[planet-web/oscp] Force en_US.utf-8 on the container + land the missing encoding now that parseFragment supports it



commit adbe3ec33681b5053a61004d907b59362bbb9435
Author: Andrea Veri <averi redhat com>
Date:   Wed Jan 20 19:22:13 2021 +0100

    Force en_US.utf-8 on the container + land the missing encoding now that parseFragment supports it

 Dockerfile                              | 12 ++++++++++--
 patches/01_land_required_encoding.patch | 12 ++++++++++++
 2 files changed, 22 insertions(+), 2 deletions(-)
---
diff --git a/Dockerfile b/Dockerfile
index b90d02ae..8012a7ed 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -2,9 +2,15 @@ FROM debian:10-slim
 ARG DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get update && \
-    apt-get install -y --no-install-recommends planet-venus git nginx-light xsltproc patch && \
+    apt-get install -y --no-install-recommends planet-venus git nginx-light xsltproc patch locales && \
     apt-get clean && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 
+RUN sed -i -e 's/# en_US.UTF-8 UTF-8/en_US.UTF-8 UTF-8/' /etc/locale.gen && \
+    dpkg-reconfigure --frontend=noninteractive locales && \
+    update-locale LANG=en_US.UTF-8
+
+ENV LANG en_US.UTF-8
+
 RUN ln -sf /dev/stdout /var/log/nginx/access.log && \
     ln -sf /dev/stderr /var/log/nginx/error.log
 
@@ -15,8 +21,10 @@ RUN groupadd planet -g 1000510000 && useradd planet -g 1000510000 -u 1000510000
     chown -R 1000510000:100051000 /planet
 
 COPY patches/00_override_encoding_to_encoding.patch /planet/00_override_encoding_to_encoding.patch
+COPY patches/01_land_required_encoding.patch /planet/01_land_required_encoding.patch
 RUN cd /usr/lib/python2.7/dist-packages/planet && patch -p0 < /planet/00_override_encoding_to_encoding.patch 
&& \
-    rm /planet/00_override_encoding_to_encoding.patch
+    patch -p0 < /planet/01_land_required_encoding.patch && \
+    rm /planet/00_override_encoding_to_encoding.patch /planet/01_land_required_encoding.patch
 
 RUN mkdir -p /var/cache/planet-venus/theme/common && \
     cp -r /usr/share/planet-venus/theme/common/* /var/cache/planet-venus/theme/common/ && \
diff --git a/patches/01_land_required_encoding.patch b/patches/01_land_required_encoding.patch
new file mode 100644
index 00000000..3d4d7626
--- /dev/null
+++ b/patches/01_land_required_encoding.patch
@@ -0,0 +1,12 @@
+--- ./scrub.py.orig    2021-01-20 18:20:05.896444525 +0000
++++ ./scrub.py 2021-01-20 18:17:51.848544932 +0000
+@@ -141,7 +141,7 @@
+                 if not doc:
+                     from html5lib import html5parser, treebuilders
+                     p=html5parser.HTMLParser(tree=treebuilders.getTreeBuilder('dom'))
+-                    doc = p.parseFragment(node['value'])
++                    doc = p.parseFragment(node['value'], encoding='utf-8')
+
+                 from html5lib import treewalkers, serializer
+                 walker = treewalkers.getTreeWalker('dom')(doc)
+


[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]