├── .gitignore ├── .env ├── sample-configs ├── grobid │ ├── org │ │ └── apache │ │ │ └── tika │ │ │ └── parser │ │ │ └── journal │ │ │ └── GrobidExtractor.properties │ └── tika-config.xml ├── customocr │ ├── org │ │ └── apache │ │ │ └── tika │ │ │ └── parser │ │ │ └── ocr │ │ │ └── TesseractOCRConfig.properties │ ├── tika-config-inline.xml │ └── tika-config-rendered.xml ├── ner │ ├── tika-config.xml │ └── run_tika_server.sh └── vision │ ├── inception-rest.xml │ ├── inception-rest-caption.xml │ └── inception-rest-video.xml ├── .asf.yaml ├── docker-compose-tika-ner.yml ├── docker-compose-tika-grobid.yml ├── docker-compose-tika-customocr.yml ├── CHANGES.md ├── docker-compose-tika-vision.yml ├── republish-images.sh ├── minimal └── Dockerfile ├── full └── Dockerfile ├── docker-tool.sh ├── README.md └── LICENSE /.gitignore: -------------------------------------------------------------------------------- 1 | .svn 2 | target 3 | dependency-reduced-pom.xml 4 | .idea 5 | .classpath 6 | .project 7 | .settings 8 | *.iml 9 | *.ipr 10 | *.iws 11 | *.bin 12 | nbactions.xml 13 | nb-configuration.xml 14 | *.DS_Store 15 | *.tmp-inception 16 | *.snap 17 | .*.swp 18 | tika-deployment/tika-snap-app/parts/ 19 | tika-deployment/tika-snap-app/prime/ 20 | tika-deployment/tika-snap-app/snap/ 21 | tika-deployment/tika-snap-app/stage/ 22 | tika-deployment/tika-snap-app/test/ 23 | tika-deployment/tika-snap-server/parts/ 24 | tika-deployment/tika-snap-server/prime/ 25 | tika-deployment/tika-snap-server/snap/ 26 | tika-deployment/tika-snap-server/stage/ 27 | 28 | -------------------------------------------------------------------------------- /.env: -------------------------------------------------------------------------------- 1 | # Licensed to the Apache Software Foundation (ASF) under one or more 2 | # contributor license agreements. See the NOTICE file distributed with 3 | # this work for additional information regarding copyright ownership. 4 | # The ASF licenses this file to You under the Apache License, Version 2.0 5 | # (the "License"); you may not use this file except in compliance with 6 | # the License. You may obtain a copy of the License at 7 | # 8 | # http://www.apache.org/licenses/LICENSE-2.0 9 | # 10 | # Unless required by applicable law or agreed to in writing, software 11 | # distributed under the License is distributed on an "AS IS" BASIS, 12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | # See the License for the specific language governing permissions and 14 | # limitations under the License. 15 | 16 | TAG=3.2.3.0 -------------------------------------------------------------------------------- /sample-configs/grobid/org/apache/tika/parser/journal/GrobidExtractor.properties: -------------------------------------------------------------------------------- 1 | # Licensed to the Apache Software Foundation (ASF) under one or more 2 | # contributor license agreements. See the NOTICE file distributed with 3 | # this work for additional information regarding copyright ownership. 4 | # The ASF licenses this file to You under the Apache License, Version 2.0 5 | # (the "License"); you may not use this file except in compliance with 6 | # the License. You may obtain a copy of the License at 7 | # 8 | # http://www.apache.org/licenses/LICENSE-2.0 9 | # 10 | # Unless required by applicable law or agreed to in writing, software 11 | # distributed under the License is distributed on an "AS IS" BASIS, 12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | # See the License for the specific language governing permissions and 14 | # limitations under the License. 15 | 16 | grobid.server.url=http://grobid:8070 -------------------------------------------------------------------------------- /.asf.yaml: -------------------------------------------------------------------------------- 1 | # Licensed to the Apache Software Foundation (ASF) under one or more 2 | # contributor license agreements. See the NOTICE file distributed with 3 | # this work for additional information regarding copyright ownership. 4 | # The ASF licenses this file to You under the Apache License, Version 2.0 5 | # the License. You may obtain a copy of the License at 6 | # 7 | # http://www.apache.org/licenses/LICENSE-2.0 8 | # 9 | # Unless required by applicable law or agreed to in writing, software 10 | # distributed under the License is distributed on an "AS IS" BASIS, 11 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | # See the License for the specific language governing permissions and 13 | # limitations under the License. 14 | github: 15 | description: "Convenience Docker images for Apache Tika Server" 16 | homepage: https://tika.apache.org/ 17 | labels: 18 | - docker 19 | - image 20 | - tika 21 | 22 | notifications: 23 | commits: commits@tika.apache.org 24 | issues: dev@tika.apache.org 25 | pullrequests: dev@tika.apache.org 26 | jira_options: link label comment 27 | -------------------------------------------------------------------------------- /sample-configs/customocr/org/apache/tika/parser/ocr/TesseractOCRConfig.properties: -------------------------------------------------------------------------------- 1 | # Licensed to the Apache Software Foundation (ASF) under one or more 2 | # contributor license agreements. See the NOTICE file distributed with 3 | # this work for additional information regarding copyright ownership. 4 | # The ASF licenses this file to You under the Apache License, Version 2.0 5 | # (the "License"); you may not use this file except in compliance with 6 | # the License. You may obtain a copy of the License at 7 | # 8 | # http://www.apache.org/licenses/LICENSE-2.0 9 | # 10 | # Unless required by applicable law or agreed to in writing, software 11 | # distributed under the License is distributed on an "AS IS" BASIS, 12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | # See the License for the specific language governing permissions and 14 | # limitations under the License. 