From 43a46d07e544b24590dd262739911b4f57627c83 Mon Sep 17 00:00:00 2001
From: Mathias Bergqvist <mthbqv@gmail.com>
Date: Thu, 23 Apr 2026 15:45:20 +0200
Subject: [PATCH] feat(extract): add Text() dispatcher with md/txt passthrough

---
 ingestion/internal/extract/extract.go      | 39 +++++++++++++++++++++
 ingestion/internal/extract/extract_test.go | 40 ++++++++++++++++++++++
 ingestion/internal/extract/pdf.go          |  8 +++++
 3 files changed, 87 insertions(+)
 create mode 100644 ingestion/internal/extract/extract.go
 create mode 100644 ingestion/internal/extract/extract_test.go
 create mode 100644 ingestion/internal/extract/pdf.go

diff --git a/ingestion/internal/extract/extract.go b/ingestion/internal/extract/extract.go
new file mode 100644
index 0000000..725c85f
--- /dev/null
+++ b/ingestion/internal/extract/extract.go
@@ -0,0 +1,39 @@
+// ingestion/internal/extract/extract.go
+package extract
+
+import (
+	"fmt"
+	"os"
+	"strings"
+)
+
+// Text reads the file at path and returns its plain-text content.
+// Supported extensions: .md, .txt (passthrough), .pdf (via pdftotext).
+func Text(path string) (string, error) {
+	ext := strings.ToLower(fileExt(path))
+	switch ext {
+	case ".md", ".txt":
+		b, err := os.ReadFile(path)
+		if err != nil {
+			return "", fmt.Errorf("read %s: %w", path, err)
+		}
+		return string(b), nil
+	case ".pdf":
+		return extractPDF(path)
+	default:
+		return "", fmt.Errorf("unsupported file extension: %s", ext)
+	}
+}
+
+// fileExt returns the file extension including the dot, lowercased.
+func fileExt(path string) string {
+	for i := len(path) - 1; i >= 0; i-- {
+		if path[i] == '.' {
+			return path[i:]
+		}
+		if path[i] == '/' || path[i] == '\\' {
+			break
+		}
+	}
+	return ""
+}
diff --git a/ingestion/internal/extract/extract_test.go b/ingestion/internal/extract/extract_test.go
new file mode 100644
index 0000000..44cd5fb
--- /dev/null
+++ b/ingestion/internal/extract/extract_test.go
@@ -0,0 +1,40 @@
+// ingestion/internal/extract/extract_test.go
+package extract
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestText_Markdown(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "note.md")
+	require.NoError(t, os.WriteFile(path, []byte("# Hello\n\nWorld."), 0o644))
+
+	got, err := Text(path)
+	require.NoError(t, err)
+	assert.Equal(t, "# Hello\n\nWorld.", got)
+}
+
+func TestText_Txt(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "note.txt")
+	require.NoError(t, os.WriteFile(path, []byte("plain text"), 0o644))
+
+	got, err := Text(path)
+	require.NoError(t, err)
+	assert.Equal(t, "plain text", got)
+}
+
+func TestText_UnsupportedExtension(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "data.csv")
+	require.NoError(t, os.WriteFile(path, []byte("a,b,c"), 0o644))
+
+	_, err := Text(path)
+	assert.ErrorContains(t, err, "unsupported")
+}
diff --git a/ingestion/internal/extract/pdf.go b/ingestion/internal/extract/pdf.go
new file mode 100644
index 0000000..4a073c4
--- /dev/null
+++ b/ingestion/internal/extract/pdf.go
@@ -0,0 +1,8 @@
+// ingestion/internal/extract/pdf.go
+package extract
+
+import "fmt"
+
+func extractPDF(_ string) (string, error) {
+	return "", fmt.Errorf("PDF extraction not implemented")
+}