unique_toolkit 1.45.0__py3-none-any.whl → 1.45.2__py3-none-any.whl

unique_toolkit/_common/utils/files.py

@@ -1,18 +1,101 @@
+from __future__ import annotations
+
 import mimetypes
 from enum import StrEnum
+from pathlib import Path
 
 
 class FileMimeType(StrEnum):
     PDF = "application/pdf"
     DOCX = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
     DOC = "application/msword"
+    # TODO: clean up duplicates and make the monolith compatible with this.
     XLSX = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    MSEXCEL = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
     XLS = "application/vnd.ms-excel"
+    EXCEL = "application/vnd.ms-excel"
+    PPT = "application/vnd.ms-powerpoint"
     PPTX = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
+    MSPPT = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
     CSV = "text/csv"
     HTML = "text/html"
     MD = "text/markdown"
     TXT = "text/plain"
+    JSON = "application/json"
+
+    @classmethod
+    def get_mime_from_file_path(cls, filepath: Path) -> "FileMimeType | None":
+        mime_type, _ = mimetypes.guess_type(filepath)
+        if mime_type is None:
+            return None
+        try:
+            return cls(mime_type)
+        except ValueError:
+            return None
+
+    @classmethod
+    def is_docx_mime(cls, filepath: Path) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type in {cls.DOCX, cls.DOC}
+
+    @classmethod
+    def is_pdf_mime(cls, filepath: Path) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type == cls.PDF
+
+    @classmethod
+    def is_xlsx_mime(cls, filepath: Path) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type in {cls.XLSX, cls.XLS, cls.MSEXCEL, cls.EXCEL}
+
+    @classmethod
+    def is_pptx_mime(cls, filepath: Path) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type in {cls.PPTX, cls.PPT, cls.MSPPT}
+
+    @classmethod
+    def is_json_mime(cls, filepath: Path) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type == cls.JSON
+
+    @classmethod
+    def is_valid_mime(cls, filepath: Path, valid_mimes: list[FileMimeType]) -> bool:
+        mime_type = cls.get_mime_from_file_path(filepath)
+        return mime_type in valid_mimes
+
+
+def get_common_name(extension: FileMimeType) -> str:
+    match extension:
+        case FileMimeType.DOCX | FileMimeType.DOC:
+            return "docx"
+        case (
+            FileMimeType.XLSX
+            | FileMimeType.XLS
+            | FileMimeType.MSEXCEL
+            | FileMimeType.EXCEL
+        ):
+            return "excel"
+        case FileMimeType.PPT | FileMimeType.PPTX | FileMimeType.MSPPT:
+            return "powerpoint"
+        case FileMimeType.PDF:
+            return "pdf"
+        case FileMimeType.JSON:
+            return "json"
+        case FileMimeType.CSV:
+            return "csv"
+        case FileMimeType.TXT:
+            return "text"
+        case FileMimeType.MD:
+            return "markdown"
+        case FileMimeType.HTML:
+            return "html"
+        case _:
+            return "unknown"
+
+
+def get_file_extensions(mimes: list[FileMimeType]) -> list[str]:
+    types = [mimetypes.guess_extension(mime) for mime in mimes]
+    return [t for t in types if t]
 
 
 class ImageMimeType(StrEnum):

unique_toolkit/agentic/history_manager/history_construction_with_contents.py

@@ -10,6 +10,7 @@ from pydantic import RootModel
 from unique_toolkit._common.token.token_counting import (
     num_tokens_per_language_model_message,
 )
+from unique_toolkit._common.utils import files as FileUtils
 from unique_toolkit.app import ChatEventUserMessage
 from unique_toolkit.chat.schemas import ChatMessage
 from unique_toolkit.chat.schemas import ChatMessageRole as ChatRole
@@ -29,29 +30,6 @@ map_chat_llm_message_role = {
 }
 
 
-class ImageMimeType(StrEnum):
-    JPEG = "image/jpeg"
-    PNG = "image/png"
-    GIF = "image/gif"
-    BMP = "image/bmp"
-    WEBP = "image/webp"
-    TIFF = "image/tiff"
-    SVG = "image/svg+xml"
-
-
-class FileMimeType(StrEnum):
-    PDF = "application/pdf"
-    DOCX = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-    DOC = "application/msword"
-    XLSX = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
-    XLS = "application/vnd.ms-excel"
-    PPTX = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
-    CSV = "text/csv"
-    HTML = "text/html"
-    MD = "text/markdown"
-    TXT = "text/plain"
-
-
 class ChatMessageWithContents(ChatMessage):
     contents: list[Content] = []
 
@@ -93,24 +71,6 @@ class ChatHistoryWithContent(RootModel):
         return self.root[item]
 
 
-def is_image_content(filename: str) -> bool:
-    mimetype, _ = mimetypes.guess_type(filename)
-
-    if not mimetype:
-        return False
-
-    return mimetype in ImageMimeType.__members__.values()
-
-
-def is_file_content(filename: str) -> bool:
-    mimetype, _ = mimetypes.guess_type(filename)
-
-    if not mimetype:
-        return False
-
-    return mimetype in FileMimeType.__members__.values()
-
-
 def get_chat_history_with_contents(
     user_message: ChatEventUserMessage,
     chat_id: str,
@@ -152,7 +112,7 @@ def download_encoded_images(
 ) -> list[str]:
     base64_encoded_images = []
     for im in contents:
-        if is_image_content(im.key):
+        if FileUtils.is_image_content(im.key):
             try:
                 file_bytes = content_service.download_content_to_bytes(
                     content_id=im.id,
@@ -224,8 +184,12 @@ def get_full_history_with_contents(
             text = ""
 
