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:
2026-02-07 22:53:12 -05:00
parent 98f2913eb5
commit 516cec5a7f
13 changed files with 1831 additions and 229 deletions
+30 -25
View File
@@ -3,6 +3,7 @@ package handlers
import (
"bookhoard/internal/database"
"bookhoard/internal/services"
"bookhoard/internal/utils"
"io"
"mime"
"net/http"
@@ -29,27 +30,27 @@ type CreateMediaItemRequest struct {
CoverImagePath string `json:"cover_image_path"`
Series string `json:"series"`
SeriesNumber int32 `json:"series_number"`
Tags string `json:"tags"`
Tags []string `json:"tags"`
ASIN string `json:"asin"`
DatePublished string `json:"date_published"`
Publisher string `json:"publisher"`
Contributors string `json:"contributors"`
Contributors []string `json:"contributors"`
}
// UpdateMediaItemRequest represents the request for updating a media item
type UpdateMediaItemRequest struct {
Title string `json:"title" validate:"required,min=1,max=500"`
Author string `json:"author"`
ISBN string `json:"isbn"`
Description string `json:"description"`
CoverImagePath string `json:"cover_image_path"`
Series string `json:"series"`
SeriesNumber int32 `json:"series_number"`
Tags string `json:"tags"`
ASIN string `json:"asin"`
DatePublished string `json:"date_published"`
Publisher string `json:"publisher"`
Contributors string `json:"contributors"`
Title string `json:"title" validate:"required,min=1,max=500"`
Author string `json:"author"`
ISBN string `json:"isbn"`
Description string `json:"description"`
CoverImagePath string `json:"cover_image_path"`
Series string `json:"series"`
SeriesNumber int32 `json:"series_number"`
Tags []string `json:"tags"`
ASIN string `json:"asin"`
DatePublished string `json:"date_published"`
Publisher string `json:"publisher"`
Contributors []string `json:"contributors"`
}
// CreateMediaNoteRequest represents the request for creating a media note
@@ -419,11 +420,11 @@ func (h *MediaHandler) HandleBulkUpdate(c echo.Context) error {
Updates []struct {
BookID string `json:"book_id" validate:"required"`
Updates struct {
Title *string `json:"title,omitempty"`
Author *string `json:"author,omitempty"`
Genre *string `json:"genre,omitempty"`
Language *string `json:"language,omitempty"`
Tags *string `json:"tags,omitempty"`
Title *string `json:"title,omitempty"`
Author *string `json:"author,omitempty"`
Genre *string `json:"genre,omitempty"`
Language *string `json:"language,omitempty"`
Tags []string `json:"tags,omitempty"`
} `json:"updates"`
} `json:"updates" validate:"required"`
}
@@ -500,8 +501,8 @@ func (h *MediaHandler) HandleBulkUpdate(c echo.Context) error {
if update.Updates.Language != nil {
updateParams.Language = pgtype.Text{String: *update.Updates.Language, Valid: true}
}
if update.Updates.Tags != nil {
updateParams.Tags = pgtype.Text{String: *update.Updates.Tags, Valid: true}
if update.Updates.Tags != nil && len(update.Updates.Tags) > 0 {
updateParams.Tags = update.Updates.Tags
}
_, err = h.db.UpdateMediaItem(c.Request().Context(), updateParams)
@@ -888,6 +889,10 @@ func (mh *MediaHandler) CreateMediaItem(c echo.Context) error {
return c.JSON(http.StatusBadRequest, map[string]string{"error": err.Error()})
}
if len(req.Tags) > 0 {
req.Tags = utils.NormalizeTags(req.Tags)
}
_, err := mh.db.GetLibrary(c.Request().Context(), pgtype.UUID{Bytes: req.LibraryID, Valid: true})
if err != nil {
if err == pgx.ErrNoRows {
@@ -908,11 +913,11 @@ func (mh *MediaHandler) CreateMediaItem(c echo.Context) error {
CoverImagePath: pgtype.Text{String: req.CoverImagePath, Valid: req.CoverImagePath != ""},
Series: pgtype.Text{String: req.Series, Valid: req.Series != ""},
SeriesNumber: pgtype.Int4{Int32: req.SeriesNumber, Valid: req.SeriesNumber > 0},
Tags: pgtype.Text{String: req.Tags, Valid: req.Tags != ""},
Tags: req.Tags,
Asin: pgtype.Text{String: req.ASIN, Valid: req.ASIN != ""},
DatePublished: pgtype.Date{Time: parseDate(req.DatePublished), Valid: req.DatePublished != ""},
Publisher: pgtype.Text{String: req.Publisher, Valid: req.Publisher != ""},
Contributors: pgtype.Text{String: req.Contributors, Valid: req.Contributors != ""},
Contributors: req.Contributors,
AddedByAdminID: user.ID,
})
if err != nil {
@@ -958,11 +963,11 @@ func (mh *MediaHandler) UpdateMediaItem(c echo.Context) error {
CoverImagePath: pgtype.Text{String: req.CoverImagePath, Valid: req.CoverImagePath != ""},
Series: pgtype.Text{String: req.Series, Valid: req.Series != ""},
SeriesNumber: pgtype.Int4{Int32: req.SeriesNumber, Valid: req.SeriesNumber > 0},
Tags: pgtype.Text{String: req.Tags, Valid: req.Tags != ""},
Tags: req.Tags,
Asin: pgtype.Text{String: req.ASIN, Valid: req.ASIN != ""},
DatePublished: pgtype.Date{Time: parseDate(req.DatePublished), Valid: req.DatePublished != ""},
Publisher: pgtype.Text{String: req.Publisher, Valid: req.Publisher != ""},
Contributors: pgtype.Text{String: req.Contributors, Valid: req.Contributors != ""},
Contributors: req.Contributors,
})
if err != nil {
return c.JSON(http.StatusInternalServerError, map[string]string{"error": err.Error()})