first commit

Dockerfile

@@ -0,0 +1,28 @@
+# Use an official Python runtime as a parent image
+FROM python:3.10-slim-buster
+
+# Set the working directory in the container to /app
+WORKDIR /app
+
+# Copy the current directory contents into the container at /app
+ADD . /app
+
+# Update and install system libraries
+RUN apt-get update && apt-get install -y \
+    ghostscript \
+    --no-install-recommends && \
+    rm -rf /var/lib/apt/lists/*
+
+
+# Install Poetry
+RUN pip install poetry
+
+# Install project dependencies
+RUN poetry config virtualenvs.create false \
+  && poetry install --no-interaction --no-ansi
+
+# Make port 80 available to the world outside this container
+EXPOSE 8000
+
+# Run app.py when the container launches
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

constant.py

@@ -0,0 +1,44 @@
+ps_content_template = '''% Define an ICC profile :
+/ICCProfile (/usr/share/ghostscript/{gs_version}/iccprofiles/default_rgb.icc) def
+
+% Define an OutputConditionIdentifier :
+/OutputConditionIdentifier (default_rgb) def
+
+% Create a PDF stream object to hold the XML invoice :
+[ /_objdef {{InvoiceStream}} /type /stream /OBJ pdfmark
+
+% Add the required entries to that stream dictionary :
+[ {{InvoiceStream}} << /Type /EmbeddedFile /Subtype (text/xml) cvn /Params << /ModDate (D:20130121081433+01'00') >> >> /PUT pdfmark
+
+% Read the XML invoice data from the file and store it in the PDF stream :
+[ {{InvoiceStream}} ({xml_path}) (r) file /PUT pdfmark
+
+% Close the PDF stream :
+[ {{InvoiceStream}} /CLOSE pdfmark
+
+% Create a PDF file specification dictionary to hold the file info :
+[ /_objdef {{InvoiceFile}} /type /dict /OBJ pdfmark
+
+% Add the required entries to that file specification dictionary :
+[ {{InvoiceFile}} <<
+    /Type /Filespec
+    /F ({xml_filename})
+    /EF << /F {{InvoiceStream}} >>
+>> /PUT pdfmark
+
+
+% Associate the file specification with the PDF document :
+[/Root <<
+    /Names << /EmbeddedFiles << /Names [ ({xml_filename}) {{InvoiceFile}} ] >> >>
+>> /pdfmark
+
+
+% Create an annotation to display the attachment in the PDF viewer:
+[{{Catalog}} <<
+    /Names << /EmbeddedFiles << /Names [ ({xml_filename}) {{InvoiceFile}} ] >> >>
+    /ViewerPreferences <<
+        /DisplayDocTitle true
+    >>
+    /PageLayout /SinglePage
+    /PageMode /UseAttachments
+>> /PUT pdfmark'''

main.py

@@ -0,0 +1,25 @@
+from fastapi import FastAPI, UploadFile, File
+from fastapi.responses import FileResponse
+import tempfile
+import secrets
+import subprocess
+import os
+
+from utils import save_temp_file, create_post_script_file
+
+app = FastAPI()
+
+
+
+@app.post("/upload")
+async def upload_files(pdf_file: UploadFile = File(...), xml_file: UploadFile = File(...)):
+    session_id = secrets.token_hex(8)
+    pdf_file_path = await save_temp_file(await pdf_file.read(), '.pdf', session_id)
+    xml_file_path = await save_temp_file(await xml_file.read(), '.xml', session_id)
+    ps_file = await create_post_script_file(xml_file_path,  session_id)
+    result_file_path = os.path.join(tempfile.mkdtemp(), session_id) + '.pdf'
+    command = f"gs -sDEVICE=pdfwrite -dNOSAFER -dPDFA=3 -sColorConversionStrategy=RGB -dPDFACompatibilityPolicy=2 -o {result_file_path} {pdf_file_path} {ps_file} -dDEBUG"
+    subprocess.run(command, shell=True)
+
+    print(result_file_path)
+    return FileResponse(result_file_path, filename="result.pdf")

pyproject.toml

@@ -0,0 +1,18 @@
+[tool.poetry]
+name = "pypdfa3-zugferd"
+version = "0.1.0"
+description = "Pythonfastapi to convert pdf to zugferd format"
+authors = ["Mayur Rawte <[email protected]>"]
+license = "MIT"
+
+[tool.poetry.dependencies]
+python = "^3.10"
+fastapi = "^0.98.0"
+uvicorn = "^0.22.0"
+python-multipart = "^0.0.6"
+
+[tool.poetry.dev-dependencies]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"

utils.py

@@ -0,0 +1,40 @@
+import tempfile
+from constant import ps_content_template
+from fastapi import UploadFile
+import subprocess
+
+
+xml_path = '/home/thepsygeek/zugferd/sample.xml'
+xml_filename = 'sample.xml'
+
+
+
+
+async def save_temp_file(upload_file: UploadFile, file_extension: str) -> str:
+    with tempfile.NamedTemporaryFile(suffix=file_extension, delete=False) as temp_file:
+        # Save the file
+        temp_file.write(await upload_file.read())
+        temp_file_path = temp_file.name
+    return temp_file_path
+
+
+import os
+
+async def save_temp_file(file_data: bytes, file_extension: str, folder: str) -> str:
+    os.makedirs(folder, exist_ok=True)
+    with tempfile.NamedTemporaryFile(suffix=file_extension, delete=False, dir=folder) as temp_file:
+        temp_file.write(file_data)
+        temp_file_path = temp_file.name
+    return temp_file_path
+
+
+async def create_post_script_file(xml_file_path: str, session_id):
+     content = ps_content_template.format(xml_path=xml_file_path, xml_filename='invoice.xml', gs_version=get_gs_version())
+     return await save_temp_file(content.encode('utf-8'), '.ps', session_id)
+
+def get_gs_version():
+    try:
+        gs_version = subprocess.check_output(["gs", "--version"]).strip().decode()
+        return gs_version
+    except subprocess.CalledProcessError:
+        return "Ghostscript not found"