Merge pull request #47 from ddkasa/atom-support

Atom Support

pyproject.toml

@@ -92,6 +92,9 @@ select = [
 "**/__init__.py" = [
     "F401"
 ]
+"rss_parser/models/atom/**" = [
+    "A003"
+]
 
 
 [build-system]

rss_parser/__init__.py

@@ -1 +1,3 @@
-from ._parser import Parser
+from ._parser import AtomParser, BaseParser, Parser, RSSParser
+
+__all__ = ("BaseParser", "Parser", "AtomParser", "RSSParser")

rss_parser/_parser.py

@@ -2,42 +2,72 @@
 
 from xmltodict import parse
 
+from rss_parser.custom_decorators import abstract_class_attributes
 from rss_parser.models import XMLBaseModel
+from rss_parser.models.atom import Atom
 from rss_parser.models.rss import RSS
 
 # >>> FUTURE
 # TODO: May be support generator based approach for big rss feeds
 # TODO: Add cli to parse to json
 # TODO: Possibly bundle as deb/rpm/exe
-# TODO: Atom support
-# TODO: Older RSS versions?
+# TODO: Older Atom versions
+# TODO: Older RSS versions
 
 
-class Parser:
-    """Parser for rss files."""
+@abstract_class_attributes("schema")
+class BaseParser:
+    """Parser for rss/atom files."""
 
-    schema: ClassVar[Type[XMLBaseModel]] = RSS
-
-    @staticmethod
-    def _check_atom(root: dict):
-        if "feed" in root:
-            raise NotImplementedError("ATOM feed is not currently supported")
+    schema: ClassVar[Type[XMLBaseModel]]
+    root_key: Optional[str] = None
 
     @staticmethod
     def to_xml(data: str, *args, **kwargs):
         return parse(str(data), *args, **kwargs)
 
     @classmethod
-    def parse(cls, data: str, *, schema: Optional[Type[XMLBaseModel]] = None) -> XMLBaseModel:
+    def parse(
+        cls,
+        data: str,
+        *,
+        schema: Optional[Type[XMLBaseModel]] = None,
+        root_key: Optional[str] = None,
+    ) -> XMLBaseModel:
         """
-        Parse XML data into schema (default: RSS 2.0).
-
+        Parse XML data into schema.
         :param data: string of XML data that needs to be parsed
         :return: "schema" object
         """
         root = cls.to_xml(data)
-        cls._check_atom(root)
 
-        schema = schema or cls.schema
+        schema = schema if schema else cls.schema
+
+        root_key = root_key if root_key else cls.root_key
+
+        if root_key:
+            root = root.get(root_key, root)
+
+        return schema.parse_obj(root)
+
+
+class AtomParser(BaseParser):
+    schema = Atom
+
+
+class RSSParser(BaseParser):
+    root_key = "rss"
+    schema = RSS
+
+
+class Parser(RSSParser):
+    @classmethod
+    def parse(cls, data: str, *, schema: Optional[Type[XMLBaseModel]] = None) -> XMLBaseModel:
+        import warnings
 
-        return schema.parse_obj(root["rss"])
+        warnings.warn(
+            "Class Parser was renamed to RSSParser " "and will be removed in the next major update",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        return RSSParser.parse(data, schema=schema)

rss_parser/custom_decorators.py

@@ -0,0 +1,43 @@
+def abstract_class_attributes(*names):
+    """Class decorator to add one or more abstract attribute."""
+
+    def _func(cls, *names):
+        """Function that extends the __init_subclass__ method of a class."""
+
+        # Add each attribute to the class with the value of NotImplemented
+        for name in names:
+            setattr(cls, name, NotImplemented)
+
+        # Save the original __init_subclass__ implementation, then wrap
+        # it with our new implementation.
+        orig_init_subclass = cls.__init_subclass__
+
+        def new_init_subclass(cls, **kwargs):
+            """
+            New definition of __init_subclass__ that checks that
+            attributes are implemented.
+            """
+
+            # The default implementation of __init_subclass__ takes no
+            # positional arguments, but a custom implementation does.
+            # If the user has not reimplemented __init_subclass__ then
+            # the first signature will fail and we try the second.
+            try:
+                orig_init_subclass(cls, **kwargs)
+            except TypeError:
+                orig_init_subclass(**kwargs)
+
+            # Check that each attribute is defined.
+            for name in names:
+                if getattr(cls, name, NotImplemented) is NotImplemented:
+                    raise NotImplementedError(f"Class attribute {name} must be set for class {cls}")
+
+        # Bind this new function to the __init_subclass__.
+        # For reasons beyond the scope here, it we must manually
+        # declare it as a classmethod because it is not done automatically
+        # as it would be if declared in the standard way.
+        cls.__init_subclass__ = classmethod(new_init_subclass)
+
+        return cls
+
+    return lambda cls: _func(cls, *names)

