build: pull from wolfi base image (#3213)

### Summary

Updates the `wolfi` image to pull from the upstream `wolfi-base` base
image to avoid maintaining the base layers in both locations. Closes
#3105 by pulling in the fix from upstream.

### Testing

`test_dockerfile` should continue to pass with the changes.

CHANGELOG.md

@@ -1,3 +1,13 @@
+## 0.14.7-dev0
+
+### Enhancements
+
+* **Pull from `wolfi-base` image.** The amd64 image now pulls from the `unstructured` `wolfi-base` image to avoid duplication of dependency setup steps.
+
+### Features
+
+### Fixes
+
 ## 0.14.6
 
 ### Enhancements

Dockerfile-amd64

@@ -1,34 +1,17 @@
-FROM cgr.dev/chainguard/wolfi-base:latest
+FROM quay.io/unstructured-io/base-images:wolfi-base@sha256:6c00a236c648ffdaf196ccbc446f5c6cc9eb4e3ab9e437178abcfac710b2b373
-
-WORKDIR /app
 
 USER root
 
-COPY ./docker-packages/*.apk packages/
+WORKDIR /app
+
 COPY ./requirements requirements/
 COPY unstructured unstructured
 COPY test_unstructured test_unstructured
 COPY example-docs example-docs
 
-RUN apk update && apk add py3.11-pip mesa-gl glib cmake && \
+RUN chown -R notebook-user:notebook-user /app
-  apk add --allow-untrusted packages/pandoc-3.1.8-r0.apk && \
-  apk add --allow-untrusted packages/poppler-23.09.0-r0.apk && \
-  apk add --allow-untrusted packages/leptonica-1.83.0-r0.apk && \
-  apk add --allow-untrusted packages/tesseract-5.3.2-r0.apk && \
-  apk add --allow-untrusted packages/libreoffice-7.6.5-r0.apk && \
-  apk add bash && \
-  apk add libmagic && \
-  mv /share/tessdata/configs /usr/local/share/tessdata/ && \
-  mv /share/tessdata/tessconfigs /usr/local/share/tessdata/ && \
-  ln -s /usr/local/lib/libreoffice/program/soffice.bin /usr/local/bin/libreoffice && \
-  ln -s /usr/local/lib/libreoffice/program/soffice.bin /usr/local/bin/soffice && \
-  chmod +x /usr/local/lib/libreoffice/program/soffice.bin && \
-  chmod +x /usr/local/bin/libreoffice && \
-  chmod +x /usr/local/bin/soffice
 
-RUN chown -R nonroot:nonroot /app
+USER notebook-user
-
-USER nonroot
 
 RUN find requirements/ -type f -name "*.txt" -exec pip3.11 install --no-cache-dir --user -r '{}' ';'
 RUN pip3.11 install unstructured.paddlepaddle
@@ -38,7 +21,7 @@ RUN python3.11 -c "import nltk; nltk.download('punkt')" && \
   python3.11 -c "from unstructured.partition.model_init import initialize; initialize()" && \
   python3.11 -c "from unstructured_inference.models.tables import UnstructuredTableTransformerModel; model = UnstructuredTableTransformerModel(); model.initialize('microsoft/table-transformer-structure-recognition')"
 
-ENV PATH="${PATH}:/home/nonroot/.local/bin"
+ENV PATH="${PATH}:/home/notebook-user/.local/bin"
 ENV TESSDATA_PREFIX=/usr/local/share/tessdata
 
 CMD ["/bin/bash"]

test_unstructured/partition/test_doc.py

@@ -2,7 +2,6 @@
 
 from __future__ import annotations
 
-import os
 import pathlib
 import tempfile
 from typing import Any
@@ -32,13 +31,8 @@ from unstructured.documents.elements import (
 from unstructured.partition.doc import partition_doc
 from unstructured.partition.docx import partition_docx
 
-is_in_docker = os.path.exists("/.dockerenv")
-
 
 def test_partition_doc_matches_partition_docx(request: FixtureRequest):
-    # NOTE(robinson) - was having issues with the tempfile not being found in the docker tests
-    if is_in_docker:
-        request.applymarker(pytest.mark.xfail)
     doc_file_path = example_doc_path("simple.doc")
     docx_file_path = example_doc_path("simple.docx")
 

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.14.6"  # pragma: no cover
+__version__ = "0.14.7-dev0"  # pragma: no cover