add DOCXProcessor for docx-Files

configs/config.yml

@@ -12,7 +12,7 @@ strategies:
     # file_selection_pattern: a regex pattern selecting the files to be processed
     file_name_pattern: 'regex_pattern_identifying_your_file in /path/to/your_directory'
     # file_format
-    # currently only 'pdf' and 'txt' are supported
+    # currently only 'pdf', 'docx', and 'txt' are supported
     file_format: 'pdf'
     # terms
     terms:

pyproject.toml

@@ -32,6 +32,8 @@ classifiers = [
 dependencies = [
   "pandas>=2.2.0",
   "pydantic>=2.6.1",
+  "python-docx>=1.1.0",
+  "python-pptx>=0.6.23",
   "pyyaml>=6.0.1",
   "pdfminer.six>=20231228",
   "sqlalchemy>=2.0.27",

src/rosinenpicker/processors.py

@@ -1,4 +1,5 @@
 from pdfminer.high_level import extract_text
+from docx import Document
 import re
 from .patterns import Pattern
 
@@ -102,7 +103,15 @@ class TXTProcessor(DocumentProcessor):
     def extract_text(self, file_path):
         with open(file_path, "r") as doc:
             self.text = doc.read()
-
+
+class DOCXProcessor(DocumentProcessor):
+    def extract_text(self, file_path):
+        d = Document(file_path)
+        txt = ''
+        for p in d.paragraphs:
+            txt = txt + '\n' + p.text
+        self.text = txt
+
 
 # Placeholder for future extensions
 # class MarkdownProcessor(DocumentProcessor):

src/rosinenpicker/pydantic_models.py

@@ -46,7 +46,7 @@ def validate_export_format(cls, ef: str):
     @field_validator('file_format')
     @classmethod
     def validate_file_format(cls, ff: str):
-        valid_formats = {"txt", "pdf"}
+        valid_formats = {"txt", "pdf", "docx"}
         if ff not in valid_formats:
             raise ConfigError(msg=f"Concerning '{ff}': File format must conform to one of these options: {valid_formats}!")
         return ff

src/rosinenpicker/start.py

@@ -9,14 +9,14 @@
 from .database import Base, DbRun, DbStrategy, DbProcessedFile, DbMatch
 from .utils import file_sha256
 from .exporter import BaseExporter, CSVExporter, XLSXExporter, HTMLExporter, JSONExporter
-from .processors import DocumentProcessor, PDFProcessor, TXTProcessor
+from .processors import DocumentProcessor, PDFProcessor, TXTProcessor, DOCXProcessor
 from sqlalchemy import create_engine, select
 from sqlalchemy.orm import sessionmaker, Session
 import argparse
 
 # File format
 # processor and exporter options according to file_format and export_format
-file_format_options = {"pdf": PDFProcessor, "txt": TXTProcessor}
+file_format_options = {"pdf": PDFProcessor, "txt": TXTProcessor, "docx": DOCXProcessor}
 export_format_options = {"csv": CSVExporter, "xlsx": XLSXExporter, "html": HTMLExporter, "json": JSONExporter}
 
 def read_config_file(config_file: str) -> Config: