refactor: restructure mytoolkit with new subcommands and md-to-pdf improvements

- Add new subcommands: convert, preflight, server, templates, webpage
- Migrate config from bin/config.json to ~/.config/mytoolkit
- Fix expand_bookmarks to modify writer objects instead of reader
- Improve md_to_pdf with CJK bookmark support
- Update README and project metadata
This commit is contained in:
Zhengshou Lai
2026-05-04 17:19:32 +08:00
parent 38328c28d0
commit 3e4cf618a8
20 changed files with 1846 additions and 214 deletions
+206
View File
@@ -0,0 +1,206 @@
"""Universal format conversion."""
from pathlib import Path
import click
from pypdf import PdfReader, PdfWriter
from PIL import Image
from bin.md_to_pdf import build_pdf
from bin import templates_registry
from bin.utils import handle_errors, run_command
@click.command("convert")
@click.argument("inputs", nargs=-1, required=True)
@click.option("-o", "--output", required=True, help="Output file path")
@click.option(
"-t",
"--template",
type=click.Choice(["default", "cv", "textbook", "manual", "review"]),
default="default",
help="Template for md→pdf / md→docx",
)
@click.option(
"-q",
"--quality",
type=click.Choice(["screen", "ebook", "printer", "prepress"]),
default="screen",
help="PDF compression quality",
)
@click.option("-d", "--density", default="300", help="DPI for PDF→TIFF")
@click.option("--reference-doc", help="Reference docx template for md→docx")
@click.option(
"--bookmark-depth",
type=int,
default=1,
help="PDF bookmark expansion depth (md→pdf only). 1=top-level only, 2=expand to second level, etc.",
)
@click.option("--dry-run", "-n", is_flag=True, help="Show what would be done")
@handle_errors
def convert_cmd(inputs, output, template, quality, density, reference_doc, bookmark_depth, dry_run):
"""Universal format conversion. Auto-detects from file extensions.
\b
Examples:
mytoolkit convert doc.md -o doc.pdf
mytoolkit convert doc.md -o doc.pdf -t cv
mytoolkit convert doc.md -o doc.docx
mytoolkit convert doc.md -o doc.docx -t review
mytoolkit convert *.jpg -o album.pdf
mytoolkit convert fig.eps -o fig.pdf
mytoolkit convert scan.tiff -o scan.pdf
mytoolkit convert scan.pdf -o scan.tiff
mytoolkit convert video.avi -o video.mp4
"""
out_path = Path(output)
out_ext = out_path.suffix.lower()
# Resolve input globs
input_paths = []
for pattern in inputs:
p = Path(pattern)
if p.exists():
input_paths.append(p)
else:
# Try glob
matches = list(Path(".").glob(pattern))
input_paths.extend(sorted(matches))
if not input_paths:
click.secho("No input files found", fg="red", err=True)
raise SystemExit(1)
# --- pdf → pdf (compress) ---
if len(input_paths) == 1 and input_paths[0].suffix.lower() == ".pdf" and out_ext == ".pdf":
if dry_run:
click.echo(f"Would compress {input_paths[0]} to {output} (quality={quality})")
return
run_command(
[
"gs",
"-sDEVICE=pdfwrite",
"-dNOPAUSE",
"-dQUIET",
"-dBATCH",
f"-dPDFSETTINGS=/{quality}",
"-dCompatibilityLevel=1.4",
f"-sOutputFile={out_path}",
str(input_paths[0]),
],
check=True,
)
click.secho(f"Compressed PDF: {output}", fg="green")
return
# --- md → docx ---
if all(p.suffix.lower() == ".md" for p in input_paths) and out_ext == ".docx":
ref_doc = reference_doc
if not ref_doc and template != "default":
ref_path = templates_registry.get_md_to_docx_root() / template / "template.docx"
if ref_path.exists():
