rework how pdfs are created 2

Dockerfile

@@ -6,18 +6,21 @@ LABEL maintainer="inf_sfb1288@lists.uni-bielefeld.de"
 
 ENV LANG=C.UTF-8
 
-
+RUN mkdir /usr/share/man/man1/ # needed to install pdftk https://github.com/geerlingguy/ansible-role-java/issues/64
 RUN apt-get update \
  && apt-get install -y --no-install-recommends \
+      ca-certificates \
       imagemagick \
       python3.7 \
+      pdftk \
       zip
 
 
 RUN rm -rf /var/lib/apt/lists/*
-
+RUN rm -f /etc/ImageMagick-6/policy.xml
 
 COPY file-setup /usr/local/bin
+COPY policy.xml /etc/ImageMagick-6
 
 
 ENTRYPOINT ["file-setup"]

file-setup

@@ -28,22 +28,39 @@ def parse_arguments():
 def merge_images(input_dir, output_dir, output_file_base, zip):
     try:
         os.mkdir(output_dir)
-        tmp_dir_path = os.path.join(input_dir, 'tmp')
+        tmp_dir = os.path.join(input_dir, 'tmp')
-        os.mkdir(tmp_dir_path)
+        os.mkdir(tmp_dir)
     except FileExistsError:
         pass
+    try:
+        tmp_dir = os.path.join(input_dir, 'tmp')
+        os.mkdir(tmp_dir)
+    except FileExistsError:
+        pass
+    # Sort filenames into a list ordered with version flag -v
     cmd = 'ls -Q -v "{i}"/*.* > "{i}"/file_list.txt'.format(i=input_dir)
     subprocess.run(cmd, shell=True)
-    cmd = ('mogrify -compress LZW -format pdf ',
+    # Convert all image files into pdf files
-           + '-path @"{o}" "{i}"/file_list.txt').format(i=input_dir,
+    cmd = ('mogrify -compress LZW -format pdf '
-                                                        o=tmp_dir_path)
+           + '-path "{o}" @"{i}"/file_list.txt').format(i=input_dir,
+                                                        o=tmp_dir)
     subprocess.run(cmd, shell=True)
+    # remove image files
+    cmd = 'xargs rm <{i}/file_list.txt'.format(i=input_dir)
+    subprocess.run(cmd, shell=True)
+    # remove file list
     cmd = 'rm "{i}"/file_list.txt'.format(i=input_dir)
     subprocess.run(cmd, shell=True)
-    cmd = ('pdftk "{tmp_dir_path}"/*.pdf cat ',
+    # join all pdfs into one pdf
-           + 'output "{o}"/"{ofb}".pdf').format(i=tmp_dir_path,
+    cmd = ('pdftk "{tmp_i}"/*.pdf cat '
+           + 'output "{o}"/"{ofb}".pdf').format(tmp_i=tmp_dir,
                                                 o=output_dir,
                                                 ofb=output_file_base)
+    subprocess.run(cmd, shell=True)
+    # remove single pdf files
+    cmd = 'rm -fr {i}/tmp'.format(i=input_dir)
+    subprocess.run(cmd, shell=True)
+    # zip stuff
     if zip is not None:
         # Remove .zip file extension if provided
         if zip.endswith('.zip'):

