Skip to content

feat: add Unicode-aware expression indexes for German umlaut search #261

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

Merged
hf-kklein merged 1 commit into from
Mar 30, 2026
Merged

feat: add Unicode-aware expression indexes for German umlaut search #261

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 8 additions & 0 deletions src/fundamend/sqlmodels/materialize_ahb_view.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -636,14 +636,17 @@ CREATE INDEX idx_hierarchy_gueltig_von ON ahb_hierarchy_materialized (gueltig_vo
CREATE INDEX idx_hierarchy_gueltig_bis ON ahb_hierarchy_materialized (gueltig_bis);
CREATE INDEX idx_hierarchy_beschreibung ON ahb_hierarchy_materialized (beschreibung);
CREATE INDEX idx_hierarchy_beschreibung_lower ON ahb_hierarchy_materialized (lower(beschreibung));
CREATE INDEX idx_hierarchy_beschreibung_unicode_lower ON ahb_hierarchy_materialized (REPLACE(REPLACE(REPLACE(LOWER(beschreibung), 'Ä', 'ä'), 'Ö', 'ö'), 'Ü', 'ü'));
CREATE INDEX idx_hierarchy_kommunikationsrichtungen ON ahb_hierarchy_materialized (kommunikationsrichtungen);
CREATE INDEX idx_hierarchy_edifact_format_version ON ahb_hierarchy_materialized (edifact_format_version);
CREATE INDEX idx_hierarchy_segmentgroup_id ON ahb_hierarchy_materialized (segmentgroup_id);
CREATE INDEX idx_hierarchy_segmentgroup_id_lower ON ahb_hierarchy_materialized (lower(segmentgroup_id));
CREATE INDEX idx_hierarchy_segmentgroup_id_unicode_lower ON ahb_hierarchy_materialized (REPLACE(REPLACE(REPLACE(LOWER(segmentgroup_id), 'Ä', 'ä'), 'Ö', 'ö'), 'Ü', 'ü'));
CREATE INDEX idx_hierarchy_segmentgroup_name ON ahb_hierarchy_materialized (segmentgroup_name);
CREATE INDEX idx_hierarchy_segmentgroup_position ON ahb_hierarchy_materialized (segmentgroup_position);
CREATE INDEX idx_hierarchy_segment_id ON ahb_hierarchy_materialized (segment_id);
CREATE INDEX idx_hierarchy_segment_id_lower ON ahb_hierarchy_materialized (lower(segment_id));
CREATE INDEX idx_hierarchy_segment_id_unicode_lower ON ahb_hierarchy_materialized (REPLACE(REPLACE(REPLACE(LOWER(segment_id), 'Ä', 'ä'), 'Ö', 'ö'), 'Ü', 'ü'));
CREATE INDEX idx_hierarchy_segment_name ON ahb_hierarchy_materialized (segment_name);
CREATE INDEX idx_hierarchy_segment_number ON ahb_hierarchy_materialized (segment_number);
CREATE INDEX idx_hierarchy_segment_position ON ahb_hierarchy_materialized (segment_position);
Expand All @@ -652,15 +655,18 @@ CREATE INDEX idx_hierarchy_dataelementgroup_name ON ahb_hierarchy_materialized (
CREATE INDEX idx_hierarchy_dataelementgroup_position ON ahb_hierarchy_materialized (dataelementgroup_position);
CREATE INDEX idx_hierarchy_dataelement_id ON ahb_hierarchy_materialized (dataelement_id);
CREATE INDEX idx_hierarchy_dataelement_id_lower ON ahb_hierarchy_materialized (lower(dataelement_id));
CREATE INDEX idx_hierarchy_dataelement_id_unicode_lower ON ahb_hierarchy_materialized (REPLACE(REPLACE(REPLACE(LOWER(dataelement_id), 'Ä', 'ä'), 'Ö', 'ö'), 'Ü', 'ü'));
CREATE INDEX idx_hierarchy_dataelement_name ON ahb_hierarchy_materialized (dataelement_name);
CREATE INDEX idx_hierarchy_dataelement_position ON ahb_hierarchy_materialized (dataelement_position);
CREATE INDEX idx_hierarchy_dataelement_ahb_status ON ahb_hierarchy_materialized (dataelement_ahb_status);
CREATE INDEX idx_hierarchy_code_id ON ahb_hierarchy_materialized (code_id);
CREATE INDEX idx_hierarchy_code_name ON ahb_hierarchy_materialized (code_name);
CREATE INDEX idx_hierarchy_code_description ON ahb_hierarchy_materialized (code_description);
CREATE INDEX idx_hierarchy_code_description_lower ON ahb_hierarchy_materialized (lower(code_description));
CREATE INDEX idx_hierarchy_code_description_unicode_lower ON ahb_hierarchy_materialized (REPLACE(REPLACE(REPLACE(LOWER(code_description), 'Ä', 'ä'), 'Ö', 'ö'), 'Ü', 'ü'));
CREATE INDEX idx_hierarchy_code_value ON ahb_hierarchy_materialized (code_value);
CREATE INDEX idx_hierarchy_code_value_lower ON ahb_hierarchy_materialized (lower(code_value));
CREATE INDEX idx_hierarchy_code_value_unicode_lower ON ahb_hierarchy_materialized (REPLACE(REPLACE(REPLACE(LOWER(code_value), 'Ä', 'ä'), 'Ö', 'ö'), 'Ü', 'ü'));
CREATE INDEX idx_hierarchy_code_ahb_status ON ahb_hierarchy_materialized (code_ahb_status);
CREATE INDEX idx_hierarchy_code_position ON ahb_hierarchy_materialized (code_position);
CREATE INDEX idx_hierarchy_path ON ahb_hierarchy_materialized (path);
Expand All @@ -674,8 +680,10 @@ CREATE INDEX idx_ahb_tabellen_filter2 ON ahb_hierarchy_materialized (type) WHERE
-- indexes for computed columns for v_ahbtabellen
CREATE INDEX idx_line_ahb_status ON ahb_hierarchy_materialized (line_ahb_status);
CREATE INDEX idx_line_ahb_status_lower ON ahb_hierarchy_materialized (lower(line_ahb_status));
CREATE INDEX idx_line_ahb_status_unicode_lower ON ahb_hierarchy_materialized (REPLACE(REPLACE(REPLACE(LOWER(line_ahb_status), 'Ä', 'ä'), 'Ö', 'ö'), 'Ü', 'ü'));
CREATE INDEX idx_line_name ON ahb_hierarchy_materialized (line_name);
CREATE INDEX idx_line_name_lower ON ahb_hierarchy_materialized (lower(line_name));
CREATE INDEX idx_line_name_unicode_lower ON ahb_hierarchy_materialized (REPLACE(REPLACE(REPLACE(LOWER(line_name), 'Ä', 'ä'), 'Ö', 'ö'), 'Ü', 'ü'));
CREATE INDEX idx_hierarchy_sort_path_per_ahb ON ahb_hierarchy_materialized (sort_path, pruefidentifikator, edifact_format_version);

-- Fallback: append occurrence counter '#N' to any id_paths that are still not unique after qualifier injection.
Expand Down