Rename file_converters to converters (#6390)

docs/pydoc/config-preview/file_converter.yml → docs/pydoc/config-preview/converter.yml

@@ -1,6 +1,6 @@
 loaders:
   - type: loaders.CustomPythonLoader
-    search_path: [../../../haystack/preview/components/file_converters]
+    search_path: [../../../haystack/preview/components/converters]
     modules: ["azure", "html", "markdown", "pypdf", "tika", "txt"]
     ignore_when_discovered: ["__init__"]
 processors:
@@ -15,12 +15,12 @@ renderer:
   type: renderers.ReadmePreviewRenderer
   excerpt: Extracts text from files in different formats and converts it into the unified Document format.
   category_slug: haystack-classes
-  title: File Converter API
-  slug: file-converter-api
+  title: Converter API
+  slug: converter-api
   order: 50
   markdown:
     descriptive_class_title: false
     descriptive_module_title: true
     add_method_class_prefix: true
     add_member_class_prefix: false
-    filename: file_converter_api.md
+    filename: converter_api.md

e2e/preview/pipelines/test_preprocessing_pipeline.py

@@ -2,7 +2,7 @@
 
 from haystack.preview import Pipeline
 from haystack.preview.components.embedders import SentenceTransformersDocumentEmbedder
-from haystack.preview.components.file_converters import TextFileToDocument
+from haystack.preview.components.converters import TextFileToDocument
 from haystack.preview.components.preprocessors import DocumentSplitter, DocumentCleaner
 from haystack.preview.components.classifiers import DocumentLanguageClassifier
 from haystack.preview.components.routers import FileTypeRouter, MetadataRouter

haystack/preview/components/converters/__init__.py

@@ -0,0 +1,15 @@
+from haystack.preview.components.converters.txt import TextFileToDocument
+from haystack.preview.components.converters.tika import TikaDocumentConverter
+from haystack.preview.components.converters.azure import AzureOCRDocumentConverter
+from haystack.preview.components.converters.pypdf import PyPDFToDocument
+from haystack.preview.components.converters.html import HTMLToDocument
+from haystack.preview.components.converters.markdown import MarkdownToDocument
+
+__all__ = [
+    "TextFileToDocument",
+    "TikaDocumentConverter",
+    "AzureOCRDocumentConverter",
+    "PyPDFToDocument",
+    "HTMLToDocument",
+    "MarkdownToDocument",
+]

haystack/preview/components/file_converters/html.py → haystack/preview/components/converters/html.py

@@ -19,7 +19,7 @@ class HTMLToDocument:
 
     Usage example:
     ```python
-    from haystack.preview.components.file_converters.html import HTMLToDocument
+    from haystack.preview.components.converters.html import HTMLToDocument
 
     converter = HTMLToDocument()
     results = converter.run(sources=["sample.html"])

haystack/preview/components/file_converters/markdown.py → haystack/preview/components/converters/markdown.py

@@ -23,7 +23,7 @@ class MarkdownToDocument:
 
     Usage example:
     ```python
-    from haystack.preview.components.file_converters.markdown import MarkdownToDocument
+    from haystack.preview.components.converters.markdown import MarkdownToDocument
 
     converter = MarkdownToDocument()
     results = converter.run(sources=["sample.md"])

test/preview/components/file_converters/test_azure_ocr_doc_converter.py → test/preview/components/converters/test_azure_ocr_doc_converter.py

@@ -3,7 +3,7 @@
 
 import pytest
 
-from haystack.preview.components.file_converters.azure import AzureOCRDocumentConverter
+from haystack.preview.components.converters.azure import AzureOCRDocumentConverter
 
 
 class TestAzureOCRDocumentConverter:
@@ -18,13 +18,13 @@ def test_to_dict(self):
         component = AzureOCRDocumentConverter(endpoint="test_endpoint", api_key="test_credential_key")
         data = component.to_dict()
         assert data == {
-            "type": "haystack.preview.components.file_converters.azure.AzureOCRDocumentConverter",
+            "type": "haystack.preview.components.converters.azure.AzureOCRDocumentConverter",
             "init_parameters": {"endpoint": "test_endpoint", "model_id": "prebuilt-read"},
         }
 
