38 lines
1.3 KiB
Python
38 lines
1.3 KiB
Python
|
from __future__ import annotations
|
||
|
|
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
from .records import epoch, parse_line, read_regular
|
||
|
|
|
||
|
|
RESOURCES = "resources"
|
||
|
|
SAMPLES = "samples.jsonl"
|
||
|
|
TOKENS = "tokens.jsonl"
|
||
|
|
HOUR = 3600
|
||
|
|
FILE_LIMIT = 64 << 20
|
||
|
|
|
||
|
|
|
||
|
|
def rows_between(path: Path, begin: float, end: float, width: float) -> list[dict]:
|
||
|
|
try:
|
||
|
|
lines = read_regular(path, FILE_LIMIT).splitlines()
|
||
|
|
except (OSError, ValueError):
|
||
|
|
return []
|
||
|
|
found = []
|
||
|
|
for row in map(parse_line, lines):
|
||
|
|
t = None if row is None else epoch(row.get("t"))
|
||
|
|
if t is not None and begin <= t + width and t <= end:
|
||
|
|
found.append(row)
|
||
|
|
return found
|
||
|
|
|
||
|
|
|
||
|
|
def sampled(folder: Path, span: tuple[float, float]) -> dict:
|
||
|
|
"""Args:
|
||
|
|
folder: the host sampler's directory, mounted read-only.
|
||
|
|
span: (begin, end) of the page's time window in epoch seconds.
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
{"since", "until", "samples", "tokens"}: the rows of samples.jsonl
|
||
|
|
within the span and those of tokens.jsonl whose hour overlaps it, as
|
||
|
|
the host unit wrote them; the hub reads nothing of the host itself.
|
||
|
|
"""
|
||
|
|
begin, end = span
|
||
|
|
return {"since": begin, "until": end, "samples": rows_between(folder / SAMPLES, begin, end, 0), "tokens": rows_between(folder / TOKENS, begin, end, HOUR)}
|