# Release anyparser-core@1.0.2

README.md

@@ -106,7 +106,7 @@ import os
 import asyncio
 import sys
 
-from anyparser_core import Anyparser, AnyparserOption, OcrLanguage, OCRPreset
+from anyparser_core import Anyparser, AnyparserOption, OcrLanguage, OcrPreset
 
 single_file = "docs/document.png"
 
@@ -116,7 +116,7 @@ options = AnyparserOption(
     model="ocr",
     format="markdown",
     ocr_language=[OcrLanguage.JAPANESE],
-    ocr_preset=OCRPreset.SCAN,
+    ocr_preset=OcrPreset.SCAN,
 )
 
 parser = Anyparser(options)
@@ -226,7 +226,7 @@ The `Anyparser` class utilizes the `AnyparserOption` dataclass for flexible conf
 from dataclasses import dataclass
 from typing import List, Literal, Optional, Union
 
-from anyparser_core import OcrLanguage, OCRPreset
+from anyparser_core import OcrLanguage, OcrPreset
 
 @dataclass
 class AnyparserOption:
@@ -255,7 +255,7 @@ class AnyparserOption:
 
     # OCR Configuration
     ocr_language: Optional[List[OcrLanguage]] = None  # Languages for OCR processing
-    ocr_preset: Optional[OCRPreset] = None  # Preset configuration for OCR
+    ocr_preset: Optional[OcrPreset] = None  # Preset configuration for OCR
 
     # Crawler Configuration
     max_depth: Optional[int] = None  # Maximum crawl depth
@@ -278,7 +278,7 @@ class AnyparserOption:
 | `files` | `Optional[Union[str, List[str]]]` | `None` | Input files to process |
 | `url` | `Optional[str]` | `None` | URL for crawler model |
 | `ocr_language` | `Optional[List[OcrLanguage]]` | `None` | Languages for OCR processing |
-| `ocr_preset` | `Optional[OCRPreset]` | `None` | Preset configuration for OCR |
+| `ocr_preset` | `Optional[OcrPreset]` | `None` | Preset configuration for OCR |
 | `max_depth` | `Optional[int]` | `None` | Maximum crawl depth for crawler model |
 | `max_executions` | `Optional[int]` | `None` | Maximum number of pages to crawl |
 | `strategy` | `Optional[str]` | `None` | Crawling strategy: `"LIFO"` or `"FIFO"` |
@@ -288,19 +288,19 @@ class AnyparserOption:
 
 The following OCR presets are available for optimized document processing:
 
-- `OCRPreset.DOCUMENT` - General document processing
-- `OCRPreset.HANDWRITING` - Handwritten text recognition
-- `OCRPreset.SCAN` - Scanned document processing
-- `OCRPreset.RECEIPT` - Receipt processing
-- `OCRPreset.MAGAZINE` - Magazine/article processing
-- `OCRPreset.INVOICE` - Invoice processing
-- `OCRPreset.BUSINESS_CARD` - Business card processing
-- `OCRPreset.PASSPORT` - Passport document processing
-- `OCRPreset.DRIVER_LICENSE` - Driver's license processing
-- `OCRPreset.IDENTITY_CARD` - ID card processing
-- `OCRPreset.LICENSE_PLATE` - License plate recognition
-- `OCRPreset.MEDICAL_REPORT` - Medical document processing
-- `OCRPreset.BANK_STATEMENT` - Bank statement processing
+- `OcrPreset.DOCUMENT` - General document processing
+- `OcrPreset.HANDWRITING` - Handwritten text recognition
+- `OcrPreset.SCAN` - Scanned document processing
+- `OcrPreset.RECEIPT` - Receipt processing
+- `OcrPreset.MAGAZINE` - Magazine/article processing
+- `OcrPreset.INVOICE` - Invoice processing
+- `OcrPreset.BUSINESS_CARD` - Business card processing
+- `OcrPreset.PASSPORT` - Passport document processing
+- `OcrPreset.DRIVER_LICENSE` - Driver's license processing
+- `OcrPreset.IDENTITY_CARD` - ID card processing
+- `OcrPreset.LICENSE_PLATE` - License plate recognition
+- `OcrPreset.MEDICAL_REPORT` - Medical document processing
+- `OcrPreset.BANK_STATEMENT` - Bank statement processing
 
