from __future__ import annotations import bisect from pipeline_common import * from capture_format_v2 import CaptureFile, RawChunk, iter_contiguous_segments _SPAN_CACHE: dict[int, tuple[list[RawChunk], list[int]]] = {} def _chunk_starts(chunks: list[RawChunk]) -> list[int]: key = id(chunks) cached = _SPAN_CACHE.get(key) if cached is not None and cached[0] is chunks: return cached[1] starts = [] cursor = 0 for chunk in chunks: starts.append(cursor) cursor += len(chunk.raw) _SPAN_CACHE[key] = (chunks, starts) return starts def source_for_span(chunks: list[RawChunk], start: int, end: int, segment_id: int) -> dict: starts = _chunk_starts(chunks) start_index = max(0, min(len(chunks) - 1, bisect.bisect_right(starts, start) - 1)) end_index = max(start_index, min(len(chunks) - 1, bisect.bisect_left(starts, end) - 1)) start_chunk = chunks[start_index] end_chunk = chunks[end_index] return { "source_segment_id": segment_id, "source_chunk_sequence_first": start_chunk.sequence, "source_chunk_sequence_last": end_chunk.sequence, "source_raw_file_offset": start_chunk.raw_file_offset + (start - starts[start_index]), "source_raw_byte_length": end - start, "host_receive_utc_ns": ticks_to_unix_ns(end_chunk.receive_utc_ticks), "host_receive_monotonic_ticks": end_chunk.receive_monotonic_ticks, } def parse_rtk_capture(capture: CaptureFile) -> list[dict]: rows = [] for segment_id, chunks in iter_contiguous_segments(capture.chunks): stream = b"".join(chunk.raw for chunk in chunks) cursor = 0 while cursor < len(stream): newline = stream.find(b"\n", cursor) if newline < 0: break end = newline + 1 raw_line = stream[cursor:end].rstrip(b"\r\n") start = cursor cursor = end if not raw_line: continue line = raw_line.decode("ascii", "replace") row = {"type": "UNKNOWN", "raw_line": line, "checksum_valid": parse_checksum(line)} row.update(source_for_span(chunks, start, end, segment_id)) try: if line.startswith("$GNGGA") or line.startswith("$GPGGA"): row.update(parse_gga(line)) elif line.startswith("#UNIHEADINGA"): row.update(parse_heading(line)) except ValueError as ex: row["parse_error"] = str(ex) rows.append(row) return rows def parse_imu_capture(capture: CaptureFile) -> list[dict]: rows = [] for segment_id, chunks in iter_contiguous_segments(capture.chunks): stream = b"".join(chunk.raw for chunk in chunks) cursor = 0 while True: start = stream.find(b"\x5a\xa5", cursor) if start < 0 or start + 6 > len(stream): break payload_length = int.from_bytes(stream[start + 2:start + 4], "little") frame_length = 6 + payload_length if payload_length <= 0 or payload_length > 512: cursor = start + 1 continue if start + frame_length > len(stream): break frame = stream[start:start + frame_length] expected = int.from_bytes(frame[4:6], "little") actual = crc16_hi13(frame[:4] + frame[6:]) end = start + frame_length row = { "type": "HI13", "tag": frame[6], "frame_length": frame_length, "crc_valid": expected == actual, "raw_frame_hex": frame.hex(), } row.update(source_for_span(chunks, start, end, segment_id)) if row["crc_valid"]: try: row.update(decode_hi91(frame) if frame[6] == 0x91 else decode_hi92(frame) if frame[6] == 0x92 else {}) except (IndexError, struct.error, ValueError) as ex: row["parse_error"] = str(ex) rows.append(row) cursor = end return rows