From e028901375221cc6bcdc102132fcf884fdf51fae Mon Sep 17 00:00:00 2001
From: Justin Pryzby <pryzbyj@telsasoft.com>
Date: Sat, 26 Feb 2022 19:39:10 -0600
Subject: [PATCH 4/6] WIP: cirrus: upload changed html docs as artifacts

This could be done on the client side (cfbot).  One advantage of doing
it here is that fewer docs are uploaded - many patches won't upload docs
at all.

https://www.postgresql.org/message-id/flat/20220409021853.GP24419@telsasoft.com
https://www.postgresql.org/message-id/CAB8KJ=i4qmEuopQ+PCSMBzGd4O-Xv0FCnC+q1x7hN9hsdvkBug@mail.gmail.com

https://cirrus-ci.com/task/5396696388599808

//-os-only:
---
 .cirrus.tasks.yml              | 25 ++++++++++++++++++++++++-
 src/tools/ci/copy-changed-docs | 29 +++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+), 1 deletion(-)
 create mode 100755 src/tools/ci/copy-changed-docs

diff --git a/.cirrus.tasks.yml b/.cirrus.tasks.yml
index 8ed7f7e5dd7..8b07fb2e538 100644
--- a/.cirrus.tasks.yml
+++ b/.cirrus.tasks.yml
@@ -23,6 +23,15 @@ env:
   PG_TEST_EXTRA: kerberos ldap ssl libpq_encryption load_balance
   PG_FAILED_TESTDIR: ${CIRRUS_WORKING_DIR}/failed.build
 
+  # The commit that this branch is rebased on.  There's no easy way to find this.
+  # This does the right thing for cfbot, which always squishes all patches into a single commit.
+  # And does the right thing for any 1-patch commits.
+  # Patch series manually submitted to cirrus would benefit from setting this to the
+  # number of patches in the series (or directly to the commit the series was rebased on).
+  #BASE_COMMIT: HEAD~1
+  # For demo purposes:
+  BASE_COMMIT: HEAD~55
+
 
 # What files to preserve in case tests fail
 on_failure_ac: &on_failure_ac
@@ -783,7 +792,7 @@ task:
       time make -s -j${BUILD_JOBS} world-bin
 
   ###
-  # Verify docs can be built
+  # Verify docs can be built, and upload changed docs as artifacts
   ###
   # XXX: Only do this if there have been changes in doc/ since last build
   always:
@@ -793,6 +802,20 @@ task:
         CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang-16"
       make -s -j${BUILD_JOBS} clean
       time make -s -j${BUILD_JOBS} -C doc
+      cp -r doc new-docs
+
+      # Re-build HTML docs from the base commit.
+      git checkout "$BASE_COMMIT" -- doc
+      make -s -C doc clean
+      time make -s -C doc html
+      cp -r doc old-docs
+
+    copy_changed_docs_script:
+      - src/tools/ci/copy-changed-docs "old-docs" "new-docs" "html_docs"
+
+    html_docs_artifacts:
+      paths: ['html_docs/*.html', 'html_docs/*.png', 'html_docs/*.css']
+
 
   ###
   # Verify headerscheck / cpluspluscheck succeed
diff --git a/src/tools/ci/copy-changed-docs b/src/tools/ci/copy-changed-docs
new file mode 100755
index 00000000000..1c921a8df6f
--- /dev/null
+++ b/src/tools/ci/copy-changed-docs
@@ -0,0 +1,29 @@
+#! /bin/sh
+# Copy HTML which differ between $old and $new into $outdir
+set -e
+
+old=$1
+new=$2
+outdir=$3
+
+# The index is large and changes often
+skippages="bookindex.html"
+
+mkdir "$outdir"
+cp "$new"/src/sgml/html/*.css "$new"/src/sgml/html/*.svg "$outdir"
+
+changed=`git diff --no-index --name-only "$old"/src/sgml/html "$new"/src/sgml/html` ||
+	[ $? -eq 1 ]
+
+for f in $changed
+do
+	# Avoid removed files
+	[ -f "$f" ] || continue
+
+	echo "$f" |grep -Ew "$skippages" >/dev/null &&
+		continue
+
+	cp -v "$f" "$outdir"
+done
+
+exit 0
-- 
2.42.0