New mdsplit version.
This commit is contained in:
parent
17c72ba06e
commit
a9f92aa16a
1 changed files with 146 additions and 53 deletions
197
prog/mdsplit.py
Normal file → Executable file
197
prog/mdsplit.py
Normal file → Executable file
|
|
@ -7,7 +7,9 @@
|
|||
# ///
|
||||
|
||||
import argparse
|
||||
import re
|
||||
from collections import defaultdict
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
from pathlib import Path
|
||||
|
||||
from slugify import slugify
|
||||
|
|
@ -18,6 +20,15 @@ parser = argparse.ArgumentParser(
|
|||
|
||||
parser.add_argument("mdfile", help="The org file", type=Path)
|
||||
parser.add_argument("mdbook", help="mdbook root diretory", type=Path)
|
||||
parser.add_argument(
|
||||
"-d",
|
||||
"--max-depth",
|
||||
help="Max depth for headings",
|
||||
type=int,
|
||||
default=1,
|
||||
dest="depth",
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if not args.mdfile.is_file():
|
||||
|
|
@ -28,70 +39,152 @@ if not args.mdbook.is_dir():
|
|||
"`mdbook` must be a root mdbook directory initialiezd with `mdbook init`"
|
||||
)
|
||||
|
||||
with open(args.mdfile) as f:
|
||||
data = f.read()
|
||||
if args.depth < 1:
|
||||
raise ValueError("`depth` must be >= 1")
|
||||
|
||||
data = data.split("```")
|
||||
for i, d in enumerate(data[:]):
|
||||
if i % 2 == 0:
|
||||
continue
|
||||
data[i] = "```" + re.sub(r"^(#+) ", r"\1", data[i], flags=re.MULTILINE) + "```"
|
||||
|
||||
data = "".join(data).splitlines(keepends=True)
|
||||
@dataclass
|
||||
class ExtraTitle:
|
||||
level: int
|
||||
title: str
|
||||
|
||||
output = Path(parser.mdbook) / "src"
|
||||
|
||||
splitn = [idx for (idx, d) in enumerate(data) if d.startswith("# ")]
|
||||
splitn = list(zip(splitn[:], splitn[1:] + [None]))
|
||||
class DType(Enum):
|
||||
CODE = 1
|
||||
BODY = 2
|
||||
TITLE = 3
|
||||
|
||||
summaries = []
|
||||
for idx, (start, end) in enumerate(splitn[:], start=1):
|
||||
d = data[start:end]
|
||||
title = d[0][2:].rstrip()
|
||||
num = f"{idx:02d}"
|
||||
basename = f"{num}.{slugify(title)}.md"
|
||||
summary = {"title": title, "basename": basename, "subs": []}
|
||||
|
||||
subcontent = d[1:]
|
||||
@dataclass
|
||||
class Content:
|
||||
content: str
|
||||
dtype: DType
|
||||
extra: None | ExtraTitle = None
|
||||
|
||||
name = d[0]
|
||||
|
||||
splitn = [idx for (idx, d) in enumerate(subcontent) if d.startswith("## ")]
|
||||
@dataclass
|
||||
class Config:
|
||||
inside_code: bool
|
||||
|
||||
with open(output / basename, "w") as f:
|
||||
print(f"# {title}", file=f)
|
||||
|
||||
if splitn:
|
||||
d = "".join(subcontent[: splitn[0]])
|
||||
print(d, file=f)
|
||||
else:
|
||||
print("".join(subcontent), file=f)
|
||||
OUTPUT_DIR: Path = Path("book/src")
|
||||
|
||||
splitn = list(zip(splitn[:], splitn[1:] + [None]))
|
||||
MAX_LEVEL: int = args.depth
|
||||
|
||||
for jdx, (start, end) in enumerate(splitn[:], start=1):
|
||||
d = subcontent[start:end]
|
||||
title = d[0][2:].rstrip()
|
||||
basename = f"{idx:02d}.{jdx:02d}.{slugify(title)}.md"
|
||||
summary["subs"].append(
|
||||
{
|
||||
"title": title,
|
||||
"basename": basename,
|
||||
}
|
||||
with open(args.mdfile, "r") as f:
|
||||
print(args.mdfile)
|
||||
mdlines: list[str] = f.readlines()
|
||||
|
||||
|
||||
parsed_lines: list[Content] = []
|
||||
|
||||
config: Config = Config(inside_code=False)
|
||||
|
||||
|
||||
def if_parse_begin_code(
|
||||
line: str,
|
||||
config: Config,
|
||||
parsed_lines: list[Content],
|
||||
):
|
||||
if line.startswith("```"):
|
||||
config.inside_code = True
|
||||
parsed_lines.append(Content(content=line, dtype=DType.CODE))
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
|
||||
def if_parse_title(line: str, config: dict[str, bool], parsed_lines: list[Content]):
|
||||
if line.startswith("#"):
|
||||
title = " ".join(line.split(" ")[1:])
|
||||
level = len(line.split(" ")[0])
|
||||
parsed_lines.append(
|
||||
Content(
|
||||
content=line,
|
||||
dtype=DType.TITLE,
|
||||
extra=ExtraTitle(level=level, title=title),
|
||||
)
|
||||
)
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
|
||||
def parse_code(line, config, parse_lines):
|
||||
parsed_lines.append(Content(content=line, dtype=DType.CODE))
|
||||
return True
|
||||
|
||||
|
||||
def parse_content(line, config, parse_lines):
|
||||
parsed_lines.append(Content(content=line, dtype=DType.BODY))
|
||||
return True
|
||||
|
||||
|
||||
def if_parse_end_code(line, config, parse_lines):
|
||||
if line.startswith("```"):
|
||||
parsed_lines.append(Content(content=line, dtype=DType.CODE))
|
||||
config.inside_code = False
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
|
||||
def do_parse_nocode(line, config, parse_lines):
|
||||
return any(
|
||||
f(line, config, parse_lines)
|
||||
for f in (
|
||||
if_parse_begin_code,
|
||||
if_parse_title,
|
||||
parse_content,
|
||||
)
|
||||
)
|
||||
|
||||
with open(output / basename, "w") as f:
|
||||
print("".join(d), file=f)
|
||||
|
||||
summaries.append(summary)
|
||||
for line in mdlines:
|
||||
if not config.inside_code:
|
||||
do_parse_nocode(line, config, parsed_lines)
|
||||
else:
|
||||
any(f(line, config, parsed_lines) for f in (if_parse_end_code, parse_code))
|
||||
|
||||
with open(output / "SUMMARY.md", "w") as f:
|
||||
print("# SUMMARY", file=f)
|
||||
for item in summaries:
|
||||
title = item["title"]
|
||||
basename = item["basename"]
|
||||
print(f"- [{title}](./{basename})", file=f)
|
||||
for sub in item["subs"]:
|
||||
title = sub["title"]
|
||||
basename = sub["basename"]
|
||||
print(f" - [{title}](./{basename})", file=f)
|
||||
|
||||
filepath_suffix = "_prelude.md"
|
||||
filepath = OUTPUT_DIR / ("0" + filepath_suffix)
|
||||
|
||||
num_titles = defaultdict(int)
|
||||
summaries = []
|
||||
|
||||
for parsed_line in parsed_lines:
|
||||
if parsed_line.dtype == DType.TITLE and parsed_line.extra.level <= MAX_LEVEL:
|
||||
level = parsed_line.extra.level
|
||||
|
||||
num_titles[level] += 1
|
||||
|
||||
num_title = num_titles[level]
|
||||
title = parsed_line.extra.title.strip()
|
||||
slug_title = slugify(title)
|
||||
filepath_suffix = f"_{slug_title}.md"
|
||||
|
||||
# reset key of num_titles if key > level
|
||||
keys = {k for k in num_titles.keys() if k > level}
|
||||
for key in keys:
|
||||
del num_titles[key]
|
||||
|
||||
filepath_prefix = ".".join(
|
||||
f"{i:02d}" for _, i in sorted(num_titles.items(), key=lambda x: x[0])
|
||||
)
|
||||
|
||||
basename = filepath_prefix + filepath_suffix
|
||||
filepath = OUTPUT_DIR / basename
|
||||
|
||||
summaries.append((level, title, basename))
|
||||
|
||||
with open(filepath, "a") as f:
|
||||
f.write(parsed_line.content)
|
||||
|
||||
else:
|
||||
with open(filepath, "a") as f:
|
||||
f.write(parsed_line.content)
|
||||
|
||||
with open(OUTPUT_DIR / "SUMMARY.md", "w") as f:
|
||||
for level, title, basename in summaries:
|
||||
print(level * " ", f"- [{title}](./{basename})", file=f)
|
||||
|
|
|
|||
Loading…
Reference in a new issue