 **Model Types for AI Data Pipelines:**
 

anyparser_core/__init__.py

@@ -1,4 +1,4 @@
-from .config.hardcoded import OcrLanguage, OCRPreset
+from .config.hardcoded import OcrLanguage, OcrPreset
 from .form import build_form
 from .options import AnyparserOption, AnyparserParsedOption, UploadedFile
 from .parser import (
@@ -15,8 +15,8 @@
     AnyparserUrl,
 )
 from .validator import validate_and_parse, validate_option, validate_path
+from .version import __version__
 
-__version__ = "1.0.1"
 __all__ = [
     "Anyparser",
     "AnyparserCrawlDirective",
@@ -35,6 +35,6 @@
     "validate_option",
     "build_form",
     "Anyparser",
-    "OCRPreset",
+    "OcrPreset",
     "OcrLanguage",
 ]

anyparser_core/config/hardcoded.py

@@ -21,7 +21,7 @@
 ]
 
 
-class OCRPreset(Enum):
+class OcrPreset(Enum):
     """Enumeration of supported OCR presets for document processing."""
 
     DOCUMENT = "document"

anyparser_core/form.py

@@ -54,18 +54,18 @@ def add_field(name: str, value: Any) -> None:
     if parsed.model == "ocr":
         if parsed.ocr_language:
             add_field(
-                "ocrLanguage", ",".join([lang.value for lang in parsed.ocr_language])
+                "ocr_language", ",".join([lang.value for lang in parsed.ocr_language])
             )
 
         if parsed.ocr_preset:
-            add_field("ocrPreset", parsed.ocr_preset.value)
+            add_field("ocr_preset", parsed.ocr_preset.value)
 
     if parsed.model == "crawler":
         add_field("url", parsed.url)
-        add_field("maxDepth", parsed.max_depth)
-        add_field("maxExecutions", parsed.max_executions)
+        add_field("max_depth", parsed.max_depth)
+        add_field("max_executions", parsed.max_executions)
         add_field("strategy", parsed.strategy)
-        add_field("traversalScope", parsed.traversal_scope)
+        add_field("traversal_scope", parsed.traversal_scope)
     else:
         # Add files to the form
         for file in parsed.files:

anyparser_core/options.py

@@ -5,7 +5,7 @@
 from dataclasses import dataclass, field
 from typing import List, Literal, Optional, TypedDict, Union
 
-from anyparser_core.config.hardcoded import OcrLanguage, OCRPreset
+from anyparser_core.config.hardcoded import OcrLanguage, OcrPreset
 
 # Type aliases for better readability
 AnyparserFormatType = Literal["json", "markdown", "html"]
@@ -26,7 +26,7 @@ class AnyparserOption:
     table: Optional[bool] = None
     files: Optional[Union[str, List[str]]] = None
     ocr_language: Optional[List[OcrLanguage]] = None
-    ocr_preset: Optional[OCRPreset] = None
+    ocr_preset: Optional[OcrPreset] = None
     url: Optional[str] = None
     max_depth: Optional[int] = None
     max_executions: Optional[int] = None
@@ -54,7 +54,7 @@ class AnyparserParsedOption:
     image: Optional[bool] = None
     table: Optional[bool] = None
     ocr_language: Optional[List[OcrLanguage]] = None
-    ocr_preset: Optional[OCRPreset] = None
+    ocr_preset: Optional[OcrPreset] = None
     url: Optional[str] = None
     max_depth: Optional[int] = None
     max_executions: Optional[int] = None
@@ -72,7 +72,7 @@ class DefaultOptions(TypedDict):
     image: Optional[bool]
     table: Optional[bool]
     ocr_language: Optional[List[OcrLanguage]]
-    ocr_preset: Optional[OCRPreset]
+    ocr_preset: Optional[OcrPreset]
     url: Optional[str]
     max_depth: Optional[int]
     max_executions: Optional[int]

anyparser_core/parser.py

@@ -10,6 +10,7 @@
 from .options import AnyparserOption
 from .request import async_request
 from .validator import validate_and_parse
+from .version import __version__
 
 
 @dataclass
@@ -81,6 +82,7 @@ class AnyparserUrl:
     images: List[AnyparserImageReference] = field(default_factory=list)
     text: Optional[str] = field(default=None)
 
