Fix: Remove broken getKlausurApiUrl and clean up empty lines

sed replacement left orphaned hostname references in story page and empty lines in getApiBase functions. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-24 16:02:04 +02:00
parent b07f802c24
commit 9ba420fa91
150 changed files with 30231 additions and 32053 deletions
--- a/edu-search-service/internal/database/repository_staff.go
+++ b/edu-search-service/internal/database/repository_staff.go
@@ -0,0 +1,398 @@
+package database
+
+import (
+	"context"
+	"fmt"
+	"strings"
+
+	"github.com/google/uuid"
+)
+
+// ============================================================================
+// STAFF
+// ============================================================================
+
+// CreateStaff creates or updates a staff member
+func (r *Repository) CreateStaff(ctx context.Context, s *UniversityStaff) error {
+	query := `
+		INSERT INTO university_staff (
+			university_id, department_id, first_name, last_name, full_name,
+			title, academic_title, position, position_type, is_professor,
+			email, phone, office, profile_url, photo_url,
+			orcid, google_scholar_id, researchgate_url, linkedin_url, personal_website,
+			research_interests, research_summary, supervisor_id, team_role, source_url
+		) VALUES (
+			$1, $2, $3, $4, $5, $6, $7, $8, $9, $10,
+			$11, $12, $13, $14, $15, $16, $17, $18, $19, $20,
+			$21, $22, $23, $24, $25
+		)
+		ON CONFLICT (university_id, first_name, last_name, COALESCE(department_id, '00000000-0000-0000-0000-000000000000'::uuid))
+		DO UPDATE SET
+			full_name = EXCLUDED.full_name,
+			title = EXCLUDED.title,
+			academic_title = EXCLUDED.academic_title,
+			position = EXCLUDED.position,
+			position_type = EXCLUDED.position_type,
+			is_professor = EXCLUDED.is_professor,
+			email = COALESCE(EXCLUDED.email, university_staff.email),
+			phone = COALESCE(EXCLUDED.phone, university_staff.phone),
+			office = COALESCE(EXCLUDED.office, university_staff.office),
+			profile_url = COALESCE(EXCLUDED.profile_url, university_staff.profile_url),
+			photo_url = COALESCE(EXCLUDED.photo_url, university_staff.photo_url),
+			orcid = COALESCE(EXCLUDED.orcid, university_staff.orcid),
+			google_scholar_id = COALESCE(EXCLUDED.google_scholar_id, university_staff.google_scholar_id),
+			researchgate_url = COALESCE(EXCLUDED.researchgate_url, university_staff.researchgate_url),
+			linkedin_url = COALESCE(EXCLUDED.linkedin_url, university_staff.linkedin_url),
+			personal_website = COALESCE(EXCLUDED.personal_website, university_staff.personal_website),
+			research_interests = COALESCE(EXCLUDED.research_interests, university_staff.research_interests),
+			research_summary = COALESCE(EXCLUDED.research_summary, university_staff.research_summary),
+			supervisor_id = COALESCE(EXCLUDED.supervisor_id, university_staff.supervisor_id),
+			team_role = COALESCE(EXCLUDED.team_role, university_staff.team_role),
+			source_url = COALESCE(EXCLUDED.source_url, university_staff.source_url),
+			crawled_at = NOW(),
+			updated_at = NOW()
+		RETURNING id, crawled_at, created_at, updated_at
+	`
+	return r.db.Pool.QueryRow(ctx, query,
+		s.UniversityID, s.DepartmentID, s.FirstName, s.LastName, s.FullName,
+		s.Title, s.AcademicTitle, s.Position, s.PositionType, s.IsProfessor,
+		s.Email, s.Phone, s.Office, s.ProfileURL, s.PhotoURL,
+		s.ORCID, s.GoogleScholarID, s.ResearchgateURL, s.LinkedInURL, s.PersonalWebsite,
+		s.ResearchInterests, s.ResearchSummary, s.SupervisorID, s.TeamRole, s.SourceURL,
