-
-
Save Deviad/486513dc0ab5f82f6ea1ba06d3dc9d6b to your computer and use it in GitHub Desktop.
Fscrawler Connection refused
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
--- | |
name: "idx" | |
fs: | |
url: "/usr/app/data" | |
update_rate: "15m" | |
indexed_chars: 100% | |
json_support: false | |
filename_as_id: false | |
add_filesize: true | |
remove_deleted: true | |
add_as_inner_object: false | |
store_source: false | |
index_content: false | |
attributes_support: false | |
raw_metadata: false | |
xml_support: false | |
index_folders: true | |
lang_detect: true | |
continue_on_error: false | |
ocr: | |
language: "eng" | |
enabled: true | |
pdf_strategy: "ocr_and_text" | |
follow_symlinks: false | |
elasticsearch: | |
nodes: | |
- url: "http://elasticsearch:9200" | |
username: "elastic" | |
password: "changeme" | |
bulk_size: 100 | |
flush_interval: "5s" | |
byte_size: "10mb" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
version: '3.2' | |
services: | |
elasticsearch: | |
container_name: elasticsearch | |
build: | |
context: elasticsearch/ | |
args: | |
ELK_VERSION: 7.9.3 | |
volumes: | |
- type: bind | |
source: ${PWD}/elasticsearch/config/elasticsearch.yml | |
target: /usr/share/elasticsearch/config/elasticsearch.yml | |
read_only: true | |
- type: volume | |
source: elasticsearch | |
target: /usr/share/elasticsearch/data | |
ports: | |
- "9200:9200" | |
- "9300:9300" | |
environment: | |
- "ES_JAVA_OPTS=-Xmx256m -Xms256m" | |
- "ELASTIC_PASSWORD=changeme" | |
- "node.name=elasticsearch" | |
- "discovery.seed_hosts=elasticsearch" | |
- "cluster.initial_master_nodes=elasticsearch" | |
# Use single node discovery in order to disable production mode and avoid bootstrap checks. | |
# see: https://www.elastic.co/guide/en/elasticsearch/reference/current/bootstrap-checks.html | |
networks: | |
- elk | |
logstash: | |
build: | |
context: logstash/ | |
args: | |
ELK_VERSION: 7.9.3 | |
volumes: | |
- type: bind | |
source: ${PWD}/logstash/config/logstash.yml | |
target: /usr/share/logstash/config/logstash.yml | |
read_only: true | |
- type: bind | |
source: ${PWD}/logstash/pipeline | |
target: /usr/share/logstash/pipeline | |
read_only: true | |
ports: | |
- "5044:5044" | |
- "5001:5001/tcp" | |
- "5001:5001/udp" | |
- "9600:9600" | |
environment: | |
LS_JAVA_OPTS: "-Xmx256m -Xms256m" | |
networks: | |
- elk | |
depends_on: | |
- elasticsearch | |
kibana: | |
build: | |
context: kibana/ | |
args: | |
ELK_VERSION: 7.9.3 | |
volumes: | |
- type: bind | |
source: ${PWD}/kibana/config/kibana.yml | |
target: /usr/share/kibana/config/kibana.yml | |
read_only: true | |
ports: | |
- "5601:5601" | |
networks: | |
- elk | |
depends_on: | |
- elasticsearch | |
fscrawler: | |
environment: | |
FSCRAWLER_FNAME: "fscrawler-es7-2.7-SNAPSHOT" | |
build: | |
context: fscrawler/ | |
restart: always | |
volumes: | |
- type: bind | |
source: ${HOME}/document-folder/ | |
target: /usr/app/data/ | |
read_only: true | |
- type: bind | |
source: ${PWD}/fscrawler/config/ | |
target: /usr/app/config/ | |
depends_on: | |
- elasticsearch | |
- kibana | |
command: bash -c "./wait-for-it.sh -h elasticsearch -t 60 -p 9200 && ${PWD}/${FSCRAWLER_FNAME}/bin/fscrawler --config_dir /usr/app/config idx --rest" | |
