RED-5277 update build-script EXPERIMENTAL

.dvc/config

@@ -1,8 +1,6 @@
 [core]
-    remote = azure_remote
+    remote = vector
     autostage = true
 ['remote "vector"']
     url = ssh://vector.iqser.com/research/image-prediction/
     port = 22
-['remote "azure_remote"']
-    url = azure://image-classification-dvc/

.gitignore

@@ -1,8 +1,7 @@
 .vscode/
 *.h5
-*venv
+/venv/
 .idea/
-src/data
 
 !.gitignore
 *.project
@@ -173,4 +172,4 @@ fabric.properties
 # https://plugins.jetbrains.com/plugin/12206-codestream
 .idea/codestream.xml
 
-# End of https://www.toptal.com/developers/gitignore/api/linux,pycharm
+# End of https://www.toptal.com/developers/gitignore/api/linux,pycharm

.gitlab-ci.yml

@@ -1,51 +0,0 @@
-include:
-  - project: "Gitlab/gitlab"
-    ref: main
-    file: "/ci-templates/research/dvc.gitlab-ci.yml"
-  - project: "Gitlab/gitlab"
-    ref: main
-    file: "/ci-templates/research/versioning-build-test-release.gitlab-ci.yml"
-
-variables:
-  NEXUS_PROJECT_DIR: red
-  IMAGENAME: "${CI_PROJECT_NAME}"
-  INTEGRATION_TEST_FILE: "${CI_PROJECT_ID}.pdf"
-  FF_USE_FASTZIP: "true" # enable fastzip - a faster zip implementation that also supports level configuration.
-  ARTIFACT_COMPRESSION_LEVEL: default # can also be set to fastest, fast, slow and slowest. If just enabling fastzip is not enough try setting this to fastest or fast.
-  CACHE_COMPRESSION_LEVEL: default # same as above, but for caches
-  # TRANSFER_METER_FREQUENCY: 5s # will display transfer progress every 5 seconds for artifacts and remote caches. For debugging purposes.
-
-stages:
-  - data
-  - setup
-  - tests
-  - sonarqube
-  - versioning
-  - build
-  - integration-tests
-  - release
-
-docker-build:
-  extends: .docker-build
-  needs:
-    - job: dvc-pull
-      artifacts: true
-    - !reference [.needs-versioning, needs] # leave this line as is
-  
-###################
-# INTEGRATION TESTS
-trigger-integration-tests:
-  extends: .integration-tests
-  # ADD THE MODEL BUILD WHICH SHOULD TRIGGER THE INTEGRATION TESTS
-  # needs:
-  #   - job: docker-build::model_name
-  #     artifacts: true
-  rules:
-    - when: never
-
-#########
-# RELEASE
-release:
-  extends: .release
-  needs:
-    - !reference [.needs-versioning, needs] # leave this line as is

.gitmodules

@@ -0,0 +1,6 @@
+[submodule "incl/pyinfra"]
+	path = incl/pyinfra
+	url = ssh://git@git.iqser.com:2222/rr/pyinfra.git
+[submodule "incl/pdf2image"]
+	path = incl/pdf2image
+	url = ssh://git@git.iqser.com:2222/rr/pdf2image.git

.python-version

@@ -1 +0,0 @@
-3.10

Dockerfile

@@ -1,73 +1,27 @@
-FROM python:3.10-slim AS builder
+FROM image-prediction-base
 
-ARG GITLAB_USER
-ARG GITLAB_ACCESS_TOKEN
+WORKDIR /app/service
 
-ARG PYPI_REGISTRY_RESEARCH=https://gitlab.knecon.com/api/v4/groups/19/-/packages/pypi
-ARG POETRY_SOURCE_REF_RESEARCH=gitlab-research
+COPY src src
+COPY incl/pyinfra incl/pyinfra
+COPY incl/pdf2image incl/pdf2image
+COPY data data
+COPY image_prediction image_prediction
+COPY setup.py setup.py
+COPY requirements.txt requirements.txt
+COPY config.yaml config.yaml
+COPY banner.txt banner.txt
 
-ARG PYPI_REGISTRY_RED=https://gitlab.knecon.com/api/v4/groups/12/-/packages/pypi
-ARG POETRY_SOURCE_REF_RED=gitlab-red
+# Install dependencies differing from base image.
+RUN python3 -m pip install -r requirements.txt
+RUN python3 -m pip install -r incl/pyinfra/requirements.txt
+RUN python3 -m pip install -r incl/pdf2image/requirements.txt
 
-ARG PYPI_REGISTRY_FFORESIGHT=https://gitlab.knecon.com/api/v4/groups/269/-/packages/pypi
-ARG POETRY_SOURCE_REF_FFORESIGHT=gitlab-fforesight
-
-ARG VERSION=dev
-
-LABEL maintainer="Research <research@knecon.com>"
-LABEL version="${VERSION}"
-
-WORKDIR /app
-
-###########
-# ENV SETUP
-ENV PYTHONDONTWRITEBYTECODE=true
-ENV PYTHONUNBUFFERED=true
-ENV POETRY_HOME=/opt/poetry
-ENV PATH="$POETRY_HOME/bin:$PATH"
-
-RUN apt-get update && \
-    apt-get install -y curl git bash build-essential libffi-dev libssl-dev && \
-    apt-get clean && \
-    rm -rf /var/lib/apt/lists/*
-
-RUN curl -sSL https://install.python-poetry.org | python3 -
-RUN poetry --version
-
-COPY pyproject.toml poetry.lock ./
-
-RUN poetry config virtualenvs.create true && \
-    poetry config virtualenvs.in-project true && \
-    poetry config installer.max-workers 10 && \
-    poetry config repositories.${POETRY_SOURCE_REF_RESEARCH} ${PYPI_REGISTRY_RESEARCH} && \
-    poetry config http-basic.${POETRY_SOURCE_REF_RESEARCH} ${GITLAB_USER} ${GITLAB_ACCESS_TOKEN} && \
-    poetry config repositories.${POETRY_SOURCE_REF_RED} ${PYPI_REGISTRY_RED} && \
-    poetry config http-basic.${POETRY_SOURCE_REF_RED} ${GITLAB_USER} ${GITLAB_ACCESS_TOKEN} && \
-    poetry config repositories.${POETRY_SOURCE_REF_FFORESIGHT} ${PYPI_REGISTRY_FFORESIGHT} && \
-    poetry config http-basic.${POETRY_SOURCE_REF_FFORESIGHT} ${GITLAB_USER} ${GITLAB_ACCESS_TOKEN} && \
-    poetry install --without=dev -vv --no-interaction --no-root
-
-###############
-# WORKING IMAGE
-FROM python:3.10-slim
-
-WORKDIR /app
-
-# COPY SOURCE CODE FROM BUILDER IMAGE
-COPY --from=builder /app /app
-# COPY BILL OF MATERIALS (BOM)
-COPY bom.json /bom.json
-
-ENV PATH="/app/.venv/bin:$PATH"
-
-###################
-# COPY SOURCE CODE
-COPY ./src ./src
-COPY ./config ./config
-COPY ./data ./data
-COPY banner.txt ./
+RUN python3 -m pip install -e .
+RUN python3 -m pip install -e incl/pyinfra
+RUN python3 -m pip install -e incl/pdf2image
 
 EXPOSE 5000
 EXPOSE 8080
 
-CMD [ "python", "src/serve.py"]
+CMD ["python3", "src/serve.py"]