15 | 16 | # You customise or add the settings you want here 17 | language=eng+spa+fra+deu+ita 18 | timeout=240 19 | minFileSizeToOcr=1 20 | enableImageProcessing=0 21 | density=200 22 | depth=8 23 | filter=box 24 | resize=300 25 | applyRotation=true -------------------------------------------------------------------------------- /sample-configs/grobid/tika-config.xml: -------------------------------------------------------------------------------- 1 | 2 | 18 | 19 | 20 | 21 | application/pdf 22 | 23 | 24 | 25 | -------------------------------------------------------------------------------- /docker-compose-tika-ner.yml: -------------------------------------------------------------------------------- 1 | # Licensed to the Apache Software Foundation (ASF) under one or more 2 | # contributor license agreements. See the NOTICE file distributed with 3 | # this work for additional information regarding copyright ownership. 4 | # The ASF licenses this file to You under the Apache License, Version 2.0 5 | # (the "License"); you may not use this file except in compliance with 6 | # the License. You may obtain a copy of the License at 7 | # 8 | # http://www.apache.org/licenses/LICENSE-2.0 9 | # 10 | # Unless required by applicable law or agreed to in writing, software 11 | # distributed under the License is distributed on an "AS IS" BASIS, 12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | # See the License for the specific language governing permissions and 14 | # limitations under the License. 15 | 16 | version: "3.8" 17 | services: 18 | 19 | ## Apache Tika Server 20 | tika: 21 | image: apache/tika:${TAG}-full 22 | # Use custom script as entrypoint to go fetch models and setup recognisers 23 | entrypoint: [ "/ner/run_tika_server.sh"] 24 | restart: on-failure 25 | ports: 26 | - "9998:9998" 27 | volumes: 28 | - ./sample-configs/ner/:/ner/ 29 | environment: 30 | - TAG -------------------------------------------------------------------------------- /sample-configs/ner/tika-config.xml: -------------------------------------------------------------------------------- 1 | 2 | 18 | 19 | 20 | 21 | application/pdf 22 | text/plain 23 | text/html 24 | application/xhtml+xml 25 | 26 | 27 | 28 | 29 | -------------------------------------------------------------------------------- /sample-configs/customocr/tika-config-inline.xml: -------------------------------------------------------------------------------- 1 | 2 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | true 27 | 28 | 29 | 30 | 31 | 32 | -------------------------------------------------------------------------------- /docker-compose-tika-grobid.yml: -------------------------------------------------------------------------------- 1 | # Licensed to the Apache Software Foundation (ASF) under one or more 2 | # contributor license agreements. See the NOTICE file distributed with 3 | # this work for additional information regarding copyright ownership. 4 | # The ASF licenses this file to You under the Apache License, Version 2.0 5 | # (the "License"); you may not use this file except in compliance with 6 | # the License. You may obtain a copy of the License at 7 | # 8 | # http://www.apache.org/licenses/LICENSE-2.0 9 | # 10 | # Unless required by applicable law or agreed to in writing, software 11 | # distributed under the License is distributed on an "AS IS" BASIS, 12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | # See the License for the specific language governing permissions and 14 | # limitations under the License. 15 | 16 | version: "3.8" 17 | services: 18 | 19 | ## Apache Tika Server 20 | tika: 21 | image: apache/tika:${TAG}-full 22 | # Override default so we can add configuration on classpath 23 | entrypoint: [ "/bin/sh", "-c", "exec java -cp \"/grobid:/tika-server-standard-$${TIKA_VERSION}.jar:/tika-extras/*\" org.apache.tika.server.core.TikaServerCli -h 0.0.0.0 $$0 $$@"] 24 | # Kept command as example but could be added to entrypoint too 25 | command: -c /grobid/tika-config.xml 26 | restart: on-failure 27 | ports: 28 | - "9998:9998" 29 | volumes: 30 | - ./sample-configs/grobid:/grobid 31 | depends_on: 32 | - grobid 33 | 34 | ## Grobid Service 35 | grobid: 36 | image: lfoppiano/grobid:0.6.1 37 | ports: 38 | - "8070:8070" 39 | - "8071:8071" 40 | 41 | -------------------------------------------------------------------------------- /sample-configs/vision/inception-rest.xml: -------------------------------------------------------------------------------- 1 | 2 | 18 | 19 | 20 | 21 | image/jpeg 22 | image/png 23 | image/gif 24 | 25 | http://inception-rest:8764/inception/v4 26 | 2 27 | 0.015 28 | org.apache.tika.parser.recognition.tf.TensorflowRESTRecogniser 29 | 30 | 31 | 32 | 33 | -------------------------------------------------------------------------------- /sample-configs/vision/inception-rest-caption.xml: -------------------------------------------------------------------------------- 1 | 2 | 18 | 19 | 20 | 21 | image/jpeg 22 | image/png 23 | image/gif 24 | 25 | http://inception-caption:8764/inception/v3 26 | 5 27 | 15 28 | org.apache.tika.parser.captioning.tf.TensorflowRESTCaptioner 29 | 30 | 31 | 32 | -------------------------------------------------------------------------------- /docker-compose-tika-customocr.yml: -------------------------------------------------------------------------------- 1 | # Licensed to the Apache Software Foundation (ASF) under one or more 2 | # contributor license agreements. See the NOTICE file distributed with 3 | # this work for additional information regarding copyright ownership. 4 | # The ASF licenses this file to You under the Apache License, Version 2.0 5 | # (the "License"); you may not use this file except in compliance with 6 | # the License. You may obtain a copy of the License at 7 | # 8 | # http://www.apache.org/licenses/LICENSE-2.0 9 | # 10 | # Unless required by applicable law or agreed to in writing, software 11 | # distributed under the License is distributed on an "AS IS" BASIS, 12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | # See the License for the specific language governing permissions and 14 | # limitations under the License. 