feat: migrate tags and contributors from TEXT to TEXT[] arrays
Convert tags and contributors columns from comma-separated strings to PostgreSQL TEXT[] arrays for better data normalization and query performance. Database Changes: - schema.sql: Change tags/contributors from TEXT to TEXT[] - schema.sql: Add GIN indexes for fast array searches - queries.sql: Update search queries to use ANY() operator - queries.sql: Update fuzzy search with unnest() for arrays Generated Code (sqlc): - models.go: Auto-generated with []string types for tags/contributors - queries.sql.go: Auto-generated with proper array handling Handler Changes: - media.go: Update request structs to use []string for tags/contributors - media.go: Remove pgtype.Text wrapping, use direct array assignment - media.go: Add tag normalization in CreateMediaItemHandler - collections.go: Update tags evaluation to join arrays for comparison - collections.go: Add strings import for Join() function Service Changes: - ebook_scanner.go: Update EbookMetadata struct to use []string - ebook_scanner.go: Remove string Join(), assign arrays directly - collection_service.go: Update tags rule evaluation to join arrays - collection_service.go: Add strings import New Utilities: - internal/utils/tags.go: Create NormalizeTags(), JoinTags(), SplitTags() - Normalizes tags by trimming, lowercasing, removing duplicates/empties API Documentation: - bruno/media-items/Create Media Item.bru: Update examples to use arrays - bruno/media-items/Update Media Item.bru: Update examples to use arrays - Update docs: tags/contributors now array of string Breaking Change: - JSON format changes from "tags": "tag1,tag2" to "tags": ["tag1", "tag2"] - Tests already use array format (no changes needed) Benefits: - GIN indexes enable faster array searches - Normalization prevents data quality issues (case, duplicates) - Array operations use PostgreSQL native operators (ANY, &&, unnest) - Better separation of concerns (no string parsing in application)
This commit is contained in:
@@ -342,7 +342,7 @@ RETURNING id, device_id, media_item_id, bookhoard_uuid, kobo_content_id, content
|
||||
type CreateDeviceCatalogParams struct {
|
||||
DeviceID pgtype.UUID `db:"device_id" json:"device_id"`
|
||||
MediaItemID pgtype.UUID `db:"media_item_id" json:"media_item_id"`
|
||||
BookhoardUuid pgtype.UUID `db:"bookhoard_uuid" json:"bookhoard_uuid"`
|
||||
BookhoardUuid pgtype.UUID `db:"bookhoard_uuid" json:"bookhoard_uuid"`
|
||||
KoboContentID string `db:"kobo_content_id" json:"kobo_content_id"`
|
||||
ContentIDType pgtype.Text `db:"content_id_type" json:"content_id_type"`
|
||||
Available pgtype.Bool `db:"available" json:"available"`
|
||||
@@ -602,11 +602,11 @@ type CreateMediaItemParams struct {
|
||||
CoverImagePath pgtype.Text `db:"cover_image_path" json:"cover_image_path"`
|
||||
Series pgtype.Text `db:"series" json:"series"`
|
||||
SeriesNumber pgtype.Int4 `db:"series_number" json:"series_number"`
|
||||
Tags pgtype.Text `db:"tags" json:"tags"`
|
||||
Tags []string `db:"tags" json:"tags"`
|
||||
Asin pgtype.Text `db:"asin" json:"asin"`
|
||||
DatePublished pgtype.Date `db:"date_published" json:"date_published"`
|
||||
Publisher pgtype.Text `db:"publisher" json:"publisher"`
|
||||
Contributors pgtype.Text `db:"contributors" json:"contributors"`
|
||||