rss_parser/models/atom/__init__.py

@@ -0,0 +1,3 @@
+from .atom import Atom
+
+__all__ = ("Atom",)

rss_parser/models/atom/atom.py

@@ -0,0 +1,15 @@
+from typing import Optional
+
+from rss_parser.models import XMLBaseModel
+from rss_parser.models.atom.feed import Feed
+from rss_parser.models.types.tag import Tag
+from rss_parser.pydantic_proxy import import_v1_pydantic
+
+pydantic = import_v1_pydantic()
+
+
+class Atom(XMLBaseModel):
+    """Atom 1.0"""
+
+    version: Optional[Tag[str]] = pydantic.Field(alias="@version")
+    feed: Tag[Feed]

rss_parser/models/atom/entry.py

@@ -0,0 +1,56 @@
+from typing import Optional
+
+from rss_parser.models import XMLBaseModel
+from rss_parser.models.atom.person import Person
+from rss_parser.models.types.date import DateTimeOrStr
+from rss_parser.models.types.only_list import OnlyList
+from rss_parser.models.types.tag import Tag
+from rss_parser.pydantic_proxy import import_v1_pydantic
+
+pydantic = import_v1_pydantic()
+
+
+class RequiredAtomEntryMixin(XMLBaseModel):
+    id: Tag[str]
+    "Identifier for the entry."
+
+    title: Tag[str]
+    "The title of the entry."
+
+    updated: Tag[DateTimeOrStr]
+    "Indicates when the entry was updated."
+
+
+class RecommendedAtomEntryMixin(XMLBaseModel):
+    authors: Optional[OnlyList[Tag[Person]]] = pydantic.Field(alias="author", default=[])
+    "Entry authors."
+
+    links: Optional[OnlyList[Tag[str]]] = pydantic.Field(alias="link", default=[])
+    "The URL of the entry."
+
+    content: Optional[Tag[str]] = None
+    "The main content of the entry."
+
+    summary: Optional[Tag[str]] = None
+    "Conveys a short summary, abstract, or excerpt of the entry. Some feeds use this tag as the main content."
+
+
+class OptionalAtomEntryMixin(XMLBaseModel):
+    categories: Optional[OnlyList[Tag[dict]]] = pydantic.Field(alias="category", default=[])
+    "Specifies a categories that the entry belongs to."
+
+    contributors: Optional[OnlyList[Tag[Person]]] = pydantic.Field(alias="contributor", default=[])
+    "Entry contributors."
+
+    rights: Optional[Tag[str]] = None
+    "The copyright of the entry."
+
+    published: Optional[Tag[DateTimeOrStr]] = None
+    "Indicates when the entry was published."
+
+    source: Optional[Tag[str]] = None
+    "Contains metadata from the source feed if this entry is a copy."
+
+
+class Entry(RequiredAtomEntryMixin, RecommendedAtomEntryMixin, OptionalAtomEntryMixin, XMLBaseModel):
+    """https://validator.w3.org/feed/docs/atom.html"""

rss_parser/models/atom/feed.py

@@ -0,0 +1,61 @@
+from typing import Optional
+
+from rss_parser.models import XMLBaseModel
+from rss_parser.models.atom.entry import Entry
+from rss_parser.models.atom.person import Person
+from rss_parser.models.types.date import DateTimeOrStr
+from rss_parser.models.types.only_list import OnlyList
+from rss_parser.models.types.tag import Tag
+from rss_parser.pydantic_proxy import import_v1_pydantic
+
+pydantic = import_v1_pydantic()
+
+
+class RequiredAtomFeedMixin(XMLBaseModel):
+    id: Tag[str]
+    "Identifies the feed using a universally unique and permanent URI."
+
+    title: Tag[str]
+    "Contains a human readable title for the feed."
+
+    updated: Tag[DateTimeOrStr]
+    "Indicates the last time the feed was modified in a significant way."
+
+
+class RecommendedAtomFeedMixin(XMLBaseModel):
+    authors: Optional[OnlyList[Tag[Person]]] = pydantic.Field(alias="author", default=[])
+    "Names one author of the feed. A feed may have multiple author elements."
+
+    links: Optional[OnlyList[Tag[str]]] = pydantic.Field(alias="link", default=[])
+    "The URL to the feed. A feed may have multiple link elements."
+
+
+class OptionalAtomFeedMixin(XMLBaseModel):
+    entries: Optional[OnlyList[Tag[Entry]]] = pydantic.Field(alias="entry", default=[])
+    "The entries in the feed. A feed may have multiple entry elements."
+
+    categories: Optional[OnlyList[Tag[dict]]] = pydantic.Field(alias="category", default=[])
+    "Specifies a categories that the feed belongs to. The feed may have multiple categories elements."
+
+    contributors: Optional[OnlyList[Tag[Person]]] = pydantic.Field(alias="contributor", default=[])
+    "Feed contributors."
+
+    generator: Optional[Tag[str]] = None
+    "Identifies the software used to generate the feed, for debugging and other purposes."
+
+    icon: Optional[Tag[str]] = None
+    "Identifies a small image which provides iconic visual identification for the feed. Icons should be square."
+
+    logo: Optional[Tag[str]] = None
+    "Identifies a larger image which provides visual identification for the feed. \
+    Images should be twice as wide as they are tall."
+
+    rights: Optional[Tag[str]] = None
+    "The copyright of the feed."
+
+    subtitle: Optional[Tag[str]] = None
+    "Contains a human readable description or subtitle for the feed."
+
+
+class Feed(RequiredAtomFeedMixin, RecommendedAtomFeedMixin, OptionalAtomFeedMixin, XMLBaseModel):
+    """https://validator.w3.org/feed/docs/atom.html"""

