hyperguild/ingestion/internal/pipeline/build_test.go

// ingestion/internal/pipeline/build_test.go
package pipeline

import (
	"strings"
	"testing"

	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
)

func TestBuildPages_SourcePage(t *testing.T) {
	raw := []RawPage{
		{
			Title:   "Shape Up",
			Type:    "source",
			Subtype: "book",
			Domain:  "product-strategy",
			Content: "## Summary\n\nA book about shaping product work.\n",
		},
	}
	pages, warnings := BuildPages(raw, "shape-up", "2026-04-23")
	require.Len(t, pages, 1)
	assert.Empty(t, warnings)

	p := pages[0]
	assert.Equal(t, "wiki/sources/shape-up.md", p.Path)
	assert.Contains(t, p.Content, "title: 'Shape Up'")
	assert.Contains(t, p.Content, "type: 'book'")
	assert.Contains(t, p.Content, "domain: 'product-strategy'")
	assert.Contains(t, p.Content, "date_ingested: 2026-04-23")
	assert.Contains(t, p.Content, "last_updated: 2026-04-23")
	assert.Contains(t, p.Content, "aliases:\n  - 'Shape Up'")
	assert.Contains(t, p.Content, "## Summary")
	assert.True(t, strings.HasPrefix(p.Content, "---\n"), "content must start with frontmatter")
}

func TestBuildPages_ConceptPage(t *testing.T) {
	raw := []RawPage{
		{
			Title:   "Betting",
			Type:    "concept",
			Domain:  "product-strategy",
			Content: "## Definition\n\nA resource allocation technique.\n",
		},
	}
	pages, warnings := BuildPages(raw, "shape-up", "2026-04-23")
	require.Len(t, pages, 1)
	assert.Empty(t, warnings)

	p := pages[0]
	assert.Equal(t, "wiki/concepts/betting.md", p.Path)
	assert.Contains(t, p.Content, "title: 'Betting'")
	assert.Contains(t, p.Content, "domain: 'product-strategy'")
	assert.Contains(t, p.Content, "last_updated: 2026-04-23")
	assert.Contains(t, p.Content, "aliases:\n  - 'Betting'")
	assert.NotContains(t, p.Content, "date_ingested")
	assert.Contains(t, p.Content, "## Definition")
}

func TestBuildPages_EntityPage(t *testing.T) {
	raw := []RawPage{
		{
			Title:   "Ryan Singer",
			Type:    "entity",
			Subtype: "person",
			Domain:  "product-strategy",
			Content: "## Description\n\nA product designer.\n",
		},
	}
	pages, warnings := BuildPages(raw, "shape-up", "2026-04-23")
	require.Len(t, pages, 1)
	assert.Empty(t, warnings)

	p := pages[0]
	assert.Equal(t, "wiki/entities/ryan-singer.md", p.Path)
	assert.Contains(t, p.Content, "title: 'Ryan Singer'")
	assert.Contains(t, p.Content, "type: 'person'")
	assert.Contains(t, p.Content, "domain: 'product-strategy'")
	assert.Contains(t, p.Content, "last_updated: 2026-04-23")
	assert.Contains(t, p.Content, "aliases:\n  - 'Ryan Singer'")
	assert.NotContains(t, p.Content, "date_ingested")
}

func TestBuildPages_SourceSlugUsedForSourcePage(t *testing.T) {
	// LLM title differs from filename — pipeline uses sourceSlug for the source page path.
	raw := []RawPage{
		{Title: "FinBERT: A Pretrained Model", Type: "source", Subtype: "article", Content: "## Summary\n\nA model.\n"},
	}
	pages, _ := BuildPages(raw, "finbert-huggingface", "2026-04-23")
	require.Len(t, pages, 1)
	assert.Equal(t, "wiki/sources/finbert-huggingface.md", pages[0].Path)
}

func TestBuildPages_ConceptSlugDerivedFromTitle(t *testing.T) {
	raw := []RawPage{
		{Title: "Domain-Driven Design", Type: "concept", Content: "## Definition\n\nFoo.\n"},
	}
	pages, _ := BuildPages(raw, "some-source", "2026-04-23")
	require.Len(t, pages, 1)
	assert.Equal(t, "wiki/concepts/domain-driven-design.md", pages[0].Path)
}

func TestBuildPages_SourceDefaultSubtype(t *testing.T) {
	// If subtype is omitted for a source, default to "article"
	raw := []RawPage{
		{Title: "Some Post", Type: "source", Content: "## Summary\n\nA post.\n"},
	}
	pages, _ := BuildPages(raw, "some-post", "2026-04-23")
	require.Len(t, pages, 1)
	assert.Contains(t, pages[0].Content, "type: 'article'")
}

func TestBuildPages_OmitsDomainWhenEmpty(t *testing.T) {
	raw := []RawPage{
		{Title: "Betting", Type: "concept", Content: "## Definition\n\nFoo.\n"},
	}
	pages, _ := BuildPages(raw, "src", "2026-04-23")
	require.Len(t, pages, 1)
	assert.NotContains(t, pages[0].Content, "domain:")
}

func TestBuildPages_MultiplePages(t *testing.T) {
	raw := []RawPage{
		{Title: "Shape Up", Type: "source", Subtype: "book", Content: "## Summary\n\nA book.\n"},
		{Title: "Betting", Type: "concept", Content: "## Definition\n\nA technique.\n"},
		{Title: "Ryan Singer", Type: "entity", Subtype: "person", Content: "## Description\n\nA designer.\n"},
	}
	pages, _ := BuildPages(raw, "shape-up", "2026-04-23")
	require.Len(t, pages, 3)
	assert.Equal(t, "wiki/sources/shape-up.md", pages[0].Path)
	assert.Equal(t, "wiki/concepts/betting.md", pages[1].Path)
	assert.Equal(t, "wiki/entities/ryan-singer.md", pages[2].Path)
}

func TestBuildPages_TitleWithColon(t *testing.T) {
	raw := []RawPage{
		{Title: "Shape Up: The Basecamp Method", Type: "source", Subtype: "book", Content: "## Summary\n\nA book.\n"},
	}
	pages, _ := BuildPages(raw, "shape-up", "2026-04-23")
	require.Len(t, pages, 1)
	// Title with colon must be quoted in YAML
	assert.Contains(t, pages[0].Content, "title: 'Shape Up: The Basecamp Method'")
	assert.Contains(t, pages[0].Content, "aliases:\n  - 'Shape Up: The Basecamp Method'")
}

func TestBuildPages_EntityNoSubtype(t *testing.T) {
	raw := []RawPage{
		{Title: "Basecamp", Type: "entity", Content: "## Description\n\nA company.\n"},
	}
	pages, _ := BuildPages(raw, "src", "2026-04-23")
	require.Len(t, pages, 1)
	assert.NotContains(t, pages[0].Content, "type:")
	assert.Contains(t, pages[0].Content, "title: 'Basecamp'")
}

func TestBuildPages_EmptyTitleSkippedWithWarning(t *testing.T) {
	raw := []RawPage{
		{Title: "", Type: "concept", Content: "## Definition\n\nFoo.\n"},
		{Title: "Betting", Type: "concept", Content: "## Definition\n\nA technique.\n"},
	}
	pages, warnings := BuildPages(raw, "src", "2026-04-23")
	require.Len(t, pages, 1, "empty-title page should be skipped")
	assert.Equal(t, "wiki/concepts/betting.md", pages[0].Path)
	assert.Len(t, warnings, 1)
	assert.Contains(t, warnings[0], "empty title")
}