markdown_convert 1.2.46__tar.gz → 1.2.48__tar.gz

{markdown_convert-1.2.46 → markdown_convert-1.2.48}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: markdown_convert
-Version: 1.2.46
+Version: 1.2.48
 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-1.2.46 → markdown_convert-1.2.48}/markdown_convert/default.css

@@ -12,12 +12,18 @@
   --left-margin-big: 2em;
 
   /* -- Colors -- */
-  --color-text: #333; /* Main text color */
-  --color-text-light: #666; /* Tables, blockquotes, footers */
-  --color-text-background: #eee; /* Code blocks, table headers */
-  --color-border: #999; /* Image borders, rules */
-  --color-border-light: #ccc; /* Table borders, blockquotes */
-  --color-links: #09f; /* Hyperlinks */
+  /* Main text color */
+  --color-text: #333;
+  /* Tables, blockquotes, footers */
+  --color-text-light: #666;
+  /* Code blocks, table headers */
+  --color-text-background: #eee;
+  /* Image borders, rules */
+  --color-border: #999;
+  /* Table borders, blockquotes */
+  --color-border-light: #ccc;
+  /* Hyperlinks */
+  --color-links: #09f;
 }
 
 /* Document */
@@ -59,6 +65,7 @@ h2,
 h3,
 h4,
 h5 {
+  line-height: 1;
   color: var(--color-text);
   font-weight: 600;
 }
@@ -122,7 +129,7 @@ pre {
   white-space: pre-wrap;
 }
 
-pre > code {
+pre>code {
   display: block;
   padding: 1em;
   margin-top: 0;
@@ -160,7 +167,7 @@ blockquote {
   color: var(--color-text-light);
 }
 
-blockquote > blockquote {
+blockquote>blockquote {
   padding-left: var(--left-margin-small);
 }
 
@@ -175,13 +182,13 @@ img {
 }
 
 /* Image footers */
-p > img + em {
+p>img+em {
   text-align: center;
   font-size: 1rem;
   font-style: italic;
   color: var(--color-text-light);
   display: block;
-  margin: 1em auto;
+  margin: 0 auto;
 }
 
 /* Image alt text attributes */
@@ -212,6 +219,22 @@ img[alt*="::wide::"] {
   max-width: 100vw;
 }
 
+p:has(> img[alt*="::left::"]) {
+  display: flex;
+  flex-direction: column;
+  width: fit-content;
+  margin-right: auto;
+  align-items: center;
+}
+
+p:has(> img[alt*="::right::"]) {
+  display: flex;
+  flex-direction: column;
+  width: fit-content;
+  margin-left: auto;
+  align-items: center;
+}
+
 p:has(> img[alt*="::inline::"]) {
   display: inline-block;
   width: min-content;
@@ -268,19 +291,10 @@ th,
 td {
   padding: 0.5em 0.75em;
   border: 1px solid var(--color-border-light);
-  overflow-wrap: break-word;
   vertical-align: top;
-}
-
-th {
-  white-space: normal;
-  word-break: keep-all;
-  hyphens: auto;
-}
-
-td {
+  overflow-wrap: break-word;
+  word-break: normal;
   white-space: normal;
-  word-break: break-word;
 }
 
 /* Horizontal rulers */
@@ -295,7 +309,7 @@ hr:has(+ hr) {
   visibility: hidden;
 }
 
-hr + hr {
+hr+hr {
   clear: both;
   break-after: always;
   page-break-after: always;
@@ -391,8 +405,7 @@ math {
 .keyboard,
 .key {
   font-family:
-    "Segoe UI Symbol", "DejaVu Sans", "Liberation Sans", "Arial",
-    "sans-serif";
+    "Segoe UI Symbol", "DejaVu Sans", "Liberation Sans", "Arial", "sans-serif";
   font-size: 0.9rem;
   background-color: var(--color-text-background);
   border: 1px solid var(--color-border);
@@ -400,3 +413,8 @@ math {
   padding: 0.1em 0.4em;
   box-shadow: rgba(100, 100, 100, 0.4) 0px 2px 4px 0px;
 }
+
+.center {
+  display: block;
+  text-align: center;
+}

{markdown_convert-1.2.46 → markdown_convert-1.2.48}/markdown_convert/modules/convert.py

@@ -18,8 +18,7 @@ from .transform import (
     create_sections,
     render_mermaid_diagrams,
     create_html_document,
-    render_checkboxes,
-    create_spans,
+    render_extra_features,
 )
 from .utils import drop_duplicates
 
@@ -135,8 +134,7 @@ def convert(
         html = markdown2.markdown_path(markdown_path, extras=MARKDOWN_EXTENSIONS)
         html = create_sections(html)
         html = render_mermaid_diagrams(html, nonce=nonce)
-        html = render_checkboxes(html)
-        html = create_spans(html)
+        html = render_extra_features(html)
 
