Merge pull request #199 from openzim/types

Introducing Type Hints

Author: rgaudin

CHANGELOG.md

@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 
 - Windows (x64) support (#91)
+- Type stubs (#198)
 
 ### Changed
 

README.md

@@ -149,6 +149,12 @@ with Creator("test.zim") as creator:
         creator.add_item(item2)
 ```
 
+#### Type hints
+
+`libzim` being a binary extension, there is no Python source to provide types information. We provide them as type stub files. When using `pyright`, you would normally receive a warning when importing from `libzim` as there could be discrepencies between actual sources and the (manually crafted) stub files.
+
+You can disable the warning via `reportMissingModuleSource = "none"`.
+
 ## Building
 
 `libzim` package building offers different behaviors via environment variables

libzim/__init__.pyi

@@ -0,0 +1,7 @@
+from libzim import (
+    reader,  # noqa: F401 # pyright: ignore[reportUnusedImport]
+    search,  # noqa: F401 # pyright: ignore[reportUnusedImport]
+    suggestion,  # noqa: F401 # pyright: ignore[reportUnusedImport]
+    version,  # noqa: F401 # pyright: ignore[reportUnusedImport]
+    writer,  # noqa: F401 # pyright: ignore[reportUnusedImport]
+)

libzim/libwrapper.cpp

@@ -224,9 +224,13 @@ WriterItemWrapper::getContentProvider() const
 std::shared_ptr<zim::writer::IndexData>
 WriterItemWrapper::getIndexData() const
 {
+  // Item without method defined (should not happen on proper subclass)
   if (!obj_has_attribute(m_obj, "get_indexdata")) {
     return zim::writer::Item::getIndexData();
   }
+  if (method_is_none(m_obj, "get_indexdata")) {
+    return zim::writer::Item::getIndexData();
+  }
   return callMethodOnObj<std::shared_ptr<zim::writer::IndexData>>(m_obj, "get_indexdata");
 }
 

libzim/libzim.pyx

@@ -88,6 +88,12 @@ cdef object call_method(object obj, string method):
 # object to the correct cpp type.
 # Will be used by cpp side to call python method.
 cdef public api:
+
+    # this tells whether a method/property is none or not
+    bool method_is_none(object obj, string method) with gil:
+        func = getattr(obj, method.decode('UTF-8'))
+        return func is None
+
     bool obj_has_attribute(object obj, string attribute) with gil:
         """Check if a object has a given attribute"""
         return hasattr(obj, attribute.decode('UTF-8'))
@@ -537,6 +543,7 @@ class BaseWritingItem:
 
     def __init__(self):
         self._blob = None
+        get_indexdata = None
 
     def get_path(self) -> str:
         """Full path of item"""
@@ -567,7 +574,7 @@ class BaseWritingItem:
 
 class Creator(_Creator):
     __module__ = writer_module_name
-    def config_compression(self, compression: Compression):
+    def config_compression(self, compression: Union[Compression, str]):
         if not isinstance(compression, Compression):
             compression = getattr(Compression, compression.lower())
         return super().config_compression(compression)

libzim/reader.pyi

@@ -0,0 +1,79 @@
+from __future__ import annotations
+
+import pathlib
+from uuid import UUID
+
+class Item:
+    @property
+    def title(self) -> str: ...
+    @property
+    def path(self) -> str: ...
+    @property
+    def content(self) -> memoryview: ...
+    @property
+    def mimetype(self) -> str: ...
+    @property
+    def _index(self) -> int: ...
+    @property
+    def size(self) -> int: ...
+    def __repr__(self) -> str: ...
+
+class Entry:
+    @property
+    def title(self) -> str: ...
+    @property
+    def path(self) -> str: ...
+    @property
+    def _index(self) -> int: ...
+    @property
+    def is_redirect(self) -> bool: ...
+    def get_redirect_entry(self) -> Entry: ...
+    def get_item(self) -> Item: ...
+    def __repr__(self) -> str: ...
+
+class Archive:
+    def __init__(self, filename: pathlib.Path) -> None: ...
+    @property
+    def filename(self) -> pathlib.Path: ...
+    @property
+    def filesize(self) -> int: ...
+    def has_entry_by_path(self, path: str) -> bool: ...
+    def get_entry_by_path(self, path: str) -> Entry: ...
+    def has_entry_by_title(self, title: str) -> bool: ...
+    def get_entry_by_title(self, title: str) -> Entry: ...
+    @property
+    def metadata_keys(self) -> list[str]: ...
+    def get_metadata_item(self, name: str) -> Item: ...
+    def get_metadata(self, name: str) -> bytes: ...
+    def _get_entry_by_id(self, entry_id: int) -> Entry: ...
+    @property
+    def has_main_entry(self) -> bool: ...
+    @property
+    def main_entry(self) -> Entry: ...
+    @property
+    def uuid(self) -> UUID: ...
+    @property
+    def has_new_namespace_scheme(self) -> bool: ...
+    @property
+    def is_multipart(self) -> bool: ...
+    @property
+    def has_fulltext_index(self) -> bool: ...
+    @property
+    def has_title_index(self) -> bool: ...
+    @property
+    def has_checksum(self) -> str: ...
+    @property
+    def checksum(self) -> str: ...
