Files

34 lines
1.5 KiB
Python

import hashlib
import pathlib
import typing
from claude_code.transcript import first_timestamped_line
from transcript_archive.project_key import project_key
# What an outcomes file's name ends with, in place of its transcript copy's .jsonl.
FILE_SUFFIX = ".outcomes.md"
def archive_root(home: pathlib.Path, env: typing.Mapping[str, str]) -> pathlib.Path:
"""Where loop-claude archives every project's chunks."""
return pathlib.Path(env["LOOP_CLAUDE_TRANSCRIPTS"]).expanduser() if env.get("LOOP_CLAUDE_TRANSCRIPTS") else home / ".claude" / "loop-claude-transcripts"
def project_archive(checkout_root: str, home: pathlib.Path, env: typing.Mapping[str, str]) -> pathlib.Path:
return archive_root(home, env) / project_key(checkout_root, home)
def chunk_folder(project_archive: pathlib.Path, transcript: bytes) -> pathlib.Path:
# Each chunk's first timestamped line is its own: a finished chunk's session is deleted, so the next chunk's transcript starts afresh.
return project_archive / hashlib.sha256(first_timestamped_line(transcript)).hexdigest()
def outcomes_of(copy: pathlib.Path) -> pathlib.Path:
"""The outcomes file beside a transcript copy; transcript_of is its inverse."""
return copy.with_suffix(FILE_SUFFIX)
def transcript_of(outcomes: pathlib.Path) -> pathlib.Path:
"""The plain name of the transcript copy an outcomes file sits beside, which text_files.compressed reads whether gzipped or not; outcomes_of is its inverse."""
return outcomes.with_name(outcomes.name.removesuffix(FILE_SUFFIX) + ".jsonl")