dd-format 0.1.0__tar.gz

dd_format-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 digital-duck
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

dd_format-0.1.0/PKG-INFO

@@ -0,0 +1,22 @@
+Metadata-Version: 2.4
+Name: dd-format
+Version: 0.1.0
+Summary: Abstraction layer for formatting documents from markdown to HTML, PDF, and DOCX.
+Author-email: Digital Duck & Dog Team <info@digitalduck.org>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/digital-duck/dd-format
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: fpdf2>=2.7
+Requires-Dist: click>=8.0
+Provides-Extra: docx
+Requires-Dist: python-docx>=1.0; extra == "docx"
+Provides-Extra: all
+Requires-Dist: python-docx>=1.0; extra == "all"
+Dynamic: license-file
+
+# dd-format
+Abstraction layer for formatting document from markdown to others such as html, pdf

dd_format-0.1.0/README.md

@@ -0,0 +1,2 @@
+# dd-format
+Abstraction layer for formatting document from markdown to others such as html, pdf

dd_format-0.1.0/dd_format/__init__.py

@@ -0,0 +1,13 @@
+"""dd-format: convert markdown to PDF, DOCX, and HTML."""
+
+from dd_format.pdf_writer import markdown_to_pdf
+from dd_format.html_writer import markdown_to_html
+
+__all__ = ["markdown_to_pdf", "markdown_to_html", "markdown_to_docx"]
+__version__ = "0.1.0"
+
+
+def markdown_to_docx(md_text: str, output_path: str, title: str = ""):
+    """Lazy import — requires ``pip install dd-format[docx]``."""
+    from dd_format.docx_writer import markdown_to_docx as _impl
+    return _impl(md_text, output_path, title=title)

dd_format-0.1.0/dd_format/cli.py

@@ -0,0 +1,68 @@
+"""dd-format CLI: convert markdown files to PDF, DOCX, or HTML."""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import click
+
+
+@click.command()
+@click.argument("source", type=click.Path(exists=True))
+@click.option(
+    "--format",
+    "out_fmt",
+    type=click.Choice(["pdf", "html", "docx"]),
+    default="pdf",
+    show_default=True,
+    help="Output format.",
+)
+@click.option(
+    "--out",
+    default="",
+    help="Output file path (default: <source>.<format>).",
+)
+@click.option(
+    "--title",
+    default="",
+    help="Document title.",
+)
+def main(source: str, out_fmt: str, out: str, title: str) -> None:
+    """Convert a markdown file to PDF, DOCX, or HTML.
+
+    \b
+    Examples:
+      dd-format notes.md
+      dd-format notes.md --format html --out notes.html
+      dd-format notes.md --format docx --title "My Notes"
+    """
+    src = Path(source)
+    md_text = src.read_text(encoding="utf-8")
+
+    if not out:
+        out = str(src.with_suffix(f".{out_fmt}"))
+
+    if out_fmt == "pdf":
+        from dd_format.pdf_writer import markdown_to_pdf
+        markdown_to_pdf(md_text, out, title=title)
+    elif out_fmt == "html":
+        from dd_format.html_writer import markdown_to_html
+        markdown_to_html(md_text, out, title=title)
+    elif out_fmt == "docx":
+        try:
+            from dd_format.docx_writer import markdown_to_docx
+        except ImportError:
+            click.echo(
+                "Error: python-docx is required for DOCX output.\n"
+                "Install it with: pip install dd-format[docx]",
+                err=True,
+            )
+            sys.exit(1)
+        markdown_to_docx(md_text, out, title=title)
+
+    click.echo(f"Written: {out}")
+
+
+if __name__ == "__main__":
+    main()