policy.xml

@@ -0,0 +1,87 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE policymap [
+<!ELEMENT policymap (policy)+>
+<!ELEMENT policy (#PCDATA)>
+<!ATTLIST policy domain (delegate|coder|filter|path|resource) #IMPLIED>
+<!ATTLIST policy name CDATA #IMPLIED>
+<!ATTLIST policy rights CDATA #IMPLIED>
+<!ATTLIST policy pattern CDATA #IMPLIED>
+<!ATTLIST policy value CDATA #IMPLIED>
+]>
+<!--
+  Configure ImageMagick policies.
+
+  Domains include system, delegate, coder, filter, path, or resource.
+
+  Rights include none, read, write, and execute.  Use | to combine them,
+  for example: "read | write" to permit read from, or write to, a path.
+
+  Use a glob expression as a pattern.
+
+  Suppose we do not want users to process MPEG video images:
+
+    <policy domain="delegate" rights="none" pattern="mpeg:decode" />
+
+  Here we do not want users reading images from HTTP:
+
+    <policy domain="coder" rights="none" pattern="HTTP" />
+
+  Lets prevent users from executing any image filters:
+
+    <policy domain="filter" rights="none" pattern="*" />
+
+  The /repository file system is restricted to read only.  We use a glob
+  expression to match all paths that start with /repository:
+
+    <policy domain="path" rights="read" pattern="/repository/*" />
+
+  Let's prevent possible exploits by removing the right to use indirect reads.
+
+    <policy domain="path" rights="none" pattern="@*" />
+
+  Any large image is cached to disk rather than memory:
+
+    <policy domain="resource" name="area" value="1GB"/>
+
+  Define arguments for the memory, map, area, width, height, and disk resources
+  with SI prefixes (.e.g 100MB).  In addition, resource policies are maximums
+  for each instance of ImageMagick (e.g. policy memory limit 1GB, -limit 2GB
+  exceeds policy maximum so memory limit is 1GB).
+-->
+<policymap>
+  <!-- <policy domain="system" name="shred" value="2"/> -->
+  <!-- <policy domain="system" name="precision" value="6"/> -->
+  <!-- <policy domain="system" name="memory-map" value="anonymous"/> -->
+  <!-- <policy domain="system" name="max-memory-request" value="256MiB"/> -->
+  <!-- <policy domain="resource" name="temporary-path" value="/tmp"/> -->
+  <policy domain="resource" name="memory" value="256MiB"/>
+  <policy domain="resource" name="map" value="512MiB"/>
+  <policy domain="resource" name="width" value="16KP"/>
+  <policy domain="resource" name="height" value="16KP"/>
+  <!-- <policy domain="resource" name="list-length" value="128"/> -->
+  <policy domain="resource" name="area" value="128MB"/>
+  <policy domain="resource" name="disk" value="1GiB"/>
+  <!-- <policy domain="resource" name="file" value="768"/> -->
+  <!-- <policy domain="resource" name="thread" value="4"/> -->
+  <!-- <policy domain="resource" name="throttle" value="0"/> -->
+  <!-- <policy domain="resource" name="time" value="3600"/> -->
+  <!-- <policy domain="coder" rights="none" pattern="MVG" /> -->
+  <policy domain="module" rights="read|write" pattern="{PS,PDF,XPS}" />
+  <!-- <policy domain="delegate" rights="none" pattern="HTTPS" /> -->
+  <!-- <policy domain="path" rights="none" pattern="@*" /> -->
+  <!-- <policy domain="cache" name="memory-map" value="anonymous"/> -->
+  <!-- <policy domain="cache" name="synchronize" value="True"/> -->
+  <!-- <policy domain="cache" name="shared-secret" value="passphrase" stealth="true"/> -->
+  <!-- <policy domain="system" name="pixel-cache-memory" value="anonymous"/> -->
+  <!-- <policy domain="system" name="shred" value="2"/> -->
+  <!-- <policy domain="system" name="precision" value="6"/> -->
+  <!-- not needed due to the need to use explicitly by mvg: -->
+  <!-- <policy domain="delegate" rights="none" pattern="MVG" /> -->
+  <!-- use curl -->
+  <policy domain="delegate" rights="none" pattern="URL" />
+  <policy domain="delegate" rights="none" pattern="HTTPS" />
+  <policy domain="delegate" rights="none" pattern="HTTP" />
+  <!-- in order to avoid to get image with password text -->
+  <!-- <policy domain="path" rights="none" pattern="@*"/> -->
+</policymap>
+

wrapper/file-setup

@@ -14,6 +14,7 @@ GID = str(os.getgid())
 parser = ArgumentParser(add_help=False)
 parser.add_argument('-i')
 parser.add_argument('-o')
+parser.add_argument('-f')
 args, remaining_args = parser.parse_known_args()
 
 cmd = ['docker', 'run', '--rm', '-it', '-u', '{}:{}'.format(UID, GID)]
@@ -25,5 +26,4 @@ if args.i is not None:
     remaining_args.insert(0, CONTAINER_INPUT_DIR)
 cmd.append(CONTAINER_IMAGE)
 cmd += remaining_args
-
 subprocess.run(cmd)