adds new audiobook test and reorganizes tests

e2e_tests/docx-tools/test_compare_zip_or_docx_files.py

@@ -0,0 +1,144 @@
+import pytest
+import os
+import shutil
+import zipfile
+import textwrap
+from deepdiff import DeepDiff
+import docx2txt
+
+"""
+Compares docx files. To run:
+1. run two docx jobs in corgi
+2. download the docx zip files or docx files from corgi (by default to Downloads folder on Mac)
+- make sure that BASE_TO_DIR exists and contains 2 subdirectories named 0 and 1
+3. make sure that BASE_FROM_DIR variable is set correctly and files are copied there from Downloads folder
+4. run 'pytest -k test_compare_zip_or_docx_files.py docx-tools > docx_diffs.txt'
+
+Note, that the test accepts two .zip files from corgi docx job, two .docx files (or one of each)
+
+Latest update on March 31st, 2026
+"""
+
+HOME_DIR = os.path.expanduser("~")
+BASE_FROM_DIR = f"{HOME_DIR}/Downloads/2pdfs"
+BASE_TO_DIR = f"{os.getcwd()}/docx_old_new"
+MAX_WIDTH = 120
+
+
+def unzip_file(zip_path, extract_to):
+    """Unzips a zip file into extract_to directory."""
+    with zipfile.ZipFile(zip_path) as z:
+        z.extractall(extract_to)
+
+
+def get_docx_texts_from_dir(directory):
+    """Returns a dict of {book_name: {filename: text}} for all docx files in subdirs."""
+    result = {}
+    for sub in os.listdir(directory):
+        sub_path = os.path.join(directory, sub)
+        if os.path.isdir(sub_path):
+            result[sub] = {
+                f: docx2txt.process(os.path.join(sub_path, f))
+                for f in os.listdir(sub_path)
+                if f.endswith(".docx")
+            }
+    return result
+
+
+def get_docx_texts_from_file(docx_path):
+    """Returns a dict for a single docx file."""
+    filename = os.path.basename(docx_path)
+    return {filename: docx2txt.process(docx_path)}
+
+
+def prepare_files(file_path, dest_dir):
+    """
+    Copies and extracts zip files or copies docx files to dest_dir.
+    Returns a dict of docx texts.
+    """
+    file_path = str(file_path)
+    dest_dir = str(dest_dir)
+
+    os.makedirs(dest_dir, exist_ok=True)
+
+    if file_path.endswith(".zip"):
+        dest_path = os.path.join(dest_dir, os.path.basename(file_path))
+        shutil.copy(file_path, dest_path)
+        unzip_file(dest_path, dest_dir)
+        return get_docx_texts_from_dir(dest_dir)
+
+    elif file_path.endswith(".docx"):
+        dest_path = os.path.join(dest_dir, os.path.basename(file_path))
+        shutil.copy(file_path, dest_path)
+        return get_docx_texts_from_file(dest_path)
+
+    else:
+        pytest.fail(
+            f"Unsupported file type: {file_path}. Only .zip and .docx are supported."
+        )
+
+
+def print_diffs(diffs):
+    for diff_type, changes in diffs.items():
+        # Diff type header
+        print(f"\n{'#' * 60}")
+        print(f"  {diff_type.replace('_', ' ').upper()}")
+        print(f"{'#' * 60}")
+
+        for key, value in changes.items():
+            # Extract book/file name from key for readability
+            print(f"\n  {'─' * 40}")
+            print(f"  LOCATION: {key}")
+            print(f"  {'─' * 40}")
+
+            # Handle old/new values separately if present
+            if hasattr(value, "get"):
+                old_val = str(value.get("old_value", ""))
+                new_val = str(value.get("new_value", ""))
+                if old_val:
+                    print(f"\n  OLD VALUE:")
+                    for line in textwrap.wrap(old_val, width=MAX_WIDTH):
+                        print(f"    {line}")
+                if new_val:
+                    print(f"\n  NEW VALUE:")
+                    for line in textwrap.wrap(new_val, width=MAX_WIDTH):
+                        print(f"    {line}")
+            else:
+                print(f"\n  CHANGE:")
+                for line in textwrap.wrap(str(value), width=MAX_WIDTH):
+                    print(f"    {line}")
+
+
+def test_compare_zip_or_docx_files():
+    # Part 1: Find zip or docx files
+    all_files = [
+        f
+        for f in os.listdir(BASE_FROM_DIR)
+        if f.endswith(".zip") or f.endswith(".docx")
+    ]
+
+    if len(all_files) != 2:
+        pytest.fail(
+            f"Two files required (.zip or .docx): {len(all_files)} file(s) available"
+        )
+
+    file1 = os.path.join(BASE_FROM_DIR, all_files[0])
+    file2 = os.path.join(BASE_FROM_DIR, all_files[1])
+
+    print(f"\nFile 1: {all_files[0]}")
+    print(f"File 2: {all_files[1]}")
+
+    # Part 2: Prepare and extract text
+    dest_dir_0 = os.path.join(BASE_TO_DIR, "0")
+    dest_dir_1 = os.path.join(BASE_TO_DIR, "1")
+
+    dict_old = prepare_files(file1, dest_dir_0)
+    dict_new = prepare_files(file2, dest_dir_1)
+
+    # Part 3: Compare and print diffs
+    diffs = DeepDiff(dict_new, dict_old, verbose_level=2)
+
+    if not diffs:
+        print("------>>>>> NO DIFFERENCES <<<<<------")
+    else:
+        print_diffs(diffs)

