add service

pkg/fileparser/parser_test.go

@@ -0,0 +1,110 @@
+package fileparser
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestExtractText_EmptyData(t *testing.T) {
+	result, err := ExtractText(nil, "test.txt")
+	assert.NoError(t, err)
+	assert.Empty(t, result)
+
+	result, err = ExtractText([]byte{}, "test.txt")
+	assert.NoError(t, err)
+	assert.Empty(t, result)
+}
+
+func TestExtractText_PlainText(t *testing.T) {
+	content := "Тестовый текст для проверки"
+	result, err := ExtractText([]byte(content), "document.txt")
+
+	assert.NoError(t, err)
+	assert.Equal(t, content, result)
+}
+
+func TestExtractText_PlainTextWithNewlines(t *testing.T) {
+	content := "Первая строка\nВторая строка\nТретья строка"
+	result, err := ExtractText([]byte(content), "document.txt")
+
+	assert.NoError(t, err)
+	assert.Equal(t, content, result)
+}
+
+func TestExtractText_RealDocxFile(t *testing.T) {
+	testdataPath := filepath.Join("testdata", "test_document.docx")
+	data, err := os.ReadFile(testdataPath)
+	require.NoError(t, err, "не удалось прочитать тестовый файл")
+
+	result, err := ExtractText(data, "тестовый.docx")
+
+	assert.NoError(t, err)
+	assert.NotEmpty(t, result, "текст из docx не должен быть пустым")
+	t.Logf("Извлеченный текст из docx:\n%s", result)
+}
+
+func TestExtractText_DocxWithAnyFilename(t *testing.T) {
+	testdataPath := filepath.Join("testdata", "test_document.docx")
+	data, err := os.ReadFile(testdataPath)
+	require.NoError(t, err)
+
+	result1, err := ExtractText(data, "random_name_without_extension")
+	assert.NoError(t, err)
+	assert.NotEmpty(t, result1)
+
+	result2, err := ExtractText(data, "document.pdf")
+	assert.NoError(t, err)
+	assert.NotEmpty(t, result2)
+
+	assert.Equal(t, result1, result2, "результат должен быть одинаковым независимо от имени файла")
+}
+
+func TestExtractText_UnsupportedFormat_PDF(t *testing.T) {
+	pdfHeader := []byte("%PDF-1.4\n")
+	result, err := ExtractText(pdfHeader, "document.pdf")
+
+	assert.Error(t, err)
+	assert.Empty(t, result)
+	assert.Contains(t, err.Error(), "UNSUPPORTED_FILE_FORMAT")
+}
+
+func TestExtractText_UnsupportedFormat_Image(t *testing.T) {
+	pngHeader := []byte{0x89, 0x50, 0x4E, 0x47, 0x0D, 0x0A, 0x1A, 0x0A}
+	result, err := ExtractText(pngHeader, "image.png")
+
+	assert.Error(t, err)
+	assert.Empty(t, result)
+	assert.Contains(t, err.Error(), "UNSUPPORTED_FILE_FORMAT")
+}
+
+func TestExtractText_InvalidDocx(t *testing.T) {
+	zipHeader := []byte{0x50, 0x4B, 0x03, 0x04}
+	fakeZip := append(zipHeader, []byte("not a valid zip content")...)
+
+	result, err := ExtractText(fakeZip, "fake.docx")
+
+	assert.Error(t, err)
+	assert.Empty(t, result)
+}
+
+func TestIsDocx_ValidDocx(t *testing.T) {
+	testdataPath := filepath.Join("testdata", "test_document.docx")
+	data, err := os.ReadFile(testdataPath)
+	require.NoError(t, err)
+
+	assert.True(t, isDocx(data))
+}
+
+func TestIsDocx_RegularZip(t *testing.T) {
+	zipHeader := []byte{0x50, 0x4B, 0x03, 0x04}
+	assert.False(t, isDocx(zipHeader))
+}
+
+func TestIsDocx_NotZip(t *testing.T) {
+	textData := []byte("plain text content")
+	assert.False(t, isDocx(textData))
+}