rlmgrep 0.1.10__py3-none-any.whl → 0.1.12__py3-none-any.whl

rlmgrep/__init__.py

@@ -1,2 +1,2 @@
 __all__ = ["__version__"]
-__version__ = "0.1.10"
+__version__ = "0.1.12"

rlmgrep/cli.py

@@ -9,7 +9,13 @@ import dspy
 from . import __version__
 from .config import ensure_default_config, load_config
 from .file_map import build_file_map
-from .ingest import FileRecord, collect_candidates, load_files, resolve_type_exts
+from .ingest import (
+    FileRecord,
+    build_gitignore_spec,
+    collect_candidates,
+    load_files,
+    resolve_type_exts,
+)
 from .rlm import Match, build_lm, run_rlm
 from .render import render_matches
 
@@ -81,6 +87,8 @@ def _parse_args(argv: list[str]) -> argparse.Namespace:
     parser.add_argument("-B", dest="before", type=int, default=None, help="Context lines before")
     parser.add_argument("-m", dest="max_count", type=int, default=None, help="Max matching lines per file")
     parser.add_argument("-a", "--text", dest="binary_as_text", action="store_true", help="Search binary files as text")
+    parser.add_argument("--hidden", action="store_true", help="Include hidden files and directories")
+    parser.add_argument("--no-ignore", dest="no_ignore", action="store_true", help="Do not respect .gitignore")
     parser.add_argument("--answer", action="store_true", help="Print a narrative answer before grep output")
     parser.add_argument("-y", "--yes", action="store_true", help="Skip file count confirmation")
     parser.add_argument(
@@ -139,6 +147,13 @@ def _pick(cli_value, config: dict, key: str, default=None):
     return default
 
 
+def _find_git_root(start: Path) -> Path | None:
+    for p in [start, *start.parents]:
+        if (p / ".git").is_dir():
+            return p
+    return None
+
+
 def _env_value(name: str) -> str | None:
     val = os.getenv(name)
     if val is None:
@@ -424,12 +439,21 @@ def main(argv: list[str] | None = None) -> int:
         if hard_max is not None and hard_max <= 0:
             hard_max = None
 
+        ignore_spec = None
+        ignore_root = None
+        if not args.no_ignore:
+            ignore_root = _find_git_root(cwd) or cwd
+            ignore_spec = build_gitignore_spec(ignore_root)
+
         candidates = collect_candidates(
             input_paths,
             cwd=cwd,
             recursive=args.recursive,
             include_globs=globs,
             type_exts=type_exts,
+            include_hidden=args.hidden,
+            ignore_spec=ignore_spec,
+            ignore_root=ignore_root,
         )
         candidate_count = len(candidates)
         if hard_max is not None and candidate_count > hard_max:

rlmgrep/ingest.py

@@ -2,8 +2,14 @@ from __future__ import annotations
 
 from dataclasses import dataclass
 from fnmatch import fnmatch
+import os
 from pathlib import Path, PurePosixPath
-from typing import Iterable, Any, Callable
+from typing import Any, Callable, Iterable
+
+try:
+    import pathspec
+except Exception:  # pragma: no cover - optional at import time
+    pathspec = None
 
 from pypdf import PdfReader
 
@@ -161,6 +167,64 @@ def collect_files(paths: Iterable[str], recursive: bool = True) -> list[Path]:
     return files
 
 
+def build_gitignore_spec(root: Path) -> "pathspec.PathSpec | None":
+    if pathspec is None:
+        return None
+    root = root.resolve()
+    gitignore_paths: list[Path] = []
+    for dirpath, dirnames, filenames in os.walk(root):
+        if ".git" in dirnames:
+            dirnames.remove(".git")
+        if ".gitignore" in filenames:
+            gitignore_paths.append(Path(dirpath) / ".gitignore")
+
+    if not gitignore_paths:
+        return None
+
+    def _sort_key(p: Path) -> tuple[int, str]:
+        try:
+            rel = p.parent.relative_to(root)
+            depth = len(rel.parts)
+            return depth, rel.as_posix()
+        except ValueError:
+            return 0, p.as_posix()
+
+    gitignore_paths.sort(key=_sort_key)
+
+    patterns: list[str] = []
+    for gi in gitignore_paths:
+        try:
+            rel_dir = gi.parent.relative_to(root).as_posix()
+        except ValueError:
+            rel_dir = ""
+        try:
+            raw_lines = gi.read_text(encoding="utf-8", errors="ignore").splitlines()
+        except Exception:
+            continue
+        for raw in raw_lines:
+            line = raw.rstrip("\n")
+            if not line:
+                continue
+            if line.startswith("\\#") or line.startswith("\\!"):
+                line = line[1:]
+            elif line.startswith("#"):
+                continue
+            negated = line.startswith("!")
+            if negated:
+                line = line[1:]
+            if line.startswith("/"):
+                line = line[1:]
+            if rel_dir:
+                line = f"{rel_dir}/{line}"
+            if negated:
+                line = "!" + line
+            patterns.append(line)
+
+    if not patterns:
+        return None
+    return pathspec.PathSpec.from_lines("gitwildmatch", patterns)
+
+
 TYPE_EXTS = {
     "bash": {".bash"},
     "c": {".c", ".h"},
@@ -237,21 +301,46 @@ def _matches_globs(path: str, globs: list[str]) -> bool:
     return False
 