15 | 16 | version: "3.8" 17 | services: 18 | 19 | ## Apache Tika Server 20 | tika: 21 | image: apache/tika:${TAG}-full 22 | # Override default so we can add configuration on classpath 23 | entrypoint: [ "/bin/sh", "-c", "exec java -cp \"/customocr:/tika-server-standard-$${TIKA_VERSION}.jar:/tika-extras/*\" org.apache.tika.server.core.TikaServerCli -h 0.0.0.0 $$0 $$@"] 24 | # Kept command as example but could be added to entrypoint too 25 | command: -c /tika-config.xml 26 | restart: on-failure 27 | ports: 28 | - "9998:9998" 29 | volumes: 30 | # Choose the configuration you want, or add your own custom one 31 | # - ./sample-configs/customocr/tika-config-inline.xml:/tika-config.xml 32 | - ./sample-configs/customocr/tika-config-rendered.xml:/tika-config.xml 33 | 34 | 35 | -------------------------------------------------------------------------------- /sample-configs/vision/inception-rest-video.xml: -------------------------------------------------------------------------------- 1 | 2 | 18 | 19 | 20 | 21 | video/mp4 22 | video/quicktime 23 | 24 | http://inception-video:8764/inception/v4 25 | 4 26 | 0.015 27 | fixed 28 | org.apache.tika.parser.recognition.tf.TensorflowRESTVideoRecogniser 29 | 30 | 31 | 32 | -------------------------------------------------------------------------------- /sample-configs/customocr/tika-config-rendered.xml: -------------------------------------------------------------------------------- 1 | 2 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | 31 | ocr_only 32 | rgb 33 | 100 34 | 35 | 36 | 37 | 38 | 39 | -------------------------------------------------------------------------------- /CHANGES.md: -------------------------------------------------------------------------------- 1 | # Changes 2 | 3 | As of 2.5.0.1, we started adding a digit for Docker versions. Going forward, we'll include 4 | a four digit version, where the first three are the Tika version and the last one is the docker version. 5 | As of 2.5.0.2, we started tagging release commits in our github repo. 6 | 7 | * 3.2.3.0 (15 Sep 2025) 8 | * First 3.2.3 release 9 | 10 | * 3.2.2.0 (8 Aug 2025) 11 | * First 3.2.2 release 12 | 13 | * 3.2.1.0 (9 Jul 2025) 14 | * First 3.2.1 release 15 | 16 | * 3.2.0.0 (2 Jun 2025) 17 | * First 3.2.0 release 18 | * Update base to plucky 19 | * Add Japanese language pack for tesseract 20 | * Add ImageMagick 21 | 22 | * 3.1.0.0 (31 Jan 2025) 23 | * First 3.1.0 release 24 | * Update base to oracular 25 | 26 | * 3.0.0.0 (21 Oct 2024) 27 | * First 3.x stable release 28 | * Bump jre to 21 29 | 30 | * 2.9.2.1 (21 May 2024) 31 | * Updated to noble 32 | * First multi-arch release 33 | 34 | * 2.9.2.0 (10 October 2023) 35 | * Initial release for Tika 2.9.2 36 | 37 | * 2.9.1.0 (10 October 2023) 38 | * Initial release for Tika 2.9.1 39 | 40 | * 2.9.0.0 (28 August 2023) 41 | * Initial release for Tika 2.9.0 42 | 43 | * 2.8.0.0 (15 May 2023) 44 | * Initial release for Tika 2.8.0 45 | 46 | 47 | * 2.7.0.1 (27 March 2023) 48 | * More efficient build process and final image size via @stumpylog on [pr#17](https://github.com/apache/tika-docker/pull). 49 | 50 | * 2.7.0.0 (6 Feb 2023) 51 | * Initial release for Tika 2.7.0 52 | 53 | * 2.6.0.1 (10 November 2022) 54 | * Update operating system against OpenSSL CVE (TIKA-3926). 55 | 56 | * 2.6.0.0 (7 November 2022) 57 | * Initial release for Tika 2.6.0 58 | 59 | * 2.5.0.2 (31 October 2022) 60 | * Fixed root-user regression caused by differences in Docker behavior based on the build system's OS (TIKA-3912) 61 | * Added tika-extras/ directory to pick up extra jars via mounted drive or for those using our image as a base image (TIKA-3907) 62 | * 63 | * 2.5.0.1 (27 October 2022) 64 | * Update to latest jammy to avoid recent CVEs (TIKA-3906) -------------------------------------------------------------------------------- /docker-compose-tika-vision.yml: -------------------------------------------------------------------------------- 1 | # Licensed to the Apache Software Foundation (ASF) under one or more 2 | # contributor license agreements. See the NOTICE file distributed with 3 | # this work for additional information regarding copyright ownership. 4 | # The ASF licenses this file to You under the Apache License, Version 2.0 5 | # (the "License"); you may not use this file except in compliance with 6 | # the License. You may obtain a copy of the License at 7 | # 8 | # http://www.apache.org/licenses/LICENSE-2.0 9 | # 10 | # Unless required by applicable law or agreed to in writing, software 11 | # distributed under the License is distributed on an "AS IS" BASIS, 12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | # See the License for the specific language governing permissions and 14 | # limitations under the License. 15 | 16 | version: "3.8" 17 | services: 18 | 19 | ## Apache Tika Server 20 | tika: 21 | image: apache/tika:latest-full 22 | command: -c /tika-config.xml 23 | restart: on-failure 24 | ports: 25 | - "9998:9998" 26 | 27 | volumes: 28 | # Replace the below with the configuration you want to use, or with your own custom one 29 | # - ./sample-configs/vision/inception-rest.xml:/tika-config.xml 30 | # - ./sample-configs/vision/inception-rest-video.xml:/tika-config.xml 31 | - ./sample-configs/vision/inception-rest-caption.xml:/tika-config.xml 32 | 33 | depends_on: 34 | # You can comment out any you don't need here and in the Vision Service section below 35 | - inception-rest 36 | - inception-caption 37 | - inception-video 38 | 39 | ## Vision Services 40 | inception-rest: 41 | build: https://raw.githubusercontent.com/dameikle/tika-dockers/patch-1/InceptionRestDockerfile 42 | ports: 43 | - "8764:8764" 44 | 45 | inception-caption: 46 | build: https://raw.githubusercontent.com/dameikle/tika-dockers/patch-1/Im2txtRestDockerfile 47 | ports: 48 | - "8765:8764" 49 | 50 | inception-video: 51 | build: https://raw.githubusercontent.com/dameikle/tika-dockers/patch-1/InceptionVideoRestDockerfile 52 | ports: 53 | - "8766:8764" 54 | 55 | -------------------------------------------------------------------------------- /republish-images.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Licensed to the Apache Software Foundation (ASF) under one 4 | # or more contributor license agreements. See the NOTICE file 5 | # distributed with this work for additional information 6 | # regarding copyright ownership. The ASF licenses this file 7 | # to you under the Apache License, Version 2.0 (the 8 | # "License"); you may not use this file except in compliance 9 | # with the License. You may obtain a copy of the License at 10 | # 11 | # http://www.apache.org/licenses/LICENSE-2.0 12 | # 13 | # Unless required by applicable law or agreed to in writing, 14 | # software distributed under the License is distributed on an 15 | # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY 16 | # KIND, either express or implied. See the License for the 17 | # specific language governing permissions and limitations 18 | # under the License. 