py2docfx 0.1.16.dev2064350__py3-none-any.whl → 0.1.17__py3-none-any.whl

py2docfx/convert_prepare/environment.py

@@ -126,9 +126,7 @@ async def prepare_base_venv(required_package_list: list[PackageInfo], github_tok
 async def prepare_venv(venv_num: int, package_info: PackageInfo, package_number: int, github_token: str, ado_token: str):
     py2docfx_logger = get_logger(__name__)
     await create_environment(get_venv_path(venv_num))
-    if package_info.install_type != package_info.InstallType.SOURCE_CODE or package_info.skip_install != True:
-        # Skip build if the package is source code and skip_install is set to True
-        await install_venv_requirements(venv_num)
+    await install_venv_requirements(venv_num)
     await get_source(get_venv_exe(venv_num), package_info, package_number, vststoken=ado_token, githubtoken=github_token)
     package_name, options = package_info.get_install_command()
     await pip_utils.install_in_exe_async(get_venv_exe(venv_num), package_name, options)

py2docfx/convert_prepare/get_source.py

@@ -42,8 +42,7 @@ def update_package_info(executable: str, pkg: PackageInfo, source_folder: str):
             setattr(pkg, attr, attr_val)
     else:
         folder = next(
-            (f for f in all_files if path.isdir(f) and f.endswith(".dist-info")),
-            None  # Default to None if no match is found
+            f for f in all_files if path.isdir(f) and f.endswith(".dist-info")
         )
         if folder:
             if path.exists(path.join(folder, "METADATA")):
@@ -66,10 +65,6 @@ def update_package_info(executable: str, pkg: PackageInfo, source_folder: str):
                     ".dist-info", "").split("-")
                 pkg.name = "-".join(package_info[0:-1]).strip()
                 pkg.version = package_info[-1].strip()
-        else:
-            # Handle the case where no .dist-info folder is found
-            pkg.name = "unknown"
-            pkg.version = "unknown"
 
     # update package path
     os.chdir(cur_path) # TODO: replace it

py2docfx/convert_prepare/package_info.py

@@ -58,7 +58,7 @@ class PackageInfo:
             package_info.url = package_info_dict.get("url", None)
             package_info.branch = package_info_dict.get("branch", None)
             package_info.folder = package_info_dict.get("folder", None)
-            package_info.skip_install = package_info_dict.get("skip_install", False)
+
             if not package_info.url:
                 py2docfx_logger = get_logger(__name__)
                 if not package_info.folder:

py2docfx/docfx_yaml/miss_reference.py

@@ -29,7 +29,7 @@ def missing_reference(app, env, node, contnode):
             else:
                 fields = (module, node['py:class'], reftarget)
             
-            if not is_built_in_type(reftarget):
+            if not is_built_in_type(reftarget , node):
                 reftarget = '.'.join(
                     field for field in fields if field is not None)
 

py2docfx/docfx_yaml/parameter_utils.py

@@ -111,14 +111,66 @@ def resolve_xref_type(reference):
 
     return xref
 
-def is_typing(s: str) -> bool:
-        if s.startswith('typing.'):
-            s = s.split('.', 1)[1]
-        return s in typing.__all__
+def check_shorten_type_name(type_name: str) -> bool:
+    type_name_elements = type_name.split('.')
+    if len(type_name_elements) == 1:
+        return True
+    else:
+        return False
+
+def check_is_complex_type(type_name: str) -> bool:
+    # check if the type_name contains any of the complex type characters
+    complex_type_chars = ['[', ']', '(', ')', ',']
+    for char in complex_type_chars:
+        if char in type_name:
+            return True
+    return False
+
+def is_typing(node_text: str, node) -> bool:
+    is_in_typing_module_list = False
+    is_shorten_type_name = False
+    has_typing_in_node_attributes = False
+    
+    # check if the node_text is in typing module list
+    check_str = node_text.split('.', 1)[-1]
+    is_in_typing_module_list = check_str in typing.__all__
+
+    # check if the node_text is a simple type name or has form of 'typing.TypeName'
+    typing_prefix = 'typing.'
+    check_typing_str = typing_prefix + node_text.strip()
+
+    def check_shorten_name_and_typing_str(node, attr_str):
+        is_shorten_type_name = check_shorten_type_name(node[attr_str])
+        temp_str = node[attr_str]
+        has_typing_in_node_attributes = check_typing_str == temp_str.strip()
+        return is_shorten_type_name, has_typing_in_node_attributes
+
+    if 'refid' in node.attributes:
+        is_shorten_type_name, has_typing_in_node_attributes = check_shorten_name_and_typing_str(node, 'refid')
+    elif 'refuri' in node.attributes:
+        is_shorten_type_name, has_typing_in_node_attributes = check_shorten_name_and_typing_str(node, 'refuri')
+    elif 'reftarget' in node.attributes:
+        is_shorten_type_name, has_typing_in_node_attributes = check_shorten_name_and_typing_str(node, 'reftarget')
+    else:
+        has_typing_in_node_attributes = False
+
+    # 1. The type has to be in typing module list to be a typing type.
+    # 2. The node['refid'] or node['refuri'] is an abbreviated type name or has typing prefix in its attributes, it is a typing type
+    if is_in_typing_module_list and (is_shorten_type_name or has_typing_in_node_attributes):
+        return True
+    else:
+        return False
 
 def is_system_type(name: str) -> bool:
     return isclass(getattr(builtins, name, None))
 
+def is_complex_type(node_text: str) -> bool:
+    complex_type_chars = ['[', ']', '(', ')']
+    for char in complex_type_chars:
+        if char in node_text:
+            return True
+    return False
+
 def process_complex_type(type_string: str) -> str:
     # replace "or" with ","
     type_string = type_string.replace(" or ", ",")
@@ -167,12 +219,12 @@ def extract_types(ret_data, skip_index_set = [], description_index = None):
         if node.tagname == 'reference':
             if is_system_type(node_text):
                 type_str += f'<xref:{node_text}>'
-            elif is_typing(node_text):
+            elif is_typing(node_text, node):
                 if "typing." not in node_text:
                     type_str += f'<xref:typing.{node_text}>'
                 else:
                     type_str += f'<xref:{node_text}>'
-            elif ('[' in node_text) or (']' in node_text) or ('(' in node_text) or (')' in node_text):
+            elif is_complex_type(node_text):
                 type_str += process_complex_type(node_text)
             else:
                 if 'refid' in node.attributes:

py2docfx/docfx_yaml/tests/roots/test-translator-typing/code_with_typing.py

@@ -0,0 +1,14 @@
+class TestClass:
+    def test_method_with_typing(param):
+        """
+        :param param: Test Param
+        :type param: list[typing.Container]
+        """
+        pass
+    
+    def test_method_without_typing(param):
+        """
+        :param param: Test Param
+        :type param: list[~foo.boo.dummy.Container]
+        """
+        pass

py2docfx/docfx_yaml/tests/roots/test-translator-typing/conf.py

@@ -0,0 +1,18 @@
+import os
+import sys
+
+sys.path.insert(0, os.path.abspath('.'))
+
+extensions = ['sphinx.ext.autodoc', 'yaml_builder']
+
+class includeTest:
+    pass
+
+# The suffix of source filenames.
+source_suffix = '.rst'
+
+autodoc_mock_imports = [
+    'dummy'
+]
+
+nitpicky = True