ref_doc = str(ref_path)
else:
click.secho(f"Docx template not found for '{template}': {ref_path}", fg="red", err=True)
raise SystemExit(1)
if dry_run:
msg = f"Would convert {len(input_paths)} markdown file(s) to {output}"
if ref_doc:
msg += f" (template={ref_doc})"
click.echo(msg)
return
cmd = ["pandoc"] + [str(p) for p in input_paths] + ["-o", str(out_path)]
if ref_doc:
cmd.extend(["--reference-doc", ref_doc])
run_command(cmd, check=True)
click.secho(f"Word document generated: {output}", fg="green")
return
# --- md → pdf ---
if all(p.suffix.lower() == ".md" for p in input_paths) and out_ext == ".pdf":
if template == "review":
click.secho("Template 'review' is only available for md→docx", fg="red", err=True)
raise SystemExit(1)
if dry_run:
click.echo(f"Would convert {len(input_paths)} markdown file(s) to {output}")
return
build_pdf(template, input_paths, out_path, bookmark_depth=bookmark_depth)
click.secho(f"PDF generated: {output}", fg="green")
return
# --- images → pdf ---
img_exts = (".jpg", ".jpeg", ".png", ".tif", ".tiff")
if all(p.suffix.lower() in img_exts for p in input_paths) and out_ext == ".pdf":
if dry_run:
click.echo(f"Would convert {len(input_paths)} image(s) to {output}")
return
_images_to_pdf(input_paths, out_path)
click.secho(f"PDF generated: {output}", fg="green")
return
# --- eps → pdf ---
if len(input_paths) == 1 and input_paths[0].suffix.lower() in (".eps", ".ps") and out_ext == ".pdf":
if dry_run:
click.echo(f"Would convert {input_paths[0]} to {output}")
return
run_command(["epstopdf", str(input_paths[0]), "--outfile", str(out_path)], check=True)
click.secho(f"PDF generated: {output}", fg="green")
return
# --- pdf → tiff ---
if len(input_paths) == 1 and input_paths[0].suffix.lower() == ".pdf" and out_ext in (".tiff", ".tif"):
if dry_run:
click.echo(f"Would convert {input_paths[0]} to {output}")
return
run_command(
["convert", "-density", density, str(input_paths[0]), "-compress", "zip", str(out_path)],
check=False,
)
click.secho(f"TIFF generated: {output}", fg="green")
return
# --- avi → mp4 ---
if len(input_paths) == 1 and input_paths[0].suffix.lower() == ".avi" and out_ext == ".mp4":
if dry_run:
click.echo(f"Would convert {input_paths[0]} to {output}")
return
run_command(
["ffmpeg", "-i", str(input_paths[0]), "-c:v", "libx264", "-c:a", "aac", str(out_path)],
check=False,
)
click.secho(f"MP4 generated: {output}", fg="green")
return
# --- bib → md ---
if len(input_paths) == 1 and input_paths[0].suffix.lower() == ".bib" and out_ext == ".md":
if dry_run:
click.echo(f"Would convert {input_paths[0]} to {output}")
return
content = input_paths[0].read_text()
md_content = f"# Bibliography\n\n```bibtex\n{content}\n```\n"
out_path.write_text(md_content)
click.secho(f"Markdown generated: {output}", fg="green")
return
click.secho(
f"Unsupported conversion: {[p.suffix for p in input_paths]}{out_ext}",
fg="red",
err=True,
)
raise SystemExit(1)
def _images_to_pdf(images: list[Path], output: Path) -> None:
"""Merge images into a single PDF."""
writer = PdfWriter()
for img_path in images:
img = Image.open(img_path)
if img.mode in ("RGBA", "P"):
img = img.convert("RGB")
temp_pdf = img_path.with_suffix(".temp.pdf")
img.save(temp_pdf, "PDF", resolution=150.0)
reader = PdfReader(str(temp_pdf))
writer.add_page(reader.pages[0])
temp_pdf.unlink()
with open(output, "wb") as f:
writer.write(f)