Show an estimated page count for each built book

Bindery counts the pages as the last step of a build, from the text of the ePub. The story list and the OPDS catalog show the count. A story has no count until its book is built.

The method follows "Paragraphs (APNX Accurate)" of the Count Pages plugin for calibre. Bindery counts each paragraph that a reader sees, so the same text gives the same count as <p> elements, as <div> elements and as lines with <br> between them. An empty paragraph is not counted.

tests/test_build_keys.py

@@ -11,7 +11,7 @@ from test_deliver import fake as fake
 from test_deliver import jobs as jobs
 from test_deliver import story_epub as story_epub
 
-from bindery import config, orchestrator
+from bindery import config, orchestrator, pages
 from bindery.jobs import DownloadMode, Job
 
 ONE = [(1, "One", "a")]
@@ -242,6 +242,59 @@ def test_a_download_builds_a_book_that_has_no_file_or_that_changed(builds, clien
     assert story(story_id)["last_changed"]
 
 
+# Page counts
+
+LONG = "A line of the story. " * 20
+
+
+def listed_pages(story_id):
+    return {s["id"]: s["page_count"] for s in orchestrator.list_stories()}[story_id]
+
+
+def test_a_story_has_no_page_count_until_its_book_is_built(builds, monkeypatch):
+    story_id = linked_story(ONE)
+    assert listed_pages(story_id) is None
+    site(monkeypatch, ONE)
+    update(story_id)
+    (built,) = config.TMP_DIR.iterdir()
+    assert listed_pages(story_id) == pages.epub_pages(built) == 1
+
+
+def test_each_build_counts_the_pages_of_the_new_book(builds, client, monkeypatch):
+    story_id = linked_story(ONE)
+    site(monkeypatch, [*ONE, *[(n, f"Chapter {n}", "<br/>".join([LONG] * 31)) for n in range(2, 6)]])
+    update(story_id)
+    long_book = listed_pages(story_id)
+    # Each of the 124 lines is a paragraph and 6 lines of text.
+    assert long_book >= 4 * 31 * 7 // 31
+    # The count is of the built book, so a rule that removes text changes it without a download.
+    orchestrator.save_rules(story_id, [{"pattern": "(A line of the story. ){19}", "replacement": ""}])
+    download(client, story_id)
+    assert builds.call_count == 2
+    assert 0 < listed_pages(story_id) < long_book / 3
+
+
+def test_a_book_from_before_the_page_count_is_counted_without_a_build(builds, client, monkeypatch):
+    story_id = linked_story(ONE)
+    site(monkeypatch, ONE)
+    update(story_id)
+    orchestrator.store.set_setting(story_id, "page_count", None)
+    download(client, story_id)
+    assert builds.call_count == 1
+    assert listed_pages(story_id) == 1
+
+
+def test_a_book_that_cannot_be_counted_is_still_built(builds, monkeypatch):
+    def fail(path):
+        raise orchestrator.EpubError("unreadable")
+
+    monkeypatch.setattr(pages, "epub_pages", fail)
+    story_id = linked_story(ONE)
+    site(monkeypatch, ONE)
+    assert "library book 1" in update(story_id)
+    assert listed_pages(story_id) is None
+
+
 def test_stop_tracking_deletes_the_built_book(builds, client):
     story_id, other = add_story(), orchestrator.store.create_story("https://other", "s", "Other", "W", [])
     download(client, story_id)