Phase 3: PDF/DOCX extraction, chunking, LLM client with mock interface

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

internal/parse/docx_test.go

@@ -0,0 +1,62 @@
+package parse_test
+
+import (
+	"archive/zip"
+	"bytes"
+	"strings"
+	"testing"
+
+	"qbank/internal/parse"
+)
+
+func TestExtractDOCX(t *testing.T) {
+	const docXML = `<?xml version="1.0" encoding="UTF-8"?>
+<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
+  <w:body>
+    <w:p><w:r><w:t>Question 1: What is Go?</w:t></w:r></w:p>
+    <w:p><w:r><w:t>A) A compiled language</w:t></w:r></w:p>
+    <w:p><w:r><w:t>B) An interpreted language</w:t></w:r></w:p>
+    <w:p><w:r><w:t>C) A markup language</w:t></w:r></w:p>
+  </w:body>
+</w:document>`
+
+	docx := buildDocx(t, docXML)
+
+	text, err := parse.ExtractDOCX(bytes.NewReader(docx))
+	if err != nil {
+		t.Fatalf("ExtractDOCX: %v", err)
+	}
+	for _, want := range []string{"Question 1", "compiled language", "interpreted language"} {
+		if !strings.Contains(text, want) {
+			t.Errorf("output missing %q; got:\n%s", want, text)
+		}
+	}
+}
+
+func TestExtractDOCX_MissingXML(t *testing.T) {
+	var buf bytes.Buffer
+	w := zip.NewWriter(&buf)
+	w.Close()
+
+	_, err := parse.ExtractDOCX(bytes.NewReader(buf.Bytes()))
+	if err == nil {
+		t.Error("expected error for docx without document.xml")
+	}
+}
+
+func buildDocx(t *testing.T, xmlContent string) []byte {
+	t.Helper()
+	var buf bytes.Buffer
+	w := zip.NewWriter(&buf)
+	f, err := w.Create("word/document.xml")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if _, err := f.Write([]byte(xmlContent)); err != nil {
+		t.Fatal(err)
+	}
+	if err := w.Close(); err != nil {
+		t.Fatal(err)
+	}
+	return buf.Bytes()
+}