Fix json bytes content type detection (#3941)

Fixes order of content type detection strategies for byte-encoded jsons.

Before
```
json_bytes = json.dumps([{"example": "data"}]).encode("utf-8")
file_buffer = io.BytesIO(json_bytes)
detect_filetype(file=file_buffer, metadata_file_path="filename.pdf") 
```

Before
PDF

Now
JSON

Author: plutasnyy

CHANGELOG.md

@@ -1,3 +1,14 @@
+## 0.16.25
+
+### Enhancements
+
+### Features
+
+### Fixes
+
+- **Fixes filetype detection for jsons passed as byte streams** - Now it prioritizes magic mimetype prediction over file extension when detecting filetypes
+
+
 ## 0.16.24
 
 ### Enhancements
@@ -14,6 +25,7 @@
 
 ### Fixes
 
+
 ## 0.16.23
 
 ### Enhancements

requirements/base.txt

@@ -2,14 +2,14 @@
 # This file is autogenerated by pip-compile with Python 3.9
 # by the following command:
 #
-#    pip-compile base.in
+#    pip-compile ./base.in
 #
 anyio==4.8.0
     # via httpx
 backoff==2.2.1
-    # via -r base.in
+    # via -r ./base.in
 beautifulsoup4==4.13.3
-    # via -r base.in
+    # via -r ./base.in
 certifi==2025.1.31
     # via
     #   httpcore
@@ -19,7 +19,7 @@ certifi==2025.1.31
 cffi==1.17.1
     # via cryptography
 chardet==5.2.0
-    # via -r base.in
+    # via -r ./base.in
 charset-normalizer==3.4.1
     # via
     #   requests
@@ -28,24 +28,24 @@ click==8.1.8
     # via
     #   nltk
     #   python-oxmsg
-cryptography==44.0.1
+cryptography==44.0.2
     # via unstructured-client
 dataclasses-json==0.6.7
     # via
-    #   -r base.in
+    #   -r ./base.in
     #   unstructured-client
-deepdiff==8.2.0
+deepdiff==8.3.0
     # via unstructured-client
 emoji==2.14.1
-    # via -r base.in
+    # via -r ./base.in
 exceptiongroup==1.2.2
     # via anyio
 filetype==1.2.0
-    # via -r base.in
+    # via -r ./base.in
 h11==0.14.0
     # via httpcore
 html5lib==1.1
-    # via -r base.in
+    # via -r ./base.in
 httpcore==1.0.7
     # via httpx
 httpx==0.28.1
@@ -61,9 +61,9 @@ joblib==1.4.2
 jsonpath-python==1.0.6
     # via unstructured-client
 langdetect==1.0.9
-    # via -r base.in
+    # via -r ./base.in
 lxml==5.3.1
-    # via -r base.in
+    # via -r ./base.in
 marshmallow==3.26.1
     # via
     #   dataclasses-json
@@ -75,9 +75,9 @@ mypy-extensions==1.0.0
 nest-asyncio==1.6.0
     # via unstructured-client
 nltk==3.9.1
-    # via -r base.in
+    # via -r ./base.in
 numpy==1.26.4
-    # via -r base.in
+    # via -r ./base.in
 olefile==0.47
     # via python-oxmsg
 orderly-set==5.3.0
@@ -87,26 +87,26 @@ packaging==24.2
     #   marshmallow
     #   unstructured-client
 psutil==7.0.0
-    # via -r base.in
+    # via -r ./base.in
 pycparser==2.22
     # via cffi
-pypdf==5.3.0
+pypdf==5.3.1
     # via unstructured-client
 python-dateutil==2.9.0.post0
     # via unstructured-client
 python-iso639==2025.2.18
-    # via -r base.in
+    # via -r ./base.in
 python-magic==0.4.27
-    # via -r base.in
+    # via -r ./base.in
 python-oxmsg==0.0.2
-    # via -r base.in
-rapidfuzz==3.12.1
-    # via -r base.in
+    # via -r ./base.in
+rapidfuzz==3.12.2
+    # via -r ./base.in
 regex==2024.11.6
     # via nltk
 requests==2.32.3
     # via
-    #   -r base.in
+    #   -r ./base.in
     #   requests-toolbelt
     #   unstructured-client
 requests-toolbelt==1.0.0
@@ -123,11 +123,11 @@ soupsieve==2.6
     # via beautifulsoup4
 tqdm==4.67.1
     # via
-    #   -r base.in
+    #   -r ./base.in
     #   nltk
 typing-extensions==4.12.2
     # via
-    #   -r base.in
+    #   -r ./base.in
     #   anyio
     #   beautifulsoup4
     #   pypdf
@@ -140,14 +140,14 @@ typing-inspect==0.9.0
     #   unstructured-client
 unstructured-client==0.25.9
     # via
-    #   -c ./deps/constraints.txt
-    #   -r base.in
+    #   -c ././deps/constraints.txt
+    #   -r ./base.in
 urllib3==1.26.20
     # via
-    #   -c ./deps/constraints.txt
+    #   -c ././deps/constraints.txt
     #   requests
     #   unstructured-client
 webencodings==0.5.1
     # via html5lib
 wrapt==1.17.2
-    # via -r base.in
+    # via -r ./base.in

requirements/deps/constraints.txt

@@ -6,6 +6,8 @@
 # we are using v3 client https://weaviate.io/developers/weaviate/client-libraries/python/python_v3
 weaviate-client>=3.26.7,<4.0.0
 # TODO: Constriant due to multiple versions being installed during pip-compile
+protobuf>=6.30.0
+# TODO: Constriant due to multiple versions being installed during pip-compile
 grpcio>=1.65.5
 # TODO: Pinned in transformers package, remove when that gets updated (https://github.com/huggingface/transformers/blob/main/setup.py)
 tokenizers>=0.21,<0.22

requirements/dev.txt

@@ -2,56 +2,56 @@
 # This file is autogenerated by pip-compile with Python 3.9
 # by the following command:
 #
-#    pip-compile dev.in
+#    pip-compile ./dev.in
 #
 build==1.2.2.post1
     # via pip-tools
 cfgv==3.4.0
     # via pre-commit
 click==8.1.8
     # via
-    #   -c base.txt
-    #   -c test.txt
+    #   -c ./base.txt
+    #   -c ./test.txt
     #   pip-tools
 distlib==0.3.9
     # via virtualenv
 filelock==3.17.0
     # via virtualenv
-identify==2.6.7
+identify==2.6.8
     # via pre-commit
 importlib-metadata==8.6.1
     # via
-    #   -c ./deps/constraints.txt
+    #   -c ././deps/constraints.txt
     #   build
 nodeenv==1.9.1
     # via pre-commit
 packaging==24.2
     # via
-    #   -c base.txt
-    #   -c test.txt
+    #   -c ./base.txt
+    #   -c ./test.txt
     #   build
 pip-tools==7.4.1
-    # via -r dev.in
+    # via -r ./dev.in
 platformdirs==4.3.6
     # via
-    #   -c test.txt
+    #   -c ./test.txt
     #   virtualenv
 pre-commit==4.1.0
-    # via -r dev.in
+    # via -r ./dev.in
 pyproject-hooks==1.2.0
     # via
     #   build
     #   pip-tools
 pyyaml==6.0.2
     # via
-    #   -c test.txt
+    #   -c ./test.txt
     #   pre-commit
 tomli==2.2.1
     # via
-    #   -c test.txt
+    #   -c ./test.txt
     #   build
     #   pip-tools
-virtualenv==20.29.2
+virtualenv==20.29.3
     # via pre-commit
 wheel==0.45.1
     # via pip-tools

requirements/extra-csv.txt

@@ -2,23 +2,23 @@
 # This file is autogenerated by pip-compile with Python 3.9
 # by the following command:
 #
-#    pip-compile extra-csv.in
+#    pip-compile ./extra-csv.in
 #
 numpy==1.26.4
     # via
-    #   -c base.txt
+    #   -c ./base.txt
     #   pandas
 pandas==2.2.3
-    # via -r extra-csv.in
+    # via -r ./extra-csv.in
 python-dateutil==2.9.0.post0
     # via
-    #   -c base.txt
+    #   -c ./base.txt
     #   pandas
 pytz==2025.1
     # via pandas
 six==1.17.0
     # via
-    #   -c base.txt
+    #   -c ./base.txt
     #   python-dateutil
 tzdata==2025.1
     # via pandas

requirements/extra-docx.txt

@@ -2,15 +2,15 @@
 # This file is autogenerated by pip-compile with Python 3.9
 # by the following command:
 #
-#    pip-compile extra-docx.in
+#    pip-compile ./extra-docx.in
 #
 lxml==5.3.1
     # via
-    #   -c base.txt
+    #   -c ./base.txt
     #   python-docx
 python-docx==1.1.2
-    # via -r extra-docx.in
+    # via -r ./extra-docx.in
 typing-extensions==4.12.2
     # via
-    #   -c base.txt
+    #   -c ./base.txt
     #   python-docx

requirements/extra-epub.txt

@@ -2,7 +2,7 @@
 # This file is autogenerated by pip-compile with Python 3.9
 # by the following command:
 #
-#    pip-compile extra-epub.in
+#    pip-compile ./extra-epub.in
 #
 pypandoc==1.15
-    # via -r extra-epub.in
+    # via -r ./extra-epub.in

requirements/extra-markdown.txt

@@ -2,13 +2,13 @@
 # This file is autogenerated by pip-compile with Python 3.9
 # by the following command:
 #
-#    pip-compile extra-markdown.in
+#    pip-compile ./extra-markdown.in
 #
 importlib-metadata==8.6.1
     # via
-    #   -c ./deps/constraints.txt
+    #   -c ././deps/constraints.txt
     #   markdown
 markdown==3.7
-    # via -r extra-markdown.in
+    # via -r ./extra-markdown.in
 zipp==3.21.0
     # via importlib-metadata

requirements/extra-odt.txt

@@ -2,17 +2,17 @@
 # This file is autogenerated by pip-compile with Python 3.9
 # by the following command:
 #
-#    pip-compile extra-odt.in
+#    pip-compile ./extra-odt.in
 #
 lxml==5.3.1
     # via
-    #   -c base.txt
+    #   -c ./base.txt
     #   python-docx
 pypandoc==1.15
-    # via -r extra-odt.in
+    # via -r ./extra-odt.in
 python-docx==1.1.2
-    # via -r extra-odt.in
+    # via -r ./extra-odt.in
 typing-extensions==4.12.2
     # via
-    #   -c base.txt
+    #   -c ./base.txt
     #   python-docx