def test_noindexlanguage(tmp_path):
fpath = tmp_path / "test.zim"
with Creator(fpath, "welcome", "") as creator:
creator.add_item(StaticItem(path="welcome", content="hello"))
creator.update_metadata(language="bam")
creator.add_item_for("index",
"Index",
content="-",
mimetype="text/html")
reader = Archive(fpath)
assert reader.get_metadata("Language").decode(UTF8) == "bam"
# html content triggers both title and content xapian indexes
# but since indexing is disabled, we should only have title one
assert reader.has_title_index
assert not reader.has_fulltext_index
def get_metadata(self, zimfile, name):
zim_fh = Archive(zimfile)
return zim_fh.get_metadata(name)
def test_zim_creator(tmp_path, png_image, html_file, html_str):
fpath = tmp_path / "test.zim"
main_path, language, title = "welcome", "fra", "My Title"
tags = ";".join(["toto", "tata"])
with open(png_image, "rb") as fh:
png_data = fh.read()
with Creator(fpath, main_path, language, title=title,
tags=tags) as creator:
# verbatim HTML from string
creator.add_item_for("welcome", "wel", content=html_str, is_front=True)
# verbatim HTML from file
creator.add_item_for("welcome3", "wel3", fpath=html_file)
creator.add_item_for("welcome4", "wel4", fpath=html_file)
# single binary image
creator.add_item_for("images/yahoo.png",
"Home !!",
fpath=png_image,
is_front=True)
# redirect to our main page (no title)
creator.add_redirect("home", "welcome")
# redirect to our main page (with a custom title)
creator.add_redirect("home2", "welcome", "Home !!")
creator.add_redirect("home3", "welcome3", "Home !!", is_front=True)
creator.add_redirect("home4", "welcome4", "Home !!", is_front=False)
# ensure args requirement are checked
with pytest.raises(ValueError,
match="One of fpath or content is required"):
creator.add_item_for("images/yahoo.png")
with open(png_image, "rb") as fh:
creator.add_default_illustration(png_data)
assert fpath.exists()
reader = Archive(fpath)
assert reader.get_metadata("Title").decode(UTF8) == title
assert reader.get_metadata("Language").decode(UTF8) == language
assert reader.get_metadata("Tags").decode(UTF8) == tags
assert reader.main_entry.get_item().path == f"{main_path}"
# make sure we have our image
assert reader.get_item("images/yahoo.png")
# make sure we have our redirects
assert reader.get_entry_by_path("home2").is_redirect
assert reader.get_entry_by_path(
"home2").get_redirect_entry().path == f"{main_path}"
# make sure titles were indexed (html with title for xapian)
# see https://github.com/openzim/python-libzim/issues/125
assert "home2" in list(reader.get_suggestions("Home !!"))
assert "home3" in list(reader.get_suggestions("Home !!"))
assert "home4" in list(reader.get_suggestions("Home !!"))
assert "images/yahoo.png" not in list(reader.get_suggestions("Home !!"))
# make sure full text was indexed
assert reader.get_search_results_count("PDF doc") >= 1
# ensure non-rewritten articles have not been rewritten
assert bytes(reader.get_item("welcome").content).decode(UTF8) == html_str
assert bytes(reader.get_item("welcome3").content).decode(UTF8) == html_str
# ensure illustration is present and corrext
assert reader.has_illustration()
assert bytes(reader.get_illustration_item().content) == png_data