py2docfx/docfx_yaml/tests/test_translator_typing.py

@@ -0,0 +1,39 @@
+import pytest
+
+from translator import translator
+
+from .utils.test_utils import prepare_app_envs,load_rst_transform_to_doctree
+
+@pytest.mark.sphinx('yaml', testroot='translator-typing')
+def test_with_typing(app):
+    # Test data definition
+    objectToGenXml = 'code_with_typing.TestClass.test_method_with_typing'
+    objectToGenXmlType = 'function'
+
+    # Arrange
+    prepare_app_envs(app, objectToGenXml)
+    doctree = load_rst_transform_to_doctree(app, objectToGenXmlType, objectToGenXml)
+    
+    # Act
+    translator(app, '', doctree)
+
+    # Assert
+    parameterDetail = app.env.docfx_info_field_data[objectToGenXml]['parameters'][0]
+    assert (parameterDetail["type"] == ['<xref:list>[<xref:typing.Container>]'])
+    
+@pytest.mark.sphinx('yaml', testroot='translator-typing')
+def test_without_typing(app):
+    # Test data definition
+    objectToGenXml = 'code_with_typing.TestClass.test_method_without_typing'
+    objectToGenXmlType = 'function'
+
+    # Arrange
+    prepare_app_envs(app, objectToGenXml)
+    doctree = load_rst_transform_to_doctree(app, objectToGenXmlType, objectToGenXml)
+    
+    # Act
+    translator(app, '', doctree)
+
+    # Assert
+    parameterDetail = app.env.docfx_info_field_data[objectToGenXml]['parameters'][0]
+    assert (parameterDetail["type"] == ['<xref:list>[<xref:foo.boo.dummy.Container>]'])

py2docfx/docfx_yaml/utils.py

@@ -47,5 +47,5 @@ def transform_node(app, node):
     writer.write(doc, destination)
     return destination.destination.decode('utf-8')
 
-def is_built_in_type(name: str) -> bool:
-    return parameter_utils.is_system_type(name) or parameter_utils.is_typing(name)
+def is_built_in_type(name: str, node) -> bool:
+    return parameter_utils.is_system_type(name) or parameter_utils.is_typing(name, node)

py2docfx/venv/basevenv/Lib/site-packages/certifi/__init__.py

@@ -1,4 +1,4 @@
 from .core import contents, where
 
 __all__ = ["contents", "where"]
-__version__ = "2025.01.31"
+__version__ = "2025.06.15"

py2docfx/venv/basevenv/Lib/site-packages/certifi/core.py

@@ -46,7 +46,7 @@ if sys.version_info >= (3, 11):
     def contents() -> str:
         return files("certifi").joinpath("cacert.pem").read_text(encoding="ascii")
 
-elif sys.version_info >= (3, 7):
+else:
 
     from importlib.resources import path as get_path, read_text
 
@@ -81,34 +81,3 @@ elif sys.version_info >= (3, 7):
 
     def contents() -> str:
         return read_text("certifi", "cacert.pem", encoding="ascii")
-
-else:
-    import os
-    import types
-    from typing import Union
-
-    Package = Union[types.ModuleType, str]
-    Resource = Union[str, "os.PathLike"]
-
-    # This fallback will work for Python versions prior to 3.7 that lack the
-    # importlib.resources module but relies on the existing `where` function
-    # so won't address issues with environments like PyOxidizer that don't set
-    # __file__ on modules.
-    def read_text(
-        package: Package,
-        resource: Resource,
-        encoding: str = 'utf-8',
-        errors: str = 'strict'
-    ) -> str:
-        with open(where(), encoding=encoding) as data:
-            return data.read()
-
-    # If we don't have importlib.resources, then we will just do the old logic
-    # of assuming we're on the filesystem and munge the path directly.
-    def where() -> str:
-        f = os.path.dirname(__file__)
-
-        return os.path.join(f, "cacert.pem")
-
-    def contents() -> str:
-        return read_text("certifi", "cacert.pem", encoding="ascii")

py2docfx/venv/basevenv/Lib/site-packages/charset_normalizer/cli/__main__.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import argparse
 import sys
+import typing
 from json import dumps
 from os.path import abspath, basename, dirname, join, realpath
 from platform import python_version
@@ -43,7 +44,66 @@ def query_yes_no(question: str, default: str = "yes") -> bool:
         elif choice in valid:
             return valid[choice]
         else:
-            sys.stdout.write("Please respond with 'yes' or 'no' " "(or 'y' or 'n').\n")
+            sys.stdout.write("Please respond with 'yes' or 'no' (or 'y' or 'n').\n")
+
+
+class FileType:
+    """Factory for creating file object types
+
+    Instances of FileType are typically passed as type= arguments to the
+    ArgumentParser add_argument() method.
+
+    Keyword Arguments:
+        - mode -- A string indicating how the file is to be opened. Accepts the
+            same values as the builtin open() function.
+        - bufsize -- The file's desired buffer size. Accepts the same values as
+            the builtin open() function.
+        - encoding -- The file's encoding. Accepts the same values as the
+            builtin open() function.
+        - errors -- A string indicating how encoding and decoding errors are to
+            be handled. Accepts the same value as the builtin open() function.
+
+    Backported from CPython 3.12
+    """
+
+    def __init__(
+        self,
+        mode: str = "r",
+        bufsize: int = -1,
+        encoding: str | None = None,
+        errors: str | None = None,
+    ):
+        self._mode = mode
+        self._bufsize = bufsize
+        self._encoding = encoding
+        self._errors = errors
+
+    def __call__(self, string: str) -> typing.IO:  # type: ignore[type-arg]
+        # the special argument "-" means sys.std{in,out}
+        if string == "-":
+            if "r" in self._mode:
+                return sys.stdin.buffer if "b" in self._mode else sys.stdin
+            elif any(c in self._mode for c in "wax"):
+                return sys.stdout.buffer if "b" in self._mode else sys.stdout
+            else:
+                msg = f'argument "-" with mode {self._mode}'
+                raise ValueError(msg)
+
+        # all other arguments are used as file names
+        try:
+            return open(string, self._mode, self._bufsize, self._encoding, self._errors)
+        except OSError as e:
+            message = f"can't open '{string}': {e}"
+            raise argparse.ArgumentTypeError(message)
+
+    def __repr__(self) -> str:
+        args = self._mode, self._bufsize
+        kwargs = [("encoding", self._encoding), ("errors", self._errors)]
+        args_str = ", ".join(
+            [repr(arg) for arg in args if arg != -1]
+            + [f"{kw}={arg!r}" for kw, arg in kwargs if arg is not None]
+        )
+        return f"{type(self).__name__}({args_str})"
 
 
 def cli_detect(argv: list[str] | None = None) -> int:
@@ -59,7 +119,7 @@ def cli_detect(argv: list[str] | None = None) -> int:
     )
 
     parser.add_argument(
-        "files", type=argparse.FileType("rb"), nargs="+", help="File(s) to be analysed"
+        "files", type=FileType("rb"), nargs="+", help="File(s) to be analysed"
     )
     parser.add_argument(
         "-v",

py2docfx/venv/basevenv/Lib/site-packages/charset_normalizer/constant.py

@@ -549,6 +549,23 @@ COMMON_SAFE_ASCII_CHARACTERS: set[str] = {
     ")",
 }
 
+# Sample character sets — replace with full lists if needed
+COMMON_CHINESE_CHARACTERS = "的一是在不了有和人这中大为上个国我以要他时来用们生到作地于出就分对成会可主发年动同工也能下过子说产种面而方后多定行学法所民得经十三之进着等部度家电力里如水化高自二理起小物现实加量都两体制机当使点从业本去把性好应开它合还因由其些然前外天政四日那社义事平形相全表间样与关各重新线内数正心反你明看原又么利比或但质气第向道命此变条只没结解问意建月公无系军很情者最立代想已通并提直题党程展五果料象员革位入常文总次品式活设及管特件长求老头基资边流路级少图山统接知较将组见计别她手角期根论运农指几九区强放决西被干做必战先回则任取据处队南给色光门即保治北造百规热领七海口东导器压志世金增争济阶油思术极交受联什认六共权收证改清己美再采转更单风切打白教速花带安场身车例真务具万每目至达走积示议声报斗完类八离华名确才科张信马节话米整空元况今集温传土许步群广石记需段研界拉林律叫且究观越织装影算低持音众书布复容儿须际商非验连断深难近矿千周委素技备半办青省列习响约支般史感劳便团往酸历市克何除消构府太准精值号率族维划选标写存候毛亲快效斯院查江型眼王按格养易置派层片始却专状育厂京识适属圆包火住调满县局照参红细引听该铁价严龙飞"
+
+COMMON_JAPANESE_CHARACTERS = "日一国年大十二本中長出三時行見月分後前生五間上東四今金九入学高円子外八六下来気小七山話女北午百書先名川千水半男西電校語土木聞食車何南万毎白天母火右読友左休父雨"
+
+COMMON_KOREAN_CHARACTERS = "一二三四五六七八九十百千萬上下左右中人女子大小山川日月火水木金土父母天地國名年時文校學生"
+
+# Combine all into a set
+COMMON_CJK_CHARACTERS = set(
+    "".join(
+        [
+            COMMON_CHINESE_CHARACTERS,
+            COMMON_JAPANESE_CHARACTERS,
+            COMMON_KOREAN_CHARACTERS,
+        ]
+    )
+)
 