Dockerfile_base

@@ -0,0 +1,25 @@
+FROM python:3.8 as builder1
+
+# Use a virtual environment.
+RUN python -m venv /app/venv
+ENV PATH="/app/venv/bin:$PATH"
+
+# Upgrade pip.
+RUN python -m pip install --upgrade pip
+
+# Make a directory for the service files and copy the service repo into the container.
+WORKDIR /app/service
+COPY ./requirements.txt ./requirements.txt
+
+# Install dependencies.
+RUN python3 -m pip install -r requirements.txt
+
+# Make a new container and copy all relevant files over to filter out temporary files
+# produced during setup to reduce the final container's size.
+FROM python:3.8
+
+WORKDIR /app/
+COPY --from=builder1  /app .
+ENV PATH="/app/venv/bin:$PATH"
+
+WORKDIR /app/service

Dockerfile_tests

@@ -1,40 +1,28 @@
-FROM python:3.10
+ARG BASE_ROOT="nexus.iqser.com:5001/red/"
+ARG VERSION_TAG="dev"
 
-ARG USERNAME
-ARG TOKEN
-ARG PYPI_REGISTRY_RESEARCH=https://gitlab.knecon.com/api/v4/groups/19/-/packages/pypi
-ARG POETRY_SOURCE_REF_RESEARCH=gitlab-research
-ARG PYPI_REGISTRY_RED=https://gitlab.knecon.com/api/v4/groups/12/-/packages/pypi
-ARG POETRY_SOURCE_REF_RED=gitlab-red
-ARG VERSION=dev
+FROM ${BASE_ROOT}image-prediction:${VERSION_TAG}
 
-LABEL maintainer="Research <research@knecon.com>"
-LABEL version="${VERSION}"
+WORKDIR /app/service
 
-WORKDIR /app
+COPY src src
+COPY incl/pyinfra incl/pyinfra
+COPY incl/pdf2image incl/pdf2image
+COPY data data
+COPY image_prediction image_prediction
+COPY setup.py setup.py
+COPY requirements.txt requirements.txt
+COPY config.yaml config.yaml
+COPY banner.txt banner.txt
 
-ENV PYTHONUNBUFFERED=true
-ENV POETRY_HOME=/opt/poetry
-ENV PATH="$POETRY_HOME/bin:$PATH"
+# Install module & dependencies
+RUN python3 -m pip install -r requirements.txt
+RUN python3 -m pip install -r incl/pyinfra/requirements.txt
+RUN python3 -m pip install -r incl/pdf2image/requirements.txt
 
-RUN curl -sSL https://install.python-poetry.org | python3 -
-
-COPY ./data ./data
-COPY ./test ./test
-COPY ./config ./config
-COPY ./src ./src
-COPY pyproject.toml poetry.lock banner.txt config.yaml./
-
-RUN poetry config virtualenvs.create false && \
-    poetry config installer.max-workers 10 && \
-    poetry config repositories.${POETRY_SOURCE_REF_RESEARCH} ${PYPI_REGISTRY_RESEARCH} && \
-    poetry config http-basic.${POETRY_SOURCE_REF_RESEARCH} ${USERNAME} ${TOKEN} && \
-    poetry config repositories.${POETRY_SOURCE_REF_RED} ${PYPI_REGISTRY_RED} && \
-    poetry config http-basic.${POETRY_SOURCE_REF_RED} ${USERNAME} ${TOKEN} && \
-    poetry install --without=dev -vv --no-interaction --no-root
-
-EXPOSE 5000
-EXPOSE 8080
+RUN python3 -m pip install -e .
+RUN python3 -m pip install -e incl/pyinfra
+RUN python3 -m pip install -e incl/pdf2image
 
 RUN apt update --yes
 RUN apt install vim --yes

README.md

@@ -2,11 +2,8 @@
 
 Build base image
 ```bash
-docker build -t image-classification-image --progress=plain --no-cache \
-    -f Dockerfile \
-    --build-arg USERNAME=$GITLAB_USER \
-    --build-arg TOKEN=$GITLAB_ACCESS_TOKEN \
-    .
+docker build -f Dockerfile_base -t image-prediction-base .
+docker build -f Dockerfile -t image-prediction .
 ```
 
 ### Usage

bamboo-specs/pom.xml

@@ -0,0 +1,40 @@
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+  <modelVersion>4.0.0</modelVersion>
+
+  <parent>
+    <groupId>com.atlassian.bamboo</groupId>
+    <artifactId>bamboo-specs-parent</artifactId>
+    <version>7.1.2</version>
+    <relativePath/>
+  </parent>
+
+  <artifactId>bamboo-specs</artifactId>
+  <version>1.0.0-SNAPSHOT</version>
+  <packaging>jar</packaging>
+
+  <properties>
+    <sonar.skip>true</sonar.skip>
+  </properties>
+
+  <dependencies>
+    <dependency>
+      <groupId>com.atlassian.bamboo</groupId>
+      <artifactId>bamboo-specs-api</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>com.atlassian.bamboo</groupId>
+      <artifactId>bamboo-specs</artifactId>
+    </dependency>
+
+    <!-- Test dependencies -->
+    <dependency>
+      <groupId>junit</groupId>
+      <artifactId>junit</artifactId>
+      <scope>test</scope>
+    </dependency>
+  </dependencies>
+
+  <!-- run 'mvn test' to perform offline validation of the plan -->
+  <!-- run 'mvn -Ppublish-specs' to upload the plan to your Bamboo server -->
+</project>

bamboo-specs/src/main/java/buildjob/PlanSpec.java

@@ -0,0 +1,180 @@
+package buildjob;
+
+import static com.atlassian.bamboo.specs.builders.task.TestParserTask.createJUnitParserTask;
+
+import java.time.LocalTime;
+
+import com.atlassian.bamboo.specs.api.BambooSpec;
+import com.atlassian.bamboo.specs.api.builders.BambooKey;
+import com.atlassian.bamboo.specs.api.builders.docker.DockerConfiguration;
+import com.atlassian.bamboo.specs.api.builders.permission.PermissionType;
+import com.atlassian.bamboo.specs.api.builders.permission.Permissions;
+import com.atlassian.bamboo.specs.api.builders.permission.PlanPermissions;
+import com.atlassian.bamboo.specs.api.builders.plan.Job;
+import com.atlassian.bamboo.specs.api.builders.plan.Plan;
+import com.atlassian.bamboo.specs.api.builders.plan.PlanIdentifier;
+import com.atlassian.bamboo.specs.api.builders.plan.Stage;
+import com.atlassian.bamboo.specs.api.builders.plan.branches.BranchCleanup;
+import com.atlassian.bamboo.specs.api.builders.plan.branches.PlanBranchManagement;
+import com.atlassian.bamboo.specs.api.builders.project.Project;
+import com.atlassian.bamboo.specs.builders.task.CheckoutItem;
+import com.atlassian.bamboo.specs.builders.task.InjectVariablesTask;
+import com.atlassian.bamboo.specs.builders.task.ScriptTask;
+import com.atlassian.bamboo.specs.builders.task.VcsCheckoutTask;
+import com.atlassian.bamboo.specs.builders.task.CleanWorkingDirectoryTask;
+import com.atlassian.bamboo.specs.builders.task.VcsTagTask;
+import com.atlassian.bamboo.specs.builders.trigger.BitbucketServerTrigger;
+import com.atlassian.bamboo.specs.builders.trigger.ScheduledTrigger;
+import com.atlassian.bamboo.specs.model.task.InjectVariablesScope;
+import com.atlassian.bamboo.specs.api.builders.Variable;
+import com.atlassian.bamboo.specs.util.BambooServer;
+import com.atlassian.bamboo.specs.builders.task.ScriptTask;
+import com.atlassian.bamboo.specs.model.task.ScriptTaskProperties.Location;
+
+/**
+ * Plan configuration for Bamboo.
+ * Learn more on: <a href="https://confluence.atlassian.com/display/BAMBOO/Bamboo+Specs">https://confluence.atlassian.com/display/BAMBOO/Bamboo+Specs</a>
+ */
+@BambooSpec
+public class PlanSpec {
+
+    private static final String SERVICE_NAME = "image-prediction";
+    private static final String SERVICE_NAME_BASE = "image-prediction-base";
+
+    private static final String SERVICE_KEY = SERVICE_NAME.toUpperCase().replaceAll("-","").replaceAll("_","");
+
+    /**
+     * Run main to publish plan on Bamboo
+     */
+    public static void main(final String[] args) throws Exception {
+        //By default credentials are read from the '.credentials' file.
+        BambooServer bambooServer = new BambooServer("http://localhost:8085");
+
+        Plan plan = new PlanSpec().createDockerBuildPlan();
+        bambooServer.publish(plan);
+        PlanPermissions planPermission = new PlanSpec().createPlanPermission(plan.getIdentifier());
+        bambooServer.publish(planPermission);
+
+        Plan secPlan = new PlanSpec().createSecBuild();
+        bambooServer.publish(secPlan);
+        PlanPermissions secPlanPermission = new PlanSpec().createPlanPermission(secPlan.getIdentifier());
+        bambooServer.publish(secPlanPermission);
+    }
+
+    private PlanPermissions createPlanPermission(PlanIdentifier planIdentifier) {
+        Permissions permission = new Permissions()
+                .userPermissions("atlbamboo", PermissionType.EDIT, PermissionType.VIEW, PermissionType.ADMIN, PermissionType.CLONE, PermissionType.BUILD)
+                .groupPermissions("research", PermissionType.EDIT, PermissionType.VIEW, PermissionType.CLONE, PermissionType.BUILD)
+                .groupPermissions("Development", PermissionType.EDIT, PermissionType.VIEW, PermissionType.CLONE, PermissionType.BUILD)
+                .groupPermissions("QA", PermissionType.EDIT, PermissionType.VIEW, PermissionType.CLONE, PermissionType.BUILD)
+                .loggedInUserPermissions(PermissionType.VIEW)
+                .anonymousUserPermissionView();
+        return new PlanPermissions(planIdentifier.getProjectKey(), planIdentifier.getPlanKey()).permissions(permission);
+    }
+
+    private Project project() {
+        return new Project()
+                .name("RED")
+                .key(new BambooKey("RED"));
+    }
+
+    public Plan createDockerBuildPlan() {
+    return new Plan(
+            project(),
+            SERVICE_NAME, new BambooKey(SERVICE_KEY))
+            .description("Docker build for image-prediction.")
+            .stages(
+            new Stage("Build Stage")
+              .jobs(
+                new Job("Build Job", new BambooKey("BUILD"))
+                  .tasks(
+                    new CleanWorkingDirectoryTask()
+                        .description("Clean working directory.")
+                        .enabled(true),
+                    new VcsCheckoutTask()
+                        .description("Checkout default repository.")
+                        .checkoutItems(new CheckoutItem().defaultRepository()),
+                    new ScriptTask()
+                        .description("Set config and keys.")
+                        .location(Location.FILE)
+                        .fileFromPath("bamboo-specs/src/main/resources/scripts/key-prepare.sh"),
+                    new ScriptTask()
+                        .description("Build Docker container.")
+                        .location(Location.FILE)
+                        .fileFromPath("bamboo-specs/src/main/resources/scripts/docker-build.sh")
+                        .argument(SERVICE_NAME + " " + SERVICE_NAME_BASE),
+                    new InjectVariablesTask()
+                        .description("Inject git tag.")
+                        .path("git.tag")
+                        .namespace("g")
+                        .scope(InjectVariablesScope.LOCAL),
+                    new VcsTagTask()
+                        .description("${bamboo.g.gitTag}")
+                        .tagName("${bamboo.g.gitTag}")
+                        .defaultRepository())
+                .dockerConfiguration(
+                    new DockerConfiguration()
+                      .image("nexus.iqser.com:5001/infra/release_build:4.5.0")
+                      .volume("/var/run/docker.sock", "/var/run/docker.sock")),
+                new Job("Licence Job", new BambooKey("LICENCE"))
+                  .enabled(false)
+                  .tasks(
+                    new VcsCheckoutTask()
+                        .description("Checkout default repository.")
+                        .checkoutItems(new CheckoutItem().defaultRepository()),
+                    new ScriptTask()
+                        .description("Build licence.")
+                        .location(Location.FILE)
+                        .fileFromPath("bamboo-specs/src/main/resources/scripts/create-licence.sh"))
+                  .dockerConfiguration(
+                    new DockerConfiguration()
+                        .image("nexus.iqser.com:5001/infra/maven:3.6.2-jdk-13-3.0.0")
+                        .volume("/etc/maven/settings.xml", "/usr/share/maven/ref/settings.xml")
+                        .volume("/var/run/docker.sock", "/var/run/docker.sock"))))
+            .linkedRepositories("RR / " + SERVICE_NAME)
+            .linkedRepositories("RR / redai_image")
+            .triggers(
+                    new BitbucketServerTrigger())
+            .planBranchManagement(
+                new PlanBranchManagement()
+                    .createForVcsBranch()
+                    .delete(
+                        new BranchCleanup()
+                            .whenInactiveInRepositoryAfterDays(14))
+                    .notificationForCommitters());
+    }
+
+    public Plan createSecBuild() {
+        return new Plan(project(), SERVICE_NAME + "-Sec", new BambooKey(SERVICE_KEY + "SEC")).description("Security Analysis Plan")
+                .stages(new Stage("Default Stage").jobs(
+                    new Job("Sonar Job", new BambooKey("SONAR"))
+                      .tasks(
+                        new CleanWorkingDirectoryTask()
+                            .description("Clean working directory.")
+                            .enabled(true),
+                        new VcsCheckoutTask()
+                            .description("Checkout default repository.")
+                            .checkoutItems(new CheckoutItem().defaultRepository()),
+                        new ScriptTask()
+                            .description("Set config and keys.")
+                            .location(Location.FILE)
+                            .fileFromPath("bamboo-specs/src/main/resources/scripts/key-prepare.sh"),
+                        new ScriptTask()
+                            .description("Run Sonarqube scan.")
+                            .location(Location.FILE)
+                            .fileFromPath("bamboo-specs/src/main/resources/scripts/sonar-scan.sh")
+                            .argument(SERVICE_NAME))
+                      .dockerConfiguration(
+                          new DockerConfiguration()
+                            .image("nexus.iqser.com:5001/infra/release_build:4.2.0")
+                            .volume("/var/run/docker.sock", "/var/run/docker.sock"))))
+                .linkedRepositories("RR / " + SERVICE_NAME)
+                .triggers(
+                    new ScheduledTrigger()
+                        .scheduleOnceDaily(LocalTime.of(23, 00)))
+                .planBranchManagement(
+                    new PlanBranchManagement()
+                        .createForVcsBranchMatching("release.*")
+                        .notificationForCommitters());
+    }
+}

bamboo-specs/src/main/resources/scripts/create-licence.sh

@@ -0,0 +1,19 @@
+#!/bin/bash
+set -e
+
+if [[ \"${bamboo_version_tag}\" != \"dev\" ]]
+then
+    ${bamboo_capability_system_builder_mvn3_Maven_3}/bin/mvn \
+                    -f ${bamboo_build_working_directory}/pom.xml \
+                    versions:set  \
+                    -DnewVersion=${bamboo_version_tag}
+
+    ${bamboo_capability_system_builder_mvn3_Maven_3}/bin/mvn \
+                    -f ${bamboo_build_working_directory}/pom.xml \
+                    -B clean deploy \
+                    -e -DdeployAtEnd=true \
+                    -Dmaven.wagon.http.ssl.insecure=true \
+                    -Dmaven.wagon.http.ssl.allowall=true \
+                    -Dmaven.wagon.http.ssl.ignore.validity.dates=true \
+                    -DaltDeploymentRepository=iqser_release::default::https://nexus.iqser.com/repository/gin4-platform-releases
+fi

