Merge d286aea402 into a54a8f2057

BUILD.md

@@ -260,11 +260,17 @@ The following instructions require typing commands in a terminal in dom0.
 
    ```
    qvm-create --class AppVM --label red --template fedora-40-dz dz
+   qvm-volume resize dz:private $(numfmt --from=auto 20Gi)
    ```
 
    > :bulb: Alternatively, you can use a different app qube for Dangerzone
    > development. In that case, replace `dz` with the qube of your choice in the
    > steps below.
+   >
+   > In the commands above, we also resize the private volume of the `dz` qube
+   > to 20GiB, since you may need some extra storage space when developing on
+   > Dangerzone (e.g., for container images, Tesseract data, and Python
+   > virtualenvs).
 
 4. Add an RPC policy (`/etc/qubes/policy.d/50-dangerzone.policy`) that will
    allow launching a disposable qube (`dz-dvm`) when Dangerzone converts a

README.md

@@ -6,7 +6,7 @@ Take potentially dangerous PDFs, office documents, or images and convert them to
 | ![Settings](./assets/screenshot1.png) | ![Converting](./assets/screenshot2.png)
 |--|--|
 
-Dangerzone works like this: You give it a document that you don't know if you can trust (for example, an email attachment). Inside of a sandbox, Dangerzone converts the document to a PDF (if it isn't already one), and then converts the PDF into raw pixel data: a huge list of RGB color values for each page. Then, in a separate sandbox, Dangerzone takes this pixel data and converts it back into a PDF.
+Dangerzone works like this: You give it a document that you don't know if you can trust (for example, an email attachment). Inside of a sandbox, Dangerzone converts the document to a PDF (if it isn't already one), and then converts the PDF into raw pixel data: a huge list of RGB color values for each page. Then, outside of the sandbox, Dangerzone takes this pixel data and converts it back into a PDF.
 
 _Read more about Dangerzone in the [official site](https://dangerzone.rocks/about/)._
 

dev_scripts/qa.py

@@ -3,14 +3,21 @@
 import abc
 import argparse
 import difflib
+import json
 import logging
 import re
 import selectors
 import subprocess
 import sys
+import urllib.request
+from pathlib import Path
 
 logger = logging.getLogger(__name__)
 
+PYTHON_VERSION_STR = "3.12"
+PYTHON_VERSION = [int(num) for num in PYTHON_VERSION_STR.split(".")]
+EOL_PYTHON_URL = "https://endoflife.date/api/python.json"
+
 CONTENT_QA = r"""## QA
 
 To ensure that new releases do not introduce regressions, and support existing
@@ -776,6 +783,10 @@ class QABase(abc.ABC):
                 self.prompt("Does it pass?", choices=["y", "n"])
         logger.info("Successfully completed QA scenarios")
 
+    @task("Download Tesseract data", auto=True)
+    def download_tessdata(self):
+        self.run("python", str(Path("install", "common", "download-tessdata.py")))
+
     @classmethod
     @abc.abstractmethod
     def get_id(cls):
@@ -802,6 +813,31 @@ class QAWindows(QABase):
         while msvcrt.kbhit():
             msvcrt.getch()
 
+    @QABase.task(
+        f"Install the latest version of Python {PYTHON_VERSION_STR}", ref=REF_BUILD
+    )
+    def install_python(self):
+        cur_version = list(sys.version_info[:3])
+
+        logger.info("Getting latest Python release")
+        with urllib.request.urlopen(EOL_PYTHON_URL) as f:
+            resp = f.read()
+            releases = json.loads(resp)
+            for release in releases:
+                if release["cycle"] == PYTHON_VERSION_STR:
+                    latest_version = [int(num) for num in release["latest"].split(".")]
+                    if latest_version > cur_version:
+                        self.prompt(
+                            f"You need to install the latest Python version ({release['latest']})"
+                        )
+                    elif latest_version == cur_version:
+                        logger.info(
+                            f"Verified that the latest Python version ({release['latest']}) is installed"
+                        )
+                        return
+
+        logger.error("Could not verify that the latest Python version is installed")
+
     @QABase.task("Install and Run Docker Desktop", ref=REF_BUILD)
     def install_docker(self):
         logger.info("Checking if Docker Desktop is installed and running")
@@ -816,7 +852,7 @@ class QAWindows(QABase):
     )
     def install_poetry(self):
         self.run("python", "-m", "pip", "install", "poetry")
-        self.run("poetry", "install")
+        self.run("poetry", "install", "--sync")
 
     @QABase.task("Build Dangerzone container image", ref=REF_BUILD, auto=True)
     def build_image(self):
@@ -838,9 +874,11 @@ class QAWindows(QABase):
         return "windows"
 
     def start(self):
+        self.install_python()
         self.install_docker()
         self.install_poetry()
         self.build_image()
+        self.download_tessdata()
         self.run_tests()
         self.build_dangerzone_exe()
 
@@ -933,6 +971,7 @@ class QALinux(QABase):
     def start(self):
         self.build_dev_image()
         self.build_container_image()
+        self.download_tessdata()
         self.run_tests()
         self.build_package()
         self.build_qa_image()