markdown_convert 1.2.22__tar.gz → 1.2.25__tar.gz

{markdown_convert-1.2.22 → markdown_convert-1.2.25}/.gitignore

@@ -3,6 +3,8 @@ clean
 test
 test*
 
+desktop.ini
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

{markdown_convert-1.2.22 → markdown_convert-1.2.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: markdown_convert
-Version: 1.2.22
+Version: 1.2.25
 Summary: Convert Markdown files to PDF from your command line.
 Project-URL: homepage, https://github.com/Julynx/markdown_convert
 Author-email: Julio Cabria <juliocabria@tutanota.com>

{markdown_convert-1.2.22 → markdown_convert-1.2.25}/markdown_convert/__main__.py

@@ -32,8 +32,8 @@ def main():
 
         # Get the markdown path
         try:
-            md_path = arg["markdown_file_path"]
-            validate_markdown_path(md_path)
+            markdown_path = arg["markdown_file_path"]
+            validate_markdown_path(markdown_path)
         except KeyError as key_err:
             raise IndexError("Missing 'markdown_file_path' argument.") from key_err
         except Exception as exc:
@@ -61,18 +61,18 @@ def main():
         try:
             output_path = arg["--out"]
             validate_output_path(output_path)
-            output_path = get_output_path(md_path, output_path)
+            output_path = get_output_path(markdown_path, output_path)
         except KeyError:
-            output_path = get_output_path(md_path, None)
+            output_path = get_output_path(markdown_path, None)
         except Exception as exc:
             raise IndexError(f"Invalid 'output_path' argument: {exc}") from exc
 
         # Compile the markdown file
-        print(f"\nGenerating PDF file from '{md_path}'...\n")
+        print(f"\nGenerating PDF file from '{markdown_path}'...\n")
         if mode in ("once", "debug"):
-            convert(md_path, css_path, output_path, dump_html=mode == "debug")
+            convert(markdown_path, css_path, output_path, dump_html=mode == "debug")
         else:
-            live_convert(md_path, css_path, output_path)
+            live_convert(markdown_path, css_path, output_path)
 
         sys_exit(0)
 

{markdown_convert-1.2.22 → markdown_convert-1.2.25}/markdown_convert/modules/constants.py

@@ -14,10 +14,11 @@ OPTIONS = ("markdown_file_path", "--mode", "--css", "--out", "-h", "--help")
 
 OPTIONS_MODES = ("once", "live", "debug")
 
-MD_EXTENSIONS = {
+MARKDOWN_EXTENSIONS = {
     "fenced-code-blocks": None,
     "header-ids": True,
     "breaks": {"on_newline": True},
     "tables": True,
     "latex": True,
+    "mermaid": None,
 }

{markdown_convert-1.2.22 → markdown_convert-1.2.25}/markdown_convert/modules/convert.py

@@ -4,7 +4,7 @@ Author: @julynx
 """
 
 import os
-import re
+import secrets
 import time
 from datetime import datetime
 from pathlib import Path
@@ -12,8 +12,9 @@ from pathlib import Path
 import markdown2
 from playwright.sync_api import sync_playwright
 
-from .constants import MD_EXTENSIONS
+from .constants import MARKDOWN_EXTENSIONS
 from .resources import get_code_css_path, get_css_path, get_output_path
+from .transform import create_sections, render_mermaid_diagrams, create_html_document
 from .utils import drop_duplicates
 