19 | 20 | 21 | ## 22 | ## Helper script to allow a republish of all versions released so far. 23 | ## This was used to support the original seeding of the DockerHub repo 24 | ## 25 | 26 | # Early releases on JRE 8 27 | for i in {6..13}; 28 | do 29 | docker build -t apache/tika:"1.$i" --build-arg TIKA_VERSION="1.$i" --build-arg JRE=openjdk-8-jre-headless - < minimal/Dockerfile 30 | docker build -t apache/tika:"1.$i"-full --build-arg TIKA_VERSION="1.$i" --build-arg JRE=openjdk-8-jre-headless - < full/Dockerfile 31 | ./docker-tool.sh test "1.$i" 32 | if [ $? -eq 0 ] 33 | then 34 | ./docker-tool.sh publish "1.$i" 35 | else 36 | echo "Failed to test and publish version ${1.$i}" 37 | echo "$(tput setaf 1)Failed to test and publish image : apache/tika:${1.$i}$(tput sgr0)" 38 | exit 1 39 | fi 40 | done; 41 | 42 | # Signing issues on these release where public key is not available 43 | for i in {14..19}; 44 | do 45 | docker build -t apache/tika:"1.$i" --build-arg TIKA_VERSION="1.$i" --build-arg JRE=openjdk-8-jre-headless --build-arg CHECK_SIG=false - < minimal/Dockerfile 46 | docker build -t apache/tika:"1.$i"-full --build-arg TIKA_VERSION="1.$i" --build-arg JRE=openjdk-8-jre-headless --build-arg CHECK_SIG=false - < full/Dockerfile 47 | ./docker-tool.sh test "1.$i" 48 | if [ $? -eq 0 ] 49 | then 50 | ./docker-tool.sh publish "1.$i" 51 | else 52 | echo "Failed to test and publish version ${1.$i}" 53 | echo "$(tput setaf 1)Failed to test and publish image : apache/tika:${1.$i}$(tput sgr0)" 54 | exit 1 55 | fi 56 | done; 57 | 58 | # Moved to JRE 11 by default 59 | for i in {20..23}; 60 | do 61 | ./docker-tool.sh build "1.$i" 62 | ./docker-tool.sh test "1.$i" 63 | if [ $? -eq 0 ] 64 | then 65 | ./docker-tool.sh publish "1.$i" 66 | else 67 | echo "Failed to test and publish version ${1.$i}" 68 | echo "$(tput setaf 1)Failed to test and publish image : apache/tika:${1.$i}$(tput sgr0)" 69 | exit 1 70 | fi 71 | done; -------------------------------------------------------------------------------- /sample-configs/ner/run_tika_server.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | # Licensed to the Apache Software Foundation (ASF) under one or more 4 | # contributor license agreements. See the NOTICE file distributed with 5 | # this work for additional information regarding copyright ownership. 6 | # The ASF licenses this file to You under the Apache License, Version 2.0 7 | # (the "License"); you may not use this file except in compliance with 8 | # the License. You may obtain a copy of the License at 9 | # 10 | # http://www.apache.org/licenses/LICENSE-2.0 11 | # 12 | # Unless required by applicable law or agreed to in writing, software 13 | # distributed under the License is distributed on an "AS IS" BASIS, 14 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 15 | # See the License for the specific language governing permissions and 16 | # limitations under the License. 17 | 18 | 19 | ############################################################################# 20 | # See https://cwiki.apache.org/confluence/display/TIKA/TikaAndNER for details 21 | # on how to configure additional NER libraries 22 | ############################################################################# 23 | 24 | # ------------------------------------ 25 | # Download OpenNLP Models to classpath 26 | # ------------------------------------ 27 | 28 | OPENNLP_LOCATION="/ner/org/apache/tika/parser/ner/opennlp" 29 | URL="http://opennlp.sourceforge.net/models-1.5" 30 | 31 | mkdir -p $OPENNLP_LOCATION 32 | if [ "$(ls -A $OPENNLP_LOCATION/*.bin)" ]; then 33 | echo "OpenNLP models directory has files, so skipping fetch"; 34 | else 35 | echo "No OpenNLP models found, so fetching them" 36 | wget "$URL/en-ner-person.bin" -O $OPENNLP_LOCATION/ner-person.bin 37 | wget "$URL/en-ner-location.bin" -O $OPENNLP_LOCATION/ner-location.bin 38 | wget "$URL/en-ner-organization.bin" -O $OPENNLP_LOCATION/ner-organization.bin; 39 | wget "$URL/en-ner-date.bin" -O $OPENNLP_LOCATION/ner-date.bin 40 | wget "$URL/en-ner-time.bin" -O $OPENNLP_LOCATION/ner-time.bin 41 | wget "$URL/en-ner-percentage.bin" -O $OPENNLP_LOCATION/ner-percentage.bin 42 | wget "$URL/en-ner-money.bin" -O $OPENNLP_LOCATION/ner-money.bin 43 | fi 44 | 45 | # -------------------------------------------- 46 | # Create RexExp Example for Email on classpath 47 | # -------------------------------------------- 48 | REGEXP_LOCATION="/ner/org/apache/tika/parser/ner/regex" 49 | mkdir -p $REGEXP_LOCATION 50 | echo "EMAIL=(?:[a-z0-9!#$%&'*+/=?^_\`{|}~-]+(?:\.[a-z0-9!#$%&'*+/=?^_\`{|}~-]+)*|\"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])*\")@(?:(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?|\[(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?|[a-z0-9-]*[a-z0-9]:(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21-\x5a\x53-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])+)\])" > $REGEXP_LOCATION/ner-regex.txt 51 | 52 | 53 | # ------------------- 54 | # Now run Tika Server 55 | # ------------------- 56 | 57 | # Can be a single implementation or comma seperated list for multiple for "ner.impl.class" property 58 | RECOGNISERS=org.apache.tika.parser.ner.opennlp.OpenNLPNERecogniser,org.apache.tika.parser.ner.regex.RegexNERecogniser 59 | # Set classpath to the Tika Server JAR and the /ner folder so it has the configuration and models from above 60 | CLASSPATH="/ner:/tika-server-standard-${TIKA_VERSION}.jar:/tika-extras/*" 61 | # Run the server with the custom configuration ner.impl.class property and custom /ner/tika-config.xml 62 | exec java -Dner.impl.class=$RECOGNISERS -cp $CLASSPATH org.apache.tika.server.core.TikaServerCli -h 0.0.0.0 -c /ner/tika-config.xml -------------------------------------------------------------------------------- /minimal/Dockerfile: -------------------------------------------------------------------------------- 1 | 2 | # Licensed under the Apache License, Version 2.0 (the "License"); you may not 3 | # use this file except in compliance with the License. You may obtain a copy of 4 | # the License at 5 | # 6 | # http://www.apache.org/licenses/LICENSE-2.0 7 | # 8 | # Unless required by applicable law or agreed to in writing, software 9 | # distributed under the License is distributed on an "AS IS" BASIS, WITHOUT 10 | # WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the 11 | # License for the specific language governing permissions and limitations under 12 | # the License. 