From 994c0df0b98fab4f10ac987f13302e0eb3aa07a9 Mon Sep 17 00:00:00 2001
From: Justin Pryzby <pryzbyj@telsasoft.com>
Date: Sat, 26 Feb 2022 19:39:10 -0600
Subject: [PATCH 08/10] 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

ci-os-only: html
---
 .cirrus.yml                    | 31 ++++++++++++++++++++++++++++---
 src/tools/ci/copy-changed-docs | 29 +++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+), 3 deletions(-)
 create mode 100755 src/tools/ci/copy-changed-docs

diff --git a/.cirrus.yml b/.cirrus.yml
index 0bc7c5e3796..2f2c09027d8 100644
--- a/.cirrus.yml
+++ b/.cirrus.yml
@@ -27,6 +27,14 @@ env:
   TEMP_CONFIG: ${CIRRUS_WORKING_DIR}/src/tools/ci/pg_ci_base.conf
   PG_TEST_EXTRA: kerberos ldap ssl
 
+  # 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: 3d14e171e9e2236139e8976f3309a588bcc8683b
 
 # What files to preserve in case tests fail
 on_failure_ac: &on_failure_ac
@@ -756,7 +764,7 @@ task:
 
 
 ###
-# Verify docs can be built
+# Verify docs can be built, and upload changed docs as artifacts
 # changesInclude() will skip this task if none of the commits since
 # CIRRUS_LAST_GREEN_CHANGE touched any relevant files. The comparison appears
 # to be like "git log a..b -- ./file", not "git diff a..b -- ./file"
@@ -764,18 +772,21 @@ task:
 
 task:
   name: Documentation
+  only_if: $CIRRUS_CHANGE_MESSAGE !=~ '.*\nci-os-only:.*' || $CIRRUS_CHANGE_MESSAGE =~ '.*\nci-os-only:[^\n]*(docs|html).*'
+  #skip: "!changesInclude('.cirrus.yml', 'doc/**', 'src/tools/ci/copy-changed-docs')"
 
   env:
     CPUS: 1
     BUILD_JOBS: 1
 
-  only_if: $CIRRUS_CHANGE_MESSAGE !=~ '.*\nci-os-only:.*' || $CIRRUS_CHANGE_MESSAGE =~ '.*\nci-os-only:[^\n]*(docs|html).*'
-
   container:
     image: $CONTAINER_REPO/linux_debian_bullseye_ci:latest
     cpu: $CPUS
     memory: 2G
 
+  sysinfo_script: |
+    git diff --name-only "$BASE_COMMIT"
+
   # Exercise HTML and other docs:
   ninja_docs_build_script: |
     mkdir build-ninja
@@ -787,3 +798,17 @@ task:
   docs_build_script: |
     time ./configure
     make -s -j${BUILD_JOBS} -C doc
+    cp -r doc new-docs
+
+    # Build HTML docs from the base commit.
+    git checkout "$BASE_COMMIT" -- doc
+    #html-stamp
+    make -s -C doc clean
+    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']
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
-- 
2.25.1