 
@@ -24,6 +25,7 @@ def _generate_pdf_with_playwright(
     css_content=None,
     base_dir=None,
     dump_html=False,
+    nonce=None,
 ):
     """
     Generate a PDF from HTML content using Playwright.
@@ -35,27 +37,65 @@ def _generate_pdf_with_playwright(
         base_dir (Path, optional): Base directory for resolving relative paths in HTML.
         dump_html (bool, optional): Whether to dump the HTML content to a file.
     """
-    with sync_playwright() as p:
-        browser = p.chromium.launch(headless=True)
-        page = browser.new_page()
+    # Generate a cryptographic nonce for the Mermaid script
+
+    # Content Security Policy using nonce to whitelist only the Mermaid initialization script
+    # This prevents arbitrary JavaScript injection while allowing Mermaid to work
+    csp = (
+        "default-src 'none'; "
+        f"script-src 'nonce-{nonce}' https://cdn.jsdelivr.net; "
+        f"script-src-elem 'nonce-{nonce}' https://cdn.jsdelivr.net; "
+        "style-src 'unsafe-inline'; "
+        "img-src data: https: file:; "
+        "font-src data: https:; "
+        "connect-src https://cdn.jsdelivr.net;"
+    )
+
+    # Wrap HTML content with CSP and CSS
+    if css_content:
+        full_html = create_html_document(html_content, css_content, csp)
+    else:
+        full_html = html_content
+
+    with sync_playwright() as playwright:
+        browser = playwright.chromium.launch(
+            headless=True,
+            args=[
+                "--disable-dev-shm-usage",
+                "--disable-extensions",
+                "--disable-plugins",
+                "--disable-gpu",
+                "--no-first-run",
+                "--no-default-browser-check",
+            ],
+        )
+        context = browser.new_context(
+            java_script_enabled=True,
+            permissions=[],
+            geolocation=None,
+            accept_downloads=False,
+        )
+        page = context.new_page()
 
         # Handle loading based on presence of base_dir
         temp_html = None
         try:
             if base_dir:
                 temp_html = base_dir / f".temp_{os.getpid()}.html"
-                temp_html.write_text(html_content, encoding="utf-8")
-                page.goto(temp_html.as_uri(), wait_until="networkidle")
+                temp_html.write_text(full_html, encoding="utf-8")
+                page.goto(temp_html.as_uri(), wait_until="networkidle", timeout=30000)
             else:
-                page.set_content(html_content, wait_until="networkidle")
-
-            if css_content:
-                page.add_style_tag(content=css_content)
+                page.set_content(full_html, wait_until="networkidle", timeout=30000)
 
             pdf_params = {
                 "format": "A4",
                 "print_background": True,
-                "margin": {"top": "20mm", "bottom": "20mm", "left": "20mm", "right": "20mm"},
+                "margin": {
+                    "top": "20mm",
+                    "bottom": "20mm",
+                    "left": "20mm",
+                    "right": "20mm",
+                },
                 "path": output_path,
             }  # Playwright ignores None paths
 
@@ -83,25 +123,8 @@ def _get_css_content(css_sources):
     return css_buffer
 
 
-def _create_sections(html):
-    """
-    Creates h2 sections, from the first h2 to the next h2, wrapping them in <section> tags
-    using regular expressions.
-    Args:
-        html (str): HTML content.
-    Returns:
-        HTML content with sections wrapped in <section> tags.
-    """
-    pattern = re.compile(r"(<h2.*?>.*?</h2>)(.*?)(?=(<h2.*?>|$))", re.DOTALL)
-
-    def wrap_section(match):
-        return f"<section>\n{match.group(1)}\n{match.group(2)}\n</section>\n"
-
-    return pattern.sub(wrap_section, html)
-
-
 def convert(
-    md_path,
+    markdown_path,
     css_path=None,
     output_path=None,
     *,
@@ -112,7 +135,7 @@ def convert(
     Convert a markdown file to a pdf file.
 
