[R-package] [ci] Reduce manual effort for version updates (#3335)

* [R-package] [ci] Reduce manual effort for version updates

* fix configure

* remove useless comment

* Update build_r.R
Co-authored-by: Guolin Ke <guolin.ke@outlook.com>

* fix recreate-configure check in CI
Co-authored-by: Guolin Ke <guolin.ke@outlook.com>

.ci/test_r_package.sh

@@ -134,12 +134,7 @@ elif [[ $R_BUILD_TYPE == "cran" ]]; then
     # on Linux, we recreate configure in CI to test if
     # a change in a PR has changed configure.ac
     if [[ $OS_NAME == "linux" ]]; then
-        cd ${BUILD_DIRECTORY}/R-package
-        autoconf \
-            --output configure \
-                configure.ac \
-        || exit -1
-        cd ${BUILD_DIRECTORY}
+        ${BUILD_DIRECTORY}/R-package/recreate-configure.sh
 
         num_files_changed=$(
             git diff --name-only | wc -l

R-package/DESCRIPTION

 Package: lightgbm
 Type: Package
 Title: Light Gradient Boosting Machine
-Version: 3.0.0-1
-Date: 2020-08-06
+Version: ~~VERSION~~
+Date: ~~DATE~~
 Authors@R: c(
     person("Guolin", "Ke", email = "guolin.ke@microsoft.com", role = c("aut", "cre")),
     person("Damien", "Soukhavong", email = "damien.soukhavong@skema.edu", role = c("aut")),

R-package/README.md

@@ -250,7 +250,7 @@ At build time, `configure` will be run and used to create a file `Makevars`, usi
     ./R-package/recreate-configure.sh
     ```
 
-    If you do not have easy access to an Ubuntu 18.04 environment, the `configure` script can be generated using Docker.
+    If you do not have easy access to an Ubuntu 18.04 environment, the `configure` script can be generated using Docker by running the code below from the root of this repo.
 
     ```shell
     docker run \

R-package/configure

 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for lightgbm 3.0.0-1.
+# Generated by GNU Autoconf 2.69 for lightgbm 3.0.0.
 #
 #
 # Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@@ -576,8 +576,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='lightgbm'
 PACKAGE_TARNAME='lightgbm'
-PACKAGE_VERSION='3.0.0-1'
-PACKAGE_STRING='lightgbm 3.0.0-1'
+PACKAGE_VERSION='3.0.0'
+PACKAGE_STRING='lightgbm 3.0.0'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1182,7 +1182,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures lightgbm 3.0.0-1 to adapt to many kinds of systems.
+\`configure' configures lightgbm 3.0.0 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1244,7 +1244,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of lightgbm 3.0.0-1:";;
+     short | recursive ) echo "Configuration of lightgbm 3.0.0:";;
    esac
   cat <<\_ACEOF
 
@@ -1311,7 +1311,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-lightgbm configure 3.0.0-1
+lightgbm configure 3.0.0
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1328,7 +1328,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by lightgbm $as_me 3.0.0-1, which was
+It was created by lightgbm $as_me 3.0.0, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -2377,7 +2377,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by lightgbm $as_me 3.0.0-1, which was
+This file was extended by lightgbm $as_me 3.0.0, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -2430,7 +2430,7 @@ _ACEOF
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-lightgbm config.status 3.0.0-1
+lightgbm config.status 3.0.0
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

R-package/configure.ac

@@ -4,7 +4,7 @@
 #   * https://cran.r-project.org/doc/manuals/r-release/R-exts.html#Configure-and-cleanup
 
 AC_PREREQ(2.69)
-AC_INIT([lightgbm], [3.0.0-1], [], [lightgbm], [])
+AC_INIT([lightgbm], [~~VERSION~~], [], [lightgbm], [])
 
 ###########################
 # find compiler and flags #

R-package/recreate-configure.sh

@@ -4,6 +4,14 @@
 # this script should run on Ubuntu 18.04
 AUTOCONF_VERSION=$(cat R-package/AUTOCONF_UBUNTU_VERSION)
 
+# R packages cannot have versions like 3.0.0rc1, but
+# 3.0.0-1 is acceptable
+LGB_VERSION=$(cat VERSION.txt | sed "s/rc/-/g")
+
+# this script changes configure.ac. Copying to a temporary file
+# so changes to configure.ac don't get committed in git
+TMP_CONFIGURE_AC=".configure.ac"
+
 echo "Creating 'configure' script with Autoconf ${AUTOCONF_VERSION}"
 
 apt update
@@ -13,11 +21,17 @@ apt-get install \
         autoconf=${AUTOCONF_VERSION}
 
 cd R-package
+
+cp configure.ac ${TMP_CONFIGURE_AC}
+sed -i.bak -e "s/~~VERSION~~/${LGB_VERSION}/" ${TMP_CONFIGURE_AC}
+
 autoconf \
     --output configure \
-    configure.ac \
+    ${TMP_CONFIGURE_AC} \
     || exit -1
 
+rm ${TMP_CONFIGURE_AC}
+
 rm -r autom4te.cache || echo "no autoconf cache found"
 
 echo "done creating 'configure' script"

build-cran-package.sh

@@ -17,6 +17,12 @@ if test -d ${TEMP_R_DIR}; then
 fi
 mkdir -p ${TEMP_R_DIR}
 
+CURRENT_DATE=$(date +'%Y-%m-%d')
+
+# R packages cannot have versions like 3.0.0rc1, but
+# 3.0.0-1 is acceptable
+LGB_VERSION=$(cat VERSION.txt | sed "s/rc/-/g")
+
 # move relevant files
 cp -R R-package/* ${TEMP_R_DIR}
 cp -R include ${TEMP_R_DIR}/src/
@@ -38,6 +44,12 @@ cd ${TEMP_R_DIR}
     # for the R package
     rm src/main.cpp
 
+    # configure.ac and DESCRIPTION have placeholders for version
+    # and date so they don't have to be updated manually
+    sed -i.bak -e "s/~~VERSION~~/${LGB_VERSION}/" configure.ac
+    sed -i.bak -e "s/~~VERSION~~/${LGB_VERSION}/" DESCRIPTION
+    sed -i.bak -e "s/~~DATE~~/${CURRENT_DATE}/" DESCRIPTION
+
     # Remove 'region' and 'endregion' pragmas. This won't change
     # the correctness of the code. CRAN does not allow you
     # to use compiler flag '-Wno-unknown-pragmas' or

build_r.R

@@ -155,6 +155,31 @@ result <- file.copy(
 )
 .handle_result(result)
 
+# R packages cannot have versions like 3.0.0rc1, but
+# 3.0.0-1 is acceptable
+LGB_VERSION <- readLines("VERSION.txt")[1L]
+LGB_VERSION <- gsub(
+  pattern = "rc"
+  , replacement = "-"
+  , x = LGB_VERSION
+)
+
+# DESCRIPTION has placeholders for version
+# and date so it doesn't have to be updated manually
+DESCRIPTION_FILE <- file.path(TEMP_R_DIR, "DESCRIPTION")
+description_contents <- readLines(DESCRIPTION_FILE)
+description_contents <- gsub(
+  pattern = "~~VERSION~~"
+  , replacement = LGB_VERSION
+  , x = description_contents
+)
+description_contents <- gsub(
+  pattern = "~~DATE~~"
+  , replacement = as.character(Sys.Date())
+  , x = description_contents
+)
+writeLines(description_contents, DESCRIPTION_FILE)
+
 # NOTE: --keep-empty-dirs is necessary to keep the deep paths expected
 #       by CMake while also meeting the CRAN req to create object files
 #       on demand