Update HTML2PDF.js to 0.2.1, add a testable and observable Dockerfile (#25)

Author: stanislaw

.github/workflows/docker.yml

@@ -0,0 +1,31 @@
+name: HTML2Print Docker CI
+
+on:
+  pull_request:
+    branches: [ "**" ]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Upgrade pip
+      run: |
+        python -m pip install --upgrade pip
+
+    - name: Install Python packages
+      run: |
+        pip install -r requirements.development.txt
+
+    - name: Build Docker image with PR branch
+      run: |
+        invoke build-docker \
+          --image pr-${{ github.event.pull_request.number }} \
+          --source=${{ github.event.pull_request.head.sha }}
+
+    - name: Run container and test StrictDoc installation
+      run: |
+        invoke test-docker \
+          --image pr-${{ github.event.pull_request.number }}

.gitignore

@@ -1,10 +1,11 @@
 # HTML2PDF JS file.
-html2print/html2pdf_js/
+# html2print/html2pdf_js/
 
 .idea/
 **/.wdm/
 build/
 dist/
 tests/integration/.lit_test_times.txt
 tests/integration/**/Output/
+output/
 

Dockerfile

@@ -0,0 +1,55 @@
+FROM ubuntu:24.04
+
+# Install dependencies
+RUN apt-get update && apt-get install -y \
+    curl \
+    git \
+    python3 \
+    python3-pip \
+    python3-venv \
+    sudo \
+    vim \
+    wget \
+    && rm -rf /var/lib/apt/lists/*
+
+# Download and install Google Chrome
+RUN wget -q -O google-chrome.deb https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb \
+    && apt-get update \
+    && apt-get install -y ./google-chrome.deb \
+    && rm google-chrome.deb
+
+# Create a new non-root user and group.
+# NOTE: It is important that a non-root user is used because otherwise the
+# Chrome Driver fails with: "User data directory is already in use"
+# https://github.com/SeleniumHQ/selenium/issues/15327#issuecomment-2688613182
+RUN groupadd -r html2print && useradd -r -m -g html2print html2print
+
+# Grant the new user sudo privileges.
+RUN echo "html2print ALL=(ALL) NOPASSWD:ALL" > /etc/sudoers.d/html2print
+
+# Create a virtual environment in the user's home directory.
+RUN python3 -m venv /opt/venv
+
+# Ensure the virtual environment is used by modifying the PATH.
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Install StrictDoc. Set default StrictDoc installation from PyPI but allow
+# overriding it with an environment variable.
+ARG HTML2PRINT_SOURCE="pypi"
+ENV HTML2PRINT_SOURCE=${HTML2PRINT_SOURCE}
+
+RUN if [ "$HTML2PRINT_SOURCE" = "pypi" ]; then \
+      pip install --no-cache-dir --upgrade pip && \
+      pip install --no-cache-dir html2print; \
+    else \
+      pip install --no-cache-dir --upgrade pip && \
+      pip install --no-cache-dir git+https://github.com/mettta/html2pdf_python.git@${HTML2PRINT_SOURCE}; \
+    fi; \
+    chmod -R 777 /opt/venv;
+
+USER html2print
+
+# Set the working directory to the user's home directory.
+WORKDIR /data
+
+ENTRYPOINT ["/bin/bash"]

html2print/html2pdf_js/html2pdf.min.js

@@ -20,14 +20,16 @@
 from selenium.webdriver.chrome.service import Service
 from webdriver_manager.core.os_manager import ChromeType, OperationSystemManager
 
-__version__ = "0.0.14"
+__version__ = "0.0.15a2"
 
 PATH_TO_HTML2PDF_JS = os.path.join(
     os.path.dirname(os.path.join(__file__)), "html2pdf_js", "html2pdf.min.js"
 )
 
 DEFAULT_CACHE_DIR = os.path.join(Path.home(), ".html2print", "chromedriver")
 
+PATH_TO_CHROME_DRIVER_DEBUG_LOG = "/tmp/chromedriver.log"
+
 # HTML2PDF.js prints unicode symbols to console. The following makes it work on
 # Windows which otherwise complains:
 # UnicodeEncodeError: 'charmap' codec can't encode characters in position 129-130: character maps to <undefined>
@@ -303,7 +305,10 @@ class Done(Exception):
 
 
 def create_webdriver(
-    chromedriver: Optional[str], path_to_cache_dir: str, page_load_timeout: int
+    chromedriver: Optional[str],
+    path_to_cache_dir: str,
+    page_load_timeout: int,
+    debug: bool = False,
 ) -> webdriver.Chrome:
     print("html2print: creating ChromeDriver service.", flush=True)  # noqa: T201
     if chromedriver is None:
@@ -314,13 +319,20 @@ def create_webdriver(
         path_to_chrome = chromedriver
     print(f"html2print: ChromeDriver available at path: {path_to_chrome}")  # noqa: T201
 