     Args:
-        md_path (str): Path to the markdown file.
+        markdown_path (str): Path to the markdown file.
         css_path (str=None): Path to the CSS file.
         output_path (str=None): Path to the output file.
         extend_default_css (bool=True): Extend the default CSS file.
@@ -122,7 +145,7 @@ def convert(
         css_path = get_css_path()
 
     if output_path is None:
-        output_path = get_output_path(md_path, None)
+        output_path = get_output_path(markdown_path, None)
 
     if extend_default_css:
         css_sources = [get_code_css_path(), get_css_path(), css_path]
@@ -132,27 +155,32 @@ def convert(
     css_sources = drop_duplicates(css_sources)
 
     try:
-        html = markdown2.markdown_path(md_path, extras=MD_EXTENSIONS)
-        html = _create_sections(html)
+        nonce = secrets.token_urlsafe(16)
+        html = markdown2.markdown_path(markdown_path, extras=MARKDOWN_EXTENSIONS)
+        html = create_sections(html)
+        html = render_mermaid_diagrams(html, nonce=nonce)
 
         _generate_pdf_with_playwright(
             html,
             output_path,
             css_content=_get_css_content(css_sources),
-            base_dir=Path(md_path).resolve().parent,
+            base_dir=Path(markdown_path).resolve().parent,
             dump_html=dump_html,
+            nonce=nonce,
         )
 
     except Exception as exc:
         raise RuntimeError(exc) from exc
 
 
-def live_convert(md_path, css_path=None, output_path=None, *, extend_default_css=True):
+def live_convert(
+    markdown_path, css_path=None, output_path=None, *, extend_default_css=True
+):
     """
     Convert a markdown file to a pdf file and watch for changes.
 
     Args:
-        md_path (str): Path to the markdown file.
+        markdown_path (str): Path to the markdown file.
         css_path (str=None): Path to the CSS file.
         output_path (str=None): Path to the output file.
         extend_default_css (bool=True): Extend the default CSS file.
@@ -161,10 +189,10 @@ def live_convert(md_path, css_path=None, output_path=None, *, extend_default_css
         css_path = get_css_path()
 
     if output_path is None:
-        output_path = get_output_path(md_path, None)
+        output_path = get_output_path(markdown_path, None)
 
     live_converter = LiveConverter(
-        md_path,
+        markdown_path,
         css_path,
         output_path,
         extend_default_css=extend_default_css,
@@ -173,12 +201,12 @@ def live_convert(md_path, css_path=None, output_path=None, *, extend_default_css
     live_converter.observe()
 
 
-def convert_text(md_text, css_text=None, *, extend_default_css=True):
+def convert_text(markdown_text, css_text=None, *, extend_default_css=True):
     """
     Convert markdown text to a pdf file.
 
     Args:
-        md_text (str): Markdown text.
+        markdown_text (str): Markdown text.
         css_text (str=None): CSS text.
         extend_default_css (bool=True): Extend the default CSS file.
 
@@ -197,13 +225,16 @@ def convert_text(md_text, css_text=None, *, extend_default_css=True):
         css_sources = [code_css, css_text]
 
     try:
-        html = markdown2.markdown(md_text, extras=MD_EXTENSIONS)
-        html = _create_sections(html)
+        nonce = secrets.token_urlsafe(16)
+        html = markdown2.markdown(markdown_text, extras=MARKDOWN_EXTENSIONS)
+        html = create_sections(html)
+        html = render_mermaid_diagrams(html, nonce=nonce)
 
         return _generate_pdf_with_playwright(
             html,
             None,
             css_content=_get_css_content(css_sources),
+            nonce=nonce,
         )
 
     except Exception as exc:
@@ -215,17 +246,25 @@ class LiveConverter:
     Class to convert a markdown file to a pdf file and watch for changes.
     """
 
-    def __init__(self, md_path, css_path, output_path, *, extend_default_css=True, loud=False):
+    def __init__(
+        self,
+        markdown_path,
+        css_path,
+        output_path,
+        *,
+        extend_default_css=True,
+        loud=False,
+    ):
         """
         Initialize the LiveConverter class.
 