rss_parser/models/atom/person.py

@@ -0,0 +1,18 @@
+from typing import Optional
+
+from rss_parser.models import XMLBaseModel
+from rss_parser.models.types.tag import Tag
+from rss_parser.pydantic_proxy import import_v1_pydantic
+
+pydantic = import_v1_pydantic()
+
+
+class Person(XMLBaseModel):
+    name: Tag[str]
+    "Conveys a human-readable name for the person."
+
+    uri: Optional[Tag[str]] = None
+    "Contains a home page for the person."
+
+    email: Optional[Tag[str]] = None
+    "Contains an email address for the person."

rss_parser/models/atom/source.py

@@ -0,0 +1,19 @@
+from typing import Optional
+
+from rss_parser.models import XMLBaseModel
+from rss_parser.models.types.date import DateTimeOrStr
+from rss_parser.models.types.tag import Tag
+from rss_parser.pydantic_proxy import import_v1_pydantic
+
+pydantic = import_v1_pydantic()
+
+
+class Source(XMLBaseModel):
+    id: Optional[Tag[str]] = None
+    "Source id."
+
+    title: Optional[Tag[str]] = None
+    "Title of the source."
+
+    updated: Optional[Tag[DateTimeOrStr]] = None
+    "When source was updated."

rss_parser/models/rss/__init__.py

@@ -0,0 +1,3 @@
+from .rss import RSS
+
+__all__ = ("RSS",)

rss_parser/models/channel.py → rss_parser/models/rss/channel.py

@@ -1,9 +1,9 @@
 from typing import Optional
 
 from rss_parser.models import XMLBaseModel
-from rss_parser.models.image import Image
-from rss_parser.models.item import Item
-from rss_parser.models.text_input import TextInput
+from rss_parser.models.rss.image import Image
+from rss_parser.models.rss.item import Item
+from rss_parser.models.rss.text_input import TextInput
 from rss_parser.models.types.date import DateTimeOrStr
 from rss_parser.models.types.only_list import OnlyList
 from rss_parser.models.types.tag import Tag

rss_parser/models/rss.py → rss_parser/models/rss/rss.py

@@ -1,7 +1,7 @@
 from typing import Optional
 
 from rss_parser.models import XMLBaseModel
-from rss_parser.models.channel import Channel
+from rss_parser.models.rss.channel import Channel
 from rss_parser.models.types.tag import Tag
 from rss_parser.pydantic_proxy import import_v1_pydantic
 

rss_parser/models/types/date.py

@@ -1,6 +1,10 @@
 from datetime import datetime
 from email.utils import parsedate_to_datetime
 
+from rss_parser.pydantic_proxy import import_v1_pydantic
+
+pydantic_validators = import_v1_pydantic(".validators")
+
 
 class DateTimeOrStr(datetime):
     @classmethod
@@ -25,16 +29,11 @@ def validate_dt_or_str(value: str) -> datetime:
     # Try to parse standard (RFC 822)
     try:
         return parsedate_to_datetime(value)
-    except ValueError:
-        pass
-    # Try ISO
-    try:
-        return datetime.fromisoformat(value)
-    except ValueError:
+    except (ValueError, TypeError):  # https://github.com/python/cpython/issues/74866
         pass
-    # Try timestamp
+    # Try ISO or timestamp
     try:
-        return datetime.fromtimestamp(int(value))
+        return pydantic_validators.parse_datetime(value)
     except ValueError:
         pass
 

rss_parser/models/types/tag.py

@@ -28,7 +28,7 @@ class Tag(pydantic_generics.GenericModel, Generic[T]):
     >>> m.width.content
     48
     >>> type(m.width), type(m.width.content)
-    (<class 'rss_parser.models.image.Tag[int]'>, <class 'int'>)
+    (<class 'rss_parser.models.rss.image.Tag[int]'>, <class 'int'>)
     >>> # The attributes are empty by default
     >>> m.width.attributes
     {}