Contributors []string `db:"contributors" json:"contributors"`
|
||||
Language pgtype.Text `db:"language" json:"language"`
|
||||
Edition pgtype.Text `db:"edition" json:"edition"`
|
||||
PageCount pgtype.Int4 `db:"page_count" json:"page_count"`
|
||||
@@ -1824,7 +1824,7 @@ SELECT id, device_id, media_item_id, bookhoard_uuid, kobo_content_id, content_id
|
||||
`
|
||||
|
||||
type GetDeviceCatalogByBookhoardUUIDParams struct {
|
||||
DeviceID pgtype.UUID `db:"device_id" json:"device_id"`
|
||||
DeviceID pgtype.UUID `db:"device_id" json:"device_id"`
|
||||
BookhoardUuid pgtype.UUID `db:"bookhoard_uuid" json:"bookhoard_uuid"`
|
||||
}
|
||||
|
||||
@@ -1880,7 +1880,7 @@ type GetDeviceCatalogEntriesRow struct {
|
||||
ID pgtype.UUID `db:"id" json:"id"`
|
||||
DeviceID pgtype.UUID `db:"device_id" json:"device_id"`
|
||||
MediaItemID pgtype.UUID `db:"media_item_id" json:"media_item_id"`
|
||||
BookhoardUuid pgtype.UUID `db:"bookhoard_uuid" json:"bookhoard_uuid"`
|
||||
BookhoardUuid pgtype.UUID `db:"bookhoard_uuid" json:"bookhoard_uuid"`
|
||||
KoboContentID string `db:"kobo_content_id" json:"kobo_content_id"`
|
||||
ContentIDType pgtype.Text `db:"content_id_type" json:"content_id_type"`
|
||||
Available pgtype.Bool `db:"available" json:"available"`
|
||||
@@ -4931,11 +4931,11 @@ type ListMediaItemsRow struct {
|
||||
CoverImagePath pgtype.Text `db:"cover_image_path" json:"cover_image_path"`
|
||||
Series pgtype.Text `db:"series" json:"series"`
|
||||
SeriesNumber pgtype.Int4 `db:"series_number" json:"series_number"`
|
||||
Tags pgtype.Text `db:"tags" json:"tags"`
|
||||
Tags []string `db:"tags" json:"tags"`
|
||||
Asin pgtype.Text `db:"asin" json:"asin"`
|
||||
DatePublished pgtype.Date `db:"date_published" json:"date_published"`
|
||||
Publisher pgtype.Text `db:"publisher" json:"publisher"`
|
||||
Contributors pgtype.Text `db:"contributors" json:"contributors"`
|
||||
Contributors []string `db:"contributors" json:"contributors"`
|
||||
Language pgtype.Text `db:"language" json:"language"`
|
||||
Edition pgtype.Text `db:"edition" json:"edition"`
|
||||
PageCount pgtype.Int4 `db:"page_count" json:"page_count"`
|
||||
@@ -5052,11 +5052,11 @@ type ListMediaItemsByLibraryRow struct {
|
||||
CoverImagePath pgtype.Text `db:"cover_image_path" json:"cover_image_path"`
|
||||
Series pgtype.Text `db:"series" json:"series"`
|
||||
SeriesNumber pgtype.Int4 `db:"series_number" json:"series_number"`
|
||||
Tags pgtype.Text `db:"tags" json:"tags"`
|
||||
Tags []string `db:"tags" json:"tags"`
|
||||
Asin pgtype.Text `db:"asin" json:"asin"`
|
||||
DatePublished pgtype.Date `db:"date_published" json:"date_published"`
|
||||
Publisher pgtype.Text `db:"publisher" json:"publisher"`
|
||||
Contributors pgtype.Text `db:"contributors" json:"contributors"`
|
||||
Contributors []string `db:"contributors" json:"contributors"`
|
||||
Language pgtype.Text `db:"language" json:"language"`
|
||||
Edition pgtype.Text `db:"edition" json:"edition"`
|
||||
PageCount pgtype.Int4 `db:"page_count" json:"page_count"`
|
||||
@@ -5223,11 +5223,11 @@ type ListMediaItemsFilteredRow struct {
|
||||
CoverImagePath pgtype.Text `db:"cover_image_path" json:"cover_image_path"`
|
||||
Series pgtype.Text `db:"series" json:"series"`
|
||||
SeriesNumber pgtype.Int4 `db:"series_number" json:"series_number"`
|
||||
Tags pgtype.Text `db:"tags" json:"tags"`
|
||||
Tags []string `db:"tags" json:"tags"`
|
||||
Asin pgtype.Text `db:"asin" json:"asin"`
|
||||
DatePublished pgtype.Date `db:"date_published" json:"date_published"`
|
||||
Publisher pgtype.Text `db:"publisher" json:"publisher"`
|
||||
Contributors pgtype.Text `db:"contributors" json:"contributors"`
|
||||
Contributors []string `db:"contributors" json:"contributors"`
|
||||
Language pgtype.Text `db:"language" json:"language"`
|
||||
Edition pgtype.Text `db:"edition" json:"edition"`
|
||||
PageCount pgtype.Int4 `db:"page_count" json:"page_count"`
|
||||
@@ -5430,11 +5430,11 @@ type ListMediaItemsSortedRow struct {
|
||||
CoverImagePath pgtype.Text `db:"cover_image_path" json:"cover_image_path"`
|
||||
Series pgtype.Text `db:"series" json:"series"`
|
||||
SeriesNumber pgtype.Int4 `db:"series_number" json:"series_number"`
|
||||
Tags pgtype.Text `db:"tags" json:"tags"`
|
||||
Tags []string `db:"tags" json:"tags"`
|
||||
Asin pgtype.Text `db:"asin" json:"asin"`
|
||||
DatePublished pgtype.Date `db:"date_published" json:"date_published"`
|
||||
Publisher pgtype.Text `db:"publisher" json:"publisher"`
|
||||
Contributors pgtype.Text `db:"contributors" json:"contributors"`
|
||||
Contributors []string `db:"contributors" json:"contributors"`
|
||||
Language pgtype.Text `db:"language" json:"language"`
|
||||
Edition pgtype.Text `db:"edition" json:"edition"`
|
||||
PageCount pgtype.Int4 `db:"page_count" json:"page_count"`
|
||||
@@ -6052,16 +6052,16 @@ WHERE COALESCE(lv.is_visible, true) = true
|
||||
AND (
|
||||
mi.title ILIKE $2 OR
|
||||
mi.author ILIKE $2 OR
|
||||
mi.series ILIKE $2 OR
|
||||
mi.tags ILIKE $2 OR
|
||||
mi.contributors ILIKE $2
|
||||
mi.series ILIKE $2 OR
|
||||
$2 = ANY(mi.tags) OR
|
||||
$2 = ANY(mi.contributors)
|
||||
)
|
||||
ORDER BY
|
||||
CASE
|
||||
CASE
|
||||
WHEN mi.title ILIKE $2 THEN 1
|
||||
WHEN mi.author ILIKE $2 THEN 2
|
||||
WHEN mi.series ILIKE $2 THEN 3
|
||||
WHEN mi.tags ILIKE $2 THEN 4
|
||||
WHEN $2 = ANY(mi.tags) THEN 4
|
||||
ELSE 5
|
||||
END,
|
||||
mi.title ASC
|
||||
@@ -6088,11 +6088,11 @@ type SearchMediaItemsRow struct {
|
||||
CoverImagePath pgtype.Text `db:"cover_image_path" json:"cover_image_path"`
|
||||
Series pgtype.Text `db:"series" json:"series"`
|
||||
SeriesNumber pgtype.Int4 `db:"series_number" json:"series_number"`
|
||||
Tags pgtype.Text `db:"tags" json:"tags"`
|
||||
Tags []string `db:"tags" json:"tags"`
|
||||
Asin pgtype.Text `db:"asin" json:"asin"`
|
||||
DatePublished pgtype.Date `db:"date_published" json:"date_published"`
|
||||
Publisher pgtype.Text `db:"publisher" json:"publisher"`
|
||||
Contributors pgtype.Text `db:"contributors" json:"contributors"`
|
||||
Contributors []string `db:"contributors" json:"contributors"`
|
||||
Language pgtype.Text `db:"language" json:"language"`
|
||||
Edition pgtype.Text `db:"edition" json:"edition"`
|
||||
PageCount pgtype.Int4 `db:"page_count" json:"page_count"`
|
||||
@@ -6202,23 +6202,39 @@ JOIN libraries l ON mi.library_id = l.id
|
||||
JOIN library_types lt ON l.library_type_id = lt.id
|
||||
LEFT JOIN library_visibility lv ON l.id = lv.library_id AND lv.user_id = $1
|
||||
WHERE COALESCE(lv.is_visible, true) = true
|
||||
AND (
|
||||
word_similarity($2, mi.title) > 0.3 OR
|
||||
word_similarity($2, COALESCE(mi.author, '')) > 0.3 OR
|
||||
word_similarity($2, COALESCE(mi.series, '')) > 0.3 OR