         Args:
-            md_path (str): Path to the markdown file.
+            markdown_path (str): Path to the markdown file.
             css_path (str): Path to the CSS file.
             output_path (str): Path to the output file.
             extend_default_css (bool): Extend the default CSS file.
         """
-        self.md_path = Path(md_path).absolute()
+        self.md_path = Path(markdown_path).absolute()
         self.css_path = Path(css_path).absolute()
         self.output_path = output_path
         self.extend_default_css = extend_default_css
@@ -272,14 +311,17 @@ class LiveConverter:
         try:
             while True:
 
-                md_modified = self.get_last_modified_date(self.md_path)
+                markdown_modified = self.get_last_modified_date(self.md_path)
                 css_modified = self.get_last_modified_date(self.css_path)
 
-                if md_modified != self.md_last_modified or css_modified != self.css_last_modified:
+                if (
+                    markdown_modified != self.md_last_modified
+                    or css_modified != self.css_last_modified
+                ):
 
                     self.write_pdf()
 
-                    self.md_last_modified = md_modified
+                    self.md_last_modified = markdown_modified
                     self.css_last_modified = css_modified
 
                 time.sleep(poll_interval)

{markdown_convert-1.2.22 → markdown_convert-1.2.25}/markdown_convert/modules/resources.py

@@ -17,28 +17,28 @@ from .constants import BLUE, CYAN, GREEN, YELLOW, OPTIONS, OPTIONS_MODES
 from .utils import color
 
 
-def get_output_path(md_path, output_dir=None):
+def get_output_path(markdown_path, output_dir=None):
     """
     Get the output path for the pdf file.
 
     Args:
-        md_path (str): The path to the markdown file.
+        markdown_path (str): The path to the markdown file.
         output_dir (str): The output directory.
 
     Returns:
         str: The output path.
     """
-    md_path = Path(md_path)
+    markdown_path = Path(markdown_path)
 
     if output_dir is None:
-        return md_path.parent / f"{md_path.stem}.pdf"
+        return markdown_path.parent / f"{markdown_path.stem}.pdf"
 
     output_dir = Path(output_dir)
 
     if output_dir.suffix == ".pdf":
         return output_dir
 
-    return output_dir.parent / f"{Path(md_path).stem}.pdf"
+    return output_dir.parent / f"{Path(markdown_path).stem}.pdf"
 
 
 def get_css_path():
@@ -76,11 +76,14 @@ def get_usage():
         f"{color(GREEN, 'markdown-convert')} "
         f"[{color(YELLOW, OPTIONS[0])}] [{color(BLUE, 'options')}]"
     )
-    opt_1 = f"{color(BLUE, OPTIONS[1])}{color(CYAN, '=')}{color(CYAN, '|'.join(OPTIONS_MODES))}"
-    opt_2 = (
+    option_one = (
+        f"{color(BLUE, OPTIONS[1])}{color(CYAN, '=')}"
+        f"{color(CYAN, '|'.join(OPTIONS_MODES))}"
+    )
+    option_two = (
         f"{color(BLUE, OPTIONS[2])}{color(CYAN, '=')}[{color(CYAN, 'css_file_path')}]"
     )
-    opt_3 = f"{color(BLUE, OPTIONS[3])}{color(CYAN, '=')}[{color(CYAN, 'output_file_path')}]"
+    option_three = f"{color(BLUE, OPTIONS[3])}{color(CYAN, '=')}[{color(CYAN, 'output_file_path')}]"
 
     usage = (
         "\n"
@@ -88,11 +91,11 @@ def get_usage():
         f"  {commd}\n"
         "\n"
         "Options:\n"
-        f"  {opt_1}\n"
+        f"  {option_one}\n"
         "    Convert the markdown file once (default) or live.\n"
-        f"  {opt_2}\n"
+        f"  {option_two}\n"
         "    Use a custom CSS file.\n"
-        f"  {opt_3}\n"
+        f"  {option_three}\n"
         "    Specify the output file path.\n"
     )
     return usage

