Enhancement: document_index reindex --if-needed; simplify Docker startup

Add --if-needed flag to `document_index reindex`: checks _needs_rebuild()
(schema version + language sentinels) and skips if index is up to date.
Safe to run on every upgrade or startup.

Simplify Docker init-search-index script to unconditionally call
`reindex --if-needed` — schema/language change detection is now fully
delegated to Python. Removes the bash index_version and language file
tracking entirely; Tantivy's own sentinels are the source of truth.

Update docs: bare metal upgrade step uses --if-needed; Docker note
updated to describe the new always-runs-but-skips-if-current behaviour.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Trenton H
2026-03-30 14:08:49 -07:00
co-authored by Claude Sonnet 4.6
parent ae494d4b6a
commit da3ff7865e
3 changed files with 34 additions and 49 deletions
@@ -3,39 +3,10 @@
declare -r log_prefix="[init-index]"
# Version 1: Tantivy backend (replaces Whoosh; resets versioning from scratch)
declare -r index_version=1
declare -r data_dir="${PAPERLESS_DATA_DIR:-/usr/src/paperless/data}"
declare -r index_version_file="${data_dir}/.index_version"
declare -r index_language_file="${data_dir}/.index_language"
# Track the raw env var (not the resolved language) so inference changes
# don't cause spurious reindexes — only explicit setting changes trigger one.
declare -r search_language="${PAPERLESS_SEARCH_LANGUAGE:-}"
update_index () {
echo "${log_prefix} Search index out of date. Updating..."
cd "${PAPERLESS_SRC_DIR}"
if [[ -n "${USER_IS_NON_ROOT}" ]]; then
python3 manage.py document_index reindex --no-progress-bar
echo ${index_version} | tee "${index_version_file}" > /dev/null
echo "${search_language}" | tee "${index_language_file}" > /dev/null
else
s6-setuidgid paperless python3 manage.py document_index reindex --no-progress-bar
echo ${index_version} | s6-setuidgid paperless tee "${index_version_file}" > /dev/null
echo "${search_language}" | s6-setuidgid paperless tee "${index_language_file}" > /dev/null
fi
}
if [[ ! -f "${index_version_file}" ]]; then
echo "${log_prefix} No index version file found"
update_index
elif [[ $(<"${index_version_file}") != "${index_version}" ]]; then
echo "${log_prefix} Index version updated"
update_index
elif [[ ! -f "${index_language_file}" ]]; then
echo "${log_prefix} No language file found"
update_index
elif [[ $(<"${index_language_file}") != "${search_language}" ]]; then
echo "${log_prefix} Search language changed"
update_index
echo "${log_prefix} Checking search index..."
cd "${PAPERLESS_SRC_DIR}"
if [[ -n "${USER_IS_NON_ROOT}" ]]; then
python3 manage.py document_index reindex --if-needed --no-progress-bar
else
s6-setuidgid paperless python3 manage.py document_index reindex --if-needed --no-progress-bar
fi