-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
96 changed files
with
8,150 additions
and
12,953 deletions.
There are no files selected for viewing
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,64 @@ | ||
| name: ARCHE-Ingest | ||
|
|
||
| on: | ||
| workflow_dispatch | ||
|
|
||
| jobs: | ||
| build_pages: | ||
| name: Ingest Data into ARCHE | ||
| runs-on: ubuntu-latest | ||
| env: | ||
| ANT_OPTS: -Xmx5g | ||
| REDMINE_ID: 20352 | ||
| ARCHE_INSTANCE: arche-curation.acdh-dev | ||
| ARCHE_INSTANCE_NAME: Curation | ||
| PROJECT_NAME : auden-musulin-papers | ||
| OUTPUT_DIR: rdf | ||
| DATA_DIR: data/editions | ||
| META_DIR: data/metadata | ||
| INDICES_DIR: data/indexes | ||
| steps: | ||
| - name: Perform Checkout | ||
| uses: actions/checkout@v3 | ||
| - name: ingestion dependencies | ||
| run: | | ||
| composer require "acdh-oeaw/arche-ingest:^1" | ||
| - name: Fetch WF-URL | ||
| run: | | ||
| echo "RUN_URL=$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID" >> $GITHUB_ENV | ||
| - name: ingest arche metadata topcol, col, res | ||
| run: | | ||
| echo 'STEP=Upload AIP to ${ARCHE_INSTANCE_NAME} Instance' >> $GITHUB_ENV | ||
| vendor/bin/arche-import-metadata ${OUTPUT_DIR}/arche.ttl https://${ARCHE_INSTANCE}.oeaw.ac.at/api ${{secrets.ARCHE_LOGIN}} ${{secrets.ARCHE_PASSWORD}} --retriesOnConflict 25 | ||
| # vendor/bin/arche-update-redmine --token ${{ secrets.REDMINE_TOKEN }} --append "$RUN_URL" $REDMINE_ID 'Upload AIP to ${ARCHE_INSTANCE_NAME} Instance' | ||
| - name: Copy XML Files to to_ingest | ||
| run: | | ||
| mkdir $PWD/to_ingest | ||
| find -path "./${DATA_DIR}/*.xml" -exec cp -prv '{}' './to_ingest' ';' | ||
| find -path "./${INDICES_DIR}/*.xml" -exec cp -prv '{}' './to_ingest' ';' | ||
| find -path "./${META_DIR}/*.odd" -exec cp -prv '{}' './to_ingest' ';' | ||
| find -path "./${META_DIR}/*.rng" -exec cp -prv '{}' './to_ingest' ';' | ||
| - name: cache AV database | ||
| id: avdb | ||
| uses: actions/cache@v3 | ||
| with: | ||
| path: ~/.cvdupdate | ||
| key: constant | ||
| - name: refresh AV database | ||
| run: | | ||
| python3 -m pip install --user cvdupdate && cvd update | ||
| - name: run repo-file-checker | ||
| run: | | ||
| echo 'STEP=Run repo-file-checker' >> $GITHUB_ENV | ||
| docker run --rm -d --name filechecker -v `pwd`/filechecker/reports:/reports -v `pwd`/to_ingest:/data -v ~/.cvdupdate/database/:/var/lib/clamav -e DAEMONIZE=1 acdhch/arche-filechecker | ||
| # vendor/bin/arche-update-redmine --token ${{ secrets.REDMINE_TOKEN }} --append "$RUN_URL" $REDMINE_ID 'Virus scan' | ||
| # vendor/bin/arche-update-redmine --token ${{ secrets.REDMINE_TOKEN }} --append "$RUN_URL" $REDMINE_ID 'Run repo-file-checker' | ||
| - name: ingest binaries | ||
| run: | | ||
| echo 'STEP=Upload Binaries' >> $GITHUB_ENV | ||
| vendor/bin/arche-import-binary to_ingest https://id.acdh.oeaw.ac.at/${PROJECT_NAME} https://${ARCHE_INSTANCE}.oeaw.ac.at/api ${{secrets.ARCHE_LOGIN}} ${{secrets.ARCHE_PASSWORD}} --skip not_exist | ||
| # vendor/bin/arche-update-redmine --token ${{ secrets.REDMINE_TOKEN }} --append "$RUN_URL" $REDMINE_ID 'Upload AIP to ${ARCHE_INSTANCE_NAME} Instance' | ||
| - name: on failure | ||
| if: ${{ failure() }} | ||
| run: | | ||
| vendor/bin/arche-update-redmine --token ${{ secrets.REDMINE_TOKEN }} --append "$RUN_URL" --statusCode 1 $REDMINE_ID "$STEP" |
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -138,4 +138,5 @@ requirements_php.txt | |
| composer.* | ||
| /filechecker | ||
| /to_ingest | ||
| /data/images | ||
| /data/images | ||
| /saxon | ||
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,30 @@ | ||
| <?xml version="1.0" encoding="UTF-8"?> | ||
| <project basedir="." name="tei2html"> | ||
| <property name="xsl_preprocess" value="${basedir}/preprocess.xsl"/> | ||
| <property name="editions" value="${basedir}/data/editions"/> | ||
| <property name="indexes" value="${basedir}/data/indexes"/> | ||
| <property name="target" value="${basedir}/data/tmp"/> | ||
| <property name="target_id" value="${basedir}/data/tmp_id"/> | ||
|
|
||
| <mkdir dir="${target}"/> | ||
| <mkdir dir="${target_id}"/> | ||
|
|
||
| <xslt style="${xsl_preprocess}" basedir="${editions}" destdir="${target}" includes="*.xml" extension=".xml"> | ||
| <factory name="net.sf.saxon.TransformerFactoryImpl"/> | ||
| <classpath location="${basedir}/saxon/saxon9he.jar"/> | ||
| </xslt> | ||
| <xslt style="${xsl_preprocess}" basedir="${indexes}" destdir="${target_id}" includes="*.xml" extension=".xml"> | ||
| <factory name="net.sf.saxon.TransformerFactoryImpl"/> | ||
| <classpath location="${basedir}/saxon/saxon9he.jar"/> | ||
| </xslt> | ||
|
|
||
| <copy todir="${editions}"> | ||
| <fileset dir="${target}" includes="*.xml"/> | ||
| </copy> | ||
| <copy todir="${indexes}"> | ||
| <fileset dir="${target_id}" includes="*.xml"/> | ||
| </copy> | ||
| <delete dir="${target}"/> | ||
| <delete dir="${target_id}"/> | ||
|
|
||
| </project> |
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
Oops, something went wrong.