         _generate_pdf_with_playwright(
             html,
@@ -207,8 +205,7 @@ def convert_text(markdown_text, css_text=None, *, extend_default_css=True):
         html = markdown2.markdown(markdown_text, extras=MARKDOWN_EXTENSIONS)
         html = create_sections(html)
         html = render_mermaid_diagrams(html, nonce=nonce)
-        html = render_checkboxes(html)
-        html = create_spans(html)
+        html = render_extra_features(html)
 
         return _generate_pdf_with_playwright(
             html,

markdown_convert-1.2.48/markdown_convert/modules/transform.py

@@ -0,0 +1,171 @@
+"""
+Module for transforming HTML content.
+"""
+
+import re
+
+from bs4 import BeautifulSoup
+
+
+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 or ""}">
+<style>
+{css_content or ""}
+</style>
+</head>
+<body>
+{html_content or ""}
+</body>
+</html>"""
+
+
+def create_sections(html_string):
+    """
+    Wraps each h2 or h3 and its following content in a <section> tag.
+    The section ends when the next h2 or h3 is encountered, or the parent ends.
+
+    Args:
+        html_string (str): The input HTML string.
+    Returns:
+        str: The modified HTML string with sections wrapped.
+    """
+    soup = BeautifulSoup(html_string, "html.parser")
+
+    for header in soup.find_all(["h2", "h3"]):
+        new_section = soup.new_tag("section")
+        header.insert_before(new_section)
+
+        current = header
+        while current is not None and (
+            current == header or current.name not in ["h2", "h3"]
+        ):
+            next_sibling = current.next_sibling
+            new_section.append(current)
+            current = next_sibling
+
+    return str(soup)
+
+
+def render_mermaid_diagrams(html, *, nonce):
+    """
+    Renders Mermaid diagrams in the HTML content.
+
+    Args:
+        html (str): HTML content.
+        nonce (str): Cryptographic nonce for CSP.
+    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@11/dist/mermaid.esm.min.mjs';
+  mermaid.initialize({{
+    startOnLoad: true,
+    theme: 'default',
+    themeVariables: {{}},
+    fontFamily: 'arial, verdana, sans-serif'
+  }});
+</script>
+"""
+
+    if '<div class="mermaid">' in html:
+        html = mermaid_script + html
+
+    return html
+
+
+def render_extra_features(html):
+    """
+    Renders extra features like checkboxes, highlights, and custom spans in the HTML content.
+
+    Args:
+        html (str): HTML content.
+    Returns:
+        str: HTML content with extra features rendered.
+    """
+
+    def _create_checkbox(soup, match):
+        tag = soup.new_tag("input", type="checkbox")
+        if "[x]" in match.group("checkbox"):
+            tag["checked"] = ""
+        return tag
+
+    def _create_highlight(soup, match):
+        tag = soup.new_tag("span", attrs={"class": "highlight"})
+        tag.string = match.group("hl_content")
+        return tag
+
+    def _create_custom_span(soup, match):
+        tag = soup.new_tag("span", attrs={"class": match.group("cls")})
+        tag.string = match.group("sp_content")
+        return tag
+
+    handlers = {
+        "checkbox": _create_checkbox,
+        "highlight": _create_highlight,
+        "span": _create_custom_span,
+    }
+
+    master_pattern = re.compile(
+        r"(?P<checkbox>\[\s\]|\[x\])|"
+        r"(?P<highlight>==(?P<hl_content>.*?)==)|"
+        r"(?P<span>(?P<cls>[a-zA-Z0-9_-]+)\{\{\s*(?P<sp_content>.*?)\s*\}\})"
+    )
+
+    ignored_tags = {"code", "pre", "script", "style"}
+
+    soup = BeautifulSoup(html, "html.parser")
+    for text_node in soup.find_all(string=True):
+        # Ignore text nodes within certain tags
+        if text_node.parent.name in ignored_tags:
+            continue
+
+        # If no match, skip processing
+        content = text_node.string
+        if not master_pattern.search(content):
+            continue
+
+        new_nodes = []
+        last_end = 0
+        for match in master_pattern.finditer(content):
+            start, end = match.span()
+
+            # Append text before the match
+            if start > last_end:
+                new_nodes.append(content[last_end:start])
+
+            kind = match.lastgroup
+
+            # Call the appropriate handler
+            handler = handlers.get(kind)
+            if handler:
+                try:
+                    tag = handler(soup, match)
+                    new_nodes.append(tag)
+                except Exception as exc:
+                    print(f"Warning: Handler for '{kind}' failed with exception: {exc}")
+                    new_nodes.append(match.group(0))
+
+            last_end = end
+
+        # Append any remaining text after the last match
+        if new_nodes:
+            if last_end < len(content):
+                new_nodes.append(content[last_end:])
+
+            text_node.replace_with(*new_nodes)
+
+    return str(soup)