+	).Scan(&s.ID, &s.CrawledAt, &s.CreatedAt, &s.UpdatedAt)
+}
+
+// GetStaff retrieves a staff member by ID
+func (r *Repository) GetStaff(ctx context.Context, id uuid.UUID) (*UniversityStaff, error) {
+	query := `SELECT * FROM v_staff_full WHERE id = $1`
+
+	s := &UniversityStaff{}
+	err := r.db.Pool.QueryRow(ctx, query, id).Scan(
+		&s.ID, &s.UniversityID, &s.DepartmentID, &s.FirstName, &s.LastName, &s.FullName,
+		&s.Title, &s.AcademicTitle, &s.Position, &s.PositionType, &s.IsProfessor,
+		&s.Email, &s.Phone, &s.Office, &s.ProfileURL, &s.PhotoURL,
+		&s.ORCID, &s.GoogleScholarID, &s.ResearchgateURL, &s.LinkedInURL, &s.PersonalWebsite,
+		&s.ResearchInterests, &s.ResearchSummary, &s.CrawledAt, &s.LastVerified, &s.IsActive, &s.SourceURL,
+		&s.CreatedAt, &s.UpdatedAt, &s.UniversityName, &s.UniversityShort, nil, nil,
+		&s.DepartmentName, nil, &s.PublicationCount,
+	)
+	if err != nil {
+		return nil, err
+	}
+	return s, nil
+}
+
+// SearchStaff searches for staff members
+func (r *Repository) SearchStaff(ctx context.Context, params StaffSearchParams) (*StaffSearchResult, error) {
+	// Build query dynamically
+	var conditions []string
+	var args []interface{}
+	argNum := 1
+
+	baseQuery := `
+		SELECT s.id, s.university_id, s.department_id, s.first_name, s.last_name, s.full_name,
+			s.title, s.academic_title, s.position, s.position_type, s.is_professor,
+			s.email, s.profile_url, s.photo_url, s.orcid,
+			s.research_interests, s.crawled_at, s.is_active,
+			u.name as university_name, u.short_name as university_short, u.state as university_state,
+			d.name as department_name,
+			(SELECT COUNT(*) FROM staff_publications sp WHERE sp.staff_id = s.id) as publication_count
+		FROM university_staff s
+		JOIN universities u ON s.university_id = u.id
+		LEFT JOIN departments d ON s.department_id = d.id
+	`
+
+	if params.Query != "" {
+		conditions = append(conditions, fmt.Sprintf(
+			`(to_tsvector('german', COALESCE(s.full_name, '') || ' ' || COALESCE(s.research_summary, '')) @@ plainto_tsquery('german', $%d)
+			 OR s.full_name ILIKE '%%' || $%d || '%%'
+			 OR s.last_name ILIKE '%%' || $%d || '%%')`,
+			argNum, argNum, argNum))
+		args = append(args, params.Query)
+		argNum++
+	}
+
+	if params.UniversityID != nil {
+		conditions = append(conditions, fmt.Sprintf("s.university_id = $%d", argNum))
+		args = append(args, *params.UniversityID)
+		argNum++
+	}
+
+	if params.DepartmentID != nil {
+		conditions = append(conditions, fmt.Sprintf("s.department_id = $%d", argNum))
+		args = append(args, *params.DepartmentID)
+		argNum++
+	}
+
+	if params.State != nil {
+		conditions = append(conditions, fmt.Sprintf("u.state = $%d", argNum))
+		args = append(args, *params.State)
+		argNum++
+	}
+
+	if params.UniType != nil {
+		conditions = append(conditions, fmt.Sprintf("u.uni_type = $%d", argNum))
+		args = append(args, *params.UniType)
+		argNum++
+	}
+
+	if params.PositionType != nil {
+		conditions = append(conditions, fmt.Sprintf("s.position_type = $%d", argNum))
+		args = append(args, *params.PositionType)
+		argNum++
+	}
+
+	if params.IsProfessor != nil {
+		conditions = append(conditions, fmt.Sprintf("s.is_professor = $%d", argNum))
+		args = append(args, *params.IsProfessor)
+		argNum++
+	}
+
+	// Build WHERE clause
+	whereClause := ""
+	if len(conditions) > 0 {
+		whereClause = "WHERE " + strings.Join(conditions, " AND ")
+	}
+
+	// Count total
+	countQuery := fmt.Sprintf("SELECT COUNT(*) FROM university_staff s JOIN universities u ON s.university_id = u.id LEFT JOIN departments d ON s.department_id = d.id %s", whereClause)