13 | 14 | # "random" uid/gid hopefully not used anywhere else 15 | # This needs to be set globally and then referenced in 16 | # the subsequent stages -- see TIKA-3912 17 | ARG UID_GID="35002:35002" 18 | 19 | FROM ubuntu:plucky AS base 20 | 21 | FROM base AS fetch_tika 22 | 23 | ARG TIKA_VERSION 24 | ARG CHECK_SIG=true 25 | 26 | ENV NEAREST_TIKA_SERVER_URL="https://dlcdn.apache.org/tika/${TIKA_VERSION}/tika-server-standard-${TIKA_VERSION}.jar" \ 27 | ARCHIVE_TIKA_SERVER_URL="https://archive.apache.org/dist/tika/${TIKA_VERSION}/tika-server-standard-${TIKA_VERSION}.jar" \ 28 | BACKUP_TIKA_SERVER_URL="https://downloads.apache.org/tika/${TIKA_VERSION}/tika-server-standard-${TIKA_VERSION}.jar" \ 29 | DEFAULT_TIKA_SERVER_ASC_URL="https://downloads.apache.org/tika/${TIKA_VERSION}/tika-server-standard-${TIKA_VERSION}.jar.asc" \ 30 | ARCHIVE_TIKA_SERVER_ASC_URL="https://archive.apache.org/dist/tika/${TIKA_VERSION}/tika-server-standard-${TIKA_VERSION}.jar.asc" \ 31 | TIKA_VERSION=$TIKA_VERSION 32 | 33 | RUN set -eux \ 34 | && apt-get update \ 35 | && DEBIAN_FRONTEND=noninteractive apt-get install --yes --no-install-recommends \ 36 | gnupg2 \ 37 | wget \ 38 | ca-certificates \ 39 | && wget -t 10 --max-redirect 1 --retry-connrefused -qO- https://downloads.apache.org/tika/KEYS | gpg --import \ 40 | && wget -t 10 --max-redirect 1 --retry-connrefused $NEAREST_TIKA_SERVER_URL -O /tika-server-standard-${TIKA_VERSION}.jar || rm /tika-server-standard-${TIKA_VERSION}.jar \ 41 | && sh -c "[ -f /tika-server-standard-${TIKA_VERSION}.jar ]" || wget $ARCHIVE_TIKA_SERVER_URL -O /tika-server-standard-${TIKA_VERSION}.jar || rm /tika-server-standard-${TIKA_VERSION}.jar \ 42 | && sh -c "[ -f /tika-server-standard-${TIKA_VERSION}.jar ]" || wget $BACKUP_TIKA_SERVER_URL -O /tika-server-standard-${TIKA_VERSION}.jar || rm /tika-server-standard-${TIKA_VERSION}.jar \ 43 | && sh -c "[ -f /tika-server-standard-${TIKA_VERSION}.jar ]" || exit 1 \ 44 | && wget -t 10 --max-redirect 1 --retry-connrefused $DEFAULT_TIKA_SERVER_ASC_URL -O /tika-server-standard-${TIKA_VERSION}.jar.asc || rm /tika-server-standard-${TIKA_VERSION}.jar.asc \ 45 | && sh -c "[ -f /tika-server-standard-${TIKA_VERSION}.jar.asc ]" || wget $ARCHIVE_TIKA_SERVER_ASC_URL -O /tika-server-standard-${TIKA_VERSION}.jar.asc || rm /tika-server-standard-${TIKA_VERSION}.jar.asc \ 46 | && sh -c "[ -f /tika-server-standard-${TIKA_VERSION}.jar.asc ]" || exit 1 \ 47 | && gpg --verify /tika-server-standard-${TIKA_VERSION}.jar.asc /tika-server-standard-${TIKA_VERSION}.jar 48 | 49 | # this used to work, but I'm getting "ERROR: failed to solve: failed to prepare $data as $data2: invalid argument" 50 | # when trying to build 2.9.2.0 51 | #RUN if [ "$CHECK_SIG" = "true" ] ; then gpg --verify /tika-server-standard-${TIKA_VERSION}.jar.asc /tika-server-standard-${TIKA_VERSION}.jar; fi 52 | 53 | FROM base AS runtime 54 | # must reference uid_gid 55 | ARG UID_GID 56 | ARG JRE='openjdk-21-jre-headless' 57 | RUN set -eux \ 58 | && apt-get update \ 59 | && apt-get install --yes --no-install-recommends \ 60 | ${JRE} \ 61 | ca-certificates \ 62 | && apt-get clean -y && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* 63 | ARG TIKA_VERSION 64 | ENV TIKA_VERSION=$TIKA_VERSION 65 | COPY --from=fetch_tika /tika-server-standard-${TIKA_VERSION}.jar /tika-server-standard-${TIKA_VERSION}.jar 66 | USER $UID_GID 67 | EXPOSE 9998 68 | ENTRYPOINT [ "/bin/sh", "-c", "exec java -cp \"/tika-server-standard-${TIKA_VERSION}.jar:/tika-extras/*\" org.apache.tika.server.core.TikaServerCli -h 0.0.0.0 $0 $@"] 69 | 70 | LABEL maintainer="Apache Tika Developers dev@tika.apache.org" 71 | -------------------------------------------------------------------------------- /full/Dockerfile: -------------------------------------------------------------------------------- 1 | # Licensed under the Apache License, Version 2.0 (the "License"); you may not 2 | # use this file except in compliance with the License. You may obtain a copy of 3 | # the License at 4 | # 5 | # http://www.apache.org/licenses/LICENSE-2.0 6 | # 7 | # Unless required by applicable law or agreed to in writing, software 8 | # distributed under the License is distributed on an "AS IS" BASIS, WITHOUT 9 | # WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the 10 | # License for the specific language governing permissions and limitations under 11 | # the License. 12 | 13 | # "random" uid/gid hopefully not used anywhere else 14 | # This needs to be set globally and then referenced in 15 | # the subsequent stages -- see TIKA-3912 16 | ARG UID_GID="35002:35002" 17 | 18 | FROM ubuntu:plucky AS base 19 | 20 | FROM base AS fetch_tika 21 | 22 | ARG TIKA_VERSION 23 | ARG CHECK_SIG=true 24 | 25 | ENV NEAREST_TIKA_SERVER_URL="https://dlcdn.apache.org/tika/${TIKA_VERSION}/tika-server-standard-${TIKA_VERSION}.jar" \ 26 | ARCHIVE_TIKA_SERVER_URL="https://archive.apache.org/dist/tika/${TIKA_VERSION}/tika-server-standard-${TIKA_VERSION}.jar" \ 27 | BACKUP_TIKA_SERVER_URL="https://downloads.apache.org/tika/${TIKA_VERSION}/tika-server-standard-${TIKA_VERSION}.jar" \ 28 | DEFAULT_TIKA_SERVER_ASC_URL="https://downloads.apache.org/tika/${TIKA_VERSION}/tika-server-standard-${TIKA_VERSION}.jar.asc" \ 29 | ARCHIVE_TIKA_SERVER_ASC_URL="https://archive.apache.org/dist/tika/${TIKA_VERSION}/tika-server-standard-${TIKA_VERSION}.jar.asc" \ 30 | TIKA_VERSION=$TIKA_VERSION 31 | 32 | RUN DEBIAN_FRONTEND=noninteractive apt-get update && apt-get -y install gnupg2 wget ca-certificates \ 33 | && wget -t 10 --max-redirect 1 --retry-connrefused -qO- https://downloads.apache.org/tika/KEYS | gpg --import \ 34 | && wget -t 10 --max-redirect 1 --retry-connrefused $NEAREST_TIKA_SERVER_URL -O /tika-server-standard-${TIKA_VERSION}.jar || rm /tika-server-standard-${TIKA_VERSION}.jar \ 35 | && sh -c "[ -f /tika-server-standard-${TIKA_VERSION}.jar ]" || wget $ARCHIVE_TIKA_SERVER_URL -O /tika-server-standard-${TIKA_VERSION}.jar || rm /tika-server-standard-${TIKA_VERSION}.jar \ 36 | && sh -c "[ -f /tika-server-standard-${TIKA_VERSION}.jar ]" || wget $BACKUP_TIKA_SERVER_URL -O /tika-server-standard-${TIKA_VERSION}.jar || rm /tika-server-standard-${TIKA_VERSION}.jar \ 37 | && sh -c "[ -f /tika-server-standard-${TIKA_VERSION}.jar ]" || exit 1 \ 38 | && wget -t 10 --max-redirect 1 --retry-connrefused $DEFAULT_TIKA_SERVER_ASC_URL -O /tika-server-standard-${TIKA_VERSION}.jar.asc || rm /tika-server-standard-${TIKA_VERSION}.jar.asc \ 39 | && sh -c "[ -f /tika-server-standard-${TIKA_VERSION}.jar.asc ]" || wget $ARCHIVE_TIKA_SERVER_ASC_URL -O /tika-server-standard-${TIKA_VERSION}.jar.asc || rm /tika-server-standard-${TIKA_VERSION}.jar.asc \ 40 | && sh -c "[ -f /tika-server-standard-${TIKA_VERSION}.jar.asc ]" || exit 1 \ 41 | && gpg --verify /tika-server-standard-${TIKA_VERSION}.jar.asc /tika-server-standard-${TIKA_VERSION}.jar 42 | 43 | #RUN if [ "$CHECK_SIG" = "true" ] ; then gpg --verify /tika-server-standard-${TIKA_VERSION}.jar.asc /tika-server-standard-${TIKA_VERSION}.jar; fi 44 | 45 | FROM base AS runtime 46 | ARG UID_GID 47 | ARG JRE='openjdk-21-jre-headless' 48 | RUN set -eux \ 49 | && apt-get update \ 50 | && apt-get install --yes --no-install-recommends gnupg2 software-properties-common \ 51 | && apt-get update \ 52 | && DEBIAN_FRONTEND=noninteractive apt-get install --yes --no-install-recommends $JRE \ 53 | gdal-bin \ 54 | imagemagick \ 55 | tesseract-ocr \ 56 | tesseract-ocr-eng \ 57 | tesseract-ocr-ita \ 58 | tesseract-ocr-fra \ 59 | tesseract-ocr-spa \ 60 | tesseract-ocr-deu \ 61 | tesseract-ocr-jpn \ 62 | && echo ttf-mscorefonts-installer msttcorefonts/accepted-mscorefonts-eula select true | debconf-set-selections \ 63 | && DEBIAN_FRONTEND=noninteractive apt-get install --yes --no-install-recommends \ 64 | xfonts-utils \ 65 | fonts-freefont-ttf \ 66 | fonts-liberation \ 67 | ttf-mscorefonts-installer \ 68 | wget \ 69 | cabextract \ 70 | && apt-get clean -y \ 71 | && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* 72 | ARG TIKA_VERSION 73 | ENV TIKA_VERSION=$TIKA_VERSION 74 | 75 | COPY --from=fetch_tika /tika-server-standard-${TIKA_VERSION}.jar /tika-server-standard-${TIKA_VERSION}.jar 76 | USER $UID_GID 77 | 78 | EXPOSE 9998 79 | ENTRYPOINT [ "/bin/sh", "-c", "exec java -cp \"/tika-server-standard-${TIKA_VERSION}.jar:/tika-extras/*\" org.apache.tika.server.core.TikaServerCli -h 0.0.0.0 $0 $@"] 80 | 81 | LABEL maintainer="Apache Tika Developers dev@tika.apache.org" 82 | 83 | -------------------------------------------------------------------------------- /docker-tool.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Licensed to the Apache Software Foundation (ASF) under one 4 | # or more contributor license agreements. See the NOTICE file 5 | # distributed with this work for additional information 6 | # regarding copyright ownership. The ASF licenses this file 7 | # to you under the Apache License, Version 2.0 (the 8 | # "License"); you may not use this file except in compliance 9 | # with the License. You may obtain a copy of the License at 10 | # 11 | # http://www.apache.org/licenses/LICENSE-2.0 12 | # 13 | # Unless required by applicable law or agreed to in writing, 14 | # software distributed under the License is distributed on an 15 | # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY 16 | # KIND, either express or implied. See the License for the 17 | # specific language governing permissions and limitations 18 | # under the License. 19 | 20 | image_name=apache/tika 21 | 22 | stop_and_die() { 23 | docker buildx rm tika-builder || die "couldn't stop builder -- make sure to stop the builder manually! " 24 | die "$*" 25 | } 26 | 27 | die() { 28 | echo "$*" >&2 29 | exit 1 30 | } 31 | 32 | while getopts ":h" opt; do 33 | case ${opt} in 34 | h ) 35 | echo "Usage:" 36 | echo " docker-tool.sh -h Display this help message." 37 | echo " docker-tool.sh build Builds images for ." 38 | echo " docker-tool.sh test Tests images for ." 39 | echo " docker-tool.sh publish Builds multi-arch images for and pushes to Docker Hub." 40 | exit 0 41 | ;; 42 | \? ) 43 | echo "Invalid Option: -$OPTARG" 1>&2 44 | exit 1 45 | ;; 46 | esac 47 | done 48 | 49 | stop_test_container() { 50 | container_name=$1 51 | docker kill "$container_name" 52 | docker rm "$container_name" 53 | } 54 | 55 | test_docker_image() { 56 | container_name=$1 57 | image=$image_name:$1 58 | full=$2 59 | 60 | docker run -d --name "$container_name" -p 127.0.0.1:9998:9998 "$image" 61 | sleep 10 62 | url=http://localhost:9998/ 63 | status=$(curl --head --location --connect-timeout 5 --write-out %{http_code} --silent --output /dev/null ${url}) 64 | user=$(docker inspect "$container_name" --format '{{.Config.User}}') 65 | 66 | if [[ $status == '200' ]] 67 | then 68 | echo "$(tput setaf 2)Image: $image - Basic test passed$(tput sgr0)" 69 | else 70 | echo "$(tput setaf 1)Image: $image - Basic test failed$(tput sgr0)" 71 | stop_test_container "$container_name" 72 | exit 1 73 | fi 74 | 75 | #now test that the user is correctly set 76 | if [[ $user == '35002:35002' ]] 77 | then 78 | echo "$(tput setaf 2)Image: $image - User passed$(tput sgr0)" 79 | else 80 | echo "$(tput setaf 1)Image: $image - User failed$(tput sgr0)" 81 | stop_test_container "$container_name" 82 | exit 1 83 | fi 84 | 85 | if [ $full == true ] 86 | then 87 | # Test ImageMagick is installed and runnable 88 | if docker exec "$1" /usr/bin/convert -version >/dev/null 89 | then 90 | echo "$(tput setaf 2)Image: $image - ImageMagick passed$(tput sgr0)" 91 | else 92 | echo "$(tput setaf 1)Image: $image - ImageMagick failed$(tput sgr0)" 93 | stop_test_container "$container_name" 94 | exit 1 95 | fi 96 | fi 97 | 98 | stop_test_container "$container_name" 99 | } 100 | 101 | shift $((OPTIND -1)) 102 | subcommand=$1; shift 103 | tika_docker_version=$1; shift 104 | tika_version=$1; shift 105 | 106 | 107 | case "$subcommand" in 108 | build) 109 | # Build slim tika- with minimal dependencies 110 | docker build -t ${image_name}:${tika_docker_version} --build-arg TIKA_VERSION=${tika_version} - < minimal/Dockerfile --no-cache || die "couldn't build minimal" 111 | # Build full tika- with OCR, Fonts and GDAL 112 | docker build -t ${image_name}:${tika_docker_version}-full --build-arg TIKA_VERSION=${tika_version} - < full/Dockerfile --no-cache || die "couldn't build full" 113 | ;; 114 | 115 | test) 116 | # Test the images 117 | test_docker_image ${tika_docker_version} false 118 | test_docker_image "${tika_docker_version}-full" true 119 | ;; 120 | 121 | publish) 122 | docker buildx create --use --name tika-builder || die "couldn't create builder" 123 | # Build multi-arch with buildx and push 124 | docker buildx build --platform linux/arm/v7,linux/arm64/v8,linux/amd64 --output "type=image,push=true" \ 125 | --tag ${image_name}:latest --tag ${image_name}:${tika_docker_version} --build-arg TIKA_VERSION=${tika_version} --no-cache --builder tika-builder minimal || stop_and_die "couldn't build multi-arch minimal" 126 | docker buildx build --platform linux/arm/v7,linux/arm64/v8,linux/amd64 --output "type=image,push=true" \ 127 | --tag ${image_name}:latest-full --tag ${image_name}:${tika_docker_version}-full --build-arg TIKA_VERSION=${tika_version} --no-cache --builder tika-builder full || stop_and_die "couldn't build multi-arch full" 128 | docker buildx rm tika-builder || die "couldn't stop builder -- make sure to stop the builder manually! " 129 | ;; 130 | 131 | esac 132 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # tika-docker 2 | 3 | This repo is used to create convenience Docker images for Apache Tika Server published as [apache/tika](https://hub.docker.com/r/apache/tika) on DockerHub by the [Apache Tika](http://tika.apache.org) Dev team 4 | 5 | The images create a functional Apache Tika Server instance that contains the latest Ubuntu running the appropriate version's server on Port 9998 using Java 8 (until version 1.20), Java 11 (1.21 and 1.24.1), Java 14 (until 1.27/2.0.0), Java 16 (for 2.1.0), and Java 17 LTS for newer versions. 6 | 7 | There is a minimal version, which contains only Apache Tika and it's core dependencies, and a full version, which also includes dependencies for the GDAL and Tesseract OCR parsers. To balance showing functionality versus the size of the full image, this file currently installs the language packs for the following languages: 8 | * English 9 | * French 10 | * German 11 | * Italian 12 | * Spanish 13 | * Japanese 14 | 15 | To install more languages simply update the apt-get command to include the package containing the language you required, or include your own custom packs using an ADD command. 16 | 17 | ## Available Tags 18 | 19 | Below are the most recent 3.x series tags: 20 | - `latest`, `3.2.3.0`: Apache Tika Server 3.2.3.0 (Minimal) 21 | - `latest-full`, `3.2.3.0-full`: Apache Tika Server 3.2.3.0 (Full) 22 | - `3.2.3.0`, `3.2.3.0`: Apache Tika Server 3.2.3.0 (Minimal) 23 | - `3.2.3.0`, `3.2.3.0-full`: Apache Tika Server 3.2.3.0 (Full) 24 | - `3.2.2.0`, `3.2.2.0`: Apache Tika Server 3.2.2.0 (Minimal) 25 | - `3.2.2.0`, `3.2.2.0-full`: Apache Tika Server 3.2.2.0 (Full) 26 | - `3.2.1.0`, `3.2.1.0`: Apache Tika Server 3.2.1.0 (Minimal) 27 | - `3.2.1.0`, `3.2.1.0-full`: Apache Tika Server 3.2.1.0 (Full) 28 | - `3.2.0.0`, `3.2.0.0`: Apache Tika Server 3.2.0.0 (Minimal) 29 | - `3.2.0.0`, `3.2.0.0-full`: Apache Tika Server 3.2.0.0 (Full) 30 | - `3.1.0.0`, `3.1.0.0`: Apache Tika Server 3.1.0.0 (Minimal) 31 | - `3.1.0.0`, `3.1.0.0-full`: Apache Tika Server 3.1.0.0 (Full) 32 | - `3.0.0.0`, `3.0.0.0`: Apache Tika Server 3.0.0.0 (Minimal) 33 | - `3.0.0.0`, `3.0.0.0-full`: Apache Tika Server 3.0.0.0 (Full) 34 | - `3.0.0.0-BETA2`, `3.0.0.0-BETA2`: Apache Tika Server 3.0.0.0-BETA2 (Minimal) 35 | - `3.0.0.0-BETA2`, `3.0.0.0-BETA2-full`: Apache Tika Server 3.0.0.0-BETA2 (Full) 36 | - `2.9.2.1`, `2.9.2.1`: Apache Tika Server 2.9.2.1 (Minimal) 37 | - `2.9.2.1`, `2.9.2.1-full`: Apache Tika Server 2.9.2.1 (Full) 38 | - `2.9.2.0`, `2.9.2.0`: Apache Tika Server 2.9.2.0 (Minimal) 39 | - `2.9.2.0`, `2.9.2.0-full`: Apache Tika Server 2.9.2.0 (Full) 40 | - `2.9.1.0`, `2.9.1.0`: Apache Tika Server 2.9.1.0 (Minimal) 41 | - `2.9.1.0`, `2.9.1.0-full`: Apache Tika Server 2.9.1.0 (Full) 42 | - `2.9.0.0`, `2.9.0.0`: Apache Tika Server 2.9.0.0 (Minimal) 43 | - `2.9.0.0`, `2.9.0.0-full`: Apache Tika Server 2.9.0.0 (Full) 44 | - `2.8.0.0`, `2.8.0.0`: Apache Tika Server 2.8.0.0 (Minimal) 45 | - `2.8.0.0`, `2.8.0.0-full`: Apache Tika Server 2.8.0.0 (Full) 46 | - `2.7.0.1`, `2.7.0.1`: Apache Tika Server 2.7.0.1 (Minimal) 47 | - `2.7.0.1`, `2.7.0.1-full`: Apache Tika Server 2.7.0.1 (Full) 48 | - `2.7.0.0`, `2.7.0.0`: Apache Tika Server 2.7.0.0 (Minimal) 49 | - `2.7.0.0`, `2.7.0.0-full`: Apache Tika Server 2.7.0.0 (Full) 50 | - `2.6.0.1`: Apache Tika Server 2.6.0.1 (Minimal) 51 | - `2.6.0.1-full`: Apache Tika Server 2.6.0.1 (Full) 52 | - `2.6.0.0`: Apache Tika Server 2.6.0.0 (Minimal) 53 | - `2.6.0.0-full`: Apache Tika Server 2.6.0.0 (Full) 54 | - `2.5.0.2`: Apache Tika Server 2.5.0.2 (Minimal) 55 | - `2.5.0.2-full`: Apache Tika Server 2.5.0.2 (Full) 56 | - `2.5.0.1`: Apache Tika Server 2.5.0.1 (Minimal) 57 | - `2.5.0.1-full`: Apache Tika Server 2.5.0.1 (Full) 58 | - `2.5.0`: Apache Tika Server 2.5.0 (Minimal) 59 | - `2.5.0-full`: Apache Tika Server 2.5.0 (Full) 60 | - `2.4.1`: Apache Tika Server 2.4.1 (Minimal) 61 | - `2.4.1-full`: Apache Tika Server 2.4.1 (Full) 62 | - `2.4.0`: Apache Tika Server 2.4.0 (Minimal) 63 | - `2.4.0-full`: Apache Tika Server 2.4.0 (Full) 64 | - `2.3.0`: Apache Tika Server 2.3.0 (Minimal) 65 | - `2.3.0-full`: Apache Tika Server 2.3.0 (Full) 66 | - `2.2.1`: Apache Tika Server 2.2.1 (Minimal) 67 | - `2.2.1-full`: Apache Tika Server 2.2.1 (Full) 68 | 69 | Below are the most recent 1.x series tags. **Note** that as of 30 September 2022, the 1.x branch is no longer supported. 70 | 71 | - `1.28.5`: Apache Tika Server 1.28.5 (Minimal) 72 | - `1.28.5-full`: Apache Tika Server 1.28.5 (Full) 73 | - `1.28.4`: Apache Tika Server 1.28.4 (Minimal) 74 | - `1.28.4-full`: Apache Tika Server 1.28.4 (Full) 75 | - `1.28.3`: Apache Tika Server 1.28.3 (Minimal) 76 | - `1.28.3-full`: Apache Tika Server 1.28.3 (Full) 77 | - `1.28.2`: Apache Tika Server 1.28.2 (Minimal) 78 | - `1.28.2-full`: Apache Tika Server 1.28.2 (Full) 79 | - `1.28.1`: Apache Tika Server 1.28.1 (Minimal) 80 | - `1.28.1-full`: Apache Tika Server 1.28.1 (Full) 81 | 82 | You can see a full set of tags for historical versions [here](https://hub.docker.com/r/apache/tika/tags?page=1&ordering=last_updated). 83 | 84 | ## Usage 85 | 86 | ### Default 87 | 88 | You can pull down the version you would like using: 89 | 90 | docker pull apache/tika: 91 | 92 | Then to run the container, execute the following command: 93 | 94 | docker run -d -p 127.0.0.1:9998:9998 apache/tika: 95 | 96 | Where is the DockerHub tag corresponding to the Apache Tika Server version - e.g. 1.23, 1.22, 1.23-full, 1.22-full. 97 | 98 | NOTE: The latest and latest-full tags are explicitly set to the latest released version when they are published. 99 | 100 | NOTE: In the example above, we recommend binding the server to localhost because Docker alters iptables and may expose 101 | your tika-server to the internet. If you are confident that your tika-server is on an isolated network 102 | you can simply run: 103 | 104 | docker run -d -p 9998:9998 apache/tika: 105 | 106 | ### Custom Config 107 | 108 | From version 1.25 and 1.25-full of the image it is now easier to override the defaults and pass parameters to the running instance. 109 | 110 | So for example if you wish to disable the OCR parser in the full image you could write a custom configuration: 111 | 112 | ``` 113 | cat <> tika-config.xml 114 | 115 | 116 | 117 | 118 | 119 | 120 | 121 | 122 | EOT 123 | ``` 124 | Then by mounting this custom configuration as a volume, you could pass the command line parameter to load it 125 | 126 | docker run -d -p 127.0.0.1:9998:9998 -v `pwd`/tika-config.xml:/tika-config.xml apache/tika:2.5.0-full --config /tika-config.xml 127 | 128 | You can see more configuration examples [here](https://tika.apache.org/2.5.0/configuring.html). 129 | 130 | As of 2.5.0.2, if you'd like to add extra jars from your local `my-jars` directory to Tika's classpath, mount to `/tika-extras` like so: 131 | 132 | docker run -d -p 127.0.0.1:9998:9998 -v `pwd`/my-jars:/tika-extras apache/tika:2.5.0.2-full 133 | 134 | You may want to do this to add optional components, such as the tika-eval metadata filter, or optional 135 | dependencies such as jai-imageio-jpeg2000 (check license compatibility first!). 136 | 137 | ### Docker Compose Examples 138 | 139 | There are a number of sample Docker Compose files included in the repos to allow you to test some different scenarios. 140 | 141 | These files use docker-compose 3.x series and include: 142 | 143 | * docker-compose-tika-vision.yml - TensorFlow Inception REST API Vision examples 144 | * docker-compose-tika-grobid.yml - Grobid REST parsing example 145 | * docker-compose-tika-customocr.yml - Tesseract OCR example with custom configuration 146 | * docker-compose-tika-ner.yml - Named Entity Recognition example 147 | 148 | The Docker Compose files and configurations (sourced from _sample-configs_ directory) all have comments in them so you can try different options, or use them as a base to create your own custom configuration. 149 | 150 | **N.B.** You will want to create a environment variable (used in some bash scripts) matching the version of tika-docker you want to work with in the docker compositions e.g. `export TAG=1.26`. Similarly you should also consult `.env` which is used in the docker-compose `.yml` files. 151 | 152 | You can install docker-compose from [here](https://docs.docker.com/compose/install/). 153 | 154 | ## Building 155 | 156 | To build the image from scratch, simply invoke: 157 | 158 | docker build -t 'apache/tika' github.com/apache/tika-docker 159 | 160 | You can then use the following command (using the name you allocated in the build command as part of -t option): 161 | 162 | docker run -d -p 127.0.0.1:9998:9998 apache/tika 163 | 164 | ## More Information 165 | 166 | For more infomation on Apache Tika Server, go to the [Apache Tika Server documentation](https://cwiki.apache.org/confluence/display/TIKA/TikaServer). 167 | 168 | For more information on Apache Tika, go to the official [Apache Tika](http://tika.apache.org) project website. 169 | 170 | To meet up with others using Apache Tika, consider coming to one of the [Apache Tika Virtual Meetups](https://www.meetup.com/apache-tika-community/). 171 | 172 | For more information on the Apache Software Foundation, go to the [Apache Software Foundation](http://apache.org) website. 173 | 174 | For a full list of changes as of 2.5.0.1, visit [CHANGES.md](CHANGES.md). 175 | 176 | For our current release process, visit [tika-docker Release Process](https://cwiki.apache.org/confluence/display/TIKA/Release+Process+for+tika-docker) 177 | 178 | ## Authors 179 | 180 | Apache Tika Dev Team (dev@tika.apache.org) 181 | 182 | ## Contributors 183 | 184 | There have been a range of [contributors](https://github.com/apache/tika-docker/graphs/contributors) on GitHub and via suggestions, including: 185 | 186 | - [@grossws](https://github.com/grossws) 187 | - [@arjunyel](https://github.com/arjunyel) 188 | - [@mpdude](https://github.com/mpdude) 189 | - [@laszlocsontosuw](https://github.com/laszlocsontosuw) 190 | - [@tallisonapache](https://github.com/tballison) 191 | 192 | ## License 193 | 194 | Licensed under the Apache License, Version 2.0 (the "License"); 195 | you may not use this file except in compliance with the License. 196 | You may obtain a copy of the License at 197 | 198 | http://www.apache.org/licenses/LICENSE-2.0 199 | 200 | Unless required by applicable law or agreed to in writing, software 201 | distributed under the License is distributed on an "AS IS" BASIS, 202 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 203 | See the License for the specific language governing permissions and 204 | limitations under the License. 205 | 206 | ## Disclaimer 207 | 208 | It is worth noting that whilst these Docker images download the binary JARs published by the Apache Tika Team on the Apache Software Foundation distribution sites, only the source release of an Apache Software Foundation project is an official release artefact. See [Release Distribution Policy](https://www.apache.org/dev/release-distribution.html) for more details. 209 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------