markdown_convert-1.2.25/markdown_convert/modules/transform.py

@@ -0,0 +1,69 @@
+"""
+Module for transforming HTML content.
+"""
+
+import re
+
+
+def create_html_document(html_content, css_content, csp):
+    """
+    Creates a complete HTML document with the given content, CSS, and Content Security Policy.
+    Args:
+        html_content (str): The HTML content to include in the body.
+        css_content (str): The CSS styles to include in the head.
+        csp (str): The Content Security Policy string.
+    Returns:
+        str: A complete HTML document as a string.
+    """
+    return f"""<!DOCTYPE html>
+<html>
+<head>
+<meta charset="UTF-8">
+<meta http-equiv="Content-Security-Policy" content="{csp}">
+<style>
+{css_content}
+</style>
+</head>
+<body>
+{html_content}
+</body>
+</html>"""
+
+
+def create_sections(html):
+    """
+    Creates h2 sections, from the first h2 to the next h2, wrapping them in <section> tags
+    using regular expressions.
+    Args:
+        html (str): HTML content.
+    Returns:
+        HTML content with sections wrapped in <section> tags.
+    """
+    pattern = re.compile(r"(<h2.*?>.*?</h2>)(.*?)(?=(<h2.*?>|$))", re.DOTALL)
+
+    def wrap_section(match):
+        return f"<section>\n{match.group(1)}\n{match.group(2)}\n</section>\n"
+
+    return pattern.sub(wrap_section, html)
+
+
+def render_mermaid_diagrams(html, *, nonce):
+    """
+    Renders Mermaid diagrams in the HTML content.
+
+    Args:
+        html (str): HTML content.
+    Returns:
+        str: HTML content with rendered Mermaid diagrams.
+    """
+    mermaid_script = f"""
+<script type="module" nonce="{nonce}">
+  import mermaid from 'https://cdn.jsdelivr.net/npm/mermaid@10/dist/mermaid.esm.min.mjs';
+  mermaid.initialize({{ startOnLoad: true }});
+</script>
+"""
+
+    if '<div class="mermaid">' in html:
+        html = mermaid_script + html
+
+    return html

{markdown_convert-1.2.22 → markdown_convert-1.2.25}/markdown_convert/modules/validate.py

@@ -6,21 +6,21 @@ Author: @julynx
 from pathlib import Path
 
 
-def validate_markdown_path(md_path):
+def validate_markdown_path(markdown_path):
     """
     Validate the markdown file path.
 
     Args:
-        md_path (str): The path to the markdown file.
+        markdown_path (str): The path to the markdown file.
 
     Raises:
         FileNotFoundError: If the file is not found.
         ValueError: If the file is not a Markdown file.
     """
-    if not Path(md_path).is_file():
-        raise FileNotFoundError(f"File not found: '{md_path}'")
+    if not Path(markdown_path).is_file():
+        raise FileNotFoundError(f"File not found: '{markdown_path}'")
 
-    if not md_path.endswith(".md"):
+    if not markdown_path.endswith(".md"):
         raise ValueError("File must be a Markdown file.")
 
 

{markdown_convert-1.2.22 → markdown_convert-1.2.25}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "markdown_convert"
-version = "1.2.22"
+version = "1.2.25"
 description = "Convert Markdown files to PDF from your command line."
 authors = [
     { name = "Julio Cabria", email = "juliocabria@tutanota.com" },
@@ -40,6 +40,7 @@ include = [
     "markdown_convert/modules/__init__.py",
     "markdown_convert/modules/constants.py",
     "markdown_convert/modules/convert.py",
+    "markdown_convert/modules/transform.py",
     "markdown_convert/modules/resources.py",
     "markdown_convert/modules/utils.py",
     "markdown_convert/modules/validate.py",
@@ -55,7 +56,14 @@ include = [
     "markdown_convert/modules/__init__.py",
     "markdown_convert/modules/constants.py",
     "markdown_convert/modules/convert.py",
+    "markdown_convert/modules/transform.py",
     "markdown_convert/modules/resources.py",
     "markdown_convert/modules/utils.py",
     "markdown_convert/modules/validate.py",
 ]
+
+[dependency-groups]
+dev = [
+    "black>=25.11.0",
+    "pylint>=3.3.9",
+]