Restructuration de l'application

This commit is contained in:
2026-08-22 13:39:20 +02:00
parent dc25b5fefa
commit b9e9d00e7d
44 changed files with 561 additions and 8675 deletions
+280
View File
@@ -0,0 +1,280 @@
from __future__ import annotations
import argparse
import re
import shutil
from collections.abc import Sequence
from dataclasses import dataclass
from pathlib import Path
from typing import Any
from pypdf import PdfWriter
from copienator import (
CliError,
EvaluationWorkspace,
ExitCode,
atomic_write_json,
evaluation_parser,
execute,
read_json,
workspace_from_args,
)
OPERATORS = ("-x", "->", "x>", "ss", "sx", "xx", "xs")
OPERATOR_PATTERN = re.compile(r"\s+(-x|->|x>|ss|sx|xx|xs)\s+")
COPY_PATTERN = re.compile(r"Copie(\d+)\s+(.+)")
@dataclass(frozen=True, slots=True)
class ManualInstruction:
copy_id: str
old_label: str
operator: str
new_label: str
pipe_first: bool
@property
def should_merge(self) -> bool:
return self.operator.endswith(">")
@property
def should_copy(self) -> bool:
return not self.should_merge and "s" not in self.operator
def build_parser() -> argparse.ArgumentParser:
return evaluation_parser("Apply the instructions from manual_resolutions.txt.")
def parse_instructions(path: Path) -> list[ManualInstruction]:
instructions: list[ManualInstruction] = []
malformed: list[int] = []
for line_number, raw_line in enumerate(
path.read_text(encoding="utf-8").splitlines(), start=1
):
line = raw_line.strip()
if not line or line.startswith("###"):
continue
operator_match = OPERATOR_PATTERN.search(line)
if operator_match is None:
malformed.append(line_number)
continue
left = line[: operator_match.start()].strip()
right = line[operator_match.end() :].strip()
copy_match = COPY_PATTERN.fullmatch(left)
new_label = right.strip("|").strip()
if copy_match is None or not new_label:
malformed.append(line_number)
continue
instructions.append(
ManualInstruction(
copy_id=copy_match.group(1),
old_label=copy_match.group(2).strip(),
operator=operator_match.group(1),
new_label=new_label,
pipe_first=right.startswith("|"),
)
)
if malformed:
lines = ", ".join(str(number) for number in malformed)
raise CliError(f"Malformed manual resolution instruction at line(s): {lines}")
return instructions
def set_suffix_and_clean_error(
results: dict[str, Any],
copy_id: str,
label: str,
suffix: str | None,
new_label_target: str | None = None,
) -> None:
for batch in results.get(label, []):
for item in batch:
if item["id"] != copy_id:
continue
if suffix:
item["result"]["suffix"] = suffix
error = item["result"].get("error", "")
if new_label_target:
if f"wrg-lbl:{new_label_target}?delayed" in error:
item["result"]["error"] = (
f"wrg-lbl-moved-to:{new_label_target}"
)
if f"(delayed){new_label_target}" in error:
item["result"]["error"] = error.replace(
f"(delayed){new_label_target}",
f"(->){new_label_target}",
)
def get_actual_pdf(copies_dir: Path, copy_id: str, label: str) -> Path:
base = copies_dir / f"Copie{copy_id}" / f"{label}.pdf"
for candidate in (
base,
base.with_name(f"{label}_new.pdf"),
base.with_name(f"{label}_old.pdf"),
):
if candidate.exists():
return candidate
return base
def safe_strip_suffix(stem: str) -> str:
if stem.endswith(("_new", "_old")):
return stem[:-4]
return stem
def _validate_pdf_inputs(
instructions: list[ManualInstruction],
initial_paths: dict[tuple[str, str], Path],
) -> None:
missing: set[Path] = set()
for instruction in instructions:
source = initial_paths[(instruction.copy_id, instruction.old_label)]
destination = initial_paths[(instruction.copy_id, instruction.new_label)]
if instruction.should_merge:
if not source.exists():
missing.add(source)
if not destination.exists():
missing.add(destination)
elif instruction.should_copy and not source.exists():
missing.add(source)
if missing:
rendered = ", ".join(str(path) for path in sorted(missing))
raise CliError(f"PDF input(s) required by manual resolutions not found: {rendered}")