networks: | |
- elk | |
networks: | |
elk: | |
driver: bridge | |
volumes: | |
elasticsearch: |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
FROM openjdk:8-alpine AS builder | |
ENV LANG C.UTF-8 | |
ENV MAVEN_OPTS "-Xmx256m -Xms256m" | |
RUN apk add --update --no-cache openssl wget maven | |
COPY . /usr/src/ | |
WORKDIR /usr/src/ | |
RUN mvn clean package | |
FROM openjdk:8-jre-alpine | |
ENV ES es7 | |
ENV VERSION 2.7-SNAPSHOT | |
ENV FSCRAWLER_FNAME fscrawler-$ES-$VERSION | |
RUN apk add --update \ | |
&& addgroup -S fscrawler && adduser -S -G fscrawler fscrawler | |
WORKDIR /usr/app | |
COPY --from=builder /usr/src/distribution/es7/target/$FSCRAWLER_FNAME.zip . | |
RUN unzip $FSCRAWLER_FNAME.zip && rm $FSCRAWLER_FNAME.zip \ | |
&& mkdir -p data/idx \ | |
&& mkdir config \ | |
&& chown -R fscrawler:fscrawler . | |
ENTRYPOINT $FSCRAWLER_FNAME/bin/fscrawler --config_dir /usr/app/config idx --rest |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
drwxr-xr-x@ 37 spotted staff 1184 Nov 21 18:31 . | |
drwxr-xr-x 9 spotted admin 288 Nov 21 18:16 .. | |
-rw-r--r--@ 1 spotted staff 14340 Nov 21 21:19 .DS_Store | |
drwxr-xr-x@ 4 spotted staff 128 Nov 20 07:11 .github | |
-rwxr-xr-x@ 1 spotted staff 59 Nov 20 07:11 .gitignore | |
-rwxr-xr-x@ 1 spotted staff 228 Nov 20 07:11 .mergify.yml | |
drwxr-xr-x@ 4 spotted staff 128 Nov 20 07:11 .mvn | |
-rwxr-xr-x@ 1 spotted staff 546 Nov 20 07:11 .travis.yml | |
-rwxr-xr-x@ 1 spotted staff 3225 Nov 20 07:11 CODE_OF_CONDUCT.md | |
-rwxr-xr-x@ 1 spotted staff 4688 Nov 20 07:11 CONTRIBUTING.md | |
-rw-r--r--@ 1 spotted staff 701 Nov 21 19:39 Dockerfile | |
-rwxr-xr-x@ 1 spotted staff 11358 Nov 20 07:11 LICENSE | |
-rwxr-xr-x@ 1 spotted staff 137 Nov 20 07:11 NOTICE | |
-rwxr-xr-x@ 1 spotted staff 5356 Nov 20 07:11 README.md | |
drwxr-xr-x@ 5 spotted staff 160 Nov 21 17:01 beans | |
drwxr-xr-x@ 4 spotted staff 128 Nov 20 07:11 cli | |
drwxr-xr-x@ 5 spotted staff 160 Nov 21 18:16 config | |
drwxr-xr-x@ 4 spotted staff 128 Nov 21 16:30 contrib | |
drwxr-xr-x@ 4 spotted staff 128 Nov 20 07:11 core | |
drwxr-xr-x@ 6 spotted staff 192 Nov 20 07:11 crawler | |
-rwxr-xr-x@ 1 spotted staff 235 Nov 20 07:11 deploy-settings.xml | |
drwxr-xr-x@ 7 spotted staff 224 Nov 21 18:13 distribution | |
drwxr-xr-x@ 7 spotted staff 224 Nov 20 07:11 docs | |
drwxr-xr-x@ 7 spotted staff 224 Nov 21 19:24 elasticsearch-client | |
drwxr-xr-x@ 4 spotted staff 128 Nov 20 07:11 framework | |
drwxr-xr-x@ 6 spotted staff 192 Nov 20 07:11 integration-tests | |
-rwxr-xr-x@ 1 spotted staff 79 Nov 20 07:11 lgtm.yml | |
-rwxr-xr-x@ 1 spotted staff 45158 Nov 20 07:11 pom.xml | |
-rwxr-xr-x@ 1 spotted staff 6969 Nov 20 07:11 release.sh | |
drwxr-xr-x@ 4 spotted staff 128 Nov 20 07:11 rest | |
drwxr-xr-x@ 4 spotted staff 128 Nov 20 07:11 settings | |
drwxr-xr-x@ 4 spotted staff 128 Nov 21 16:15 src | |
drwxr-xr-x@ 4 spotted staff 128 Nov 20 07:11 test-documents | |
drwxr-xr-x@ 4 spotted staff 128 Nov 20 07:11 test-framework | |
drwxr-xr-x@ 4 spotted staff 128 Nov 20 07:11 tika | |
-rwxr-xr-x@ 1 spotted staff 291 Nov 20 07:11 travis.sh | |
-rwxr-xr-x@ 1 spotted staff 5224 Nov 20 07:11 wait-for-it.sh |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment