cc-transcript 13.0.0__tar.gz → 13.2.0__tar.gz

{cc_transcript-13.0.0 → cc_transcript-13.2.0}/Cargo.lock

@@ -30,6 +30,18 @@ dependencies = [
  "memchr",
 ]
 
+[[package]]
+name = "anes"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4b46cbb362ab8752921c97e041f5e366ee6297bd428a31275b9fcf1e380f7299"
+
+[[package]]
+name = "anstyle"
+version = "1.0.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "940b3a0ca603d1eade50a4846a2afffd5ef57a9feac2c0e2ec2e14f9ead76000"
+
 [[package]]
 name = "autocfg"
 version = "1.5.1"
@@ -60,6 +72,12 @@ version = "1.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e748733b7cbc798e1434b6ac524f0c1ff2ab456fe201501e6497c8417a4fc33"
 
+[[package]]
+name = "cast"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5"
+
 [[package]]
 name = "cc"
 version = "1.2.63"
@@ -75,6 +93,7 @@ name = "cc_transcript_parser"
 version = "0.9.0"
 dependencies = [
  "chrono",
+ "criterion",
  "crossbeam-channel",
  "memchr",
  "num_cpus",
@@ -113,6 +132,58 @@ dependencies = [
  "num-traits",
 ]
 
+[[package]]
+name = "ciborium"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42e69ffd6f0917f5c029256a24d0161db17cea3997d185db0d35926308770f0e"
+dependencies = [
+ "ciborium-io",
+ "ciborium-ll",
+ "serde",
+]
+
+[[package]]
+name = "ciborium-io"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "05afea1e0a06c9be33d539b876f1ce3692f4afea2cb41f740e7743225ed1c757"
+
+[[package]]
+name = "ciborium-ll"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "57663b653d948a338bfb3eeba9bb2fd5fcfaecb9e199e87e1eda4d9e8b240fd9"
+dependencies = [
+ "ciborium-io",
+ "half",
+]
+
+[[package]]
+name = "clap"
+version = "4.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1ddb117e43bbf7dacf0a4190fef4d345b9bad68dfc649cb349e7d17d28428e51"
+dependencies = [
+ "clap_builder",
+]
+
+[[package]]
+name = "clap_builder"
+version = "4.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "714a53001bf66416adb0e2ef5ac857140e7dc3a0c48fb28b2f10762fc4b5069f"
+dependencies = [
+ "anstyle",
+ "clap_lex",
+]
+
+[[package]]
+name = "clap_lex"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9"
+
 [[package]]
 name = "crc32fast"
 version = "1.5.0"
@@ -122,6 +193,40 @@ dependencies = [
  "cfg-if",
 ]
 
+[[package]]
+name = "criterion"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f2b12d017a929603d80db1831cd3a24082f8137ce19c69e6447f54f5fc8d692f"
+dependencies = [
+ "anes",
+ "cast",
+ "ciborium",
+ "clap",
+ "criterion-plot",
+ "is-terminal",
+ "itertools",
+ "num-traits",
+ "once_cell",
+ "oorandom",
+ "regex",
+ "serde",
+ "serde_derive",
+ "serde_json",
+ "tinytemplate",
+ "walkdir",
+]
+
+[[package]]
+name = "criterion-plot"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1"
+dependencies = [
+ "cast",
+ "itertools",
+]
+
 [[package]]
 name = "crossbeam-channel"
 version = "0.5.15"
@@ -156,6 +261,12 @@ version = "0.8.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
 
+[[package]]
+name = "crunchy"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "460fbee9c2c2f33933d720630a6a0bac33ba7053db5344fac858d4b8952d77d5"
+
 [[package]]
 name = "either"
 version = "1.16.0"
@@ -259,6 +370,17 @@ dependencies = [
  "wasip2",
 ]
 
+[[package]]
+name = "half"
+version = "2.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ea2d84b969582b4b1864a92dc5d27cd2b77b622a8d79306834f1be5ba20d84b"
+dependencies = [
+ "cfg-if",
+ "crunchy",
+ "zerocopy",
+]
+
 [[package]]
 name = "hashbrown"
 version = "0.17.1"
@@ -303,6 +425,26 @@ dependencies = [
  "hashbrown",
 ]
 
+[[package]]
+name = "is-terminal"
+version = "0.4.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3640c1c38b8e4e43584d8df18be5fc6b0aa314ce6ebf51b53313d4306cca8e46"
+dependencies = [
+ "hermit-abi",
+ "libc",
+ "windows-sys",
+]
+
+[[package]]
+name = "itertools"
+version = "0.10.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b0fd2260e829bddf4cb6ea802289de2f86d6a7a690192fbe91b3f46e0f2c8473"
+dependencies = [
+ "either",
+]
+
 [[package]]
 name = "itoa"
 version = "1.0.18"
@@ -400,6 +542,12 @@ version = "1.21.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
 
+[[package]]
+name = "oorandom"
+version = "11.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e"
+
 [[package]]
 name = "percent-encoding"
 version = "2.3.2"
@@ -702,6 +850,15 @@ version = "1.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
 
+[[package]]
+name = "same-file"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
+dependencies = [
+ "winapi-util",
+]
+
 [[package]]
 name = "serde"
 version = "1.0.228"
@@ -927,6 +1084,16 @@ dependencies = [
  "syn 2.0.117",
 ]
 
+[[package]]
+name = "tinytemplate"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "be4d6b5f19ff7664e8c98d03e2139cb510db9b0a60b55f8e8709b689d939b6bc"
+dependencies = [
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "tinyvec"
 version = "1.11.0"
@@ -1045,6 +1212,16 @@ version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
 
+[[package]]
+name = "walkdir"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29790946404f91d9c5d06f9874efddea1dc06c5efe94541a7d6863108e3a5e4b"
+dependencies = [
+ "same-file",
+ "winapi-util",
+]
+
 [[package]]
 name = "wasi"
 version = "0.11.1+wasi-snapshot-preview1"
@@ -1114,6 +1291,15 @@ dependencies = [
  "rustls-pki-types",
 ]
 
+[[package]]
+name = "winapi-util"
+version = "0.1.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
+dependencies = [
+ "windows-sys",
+]
+
 [[package]]
 name = "windows-sys"
 version = "0.52.0"

{cc_transcript-13.0.0 → cc_transcript-13.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cc-transcript
-Version: 13.0.0
+Version: 13.2.0
 Classifier: Development Status :: 3 - Alpha
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers

{cc_transcript-13.0.0 → cc_transcript-13.2.0}/cc_transcript/__init__.py

@@ -78,6 +78,7 @@ EXPORTS: dict[str, str] = {
             "Command",
             "CommandLine",
             "CommandLineQuery",
+            "Occurrence",
             "Redirect",
             "command_prefixes",
             "parse_command_line",

{cc_transcript-13.0.0 → cc_transcript-13.2.0}/cc_transcript/command.py

@@ -10,7 +10,7 @@ prefix (``"git commit"``, ``"docker compose"``).
 from __future__ import annotations
 
 import re
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from functools import cached_property, lru_cache
 from itertools import dropwhile
 from typing import TYPE_CHECKING
@@ -19,7 +19,7 @@ import tree_sitter_bash as tsbash
 from tree_sitter import Language, Node, Parser
 
 if TYPE_CHECKING:
-    from collections.abc import Callable, Iterator, Sequence
+    from collections.abc import Callable, Iterator, Mapping, Sequence
 
 BASH_PARSER = Parser(Language(tsbash.language()))
 
@@ -52,6 +52,10 @@ WRAPPER_COMMANDS = frozenset({"sudo", "env", "time", "timeout", "nice", "nohup",
 
 ASSIGNMENT_RE = re.compile(r"^\w+=")
 
+PIPE_GAP_RE = re.compile(r"\s*\|&?\s*")
+
+REDIRECT_OP_TYPES = frozenset({"file_descriptor", ">", ">>", "<", "<<", ">&", "<&", ">|"})
+
 
 @dataclass(frozen=True)
 class Redirect:
@@ -74,6 +78,7 @@ class Command:
     args: tuple[str, ...]
     env: tuple[tuple[str, str], ...] = ()
     redirects: tuple[Redirect, ...] = ()
+    span: tuple[int, int] | None = field(default=None, compare=False, repr=False)
 
     @classmethod
     def parse(cls, raw: str) -> Command | None:
@@ -131,6 +136,7 @@ class Command:
             args=argv[1:],
             env=self.env,
             redirects=self.redirects,
+            span=self.span,
         )
 
     @property
@@ -252,6 +258,56 @@ class CommandLine:
     def q(self) -> CommandLineQuery:
         return CommandLineQuery(self)
 
+    @cached_property
+    def occurrences(self) -> tuple[Occurrence, ...]:
+        """One ``Occurrence`` per part, in line order."""
+        return tuple(Occurrence(self, index) for index in range(len(self.parts)))
+
+    def splice(self, replacements: Mapping[int, str]) -> str:
+        """Swap each indexed command's byte span for its replacement, preserving every other byte.
+
+        Args:
+            replacements: Command index → replacement text. Operates on
+                ``raw.encode()``; untouched bytes (operators, redirects,
+                heredoc bodies, comments) pass through verbatim.
+
+        Returns:
+            The rewritten line, decoded once at the end.
+
+        Raises:
+            ValueError: If an indexed command has no ``span``, or the spans are
+                out of order or overlap.
+        """
+        source = self.raw.encode()
+        out = bytearray()
+        cursor = 0
+        for index in sorted(replacements):
+            span = self.parts[index][0].span
+            if span is None:
+                raise ValueError(f"command at index {index} has no span")
+            start, end = span
+            if start < cursor:
+                raise ValueError(f"span {span} at index {index} overlaps or precedes cursor {cursor}")
+            out += source[cursor:start]
+            out += replacements[index].encode()
+            cursor = end
+        out += source[cursor:]
+        return out.decode()
+
+    def rewrite_occurrences(self, to: Callable[[Occurrence], str | None]) -> str | None:
+        """Map ``to`` over each occurrence and splice in its non-``None`` results.
+
+        Args:
+            to: Maps an ``Occurrence`` to replacement text, or ``None`` to leave
+                that command untouched.
+
+        Returns:
+            The spliced line, or ``None`` when ``to`` returned ``None`` for every
+            occurrence.
+        """
+        replacements = {occ.index: text for occ in self.occurrences if (text := to(occ)) is not None}
+        return self.splice(replacements) if replacements else None
+
     @staticmethod
     def node_text(node: Node) -> str:
         return node.text.decode() if node.text else ""
@@ -330,12 +386,16 @@ class CommandLine:
                 case _:
                     pass
 
+        content = [c for c in node.children if c.type != "file_redirect"]
+        span = (content[0].start_byte, content[-1].end_byte) if content else (node.start_byte, node.end_byte)
+
         return Command(
             raw=CommandLine.node_text(node),
             executable=executable,
             args=tuple(args),
             env=tuple(env),
             redirects=tuple(redirects),
+            span=span,
         )
 
     @staticmethod
@@ -352,13 +412,26 @@ class CommandLine:
                 parts.extend(sub)
         return parts
 
+    @staticmethod
+    def redirect_absorbed_word(node: Node) -> bool:
+        """Whether a ``file_redirect`` swallowed a command word past its target.
+
+        Tree-sitter-bash folds a word that trails a redirect (the ``b`` in
+        ``echo a >out b``) into the ``file_redirect`` node beside the target, so
+        a redirect carrying more than one target word split the command's
+        arguments — leaving it no contiguous byte span to splice.
+        """
+        return sum(c.type not in REDIRECT_OP_TYPES for c in node.children) > 1
+
     @staticmethod
     def walk_redirected(node: Node) -> list[tuple[Command, str | None]]:
         redirects: list[Redirect] = []
         inner_parts: list[tuple[Command, str | None]] = []
+        broken = False
         for child in node.children:
             if child.type == "file_redirect":
                 redirects.append(CommandLine.extract_redirect(child))
+                broken = broken or CommandLine.redirect_absorbed_word(child)
             else:
                 inner_parts.extend(CommandLine.walk_node(child))
         if redirects and inner_parts:
@@ -370,6 +443,7 @@ class CommandLine:
                         args=cmd.args,
                         env=cmd.env,
                         redirects=(*cmd.redirects, *redirects),
+                        span=None if broken else cmd.span,
                     ),
                     op,
                 )
@@ -382,6 +456,7 @@ class CommandLine:
                     executable="",
                     args=(),
                     redirects=tuple(redirects),
+                    span=(node.start_byte, node.end_byte),
                 ),
                 None,
             )
@@ -407,6 +482,63 @@ class CommandLine:
                 return parts
 
 
+@dataclass(frozen=True)
+class Occurrence:
+    """One command of a ``CommandLine`` with its position and joining context.
+
+    Pairs the ``line`` with this command's ``index`` into ``line.parts``,
+    exposing the command, the operators on either side, and whether it sits in a
+    pipeline. Hook packs map over ``CommandLine.occurrences`` and return
+    replacement text per occurrence to rewrite individual commands in place.
+    """
+
+    line: CommandLine
+    index: int
+
+    @property
+    def command(self) -> Command:
+        """The command at this occurrence's index."""
+        return self.line.parts[self.index][0]
+
+    @property
+    def prev_op(self) -> str | None:
+        """The operator joining the previous command to this one; ``None`` at index 0."""
+        return self.line.parts[self.index - 1][1] if self.index > 0 else None
+
+    @property
+    def next_op(self) -> str | None:
+        """The operator joining this command to the next; ``None`` for the final command."""
+        return self.line.parts[self.index][1]
+
+    @cached_property
+    def piped(self) -> bool:
+        """Whether this command sits on either side of a pipe.
+
+        ``True`` when a neighboring operator is ``|``. Tree-sitter records no
+        operator token for ``|&``, and newline-separated statements also carry a
+        ``None`` operator, so a ``None`` neighbor falls back to inspecting the
+        decoded source gap toward that neighbor: it counts as piped only when the
+        gap is exactly one pipe operator token (``|`` or ``|&``) surrounded by
+        whitespace. Anything else in the gap — a comment, a redirect target, a
+        heredoc body, ``||``, an intervening statement — is not a pipe.
+        """
+        if self.prev_op == "|" or self.next_op == "|":
+            return True
+        span = self.command.span
+        if span is None:
+            return False
+        source = self.line.raw.encode()
+        if self.next_op is None and self.index + 1 < len(self.line.parts):
+            nxt = self.line.parts[self.index + 1][0].span
+            if nxt is not None and PIPE_GAP_RE.fullmatch(source[span[1] : nxt[0]].decode()):
+                return True
+        if self.prev_op is None and self.index > 0:
+            prev = self.line.parts[self.index - 1][0].span
+            if prev is not None and PIPE_GAP_RE.fullmatch(source[prev[1] : span[0]].decode()):
+                return True
+        return False
+
+
 @dataclass(frozen=True)
 class CommandLineQuery:
     """Predicate helpers for inspecting a parsed ``CommandLine``.

cc_transcript-13.2.0/cc_transcript/heartbeats.py

@@ -0,0 +1,117 @@
+"""Per-(session, event) dispatch heartbeats — proof a hook event reached dispatch at all.
+
+The decision ledger records only hooks that *fired*, so it cannot distinguish "this event
+was never dispatched" from "it dispatched and matched nothing". A heartbeat is written
+unconditionally at dispatch entry, before matching, keyed by ``(session_id, event)`` and
+counting hits — so a missing beat for an event a session should emit is an unambiguous
+wiring gap. It shares the ``decisions.db`` file with
+:class:`~cc_transcript.decisions.DecisionLog` in a separate ``dispatch_heartbeats`` table,
+so the vendored, Go-byte-compared ``decisions`` schema is untouched. The upsert keeps at
+most one row per ``(session, event)``, so the table stays small however hot the path.
+"""
+
+from __future__ import annotations
+
+import sqlite3
+from dataclasses import dataclass
+from pathlib import Path
+from typing import TYPE_CHECKING, Self
+
+if TYPE_CHECKING:
+    from cc_transcript.ids import SessionId
+
+HEARTBEATS_DDL = """\
+CREATE TABLE IF NOT EXISTS dispatch_heartbeats (
+    session_id TEXT NOT NULL,
+    event TEXT NOT NULL,
+    first_ts_ms INTEGER NOT NULL,
+    last_ts_ms INTEGER NOT NULL,
+    count INTEGER NOT NULL DEFAULT 1,
+    PRIMARY KEY (session_id, event)
+);
+
+CREATE INDEX IF NOT EXISTS idx_heartbeats_session ON dispatch_heartbeats (session_id);
+"""
+
+FILENAME = "decisions.db"
+
+
+@dataclass(frozen=True, slots=True)
+class Heartbeat:
+    """One ``(session, event)`` dispatch heartbeat.
+
+    Attributes:
+        session_id: The Claude session the event dispatched in.
+        event: The Claude Code event name, e.g. ``PreToolUse`` or ``Stop``.
+        first_ts_ms: Millisecond timestamp of the first dispatch this session.
+        last_ts_ms: Millisecond timestamp of the most recent dispatch.
+        count: How many times the event has dispatched this session.
+    """
+
+    session_id: SessionId
+    event: str
+    first_ts_ms: int
+    last_ts_ms: int
+    count: int
+
+
+class HeartbeatLog:
+    """The ``dispatch_heartbeats`` table in ``~/.cc-transcript/decisions.db``.
+
+    Opened in WAL mode with a busy timeout, matching the decision ledger it shares a file
+    with. ``beat`` upserts one ``(session, event)`` row per dispatch, so a session holds at
+    most one row per event. Requires a local disk — WAL does not work over NFS.
+
+    Example:
+        >>> log = HeartbeatLog.open()
+        >>> log.beat(session_id, "PreToolUse", ts_ms)
+        >>> log.for_session(session_id)
+    """
+
+    def __init__(self, conn: sqlite3.Connection) -> None:
+        self.conn = conn
+
+    @classmethod
+    def open(cls, path: Path | None = None) -> Self:
+        """Opens (creating if needed) the heartbeat table at ``path`` (defaults to ``decisions.db``)."""
+        path = path or Path.home() / ".cc-transcript" / FILENAME
+        path.parent.mkdir(parents=True, exist_ok=True)
+        conn = sqlite3.connect(path, autocommit=True)
+        conn.row_factory = sqlite3.Row
+        conn.execute("PRAGMA journal_mode = WAL")
+        conn.execute("PRAGMA busy_timeout = 2000")
+        conn.executescript(HEARTBEATS_DDL)
+        return cls(conn)
+
+    def beat(self, session_id: SessionId, event: str, ts_ms: int) -> None:
+        """Records one dispatch of ``event`` in ``session_id`` at ``ts_ms`` (upsert; ``count += 1``)."""
+        self.conn.execute(
+            "INSERT INTO dispatch_heartbeats (session_id, event, first_ts_ms, last_ts_ms, count) "
+            "VALUES (?, ?, ?, ?, 1) "
+            "ON CONFLICT (session_id, event) DO UPDATE SET last_ts_ms = excluded.last_ts_ms, count = count + 1",
+            (session_id, event, ts_ms, ts_ms),
+        )
+
+    def for_session(self, session_id: SessionId) -> tuple[Heartbeat, ...]:
+        """Every ``(session, event)`` beat for ``session_id``, ordered by first dispatch."""
+        return tuple(
+            Heartbeat(
+                session_id=row["session_id"],
+                event=row["event"],
+                first_ts_ms=row["first_ts_ms"],
+                last_ts_ms=row["last_ts_ms"],
+                count=row["count"],
+            )
+            for row in self.conn.execute(
+                "SELECT * FROM dispatch_heartbeats WHERE session_id = ? ORDER BY first_ts_ms, event", (session_id,)
+            )
+        )
+
+    def events_seen(self, session_id: SessionId) -> frozenset[str]:
+        """The set of event names that have dispatched at least once in ``session_id``."""
+        return frozenset(
+            row["event"]
+            for row in self.conn.execute(
+                "SELECT event FROM dispatch_heartbeats WHERE session_id = ?", (session_id,)
+            )
+        )

