rlmgrep 0.1.18__py3-none-any.whl → 0.1.26__py3-none-any.whl

rlmgrep/__init__.py

@@ -1,2 +1,2 @@
 __all__ = ["__version__"]
-__version__ = "0.1.18"
+__version__ = "0.1.26"

rlmgrep/cli.py

@@ -1,13 +1,26 @@
 from __future__ import annotations
 
 import argparse
+import logging
 import os
-import sys
 import shutil
 import subprocess
+import sys
 from pathlib import Path
 
 import dspy
+from rich import box
+from rich.console import Console
+from rich.panel import Panel
+from rich.progress import (
+    BarColumn,
+    Progress,
+    SpinnerColumn,
+    TaskProgressColumn,
+    TextColumn,
+    TimeElapsedColumn,
+)
+from rich.text import Text
 from . import __version__
 from .config import ensure_default_config, load_config
 from .file_map import build_file_map
@@ -23,7 +36,81 @@ from .render import render_matches
 
 
 def _warn(msg: str) -> None:
-    print(f"rlmgrep: {msg}", file=sys.stderr)
+    print(f"rlmgrep: {msg}", file=sys.stderr, flush=True)
+
+
+def _console() -> Console:
+    use_color = sys.stderr.isatty() and not os.getenv("NO_COLOR")
+    return Console(stderr=True, force_terminal=use_color, color_system="auto")
+
+
+class _RLMIterationHandler(logging.Handler):
+    def __init__(self, console: Console) -> None:
+        super().__init__(level=logging.INFO)
+        self._console = console
+        self._title: str | None = None
+        self._lines: list[str] = []
+
+    def emit(self, record: logging.LogRecord) -> None:
+        msg = record.getMessage()
+        if "RLM iteration" in msg:
+            self.flush_panel()
+            self._title = "RLM iteration"
+            self._lines = [msg]
+            return
+        if self._title is None:
+            self._title = "RLM output"
+        self._lines.append(msg)
+
+    def flush_panel(self) -> None:
+        if self._title is None:
+            return
+        body = "\n".join(self._lines).strip() or " "
+        self._console.print(
+            Panel(
+                Text(body),
+                title=self._title,
+                border_style="blue",
+                box=box.ROUNDED,
+            )
+        )
+        self._title = None
+        self._lines = []
+
+
+def _setup_verbose_logging(console: Console) -> _RLMIterationHandler:
+    logger = logging.getLogger("dspy.predict.rlm")
+    handler = _RLMIterationHandler(console)
+    logger.addHandler(handler)
+    logger.setLevel(logging.INFO)
+    logger.propagate = False
+    return handler
+
+
+def _print_answer(console: Console, answer: str) -> None:
+    text = Text(answer.strip())
+    panel = Panel(
+        text,
+        title="Answer",
+        border_style="cyan",
+        box=box.ROUNDED,
+    )
+    console.print(panel)
+
+
+def _print_matches(console: Console, lines: list[str], use_color: bool) -> None:
+    body = "\n".join(lines).strip()
+    if not body:
+        body = "No matches"
+    text = Text.from_ansi(body) if use_color else Text(body)
+    console.print(
+        Panel(
+            text,
+            title="Matches",
+            border_style="cyan",
+            box=box.ROUNDED,
+        )
+    )
 
 
 def _confirm_over_limit(count: int, threshold: int) -> bool:
@@ -450,6 +537,8 @@ def main(argv: list[str] | None = None) -> int:
     for w in config_warnings:
         _warn(w)
 
+    console = _console()
+
     # Resolve input corpus.
     globs = _split_list(args.globs)
     type_names = _split_list(args.types)
@@ -511,7 +600,34 @@ def main(argv: list[str] | None = None) -> int:
             extra_ignores.extend(_global_ignore_paths(ignore_root))
             ignore_spec = build_ignore_spec(ignore_root, extra_paths=extra_ignores)
 