 KO_NAMES: set[str] = {"johab", "cp949", "euc_kr"}
 ZH_NAMES: set[str] = {"big5", "cp950", "big5hkscs", "hz"}

py2docfx/venv/basevenv/Lib/site-packages/charset_normalizer/legacy.py

@@ -37,9 +37,7 @@ def detect(
 
     if not isinstance(byte_str, (bytearray, bytes)):
         raise TypeError(  # pragma: nocover
-            "Expected object of type bytes or bytearray, got: " "{}".format(
-                type(byte_str)
-            )
+            f"Expected object of type bytes or bytearray, got: {type(byte_str)}"
         )
 
     if isinstance(byte_str, bytearray):

py2docfx/venv/basevenv/Lib/site-packages/charset_normalizer/md.py

@@ -26,6 +26,7 @@ from .utils import (
     is_unprintable,
     remove_accent,
     unicode_range,
+    is_cjk_uncommon,
 )
 
 
@@ -365,35 +366,39 @@ class SuperWeirdWordPlugin(MessDetectorPlugin):
         return self._bad_character_count / self._character_count
 
 
-class CjkInvalidStopPlugin(MessDetectorPlugin):
+class CjkUncommonPlugin(MessDetectorPlugin):
     """
-    GB(Chinese) based encoding often render the stop incorrectly when the content does not fit and
-    can be easily detected. Searching for the overuse of '丅' and '丄'.
+    Detect messy CJK text that probably means nothing.
     """
 
     def __init__(self) -> None:
-        self._wrong_stop_count: int = 0
-        self._cjk_character_count: int = 0
+        self._character_count: int = 0
+        self._uncommon_count: int = 0
 
     def eligible(self, character: str) -> bool:
-        return True
+        return is_cjk(character)
 
     def feed(self, character: str) -> None:
-        if character in {"丅", "丄"}:
-            self._wrong_stop_count += 1
+        self._character_count += 1
+
+        if is_cjk_uncommon(character):
+            self._uncommon_count += 1
             return
-        if is_cjk(character):
-            self._cjk_character_count += 1
 
     def reset(self) -> None:  # Abstract
-        self._wrong_stop_count = 0
-        self._cjk_character_count = 0
+        self._character_count = 0
+        self._uncommon_count = 0
 
     @property
     def ratio(self) -> float:
-        if self._cjk_character_count < 16:
+        if self._character_count < 8:
             return 0.0
-        return self._wrong_stop_count / self._cjk_character_count
+
+        uncommon_form_usage: float = self._uncommon_count / self._character_count
+
+        # we can be pretty sure it's garbage when uncommon characters are widely
+        # used. otherwise it could just be traditional chinese for example.
+        return uncommon_form_usage / 10 if uncommon_form_usage > 0.5 else 0.0
 
 
 class ArchaicUpperLowerPlugin(MessDetectorPlugin):

py2docfx/venv/basevenv/Lib/site-packages/charset_normalizer/utils.py

@@ -20,6 +20,7 @@ from .constant import (
     UNICODE_RANGES_COMBINED,
     UNICODE_SECONDARY_RANGE_KEYWORD,
     UTF8_MAXIMAL_ALLOCATION,
+    COMMON_CJK_CHARACTERS,
 )
 
 
@@ -200,6 +201,11 @@ def is_arabic_isolated_form(character: str) -> bool:
     return "ARABIC" in character_name and "ISOLATED FORM" in character_name
 
