swarmauri_parser_fitzpdf 0.6.0.dev154__tar.gz

swarmauri_parser_fitzpdf-0.6.0.dev154/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.3
+Name: swarmauri_parser_fitzpdf
+Version: 0.6.0.dev154
+Summary: Fitz PDF 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: PyMuPDF (>=1.24.12,<2.0.0)
+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_fitzpdf-0.6.0.dev154/README.md

@@ -0,0 +1 @@
+# Swarmauri Example Community Package

swarmauri_parser_fitzpdf-0.6.0.dev154/pyproject.toml

@@ -0,0 +1,57 @@
+[tool.poetry]
+name = "swarmauri_parser_fitzpdf"
+version = "0.6.0.dev154"
+description = "Fitz PDF Parser for Swarmauri."
+authors = ["Jacob Stewart <jacob@swarmauri.com>"]
+license = "Apache-2.0"
+readme = "README.md"
+repository = "http://github.com/swarmauri/swarmauri-sdk"
+classifiers = [
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12"
+]
+
+[tool.poetry.dependencies]
+python = ">=3.10,<3.13"
+
+# Swarmauri
+swarmauri_core = {version = "^0.6.0.dev154"}
+swarmauri_base = {version = "^0.6.0.dev154"}
+
+# Dependencies
+PyMuPDF = "^1.24.12"
+
+
+[tool.poetry.group.dev.dependencies]
+flake8 = "^7.0"
+pytest = "^8.0"
+pytest-asyncio = ">=0.24.0"
+pytest-xdist = "^3.6.1"
+pytest-json-report = "^1.5.0"
+python-dotenv = "*"
+requests = "^2.32.3"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+norecursedirs = ["combined", "scripts"]
+
+markers = [
+    "test: standard test",
+    "unit: Unit tests",
+    "integration: Integration tests",
+    "acceptance: Acceptance tests",
+    "experimental: Experimental tests"
+]
+log_cli = true
+log_cli_level = "INFO"
+log_cli_format = "%(asctime)s [%(levelname)s] %(message)s"
+log_cli_date_format = "%Y-%m-%d %H:%M:%S"
+asyncio_default_fixture_loop_scope = "function"
+
+[tool.poetry.plugins."swarmauri.parsers"]
+FitzPdfParser = "swarmauri_parser_fitzpdf.FitzPdfParser:FitzPdfParser"

swarmauri_parser_fitzpdf-0.6.0.dev154/swarmauri_parser_fitzpdf/FitzPdfParser.py

@@ -0,0 +1,47 @@
+from swarmauri_core.ComponentBase import ComponentBase
+import pymupdf  # PyMuPDF
+from typing import List, Union, Any, Literal
+from swarmauri.parsers.base.ParserBase import ParserBase
+from swarmauri_core.documents.IDocument import IDocument
+from swarmauri.documents.concrete.Document import Document
+
+
+@ComponentBase.register_type(ParserBase, "FitzPdfParser")
+class PDFtoTextParser(ParserBase):
+    """
+    A parser to extract text from PDF files.
+    """
+
+    type: Literal["FitzPdfParser"] = "FitzPdfParser"
+
+    def parse(self, data: Union[str, Any]) -> List[IDocument]:
+        """
+        Parses a PDF file and extracts its text content as Document instances.
+
+        Parameters:
+        - data (Union[str, Any]): The path to the PDF file.
+
+        Returns:
+        - List[IDocument]: A list with a single IDocument instance containing the extracted text.
+        """
+        # Ensure data is a valid str path to a PDF file
+        if not isinstance(data, str):
+            raise ValueError("PDFtoTextParser expects a file path in str format.")
+
+        try:
+            # Open the PDF file
+            doc = pymupdf.open(data)
+            text = ""
+
+            # Extract text from each page
+            for page_num in range(len(doc)):
+                page = doc.load_page(page_num)
+                text += page.get_text()
+
+            # Create a document with the extracted text
+            document = Document(content=text, metadata={"source": data})
+            return [document]
+
+        except Exception as e:
+            print(f"An error occurred while parsing the PDF: {e}")
+            return []

swarmauri_parser_fitzpdf-0.6.0.dev154/swarmauri_parser_fitzpdf/__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
+
+"""
+
+