+	var total int
+	if err := r.db.Pool.QueryRow(ctx, countQuery, args...).Scan(&total); err != nil {
+		return nil, err
+	}
+
+	// Apply pagination
+	limit := params.Limit
+	if limit <= 0 {
+		limit = 20
+	}
+	if limit > 100 {
+		limit = 100
+	}
+
+	offset := params.Offset
+	if offset < 0 {
+		offset = 0
+	}
+
+	// Full query with pagination
+	fullQuery := fmt.Sprintf("%s %s ORDER BY s.is_professor DESC, s.last_name ASC LIMIT %d OFFSET %d",
+		baseQuery, whereClause, limit, offset)
+
+	rows, err := r.db.Pool.Query(ctx, fullQuery, args...)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+
+	var staff []UniversityStaff
+	for rows.Next() {
+		var s UniversityStaff
+		var uniState *string
+		if err := rows.Scan(
+			&s.ID, &s.UniversityID, &s.DepartmentID, &s.FirstName, &s.LastName, &s.FullName,
+			&s.Title, &s.AcademicTitle, &s.Position, &s.PositionType, &s.IsProfessor,
+			&s.Email, &s.ProfileURL, &s.PhotoURL, &s.ORCID,
+			&s.ResearchInterests, &s.CrawledAt, &s.IsActive,
+			&s.UniversityName, &s.UniversityShort, &uniState,
+			&s.DepartmentName, &s.PublicationCount,
+		); err != nil {
+			return nil, err
+		}
+		staff = append(staff, s)
+	}
+
+	return &StaffSearchResult{
+		Staff:  staff,
+		Total:  total,
+		Limit:  limit,
+		Offset: offset,
+		Query:  params.Query,
+	}, rows.Err()
+}
+
+// ============================================================================
+// PUBLICATIONS
+// ============================================================================
+
+// CreatePublication creates or updates a publication
+func (r *Repository) CreatePublication(ctx context.Context, p *Publication) error {
+	query := `
+		INSERT INTO publications (
+			title, title_en, abstract, abstract_en, year, month,
+			pub_type, venue, venue_short, publisher,
+			doi, isbn, issn, arxiv_id, pubmed_id,
+			url, pdf_url, citation_count, keywords, topics, source, raw_data
+		) VALUES (
+			$1, $2, $3, $4, $5, $6, $7, $8, $9, $10,
+			$11, $12, $13, $14, $15, $16, $17, $18, $19, $20, $21, $22
+		)
+		ON CONFLICT (doi) WHERE doi IS NOT NULL DO UPDATE SET
+			title = EXCLUDED.title,
+			abstract = EXCLUDED.abstract,
+			year = EXCLUDED.year,
+			venue = EXCLUDED.venue,
+			citation_count = EXCLUDED.citation_count,
+			updated_at = NOW()
+		RETURNING id, crawled_at, created_at, updated_at
+	`
+
+	// Handle potential duplicate without DOI
+	err := r.db.Pool.QueryRow(ctx, query,
+		p.Title, p.TitleEN, p.Abstract, p.AbstractEN, p.Year, p.Month,
+		p.PubType, p.Venue, p.VenueShort, p.Publisher,
+		p.DOI, p.ISBN, p.ISSN, p.ArxivID, p.PubmedID,
+		p.URL, p.PDFURL, p.CitationCount, p.Keywords, p.Topics, p.Source, p.RawData,
+	).Scan(&p.ID, &p.CrawledAt, &p.CreatedAt, &p.UpdatedAt)
+
+	if err != nil && strings.Contains(err.Error(), "duplicate") {
+		// Try to find existing publication by title and year
+		findQuery := `SELECT id FROM publications WHERE title = $1 AND year = $2`
+		err = r.db.Pool.QueryRow(ctx, findQuery, p.Title, p.Year).Scan(&p.ID)
+	}
+
+	return err
+}
+
+// LinkStaffPublication creates a link between staff and publication
+func (r *Repository) LinkStaffPublication(ctx context.Context, sp *StaffPublication) error {
+	query := `
+		INSERT INTO staff_publications (staff_id, publication_id, author_position, is_corresponding)
+		VALUES ($1, $2, $3, $4)
+		ON CONFLICT (staff_id, publication_id) DO UPDATE SET
+			author_position = EXCLUDED.author_position,
+			is_corresponding = EXCLUDED.is_corresponding
+	`
+	_, err := r.db.Pool.Exec(ctx, query,
