# QuickSearch configuration reference.
#
# The live config is auto-created at ~/.config/quicksearch/config.toml
# (Windows: %APPDATA%\quicksearch\config.toml). A config.toml placed next
# to the quicksearch binary overrides it entirely (portable mode).
# Relative paths resolve against the directory containing the config
# file, so a portable folder can be moved wholesale.
#
# Every key is optional; missing keys take the defaults shown here.

[paths]
# One or more directory roots to index. Walked in order; duplicate and
# nested roots are de-duplicated automatically. `~` expands to home.
indexing_paths = ["~"]
# SQLite index location. Default: ~/.local/share/quicksearch/index.sqlite
# On Windows the default is %LOCALAPPDATA%\quicksearch\index.sqlite. Write
# Windows paths as TOML *literal* strings (single quotes) so the
# backslashes need no escaping, and keep the index out of a roaming
# profile — it is far too large to synchronise:
#   database_path = 'C:\Users\you\AppData\Local\quicksearch\index.sqlite'
database_path = "~/.local/share/quicksearch/index.sqlite"

[indexing]
# Automatic mode: filesystem watchers apply changes as they happen and a
# full reindex runs every reindex_interval_minutes. The watcher catches
# changes as they happen, so this only needs to be often enough to cover
# whatever the watcher missed.
auto_index = true
reindex_interval_minutes = 1440
# Follow symbolic links during directory walks.
follow_symlinks = false
# Index hidden files and directories. That means dot-files everywhere, and
# additionally anything carrying the Hidden or System attribute on Windows
# (AppData, $RECYCLE.BIN, System Volume Information, pagefile.sys ...).
include_hidden = false
# Empty = extract text from every supported format. Non-empty = content
# indexing only for these extensions; other files are still listed for
# filename search. Entries are case-insensitive, leading dot optional.
content_extensions = []
# Excluded from the index entirely. A pattern without a separator matches
# any single path component (so ".git" prunes whole subtrees); patterns
# containing one match full paths. Glob syntax (*, ?, [..]). Matching is
# case-insensitive on Windows and macOS, case-sensitive elsewhere,
# following the filesystem.
#
# The Windows defaults add: "$RECYCLE.BIN", "System Volume Information",
# "pagefile.sys", "hiberfil.sys", "swapfile.sys", "Thumbs.db",
# "desktop.ini".
ignore_patterns = [".git", "node_modules", "*.tmp", ".venv", "venv"]

# Worth adding by hand if you index a whole Windows drive rather than just
# your profile. Neither is excluded by default, because the default root
# is your profile and a bare "Windows" pattern would also match a folder
# of your own with that name:
#   'C:\Windows'        — system files, nothing you would search for
#   'C:\Windows\WinSxS' — a hardlink farm that floods the Duplicates tab

# Walker threads per root, keyed by the exact root string from
# indexing_paths. Absent or 0 = auto (4 on local storage, 16 on network
# mounts, detected per root). Applies at the start of the next run.
# root_workers = { "/media/share" = 24 }

[processing]
# Bytes read from the start of each file for its content hash, which is
# `sha256(size || first hash_length bytes)` and backs duplicate detection.
# Only the head is read: seeking to the end for a second block costs an
# extra round trip per file on network shares.
#
# Known limitation: files of identical size whose heads match will be
# reported as duplicates. In practice that means pre-allocated VM disk
# images: a fixed-size VHD stores its unique footer at the end of the
# file, and a freshly pre-allocated raw/qcow2/VMDK image is all zeros at
# the head until it is partitioned.
hash_length = 8192
# Maximum extracted text stored per file (bytes).
maximum_text_size = 262144
# Files larger than this skip text extraction entirely (bytes).
maximum_text_file_size = 2097152
# Files per batch during walks / inserts / extraction.
batch_size = 200
# Files per transaction for incremental FTS updates.
fts_update_batch_size = 1000
# FTS5 tokenizer: 'trigram' (substring matching, the default; gets
# remove_diacritics 1 appended), 'unicode61', 'porter', or a full FTS5
# option string. See https://www.sqlite.org/fts5.html#tokenizers
tokenize = "trigram"
# Store extracted text (zstd-compressed) alongside the FTS index. Off:
# the index shrinks to roughly stock-Baloo size, but search loses snippet
# previews, occurrence ranking, case verification, and fuzzy full-text.
store_text_for_snippets = true

[ui]
# Zoom factor for the whole GUI: fonts, spacing, and widgets scale
# together (0.5 – 2.5). Ctrl +/- and Ctrl 0 adjust it temporarily at
# runtime; this value is the persistent baseline.
scale = 1.1

[search]
# Start with the fuzzy passes enabled.
fuzzy_default = false
# Ceiling on the fuzzy stages' typo budget. The allowance grows with the
# search term, one edit per three characters, up to this value, so 2
# means "1 edit for 3-5 character terms, 2 for anything longer". 0 turns
# the fuzzy stages off. Above 3 is allowed but not recommended: matches
# become dominated by coincidence and every fuzzy pass slows down.
fuzzy_max_edits = 2
# Hard cap on results per search (the GUI's scroll list length).
display_limit = 1000
# Results per streamed batch (latency/overhead knob, not a page size).
results_per_page = 100
# How long the GUI waits after the last keystroke before searching (ms).
debounce_ms = 150