+
 @dataclass
 class AnyparserPdfPage:
     """Represents a parsed PDF page with extracted content."""
@@ -152,7 +154,8 @@ async def parse(
 
         # Set up the headers, using the same boundary
         headers: Dict[str, str] = {
-            "Content-Type": f"multipart/form-data; boundary={boundary}"
+            "Content-Type": f"multipart/form-data; boundary={boundary}",
+            "User-Agent": f"anyparser_core@{__version__}",
         }
 
         if parsed.api_key:

anyparser_core/validator/path.py

@@ -17,10 +17,7 @@ async def validate_path(file_paths: Union[str, List[str]]) -> PathValidationResu
     Validates file paths exist and are accessible
     """
     if not file_paths or (isinstance(file_paths, str) and not file_paths.strip()):
-        return InvalidPathValidationResult(
-            error=FileNotFoundError("No files provided")
-        )
-
+        return InvalidPathValidationResult(error=FileNotFoundError("No files provided"))
 
     if isinstance(file_paths, (str, Path)):
         files = [file_paths]

anyparser_core/version.py

@@ -0,0 +1 @@
+__version__ = "1.0.2"

changelogs/v1.0.2-changelog.md

@@ -0,0 +1,26 @@
+# Release anyparser-core@1.0.2
+
+## Changes
+
+**User Agent**
+
+- Added a User-Agent header.
+- Moved the version literal `__version__` to a separate file to prevent circular referencing.
+
+**Rename "OCRPreset" to "OcrPreset"**
+
+This pull request refactors the OCRPreset class to OcrPreset across the codebase for consistency in naming conventions.
+
+- Renamed OCRPreset to `OcrPreset` in files like `README.md`, `anyparser_core/__init__.py`, and examples.
+- Updated variable names and documentation to reflect the new class name.
+- Modified test files to use the updated class.
+
+This change is purely a refactor with no functional impact, aiming for consistency and improved readability.
+
+## Breaking Changes
+
+The class `OCRPreset` has been renamed to `OcrPreset` to maintain consistency in naming conventions.
+
+## Migration Guide
+
+Search and replace all instances of `OCRPreset` with `OcrPreset` in your codebase.

examples/03_one_liner.py

@@ -4,17 +4,8 @@
 
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
 
-from anyparser_core import Anyparser
-
-multiple_files = ["docs/sample.docx", "docs/sample.pdf"]
+# ------------------------------------------------------------------------------
 
-result = asyncio.run(Anyparser().parse(multiple_files))
-
-for item in result:
-    print("-" * 100)
-    print("File:", item.original_filename)
-    print("Checksum:", item.checksum)
-    print("Total characters:", item.total_characters)
-    print("Markdown:", item.markdown)
+from anyparser_core import Anyparser
 
-print("-" * 100)
+print(asyncio.run(Anyparser().parse(["docs/sample.docx", "docs/sample.pdf"])))

examples/04_ocr.py

@@ -4,7 +4,7 @@
 
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
 
-from anyparser_core import Anyparser, AnyparserOption, OcrLanguage, OCRPreset
+from anyparser_core import Anyparser, AnyparserOption, OcrLanguage, OcrPreset
 
 single_file = "docs/document.png"
 
@@ -14,7 +14,7 @@
     model="ocr",
     format="markdown",
     ocr_language=[OcrLanguage.JAPANESE],
-    ocr_preset=OCRPreset.SCAN,
+    ocr_preset=OcrPreset.SCAN,
 )
 
 parser = Anyparser(options)

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [project]
 name = "anyparser-core"
-version = "1.0.1"
+version = "1.0.2"
 description = "Anyparser SDK for Python"
 readme = "README.md"
 requires-python = ">=3.9"

tests/test_form.py

@@ -5,7 +5,7 @@
 
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
 
-from anyparser_core import OcrLanguage, OCRPreset
+from anyparser_core import OcrLanguage, OcrPreset
 from anyparser_core.form import build_form
 from anyparser_core.options import AnyparserParsedOption, UploadedFile
 
