151 lines
7.3 KiB
Python
151 lines
7.3 KiB
Python
|
|
"""Immutable multi-document composition and transactional publication."""
|
|||
|
|
from __future__ import annotations
|
|||
|
|
import hashlib
|
|||
|
|
import html
|
|||
|
|
import re
|
|||
|
|
import shutil
|
|||
|
|
from dataclasses import dataclass
|
|||
|
|
from pathlib import Path
|
|||
|
|
from urllib.parse import unquote, urlsplit, urlunsplit
|
|||
|
|
|
|||
|
|
from .document_resources import analyze_document, apply_source_edits, resolve_local_reference, SourceEdit
|
|||
|
|
from .doc_check import document_anchors
|
|||
|
|
from .export_jobs import check_cancelled
|
|||
|
|
from .file_versions import atomic_write
|
|||
|
|
from .markdown_utils import Heading
|
|||
|
|
|
|||
|
|
|
|||
|
|
@dataclass(frozen=True)
|
|||
|
|
class BatchDocument:
|
|||
|
|
path: Path
|
|||
|
|
source: str
|
|||
|
|
|
|||
|
|
|
|||
|
|
@dataclass
|
|||
|
|
class CombinedDocument:
|
|||
|
|
word_source: str
|
|||
|
|
html_body: str
|
|||
|
|
headings: list[Heading]
|
|||
|
|
|
|||
|
|
|
|||
|
|
def combine_documents(documents: list[BatchDocument], renderer, cancel=None) -> CombinedDocument:
|
|||
|
|
documents = [BatchDocument(d.path.resolve(), d.source) for d in documents]
|
|||
|
|
mappings, analyses = {}, {}
|
|||
|
|
for index, document in enumerate(documents, 1):
|
|||
|
|
check_cancelled(cancel)
|
|||
|
|
analysis = analyses[document.path] = analyze_document(document.source)
|
|||
|
|
mapping = {"": f"mdh{index}"}
|
|||
|
|
for number, token in enumerate(t for t in analysis.tokens if t.type == "heading_open"):
|
|||
|
|
if token.attrGet("id"):
|
|||
|
|
mapping[token.attrGet("id")] = f"mdh{index}h{number + 1}"
|
|||
|
|
for number, anchor in enumerate(sorted(document_anchors(analysis) - mapping.keys()), 1):
|
|||
|
|
mapping[anchor] = f"mdh{index}a{number}"
|
|||
|
|
mappings[document.path] = mapping
|
|||
|
|
word, bodies, headings = [], [], []
|
|||
|
|
for document in documents:
|
|||
|
|
check_cancelled(cancel)
|
|||
|
|
mapping = mappings[document.path]
|
|||
|
|
edits, word_resource_edits = [], []
|
|||
|
|
for reference in analyses[document.path].references:
|
|||
|
|
parsed = urlsplit(reference.url)
|
|||
|
|
target = resolve_local_reference(document.path, reference.url)
|
|||
|
|
local = parsed.scheme in {"", "file"} and (not parsed.netloc or parsed.scheme == "file")
|
|||
|
|
if local and not parsed.path:
|
|||
|
|
target = document.path
|
|||
|
|
new_url = reference.url
|
|||
|
|
if not reference.image and target in mappings and unquote(parsed.fragment) in mappings[target]:
|
|||
|
|
new_url = "#" + mappings[target][unquote(parsed.fragment)]
|
|||
|
|
elif target is not None and parsed.path:
|
|||
|
|
new_url = urlunsplit(urlsplit(target.as_uri())._replace(query=parsed.query, fragment=parsed.fragment))
|
|||
|
|
# Expand reference-style links before joining documents with identical definitions.
|
|||
|
|
if new_url != reference.url or reference.syntax == "reference":
|
|||
|
|
edits.append(reference.edit_url(new_url))
|
|||
|
|
word_url = new_url
|
|||
|
|
if reference.image and target is not None:
|
|||
|
|
# Pandoc does not decode file-URI escapes on Windows. Angle-bracket
|
|||
|
|
# destinations preserve literal Unicode, spaces and parentheses.
|
|||
|
|
word_url = target.as_posix()
|
|||
|
|
if reference.syntax != 'html' and document.source[reference.start - 1:reference.start] != '<':
|
|||
|
|
word_url = '<' + word_url + '>'
|
|||
|
|
word_resource_edits.append(reference.edit_url(word_url))
|
|||
|
|
source = apply_source_edits(document.source, edits)
|
|||
|
|
word_source = apply_source_edits(document.source, word_resource_edits)
|
|||
|
|
env = {"path": str(document.path), "headings": []}
|
|||
|
|
tokens = renderer.markdown.parse(source, env)
|
|||
|
|
offsets = [0]
|
|||
|
|
for line in word_source.splitlines(keepends=True): offsets.append(offsets[-1] + len(line))
|
|||
|
|
word_tokens = renderer.markdown.parse(word_source, {})
|
|||
|
|
word_heading_texts = iter(word_tokens[i + 1].content for i, token in enumerate(word_tokens) if token.type == 'heading_open')
|
|||
|
|
word_edits = []
|
|||
|
|
heading_number = 0
|
|||
|
|
for index, token in enumerate(tokens):
|
|||
|
|
if token.type == "heading_open":
|
|||
|
|
heading_number += 1
|
|||
|
|
anchor = f"{mapping['']}h{heading_number}"
|
|||
|
|
token.attrSet("id", anchor)
|
|||
|
|
level = min(6, int(token.tag[1:]) + 1)
|
|||
|
|
token.tag = f"h{level}"
|
|||
|
|
content = tokens[index + 1].content
|
|||
|
|
headings.append(Heading(level, content, anchor))
|
|||
|
|
start, end = token.map
|
|||
|
|
prefix = re.match(r"[ \t]*(?:>[ \t]*)*", word_source[offsets[start]:]).group()
|
|||
|
|
word_edits.append(SourceEdit(offsets[start], offsets[end], f"{prefix}{'#' * level} {next(word_heading_texts)} {{#{anchor}}}\n"))
|
|||
|
|
elif token.type == "heading_close":
|
|||
|
|
token.tag = f"h{min(6, int(token.tag[1:]) + 1)}"
|
|||
|
|
for raw in [token, *(token.children or [])]:
|
|||
|
|
if raw.type in {"html_inline", "html_block"}:
|
|||
|
|
raw.content = re.sub(r'\b(id|name)\s*=\s*([\"\x27])([^\"\x27]+)\2',
|
|||
|
|
lambda m: f'{m[1]}={m[2]}{mapping.get(html.unescape(m[3]), m[3])}{m[2]}', raw.content)
|
|||
|
|
title = document.path.stem
|
|||
|
|
chapter = Heading(1, title, mapping[""])
|
|||
|
|
first = len(headings) - sum(1 for token in tokens if token.type == "heading_open")
|
|||
|
|
headings.insert(first, chapter)
|
|||
|
|
safe_title = re.sub(r'([\\`*_{}\[\]<>#])', r'\\\1', title)
|
|||
|
|
word.append(f"# {safe_title} {{#{mapping['']}}}\n\n" + apply_source_edits(word_source, word_edits))
|
|||
|
|
bodies.append(f'<section class="batch-chapter"><h1 id="{mapping[""]}">{html.escape(title)}</h1>' +
|
|||
|
|
renderer.markdown.renderer.render(tokens, renderer.markdown.options, env) + '</section>')
|
|||
|
|
return CombinedDocument("\n\n".join(word), "\n".join(bodies), headings)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def fingerprint(path: Path):
|
|||
|
|
if not path.exists(): return None
|
|||
|
|
digest = hashlib.sha256()
|
|||
|
|
with path.open('rb') as stream:
|
|||
|
|
for block in iter(lambda: stream.read(1024 * 1024), b''): digest.update(block)
|
|||
|
|
return digest.hexdigest()
|
|||
|
|
|
|||
|
|
|
|||
|
|
def publish_outputs(outputs: dict[Path, Path], expected: dict, backup: Path, cancel=None):
|
|||
|
|
"""Publish only after all conversions succeed; restore earlier outputs on any failure."""
|
|||
|
|
check_cancelled(cancel)
|
|||
|
|
originals = {}
|
|||
|
|
for index, destination in enumerate(outputs):
|
|||
|
|
check_cancelled(cancel)
|
|||
|
|
if fingerprint(destination) != expected[destination]:
|
|||
|
|
raise OSError(f"导出期间目标文件发生变化,已停止替换:{destination}")
|
|||
|
|
if destination.exists():
|
|||
|
|
copy = backup / f"previous-{index}"
|
|||
|
|
shutil.copyfile(destination, copy)
|
|||
|
|
originals[destination] = copy
|
|||
|
|
else:
|
|||
|
|
originals[destination] = None
|
|||
|
|
written = []
|
|||
|
|
try:
|
|||
|
|
for destination, staged in outputs.items():
|
|||
|
|
check_cancelled(cancel)
|
|||
|
|
atomic_write(destination, staged.read_bytes())
|
|||
|
|
written.append(destination)
|
|||
|
|
check_cancelled(cancel)
|
|||
|
|
except Exception as error:
|
|||
|
|
failures = []
|
|||
|
|
for destination in reversed(written):
|
|||
|
|
try:
|
|||
|
|
if originals[destination] is None: destination.unlink(missing_ok=True)
|
|||
|
|
else: atomic_write(destination, originals[destination].read_bytes())
|
|||
|
|
except OSError as rollback:
|
|||
|
|
failures.append(str(rollback))
|
|||
|
|
if failures:
|
|||
|
|
raise OSError(f"输出恢复失败,备份位于 {backup}:{';'.join(failures)}") from error
|
|||
|
|
raise
|
|||
|
|
return list(outputs)
|