bamboo-specs/src/main/resources/scripts/docker-build.sh

@@ -0,0 +1,60 @@
+#!/bin/bash
+set -e
+
+SERVICE_NAME=$1
+SERVICE_NAME_BASE=$2
+if [[ "$bamboo_planRepository_branchName" == "master" ]]
+then
+    branchVersion=$(cat version.yaml | grep -Eo "version: .*" | sed -s 's|version: \(.*\)\..*\..*|\1|g')
+    latestVersion=$( semver $(git tag -l "${branchVersion}.*" ) | tail -n1 )
+    newVersion="$(semver $latestVersion -p -i minor)"
+    echo "new release on master with version $newVersion"
+elif [[ "$bamboo_planRepository_branchName" == release* ]]
+then
+#    branchVersion=$(echo $bamboo_planRepository_branchName | sed -s 's|release\/\([0-9]\+\.[0-9]\+\)\.x|\1|')
+#    latestVersion=$( semver $(git tag -l "${branchVersion}.*" ) | tail -n1 )
+#    newVersion="$(semver $latestVersion -p -i patch)"
+# FIXME: obviously not the best solution
+    newVersion="1.16.1"
+    echo "new release on $bamboo_planRepository_branchName with version $newVersion"
+elif [[ "${bamboo_version_tag}" != "dev" ]]
+then
+    newVersion="${bamboo_version_tag}"
+    echo "new special version bild with $newVersion"
+else
+    newVersion="${bamboo_planRepository_1_branch}_${bamboo_buildNumber}"
+    echo "gitTag=${newVersion}" > git.tag
+    dev_tag="dev"
+    echo "dev build with tag $dev_tag"
+    python3 -m venv build_venv
+    source build_venv/bin/activate
+    python3 -m pip install --upgrade pip
+
+    pip install dvc
+    pip install 'dvc[ssh]'
+    dvc pull
+
+    echo "index-url = https://${bamboo_nexus_user}:${bamboo_nexus_password}@nexus.iqser.com/repository/python-combind/simple" >> pip.conf
+    echo "${bamboo_nexus_password}" | docker login --username "${bamboo_nexus_user}" --password-stdin nexus.iqser.com:5001
+    docker build -f Dockerfile_base -t $SERVICE_NAME_BASE .
+    docker build -f Dockerfile  -t nexus.iqser.com:5001/red/$SERVICE_NAME:$dev_tag .
+    docker push nexus.iqser.com:5001/red/$SERVICE_NAME:$dev_tag
+    exit 0
+fi
+
+echo "gitTag=${newVersion}" > git.tag
+
+python3 -m venv build_venv
+source build_venv/bin/activate
+python3 -m pip install --upgrade pip
+
+pip install dvc
+pip install 'dvc[ssh]'
+echo "Pulling dvc data"
+dvc pull
+
+echo "index-url = https://${bamboo_nexus_user}:${bamboo_nexus_password}@nexus.iqser.com/repository/python-combind/simple" >> pip.conf
+docker build -f Dockerfile_base -t $SERVICE_NAME_BASE .
+docker build -f Dockerfile  -t nexus.iqser.com:5001/red/$SERVICE_NAME:${newVersion} .
+echo "${bamboo_nexus_password}" | docker login --username "${bamboo_nexus_user}" --password-stdin nexus.iqser.com:5001
+docker push nexus.iqser.com:5001/red/$SERVICE_NAME:${newVersion}

bamboo-specs/src/main/resources/scripts/key-prepare.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+set -e
+
+mkdir -p ~/.ssh
+echo "${bamboo_agent_ssh}" | base64 -d >> ~/.ssh/id_rsa
+echo "host vector.iqser.com" > ~/.ssh/config
+echo "    user bamboo-agent" >> ~/.ssh/config
+chmod 600 ~/.ssh/config ~/.ssh/id_rsa

bamboo-specs/src/main/resources/scripts/sonar-scan.sh

@@ -0,0 +1,57 @@
+#!/bin/bash
+set -e
+
+export JAVA_HOME=/usr/bin/sonar-scanner/jre
+
+python3 -m venv build_venv
+source build_venv/bin/activate
+python3 -m pip install --upgrade pip
+python3 -m pip install dependency-check
+python3 -m pip install coverage
+
+echo "coverage report generation"
+
+bash run_tests.sh
+
+if [ ! -f reports/coverage.xml ]
+then
+  exit 1
+fi
+
+SERVICE_NAME=$1
+
+echo "dependency-check:aggregate"
+mkdir -p reports
+dependency-check --enableExperimental -f JSON -f HTML -f XML \
+  --disableAssembly -s . -o reports --project $SERVICE_NAME --exclude ".git/**" --exclude "venv/**" \
+  --exclude "build_venv/**" --exclude "**/__pycache__/**" --exclude "bamboo-specs/**"
+
+if [[ -z "${bamboo_repository_pr_key}" ]]
+then
+    echo "Sonar Scan for branch: ${bamboo_planRepository_1_branch}"
+    /usr/bin/sonar-scanner/bin/sonar-scanner \
+      -Dsonar.projectKey=RED_$SERVICE_NAME \
+      -Dsonar.sources=image_prediction \
+      -Dsonar.host.url=https://sonarqube.iqser.com \
+      -Dsonar.login=${bamboo_sonarqube_api_token_secret} \
+      -Dsonar.branch.name=${bamboo_planRepository_1_branch} \
+      -Dsonar.dependencyCheck.jsonReportPath=reports/dependency-check-report.json \
+      -Dsonar.dependencyCheck.xmlReportPath=reports/dependency-check-report.xml \
+      -Dsonar.dependencyCheck.htmlReportPath=reports/dependency-check-report.html \
+      -Dsonar.python.coverage.reportPaths=reports/coverage.xml
+ 
+else
+    echo "Sonar Scan for PR with key1: ${bamboo_repository_pr_key}"
+    /usr/bin/sonar-scanner/bin/sonar-scanner \
+      -Dsonar.projectKey=RED_$SERVICE_NAME \
+      -Dsonar.sources=image_prediction \
+      -Dsonar.host.url=https://sonarqube.iqser.com \
+      -Dsonar.login=${bamboo_sonarqube_api_token_secret} \
+      -Dsonar.pullrequest.key=${bamboo_repository_pr_key} \
+      -Dsonar.pullrequest.branch=${bamboo_repository_pr_sourceBranch} \
+      -Dsonar.pullrequest.base=${bamboo_repository_pr_targetBranch} \
+      -Dsonar.dependencyCheck.jsonReportPath=reports/dependency-check-report.json \
+      -Dsonar.dependencyCheck.xmlReportPath=reports/dependency-check-report.xml \
+      -Dsonar.dependencyCheck.htmlReportPath=reports/dependency-check-report.html \
+      -Dsonar.python.coverage.reportPaths=reports/coverage.xml
+fi

bamboo-specs/src/test/java/buildjob/PlanSpecTest.java

@@ -0,0 +1,21 @@
+package buildjob;
+
+
+import com.atlassian.bamboo.specs.api.builders.plan.Plan;
+import com.atlassian.bamboo.specs.api.exceptions.PropertiesValidationException;
+import com.atlassian.bamboo.specs.api.util.EntityPropertiesBuilders;
+import org.junit.Test;
+
+public class PlanSpecTest {
+    @Test
+    public void checkYourPlanOffline() throws PropertiesValidationException {
+        Plan plan = new PlanSpec().createDockerBuildPlan();
+        EntityPropertiesBuilders.build(plan);
+    }
+
+    @Test
+    public void checkYourSecPlanOffline() throws PropertiesValidationException {
+        Plan secPlan = new PlanSpec().createSecBuild();
+        EntityPropertiesBuilders.build(secPlan);
+    }
+}

