feat(pipeline): add BuildPages — compute slugs/paths/frontmatter from RawPage

2026-04-23 18:50:37 +02:00
parent a620f6cb01
commit 7b57051af8
2 changed files with 219 additions and 0 deletions
--- a/ingestion/internal/pipeline/build.go
+++ b/ingestion/internal/pipeline/build.go
@@ -0,0 +1,88 @@
+// ingestion/internal/pipeline/build.go
+package pipeline
+
+import (
+	"fmt"
+	"strings"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
+)
+
+// BuildPages converts RawPages from the LLM into wiki.Pages with computed slugs,
+// paths, and YAML frontmatter. sourceSlug is the slug of the source being ingested
+// (derived from the filename, not the LLM title).
+func BuildPages(rawPages []RawPage, sourceSlug, date string) []wiki.Page {
+	out := make([]wiki.Page, 0, len(rawPages))
+	for _, rp := range rawPages {
+		out = append(out, buildPage(rp, sourceSlug, date))
+	}
+	return out
+}
+
+func buildPage(rp RawPage, sourceSlug, date string) wiki.Page {
+	var slug, dir string
+	switch rp.Type {
+	case "source":
+		slug = sourceSlug
+		dir = "wiki/sources"
+	case "concept":
+		slug = wiki.Slug(rp.Title)
+		dir = "wiki/concepts"
+	case "entity":
+		slug = wiki.Slug(rp.Title)
+		dir = "wiki/entities"
+	default:
+		slug = wiki.Slug(rp.Title)
+		dir = "wiki/" + rp.Type
+	}
+
+	path := dir + "/" + slug + ".md"
+	fm := buildFrontmatter(rp, date)
+
+	return wiki.Page{
+		Path:    path,
+		Content: fm + "\n" + rp.Content,
+	}
+}
+
+func buildFrontmatter(rp RawPage, date string) string {
+	var sb strings.Builder
+	sb.WriteString("---\n")
+	fmt.Fprintf(&sb, "title: %s\n", rp.Title)
+
+	switch rp.Type {
+	case "source":
+		subtype := rp.Subtype
+		if subtype == "" {
+			subtype = "article"
+		}
+		fmt.Fprintf(&sb, "type: %s\n", subtype)
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "date_ingested: %s\n", date)
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	case "concept":
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	case "entity":
+		if rp.Subtype != "" {
+			fmt.Fprintf(&sb, "type: %s\n", rp.Subtype)
+		}
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	default:
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	}
+
+	fmt.Fprintf(&sb, "aliases:\n  - %s\n", rp.Title)
+	sb.WriteString("---\n")
+	return sb.String()
+}
--- a/ingestion/internal/pipeline/build_test.go
+++ b/ingestion/internal/pipeline/build_test.go
@@ -0,0 +1,131 @@
+// 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 := BuildPages(raw, "shape-up", "2026-04-23")
+	require.Len(t, pages, 1)
+
+	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 := BuildPages(raw, "shape-up", "2026-04-23")
+	require.Len(t, pages, 1)
+
+	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 := BuildPages(raw, "shape-up", "2026-04-23")
+	require.Len(t, pages, 1)
+
+	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)
+}