+    def check(self) -> bool: ...
+    @property
+    def entry_count(self) -> int: ...
+    @property
+    def all_entry_count(self) -> int: ...
+    @property
+    def article_count(self) -> int: ...
+    @property
+    def media_count(self) -> int: ...
+    def get_illustration_sizes(self) -> set[int]: ...
+    def has_illustration(self, size: int | None = None) -> bool: ...
+    def get_illustration_item(self, size: int | None = None) -> Item: ...
+    def __repr__(self) -> str: ...

libzim/search.pyi

@@ -0,0 +1,20 @@
+from __future__ import annotations
+
+from collections.abc import Iterator
+from typing import Self
+
+from libzim.reader import Archive
+
+class Query:
+    def set_query(self, query: str) -> Self: ...
+
+class SearchResultSet:
+    def __iter__(self) -> Iterator[str]: ...
+
+class Search:
+    def getEstimatedMatches(self) -> int: ...  # noqa: N802
+    def getResults(self, start: int, count: int) -> SearchResultSet: ...  # noqa: N802
+
+class Searcher:
+    def __init__(self, archive: Archive) -> None: ...
+    def search(self, query: Query) -> Search: ...

libzim/suggestion.pyi

@@ -0,0 +1,18 @@
+from __future__ import annotations
+
+from collections.abc import Iterator
+
+from libzim.reader import Archive
+
+class SuggestionResultSet:
+    def __iter__(self) -> Iterator[str]: ...
+
+class SuggestionSearch:
+    def getEstimatedMatches(self) -> int: ...  # noqa: N802
+    def getResults(  # noqa: N802
+        self, start: int, count: int
+    ) -> SuggestionResultSet: ...
+
+class SuggestionSearcher:
+    def __init__(self, archive: Archive) -> None: ...
+    def suggest(self, query: str) -> SuggestionSearch: ...

libzim/version.pyi

@@ -0,0 +1,9 @@
+from __future__ import annotations
+
+import sys
+from collections import OrderedDict
+from typing import TextIO
+
+def print_versions(out: TextIO = sys.stdout) -> None: ...
+def get_versions() -> OrderedDict[str, str]: ...
+def get_libzim_version() -> str: ...

libzim/writer.pyi

@@ -0,0 +1,97 @@
+from __future__ import annotations
+
+import datetime
+import enum
+import pathlib
+import types
+from collections.abc import Callable, Generator
+from typing import Self
+
+class Compression(enum.Enum):
+    none: Self
+    zstd: Self
+
+class Hint(enum.Enum):
+    COMPRESS: Self
+    FRONT_ARTICLE: Self
+
+class Blob:
+    def __init__(self, content: str | bytes) -> None: ...
+    def size(self) -> int: ...
+    ref_content: bytes
+
+class ContentProvider:
+    def feed(self) -> Blob: ...
+    def get_size(self) -> int: ...
+    def gen_blob(self) -> Generator[Blob, None, None]: ...
+
+    generator: Generator[Blob, None, None]
+
+class StringProvider(ContentProvider):
+    def __init__(self, content: str | bytes) -> None: ...
+
+class FileProvider(ContentProvider):
+    def __init__(self, filepath: pathlib.Path | str) -> None: ...
+
+class Item:
+    def get_path(self) -> str: ...
+    def get_title(self) -> str: ...
+    def get_mimetype(self) -> str: ...
+    def get_contentprovider(self) -> ContentProvider: ...
+    def get_hints(self) -> dict[Hint, int]: ...
+    def __repr__(self) -> str: ...
+
+    get_indexdata: Callable[[], IndexData | None] | None
+    _blob: Blob
+
+class IndexData:
+    def has_indexdata(self) -> bool: ...
+    def get_title(self) -> str: ...
+    def get_content(self) -> str: ...
+    def get_keywords(self) -> str: ...
+    def get_wordcount(self) -> int: ...
+    def get_geoposition(self) -> tuple[float, float] | None: ...
+
+class Creator:
+    def __init__(self, filename: pathlib.Path) -> None: ...
+    def config_verbose(self, verbose: bool) -> Self: ...
+    def config_compression(self, compression: Compression | str) -> Self: ...
+    def config_clustersize(self, size: int) -> Self: ...
+    def config_indexing(self, indexing: bool, language: str) -> Self: ...
+    def config_nbworkers(self, nbWorkers: int) -> Self: ...  # noqa: N803
+    def set_mainpath(self, mainPath: str) -> Self: ...  # noqa: N803
+    def add_illustration(self, size: int, content: bytes) -> None: ...
+    def add_item(self, writer_item: Item) -> None: ...
+    def add_metadata(
+        self,
+        name: str,
+        content: str | bytes | datetime.date | datetime.datetime,
+        mimetype: str = "text/plain;charset=UTF-8",
+    ) -> None: ...
+    def add_redirection(
+        self,
+        path: str,
+        title: str,
+        targetPath: str,  # noqa: N803
+        hints: dict[Hint, int],
+    ) -> None: ...
+    def add_alias(
+        self,
+        path: str,
+        title: str,
+        targetPath: str,  # noqa: N803
+        hints: dict[Hint, int],
+    ) -> None: ...
+    def __enter__(self) -> Self: ...
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        exc_tb: types.TracebackType | None,
+    ) -> None: ...
+    @property
+    def filename(self) -> pathlib.Path: ...
+    def __repr__(self) -> str: ...
+
+    _filename: pathlib.Path
+    _started: bool