|
||||
word_similarity($2, COALESCE(mi.tags, '')) > 0.3 OR
|
||||
word_similarity($2, COALESCE(mi.contributors, '')) > 0.3
|
||||
)
|
||||
ORDER BY
|
||||
GREATEST(
|
||||
word_similarity($2, mi.title),
|
||||
word_similarity($2, COALESCE(mi.author, '')),
|
||||
word_similarity($2, COALESCE(mi.series, '')),
|
||||
word_similarity($2, COALESCE(mi.tags, '')),
|
||||
word_similarity($2, COALESCE(mi.contributors, ''))
|
||||
) DESC,
|
||||
mi.title ASC
|
||||
LIMIT $4 OFFSET $3
|
||||
AND (
|
||||
word_similarity($2, mi.title) > 0.3 OR
|
||||
word_similarity($2, COALESCE(mi.author, '')) > 0.3 OR
|
||||
word_similarity($2, COALESCE(mi.series, '')) > 0.3 OR
|
||||
EXISTS (
|
||||
SELECT 1 FROM unnest(mi.tags) AS tag
|
||||
WHERE word_similarity($2, tag) > 0.3
|
||||
LIMIT 1
|
||||
) OR
|
||||
EXISTS (
|
||||
SELECT 1 FROM unnest(mi.contributors) AS contributor
|
||||
WHERE word_similarity($2, contributor) > 0.3
|
||||
LIMIT 1
|
||||
)
|
||||
)
|
||||
ORDER BY
|
||||
GREATEST(
|
||||
word_similarity($2, mi.title),
|
||||
word_similarity($2, COALESCE(mi.author, '')),
|
||||
word_similarity($2, COALESCE(mi.series, '')),
|
||||
COALESCE(
|
||||
(SELECT MAX(word_similarity($2, tag))
|
||||
FROM unnest(mi.tags) AS tag),
|
||||
0
|
||||
),
|
||||
COALESCE(
|
||||
(SELECT MAX(word_similarity($2, contributor))
|
||||
FROM unnest(mi.contributors) AS contributor),
|
||||
0
|
||||
)
|
||||
) DESC,
|
||||
mi.title ASC
|
||||
LIMIT $4 OFFSET $3
|
||||
`
|
||||
|
||||
type SearchMediaItemsFuzzyParams struct {
|
||||
@@ -6241,11 +6257,11 @@ type SearchMediaItemsFuzzyRow struct {
|
||||
CoverImagePath pgtype.Text `db:"cover_image_path" json:"cover_image_path"`
|
||||
Series pgtype.Text `db:"series" json:"series"`
|
||||
SeriesNumber pgtype.Int4 `db:"series_number" json:"series_number"`
|
||||
Tags pgtype.Text `db:"tags" json:"tags"`
|
||||
Tags []string `db:"tags" json:"tags"`
|
||||
Asin pgtype.Text `db:"asin" json:"asin"`
|
||||
DatePublished pgtype.Date `db:"date_published" json:"date_published"`
|
||||
Publisher pgtype.Text `db:"publisher" json:"publisher"`
|
||||
Contributors pgtype.Text `db:"contributors" json:"contributors"`
|
||||
Contributors []string `db:"contributors" json:"contributors"`
|
||||
Language pgtype.Text `db:"language" json:"language"`
|
||||
Edition pgtype.Text `db:"edition" json:"edition"`
|
||||
PageCount pgtype.Int4 `db:"page_count" json:"page_count"`
|
||||
@@ -6946,11 +6962,11 @@ type UpdateMediaItemParams struct {
|
||||
CoverImagePath pgtype.Text `db:"cover_image_path" json:"cover_image_path"`
|
||||
Series pgtype.Text `db:"series" json:"series"`
|
||||
SeriesNumber pgtype.Int4 `db:"series_number" json:"series_number"`
|
||||
Tags pgtype.Text `db:"tags" json:"tags"`
|
||||
Tags []string `db:"tags" json:"tags"`
|
||||
Asin pgtype.Text `db:"asin" json:"asin"`
|
||||
DatePublished pgtype.Date `db:"date_published" json:"date_published"`
|
||||
Publisher pgtype.Text `db:"publisher" json:"publisher"`
|
||||
Contributors pgtype.Text `db:"contributors" json:"contributors"`
|
||||
Contributors []string `db:"contributors" json:"contributors"`
|
||||
Language pgtype.Text `db:"language" json:"language"`
|
||||
Edition pgtype.Text `db:"edition" json:"edition"`
|
||||
PageCount pgtype.Int4 `db:"page_count" json:"page_count"`
|
||||
|
||||
Reference in New Issue
Block a user