        reader = pypdf.PdfReader(fd)
-        # attachment parsing via pypdf doesn't support /Kids
-        # cf my bug report https://github.com/py-pdf/pypdf/issues/2087
-        xmlfiles = {}
-        for filename, content_list in reader.attachments.items():
-            _logger.debug("Attachment %s found in PDF", filename)
-            mime_res = mimetypes.guess_type(filename)
-            if mime_res and mime_res[0] in ["application/xml", "text/xml"]:
+        with BytesIO(self.pdf_file) as buffer:
+            pdf_reader = OdooPdfFileReader(buffer, strict=False)
+
+            # Process embedded files.
+            for xml_name, content in pdf_reader.getAttachments():
                 try:
-                    _logger.debug("Trying to parse XML attachment %s", filename)
-                    xml_root = etree.fromstring(content_list[0])
-                    if len(xml_root) > 0:
-                        _logger.info("Valid XML file %s found in attachments", filename)
-                        xmlfiles[filename] = xml_root
-                    else:
-                        _logger.warning("XML file %s is empty", filename)
-                except Exception as err:
-                    _logger.warning(
-                        "Failed to parse XML file %s. Error: %s", filename, str(err)
-                    )
-        return xmlfiles
+                    res[xml_name] = etree.fromstring(content)
+                except Exception:
+                    _logger.debug("Non XML file found in PDF")
+            if res:
+                _logger.debug("Valid XML files found in PDF: %s", list(res.keys()))
+        return res
+
+    def get_xml_files_swallable_exceptions(self):
+        return (NotImplementedError, StructError, PdfReadError)
+