hyperguild/ingestion/internal/pipeline/links_test.go

// ingestion/internal/pipeline/links_test.go
package pipeline

import (
	"testing"

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

	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
)

func TestCanonicalizeLinks_KnownTitle(t *testing.T) {
	pages := []wiki.Page{
		{
			Path:    "wiki/sources/shape-up.md",
			Content: "---\ntitle: 'Shape Up'\n---\n\n## Summary\n\nSee [[Betting]].\n",
		},
	}
	inventory := map[wiki.PageType][]wiki.Entry{
		wiki.PageTypeConcept: {
			{Slug: "betting", Title: "Betting"},
		},
	}
	got, warnings := CanonicalizeLinks(pages, inventory)
	require.Len(t, got, 1)
	assert.Empty(t, warnings)
	assert.Contains(t, got[0].Content, "[[betting|Betting]]")
	assert.NotContains(t, got[0].Content, "[[Betting]]")
}

func TestCanonicalizeLinks_UnknownTitleLeftAsIs(t *testing.T) {
	pages := []wiki.Page{
		{
			Path:    "wiki/sources/shape-up.md",
			Content: "---\ntitle: 'Shape Up'\n---\n\n## Summary\n\nSee [[Ghost Concept]].\n",
		},
	}
	inventory := map[wiki.PageType][]wiki.Entry{}
	got, warnings := CanonicalizeLinks(pages, inventory)
	require.Len(t, got, 1)
	assert.NotEmpty(t, warnings)
	assert.Contains(t, got[0].Content, "[[Ghost Concept]]")
}

func TestCanonicalizeLinks_AlreadyCanonicalLinkUntouched(t *testing.T) {
	// Links already in [[slug|Display]] format must not be double-converted
	pages := []wiki.Page{
		{
			Path:    "wiki/sources/shape-up.md",
			Content: "---\ntitle: 'Shape Up'\n---\n\n## Summary\n\nSee [[betting|Betting]].\n",
		},
	}
	inventory := map[wiki.PageType][]wiki.Entry{
		wiki.PageTypeConcept: {
			{Slug: "betting", Title: "Betting"},
		},
	}
	got, warnings := CanonicalizeLinks(pages, inventory)
	require.Len(t, got, 1)
	assert.Empty(t, warnings)
	// Should remain exactly as-is — not double-wrapped
	assert.Contains(t, got[0].Content, "[[betting|Betting]]")
	assert.NotContains(t, got[0].Content, "[[betting|[[betting|Betting]]]]")
}

func TestCanonicalizeLinks_CaseInsensitiveMatch(t *testing.T) {
	pages := []wiki.Page{
		{
			Path:    "wiki/sources/foo.md",
			Content: "---\ntitle: 'Foo'\n---\n\n## Summary\n\nSee [[domain driven design]].\n",
		},
	}
	inventory := map[wiki.PageType][]wiki.Entry{
		wiki.PageTypeConcept: {
			{Slug: "domain-driven-design", Title: "Domain Driven Design"},
		},
	}
	got, warnings := CanonicalizeLinks(pages, inventory)
	require.Len(t, got, 1)
	assert.Empty(t, warnings)
	assert.Contains(t, got[0].Content, "[[domain-driven-design|domain driven design]]")
}

func TestCanonicalizeLinks_CurrentBatchPagesResolved(t *testing.T) {
	// A concept created in the same batch should be canonicalizable
	pages := []wiki.Page{
		{
			Path:    "wiki/sources/shape-up.md",
			Content: "---\ntitle: 'Shape Up'\n---\n\n## Summary\n\nSee [[Betting]].\n",
		},
		{
			Path:    "wiki/concepts/betting.md",
			Content: "---\ntitle: 'Betting'\n---\n\n## Definition\n\nA technique.\n",
		},
	}
	inventory := map[wiki.PageType][]wiki.Entry{} // empty — Betting is in the batch, not inventory

	got, warnings := CanonicalizeLinks(pages, inventory)
	require.Len(t, got, 2)
	assert.Empty(t, warnings)
	assert.Contains(t, got[0].Content, "[[betting|Betting]]")
}

func TestCanonicalizeLinks_StripsWingColonPrefix(t *testing.T) {
	pages := []wiki.Page{
		{
			Path:    "wiki/homelab/failures/act-runner-host-mode-container-needs-node-and-libatomic.md",
			Content: "---\ntitle: 'act_runner host-mode'\n---\n\nSee [[wing:homelab/failures/rootless-buildah-act-runner-run-containers-denied]].\n",
		},
	}
	got, warnings := CanonicalizeLinks(pages, map[wiki.PageType][]wiki.Entry{})
	require.Len(t, got, 1)
	assert.Empty(t, warnings)
	assert.Contains(t, got[0].Content, "[[homelab/failures/rootless-buildah-act-runner-run-containers-denied]]")
	assert.NotContains(t, got[0].Content, "wing:")
}

func TestCanonicalizeLinks_StripsWikiSlashPrefix(t *testing.T) {
	pages := []wiki.Page{
		{
			Path:    "wiki/agentsquad/hypotheses/council-consolidation-standalone-deliberation-service.md",
			Content: "---\ntitle: 'council consolidation'\n---\n\nSee [[wiki/agentsquad/decisions/autoresearch-council-sibling-pipe]].\n",
		},
	}
	got, warnings := CanonicalizeLinks(pages, map[wiki.PageType][]wiki.Entry{})
	require.Len(t, got, 1)
	assert.Empty(t, warnings)
	assert.Contains(t, got[0].Content, "[[agentsquad/decisions/autoresearch-council-sibling-pipe]]")
	assert.NotContains(t, got[0].Content, "wiki/agentsquad/decisions/autoresearch-council-sibling-pipe]]\n\n") // no leftover wiki/ prefix
	assert.NotContains(t, got[0].Content, "[[wiki/")
}

func TestCanonicalizeLinks_TitleLookupStillTakesPriorityOverPrefixStrip(t *testing.T) {
	// A plain link that resolves via the title map must still use the
	// normal slug|Display form, not fall through to prefix-strip repair.
	pages := []wiki.Page{
		{
			Path:    "wiki/sources/shape-up.md",
			Content: "---\ntitle: 'Shape Up'\n---\n\nSee [[Betting]].\n",
		},
	}
	inventory := map[wiki.PageType][]wiki.Entry{
		wiki.PageTypeConcept: {{Slug: "betting", Title: "Betting"}},
	}
	got, warnings := CanonicalizeLinks(pages, inventory)
	require.Len(t, got, 1)
	assert.Empty(t, warnings)
	assert.Contains(t, got[0].Content, "[[betting|Betting]]")
}

func TestCanonicalizeLinks_MultipleLinksInOnePage(t *testing.T) {
	pages := []wiki.Page{
		{
			Path:    "wiki/sources/foo.md",
			Content: "---\ntitle: 'Foo'\n---\n\n## Summary\n\nSee [[Betting]] and [[Shape Up]].\n",
		},
	}
	inventory := map[wiki.PageType][]wiki.Entry{
		wiki.PageTypeConcept: {
			{Slug: "betting", Title: "Betting"},
		},
		wiki.PageTypeSource: {
			{Slug: "shape-up", Title: "Shape Up"},
		},
	}
	got, warnings := CanonicalizeLinks(pages, inventory)
	require.Len(t, got, 1)
	assert.Empty(t, warnings)
	assert.Contains(t, got[0].Content, "[[betting|Betting]]")
	assert.Contains(t, got[0].Content, "[[shape-up|Shape Up]]")
}