pdfmuse-haystack 0.1.0__tar.gz

pdfmuse_haystack-0.1.0/.gitignore

@@ -0,0 +1,43 @@
+# Rust
+/target/
+**/*.rs.bk
+
+# Node
+node_modules/
+dist/
+pkg/
+crates/pdfmuse-wasm/pkg/
+*.node
+*.tsbuildinfo
+# generated by napi/tsc in the node binding
+bindings/node/index.js
+bindings/node/index.d.ts
+bindings/node/native.js
+bindings/node/native.d.ts
+
+# Python
+__pycache__/
+*.py[cod]
+.venv/
+venv/
+*.egg-info/
+build/
+*.whl
+.pytest_cache/
+
+# Native artifacts
+*.so
+*.dylib
+*.pyd
+
+# OS / editor
+.DS_Store
+*.swp
+.idea/
+.vscode/
+
+# Note: Cargo.lock IS committed (this workspace ships a binary, pdfmuse-cli).
+
+bindings/node/package-lock.json
+bindings/node/npm/
+bindings/node/artifacts/

pdfmuse_haystack-0.1.0/PKG-INFO

@@ -0,0 +1,53 @@
+Metadata-Version: 2.4
+Name: pdfmuse-haystack
+Version: 0.1.0
+Summary: Haystack converter for pdfmuse — deterministic PDF/DOCX parsing for RAG.
+Project-URL: Homepage, https://github.com/casperkwok/pdfmuse
+Project-URL: Repository, https://github.com/casperkwok/pdfmuse
+Author: Casper Kwok
+License-Expression: MIT OR Apache-2.0
+Keywords: converter,docx,haystack,llm,parser,pdf,pdfmuse,rag
+Requires-Python: >=3.9
+Requires-Dist: haystack-ai>=2.0
+Requires-Dist: pdfmuse>=0.1.6
+Description-Content-Type: text/markdown
+
+# pdfmuse-haystack
+
+[Haystack](https://haystack.deepset.ai) converter for [**pdfmuse**](https://github.com/casperkwok/pdfmuse) —
+a **deterministic** PDF/DOCX parser for RAG. Same file in → same Document out.
+
+```bash
+pip install pdfmuse-haystack
+```
+
+## Usage
+
+```python
+from pdfmuse_haystack import PdfmuseConverter
+
+converter = PdfmuseConverter(mode="markdown")   # or "text" (default)
+docs = converter.run(sources=["report.pdf"])["documents"]
+```
+
+In a pipeline:
+
+```python
+from haystack import Pipeline
+from pdfmuse_haystack import PdfmuseConverter
+
+pipe = Pipeline()
+pipe.add_component("converter", PdfmuseConverter(mode="text"))
+# ... connect to a splitter / embedder / writer ...
+```
+
+## Modes
+
+- `"text"` *(default)* — plain reading-order text (fast path).
+- `"markdown"` — structured Markdown (headings + tables).
+
+Extracts text with exact coordinates, tables and structure; no probabilistic models
+in the core path, so your index is reproducible run-to-run. Scanned/image-only pages
+surface a `NeedsOcr` warning (OCR is a pluggable backend, kept out of the core).
+
+MIT OR Apache-2.0 · part of the [pdfmuse](https://github.com/casperkwok/pdfmuse) project.