config.yaml

@@ -0,0 +1,26 @@
+webserver:
+  host: $SERVER_HOST|"127.0.0.1"  # webserver address
+  port: $SERVER_PORT|5000  # webserver port
+
+service:
+  logging_level: $LOGGING_LEVEL_ROOT|INFO  # Logging level for service logger
+  verbose: $VERBOSE|True  # Service prints document processing progress to stdout
+  batch_size: $BATCH_SIZE|16  # Number of images in memory simultaneously
+  mlflow_run_id: $MLFLOW_RUN_ID|fabfb1f192c745369b88cab34471aba7  # The ID of the mlflow run to load the service_estimator from
+
+
+# These variables control filters that are applied to either images, image metadata or service_estimator predictions.
+# The filter result values are reported in the service responses. For convenience the response to a request contains a
+# "filters.allPassed" field, which is set to false if any of the values returned by the filters did not meet its
+# specified required value.
+filters:
+
+  image_to_page_quotient: # Image size to page size ratio (ratio of geometric means of areas)
+    min: $MIN_REL_IMAGE_SIZE|0.05  # Minimum permissible
+    max: $MAX_REL_IMAGE_SIZE|0.75  # Maximum permissible
+
+  image_width_to_height_quotient:  # Image width to height ratio
+    min: $MIN_IMAGE_FORMAT|0.1  # Minimum permissible
+    max: $MAX_IMAGE_FORMAT|10  # Maximum permissible
+
+  min_confidence: $MIN_CONFIDENCE|0.5  # Minimum permissible prediction confidence

config/pyinfra.toml

@@ -1,68 +0,0 @@
-
-[asyncio]
-max_concurrent_tasks = 10
-
-[dynamic_tenant_queues]
-enabled = true
-
-[metrics.prometheus]
-enabled = true
-prefix = "redactmanager_image_service"
-
-[tracing]
-enabled = true
-# possible values "opentelemetry" | "azure_monitor" (Excpects APPLICATIONINSIGHTS_CONNECTION_STRING environment variable.)
-type = "azure_monitor" 
-
-[tracing.opentelemetry]
-endpoint = "http://otel-collector-opentelemetry-collector.otel-collector:4318/v1/traces"
-service_name = "redactmanager_image_service"
-exporter = "otlp"
-
-[webserver]
-host = "0.0.0.0"
-port = 8080
-
-[rabbitmq]
-host = "localhost"
-port = 5672
-username = ""
-password = ""
-heartbeat = 60
-# Has to be a divider of heartbeat, and shouldn't be too big, since only in these intervals queue interactions happen (like receiving new messages)
-# This is also the minimum time the service needs to process a message
-connection_sleep = 5
-input_queue = "request_queue"
-output_queue = "response_queue"
-dead_letter_queue = "dead_letter_queue"
-
-tenant_event_queue_suffix = "_tenant_event_queue"
-tenant_event_dlq_suffix = "_tenant_events_dlq"
-tenant_exchange_name = "tenants-exchange"
-queue_expiration_time = 300000  # 5 minutes in milliseconds
-
-service_request_queue_prefix = "image_request_queue"
-service_request_exchange_name = "image_request_exchange"
-service_response_exchange_name = "image_response_exchange"
-service_dlq_name = "image_dlq"
-
-[storage]
-backend = "s3"
-
-[storage.s3]
-bucket = "redaction"
-endpoint = "http://127.0.0.1:9000"
-key = ""
-secret = ""
-region = "eu-central-1"
-
-[storage.azure]
-container = "redaction"
-connection_string = ""
-
-[storage.tenant_server]
-public_key = ""
-endpoint =  "http://tenant-user-management:8081/internal-api/tenants"
-
-[kubernetes]
-pod_name = "test_pod"

config/settings.toml

@@ -1,42 +0,0 @@
-[logging]
-level = "INFO"
-
-[service]
-# Print document processing progress to stdout
-verbose = false
-batch_size = 6
-image_stiching_tolerance = 1  # in pixels
-mlflow_run_id = "fabfb1f192c745369b88cab34471aba7"
-
-# These variables control filters that are applied to either images, image metadata or service_estimator predictions.
-# The filter result values are reported in the service responses. For convenience the response to a request contains a
-# "filters.allPassed" field, which is set to false if any of the values returned by the filters did not meet its
-# specified required value.
-[filters.confidence]
-# Minimum permissible prediction confidence
-min = 0.5
-
-# Image size to page size ratio (ratio of geometric means of areas)
-[filters.image_to_page_quotient]
-min = 0.05
-max = 0.75
-
-[filters.is_scanned_page]
-# Minimum permissible image to page ratio tolerance for a page to be considered scanned.
-# This is only used for filtering small images on scanned pages and is applied before processing the image, therefore
-# superseding the image_to_page_quotient filter that only applies a tag to the image after processing.
-tolerance = 0
-
-# Image width to height ratio
-[filters.image_width_to_height_quotient]
-min = 0.1
-max = 10
-
-# put class specific filters here ['signature', 'formula', 'logo']
-[filters.overrides.signature.image_to_page_quotient]
-max = 0.4
-
-[filters.overrides.logo.image_to_page_quotient]
-min = 0.06
-
-

image_prediction/config.py

@@ -0,0 +1,46 @@
+"""Implements a config object with dot-indexing syntax."""
+
+
+from envyaml import EnvYAML
+
+from image_prediction.locations import CONFIG_FILE
+
+
+def _get_item_and_maybe_make_dotindexable(container, item):
+    ret = container[item]
+    return DotIndexable(ret) if isinstance(ret, dict) else ret
+
+
+class DotIndexable:
+    def __init__(self, x):
+        self.x = x
+
+    def get(self, item, default=None):
+        try:
+            return _get_item_and_maybe_make_dotindexable(self.x, item)
+        except KeyError:
+            return default
+
+    def __getattr__(self, item):
+        return _get_item_and_maybe_make_dotindexable(self.x, item)
+
+    def __repr__(self):
+        return self.x.__repr__()
+
+    def __getitem__(self, item):
+        return self.__getattr__(item)
+
+
+class Config:
+    def __init__(self, config_path):
+        self.__config = EnvYAML(config_path)
+
+    def __getattr__(self, item):
+        if item in self.__config:
+            return _get_item_and_maybe_make_dotindexable(self.__config, item)
+
+    def __getitem__(self, item):
+        return self.__getattr__(item)
+
+
+CONFIG = Config(CONFIG_FILE)

image_prediction/default_objects.py

@@ -1,3 +1,5 @@
+from typing import Iterable
+
 from funcy import juxt
 
 from image_prediction.classifier.classifier import Classifier
@@ -5,6 +7,7 @@ from image_prediction.classifier.image_classifier import ImageClassifier
 from image_prediction.compositor.compositor import TransformerCompositor
 from image_prediction.encoder.encoders.hash_encoder import HashEncoder
 from image_prediction.estimator.adapter.adapter import EstimatorAdapter
+from image_prediction.formatter.formatter import format_image_plus
 from image_prediction.formatter.formatters.camel_case import Snake2CamelCaseKeyFormatter
 from image_prediction.formatter.formatters.enum import EnumFormatter
 from image_prediction.image_extractor.extractors.parsable import ParsablePDFImageExtractor
@@ -14,6 +17,7 @@ from image_prediction.model_loader.loaders.mlflow import MlflowConnector
 from image_prediction.redai_adapter.mlflow import MlflowModelReader
 from image_prediction.transformer.transformers.coordinate.pdfnet import PDFNetCoordinateTransformer
 from image_prediction.transformer.transformers.response import ResponseTransformer
+from pdf2img.extraction import extract_images_via_metadata
 
 
 def get_mlflow_model_loader(mlruns_dir):
@@ -26,10 +30,17 @@ def get_image_classifier(model_loader, model_identifier):
     return ImageClassifier(Classifier(EstimatorAdapter(model), ProbabilityMapper(classes)))
 
