From 0e12e314204c48ec9930bf5dfa9c1de6f0b1636b Mon Sep 17 00:00:00 2001
From: Markus Scherer <markus.icu@gmail.com>
Date: Wed, 27 Nov 2024 16:27:32 -0800
Subject: [PATCH] script: publish early UCD snapshot

---
 docs/data-workflow.md    | 22 +++++++++++++++
 pub/copy-ucd-to-draft.sh | 60 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 82 insertions(+)
 create mode 100755 pub/copy-ucd-to-draft.sh

diff --git a/docs/data-workflow.md b/docs/data-workflow.md
index 102ab8433..01cd0a68f 100644
--- a/docs/data-workflow.md
+++ b/docs/data-workflow.md
@@ -91,6 +91,28 @@ Make sure to publish exactly the intended set of files.
 Skip the NamesList.txt and Unihan data files (see above),
 and skip any others that are only for internal use.
 
+### Publish a UCD snapshot
+
+When we have a usable snapshot of the UCD for new repertoire, we should publish the data files,
+so that the Charts WG and others can pick them up for their work.
+As a pre-alpha snapshot, we do not yet publish security/IDNA/emoji files.
+
+Review/edit the pub/*.sh scripts and advance the version numbers and copyright years.
+
+Run the [pub/copy-ucd-to-draft.sh](https://github.com/unicode-org/unicodetools/blob/main/pub/copy-ucd-to-draft.sh)
+script from an up-to-date repo workspace.
+The script copies the set of the .../dev/ data files for an alpha snapshot
+from a unicodetools workspace to a target folder with the layout of https://www.unicode.org/Public/draft/ .
+
+Send the resulting zip file to Rick for posting to https://www.unicode.org/Public/draft/ .
+Ask Rick to add other files that are not tracked in the unicodetools repo:
+*   Unihan.zip to .../draft/UCD/ucd
+
+TODO: Figure out new process & people replacing Rick in 2025.
+
+Note: No version/delta infixes in names of data files.
+We simply use the “draft” folder and the file-internal time stamps for versioning.
+
 ### Publish an alpha snapshot
 
 For the alpha review, publish (at least) the UCD and emoji files, and the charts.
diff --git a/pub/copy-ucd-to-draft.sh b/pub/copy-ucd-to-draft.sh
new file mode 100755
index 000000000..041cd042c
--- /dev/null
+++ b/pub/copy-ucd-to-draft.sh
@@ -0,0 +1,60 @@
+# Script for
+# https://github.com/unicode-org/unicodetools/blob/main/docs/data-workflow.md#publish-a-ucd-snapshot
+#
+# Invoke like this:
+#
+# pub/copy-ucd-to-draft.sh  ~/unitools/mine/src  /tmp/unicode/Public/draft
+
+UNICODETOOLS=$1
+DRAFT=$2
+
+UNITOOLS_DATA=$UNICODETOOLS/unicodetools/data
+
+# Adjust the following for each year and version as needed.
+COPY_YEAR=2024
+UNI_VER=17.0.0
+EMOJI_VER=17.0
+
+TODAY=`date --iso-8601`
+
+mkdir -p $DRAFT
+
+cat > $DRAFT/sed-readmes.txt << eof
+s/COPY_YEAR/$COPY_YEAR/
+s/PUB_DATE/$TODAY/
+s/PUB_STATUS/draft/
+s/UNI_VER/$UNI_VER/
+s/EMOJI_VER/$EMOJI_VER/
+s%PUBLIC_EMOJI%Public/draft/emoji%
+s%PUBLIC_UCD%Public/draft/UCD%
+eof
+
+mkdir -p $DRAFT/UCD/ucd
+mkdir -p $DRAFT/zipped
+cp -r $UNITOOLS_DATA/ucd/dev/* $DRAFT/UCD/ucd
+rm -r $DRAFT/UCD/ucd/Unihan
+rm -r $DRAFT/UCD/ucd/emoji
+mv $DRAFT/UCD/ucd/version-ReadMe.txt $DRAFT/UCD/ReadMe.txt
+mv $DRAFT/UCD/ucd/zipped-ReadMe.txt $DRAFT/zipped/ReadMe.txt
+
+# Fix permissions. Everyone can read, and search directories.
+chmod a+rX -R $DRAFT
+
+# Update the readmes in-place (-i) as set up above.
+find $DRAFT -name '*ReadMe.txt' | xargs sed -i -f $DRAFT/sed-readmes.txt
+
+# Zip files for some types of data, after fixing permissions
+rm $DRAFT/UCD/ucd/UCD.zip
+(cd $DRAFT/UCD/ucd; zip -r UCD.zip * && mv UCD.zip $DRAFT/zipped)
+
+# Cleanup
+rm $DRAFT/sed-readmes.txt
+
+rm $DRAFT/ucd-snapshot.zip
+(cd $DRAFT; zip -r ucd-snapshot.zip *)
+
+echo "--------------------"
+echo "Copy files from elsewhere:"
+echo "- Unihan.zip to $DRAFT/UCD/ucd"
+echo "- Unihan.zip to $DRAFT/zipped"
+