dd_format-0.1.0/dd_format/docx_writer.py

@@ -0,0 +1,75 @@
+"""Convert markdown text to a .docx file using python-docx."""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+
+def markdown_to_docx(md_text: str, output_path: str, title: str = "") -> Path:
+    """Write *md_text* (simple markdown) to a Word document at *output_path*.
+
+    Supports: headings (# / ## / ###), bullet lists (- / *),
+    **bold**, and ``code`` spans.
+
+    Requires ``pip install dd-format[docx]``.
+
+    Parameters
+    ----------
+    md_text : str
+        Markdown-formatted text.
+    output_path : str
+        Destination file path.
+    title : str, optional
+        Document title rendered as Heading 0.
+
+    Returns
+    -------
+    Path
+        The output file path.
+    """
+    from docx import Document  # type: ignore
+
+    doc = Document()
+    if title:
+        doc.add_heading(title, level=0)
+
+    for line in md_text.split("\n"):
+        stripped = line.strip()
+        if not stripped:
+            doc.add_paragraph("")
+            continue
+
+        # Headings
+        if stripped.startswith("### "):
+            doc.add_heading(stripped[4:], level=3)
+        elif stripped.startswith("## "):
+            doc.add_heading(stripped[3:], level=2)
+        elif stripped.startswith("# "):
+            doc.add_heading(stripped[2:], level=1)
+        elif stripped.startswith("- ") or stripped.startswith("* "):
+            p = doc.add_paragraph(style="List Bullet")
+            _add_runs(p, stripped[2:])
+        else:
+            p = doc.add_paragraph()
+            _add_runs(p, stripped)
+
+    out = Path(output_path)
+    doc.save(str(out))
+    return out
+
+
+def _add_runs(paragraph, text: str) -> None:
+    """Add runs to a paragraph, handling **bold** and `code` spans."""
+    pos = 0
+    for m in re.finditer(r"\*\*(.+?)\*\*|`([^`]+)`", text):
+        if m.start() > pos:
+            paragraph.add_run(text[pos : m.start()])
+        if m.group(1) is not None:
+            paragraph.add_run(m.group(1)).bold = True
+        else:
+            run = paragraph.add_run(m.group(2))
+            run.font.name = "Courier New"
+        pos = m.end()
+    if pos < len(text):
+        paragraph.add_run(text[pos:])

dd_format-0.1.0/dd_format/html_writer.py

@@ -0,0 +1,163 @@
+"""Convert markdown text to a self-contained HTML file."""
+
+from __future__ import annotations
+
+import html
+from pathlib import Path
+
+_TEMPLATE = """\
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>{title}</title>
+<style>
+:root {{
+    --bg: #0f1117; --card: #1a1d27; --accent: #4f8ef7;
+    --text: #e0e0e0; --sub: #9ca3af; --border: #2d3148;
+}}
+* {{ box-sizing: border-box; margin: 0; padding: 0; }}
+body {{
+    background: var(--bg); color: var(--text);
+    font-family: 'Segoe UI', system-ui, sans-serif;
+    padding: 2rem; max-width: 800px; margin: 0 auto;
+    line-height: 1.7;
+}}
+h1 {{ font-size: 1.8rem; color: var(--accent); margin: 1.5rem 0 0.5rem; }}
+h2 {{ font-size: 1.4rem; color: var(--accent); margin: 1.2rem 0 0.4rem; }}
+h3 {{ font-size: 1.1rem; color: var(--accent); margin: 1rem 0 0.3rem; }}
+p  {{ margin: 0.5rem 0; }}
+ul {{ padding-left: 1.5rem; margin: 0.5rem 0; }}
+li {{ margin: 0.2rem 0; }}
+pre {{
+    background: var(--card); border: 1px solid var(--border);
+    border-radius: 8px; padding: 1rem; overflow-x: auto;
+    font-family: 'Cascadia Code', 'Fira Code', monospace; font-size: 0.88rem;
+    margin: 0.8rem 0;
+}}
+code {{
+    background: var(--card); padding: 0.15rem 0.4rem; border-radius: 4px;
+    font-family: 'Cascadia Code', 'Fira Code', monospace; font-size: 0.88rem;
+}}
+strong {{ color: #fff; }}
+hr {{ border: none; border-top: 1px solid var(--border); margin: 1.5rem 0; }}
+</style>
+</head>
+<body>
+{body}
+</body>
+</html>"""
+
+
+def markdown_to_html(md_text: str, output_path: str, title: str = "") -> Path:
+    """Convert simple markdown to a dark-mode, self-contained HTML file.
+
+    Supports: headings, bold, code spans, fenced code blocks,
+    bullet lists, horizontal rules, and paragraphs.
+
+    Parameters
+    ----------
+    md_text : str
+        Markdown-formatted text.
+    output_path : str
+        Destination file path.
+    title : str, optional
+        HTML ``<title>`` value (defaults to "Document").
+
+    Returns
+    -------
+    Path
+        The output file path.
+    """
+    lines = md_text.split("\n")
+    out: list[str] = []
+    in_code = False
+    in_list = False
+
+    for line in lines:
+        stripped = line.strip()
+
+        # Fenced code blocks
+        if stripped.startswith("```"):
+            if in_code:
+                out.append("</pre>")
+            else:
+                if in_list:
+                    out.append("</ul>")
+                    in_list = False
+                out.append("<pre>")
+            in_code = not in_code
+            continue
+        if in_code:
+            out.append(html.escape(line))
+            continue
+
+        if not stripped:
+            if in_list:
+                out.append("</ul>")
+                in_list = False
+            continue
+
+        # Horizontal rule
+        if stripped in ("---", "***", "___"):
+            if in_list:
+                out.append("</ul>")
+                in_list = False
+            out.append("<hr>")
+            continue
+
+        # Headings
+        if stripped.startswith("### "):
+            if in_list:
+                out.append("</ul>")
+                in_list = False
+            out.append(f"<h3>{_inline(stripped[4:])}</h3>")
+        elif stripped.startswith("## "):
+            if in_list:
+                out.append("</ul>")
+                in_list = False
+            out.append(f"<h2>{_inline(stripped[3:])}</h2>")
+        elif stripped.startswith("# "):
+            if in_list:
+                out.append("</ul>")
+                in_list = False
+            out.append(f"<h1>{_inline(stripped[2:])}</h1>")
+        # Bullet lists
+        elif stripped.startswith("- ") or stripped.startswith("* "):
+            if not in_list:
+                out.append("<ul>")
+                in_list = True
+            out.append(f"<li>{_inline(stripped[2:])}</li>")
+        # Paragraphs
+        else:
+            if in_list:
+                out.append("</ul>")
+                in_list = False
+            out.append(f"<p>{_inline(stripped)}</p>")
+
+    if in_list:
+        out.append("</ul>")
+    if in_code:
+        out.append("</pre>")
+
+    body = "\n".join(out)
+    doc_title = html.escape(title or "Document")
+    result = _TEMPLATE.format(title=doc_title, body=body)
+
+    p = Path(output_path)
+    p.write_text(result, encoding="utf-8")
+    return p
+
+
+def _inline(text: str) -> str:
+    """Process inline markdown: **bold**, `code`, and escape HTML."""
+    import re
+
+    # Escape HTML first, then apply markdown formatting
+    text = html.escape(text)
+    # Bold
+    text = re.sub(r"\*\*(.+?)\*\*", r"<strong>\1</strong>", text)
+    # Code spans
+    text = re.sub(r"`([^`]+)`", r"<code>\1</code>", text)
+    return text