@@ -55,15 +55,15 @@ def test_build_form_with_ocr_options(basic_parsed_option):
     """Test form building with OCR options"""
     basic_parsed_option.model = "ocr"
     basic_parsed_option.ocr_language = [OcrLanguage.ENGLISH, OcrLanguage.SPANISH]
-    basic_parsed_option.ocr_preset = OCRPreset.DOCUMENT
+    basic_parsed_option.ocr_preset = OcrPreset.DOCUMENT
 
     boundary = "boundary123"
     form_data = build_form(basic_parsed_option, boundary)
     form_str = form_data.decode("utf-8")
 
-    assert 'Content-Disposition: form-data; name="ocrLanguage"' in form_str
+    assert 'Content-Disposition: form-data; name="ocr_language"' in form_str
     assert "eng,spa" in form_str
-    assert 'Content-Disposition: form-data; name="ocrPreset"' in form_str
+    assert 'Content-Disposition: form-data; name="ocr_preset"' in form_str
     assert "document" in form_str
 
 
@@ -132,12 +132,12 @@ def test_build_form_ocr():
         format="json",
         model="ocr",
         ocr_language=[OcrLanguage.JAPANESE],
-        ocr_preset=OCRPreset.SCAN,
+        ocr_preset=OcrPreset.SCAN,
         files=[],
     )
     form_data = build_form(option, "boundary")
-    assert b'name="ocrLanguage"' in form_data
-    assert b'name="ocrPreset"' in form_data
+    assert b'name="ocr_language"' in form_data
+    assert b'name="ocr_preset"' in form_data
 
 
 def test_build_form_crawler():
@@ -155,10 +155,10 @@ def test_build_form_crawler():
     )
     form_data = build_form(option, "boundary")
     assert b'name="url"' in form_data
-    assert b'name="maxDepth"' in form_data
-    assert b'name="maxExecutions"' in form_data
+    assert b'name="max_depth"' in form_data
+    assert b'name="max_executions"' in form_data
     assert b'name="strategy"' in form_data
-    assert b'name="traversalScope"' in form_data
+    assert b'name="traversal_scope"' in form_data
 
 
 def test_build_form_with_files(tmp_path):

tests/test_options.py

@@ -5,7 +5,7 @@
 
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
 
-from anyparser_core.config.hardcoded import OcrLanguage, OCRPreset
+from anyparser_core.config.hardcoded import OcrLanguage, OcrPreset
 from anyparser_core.options import (
     AnyparserOption,
     AnyparserParsedOption,
@@ -61,7 +61,7 @@ def test_build_options_with_custom_options(mock_api_key, monkeypatch):
         image=False,
         table=False,
         ocr_language=[OcrLanguage.ENGLISH],
-        ocr_preset=OCRPreset.DOCUMENT,
+        ocr_preset=OcrPreset.DOCUMENT,
     )
 
     options = build_options(custom_options)
@@ -72,7 +72,7 @@ def test_build_options_with_custom_options(mock_api_key, monkeypatch):
     assert options["image"] is False
     assert options["table"] is False
     assert options["ocr_language"] == [OcrLanguage.ENGLISH]
-    assert options["ocr_preset"] == OCRPreset.DOCUMENT
+    assert options["ocr_preset"] == OcrPreset.DOCUMENT
 
 
 def test_anyparser_parsed_file():
@@ -94,7 +94,7 @@ def test_anyparser_parsed_option():
         image=False,
         table=True,
         ocr_language=[OcrLanguage.ENGLISH],
-        ocr_preset=OCRPreset.HANDWRITING,
+        ocr_preset=OcrPreset.HANDWRITING,
     )
 
     assert len(parsed_option.files) == 1
@@ -105,7 +105,7 @@ def test_anyparser_parsed_option():
     assert parsed_option.image is False
     assert parsed_option.table is True
     assert parsed_option.ocr_language == [OcrLanguage.ENGLISH]
-    assert parsed_option.ocr_preset == OCRPreset.HANDWRITING
+    assert parsed_option.ocr_preset == OcrPreset.HANDWRITING
 
 
 def test_anyparser_option_validation():
@@ -117,7 +117,7 @@ def test_anyparser_option_validation():
 
     # Test invalid OCR preset
     with pytest.raises(ValueError):
-        options = build_options(AnyparserOption(ocr_preset=OCRPreset("invalid")))
+        options = build_options(AnyparserOption(ocr_preset=OcrPreset("invalid")))
         validate_option(options)
 
     # Test missing API URL