{cc_transcript-13.0.0 → cc_transcript-13.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cc-transcript"
-version = "13.0.0"
+version = "13.2.0"
 description = "Grep every Claude Code session you've ever run."
 readme = "README.md"
 license = "PolyForm-Noncommercial-1.0.0"

{cc_transcript-13.0.0 → cc_transcript-13.2.0}/rust/Cargo.toml

@@ -46,3 +46,13 @@ udpipe-rs = { version = "0.2", optional = true }
 
 [build-dependencies]
 pyo3-build-config = { version = "0.28", features = ["resolve-config"], optional = true }
+
+[dev-dependencies]
+# Criterion for the v14 P0 parse/filter/activity baseline (rust/benches/parse.rs).
+# default-features off: skip the plotters/HTML report machinery; estimates.json
+# (the medians BASELINE.json reads) is written by the core regardless.
+criterion = { version = "0.5", default-features = false, features = ["cargo_bench_support"] }
+
+[[bench]]
+name = "parse"
+harness = false

cc_transcript-13.2.0/rust/benches/parse.rs

@@ -0,0 +1,77 @@
+//! v14 P0 baseline benches: parse, parse+filter, session-activity over the corpus at
+//! `CC_BENCH_CORPUS` (default `../.fixtures/corpus`; build via scripts/gen_corpus.py).
+
+use std::fs;
+use std::path::{Path, PathBuf};
+
+use criterion::{criterion_group, criterion_main, Criterion, Throughput};
+
+use _parser_rs::activity::{session_activity, ActivityOpts};
+use _parser_rs::filter::{compile_spec, spec_keep};
+use _parser_rs::parse::parse_bytes;
+
+// spec_to_json of cli.py SIGNAL_SPEC (cc_transcript/builders.py): keep_only + drop_junk + drop_synthetic + drop_sidechain + drop_empty x2.
+const FILTER_SPEC_JSON: &str = r#"{"clauses":[{"predicate":{"kind":"KindIs","kinds":["assistant","user"]},"action":"drop","applies_to":[],"negate":true,"label":null},{"predicate":{"kind":"TextMatchesAny","groups":[["xml_tags","<(?:system[_-](?:instruction|reminder)|local-command-(?:stdout|stderr|caveat)|command-(?:name|message|args)|task-notification|persisted-output|output-file)\\b"],["local_command_caveat","Caveat: The messages below were generated by the user while running local commands\\."],["remaining_tasks_ack","REMAINING_TASKS_ACKNOWLEDGED"],["angle_token","<<[a-z][a-z0-9-]*>>"],["skill_base_dir","^Base directory for this skill:"],["hash_banner","(?:###\\s+[\\w][\\w \\-]{0,30}\\s+){3,}###"],["xml_tags_extra","\\A\\s*<(?:teammate-message|scheduled-task)(?:[\\s/>]|$)"],["augment_agent","\\A\\s*# Augment Agent(?:\\s|$)"],["role_reminder","\\A\\s*\\[Role Rem(?-i:[Ii])nder(?:[\\s:\\]]|$)"],["command_echo","\\A\\s*<bash-(?:input|stdout|stderr)\\b"]],"ignore_case":true},"action":"drop","applies_to":["user"],"negate":false,"label":null},{"predicate":{"kind":"ModelIs","models":["<synthetic>"]},"action":"drop","applies_to":["assistant"],"negate":false,"label":null},{"predicate":{"kind":"MetaFlag","flag":"is_sidechain"},"action":"drop","applies_to":[],"negate":false,"label":null},{"predicate":{"kind":"TextEmpty","consider_tool_use":false},"action":"drop","applies_to":["user"],"negate":false,"label":null},{"predicate":{"kind":"TextEmpty","consider_tool_use":true},"action":"drop","applies_to":["assistant"],"negate":false,"label":null}]}"#;