-    service = Service(path_to_chrome)
+    if debug:
+        service = Service(
+            path_to_chrome, log_output=PATH_TO_CHROME_DRIVER_DEBUG_LOG
+        )
+    else:
+        service = Service(path_to_chrome)
 
     webdriver_options = Options()
     webdriver_options.add_argument("start-maximized")
     webdriver_options.add_argument("disable-infobars")
+    # Doesn't seem to be needed.
+    # webdriver_options.add_argument('--disable-gpu')  # noqa: ERA001
     webdriver_options.add_argument("--disable-extensions")
-    webdriver_options.add_argument("--headless")
+    webdriver_options.add_argument("--headless=chrome")
     # FIXME: This is not nice but otherwise it does not work in Ubuntu 24-based Docker image.
     # https://github.com/SeleniumHQ/selenium/issues/15327#issuecomment-2689287561
     webdriver_options.add_argument("--no-sandbox")
@@ -415,6 +427,14 @@ def main():
             "HTML file, load it, and let HTML2PDF.js finish its job."
         ),
     )
+    command_parser_print.add_argument(
+        "--debug",
+        action="store_true",
+        help=(
+            f"Enables ChromeDriver logging to a file: "
+            f"{PATH_TO_CHROME_DRIVER_DEBUG_LOG}."
+        ),
+    )
     command_parser_print.add_argument(
         "paths", nargs="+", help="Paths to input HTML file."
     )
@@ -442,7 +462,10 @@ def main():
             args.cache_dir if args.cache_dir is not None else DEFAULT_CACHE_DIR
         )
         driver = create_webdriver(
-            args.chromedriver, path_to_cache_dir, page_load_timeout
+            args.chromedriver,
+            path_to_cache_dir,
+            page_load_timeout,
+            debug=args.debug,
         )
 
         @atexit.register

html2print/html2print.py

@@ -30,6 +30,7 @@ def run_invoke(
     cmd,
     environment: Optional[dict] = None,
     warn: bool = False,
+    pty: bool = False,
 ) -> invoke.runners.Result:
     def one_line_command(string):
         return re.sub("\\s+", " ", string).strip()
@@ -39,7 +40,7 @@ def one_line_command(string):
         env=environment,
         hide=False,
         warn=warn,
-        pty=False,
+        pty=pty,
         echo=True,
     )
 
@@ -267,3 +268,64 @@ def release(context, test_pypi=False, username=None, password=None):
                 {user_password}
         """,
     )
+
+
+@task(aliases=["bd"])
+def build_docker(
+    context,
+    image: str = "html2print:latest",
+    no_cache: bool = False,
+    source="pypi",
+):
+    no_cache_argument = "--no-cache" if no_cache else ""
+    run_invoke(
+        context,
+        f"""
+        docker build .
+            --build-arg HTML2PRINT_SOURCE={source}
+            -t {image}
+            {no_cache_argument}
+        """,
+    )
+
+
+@task(aliases=["rd"])
+def run_docker(
+    context, image: str = "html2print:latest", command: Optional[str] = None
+):
+    command_argument = (
+        f'/bin/bash -c "{command}"' if command is not None else ""
+    )
+    entry_point_argument = '--entrypoint=""' if command_argument else ""
+
+    run_invoke(
+        context,
+        f"""
+        docker run
+            --name html2print
+            --rm
+            -it
+            -v "$(pwd):/data"
+            {entry_point_argument}
+            {image}
+            {command_argument}
+        """,
+        pty=True,
+    )
+
+
+@task(aliases=["td"])
+def test_docker(context, image: str = "html2print:latest"):
+    run_invoke(
+        context,
+        """
+        mkdir -p output/ && chmod 777 output/
+        """,
+    )
+    run_docker(
+        context,
+        image=image,
+        command=(
+            "cd tests/integration/01_hello_world && html2print print --debug index.html /data/output/index.pdf && cat /tmp/chromedriver.log"
+        ),
+    )

tasks.py

@@ -4,8 +4,8 @@
 <head>
   <meta charset="utf-8">
   <title>Test page</title>
-  <script src="../../../submodules/html2pdf/dist/bundle.js"></script>
-  <link rel="stylesheet" href="../../../submodules/html2pdf/test/shared/css/main.css">
+  <script src="../../../html2print/html2pdf_js/html2pdf.min.js"></script>
+  <link rel="stylesheet" href="../../../tests/integration/main.css">
 </head>
 
 <body>

tests/integration/01_hello_world/index.html

@@ -4,8 +4,8 @@
 <head>
   <meta charset="utf-8">
   <title>Test page</title>
-  <script src="../../../submodules/html2pdf/dist/bundle.js"></script>
-  <link rel="stylesheet" href="../../../submodules/html2pdf/test/shared/css/main.css">
+  <script src="../../../html2print/html2pdf_js/html2pdf.min.js"></script>
+  <link rel="stylesheet" href="../../../tests/integration/main.css">
 </head>
 
 <body>

tests/integration/02_two_pages/index.html

@@ -4,8 +4,8 @@
 <head>
   <meta charset="utf-8">
   <title>Test page</title>
-  <script src="../../../submodules/html2pdf/dist/bundle.js"></script>
-  <link rel="stylesheet" href="../../../submodules/html2pdf/test/shared/css/main.css">
+  <script src="../../../html2print/html2pdf_js/html2pdf.min.js"></script>
+  <link rel="stylesheet" href="../../../tests/integration/main.css">
 </head>
 
 <body>

tests/integration/03_cache_dir_argument/index.html

@@ -4,8 +4,8 @@
 <head>
   <meta charset="utf-8">
   <title>Test page</title>
-  <script src="../../../submodules/html2pdf/dist/bundle.js"></script>
-  <link rel="stylesheet" href="../../../submodules/html2pdf/test/shared/css/main.css">
+  <script src="../../../html2print/html2pdf_js/html2pdf.min.js"></script>
+  <link rel="stylesheet" href="../../../tests/integration/main.css">
 </head>
 
 <body>