chunkr-ai 0.0.8__py3-none-any.whl → 0.0.10__py3-none-any.whl

chunkr_ai/api/chunkr.py

@@ -1,4 +1,4 @@
-from .base import ChunkrBase
+from .chunkr_base import ChunkrBase
 from .config import Configuration
 from .task import TaskResponse
 from pathlib import Path
@@ -163,5 +163,3 @@ class Chunkr(ChunkrBase):
             headers=self._headers()
         )
         r.raise_for_status()
-
-  

chunkr_ai/api/chunkr_async.py

@@ -1,4 +1,4 @@
-from .base import ChunkrBase
+from .chunkr_base import ChunkrBase
 from .task import TaskResponse
 from .config import Configuration
 import httpx

chunkr_ai/api/config.py

@@ -40,7 +40,6 @@ class ChunkProcessing(BaseModel):
 
 class Property(BaseModel):
     name: str
-    title: Optional[str] = None
     prop_type: str
     description: Optional[str] = None
     default: Optional[str] = None

chunkr_ai/api/misc.py

@@ -1,11 +1,11 @@
+from .config import Configuration, Property, JsonSchema
 import io
 import json
 from pathlib import Path
 from PIL import Image
 import requests
 from typing import Union, Tuple, BinaryIO, Optional
-from .config import Configuration
-
+from pydantic import BaseModel
 
 def prepare_file(
     file: Union[str, Path, BinaryIO, Image.Image]
@@ -15,8 +15,31 @@ def prepare_file(
     if isinstance(file, str) and (file.startswith('http://') or file.startswith('https://')):
         response = requests.get(file)
         response.raise_for_status()
+        
+        # Try to get filename from Content-Disposition header first
+        filename = None
+        content_disposition = response.headers.get('Content-Disposition')
+        if content_disposition and 'filename=' in content_disposition:
+            filename = content_disposition.split('filename=')[-1].strip('"\'')
+        
+        # If no Content-Disposition, try to get clean filename from URL path
+        if not filename:
+            from urllib.parse import urlparse, unquote
+            parsed_url = urlparse(file)
+            path = unquote(parsed_url.path)
+            filename = Path(path).name if path else None
+        
+        # Fallback to default name if we couldn't extract one
+        filename = filename or 'downloaded_file'
+        
+        # Sanitize filename: remove invalid characters and limit length
+        import re
+        filename = re.sub(r'[<>:"/\\|?*%]', '_', filename)  # Replace invalid chars with underscore
+        filename = re.sub(r'\s+', '_', filename)            # Replace whitespace with underscore
+        filename = filename.strip('._')                     # Remove leading/trailing dots and underscores
+        filename = filename[:255]                           # Limit length to 255 characters
+        
         file_obj = io.BytesIO(response.content)
-        filename = Path(file.split('/')[-1]).name or 'downloaded_file'
         return filename, file_obj
 
     # Handle base64 strings
@@ -104,3 +127,33 @@ def prepare_upload_data(
             files[key] = (None, json.dumps(value), 'application/json')
                 
     return files
+
+def from_pydantic(pydantic: BaseModel) -> dict:
+    """Convert a Pydantic model to a Chunk json schema.
+    
+    Args:
+        pydantic: A Pydantic BaseModel class or instance
+        
+    Returns:
+        dict: A JSON schema compatible with Chunk's format
+    """
+    model = pydantic if isinstance(pydantic, type) else pydantic.__class__
+    schema = model.model_json_schema()
+    print(schema)
+    properties = []
+    for name, details in schema.get('properties', {}).items():
+        prop = Property(
+            name=name,
+            title=details.get('title'),
+            prop_type=details.get('type', 'string'),
+            description=details.get('description'),
+            default=str(details.get('default')) if details.get('default') is not None else None
+        )
+        properties.append(prop)
+    
+    json_schema = JsonSchema(
+        title=schema.get('title', model.__name__),
+        properties=properties
+    )
+    
+    return json_schema.model_dump(mode="json", exclude_none=True)