pdfmuse_haystack-0.1.0/README.md

@@ -0,0 +1,39 @@
+# pdfmuse-haystack
+
+[Haystack](https://haystack.deepset.ai) converter for [**pdfmuse**](https://github.com/casperkwok/pdfmuse) —
+a **deterministic** PDF/DOCX parser for RAG. Same file in → same Document out.
+
+```bash
+pip install pdfmuse-haystack
+```
+
+## Usage
+
+```python
+from pdfmuse_haystack import PdfmuseConverter
+
+converter = PdfmuseConverter(mode="markdown")   # or "text" (default)
+docs = converter.run(sources=["report.pdf"])["documents"]
+```
+
+In a pipeline:
+
+```python
+from haystack import Pipeline
+from pdfmuse_haystack import PdfmuseConverter
+
+pipe = Pipeline()
+pipe.add_component("converter", PdfmuseConverter(mode="text"))
+# ... connect to a splitter / embedder / writer ...
+```
+
+## Modes
+
+- `"text"` *(default)* — plain reading-order text (fast path).
+- `"markdown"` — structured Markdown (headings + tables).
+
+Extracts text with exact coordinates, tables and structure; no probabilistic models
+in the core path, so your index is reproducible run-to-run. Scanned/image-only pages
+surface a `NeedsOcr` warning (OCR is a pluggable backend, kept out of the core).
+
+MIT OR Apache-2.0 · part of the [pdfmuse](https://github.com/casperkwok/pdfmuse) project.

pdfmuse_haystack-0.1.0/pdfmuse_haystack/__init__.py

@@ -0,0 +1,72 @@
+"""Haystack converter for **pdfmuse** — a deterministic PDF/DOCX parser.
+
+    from pdfmuse_haystack import PdfmuseConverter
+
+    converter = PdfmuseConverter(mode="markdown")
+    docs = converter.run(sources=["report.pdf"])["documents"]
+
+Deterministic: the same file always yields the same Document, so your index is
+reproducible run-to-run. Scanned/image-only pages surface a NeedsOcr warning.
+"""
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Union
+
+from haystack import Document, component, default_from_dict, default_to_dict
+from haystack.components.converters.utils import get_bytestream_from_source, normalize_metadata
+from haystack.dataclasses import ByteStream
+
+__all__ = ["PdfmuseConverter"]
+__version__ = "0.1.0"
+
+
+def _to_str(data: bytes, mode: str) -> str:
+    import pdfmuse
+
+    if mode == "markdown":
+        return pdfmuse.to_markdown(data)
+    return pdfmuse.to_text(data)
+
+
+@component
+class PdfmuseConverter:
+    """Convert PDF/DOCX files to Haystack ``Document``s via pdfmuse.
+
+    Args:
+        mode: ``"text"`` (plain reading-order text, default) or ``"markdown"``
+            (headings + tables).
+    """
+
+    def __init__(self, mode: str = "text") -> None:
+        if mode not in ("text", "markdown"):
+            raise ValueError("mode must be 'text' or 'markdown'")
+        self.mode = mode
+
+    def to_dict(self) -> Dict[str, Any]:
+        return default_to_dict(self, mode=self.mode)
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "PdfmuseConverter":
+        return default_from_dict(cls, data)
+
+    @component.output_types(documents=List[Document])
+    def run(
+        self,
+        sources: List[Union[str, Path, ByteStream]],
+        meta: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None,
+    ):
+        documents: List[Document] = []
+        meta_list = normalize_metadata(meta, sources_count=len(sources))
+        for source, md in zip(sources, meta_list):
+            try:
+                bytestream = get_bytestream_from_source(source)
+            except Exception:
+                continue
+            try:
+                content = _to_str(bytestream.data, self.mode)
+            except Exception:
+                continue
+            merged = {**bytestream.meta, **md}
+            documents.append(Document(content=content, meta=merged))
+        return {"documents": documents}

pdfmuse_haystack-0.1.0/pyproject.toml

@@ -0,0 +1,24 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "pdfmuse-haystack"
+version = "0.1.0"
+description = "Haystack converter for pdfmuse — deterministic PDF/DOCX parsing for RAG."
+readme = "README.md"
+requires-python = ">=3.9"
+license = "MIT OR Apache-2.0"
+authors = [{ name = "Casper Kwok" }]
+keywords = ["haystack", "pdf", "docx", "rag", "llm", "parser", "pdfmuse", "converter"]
+dependencies = [
+    "pdfmuse>=0.1.6",
+    "haystack-ai>=2.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/casperkwok/pdfmuse"
+Repository = "https://github.com/casperkwok/pdfmuse"
+
+[tool.hatch.build.targets.wheel]
+packages = ["pdfmuse_haystack"]