Merge branch 'jk/sh-setup-in-filter-branch'

Refactoring to avoid code duplication in shell scripts.

* jk/sh-setup-in-filter-branch:
  filter-branch: use git-sh-setup's ident parsing functions
  git-sh-setup: refactor ident-parsing functions

3 files changed, 59 insertions, 54 deletions

diff --git a/git-filter-branch.sh b/git-filter-branch.sh
index 178e45305d..53142492af 100755
--- a/git-filter-branch.sh
+++ b/git-filter-branch.sh
@@ -64,37 +64,19 @@ EOF
 
 eval "$functions"
 
-# When piped a commit, output a script to set the ident of either
-# "author" or "committer
+finish_ident() {
+	# Ensure non-empty id name.
+	echo "case \"\$GIT_$1_NAME\" in \"\") GIT_$1_NAME=\"\${GIT_$1_EMAIL%%@*}\" && export GIT_$1_NAME;; esac"
+	# And make sure everything is exported.
+	echo "export GIT_$1_NAME"
+	echo "export GIT_$1_EMAIL"
+	echo "export GIT_$1_DATE"
+}
 
 set_ident () {
-	lid="$(echo "$1" | tr "[A-Z]" "[a-z]")"
-	uid="$(echo "$1" | tr "[a-z]" "[A-Z]")"
-	pick_id_script='
-		/^'$lid' /{
-			s/'\''/'\''\\'\'\''/g
-			h
-			s/^'$lid' \([^<]*\) <[^>]*> .*$/\1/
-			s/'\''/'\''\'\'\''/g
-			s/.*/GIT_'$uid'_NAME='\''&'\''; export GIT_'$uid'_NAME/p
-
-			g
-			s/^'$lid' [^<]* <\([^>]*\)> .*$/\1/
-			s/'\''/'\''\'\'\''/g
-			s/.*/GIT_'$uid'_EMAIL='\''&'\''; export GIT_'$uid'_EMAIL/p
-
-			g
-			s/^'$lid' [^<]* <[^>]*> \(.*\)$/@\1/
-			s/'\''/'\''\'\'\''/g
-			s/.*/GIT_'$uid'_DATE='\''&'\''; export GIT_'$uid'_DATE/p
-
-			q
-		}
-	'
-
-	LANG=C LC_ALL=C sed -ne "$pick_id_script"
-	# Ensure non-empty id name.
-	echo "case \"\$GIT_${uid}_NAME\" in \"\") GIT_${uid}_NAME=\"\${GIT_${uid}_EMAIL%%@*}\" && export GIT_${uid}_NAME;; esac"
+	parse_ident_from_commit author AUTHOR committer COMMITTER
+	finish_ident AUTHOR
+	finish_ident COMMITTER
 }
 
 USAGE="[--env-filter <command>] [--tree-filter <command>]
@@ -320,10 +302,8 @@ while read commit parents; do
 	git cat-file commit "$commit" >../commit ||
 		die "Cannot read commit $commit"
 
-	eval "$(set_ident AUTHOR <../commit)" ||
-		die "setting author failed for commit $commit"
-	eval "$(set_ident COMMITTER <../commit)" ||
-		die "setting committer failed for commit $commit"
+	eval "$(set_ident <../commit)" ||
+		die "setting author/committer failed for commit $commit"
 	eval "$filter_env" < /dev/null ||
 		die "env filter failed: $filter_env"
 
diff --git a/git-sh-setup.sh b/git-sh-setup.sh
index ee0e0bc045..22f0aed6db 100644
--- a/git-sh-setup.sh
+++ b/git-sh-setup.sh
@@ -191,28 +191,52 @@ require_clean_work_tree () {
 	fi
 }
 
+# Generate a sed script to parse identities from a commit.
+#
+# Reads the commit from stdin, which should be in raw format (e.g., from
+# cat-file or "--pretty=raw").
+#
+# The first argument specifies the ident line to parse (e.g., "author"), and
+# the second specifies the environment variable to put it in (e.g., "AUTHOR"
+# for "GIT_AUTHOR_*"). Multiple pairs can be given to parse author and
+# committer.
+pick_ident_script () {
+	while test $# -gt 0
+	do
+		lid=$1; shift
+		uid=$1; shift
+		printf '%s' "
+		/^$lid /{
+			s/'/'\\\\''/g
+			h
+			s/^$lid "'\([^<]*\) <[^>]*> .*$/\1/'"
+			s/.*/GIT_${uid}_NAME='&'/p
+
+			g
+			s/^$lid "'[^<]* <\([^>]*\)> .*$/\1/'"
+			s/.*/GIT_${uid}_EMAIL='&'/p
+
+			g
+			s/^$lid "'[^<]* <[^>]*> \(.*\)$/@\1/'"
+			s/.*/GIT_${uid}_DATE='&'/p
+		}
+		"
+	done
+	echo '/^$/q'
+}
+
+# Create a pick-script as above and feed it to sed. Stdout is suitable for
+# feeding to eval.
+parse_ident_from_commit () {
+	LANG=C LC_ALL=C sed -ne "$(pick_ident_script "$@")"
+}
+
+# Parse the author from a commit given as an argument. Stdout is suitable for
+# feeding to eval to set the usual GIT_* ident variables.
 get_author_ident_from_commit () {
-	pick_author_script='
-	/^author /{
-		s/'\''/'\''\\'\'\''/g
-		h
-		s/^author \([^<]*\) <[^>]*> .*$/\1/
-		s/.*/GIT_AUTHOR_NAME='\''&'\''/p
-
-		g
-		s/^author [^<]* <\([^>]*\)> .*$/\1/
-		s/.*/GIT_AUTHOR_EMAIL='\''&'\''/p
-
-		g
-		s/^author [^<]* <[^>]*> \(.*\)$/@\1/
-		s/.*/GIT_AUTHOR_DATE='\''&'\''/p
-
-		q
-	}
-	'
 	encoding=$(git config i18n.commitencoding || echo UTF-8)
 	git show -s --pretty=raw --encoding="$encoding" "$1" -- |
-	LANG=C LC_ALL=C sed -ne "$pick_author_script"
+	parse_ident_from_commit author AUTHOR
 }
 
 # Clear repo-local GIT_* environment variables. Useful when switching to
diff --git a/t/t7003-filter-branch.sh b/t/t7003-filter-branch.sh
index 4d13e10de1..1e7a209efa 100755
--- a/t/t7003-filter-branch.sh
+++ b/t/t7003-filter-branch.sh
@@ -167,10 +167,11 @@ test_expect_success 'author information is preserved' '
 	test_tick &&
 	GIT_AUTHOR_NAME="B V Uips" git commit -m bvuips &&
 	git branch preserved-author &&
-	git filter-branch -f --msg-filter "cat; \
+	(sane_unset GIT_AUTHOR_NAME &&
+	 git filter-branch -f --msg-filter "cat; \
 			test \$GIT_COMMIT != $(git rev-parse master) || \
 			echo Hallo" \
-		preserved-author &&
+		preserved-author) &&
 	test 1 = $(git rev-list --author="B V Uips" preserved-author | wc -l)
 '