fix: bump inference again to fix bugs

Unstructured-IO · Oct 18, 2024 · 8b6b959 · 8b6b959
1 parent 8c54153
commit 8b6b959
Show file tree

Hide file tree

Showing 6 changed files with 8 additions and 8 deletions.
diff --git a/requirements/base.txt b/requirements/base.txt
@@ -27,7 +27,7 @@ click==8.1.7
     # via
     #   nltk
     #   python-oxmsg
-cryptography==43.0.1
+cryptography==43.0.3
     # via unstructured-client
 dataclasses-json==0.6.7
     # via -r ./base.in

diff --git a/requirements/extra-pdf-image.in b/requirements/extra-pdf-image.in
@@ -11,5 +11,5 @@ google-cloud-vision
 effdet
 # Do not move to constraints.in, otherwise unstructured-inference will not be upgraded
 # when unstructured library is.
-unstructured-inference==0.7.41
+unstructured-inference==0.8.0
 unstructured.pytesseract>=0.3.12
diff --git a/requirements/extra-pdf-image.txt b/requirements/extra-pdf-image.txt
@@ -25,7 +25,7 @@ coloredlogs==15.0.1
     # via onnxruntime
 contourpy==1.3.0
     # via matplotlib
-cryptography==43.0.1
+cryptography==43.0.3
     # via
     #   -c ./base.txt
     #   pdfminer-six
@@ -93,7 +93,7 @@ lxml==5.3.0
     # via
     #   -c ./base.txt
     #   pikepdf
-markupsafe==3.0.1
+markupsafe==3.0.2
     # via jinja2
 matplotlib==3.9.2
     # via
@@ -284,7 +284,7 @@ typing-extensions==4.12.2
     #   torch
 tzdata==2024.2
     # via pandas
-unstructured-inference==0.7.41
+unstructured-inference==0.8.0
     # via -r ./extra-pdf-image.in
 unstructured-pytesseract==0.3.13
     # via -r ./extra-pdf-image.in

diff --git a/requirements/huggingface.txt b/requirements/huggingface.txt
@@ -43,7 +43,7 @@ langdetect==1.0.9
     # via
     #   -c ./base.txt
     #   -r ./huggingface.in
-markupsafe==3.0.1
+markupsafe==3.0.2
     # via jinja2
 mpmath==1.3.0
     # via sympy

diff --git a/requirements/test.txt b/requirements/test.txt
@@ -241,7 +241,7 @@ wrapt==1.16.0
     #   vcrpy
 xmljson==0.2.1
     # via label-studio-sdk
-yarl==1.15.4
+yarl==1.15.5
     # via vcrpy
 
 # The following packages are considered to be unsafe in a requirements file:

diff --git a/unstructured/partition/pdf_image/inference_utils.py b/unstructured/partition/pdf_image/inference_utils.py
@@ -98,7 +98,7 @@ def merge_text_regions(regions: TextRegions) -> TextRegion:
     max_x2 = regions.x2.max().astype(float)
     max_y2 = regions.y2.max().astype(float)
 
-    merged_text = " ".join(regions.texts)
+    merged_text = " ".join([text for text in regions.texts if text])
     source = regions.source
 
     return TextRegion.from_coords(min_x1, min_y1, max_x2, max_y2, merged_text, source)