e2e_tests/e2e/ui/test_book.py → e2e_tests/e2e/osweb/test_details_page.py

@@ -6,27 +6,6 @@
 import sys
 
 
-@pytest.mark.asyncio
-async def test_book_title_links_to_books_detail_page(chrome_page_unlogged, base_url):
-
-    # GIVEN: Playwright, chromium and the rex_base_url
-
-    # WHEN: The Home page is fully loaded
-    await chrome_page_unlogged.goto(f"{base_url}/subjects")
-    home = HomeRex(chrome_page_unlogged)
-
-    await chrome_page_unlogged.keyboard.press("Escape")
-
-    assert await home.subject_listing_book_is_visible()
-
-    await home.click_subject_listing_book()
-
-    await home.click_book_selection()
-
-    # THEN: The page navigates to {base_url}/details/books/astronomy-2e
-    assert "astronomy" in chrome_page_unlogged.url.lower()
-
-
 @pytest.mark.parametrize("book_slug", ["physics"])
 @pytest.mark.asyncio
 async def test_buy_print_copy_link(chrome_page_unlogged, base_url, book_slug):
@@ -80,44 +59,6 @@ async def test_order_options_link(chrome_page_unlogged, base_url, book_slug):
     assert "Kendall_Hunt" in await home.order_options_href()
 
 
-@pytest.mark.parametrize(
-    "book_slug, page_slug", [("astronomy-2e", "1-3-the-laws-of-nature")]
-)
-@pytest.mark.asyncio
-async def test_accessibility_help(chrome_page_unlogged, base_url, book_slug, page_slug):
-    # Verifies the hidden 'Go to accessibility page'
-
-    # GIVEN: Open osweb book details page
-
-    # WHEN: The Home page is fully loaded
-    await chrome_page_unlogged.goto(f"{base_url}/books/{book_slug}/pages/{page_slug}")
-    home = HomeRex(chrome_page_unlogged)
-
-    await chrome_page_unlogged.keyboard.press("Escape")
-
-    try:
-        await home.click_cookieyes_accept()
-
-    except TimeoutError as te:
-        print(f"{te}\nNo Cookies dialog, continue testing... ", file=sys.stderr)
-
-    finally:
-
-        await chrome_page_unlogged.keyboard.press("Tab")
-        await chrome_page_unlogged.keyboard.press("Tab")
-
-        await chrome_page_unlogged.keyboard.press("Enter")
-
-        # THEN: Accessibility help opens
-
-        accessibility_page_content = await home.accessibility_help_content.inner_text()
-
-        assert (
-            "Accessibility" in accessibility_page_content
-            and "OpenStax" in accessibility_page_content
-        )
-
-
 @pytest.mark.parametrize("book_slug", ["algebra-and-trigonometry-2e"])
 @pytest.mark.asyncio
 async def test_toc_slideout(chrome_page_unlogged, base_url, book_slug):
@@ -164,3 +105,23 @@ async def test_resources_tabs(chrome_page_unlogged, base_url, book_slug):
     await home.click_student_resources_tab()
 
     assert "Student" in chrome_page_unlogged.url
+
+
+@pytest.mark.parametrize("book_slug", ["anatomy-and-physiology-2e"])
+@pytest.mark.asyncio
+async def test_audiobook_link(chrome_page_unlogged, base_url, book_slug):
+
+    # GIVEN: Open osweb book details page
+
+    # WHEN: The Home page is fully loaded
+    details_books_url = f"{base_url}/details/books/{book_slug}"
+
+    await chrome_page_unlogged.goto(details_books_url)
+    home = HomeRex(chrome_page_unlogged)
+
+    await chrome_page_unlogged.keyboard.press("Escape")
+
+    # THEN: Audiobook link is visible and clickable
+    assert await home.audiobook_link_is_visible()
+
+    assert await home.audiobook_link_purchase_options.is_enabled()

e2e_tests/e2e/osweb/test_subjects_books_pages.py

@@ -39,3 +39,24 @@ async def test_subjects_books_pages_load(chrome_page_unlogged, base_url):
             mod_hrefs = mhrefs.replace("-", " ")
 
             assert await home.subjects_title() in mod_hrefs
+
+
+@pytest.mark.asyncio
+async def test_book_title_links_to_books_detail_page(chrome_page_unlogged, base_url):
+
+    # GIVEN: Playwright, chromium and the rex_base_url
+
+    # WHEN: The Home page is fully loaded
+    await chrome_page_unlogged.goto(f"{base_url}/subjects")
+    home = HomeRex(chrome_page_unlogged)
+
+    await chrome_page_unlogged.keyboard.press("Escape")
+
+    assert await home.subject_listing_book_is_visible()
+
+    await home.click_subject_listing_book()
+
+    await home.click_book_selection()
+
+    # THEN: The page navigates to {base_url}/details/books/astronomy-2e
+    assert "astronomy" in chrome_page_unlogged.url.lower()

e2e_tests/e2e/ui/pages/home.py

@@ -334,6 +334,14 @@ async def toc_is_visible(self):
             .is_visible()
         )
 
+    @pytest.mark.asyncio
+    async def audiobook_link_is_visible(self):
+        return await self.page.get_by_role("heading", name="Audiobook").is_visible()
+
+    @property
+    def audiobook_link_purchase_options(self):
+        return self.page.get_by_role("link", name="Purchase options")
+
     # Accessibility page (hidden link: go to accessibility page)
 
     @property