-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
initial implementation of release script (preparation for v4.0) #205
- Loading branch information
1 parent
cbfbbd9
commit ea119ef
Showing
15 changed files
with
1,983 additions
and
522 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 +1,54 @@ | ||
|
||
|
||
|
||
|
||
PWD=$(shell pwd) | ||
DATA-RELEASE=$(PWD)/data/release/ | ||
SAMPLE-DATA-IN=$(PWD)/data/sample-in/ | ||
DATA-IN=$(SAMPLE-DATA-IN) | ||
SAMPLE-DATA-SOURCE=parczech:/opt/data/data-ParlaMint3.1-FRESH/ | ||
|
||
|
||
|
||
|
||
release: | ||
mkdir -p $(DATA-RELEASE)/ | ||
$s -xsl:tools/ParCzech-finalize.xsl \ | ||
outDir=$(DATA-RELEASE)/ \ | ||
inListPerson=$(DATA-IN)/parczech.tei.ana/consolidated/ParCzech-listPerson.xml \ | ||
inListOrg=$(DATA-IN)/parczech.tei.ana/consolidated/ParCzech-listOrg.xml \ | ||
inTaxonomiesDir=$(PWD)/metadater/taxonomies/ \ | ||
type=TEI.ana \ | ||
$(DATA-IN)/parczech.tei.ana/consolidated/ParCzech.ana.xml | ||
cp ./tei2teitok/pdt-fslib.xml $(DATA-RELEASE)/ParCzech.TEI.ana/ | ||
|
||
|
||
|
||
|
||
|
||
DEV-clean-sample-for-release: | ||
rm -r $(SAMPLE-DATA-IN)/parczech.tei.* | ||
DEV-prepare-sample-for-release: DEV-prepare-sample-for-release-raw DEV-prepare-sample-for-release-ana | ||
|
||
DEV-prepare-sample-for-release-raw DEV-prepare-sample-for-release-ana: DEV-prepare-sample-for-release-%: | ||
mkdir -p $(SAMPLE-DATA-IN)/parczech.tei.$* || : | ||
rsync -a --exclude='*/' $(SAMPLE-DATA-SOURCE)/parczech.tei.$*/consolidated/ $(SAMPLE-DATA-IN)/parczech.tei.$*/consolidated/ | ||
@echo "INFO: [$*] sync files in root folder" | ||
xmlstarlet edit --inplace \ | ||
--delete "/_:teiCorpus/xi:include[not(position() = 1 or position() = last() )]" \ | ||
$(SAMPLE-DATA-IN)/parczech.tei.$*/consolidated/ParCzech.*xml | ||
@echo "INFO: [$*] sync component files" | ||
echo $(SAMPLE-DATA-IN)/parczech.tei.$*/consolidated/ParCzech.*xml \ | ||
| xargs ${getcomponentincludes} \ | ||
| xargs -I {} scp $(SAMPLE-DATA-SOURCE)/parczech.tei.$*/consolidated/{} $(SAMPLE-DATA-IN)/parczech.tei.$*/consolidated/{} | ||
make DEV-prepare-sample-for-release-$*-fix | ||
|
||
DEV-prepare-sample-for-release-raw-fix: # raw specific issues | ||
|
||
DEV-prepare-sample-for-release-ana-fix: # ana specific issues | ||
|
||
|
||
###################x | ||
s = java $(JM) -jar /usr/share/java/saxon.jar | ||
j = java $(JM) -jar /usr/share/java/jing.jar | ||
getcomponentincludes = -I % java -cp /usr/share/java/saxon.jar net.sf.saxon.Query -xi:off \!method=adaptive -qs:'/*/*[local-name()="include"]/@href' -s:% |sed 's/^ *href="//;s/"//' |
2 changes: 1 addition & 1 deletion
2
...dater/taxonomies/taxonomy-NER.cnec2.0.xml → ...ies/ParCzech-taxonomy-NER.cnec2.0.ana.xml
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 |
---|---|---|
@@ -0,0 +1,9 @@ | ||
<?xml version="1.0" encoding="UTF-8"?> | ||
<taxonomy xmlns="http://www.tei-c.org/ns/1.0" xml:id="ParCzech-taxonomy-meeting.parts" xml:lang="mul"> | ||
<desc xml:lang="cs"><term>Bod</term></desc> | ||
<desc xml:lang="en"><term>Agenda</term></desc> | ||
<category xml:id="parla.agenda"> | ||
<catDesc xml:lang="cs"><term>Bod jednání</term></catDesc> | ||
<catDesc xml:lang="en"><term>Agenda</term>: topic discussed during sitting</catDesc> | ||
</category> | ||
</taxonomy> |
2 changes: 1 addition & 1 deletion
2
...dater/taxonomies/taxonomy-parla.links.xml → ...onomies/ParCzech-taxonomy-parla.links.xml
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 |
---|---|---|
@@ -0,0 +1,21 @@ | ||
<?xml version="1.0" encoding="UTF-8"?> | ||
<taxonomy xmlns="http://www.tei-c.org/ns/1.0" xml:id="ParlaMint-taxonomy-NER.ana" xml:lang="mul"> | ||
<desc xml:lang="en"><term>Named entities</term></desc> | ||
<desc xml:lang="cs"><term>Jmenné entity</term></desc> | ||
<category xml:id="PER"> | ||
<catDesc xml:lang="en"><term>person</term></catDesc> | ||
<catDesc xml:lang="cs"><term>osoba</term></catDesc> | ||
</category> | ||
<category xml:id="LOC"> | ||
<catDesc xml:lang="en"><term>location</term></catDesc> | ||
<catDesc xml:lang="cs"><term>místo</term></catDesc> | ||
</category> | ||
<category xml:id="ORG"> | ||
<catDesc xml:lang="en"><term>organization</term></catDesc> | ||
<catDesc xml:lang="cs"><term>organizace</term></catDesc> | ||
</category> | ||
<category xml:id="MISC"> | ||
<catDesc xml:lang="en"><term>miscellaneous</term></catDesc> | ||
<catDesc xml:lang="cs"><term>různé</term></catDesc> | ||
</category> | ||
</taxonomy> |
Oops, something went wrong.