dd_format-0.1.0/dd_format/pdf_writer.py

@@ -0,0 +1,85 @@
+"""Convert markdown text to a PDF file using fpdf2."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+
+def markdown_to_pdf(md_text: str, output_path: str, title: str = "") -> Path:
+    """Write *md_text* (simple markdown) to a PDF at *output_path*.
+
+    Supports: headings (# / ## / ###), bullet lists (- / *),
+    fenced code blocks, and plain paragraphs.
+
+    Parameters
+    ----------
+    md_text : str
+        Markdown-formatted text.
+    output_path : str
+        Destination file path.
+    title : str, optional
+        Document title rendered at the top.
+
+    Returns
+    -------
+    Path
+        The output file path.
+    """
+    from fpdf import FPDF  # type: ignore
+
+    pdf = FPDF()
+    pdf.set_auto_page_break(auto=True, margin=15)
+    pdf.add_page()
+    pdf.set_font("Helvetica", size=11)
+
+    if title:
+        pdf.set_font("Helvetica", "B", 18)
+        pdf.cell(0, 12, title, new_x="LMARGIN", new_y="NEXT")
+        pdf.ln(4)
+
+    in_code_block = False
+
+    def _write_block(text: str, h: float = 6) -> None:
+        """Write a multi_cell block, resetting x to left margin afterward."""
+        pdf.set_x(pdf.l_margin)
+        w = pdf.w - pdf.l_margin - pdf.r_margin
+        pdf.multi_cell(w, h, text)
+
+    for line in md_text.split("\n"):
+        stripped = line.strip()
+
+        # Fenced code blocks
+        if stripped.startswith("```"):
+            in_code_block = not in_code_block
+            continue
+        if in_code_block:
+            pdf.set_font("Courier", size=9)
+            _write_block(line, 5)
+            pdf.set_font("Helvetica", size=11)
+            continue
+
+        if not stripped:
+            pdf.ln(4)
+            continue
+
+        # Headings
+        if stripped.startswith("### "):
+            pdf.set_font("Helvetica", "B", 13)
+            pdf.cell(0, 8, stripped[4:], new_x="LMARGIN", new_y="NEXT")
+            pdf.set_font("Helvetica", size=11)
+        elif stripped.startswith("## "):
+            pdf.set_font("Helvetica", "B", 15)
+            pdf.cell(0, 10, stripped[3:], new_x="LMARGIN", new_y="NEXT")
+            pdf.set_font("Helvetica", size=11)
+        elif stripped.startswith("# "):
+            pdf.set_font("Helvetica", "B", 17)
+            pdf.cell(0, 12, stripped[2:], new_x="LMARGIN", new_y="NEXT")
+            pdf.set_font("Helvetica", size=11)
+        elif stripped.startswith("- ") or stripped.startswith("* "):
+            _write_block(f"    - {stripped[2:]}")
+        else:
+            _write_block(stripped)
+
+    out = Path(output_path)
+    pdf.output(str(out))
+    return out