-        candidates = collect_candidates(
+        scan_task = None
+        scan_count = 0
+        scan_progress = None
+        if sys.stderr.isatty():
+            scan_progress = Progress(
+                SpinnerColumn(),
+                TextColumn("{task.description}"),
+                TextColumn("{task.completed} files"),
+                BarColumn(),
+                TaskProgressColumn(),
+                TimeElapsedColumn(),
+                console=console,
+                transient=False,
+            )
+            scan_progress.start()
+            scan_task = scan_progress.add_task("Scanning files", total=None)
+
+        def _scan_update(count: int) -> None:
+            nonlocal scan_count
+            scan_count = count
+            if scan_progress is not None and scan_task is not None:
+                scan_progress.update(
+                    scan_task,
+                    completed=count,
+                    description=f"Scanning files ({count})",
+                )
+
+        candidates, scanned = collect_candidates(
             input_paths,
             cwd=cwd,
             recursive=args.recursive,
@@ -520,7 +636,16 @@ def main(argv: list[str] | None = None) -> int:
             include_hidden=args.hidden,
             ignore_spec=ignore_spec,
             ignore_root=ignore_root,
+            scan_progress=_scan_update if scan_progress is not None else None,
         )
+        if scan_progress is not None and scan_task is not None:
+            scan_progress.update(
+                scan_task,
+                total=scanned or scan_count,
+                completed=scanned or scan_count,
+                description=f"Scanning files ({scanned or scan_count})",
+            )
+            scan_progress.stop()
         candidate_count = len(candidates)
         if hard_max is not None and candidate_count > hard_max:
             _warn(
@@ -535,6 +660,39 @@ def main(argv: list[str] | None = None) -> int:
             if not _confirm_over_limit(candidate_count, warn_threshold):
                 return 2
 
+        load_task = None
+        load_progress = None
+        if sys.stderr.isatty():
+            load_progress = Progress(
+                SpinnerColumn(),
+                TextColumn("{task.description}"),
+                TextColumn("{task.completed}/{task.total} files"),
+                BarColumn(),
+                TaskProgressColumn(),
+                TimeElapsedColumn(),
+                console=console,
+                transient=False,
+            )
+            load_progress.start()
+            load_task = load_progress.add_task(
+                "Loading files",
+                total=candidate_count,
+                completed=0,
+            )
+
+        load_done = 0
+
+        def _load_update(done: int, total: int) -> None:
+            nonlocal load_done
+            load_done = done
+            if load_progress is not None and load_task is not None:
+                load_progress.update(
+                    load_task,
+                    completed=done,
+                    total=total,
+                    description=f"Loading files ({done}/{total})",
+                )
+
         files, warnings = load_files(
             candidates,
             cwd=cwd,
@@ -543,7 +701,24 @@ def main(argv: list[str] | None = None) -> int:
             enable_audio=md_enable_audio,
             audio_transcriber=audio_transcriber,
             binary_as_text=args.binary_as_text,
+            progress=_load_update if load_progress is not None else None,
         )
+        if load_progress is not None and load_task is not None:
+            load_progress.update(
+                load_task,
+                completed=load_done,
+                total=candidate_count,
+                description=f"Loading files ({load_done}/{candidate_count})",
+            )
+            load_progress.stop()
+
+        scanned_total = scanned or scan_count
+        loaded_total = len(files)
+        skipped_total = max(0, candidate_count - loaded_total)
+        summary = f"Scanned {scanned_total} files. Loaded {loaded_total}."
+        if skipped_total:
+            summary += f" Skipped {skipped_total}."
+        _warn(summary)
 
     for w in warnings:
         _warn(w)
@@ -620,6 +795,10 @@ def main(argv: list[str] | None = None) -> int:
 
     directory = {k: v.text for k, v in files.items()}
 
+    verbose_handler = None
+    if args.verbose:
+        verbose_handler = _setup_verbose_logging(console)
+
     try:
         proposed, answer = run_rlm(
             directory=directory,
@@ -634,6 +813,9 @@ def main(argv: list[str] | None = None) -> int:
     except Exception as exc:  # pragma: no cover - defensive
         _warn(f"RLM failure: {exc}")
         return 2
+    finally:
+        if verbose_handler is not None:
+            verbose_handler.flush_panel()
 
     verified, dropped = verify_matches(proposed, files)
     if dropped:
@@ -649,7 +831,9 @@ def main(argv: list[str] | None = None) -> int:
     before = args.before if args.before is not None else args.context
     after = args.after if args.after is not None else args.context
 
-    use_color = sys.stdout.isatty() and not os.getenv("NO_COLOR")
+    stdout_tty = sys.stdout.isatty()
+    stderr_tty = sys.stderr.isatty()
+    use_color = stdout_tty and not os.getenv("NO_COLOR")
 
     output_lines = render_matches(
         files=files,
@@ -660,13 +844,18 @@ def main(argv: list[str] | None = None) -> int:
         heading=True,
     )
 