chunkr_ai/api/task_async.py

@@ -0,0 +1,111 @@
+import asyncio
+from pydantic import BaseModel, PrivateAttr
+from datetime import datetime
+from enum import Enum
+from typing import Optional, Union
+from .task_base import TaskBase
+from .protocol import ChunkrClientProtocol
+from .config import Configuration, OutputResponse
+from .misc import prepare_upload_data
+
+class Status(str, Enum):
+    STARTING = "Starting"
+    PROCESSING = "Processing"
+    SUCCEEDED = "Succeeded"
+    FAILED = "Failed"
+    CANCELLED = "Cancelled"
+
+class TaskResponseAsync(BaseModel, TaskBase):
+    configuration: Configuration
+    created_at: datetime
+    expires_at: Optional[datetime]
+    file_name: Optional[str]
+    finished_at: Optional[datetime]
+    input_file_url: Optional[str]
+    message: str
+    output: Optional[OutputResponse]
+    page_count: Optional[int]
+    pdf_url: Optional[str]
+    started_at: Optional[datetime]
+    status: Status
+    task_id: str
+    task_url: Optional[str]
+    _client: Optional[Union[ChunkrClientProtocol]] = PrivateAttr(default=None)
+
+    def with_client(self, client: Union[ChunkrClientProtocol]) -> 'TaskResponseAsync':
+        self._client = client
+        return self
+
+    async def poll(self) -> 'TaskResponseAsync':
+        while True:
+            j = await self._poll_request()
+            updated = TaskResponseAsync(**j).with_client(self._client)
+            self.__dict__.update(updated.__dict__)
+            if res := self._check_status():
+                return res
+            await asyncio.sleep(0.5)
+
+    async def _poll_request(self) -> dict:
+        if not self.task_url:
+            raise ValueError("Task URL not found")
+        while True:
+            try:
+                r = await self._client._client.get(self.task_url, headers=self._client._headers())
+                r.raise_for_status()
+                return r.json()
+            except Exception as e:
+                if self.status == Status.FAILED:
+                    raise ValueError(self.message) from e
+                await asyncio.sleep(0.5)
+
+    def _check_status(self) -> Optional['TaskResponseAsync']:
+        if self.status == Status.FAILED:
+            raise ValueError(f"Task failed: {self.message}")
+        if self.status == Status.CANCELLED:
+            return self
+        if self.status not in [Status.STARTING, Status.PROCESSING]:
+            return self
+        return None
+
+    async def update(self, config: Configuration) -> 'TaskResponseAsync':
+        if not self.task_url:
+            raise ValueError("Task URL not found")
+        f = prepare_upload_data(None, config)
+        r = await self._client._client.patch(self.task_url, files=f, headers=self._client._headers())
+        r.raise_for_status()
+        updated = TaskResponseAsync(**r.json()).with_client(self._client)
+        self.__dict__.update(updated.__dict__)
+        return await self.poll()
+
+    async def cancel(self):
+        if not self.task_url:
+            raise ValueError("Task URL not found")
+        r = await self._client._client.get(f"{self.task_url}/cancel", headers=self._client._headers())
+        r.raise_for_status()
+        return await self.poll()
+
+    async def delete(self):
+        r = await self._client._client.delete(self.task_url, headers=self._client._headers())
+        r.raise_for_status()
+
+    def html(self) -> str:
+        return self._get_content("html")
+
+    def markdown(self) -> str:
+        return self._get_content("markdown")
+
+    def content(self) -> str:
+        return self._get_content("content")
+
+    def _get_content(self, t: str) -> str:
+        if not self.output:
+            return ""
+        parts = []
+        for c in self.output.chunks:
+            for s in c.segments:
+                v = getattr(s, t)
+                if v:
+                    parts.append(v)
+        return "\n".join(parts)
+
+    # Satisfying TaskBase abstract methods with stubs

chunkr_ai/api/task_base.py

@@ -0,0 +1,31 @@
+from abc import ABC, abstractmethod
+from .config import Configuration
+
+class TaskBase(ABC):
+    @abstractmethod
+    def poll(self):
+        pass
+
+    @abstractmethod
+    def update(self, config: Configuration):
+        pass
+
+    @abstractmethod
+    def cancel(self):
+        pass
+
+    @abstractmethod
+    def delete(self):
+        pass
+
+    @abstractmethod
+    def html(self) -> str:
+        pass
+
+    @abstractmethod
+    def markdown(self) -> str:
+        pass
+
+    @abstractmethod
+    def content(self) -> str:
+        pass

{chunkr_ai-0.0.8.dist-info → chunkr_ai-0.0.10.dist-info}/METADATA

@@ -1,20 +1,20 @@
 Metadata-Version: 2.2
 Name: chunkr-ai
-Version: 0.0.8
+Version: 0.0.10
 Summary: Python client for Chunkr: open source document intelligence
 Author-email: Ishaan Kapoor <ishaan@lumina.sh>
 Project-URL: Homepage, https://chunkr.ai
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: httpx>=0.28.1
-Requires-Dist: pillow>=11.1.0
-Requires-Dist: pydantic>=2.10.4
-Requires-Dist: pytest-asyncio>=0.25.2
-Requires-Dist: python-dotenv>=1.0.1
-Requires-Dist: requests>=2.32.3
+Requires-Dist: httpx>=0.25.0
+Requires-Dist: pillow>=10.0.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pytest-asyncio>=0.21.0
+Requires-Dist: python-dotenv>=0.19.0
+Requires-Dist: requests>=2.28.0
 Provides-Extra: test
-Requires-Dist: pytest>=8.3.4; extra == "test"
-Requires-Dist: pytest-xdist>=3.6.1; extra == "test"
+Requires-Dist: pytest>=7.0.0; extra == "test"
+Requires-Dist: pytest-xdist>=3.0.0; extra == "test"
 