 
+def _is_hidden_path(path: Path) -> bool:
+    return any(part.startswith(".") for part in path.parts if part)
+
+
 def collect_candidates(
     paths: Iterable[str],
     cwd: Path,
     recursive: bool = True,
     include_globs: list[str] | None = None,
     type_exts: set[str] | None = None,
+    include_hidden: bool = False,
+    ignore_spec: "pathspec.PathSpec | None" = None,
+    ignore_root: Path | None = None,
 ) -> list[Path]:
     files = collect_files(paths, recursive=recursive)
+    explicit_files: set[Path] = set()
+    for raw in paths:
+        p = Path(raw)
+        if p.exists() and p.is_file():
+            explicit_files.add(p.resolve())
     candidates: list[Path] = []
     for fp in files:
+        fp_resolved = fp.resolve()
+        is_explicit = fp_resolved in explicit_files
+        if not include_hidden and not is_explicit and _is_hidden_path(fp):
+            continue
+
         try:
             key = fp.relative_to(cwd).as_posix()
         except ValueError:
             key = fp.as_posix()
 
+        if ignore_spec is not None and ignore_root is not None and not is_explicit:
+            try:
+                rel = fp.relative_to(ignore_root).as_posix()
+            except ValueError:
+                rel = None
+            if rel and ignore_spec.match_file(rel):
+                continue
+
         if include_globs and not _matches_globs(key, include_globs):
             continue
 

{rlmgrep-0.1.10.dist-info → rlmgrep-0.1.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rlmgrep
-Version: 0.1.10
+Version: 0.1.12
 Summary: Grep-shaped CLI search powered by DSPy RLM
 Author: rlmgrep
 License: MIT
@@ -8,6 +8,7 @@ Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 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
 
 # rlmgrep
@@ -22,10 +23,20 @@ uv tool install rlmgrep
 # uv tool install git+https://github.com/halfprice06/rlmgrep.git
 
 export OPENAI_API_KEY=...  # or set keys in ~/.rlmgrep
+```
+
+```sh
 rlmgrep --answer "What does this repo do and where are the entry points?" .
+```
+
+![Quickstart answer mode](docs/images/quickstart-answer.png)
+
+```sh
 rlmgrep -C 2 "Where is retry/backoff configured and what are the defaults?" .
 ```
 
+![Quickstart context mode](docs/images/quickstart-context.png)
+
 ## Requirements
 
 - Python 3.11+
@@ -39,8 +50,8 @@ One of rlmgrep’s most useful features is that it can “grep” **PDFs and Off
 How it works:
 - **PDFs** are parsed with `pypdf`. Each page gets a marker line like `===== Page N =====`, and output lines include a `page=N` suffix. Line numbers refer to the extracted text (not PDF coordinates).
 - **Office & binary docs** (`.docx`, `.pptx`, `.xlsx`, `.html`, `.zip`, etc.) are converted to Markdown via **MarkItDown**. This happens during ingestion, so rlmgrep can search them like any other text file.
-- **Images** can be described by a vision model through MarkItDown (OpenAI/Anthropic/Gemini).
-- **Audio** transcription is supported through OpenAI when enabled.
+- **Images** can be described by a vision model and then searched through MarkItDown (OpenAI/Anthropic/Gemini), enable and configure in config.toml.
+- **Audio** transcription is supported through OpenAI when enabled, configure in config.toml.
 
 Sidecar caching:
 - For images/audio, converted text is cached next to the original file as `<original>.<ext>.md` and reused on later runs.
@@ -48,7 +59,7 @@ Sidecar caching:
 
 ## Install Deno
 
-DSPy requires the Deno runtime. Install it with the official scripts:
+DSPy's default implementation of RLM requires the Deno runtime. Install it with the official scripts:
 
 macOS/Linux:
 
@@ -83,6 +94,8 @@ Common options:
 - `-m N` max matching lines per file
 - `-g GLOB` include files matching glob (repeatable, comma-separated)
 - `--type T` include file types (repeatable, comma-separated)
+- `--hidden` include hidden files and directories
+- `--no-ignore` do not respect `.gitignore`
 - `--no-recursive` do not recurse directories
 - `-a`, `--text` treat binary files as text
 - `-y`, `--yes` skip file count confirmation
@@ -115,6 +128,7 @@ rg -l "token" . | rlmgrep --files-from-stdin --answer "What does this token cont
 ## Input selection
 
 - Directories are searched recursively by default. Use `--no-recursive` to stop recursion.
+- Hidden files and `.gitignore` rules are respected by default. Use `--hidden` or `--no-ignore` to include them.
 - `--type` uses built-in type mappings (e.g., `py`, `js`, `md`); unknown values are treated as file extensions.
 - `-g/--glob` matches path globs against normalized paths (forward slashes).
 - Paths are printed relative to the current working directory when possible.

rlmgrep-0.1.12.dist-info/RECORD

@@ -0,0 +1,14 @@
+rlmgrep/__init__.py,sha256=Oi10B9QTmGI-1i704NHr63Oy1A8W2kzfQCYB6asuv0w,49
+rlmgrep/__main__.py,sha256=MHKZ_ae3fSLGTLUUMOx15fWdeOnJSHhq-zslRP5F5Lc,79
+rlmgrep/cli.py,sha256=sUtcvf-3U1fpUdFYmEE9j75xSgBAx9Uv3XY1lobHURk,21150
+rlmgrep/config.py,sha256=u1iz-nI8dj-dZETbpIki3RQefHJEyi5oE5zE4_IR8kg,2399
+rlmgrep/file_map.py,sha256=x2Ri1wzK8_87GUorsAV01K_nYLZcv30yIquDeTCcdEw,876
+rlmgrep/ingest.py,sha256=St-MaKUBeAUWwEKtjfNej8Wt9aVhg9-VYEm_GDOV7uU,11909
+rlmgrep/interpreter.py,sha256=s_nMRxLlAU9C0JmUzUBW5NbVbuH67doVWF54K54STlA,2478
+rlmgrep/render.py,sha256=mCTT6yuKNv7HJ46LzOyLkCbyBedCWSNd7UeubyLXcyM,3356
+rlmgrep/rlm.py,sha256=i3rCTp8OABByF60Un5gO7265gaW4spwU0OFKIz4surg,5750
+rlmgrep-0.1.12.dist-info/METADATA,sha256=UsbAYXqsGnSUfqdOypf4D4LTbgCaEuwHTCwp5MNMAxU,7849
+rlmgrep-0.1.12.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+rlmgrep-0.1.12.dist-info/entry_points.txt,sha256=UV6QkEbkwBO1JJ53mm84_n35tVyOczPvOQ14ga7vrCI,45
+rlmgrep-0.1.12.dist-info/top_level.txt,sha256=gTujSRsO58c80eN7aRH2cfe51FHxx8LJ1w1Y2YlHti0,8
+rlmgrep-0.1.12.dist-info/RECORD,,

rlmgrep-0.1.10.dist-info/RECORD

@@ -1,14 +0,0 @@
-rlmgrep/__init__.py,sha256=EFWL7tqAdmDdGhDfl3jtag-Ds4vHOCNDFdvMC2yYodU,49
-rlmgrep/__main__.py,sha256=MHKZ_ae3fSLGTLUUMOx15fWdeOnJSHhq-zslRP5F5Lc,79
-rlmgrep/cli.py,sha256=Jn7knAQq3Bnb578QK33RxDZ102yFrVSbNFjUKBGkb1o,20417
-rlmgrep/config.py,sha256=u1iz-nI8dj-dZETbpIki3RQefHJEyi5oE5zE4_IR8kg,2399
-rlmgrep/file_map.py,sha256=x2Ri1wzK8_87GUorsAV01K_nYLZcv30yIquDeTCcdEw,876
-rlmgrep/ingest.py,sha256=uCz2el9B-RIT9umFo-gFEdAsmWPP1IJOArFFQY0D_1A,9127
-rlmgrep/interpreter.py,sha256=s_nMRxLlAU9C0JmUzUBW5NbVbuH67doVWF54K54STlA,2478
-rlmgrep/render.py,sha256=mCTT6yuKNv7HJ46LzOyLkCbyBedCWSNd7UeubyLXcyM,3356
-rlmgrep/rlm.py,sha256=i3rCTp8OABByF60Un5gO7265gaW4spwU0OFKIz4surg,5750
-rlmgrep-0.1.10.dist-info/METADATA,sha256=u4EfxtRfTmzvuu4jD5lBsXZQIHjElMZs9iZe79d4Peg,7349
-rlmgrep-0.1.10.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-rlmgrep-0.1.10.dist-info/entry_points.txt,sha256=UV6QkEbkwBO1JJ53mm84_n35tVyOczPvOQ14ga7vrCI,45
-rlmgrep-0.1.10.dist-info/top_level.txt,sha256=gTujSRsO58c80eN7aRH2cfe51FHxx8LJ1w1Y2YlHti0,8
-rlmgrep-0.1.10.dist-info/RECORD,,