dd_format-0.1.0/dd_format.egg-info/PKG-INFO

@@ -0,0 +1,22 @@
+Metadata-Version: 2.4
+Name: dd-format
+Version: 0.1.0
+Summary: Abstraction layer for formatting documents from markdown to HTML, PDF, and DOCX.
+Author-email: Digital Duck & Dog Team <info@digitalduck.org>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/digital-duck/dd-format
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: fpdf2>=2.7
+Requires-Dist: click>=8.0
+Provides-Extra: docx
+Requires-Dist: python-docx>=1.0; extra == "docx"
+Provides-Extra: all
+Requires-Dist: python-docx>=1.0; extra == "all"
+Dynamic: license-file
+
+# dd-format
+Abstraction layer for formatting document from markdown to others such as html, pdf

dd_format-0.1.0/dd_format.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+README.md
+pyproject.toml
+dd_format/__init__.py
+dd_format/cli.py
+dd_format/docx_writer.py
+dd_format/html_writer.py
+dd_format/pdf_writer.py
+dd_format.egg-info/PKG-INFO
+dd_format.egg-info/SOURCES.txt
+dd_format.egg-info/dependency_links.txt
+dd_format.egg-info/entry_points.txt
+dd_format.egg-info/requires.txt
+dd_format.egg-info/top_level.txt
+tests/test_format.py

dd_format-0.1.0/dd_format.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

dd_format-0.1.0/dd_format.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+dd-format = dd_format.cli:main

dd_format-0.1.0/dd_format.egg-info/requires.txt

@@ -0,0 +1,8 @@
+fpdf2>=2.7
+click>=8.0
+
+[all]
+python-docx>=1.0
+
+[docx]
+python-docx>=1.0

dd_format-0.1.0/dd_format.egg-info/top_level.txt

@@ -0,0 +1 @@
+dd_format

dd_format-0.1.0/pyproject.toml

@@ -0,0 +1,39 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "dd-format"
+version = "0.1.0"
+authors = [
+  { name="Digital Duck & Dog Team", email="info@digitalduck.org" },
+]
+description = "Abstraction layer for formatting documents from markdown to HTML, PDF, and DOCX."
+readme = "README.md"
+requires-python = ">=3.9"
+license = "MIT"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "fpdf2>=2.7",
+    "click>=8.0",
+]
+
+[project.optional-dependencies]
+docx = ["python-docx>=1.0"]
+all  = ["python-docx>=1.0"]
+
+[project.urls]
+"Homepage" = "https://github.com/digital-duck/dd-format"
+
+[project.scripts]
+dd-format = "dd_format.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["dd_format*"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

dd_format-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

dd_format-0.1.0/tests/test_format.py

@@ -0,0 +1,67 @@
+"""Basic tests for dd-format writers."""
+
+import os
+import tempfile
+from pathlib import Path
+
+from dd_format.pdf_writer import markdown_to_pdf
+from dd_format.html_writer import markdown_to_html
+
+SAMPLE_MD = """\
+# Test Document
+
+## Section One
+
+This is a **bold** paragraph with `inline code`.
+
+- Item one
+- Item two
+
+### Subsection
+
+```
+code block here
+```
+
+---
+
+Regular paragraph.
+"""
+
+
+def test_markdown_to_pdf():
+    fd, path = tempfile.mkstemp(suffix=".pdf")
+    os.close(fd)
+    try:
+        out = markdown_to_pdf(SAMPLE_MD, path, title="Test")
+        assert out.exists()
+        assert out.stat().st_size > 0
+    finally:
+        Path(path).unlink(missing_ok=True)
+
+
+def test_markdown_to_html():
+    fd, path = tempfile.mkstemp(suffix=".html")
+    os.close(fd)
+    try:
+        out = markdown_to_html(SAMPLE_MD, path, title="Test")
+        assert out.exists()
+        content = out.read_text()
+        assert "<h1>" in content
+        assert "<strong>bold</strong>" in content
+        assert "<code>inline code</code>" in content
+        assert "<li>" in content
+        assert "<pre>" in content
+    finally:
+        Path(path).unlink(missing_ok=True)
+
+
+def test_html_no_title():
+    fd, path = tempfile.mkstemp(suffix=".html")
+    os.close(fd)
+    try:
+        out = markdown_to_html("# Hello", path)
+        content = out.read_text()
+        assert "<title>Document</title>" in content
+    finally:
+        Path(path).unlink(missing_ok=True)