Skip to content

Commit 059fc64

Browse files
authored
build: apk add libreoffice24 (#3065)
### Summary Switches to installing `libreoffice` from the Wolfi repository and upgrades the `libreoffice` version to `libreoffice==24.x.x`. Resolves a medium vulnerability in the old `libreoffice` version. Security scanning with `anchore/grype` was also added to the `test_dockerfile` job. Requirements were bumped to resolve a vulnerability in the `requests` library. ### Testing `test_dockerfile` passes with the updates.
1 parent 3eaf65a commit 059fc64

40 files changed

+168
-102
lines changed

.github/workflows/ci.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -500,3 +500,8 @@ jobs:
500500
make docker-dl-packages
501501
make docker-build
502502
make docker-test CI=true UNSTRUCTURED_INCLUDE_DEBUG_METADATA=true
503+
- name: Scan image
504+
uses: anchore/scan-action@v3
505+
with:
506+
image: "unstructured:dev"
507+
severity-cutoff: medium

Dockerfile-amd64

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -15,16 +15,16 @@ RUN apk update && apk add py3.11-pip mesa-gl glib cmake && \
1515
apk add --allow-untrusted packages/poppler-23.09.0-r0.apk && \
1616
apk add --allow-untrusted packages/leptonica-1.83.0-r0.apk && \
1717
apk add --allow-untrusted packages/tesseract-5.3.2-r0.apk && \
18-
apk add --allow-untrusted packages/libreoffice-7.6.5-r0.apk && \
18+
apk add libreoffice && \
1919
apk add bash && \
2020
apk add libmagic && \
2121
mv /share/tessdata/configs /usr/local/share/tessdata/ && \
2222
mv /share/tessdata/tessconfigs /usr/local/share/tessdata/ && \
23-
ln -s /usr/local/lib/libreoffice/program/soffice.bin /usr/local/bin/libreoffice && \
24-
ln -s /usr/local/lib/libreoffice/program/soffice.bin /usr/local/bin/soffice && \
25-
chmod +x /usr/local/lib/libreoffice/program/soffice.bin && \
26-
chmod +x /usr/local/bin/libreoffice && \
27-
chmod +x /usr/local/bin/soffice
23+
ln -s /usr/lib/libreoffice/program/soffice.bin /usr/bin/libreoffice && \
24+
ln -s /usr/lib/libreoffice/program/soffice.bin /usr/bin/soffice && \
25+
chmod +x /usr/lib/libreoffice/program/soffice.bin && \
26+
chmod +x /usr/bin/libreoffice && \
27+
chmod +x /usr/bin/soffice
2828

2929
RUN chown -R nonroot:nonroot /app
3030

docs/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -66,7 +66,7 @@ pygments==2.18.0
6666
# sphinx-tabs
6767
pyyaml==6.0.1
6868
# via myst-parser
69-
requests==2.31.0
69+
requests==2.32.1
7070
# via
7171
# -c ./base.txt
7272
# sphinx

requirements/base.txt

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ dataclasses-json==0.6.6
2525
# via -r ./base.in
2626
dataclasses-json-speakeasy==0.5.11
2727
# via unstructured-client
28-
emoji==2.11.1
28+
emoji==2.12.1
2929
# via -r ./base.in
3030
filetype==1.2.0
3131
# via -r ./base.in
@@ -67,11 +67,11 @@ python-iso639==2024.4.27
6767
# via -r ./base.in
6868
python-magic==0.4.27
6969
# via -r ./base.in
70-
rapidfuzz==3.9.0
70+
rapidfuzz==3.9.1
7171
# via -r ./base.in
7272
regex==2024.5.15
7373
# via nltk
74-
requests==2.31.0
74+
requests==2.32.1
7575
# via
7676
# -r ./base.in
7777
# unstructured-client
@@ -89,6 +89,7 @@ tqdm==4.66.4
8989
typing-extensions==4.11.0
9090
# via
9191
# -r ./base.in
92+
# emoji
9293
# typing-inspect
9394
# unstructured-client
9495
typing-inspect==0.9.0

requirements/build.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -66,7 +66,7 @@ pygments==2.18.0
6666
# sphinx-tabs
6767
pyyaml==6.0.1
6868
# via myst-parser
69-
requests==2.31.0
69+
requests==2.32.1
7070
# via
7171
# -c ./base.txt
7272
# sphinx

requirements/dev.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -315,7 +315,7 @@ referencing==0.35.1
315315
# jsonschema
316316
# jsonschema-specifications
317317
# jupyter-events
318-
requests==2.31.0
318+
requests==2.32.1
319319
# via
320320
# -c ./base.txt
321321
# -c ./test.txt

requirements/extra-paddleocr.txt

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -168,13 +168,13 @@ pytz==2024.1
168168
# via
169169
# flask-babel
170170
# pandas
171-
rapidfuzz==3.9.0
171+
rapidfuzz==3.9.1
172172
# via
173173
# -c ./base.txt
174174
# unstructured-paddleocr
175175
rarfile==4.2
176176
# via visualdl
177-
requests==2.31.0
177+
requests==2.32.1
178178
# via
179179
# -c ./base.txt
180180
# premailer

requirements/extra-pdf-image.txt

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -58,13 +58,13 @@ googleapis-common-protos==1.63.0
5858
# via
5959
# google-api-core
6060
# grpcio-status
61-
grpcio==1.63.0
61+
grpcio==1.64.0
6262
# via
6363
# google-api-core
6464
# grpcio-status
6565
grpcio-status==1.62.2
6666
# via google-api-core
67-
huggingface-hub==0.23.0
67+
huggingface-hub==0.23.1
6868
# via
6969
# timm
7070
# tokenizers
@@ -220,15 +220,15 @@ pyyaml==6.0.1
220220
# omegaconf
221221
# timm
222222
# transformers
223-
rapidfuzz==3.9.0
223+
rapidfuzz==3.9.1
224224
# via
225225
# -c ./base.txt
226226
# unstructured-inference
227227
regex==2024.5.15
228228
# via
229229
# -c ./base.txt
230230
# transformers
231-
requests==2.31.0
231+
requests==2.32.1
232232
# via
233233
# -c ./base.txt
234234
# google-api-core

requirements/huggingface.txt

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -27,7 +27,7 @@ fsspec==2024.5.0
2727
# -c ././deps/constraints.txt
2828
# huggingface-hub
2929
# torch
30-
huggingface-hub==0.23.0
30+
huggingface-hub==0.23.1
3131
# via
3232
# tokenizers
3333
# transformers
@@ -71,7 +71,7 @@ regex==2024.5.15
7171
# -c ./base.txt
7272
# sacremoses
7373
# transformers
74-
requests==2.31.0
74+
requests==2.32.1
7575
# via
7676
# -c ./base.txt
7777
# huggingface-hub

requirements/ingest/airtable.txt

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44
#
55
# pip-compile ./ingest/airtable.in
66
#
7-
annotated-types==0.6.0
7+
annotated-types==0.7.0
88
# via pydantic
99
certifi==2024.2.2
1010
# via
@@ -27,7 +27,7 @@ pydantic==2.7.1
2727
# via pyairtable
2828
pydantic-core==2.18.2
2929
# via pydantic
30-
requests==2.31.0
30+
requests==2.32.1
3131
# via
3232
# -c ./ingest/../base.txt
3333
# pyairtable

0 commit comments

Comments
 (0)