 # Chunkr Python Client
 

chunkr_ai-0.0.10.dist-info/RECORD

@@ -0,0 +1,19 @@
+chunkr_ai/__init__.py,sha256=eXygrEhGxxIHXNYIlHF2eied8rGsx2RphgR8Wo4lRyo,110
+chunkr_ai/main.py,sha256=_MT1lcnNiXjVW9ZkZYl28SB_f6M9g_IOgZxvhodTzAo,394
+chunkr_ai/models.py,sha256=T8_F-Y1US21ZJVzLIaroqp-Hd0_ZFbdkbEOxr63-PNE,827
+chunkr_ai/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+chunkr_ai/api/auth.py,sha256=iSd5Jek2BFaHGw9HY-RrqgwP56BHFU0xbSuJS4fU6AA,425
+chunkr_ai/api/chunkr.py,sha256=0qpV9b1hOpDhA9EuKkXW9X_laUmw5NY3ZYq0cUOTbww,5190
+chunkr_ai/api/chunkr_async.py,sha256=ZkLBrn4cqzu3sqMfS8cfZZgSvpdyQuWZP95lfGxuHx0,4900
+chunkr_ai/api/chunkr_base.py,sha256=IYO0pmoL02GchIggj6_Q5nvtAUoOvYAAvT7VLFU6scY,2506
+chunkr_ai/api/config.py,sha256=eu7a28UjlNaM3QRrzElRTQXqMPBynAvlusVSIAMNXUY,4203
+chunkr_ai/api/misc.py,sha256=DiY-BV5nPMDVKAiHTcND8w-8mSB-dENxrOhxnkyEoRA,6034
+chunkr_ai/api/protocol.py,sha256=XKS9RmtvBpJItYhPg18qlOCKpaSHdOuQTRSUxAdUz2g,479
+chunkr_ai/api/task.py,sha256=EB6RK8ms7EaNj57tNJZoNgNMHGWKXFhkQ1WC7gk5ht4,6059
+chunkr_ai/api/task_async.py,sha256=Dd-Fenie0Q6GxXce7OlXvuQ14NQ58F_0b9P7AGKWyYA,3833
+chunkr_ai/api/task_base.py,sha256=Tkk7dhIeB3ic5M9g_b-MVRdNv4XQTvajpaUy8JylQ8A,526
+chunkr_ai-0.0.10.dist-info/LICENSE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+chunkr_ai-0.0.10.dist-info/METADATA,sha256=W8PCDpT4hN5tpn_9fyVrjEbd0abG0ReP5reG4_9Glp8,4845
+chunkr_ai-0.0.10.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+chunkr_ai-0.0.10.dist-info/top_level.txt,sha256=0IZY7PZIiS8bw5r4NUQRUQ-ATi-L_3vLQVq3ZLouOW8,10
+chunkr_ai-0.0.10.dist-info/RECORD,,

chunkr_ai-0.0.8.dist-info/RECORD

@@ -1,18 +0,0 @@
-chunkr_ai/__init__.py,sha256=eXygrEhGxxIHXNYIlHF2eied8rGsx2RphgR8Wo4lRyo,110
-chunkr_ai/main.py,sha256=_MT1lcnNiXjVW9ZkZYl28SB_f6M9g_IOgZxvhodTzAo,394
-chunkr_ai/models.py,sha256=T8_F-Y1US21ZJVzLIaroqp-Hd0_ZFbdkbEOxr63-PNE,827
-chunkr_ai/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chunkr_ai/api/api.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chunkr_ai/api/auth.py,sha256=iSd5Jek2BFaHGw9HY-RrqgwP56BHFU0xbSuJS4fU6AA,425
-chunkr_ai/api/base.py,sha256=IYO0pmoL02GchIggj6_Q5nvtAUoOvYAAvT7VLFU6scY,2506
-chunkr_ai/api/chunkr.py,sha256=PmrK37HbK2T1KUPitKnt4wZqIujL61Jo12qW9DEpNMI,5186
-chunkr_ai/api/chunkr_async.py,sha256=2yYyAO9-j2xKQYH0fJb2S6gL26hgbtL4QyqlG9l0QBY,4893
-chunkr_ai/api/config.py,sha256=XIqXZ_8q7U_BEmY5wyIC9mbQGZBw1956EN9yhC4svD0,4235
-chunkr_ai/api/misc.py,sha256=tScsUUcrqeVh_bZv1YlbmjGkQSTDQN8NyKxoNwAG6XA,3792
-chunkr_ai/api/protocol.py,sha256=XKS9RmtvBpJItYhPg18qlOCKpaSHdOuQTRSUxAdUz2g,479
-chunkr_ai/api/task.py,sha256=EB6RK8ms7EaNj57tNJZoNgNMHGWKXFhkQ1WC7gk5ht4,6059
-chunkr_ai-0.0.8.dist-info/LICENSE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chunkr_ai-0.0.8.dist-info/METADATA,sha256=tL3OZfFIRsgfIKoDYWAS89bZw48_0C8cdqHJ6_GrT7A,4844
-chunkr_ai-0.0.8.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-chunkr_ai-0.0.8.dist-info/top_level.txt,sha256=0IZY7PZIiS8bw5r4NUQRUQ-ATi-L_3vLQVq3ZLouOW8,10
-chunkr_ai-0.0.8.dist-info/RECORD,,