 
-def get_extractor(**kwargs):
+def get_dispatched_extract(**kwargs):
     image_extractor = ParsablePDFImageExtractor(**kwargs)
 
-    return image_extractor
+    def extract(pdf: bytes, page_range: range = None, metadata_per_image: Iterable[dict] = None):
+        if metadata_per_image:
+            image_pluses = extract_images_via_metadata(pdf, metadata_per_image)
+            yield from map(format_image_plus, image_pluses)
+        else:
+            yield from image_extractor.extract(pdf, page_range)
+
+    return extract
 
 
 def get_formatter():

image_prediction/encoder/encoders/hash_encoder.py

@@ -13,7 +13,7 @@ class HashEncoder(Encoder):
         yield from self.encode(images)
 
 
-def hash_image(image: Image.Image) -> str:
+def hash_image(image: Image.Image):
     """See: https://stackoverflow.com/a/49692185/3578468"""
     image = image.resize((10, 10), Image.ANTIALIAS)
     image = image.convert("L")
@@ -21,6 +21,4 @@ def hash_image(image: Image.Image) -> str:
     avg_pixel = sum(pixel_data) / len(pixel_data)
     bits = "".join(["1" if (px >= avg_pixel) else "0" for px in pixel_data])
     hex_representation = str(hex(int(bits, 2)))[2:][::-1].upper()
-    # Note: For each 4 leading zeros, the hex representation will be shorter by one character.
-    # To ensure that all hashes have the same length, we pad the hex representation with zeros (also see RED-3813).
-    return hex_representation.zfill(25)
+    return hex_representation

image_prediction/exceptions.py

@@ -36,7 +36,3 @@ class InvalidBox(Exception):
 
 class ParsingError(Exception):
     pass
-
-
-class BadXref(ValueError):
-    pass

image_prediction/formatter/formatter.py

@@ -0,0 +1,35 @@
+import abc
+
+from image_prediction.image_extractor.extractor import ImageMetadataPair
+from image_prediction.info import Info
+
+from image_prediction.transformer.transformer import Transformer
+from pdf2img.default_objects.image import ImagePlus
+
+
+class Formatter(Transformer):
+    @abc.abstractmethod
+    def format(self, obj):
+        raise NotImplementedError
+
+    def transform(self, obj):
+        raise NotImplementedError()
+
+    def __call__(self, obj):
+        return self.format(obj)
+
+
+def format_image_plus(image: ImagePlus) -> ImageMetadataPair:
+    enum_metadata = {
+        Info.PAGE_WIDTH: image.info.pageInfo.width,
+        Info.PAGE_HEIGHT: image.info.pageInfo.height,
+        Info.PAGE_IDX: image.info.pageInfo.number,
+        Info.ALPHA: image.info.alpha,
+        Info.WIDTH: image.info.boundingBox.width,
+        Info.HEIGHT: image.info.boundingBox.height,
+        Info.X1: image.info.boundingBox.x0,
+        Info.X2: image.info.boundingBox.x1,
+        Info.Y1: image.info.boundingBox.y0,
+        Info.Y2: image.info.boundingBox.y1,
+    }
+    return ImageMetadataPair(image.aspil(), enum_metadata)

image_prediction/image_extractor/extractors/parsable.py

@@ -0,0 +1,208 @@
+import atexit
+import io
+import json
+import traceback
+from functools import partial, lru_cache
+from itertools import chain, starmap, filterfalse
+from operator import itemgetter, truth
+from typing import List, Iterable, Iterator
+
+import fitz
+from PIL import Image
+from funcy import rcompose, merge, pluck, curry, compose
+
+from image_prediction.formatter.formatters.enum import EnumFormatter
+from image_prediction.image_extractor.extractor import ImageExtractor, ImageMetadataPair
+from image_prediction.info import Info
+from image_prediction.stitching.stitching import stitch_pairs
+from image_prediction.stitching.utils import validate_box_coords, validate_box_size
+from image_prediction.utils import get_logger
+from image_prediction.utils.generic import lift
+
+logger = get_logger()
+
+
+class ParsablePDFImageExtractor(ImageExtractor):
+    def __init__(self, verbose=False, tolerance=0):
+        """
+
+        Args:
+            verbose: Whether to show progressbar
+            tolerance: The tolerance in pixels for the distance between images, beyond which they will not be stitched
+                together
+        """
+        self.doc: fitz.fitz.Document = None
+        self.verbose = verbose
+        self.tolerance = tolerance
+
+    def extract(self, pdf: bytes, page_range: range = None):
+        self.doc = fitz.Document(stream=pdf)
+
+        pages = extract_pages(self.doc, page_range) if page_range else self.doc
+
+        image_metadata_pairs = chain.from_iterable(map(self.__process_images_on_page, pages))
+
+        yield from image_metadata_pairs
+
+    def __process_images_on_page(self, page: fitz.fitz.Page):
+        images = get_images_on_page(self.doc, page)
+        metadata = get_metadata_for_images_on_page(self.doc, page)
+        clear_caches()
+
+        image_metadata_pairs = starmap(ImageMetadataPair, filter(all, zip(images, metadata)))
+        #  TODO: In the future, consider to introduce an image validator as a pipeline component rather than doing the
+        #   validation here. Invalid images can then be split into a different stream and joined with the intact images
+        #   again for the formatting step.
+        image_metadata_pairs = self.__filter_valid_images(image_metadata_pairs)
+        image_metadata_pairs = stitch_pairs(list(image_metadata_pairs), tolerance=self.tolerance)
+
+        yield from image_metadata_pairs
+
+    @staticmethod
+    def __filter_valid_images(image_metadata_pairs: Iterable[ImageMetadataPair]) -> Iterator[ImageMetadataPair]:
+        def validate(image: Image.Image, metadata: dict):
+            try:
+                # TODO: stand-in heuristic for testing if image is valid => find cleaner solution (RED-5148)
+                image.resize((100, 100)).convert("RGB")
+                return ImageMetadataPair(image, metadata)
+            except (OSError, Exception) as err:
+                metadata = json.dumps(EnumFormatter()(metadata), indent=2)
+                logger.warning(f"Invalid image encountered. Image metadata:\n{metadata}\n\n{traceback.format_exc()}")
+                return None
+
+        return filter(truth, starmap(validate, image_metadata_pairs))
+
+
+def extract_pages(doc, page_range):
+    page_range = range(page_range.start + 1, page_range.stop + 1)
+    pages = map(doc.load_page, page_range)
+
+    yield from pages
+
+
+@lru_cache(maxsize=None)
+def get_images_on_page(doc, page: fitz.Page):
+    image_infos = get_image_infos(page)
+    xrefs = map(itemgetter("xref"), image_infos)
+    images = map(partial(xref_to_image, doc), xrefs)
+
+    yield from images
+
+
+def get_metadata_for_images_on_page(doc, page: fitz.Page):
+
+    metadata = map(get_image_metadata, get_image_infos(page))
+    metadata = validate_coords_and_passthrough(metadata)
+
+    metadata = filter_out_tiny_images(metadata)
+    metadata = validate_size_and_passthrough(metadata)
+
+    metadata = add_page_metadata(page, metadata)
+
+    metadata = add_alpha_channel_info(doc, page, metadata)
+
+    yield from metadata
+
+
+@lru_cache(maxsize=None)
+def get_image_infos(page: fitz.Page) -> List[dict]:
+    return page.get_image_info(xrefs=True)
+
+
+@lru_cache(maxsize=None)
+def xref_to_image(doc, xref) -> Image:
+    maybe_image = load_image_handle_from_xref(doc, xref)
+    return Image.open(io.BytesIO(maybe_image["image"])) if maybe_image else None
+
+
+def get_image_metadata(image_info):
+
+    x1, y1, x2, y2 = map(rounder, image_info["bbox"])
+
+    width = abs(x2 - x1)
+    height = abs(y2 - y1)
+
+    return {
+        Info.WIDTH: width,
+        Info.HEIGHT: height,
+        Info.X1: x1,
+        Info.X2: x2,
+        Info.Y1: y1,
+        Info.Y2: y2,
+    }
+
+
+def validate_coords_and_passthrough(metadata):
+    yield from map(validate_box_coords, metadata)
+
+
+def filter_out_tiny_images(metadata):
+    yield from filterfalse(tiny, metadata)
+
+
+def validate_size_and_passthrough(metadata):
+    yield from map(validate_box_size, metadata)
+
+
+def add_page_metadata(page, metadata):
+    yield from map(partial(merge, get_page_metadata(page)), metadata)
+
+
+def add_alpha_channel_info(doc, page, metadata):
+
+    page_to_xrefs = compose(curry(pluck)("xref"), get_image_infos)
+    xref_to_alpha = partial(has_alpha_channel, doc)
+    page_to_alpha_value_per_image = compose(lift(xref_to_alpha), page_to_xrefs)
+    alpha_to_dict = compose(dict, lambda a: [(Info.ALPHA, a)])
+    page_to_alpha_mapping_per_image = compose(lift(alpha_to_dict), page_to_alpha_value_per_image)
+
+    metadata = starmap(merge, zip(page_to_alpha_mapping_per_image(page), metadata))
+
+    yield from metadata
+
+
+@lru_cache(maxsize=None)
+def load_image_handle_from_xref(doc, xref):
+    return doc.extract_image(xref)
+
+
+rounder = rcompose(round, int)
+
+
+def get_page_metadata(page):
+    page_width, page_height = map(rounder, page.mediabox_size)
+
+    return {
+        Info.PAGE_WIDTH: page_width,
+        Info.PAGE_HEIGHT: page_height,
+        Info.PAGE_IDX: page.number,
+    }
+
+
+def has_alpha_channel(doc, xref):
+
+    maybe_image = load_image_handle_from_xref(doc, xref)
+    maybe_smask = maybe_image["smask"] if maybe_image else None
+
+    if maybe_smask:
+        return any([doc.extract_image(maybe_smask) is not None, bool(fitz.Pixmap(doc, maybe_smask).alpha)])
+    else:
+        try:
+            return bool(fitz.Pixmap(doc, xref).alpha)
+        except ValueError:
+            logger.debug(f"Encountered invalid xref `{xref}` in {doc.metadata.get('title', '<no title>')}.")
+            return False
+
+
+def tiny(metadata):
+    return metadata[Info.WIDTH] * metadata[Info.HEIGHT] <= 4
+
+
+def clear_caches():
+    get_image_infos.cache_clear()
+    load_image_handle_from_xref.cache_clear()
+    get_images_on_page.cache_clear()
+    xref_to_image.cache_clear()
+
+
+atexit.register(clear_caches)