-    if args.answer:
-        if answer:
-            print(answer.strip())
-        print("--")
+    stdout_console = Console(force_terminal=stdout_tty, color_system="auto")
+    if args.answer and answer:
+        _print_answer(console, answer)
+
+    if stdout_tty:
+        _print_matches(stdout_console, output_lines, use_color=use_color)
+    elif stderr_tty:
+        _print_matches(console, output_lines, use_color=False)
 
-    for line in output_lines:
-        print(line)
+    if not stdout_tty:
+        for line in output_lines:
+            print(line)
 
     total_matches = sum(len(lines) for lines in verified.values())
     if total_matches > 0:

rlmgrep/ingest.py

@@ -147,20 +147,33 @@ def _load_file(
         return None, None, str(exc)
 
 
-def collect_files(paths: Iterable[str], recursive: bool = True) -> list[Path]:
+def collect_files(
+    paths: Iterable[str],
+    recursive: bool = True,
+    progress: Callable[[int], None] | None = None,
+) -> list[Path]:
     files: list[Path] = []
+    scanned = 0
     for raw in paths:
         p = Path(raw)
         if not p.exists():
             continue
         if p.is_dir():
             if recursive:
-                files.extend(fp for fp in p.rglob("*") if fp.is_file())
+                for fp in p.rglob("*"):
+                    if fp.is_file():
+                        files.append(fp)
+                        scanned += 1
+                        if progress is not None:
+                            progress(scanned)
             else:
                 # No recursion: ignore directories.
                 continue
         elif p.is_file():
             files.append(p)
+            scanned += 1
+            if progress is not None:
+                progress(scanned)
     return files
 
 
@@ -344,8 +357,10 @@ def collect_candidates(
     include_hidden: bool = False,
     ignore_spec: "pathspec.PathSpec | None" = None,
     ignore_root: Path | None = None,
-) -> list[Path]:
-    files = collect_files(paths, recursive=recursive)
+    scan_progress: Callable[[int], None] | None = None,
+) -> tuple[list[Path], int]:
+    files = collect_files(paths, recursive=recursive, progress=scan_progress)
+    scanned = len(files)
     explicit_files: set[Path] = set()
     ignore_root_resolved: Path | None = None
     if ignore_root is not None:
@@ -384,7 +399,7 @@ def collect_candidates(
             continue
 
         candidates.append(fp)
-    return candidates
+    return candidates, scanned
 
 
 def load_files(
@@ -395,13 +410,16 @@ def load_files(
     enable_audio: bool = False,
     audio_transcriber: Callable[[Path], str] | None = None,
     binary_as_text: bool = False,
+    progress: Callable[[int, int], None] | None = None,
 ) -> tuple[dict[str, FileRecord], list[str]]:
     records: dict[str, FileRecord] = {}
     warnings: list[str] = []
     image_convert_count = 0
     audio_convert_count = 0
 
-    for fp in candidates:
+    candidate_list = list(candidates)
+    total = len(candidate_list)
+    for idx, fp in enumerate(candidate_list, start=1):
         try:
             key = fp.relative_to(cwd).as_posix()
         except ValueError:
@@ -432,15 +450,21 @@ def load_files(
             }
             if err not in silent_errors and "No converter attempted a conversion" not in err:
                 warnings.append(f"skip {fp}: {err}")
+            if progress is not None:
+                progress(idx, total)
             continue
         if text is None:
             warnings.append(f"skip {fp}: unreadable")
+            if progress is not None:
+                progress(idx, total)
             continue
 
         lines = text.split("\n")
         if page_map is not None and len(page_map) != len(lines):
             page_map = None
         records[key] = FileRecord(path=key, text=text, lines=lines, page_map=page_map)
+        if progress is not None:
+            progress(idx, total)
 
     if image_convert_count > 5:
         warnings.append(

{rlmgrep-0.1.18.dist-info → rlmgrep-0.1.26.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rlmgrep
-Version: 0.1.18
+Version: 0.1.26
 Summary: Grep-shaped CLI search powered by DSPy RLM
 Author: rlmgrep
 License: MIT
@@ -10,6 +10,7 @@ Requires-Dist: dspy>=3.1.1
 Requires-Dist: markitdown[all]>=0.1.4
 Requires-Dist: pathspec>=0.12.1
 Requires-Dist: pypdf>=4.0.0
+Requires-Dist: rich>=13.7.0
 