+		sp.StaffID, sp.PublicationID, sp.AuthorPosition, sp.IsCorresponding,
+	)
+	return err
+}
+
+// GetStaffPublications retrieves all publications for a staff member
+func (r *Repository) GetStaffPublications(ctx context.Context, staffID uuid.UUID) ([]Publication, error) {
+	query := `
+		SELECT p.id, p.title, p.abstract, p.year, p.pub_type, p.venue, p.doi, p.url, p.citation_count
+		FROM publications p
+		JOIN staff_publications sp ON p.id = sp.publication_id
+		WHERE sp.staff_id = $1
+		ORDER BY p.year DESC NULLS LAST, p.title
+	`
+
+	rows, err := r.db.Pool.Query(ctx, query, staffID)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+
+	var pubs []Publication
+	for rows.Next() {
+		var p Publication
+		if err := rows.Scan(
+			&p.ID, &p.Title, &p.Abstract, &p.Year, &p.PubType, &p.Venue, &p.DOI, &p.URL, &p.CitationCount,
+		); err != nil {
+			return nil, err
+		}
+		pubs = append(pubs, p)
+	}
+	return pubs, rows.Err()
+}
+
+// SearchPublications searches for publications
+func (r *Repository) SearchPublications(ctx context.Context, params PublicationSearchParams) (*PublicationSearchResult, error) {
+	var conditions []string
+	var args []interface{}
+	argNum := 1
+
+	if params.Query != "" {
+		conditions = append(conditions, fmt.Sprintf(
+			`to_tsvector('german', COALESCE(title, '') || ' ' || COALESCE(abstract, '')) @@ plainto_tsquery('german', $%d)`,
+			argNum))
+		args = append(args, params.Query)
+		argNum++
+	}
+
+	if params.StaffID != nil {
+		conditions = append(conditions, fmt.Sprintf(
+			`id IN (SELECT publication_id FROM staff_publications WHERE staff_id = $%d)`,
+			argNum))
+		args = append(args, *params.StaffID)
+		argNum++
+	}
+
+	if params.Year != nil {
+		conditions = append(conditions, fmt.Sprintf("year = $%d", argNum))
+		args = append(args, *params.Year)
+		argNum++
+	}
+
+	if params.YearFrom != nil {
+		conditions = append(conditions, fmt.Sprintf("year >= $%d", argNum))
+		args = append(args, *params.YearFrom)
+		argNum++
+	}
+
+	if params.YearTo != nil {
+		conditions = append(conditions, fmt.Sprintf("year <= $%d", argNum))
+		args = append(args, *params.YearTo)
+		argNum++
+	}
+
+	if params.PubType != nil {
+		conditions = append(conditions, fmt.Sprintf("pub_type = $%d", argNum))
+		args = append(args, *params.PubType)
+		argNum++
+	}
+
+	whereClause := ""
+	if len(conditions) > 0 {
+		whereClause = "WHERE " + strings.Join(conditions, " AND ")
+	}
+
+	// Count
+	countQuery := fmt.Sprintf("SELECT COUNT(*) FROM publications %s", whereClause)
+	var total int
+	if err := r.db.Pool.QueryRow(ctx, countQuery, args...).Scan(&total); err != nil {
+		return nil, err
+	}
+
+	// Pagination
+	limit := params.Limit
+	if limit <= 0 {
+		limit = 20
+	}
+	offset := params.Offset
+
+	// Query
+	query := fmt.Sprintf(`
+		SELECT id, title, abstract, year, pub_type, venue, doi, url, citation_count, keywords
+		FROM publications %s
+		ORDER BY year DESC NULLS LAST, citation_count DESC
+		LIMIT %d OFFSET %d
+	`, whereClause, limit, offset)
+
+	rows, err := r.db.Pool.Query(ctx, query, args...)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+
+	var pubs []Publication
+	for rows.Next() {
+		var p Publication
+		if err := rows.Scan(
+			&p.ID, &p.Title, &p.Abstract, &p.Year, &p.PubType, &p.Venue, &p.DOI, &p.URL, &p.CitationCount, &p.Keywords,
+		); err != nil {
+			return nil, err
+		}
+		pubs = append(pubs, p)
+	}
+
+	return &PublicationSearchResult{
+		Publications: pubs,
+		Total:        total,
+		Limit:        limit,
+		Offset:       offset,
+		Query:        params.Query,
+	}, rows.Err()
+}