         if len(c.contents) > 0:
-            file_contents = [co for co in c.contents if is_file_content(co.key)]
-            image_contents = [co for co in c.contents if is_image_content(co.key)]
+            file_contents = [
+                co for co in c.contents if FileUtils.is_file_content(co.key)
+            ]
+            image_contents = [
+                co for co in c.contents if FileUtils.is_image_content(co.key)
+            ]
 
             content = (
                 text

{unique_toolkit-1.45.0.dist-info → unique_toolkit-1.45.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unique_toolkit
-Version: 1.45.0
+Version: 1.45.2
 Summary: 
 License: Proprietary
 Author: Cedric Klinkert
@@ -125,6 +125,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.45.2] - 2026-01-26
+- Make FileMimeType backwards compatible with legacy extensions
+
+## [1.45.1] - 2026-01-26
+- Add FileMimeType utility helpers
+
 ## [1.45.0] - 2026-01-23
 - Remove unused code execution options from config
 

{unique_toolkit-1.45.0.dist-info → unique_toolkit-1.45.2.dist-info}/RECORD

@@ -55,7 +55,7 @@ unique_toolkit/_common/tests/test_string_utilities.py,sha256=J2HYZ1fniOfJWI149wl
 unique_toolkit/_common/token/image_token_counting.py,sha256=VpFfZyY0GIH27q_Wy4YNjk2algqvbCtJyzuuROoFQPw,2189
 unique_toolkit/_common/token/token_counting.py,sha256=gM4B_aUqKqEPvmStFNcvCWNMNNNNKbVaywBDxlbgIps,7121
 unique_toolkit/_common/utils/__init__.py,sha256=qHrEy-3zkbFPdGFriRscPbGKuQfOuPi3O7tE5Zw5VHY,37
-unique_toolkit/_common/utils/files.py,sha256=97PkhXDUMXFEhje5HzWMMlLvZj49A6jOifqFRIrzu5M,1102
+unique_toolkit/_common/utils/files.py,sha256=GLfbk-gcLIh5J1nlWMa2hWx0IDzrCvSNDTfjMa9ktbU,3905
 unique_toolkit/_common/utils/image/encode.py,sha256=IJhtTcIT_azhiDsPp15oYs2LPze2l-sGlZrJASHrDVI,658
 unique_toolkit/_common/utils/jinja/helpers.py,sha256=UQWj0hFMtnuUFYDJ8NKbEblvYE8DrWX1o7fKQU3H9IQ,262
 unique_toolkit/_common/utils/jinja/render.py,sha256=J5UBIWoljl-Us7SjZIap9wewcLTzpXjQpOgas_YTf3Y,482
@@ -86,7 +86,7 @@ unique_toolkit/agentic/evaluation/tests/test_context_relevancy_service.py,sha256
 unique_toolkit/agentic/evaluation/tests/test_output_parser.py,sha256=RN_HcBbU6qy_e_PoYyUFcjWnp3ymJ6-gLj6TgEOupAI,3107
 unique_toolkit/agentic/feature_flags/__init__.py,sha256=LhE2cHoa9AYBOR7TjiIToOn46sttm9paKcrzE7gnDPM,149
 unique_toolkit/agentic/feature_flags/feature_flags.py,sha256=4jPH0GGGt5-tQ6PJWNpMBIlYzNrQIIqBLx8W02lwxD0,1140
-unique_toolkit/agentic/history_manager/history_construction_with_contents.py,sha256=kzxpVzTtQqL8TjdIvOy7gkRVxD4BsOMyimECryg7vdc,9060
+unique_toolkit/agentic/history_manager/history_construction_with_contents.py,sha256=TwamOOnYTYZMQdY1mAzj6_MZOe3T5RsjFDarT1tCtYo,8150
 unique_toolkit/agentic/history_manager/history_manager.py,sha256=7V7_173XkAjc8otBACF0G3dbqRs34FSlURbBPrE95Wk,9537
 unique_toolkit/agentic/history_manager/loop_token_reducer.py,sha256=3c-uonDovtanEJUpAO4zlA4-n9MS_Ws_V0Yb6G7hPM0,20172
 unique_toolkit/agentic/history_manager/utils.py,sha256=VIn_UmcR3jHtpux0qp5lQQzczgAm8XYSeQiPo87jC3A,3143
@@ -244,7 +244,7 @@ unique_toolkit/short_term_memory/service.py,sha256=5PeVBu1ZCAfyDb2HLVvlmqSbyzBBu
 unique_toolkit/smart_rules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 unique_toolkit/smart_rules/compile.py,sha256=Ozhh70qCn2yOzRWr9d8WmJeTo7AQurwd3tStgBMPFLA,1246
 unique_toolkit/test_utilities/events.py,sha256=_mwV2bs5iLjxS1ynDCjaIq-gjjKhXYCK-iy3dRfvO3g,6410
-unique_toolkit-1.45.0.dist-info/LICENSE,sha256=GlN8wHNdh53xwOPg44URnwag6TEolCjoq3YD_KrWgss,193
-unique_toolkit-1.45.0.dist-info/METADATA,sha256=wfMYzHsUT5U9jNgqX5uNaIFj_rE_1TfL-iySEmB6l-U,48751
-unique_toolkit-1.45.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-unique_toolkit-1.45.0.dist-info/RECORD,,
+unique_toolkit-1.45.2.dist-info/LICENSE,sha256=GlN8wHNdh53xwOPg44URnwag6TEolCjoq3YD_KrWgss,193
+unique_toolkit-1.45.2.dist-info/METADATA,sha256=WeKaLthzSrgmcOWbNRtK0VrZrwVEBtOhgM1Id-P5Els,48902
+unique_toolkit-1.45.2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+unique_toolkit-1.45.2.dist-info/RECORD,,