image_prediction/info.py

@@ -12,4 +12,3 @@ class Info(Enum):
     Y1 = "y1"
     Y2 = "y2"
     ALPHA = "alpha"
-    XREF = "xref"

image_prediction/locations.py

@@ -0,0 +1,17 @@
+"""Defines constant paths relative to the module root path."""
+
+from pathlib import Path
+
+MODULE_DIR = Path(__file__).resolve().parents[0]
+
+PACKAGE_ROOT_DIR = MODULE_DIR.parents[0]
+
+CONFIG_FILE = PACKAGE_ROOT_DIR / "config.yaml"
+
+BANNER_FILE = PACKAGE_ROOT_DIR / "banner.txt"
+
+DATA_DIR = PACKAGE_ROOT_DIR / "data"
+
+MLRUNS_DIR = str(DATA_DIR / "mlruns")
+
+TEST_DATA_DIR = PACKAGE_ROOT_DIR / "test" / "data"

image_prediction/pipeline.py

@@ -1,10 +1,9 @@
 import os
-from functools import lru_cache, partial
+from functools import partial
 from itertools import chain, tee
-from typing import Iterable, Any
+from typing import Iterable
 
 from funcy import rcompose, first, compose, second, chunks, identity, rpartial
-from kn_utils.logging import logger
 from tqdm import tqdm
 
 from image_prediction.config import CONFIG
@@ -12,8 +11,8 @@ from image_prediction.default_objects import (
     get_formatter,
     get_mlflow_model_loader,
     get_image_classifier,
-    get_extractor,
     get_encoder,
+    get_dispatched_extract,
 )
 from image_prediction.locations import MLRUNS_DIR
 from image_prediction.utils.generic import lift, starlift
@@ -21,9 +20,7 @@ from image_prediction.utils.generic import lift, starlift
 os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
 
 
-@lru_cache(maxsize=None)
 def load_pipeline(**kwargs):
-    logger.info(f"Loading pipeline with kwargs: {kwargs}")
     model_loader = get_mlflow_model_loader(MLRUNS_DIR)
     model_identifier = CONFIG.service.mlflow_run_id
 
@@ -41,10 +38,10 @@ def star(f):
 
 
 class Pipeline:
-    def __init__(self, model_loader, model_identifier, batch_size=16, verbose=False, **kwargs):
+    def __init__(self, model_loader, model_identifier, batch_size=16, verbose=True, **kwargs):
         self.verbose = verbose
 
-        extract = get_extractor(**kwargs)
+        extract = get_dispatched_extract(**kwargs)
         classifier = get_image_classifier(model_loader, model_identifier)
         reformat = get_formatter()
         represent = get_encoder()
@@ -55,7 +52,7 @@ class Pipeline:
         join = compose(starlift(lambda prd, rpr, mdt: {"classification": prd, **mdt, "representation": rpr}), star(zip))
 
         #                       />--classify--\
-        # --extract-->--split--+->--encode---->+--join-->reformat-->filter_duplicates
+        # --extract-->--split--+->--encode---->+--join-->reformat
         #                       \>--identity--/
 
         self.pipe = rcompose(
@@ -64,42 +61,12 @@ class Pipeline:
             pairwise_apply(classify, represent, identity),  # ... apply functions to the streams pairwise
             join,  # ... the streams by zipping
             reformat,  # ... the items
-            filter_duplicates,  # ... filter out duplicate images
         )
 
-    def __call__(self, pdf: bytes, page_range: range = None):
+    def __call__(self, pdf: bytes, page_range: range = None, metadata_per_image: Iterable[dict] = None):
         yield from tqdm(
-            self.pipe(pdf, page_range=page_range),
+            self.pipe(pdf, page_range=page_range, metadata_per_image=metadata_per_image),
             desc="Processing images from document",
             unit=" images",
             disable=not self.verbose,
         )
-
-
-def filter_duplicates(metadata: Iterable[dict[str, Any]]) -> Iterable[dict[str, Any]]:
-    """Filter out duplicate images from the `position` (image coordinates) and `page`, preferring the one with
-    `allPassed` set to True.
-    See RED-10765 (RM-241): Removed redactions reappear for why this is necessary.
-    """
-    keep = dict()
-    for image_meta in metadata:
-        key: tuple[int, int, int, int, int] = (
-            image_meta["position"]["x1"],
-            image_meta["position"]["x2"],
-            image_meta["position"]["y1"],
-            image_meta["position"]["y2"],
-            image_meta["position"]["pageNumber"],
-        )
-        if key in keep:
-            logger.warning(
-                f"Duplicate image found: x1={key[0]}, x2={key[1]}, y1={key[2]}, y2={key[3]}, pageNumber={key[4]}"
-            )
-            if image_meta["filters"]["allPassed"]:
-                logger.warning("Setting the image with allPassed flag set to True")
-                keep[key] = image_meta
-            else:
-                logger.warning("Keeping the previous image since the current image has allPassed flag set to False")
-        else:
-            keep[key] = image_meta
-
-    yield from keep.values()

image_prediction/transformer/transformers/response.py

@@ -0,0 +1,153 @@
+import json
+import math
+import os
+from functools import lru_cache
+from operator import itemgetter
+
+from funcy import first
+
+from image_prediction.config import CONFIG
+from image_prediction.exceptions import ParsingError
+from image_prediction.transformer.transformer import Transformer
+from image_prediction.utils import get_logger
+
+logger = get_logger()
+
+
+class ResponseTransformer(Transformer):
+    def transform(self, data):
+        logger.debug("ResponseTransformer.transform")
+        return build_image_info(data)
+
+
+def build_image_info(data: dict) -> dict:
+    def compute_geometric_quotient():
+        page_area_sqrt = math.sqrt(abs(page_width * page_height))
+        image_area_sqrt = math.sqrt(abs(x2 - x1) * abs(y2 - y1))
+        return image_area_sqrt / page_area_sqrt
+
+    page_width, page_height, x1, x2, y1, y2, width, height, alpha = itemgetter(
+        "page_width", "page_height", "x1", "x2", "y1", "y2", "width", "height", "alpha"
+    )(data)
+
+    classification = data["classification"]
+    label = classification["label"]
+    representation = data["representation"]
+
+    geometric_quotient = round(compute_geometric_quotient(), 4)
+
+    min_image_to_page_quotient_breached = bool(
+        geometric_quotient < get_class_specific_min_image_to_page_quotient(label)
+    )
+    max_image_to_page_quotient_breached = bool(
+        geometric_quotient > get_class_specific_max_image_to_page_quotient(label)
+    )
+
+    min_image_width_to_height_quotient_breached = bool(
+        width / height < get_class_specific_min_image_width_to_height_quotient(label)
+    )
+    max_image_width_to_height_quotient_breached = bool(
+        width / height > get_class_specific_max_image_width_to_height_quotient(label)
+    )
+
+    min_confidence_breached = bool(
+        max(classification["probabilities"].values()) < get_class_specific_min_classification_confidence(label)
+    )
+
+    image_info = {
+        "classification": classification,
+        "representation": representation,
+        "position": {"x1": x1, "x2": x2, "y1": y1, "y2": y2, "pageNumber": data["page_idx"] + 1},
+        "geometry": {"width": width, "height": height},
+        "alpha": alpha,
+        "filters": {
+            "geometry": {
+                "imageSize": {
+                    "quotient": geometric_quotient,
+                    "tooLarge": max_image_to_page_quotient_breached,
+                    "tooSmall": min_image_to_page_quotient_breached,
+                },
+                "imageFormat": {
+                    "quotient": round(width / height, 4),
+                    "tooTall": min_image_width_to_height_quotient_breached,
+                    "tooWide": max_image_width_to_height_quotient_breached,
+                },
+            },
+            "probability": {"unconfident": min_confidence_breached},
+            "allPassed": not any(
+                [
+                    max_image_to_page_quotient_breached,
+                    min_image_to_page_quotient_breached,
+                    min_image_width_to_height_quotient_breached,
+                    max_image_width_to_height_quotient_breached,
+                    min_confidence_breached,
+                ]
+            ),
+        },
+    }
+
+    return image_info
+
+
+def get_class_specific_min_image_to_page_quotient(label, table=None):
+    return get_class_specific_value(
+        "REL_IMAGE_SIZE", label, "min", CONFIG.filters.image_to_page_quotient.min, table=table
+    )
+
+
+def get_class_specific_max_image_to_page_quotient(label, table=None):
+    return get_class_specific_value(
+        "REL_IMAGE_SIZE", label, "max", CONFIG.filters.image_to_page_quotient.max, table=table
+    )
+
+
+def get_class_specific_min_image_width_to_height_quotient(label, table=None):
+    return get_class_specific_value(
+        "IMAGE_FORMAT", label, "min", CONFIG.filters.image_width_to_height_quotient.min, table=table
+    )
+
+
+def get_class_specific_max_image_width_to_height_quotient(label, table=None):
+    return get_class_specific_value(
+        "IMAGE_FORMAT", label, "max", CONFIG.filters.image_width_to_height_quotient.max, table=table
+    )
+
+
+def get_class_specific_min_classification_confidence(label, table=None):
+    return get_class_specific_value("CONFIDENCE", label, "min", CONFIG.filters.min_confidence, table=table)
+
+
+def get_class_specific_value(prefix, label, bound, fallback_value, table=None):
+    def fallback():
+        return fallback_value
+
+    def success():
+        threshold_map = parse_env_var(prefix, table=table) or {}
+        value = threshold_map.get(label, {}).get(bound)
+        if value:
+            logger.debug(f"Using class '{label}' specific {bound} {prefix.lower().replace('_', '-')} value.")
+        return value
+
+    assert bound in ["min", "max"]
+
+    return success() or fallback()
+
+
+@lru_cache(maxsize=None)
+def parse_env_var(prefix, table=None):
+    table = table or os.environ
+    head = first(filter(lambda s: s == prefix, table))
+    if head:
+        try:
+            return parse_env_var_value(table[head])
+        except ParsingError as err:
+            logger.warning(err)
+    else:
+        return None
+
+
+def parse_env_var_value(env_var_value):
+    try:
+        return json.loads(env_var_value)
+    except Exception as err:
+        raise ParsingError(f"Failed to parse {env_var_value}") from err

image_prediction/utils/generic.py

@@ -0,0 +1,15 @@
+from itertools import starmap
+
+from funcy import iterate, first, curry, map
+
+
+def until(cond, func, *args, **kwargs):
+    return first(filter(cond, iterate(func, *args, **kwargs)))
+
+
+def lift(fn):
+    return curry(map)(fn)
+
+
+def starlift(fn):
+    return curry(starmap)(fn)

image_prediction/utils/logger.py

@@ -0,0 +1,27 @@
+import logging
+
+from image_prediction.config import CONFIG
+
+
+def make_logger_getter():
+    logger = logging.getLogger("imclf")
+    logger.propagate = False
+
+    handler = logging.StreamHandler()
+    handler.setLevel(CONFIG.service.logging_level)
+
+    log_format = "%(asctime)s %(levelname)-8s %(message)s"
+    formatter = logging.Formatter(log_format, datefmt="%Y-%m-%d %H:%M:%S")
+
+    handler.setFormatter(formatter)
+    logger.addHandler(handler)
+
+    logger.setLevel(CONFIG.service.logging_level)
+
+    def get_logger():
+        return logger
+
+    return get_logger
+
+
+get_logger = make_logger_getter()

image_prediction/utils/pdf_annotation.py

@@ -56,8 +56,7 @@ def annotate_image(doc, image_info):
 
 def init():
     PDFNet.Initialize(
-        # "Knecon AG(en.knecon.swiss):OEM:DDA-R::WL+:AMS(20211029):BECC974307DAB4F34B513BC9B2531B24496F6FCB83CD8AC574358A959730B622FABEF5C7"
-        "Knecon AG:OEM:DDA-R::WL+:AMS(20270129):EA5FDFB23C7F36B9C2AE606F4F0D9197DE1FB649119F9730B622FABEF5C7"
+        "Knecon AG(en.knecon.swiss):OEM:DDA-R::WL+:AMS(20211029):BECC974307DAB4F34B513BC9B2531B24496F6FCB83CD8AC574358A959730B622FABEF5C7"
     )