 # rlmgrep
 
@@ -18,7 +19,7 @@ Grep-shaped search powered by DSPy RLM. It accepts a natural-language query, sca
 ## Quickstart
 
 ```sh
-uv tool install rlmgrep
+uv tool install --python 3.11 rlmgrep
 # or from GitHub:
 # uv tool install git+https://github.com/halfprice06/rlmgrep.git
 

rlmgrep-0.1.26.dist-info/RECORD

@@ -0,0 +1,14 @@
+rlmgrep/__init__.py,sha256=JyNu1JArYKRlsONizRn4WtReW7YQ64wHx46ZFucbFRg,49
+rlmgrep/__main__.py,sha256=MHKZ_ae3fSLGTLUUMOx15fWdeOnJSHhq-zslRP5F5Lc,79
+rlmgrep/cli.py,sha256=Sy-ZAZqeppXzWcbhDKMV7GOL1EFErNkoc6uv7gmVlW4,29373
+rlmgrep/config.py,sha256=u1iz-nI8dj-dZETbpIki3RQefHJEyi5oE5zE4_IR8kg,2399
+rlmgrep/file_map.py,sha256=x2Ri1wzK8_87GUorsAV01K_nYLZcv30yIquDeTCcdEw,876
+rlmgrep/ingest.py,sha256=906JUwWRC0XDoYRXs4-XdV3fay8mQc324l0suQLyS-k,13738
+rlmgrep/interpreter.py,sha256=s_nMRxLlAU9C0JmUzUBW5NbVbuH67doVWF54K54STlA,2478
+rlmgrep/render.py,sha256=mCTT6yuKNv7HJ46LzOyLkCbyBedCWSNd7UeubyLXcyM,3356
+rlmgrep/rlm.py,sha256=i3rCTp8OABByF60Un5gO7265gaW4spwU0OFKIz4surg,5750
+rlmgrep-0.1.26.dist-info/METADATA,sha256=D1CU5EWI9qoLsch3Nak-wUeKMuf3htk430tbhAOOJ5g,8011
+rlmgrep-0.1.26.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+rlmgrep-0.1.26.dist-info/entry_points.txt,sha256=UV6QkEbkwBO1JJ53mm84_n35tVyOczPvOQ14ga7vrCI,45
+rlmgrep-0.1.26.dist-info/top_level.txt,sha256=gTujSRsO58c80eN7aRH2cfe51FHxx8LJ1w1Y2YlHti0,8
+rlmgrep-0.1.26.dist-info/RECORD,,

rlmgrep-0.1.18.dist-info/RECORD

@@ -1,14 +0,0 @@
-rlmgrep/__init__.py,sha256=4P4PJ704cude_tDknqGG0LoqrFcJS7Bpzjp_q0uTPNg,49
-rlmgrep/__main__.py,sha256=MHKZ_ae3fSLGTLUUMOx15fWdeOnJSHhq-zslRP5F5Lc,79
-rlmgrep/cli.py,sha256=DbA8WDqkUrWYV5lItA_mlYB9v0H9ZOPm8JjZLIX1Y7E,23291
-rlmgrep/config.py,sha256=u1iz-nI8dj-dZETbpIki3RQefHJEyi5oE5zE4_IR8kg,2399
-rlmgrep/file_map.py,sha256=x2Ri1wzK8_87GUorsAV01K_nYLZcv30yIquDeTCcdEw,876
-rlmgrep/ingest.py,sha256=3qPJ-FZfWpxwTJBSj_EPWNDCdDDgNgZIGyCTXyXOZfk,12891
-rlmgrep/interpreter.py,sha256=s_nMRxLlAU9C0JmUzUBW5NbVbuH67doVWF54K54STlA,2478
-rlmgrep/render.py,sha256=mCTT6yuKNv7HJ46LzOyLkCbyBedCWSNd7UeubyLXcyM,3356
-rlmgrep/rlm.py,sha256=i3rCTp8OABByF60Un5gO7265gaW4spwU0OFKIz4surg,5750
-rlmgrep-0.1.18.dist-info/METADATA,sha256=6doosFWzRkxGxbKynYyUMMmF6ih0rs8BWGdi0BMeCFs,7969
-rlmgrep-0.1.18.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-rlmgrep-0.1.18.dist-info/entry_points.txt,sha256=UV6QkEbkwBO1JJ53mm84_n35tVyOczPvOQ14ga7vrCI,45
-rlmgrep-0.1.18.dist-info/top_level.txt,sha256=gTujSRsO58c80eN7aRH2cfe51FHxx8LJ1w1Y2YlHti0,8
-rlmgrep-0.1.18.dist-info/RECORD,,