Refine cleaning, keep license documents

Dockerfile

@@ -1,7 +1,21 @@
 FROM debian:jessie
 
+## Clean documentation in FROM image
+RUN find /usr/share/doc -depth \( -type f -o -type l \) ! -name copyright | xargs rm || true
+## Clean doc directories that are empty or only contain empty directories
+RUN while [ -n "$(find /usr/share/doc -depth -type d -empty -print -exec rmdir {} +)" ]; do :; done
+RUN rm -rf                              \
+        /usr/share/man/*                \
+        /usr/share/groff/*              \
+        /usr/share/info/*               \
+        /usr/share/lintian/*            \
+        /usr/share/linda/*              \
+        /var/cache/man/*                \
+        /usr/share/locale/*
+
 ## Set the apt source
 COPY sources.list /etc/apt/sources.list
+COPY dpkg_01_drop /etc/dpkg/dpkg.cfg.d/01_drop
 RUN apt-get clean && apt-get update
 
 ## Pre-install the fundamental packages
@@ -20,4 +34,4 @@ RUN apt-get -y purge                    \
 
 ## Clean up
 RUN apt-get clean -y; apt-get autoclean -y; apt-get autoremove -y
-RUN rm -rf /usr/share/doc/* /usr/share/locale/* /var/lib/apt/lists/* /tmp/*
+RUN rm -rf /var/lib/apt/lists/* /tmp/*

dpkg_01_drop

@@ -0,0 +1,22 @@
+## Drop unnecessary files
+## ref: https://wiki.ubuntu.com/ReducingDiskFootprint
+
+## Documentation
+path-exclude /usr/share/doc/*
+# we need to keep copyright files for legal reasons
+path-include /usr/share/doc/*/copyright
+path-exclude /usr/share/man/*
+path-exclude /usr/share/groff/*
+path-exclude /usr/share/info/*
+# lintian stuff is small, but really unnecessary
+path-exclude /usr/share/lintian/*
+path-exclude /usr/share/linda/*
+
+## Translations
+path-exclude /usr/share/locale/*
+
+## Landscape
+path-exclude /usr/share/pyshared/twisted/test*
+path-exclude /usr/lib/python*/dist-packages/twisted/test*
+path-exclude /usr/share/pyshared/twisted/*/test*
+path-exclude /usr/lib/python*/dist-packages/twisted/*/test*