1
0
mirror of https://github.com/vimagick/dockerfiles.git synced 2024-12-25 02:04:06 +02:00

add reconcile-csv

This commit is contained in:
kev 2016-07-06 18:41:50 +08:00
parent b94a1f6a9b
commit 308f770503
4 changed files with 80 additions and 0 deletions

View File

@ -0,0 +1,15 @@
#
# Dockerfile for openrefine-reconcile-csv
#
FROM java:8-jre-alpine
MAINTAINER kev <noreply@easypi.info>
ADD http://okfnlabs.org/reconcile-csv/dist/reconcile-csv-0.1.2.jar /app/
WORKDIR /data
EXPOSE 8000
CMD java -jar /app/reconcile-csv-0.1.2.jar "${CSV_FILE}" "${SEARCH_COLUMN}" "${ID_COLUMN}"

View File

@ -0,0 +1,47 @@
reconcile-csv
=============
[Reconcile-csv][1] is a reconciliation service for [OpenRefine][2] running from a
CSV file. It uses fuzzy matching to match entries in one dataset to entries in
another dataset, helping to introduce unique IDs into the system - so they can
be used to join your data painlessly.
## docker-compose.yml
```yaml
reconcile-csv:
image: vimagick/openrefine-reconcile-csv
ports:
- "8000:8000"
volumes:
- ./data:/data
environment:
- JAVA_OPTS=-Xmx2g
- CSV_FILE=input.csv
- SEARCH_COLUMN=name
- ID_COLUMN=id
restart: always
```
## input.csv
```csv
id,name
1,kevin
2,tom
3,sarah
4,mike
5,lucy
```
## up and running
```bash
$ docker-compose up -d
$ curl http://localhost:8000/reconcile?query=kev
$ curl http://localhost:8000/reconcile?query={%22query%22:%22kev%22,%22limit%22:1}
$ curl http://localhost:8000/view/1
```
[1]: http://okfnlabs.org/reconcile-csv/
[2]: https://github.com/OpenRefine/OpenRefine/wiki

View File

@ -0,0 +1,6 @@
id,name
1,kevin
2,tom
3,sarah
4,mike
5,lucy
1 id name
2 1 kevin
3 2 tom
4 3 sarah
5 4 mike
6 5 lucy

View File

@ -0,0 +1,12 @@
reconcile-csv:
image: vimagick/openrefine-reconcile-csv
ports:
- "8000:8000"
volumes:
- ./data:/data
environment:
- JAVA_OPTS=-Xmx2g
- CSV_FILE=input.csv
- SEARCH_COLUMN=name
- ID_COLUMN=id
restart: unless-stopped