Fixed type checks for libzim 3.5.0

Also ignoring warning for missing source of regex as its a C module

Author: rgaudin

src/zimscraperlib/zim/archive.py

@@ -18,7 +18,6 @@
 import libzim.suggestion  # SuggestionSearcher  # pyright: ignore
 
 from zimscraperlib.zim._libkiwix import convertTags, parseMimetypeCounter
-from zimscraperlib.zim.items import Item
 
 
 class Archive(libzim.reader.Archive):
@@ -61,7 +60,7 @@ def get_entry_by_id(self, id_: int) -> libzim.reader.Entry:
         """Entry from its Id in ZIM"""
         return self._get_entry_by_id(id_)
 
-    def get_item(self, path: str) -> Item:
+    def get_item(self, path: str) -> libzim.reader.Item:
         """Item from a path"""
         return self.get_entry_by_path(path).get_item()
 

src/zimscraperlib/zim/creator.py

@@ -30,7 +30,7 @@
 
 import libzim.writer  # pyright: ignore
 import PIL.Image
-import regex
+import regex  # pyright: ignore [reportMissingModuleSource]
 
 from zimscraperlib import logger
 from zimscraperlib.constants import (
@@ -491,7 +491,7 @@ def add_redirect(
 
         try:
             try:
-                super().add_redirection(path, title, target_path, hints)
+                super().add_redirection(path, title or path, target_path, hints)
             except RuntimeError as exc:
                 if not DUPLICATE_EXC_STR.match(str(exc)) or not duplicate_ok:
                     raise exc

src/zimscraperlib/zim/items.py

@@ -10,6 +10,7 @@
 import re
 import tempfile
 import urllib.parse
+from collections.abc import Callable
 from typing import Any
 
 import libzim.writer  # pyright: ignore
@@ -65,6 +66,11 @@ def get_hints(self) -> dict:
         return getattr(self, "hints", {})
 
 
+def no_indexing_indexdata() -> IndexData:
+    """IndexData asking libzim not to index this item"""
+    return IndexData("", "")
+
+
 class StaticItem(Item):
     """scraperlib Item with auto contentProvider from `content` or `filepath`
 
@@ -107,19 +113,17 @@ def __init__(
             path=path, title=title, mimetype=mimetype, hints=hints, **kwargs
         )
         if index_data:
-            self.get_indexdata = lambda: index_data
+            self.get_indexdata: Callable[[], IndexData] = lambda: index_data
         elif not auto_index:
-            self.get_indexdata = lambda: IndexData("", "")  # index nothing
+            self.get_indexdata = no_indexing_indexdata  # index nothing
         else:
             self._get_auto_index()  # consider to add auto index
 
         # Populate item title from index data if title is not set by caller
-        if (
-            (not hasattr(self, "title") or not self.title)
-            and hasattr(self, "get_indexdata")
-            and self.get_indexdata().get_title()
-        ):
-            self.title = self.get_indexdata().get_title()
+        if (not getattr(self, "title", None)) and hasattr(self, "get_indexdata"):
+            title = self.get_indexdata().get_title()
+            if title:
+                self.title = title
 
     def get_contentprovider(self) -> libzim.writer.ContentProvider:
         # content was set manually

src/zimscraperlib/zim/providers.py

@@ -13,6 +13,7 @@
 
 import io
 import pathlib
+from typing import Generator
 
 import libzim.writer  # pyright: ignore
 import requests
@@ -61,7 +62,7 @@ def __init__(
     def get_size(self) -> int:
         return self.size  # pyright: ignore
 
-    def gen_blob(self) -> libzim.writer.Blob:
+    def gen_blob(self) -> Generator[libzim.writer.Blob, None, None]:
         yield libzim.writer.Blob(self.fileobj.getvalue())  # pragma: no cover
 
 
@@ -92,7 +93,7 @@ def get_size_of(url) -> int | None:
     def get_size(self) -> int:
         return self.size  # pyright: ignore
 
-    def gen_blob(self) -> libzim.writer.Blob:  # pragma: no cover
+    def gen_blob(self) -> Generator[libzim.writer.Blob, None, None]:  # pragma: no cover
         for chunk in self.resp.iter_content(10 * 1024):
             if chunk:
                 yield libzim.writer.Blob(chunk)

tests/zim/test_zim_creator.py

@@ -38,11 +38,15 @@ def get_size(self) -> int:
 
 
 class SpecialURLProviderItem(StaticItem):
+    url: str
+
     def get_contentprovider(self):
         return SpecialURLProvider(self.url)
 
 
 class FileLikeProviderItem(StaticItem):
+    fileobj: io.BytesIO
+
     def get_contentprovider(self):
         if not self.fileobj:
             raise AttributeError("fileobj cannot be None")
@@ -125,7 +129,7 @@ def test_create_without_workaround(tmp_path):
         fpath, "welcome", workaround_nocancel=False
     ).config_dev_metadata() as creator:
         with pytest.raises(RuntimeError, match="AttributeError"):
-            creator.add_item("hello")
+            creator.add_item("hello")  # pyright: ignore [reportArgumentType]
 
 
 def test_noindexlanguage(tmp_path):