+
+fn corpus_dir() -> PathBuf {
+    std::env::var_os("CC_BENCH_CORPUS")
+        .map(PathBuf::from)
+        .unwrap_or_else(|| PathBuf::from("../.fixtures/corpus"))
+}
+
+fn collect_jsonl(dir: &Path, out: &mut Vec<PathBuf>) {
+    let Ok(entries) = fs::read_dir(dir) else { return };
+    for entry in entries.flatten() {
+        let path = entry.path();
+        if path.is_dir() {
+            collect_jsonl(&path, out);
+        } else if path.extension().and_then(|e| e.to_str()) == Some("jsonl") {
+            out.push(path);
+        }
+    }
+}
+
+fn largest_corpus_file() -> Vec<u8> {
+    let dir = corpus_dir();
+    let mut files = Vec::new();
+    collect_jsonl(&dir, &mut files);
+    let largest = files
+        .into_iter()
+        .max_by_key(|p| fs::metadata(p).map(|m| m.len()).unwrap_or(0))
+        .unwrap_or_else(|| {
+            panic!(
+                "no .jsonl transcripts under {} — run: uv run --no-sync python scripts/gen_corpus.py",
+                dir.display()
+            )
+        });
+    fs::read(&largest).unwrap_or_else(|e| panic!("failed to read corpus file {}: {e}", largest.display()))
+}
+
+fn bench_parse(c: &mut Criterion) {
+    let bytes = largest_corpus_file();
+    let spec = compile_spec(FILTER_SPEC_JSON).expect("filter spec compiles");
+    let mut group = c.benchmark_group("parse");
+    group.sample_size(20);
+    group.throughput(Throughput::Bytes(bytes.len() as u64));
+    group.bench_function("parse_corpus", |b| {
+        b.iter(|| parse_bytes(&bytes, |_| true).expect("corpus parses"))
+    });
+    group.bench_function("filter_spec", |b| {
+        b.iter(|| parse_bytes(&bytes, |entry| spec_keep(&spec, entry)).expect("corpus parses"))
+    });
+    group.finish();
+}
+
+fn bench_activity(c: &mut Criterion) {
+    let bytes = largest_corpus_file();
+    let entries = parse_bytes(&bytes, |_| true).expect("corpus parses");
+    let opts = ActivityOpts::default();
+    let mut group = c.benchmark_group("activity");
+    group.sample_size(20);
+    group.throughput(Throughput::Elements(entries.len() as u64));
+    group.bench_function("session_activity", |b| b.iter(|| session_activity(&entries, &opts)));
+    group.finish();
+}
+
+criterion_group!(benches, bench_parse, bench_activity);
+criterion_main!(benches);

{cc_transcript-13.0.0 → cc_transcript-13.2.0}/rust/src/lib.rs

@@ -11,7 +11,7 @@ mod command;
 #[cfg(feature = "python")]
 mod event;
 #[cfg(feature = "python")]
-mod filter;
+pub mod filter;
 #[cfg(feature = "python")]
 mod lexicon;
 #[cfg(feature = "python")]