Refactor code structure for improved readability and maintainability

docs/api.md

@@ -281,7 +281,7 @@ from textxtract.core.utils import FileInfo
 | `.docx` | `DOCXHandler` | `python-docx` |
 | `.doc` | `DOCHandler` | `antiword` |
 | `.md` | `MDHandler` | `markdown`, `beautifulsoup4` |
-| `.rtf` | `RTFHandler` | `pyrtf-ng` |
+| `.rtf` | `RTFHandler` | `striprtf` |
 | `.html`, `.htm` | `HTMLHandler` | `beautifulsoup4`, `lxml` |
 | `.csv` | `CSVHandler` | None |
 | `.json` | `JSONHandler` | None |

docs/index.md

@@ -71,7 +71,7 @@ text = asyncio.run(extract_text())
 | PDF | `.pdf` | `pip install textxtract[pdf]` | PyMuPDF |
 | Word | `.docx` | `pip install textxtract[docx]` | python-docx |
 | Word Legacy | `.doc` | `pip install textxtract[doc]` | antiword |
-| Rich Text | `.rtf` | `pip install textxtract[rtf]` | pyrtf-ng |
+| Rich Text | `.rtf` | `pip install textxtract[rtf]` | striprtf |
 | HTML | `.html`, `.htm` | `pip install textxtract[html]` | beautifulsoup4 |
 | CSV | `.csv` | Built-in | stdlib |
 | JSON | `.json` | Built-in | stdlib |

docs/installation.md

@@ -63,15 +63,15 @@ pip install textxtract[all]
 | `docx` | `python-docx` | `.docx` |
 | `doc` | `antiword` | `.doc` |
 | `md` | `markdown`, `beautifulsoup4` | `.md` |
-| `rtf` | `pyrtf-ng` | `.rtf` |
+| `rtf` | `striprtf` | `.rtf` |
 | `html` | `beautifulsoup4`, `lxml` | `.html`, `.htm` |
 | `xml` | `lxml` | `.xml` |
 | `all` | All of the above | All supported types |
 
 ## 🐍 Python Version Requirements
 
 - **Python 3.9 or higher** is required
-- Tested on Python 3.9, 3.10, 3.11, and 3.12
+- Tested on Python 3.9, 3.10, 3.11, 3.12, and 3.13
 
 ## 🔄 Upgrading
 

docs/usage.md

@@ -87,7 +87,7 @@ text = await extractor.extract(file_bytes, "document.pdf")
 | .doc      | [doc]                | antiword        |
 | .txt      |                      | stdlib          |
 | .md       | [md]                 | markdown        |
-| .rtf      | [rtf]                | pyrtf-ng        |
+| .rtf      | [rtf]                | striprtf        |
 | .html/.htm| [html]               | beautifulsoup4  |
 | .csv      |                      | stdlib          |
 | .json     |                      | stdlib          |

pyproject.toml

@@ -24,15 +24,15 @@ pdf = ["pymupdf"]
 docx = ["python-docx"]
 doc = ["antiword"]
 md = ["markdown"]
-rtf = ["pyrtf-ng"]
+rtf = ["striprtf"]
 html = ["beautifulsoup4", "lxml"]
 xml = ["lxml"]
 all = [
     "pymupdf",
     "python-docx",
     "antiword",
     "markdown",
-    "pyrtf-ng",
+    "striprtf",
     "beautifulsoup4",
     "lxml"
 ]

textxtract/core/registry.py

@@ -3,7 +3,6 @@
 import logging
 from typing import Dict, Type, Optional, List
 from functools import lru_cache
-from pathlib import Path
 
 from textxtract.core.base import FileTypeHandler
 from textxtract.core.exceptions import FileTypeNotSupportedError
@@ -73,7 +72,7 @@ def _load_default_handlers(self):
 
             self._handlers[".rtf"] = RTFHandler
         except ImportError:
-            logger.debug("RTF handler not available - pyrtf-ng not installed")
+            logger.debug("RTF handler not available - striprtf not installed")
 
         try:
             from textxtract.handlers.html import HTMLHandler

textxtract/handlers/doc.py

@@ -42,10 +42,21 @@ def _extract_with_antiword(self, file_path: Path) -> str:
             raise ExtractionError("antiword extraction timed out")
         except subprocess.CalledProcessError as e:
             error_msg = e.stderr.decode() if e.stderr else str(e)
+            # Check if the error is due to missing libreoffice dependency
+            if (
+                "libreoffice" in error_msg.lower()
+                or "no such file or directory" in error_msg.lower()
+            ):
+                # Trigger fallback by raising FileNotFoundError
+                raise FileNotFoundError(
+                    "antiword requires libreoffice which is not available"
+                )
             raise ExtractionError(f"antiword extraction failed: {error_msg}")
 
     def _extract_with_fallback(
-        self, file_path: Path, config: Optional[dict] = None
+        self,
+        file_path: Path,
+        config: Optional[dict] = None,
     ) -> str:
         """Fallback extraction methods when antiword is not available."""