 
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_cjk_uncommon(character: str) -> bool:
+    return character not in COMMON_CJK_CHARACTERS
+
+
 @lru_cache(maxsize=len(UNICODE_RANGES_COMBINED))
 def is_unicode_range_secondary(range_name: str) -> bool:
     return any(keyword in range_name for keyword in UNICODE_SECONDARY_RANGE_KEYWORD)

py2docfx/venv/basevenv/Lib/site-packages/charset_normalizer/version.py

@@ -4,5 +4,5 @@ Expose version
 
 from __future__ import annotations
 
-__version__ = "3.4.1"
+__version__ = "3.4.2"
 VERSION = __version__.split(".")

py2docfx/venv/basevenv/Lib/site-packages/packaging/__init__.py

@@ -6,7 +6,7 @@ __title__ = "packaging"
 __summary__ = "Core utilities for Python packages"
 __uri__ = "https://github.com/pypa/packaging"
 
-__version__ = "24.2"
+__version__ = "25.0"
 
 __author__ = "Donald Stufft and individual contributors"
 __email__ = "donald@stufft.io"

py2docfx/venv/basevenv/Lib/site-packages/packaging/_elffile.py

@@ -69,8 +69,7 @@ class ELFFile:
             }[(self.capacity, self.encoding)]
         except KeyError as e:
             raise ELFInvalid(
-                f"unrecognized capacity ({self.capacity}) or "
-                f"encoding ({self.encoding})"
+                f"unrecognized capacity ({self.capacity}) or encoding ({self.encoding})"
             ) from e
 
         try:

py2docfx/venv/basevenv/Lib/site-packages/packaging/_manylinux.py

@@ -161,8 +161,7 @@ def _parse_glibc_version(version_str: str) -> tuple[int, int]:
     m = re.match(r"(?P<major>[0-9]+)\.(?P<minor>[0-9]+)", version_str)
     if not m:
         warnings.warn(
-            f"Expected glibc version with 2 components major.minor,"
-            f" got: {version_str}",
+            f"Expected glibc version with 2 components major.minor, got: {version_str}",
             RuntimeWarning,
             stacklevel=2,
         )

py2docfx/venv/basevenv/Lib/site-packages/packaging/_parser.py

@@ -349,6 +349,5 @@ def _parse_marker_op(tokenizer: Tokenizer) -> Op:
         return Op(tokenizer.read().text)
     else:
         return tokenizer.raise_syntax_error(
-            "Expected marker operator, one of "
-            "<=, <, !=, ==, >=, >, ~=, ===, in, not in"
+            "Expected marker operator, one of <=, <, !=, ==, >=, >, ~=, ===, in, not in"
         )

py2docfx/venv/basevenv/Lib/site-packages/packaging/_tokenizer.py

@@ -68,7 +68,8 @@ DEFAULT_RULES: dict[str, str | re.Pattern[str]] = {
                 |platform[._](version|machine|python_implementation)
                 |python_implementation
                 |implementation_(name|version)
-                |extra
+                |extras?
+                |dependency_groups
             )\b
         """,
         re.VERBOSE,
@@ -119,9 +120,9 @@ class Tokenizer:
         another check. If `peek` is set to `True`, the token is not loaded and
         would need to be checked again.
         """
-        assert (
-            self.next_token is None
-        ), f"Cannot check for {name!r}, already have {self.next_token!r}"
+        assert self.next_token is None, (
+            f"Cannot check for {name!r}, already have {self.next_token!r}"
+        )
         assert name in self.rules, f"Unknown token name: {name!r}"
 
         expression = self.rules[name]

py2docfx/venv/basevenv/Lib/site-packages/packaging/licenses/__init__.py

@@ -37,8 +37,8 @@ from typing import NewType, cast
 from packaging.licenses._spdx import EXCEPTIONS, LICENSES
 
 __all__ = [
-    "NormalizedLicenseExpression",
     "InvalidLicenseExpression",
+    "NormalizedLicenseExpression",
     "canonicalize_license_expression",
 ]