swarmauri_parser_pypdf2 0.6.0.dev154__py3-none-any.whl

swarmauri_parser_pypdf2/PyPDF2Parser.py

@@ -0,0 +1,68 @@
+from typing import List, Literal, Union
+
+import PyPDF2
+from swarmauri_core.ComponentBase import ComponentBase
+from swarmauri_standard.documents.Document import Document
+from swarmauri_base.parsers.ParserBase import ParserBase
+from swarmauri_core.documents.IDocument import IDocument
+
+
+@ComponentBase.register_type(ParserBase, "PyPDF2Parser")
+class PyPDF2Parser(ParserBase):
+    """
+    Parser for reading and extracting text from PDF files using PyPDF2.
+    """
+
+    type: Literal["PyPDF2Parser"] = "PyPDF2Parser"
+
+    def parse(self, source: Union[str, bytes]) -> List[IDocument]:
+        """
+        Parses a PDF file and extracts text from each page as Document instances.
+
+        Parameters:
+        - source (Union[str, bytes]): The path to the PDF file or bytes of the PDF content.
+
+        Returns:
+        - List[IDocument]: A list of IDocument instances with the extracted text.
+        """
+        documents = []
+
+        if isinstance(source, str):
+            try:
+                with open(source, "rb") as file:
+                    reader = PyPDF2.PdfReader(file)
+                    for page_num, page in enumerate(reader.pages):
+                        text = page.extract_text()
+                        if text:
+                            document = Document(
+                                content=text.strip(),
+                                metadata={
+                                    "page_number": page_num + 1,
+                                    "source": source,
+                                },
+                            )
+                            documents.append(document)
+            except Exception as e:
+                print(f"An error occurred while parsing the PDF '{source}': {e}")
+                return []
+        elif isinstance(source, bytes):
+            try:
+                from io import BytesIO
+
+                file_stream = BytesIO(source)
+                reader = PyPDF2.PdfReader(file_stream)
+                for page_num, page in enumerate(reader.pages):
+                    text = page.extract_text()
+                    if text:
+                        document = Document(
+                            content=text.strip(),
+                            metadata={"page_number": page_num + 1, "source": "bytes"},
+                        )
+                        documents.append(document)
+            except Exception as e:
+                print("An error occurred while parsing the PDF from bytes:", e)
+                return []
+        else:
+            raise TypeError("Source must be of type str (file path) or bytes.")
+
+        return documents

swarmauri_parser_pypdf2/__init__.py

@@ -0,0 +1,15 @@
+# swm_example_community_package/__init__.py
+__version__ = "0.6.0.dev26"
+__long_desc__ = """
+
+# Swarmauri Example Plugin
+
+This repository includes an example of a Swarmauri Plugin.
+
+Visit us at: https://swarmauri.com
+Follow us at: https://github.com/swarmauri
+Star us at: https://github.com/swarmauri/swarmauri-sdk
+
+"""
+
+

swarmauri_parser_pypdf2-0.6.0.dev154.dist-info/METADATA

@@ -0,0 +1,20 @@
+Metadata-Version: 2.3
+Name: swarmauri_parser_pypdf2
+Version: 0.6.0.dev154
+Summary: PyPDF2 Parser for Swarmauri.
+License: Apache-2.0
+Author: Jacob Stewart
+Author-email: jacob@swarmauri.com
+Requires-Python: >=3.10,<3.13
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: pypdf (>=5.0.1,<6.0.0)
+Requires-Dist: swarmauri_base (>=0.6.0.dev154,<0.7.0)
+Requires-Dist: swarmauri_core (>=0.6.0.dev154,<0.7.0)
+Project-URL: Repository, http://github.com/swarmauri/swarmauri-sdk
+Description-Content-Type: text/markdown
+
+# Swarmauri Example Community Package

swarmauri_parser_pypdf2-0.6.0.dev154.dist-info/RECORD

@@ -0,0 +1,6 @@
+swarmauri_parser_pypdf2/__init__.py,sha256=0JPWFMiRDsSmfgYFpZWp31sknn1CPYYATVUlg4tY14o,336
+swarmauri_parser_pypdf2/PyPDF2Parser.py,sha256=aFxSVbZUcohWFPbLlw4ChhlPDgjwH9wk8FvdKztXW4o,2683
+swarmauri_parser_pypdf2-0.6.0.dev154.dist-info/entry_points.txt,sha256=Ay1D3vv7qKTKfWIWJqTgodYxit45IkQ3Fl3yaMuKWRw,84
+swarmauri_parser_pypdf2-0.6.0.dev154.dist-info/METADATA,sha256=a3nTfp-ucUiaDCIeVhzuisVJ5_POP-Z9X3hUpTv60k0,774
+swarmauri_parser_pypdf2-0.6.0.dev154.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
+swarmauri_parser_pypdf2-0.6.0.dev154.dist-info/RECORD,,

swarmauri_parser_pypdf2-0.6.0.dev154.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: poetry-core 2.0.1
+Root-Is-Purelib: true
+Tag: py3-none-any

swarmauri_parser_pypdf2-0.6.0.dev154.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[swarmauri.parsers]
+PyPDF2Parser=swarmauri_parser_pypdf2.PyPDF2Parser:PyPDF2Parser
+