def resolve_manual(workspace: EvaluationWorkspace) -> ExitCode:
workspace.require_files("manual_resolutions.txt", "correction.json")
workspace.require_directories("Copies")
loaded = read_json(workspace.correction_file)
if not isinstance(loaded, dict):
raise CliError("correction.json must contain a JSON object")
results: dict[str, Any] = loaded
instructions = parse_instructions(workspace.manual_resolutions_file)
initial_paths: dict[tuple[str, str], Path] = {}
current_paths: dict[tuple[str, str], Path] = {}
for instruction in instructions:
for label in (instruction.old_label, instruction.new_label):
key = (instruction.copy_id, label)
if key not in initial_paths:
path = get_actual_pdf(workspace.copies_dir, *key)
initial_paths[key] = path
current_paths[key] = path
_validate_pdf_inputs(instructions, initial_paths)
files_to_old: set[Path] = set()
temp_files: list[Path] = []
try:
for instruction in instructions:
key_old = (instruction.copy_id, instruction.old_label)
key_new = (instruction.copy_id, instruction.new_label)
source = initial_paths[key_old]
destination = current_paths[key_new]
temp_output = (
workspace.copies_dir
/ f"Copie{instruction.copy_id}"
/ f"temp_{len(temp_files)}.pdf"
)
if instruction.operator.startswith("x"):
files_to_old.add(initial_paths[key_old])
if instruction.operator.endswith("x"):
files_to_old.add(initial_paths[key_new])
if instruction.should_merge:
writer = PdfWriter()
try:
if instruction.pipe_first:
writer.append(source)
writer.append(destination)
else:
writer.append(destination)
writer.append(source)
writer.write(temp_output)
except Exception:
temp_output.unlink(missing_ok=True)
raise
finally:
writer.close()
current_paths[key_new] = temp_output
temp_files.append(temp_output)
files_to_old.add(initial_paths[key_new])
elif instruction.should_copy:
shutil.copy(source, temp_output)
current_paths[key_new] = temp_output
temp_files.append(temp_output)
except Exception:
for temporary in temp_files:
temporary.unlink(missing_ok=True)
raise
for pdf in files_to_old:
if not pdf.exists():
continue
copy_id = pdf.parent.name.removeprefix("Copie")
label = safe_strip_suffix(pdf.stem)
old_name = pdf.with_name(f"{label}_old.pdf")
if pdf != old_name:
old_name.unlink(missing_ok=True)
shutil.move(str(pdf), str(old_name))
set_suffix_and_clean_error(results, copy_id, label, "_old")
for instruction in instructions:
set_suffix_and_clean_error(
results,
instruction.copy_id,
instruction.old_label,
None,
instruction.new_label,
)
refaire_by_copy: dict[str, list[str]] = {}
for (copy_id, label), current_path in current_paths.items():
if not current_path.name.startswith("temp_"):
continue
final_name = workspace.copies_dir / f"Copie{copy_id}" / f"{label}_new.pdf"
final_name.unlink(missing_ok=True)
shutil.move(str(current_path), str(final_name))
set_suffix_and_clean_error(results, copy_id, label, "_new")
labels = refaire_by_copy.setdefault(f"Copie{copy_id}", [])
if label not in labels:
labels.append(label)
used_temps = set(current_paths.values())
for temporary in temp_files:
if temporary not in used_temps:
temporary.unlink(missing_ok=True)
atomic_write_json(workspace.correction_file, results)
refaire_tasks = [[copy_name, labels] for copy_name, labels in refaire_by_copy.items()]
if refaire_tasks:
atomic_write_json(workspace.refaire_file, refaire_tasks)
workspace.manual_resolutions_file.unlink()
print("Manual resolutions successfully applied.")
if refaire_tasks:
print(
f"File {workspace.refaire_file.name} generated. Run "
f'`python -m copienator correct "{workspace.command_argument()}" --refaire` '
"to process updates."
)
else:
print("No new corrections required.")
return ExitCode.SUCCESS
def run(workspace: EvaluationWorkspace) -> ExitCode:
return resolve_manual(workspace)
def main(argv: Sequence[str] | None = None) -> int:
parser = build_parser()
return execute(parser, argv, lambda args: run(workspace_from_args(args)))
if __name__ == "__main__":
raise SystemExit(main())