     @pytest.mark.unit
     def test_run(self, preview_samples_path):
-        with patch("haystack.preview.components.file_converters.azure.DocumentAnalysisClient") as mock_azure_client:
+        with patch("haystack.preview.components.converters.azure.DocumentAnalysisClient") as mock_azure_client:
             mock_result = Mock(pages=[Mock(lines=[Mock(content="mocked line 1"), Mock(content="mocked line 2")])])
             mock_result.to_dict.return_value = {
                 "api_version": "2023-02-28-preview",

test/preview/components/file_converters/test_html_to_document.py → test/preview/components/converters/test_html_to_document.py

@@ -2,7 +2,7 @@
 
 import pytest
 
-from haystack.preview.components.file_converters import HTMLToDocument
+from haystack.preview.components.converters import HTMLToDocument
 from haystack.preview.dataclasses import ByteStream
 
 

test/preview/components/file_converters/test_markdown_to_document.py → test/preview/components/converters/test_markdown_to_document.py

@@ -2,7 +2,7 @@
 
 import pytest
 
-from haystack.preview.components.file_converters.markdown import MarkdownToDocument
+from haystack.preview.components.converters.markdown import MarkdownToDocument
 from haystack.preview.dataclasses import ByteStream
 
 

test/preview/components/file_converters/test_pypdf_to_document.py → test/preview/components/converters/test_pypdf_to_document.py

@@ -3,7 +3,7 @@
 from pypdf import PdfReader
 
 from haystack.preview import Document
-from haystack.preview.components.file_converters.pypdf import PyPDFToDocument
+from haystack.preview.components.converters.pypdf import PyPDFToDocument
 from haystack.preview.dataclasses import ByteStream
 
 

test/preview/components/file_converters/test_textfile_to_document.py → test/preview/components/converters/test_textfile_to_document.py

@@ -5,7 +5,7 @@
 import pytest
 
 from haystack.preview.dataclasses import ByteStream
-from haystack.preview.components.file_converters.txt import TextFileToDocument
+from haystack.preview.components.converters.txt import TextFileToDocument
 
 
 class TestTextfileToDocument:

test/preview/components/file_converters/test_tika_doc_converter.py → test/preview/components/converters/test_tika_doc_converter.py

@@ -2,14 +2,14 @@
 
 import pytest
 
-from haystack.preview.components.file_converters.tika import TikaDocumentConverter
+from haystack.preview.components.converters.tika import TikaDocumentConverter
 
 
 class TestTikaDocumentConverter:
     @pytest.mark.unit
     def test_run(self):
         component = TikaDocumentConverter()
-        with patch("haystack.preview.components.file_converters.tika.tika_parser.from_file") as mock_tika_parser:
+        with patch("haystack.preview.components.converters.tika.tika_parser.from_file") as mock_tika_parser:
             mock_tika_parser.return_value = {"content": "Content of mock_file.pdf"}
             documents = component.run(paths=["mock_file.pdf"])["documents"]
 
@@ -19,7 +19,7 @@ def test_run(self):
     @pytest.mark.unit
     def test_run_logs_warning_if_content_empty(self, caplog):
         component = TikaDocumentConverter()
-        with patch("haystack.preview.components.file_converters.tika.tika_parser.from_file") as mock_tika_parser:
+        with patch("haystack.preview.components.converters.tika.tika_parser.from_file") as mock_tika_parser:
             mock_tika_parser.return_value = {"content": ""}
             with caplog.at_level("WARNING"):
                 component.run(paths=["mock_file.pdf"])
@@ -28,7 +28,7 @@ def test_run_logs_warning_if_content_empty(self, caplog):
     @pytest.mark.unit
     def test_run_logs_error(self, caplog):
         component = TikaDocumentConverter()
-        with patch("haystack.preview.components.file_converters.tika.tika_parser.from_file") as mock_tika_parser:
+        with patch("haystack.preview.components.converters.tika.tika_parser.from_file") as mock_tika_parser:
             mock_tika_parser.side_effect = Exception("Some error")
             with caplog.at_level("ERROR"):
                 component.run(paths=["mock_file.pdf"])