Skip to content

feat(mine): expand readable extension coverage #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mjc wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

feat(mine): expand readable extension coverage #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9b698cb
feat(mine): expand readable extension coverage
mjc Apr 28, 2026
95cb982
fix: address Copilot review on #4
mjc Apr 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 2 additions & 17 deletions mempalace/entity_detector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@
from collections import defaultdict

from mempalace.i18n import get_entity_patterns
from mempalace.readable_extensions import ENTITY_DETECTOR_READABLE_EXTENSIONS


# ==================== LANGUAGE-AWARE PATTERN LOADING ====================
Expand Down Expand Up @@ -88,23 +89,7 @@ def _get_stopwords(languages: tuple) -> frozenset:
".csv",
}

READABLE_EXTENSIONS = {
".txt",
".md",
".py",
".js",
".ts",
".json",
".yaml",
".yml",
".csv",
".rst",
".toml",
".sh",
".rb",
".go",
".rs",
}
READABLE_EXTENSIONS = ENTITY_DETECTOR_READABLE_EXTENSIONS

SKIP_DIRS = {
".git",
Expand Down
25 changes: 2 additions & 23 deletions mempalace/miner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,30 +30,9 @@
purge_file_closets,
upsert_closet_lines,
)
from .readable_extensions import MINER_READABLE_EXTENSIONS

READABLE_EXTENSIONS = {
".txt",
".md",
".py",
".js",
".ts",
".jsx",
".tsx",
".json",
".jsonl",
".yaml",
".yml",
".html",
".css",
".java",
".go",
".rs",
".rb",
".sh",
".csv",
".sql",
".toml",
}
READABLE_EXTENSIONS = MINER_READABLE_EXTENSIONS

SKIP_FILENAMES = {
"entities.json",
Expand Down
65 changes: 65 additions & 0 deletions mempalace/readable_extensions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,65 @@
"""Shared readable-extension sets used by mining and entity detection."""

BASE_READABLE_EXTENSIONS = {
".txt",
".md",
".py",
".js",
".ts",
".json",
".yaml",
".yml",
".csv",
".toml",
".sh",
".rb",
".go",
".rs",
".c",
".cc",
".cpp",
".cxx",
".h",
".hh",
".hpp",
".hxx",
".ipp",
".inl",
".m",
".mm",
".cs",
".csproj",
".props",
".sln",
".vcxproj",
".kt",
".kts",
".erl",
".hrl",
".nix",
".cmake",
".gn",
".gni",
".proto",
".ps1",
".mdx",
".patch",
".ex",
".exs",
".eex",
".heex",
}

ENTITY_DETECTOR_READABLE_EXTENSIONS = BASE_READABLE_EXTENSIONS | {
".rst",
}

MINER_READABLE_EXTENSIONS = BASE_READABLE_EXTENSIONS | {
".jsx",
".tsx",
".jsonl",
".html",
".css",
".java",
".sql",
}