{markdown_convert-1.2.46 → markdown_convert-1.2.48}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "markdown_convert"
-version = "1.2.46"
+version = "1.2.48"
 description = "Convert Markdown files to PDF from your command line."
 authors = [
     { name = "Julio Cabria", email = "juliocabria@tutanota.com" },

markdown_convert-1.2.46/markdown_convert/modules/transform.py

@@ -1,169 +0,0 @@
-"""
-Module for transforming HTML content.
-"""
-
-import re
-
-from bs4 import BeautifulSoup
-
-
-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 or ""}">
-<style>
-{css_content or ""}
-</style>
-</head>
-<body>
-{html_content or ""}
-</body>
-</html>"""
-
-
-def create_sections(html_string):
-    """
-    Wraps each h2 or h3 and its following content in a <section> tag.
-    The section ends when the next h2 or h3 is encountered, or the parent ends.
-
-    Args:
-        html_string (str): The input HTML string.
-    Returns:
-        str: The modified HTML string with sections wrapped.
-    """
-    soup = BeautifulSoup(html_string, "html.parser")
-
-    # Change 1: Search for both h2 and h3 tags
-    for header in soup.find_all(["h2", "h3"]):
-        # Create the new section
-        new_section = soup.new_tag("section")
-        header.insert_before(new_section)
-
-        current = header
-
-        # Change 2: Update loop to stop if it hits an h2 OR h3 (that isn't the current one)
-        while current is not None and (
-            current == header or current.name not in ["h2", "h3"]
-        ):
-            next_sibling = current.next_sibling
-            new_section.append(current)
-            current = next_sibling
-
-    return str(soup)
-
-
-def render_mermaid_diagrams(html, *, nonce):
-    """
-    Renders Mermaid diagrams in the HTML content.
-
-    Args:
-        html (str): HTML content.
-        nonce (str): Cryptographic nonce for CSP.
-    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@11/dist/mermaid.esm.min.mjs';
-  mermaid.initialize({{
-    startOnLoad: true,
-    theme: 'default',
-    themeVariables: {{}},
-    fontFamily: 'arial, verdana, sans-serif'
-  }});
-</script>
-"""
-
-    if '<div class="mermaid">' in html:
-        html = mermaid_script + html
-
-    return html
-
-
-def render_checkboxes(html):
-    """
-    Renders checkboxes in the HTML content by replacing input elements with SVG representations.
-    Args:
-        html (str): HTML content.
-    Returns:
-        str: HTML content with rendered checkboxes.
-    """
-    unchecked = "[ ]"
-    checked = "[x]"
-
-    unchecked_html = "<input type='checkbox'>"
-    checked_html = "<input type='checkbox' checked>"
-
-    # Split by code blocks to avoid processing text inside them
-    parts = re.split(r"(<code>.*?</code>)", html, flags=re.DOTALL)
-    for part_index, _part in enumerate(parts):
-        # Only process parts that are NOT code blocks
-        if not parts[part_index].startswith("<code>"):
-            parts[part_index] = parts[part_index].replace(unchecked, unchecked_html)
-            parts[part_index] = parts[part_index].replace(checked, checked_html)
-
-    return "".join(parts)
-
-
-def create_spans(html):
-    """
-    Renders custom spans in the HTML content by replacing classname{{ content }} tags.
-    Args:
-        html (str): HTML content.
-    Returns:
-        str: HTML content with rendered custom spans.
-    """
-    soup = BeautifulSoup(html, "html.parser")
-
-    # Regex to match classname{{ content }}
-    # It captures the class name and the content
-    pattern = re.compile(r"([a-zA-Z0-9_-]+){{\s*(.*?)\s*}}")
-
-    # We need to find all text nodes and replace the pattern
-    for text_node in soup.find_all(string=True):
-        # Skip text nodes inside code, pre, script, style tags
-        if text_node.parent.name in ["code", "pre", "script", "style"]:
-            continue
-
-        content = str(text_node)
-        if "{{" in content:
-            new_content_nodes = []
-            last_end = 0
-            for match in pattern.finditer(content):
-                # Add text before the match
-                before = content[last_end : match.start()]
-                if before:
-                    new_content_nodes.append(soup.new_string(before))
-
-                # Create the new span tag
-                class_name = match.group(1)
-                inner_text = match.group(2)
-                new_span = soup.new_tag("span", attrs={"class": class_name})
-                new_span.string = inner_text
-                new_content_nodes.append(new_span)
-
-                last_end = match.end()
-
-            # Add remaining text after the last match
-            after = content[last_end:]
-            if after:
-                new_content_nodes.append(soup.new_string(after))
-
-            if new_content_nodes:
-                # Replace the original text node with the new nodes
-                for node in reversed(new_content_nodes):
-                    text_node.insert_after(node)
-                text_node.extract()
-
-    return str(soup)