userdiff: support Bash
Support POSIX, bashism and mixed function declarations, all four compound command types, trailing comments and mixed whitespace. Even though Bash allows locale-dependent characters in function names <https://unix.stackexchange.com/a/245336/3645>, only detect function names with characters allowed by POSIX.1-2017 <https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap03.html#tag_03_235> for simplicity. This should cover the vast majority of use cases, and produces system-agnostic results. Since a word pattern has to be specified, but there is no easy way to know the default word pattern, use the default `IFS` characters for a starter. A later patch can improve this. Signed-off-by: Victor Engmark <victor@engmark.name> Acked-by: Johannes Sixt <j6t@kdbg.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Victor Engmark committed
Oct 22, 2020 at 12:45 UTC
2ff6c34612057baccbd841524106c5a05f6be6d6
18 files changed
+91
Documentation/gitattributes.txt
+3
index 2d0a03715b..e84e104f93 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -802,6 +802,9 @@ patterns are available:
- `ada` suitable for source code in the Ada language.
+- `bash` suitable for source code in the Bourne-Again SHell language.
+ Covers a superset of POSIX shell function definitions.
+
- `bibtex` suitable for files with BibTeX coded references.
- `cpp` suitable for source code in the C and C++ languages.
t/t4018-diff-funcname.sh
+1
index 9d07797579..9675bc17db 100755
--- a/t/t4018-diff-funcname.sh
+++ b/t/t4018-diff-funcname.sh
@@ -27,6 +27,7 @@ test_expect_success 'setup' '
diffpatterns="
ada
+ bash
bibtex
cpp
csharp
t/t4018/bash-arithmetic-function
+4
new file mode 100644
index 0000000000..c0b276cb50
--- /dev/null
+++ b/t/t4018/bash-arithmetic-function
@@ -0,0 +1,4 @@
+RIGHT() ((
+
+ ChangeMe = "$x" + "$y"
+))
t/t4018/bash-bashism-style-compact
+6
new file mode 100644
index 0000000000..1ca3126f61
--- /dev/null
+++ b/t/t4018/bash-bashism-style-compact
@@ -0,0 +1,6 @@
+function RIGHT {
+ function InvalidSyntax{
+ :
+ echo 'ChangeMe'
+ }
+}
t/t4018/bash-bashism-style-function
+4
new file mode 100644
index 0000000000..f1de4fa831
--- /dev/null
+++ b/t/t4018/bash-bashism-style-function
@@ -0,0 +1,4 @@
+function RIGHT {
+ :
+ echo 'ChangeMe'
+}
t/t4018/bash-bashism-style-whitespace
+4
new file mode 100644
index 0000000000..ade85dd3a5
--- /dev/null
+++ b/t/t4018/bash-bashism-style-whitespace
@@ -0,0 +1,4 @@
+ function RIGHT ( ) {
+
+ ChangeMe
+ }
t/t4018/bash-conditional-function
+4
new file mode 100644
index 0000000000..c5949e829b
--- /dev/null
+++ b/t/t4018/bash-conditional-function
@@ -0,0 +1,4 @@
+RIGHT() [[ \
+
+ "$a" > "$ChangeMe"
+]]
t/t4018/bash-missing-parentheses
+6
new file mode 100644
index 0000000000..8c8a05dd7a
--- /dev/null
+++ b/t/t4018/bash-missing-parentheses
@@ -0,0 +1,6 @@
+function RIGHT {
+ functionInvalidSyntax {
+ :
+ echo 'ChangeMe'
+ }
+}
t/t4018/bash-mixed-style-compact
+4
new file mode 100644
index 0000000000..d9364cba67
--- /dev/null
+++ b/t/t4018/bash-mixed-style-compact
@@ -0,0 +1,4 @@
+function RIGHT(){
+ :
+ echo 'ChangeMe'
+}
t/t4018/bash-mixed-style-function
+4
new file mode 100644
index 0000000000..555f9b2466
--- /dev/null
+++ b/t/t4018/bash-mixed-style-function
@@ -0,0 +1,4 @@
+function RIGHT() {
+
+ ChangeMe
+}
t/t4018/bash-nested-functions
+6
new file mode 100644
index 0000000000..2c9237ead4
--- /dev/null
+++ b/t/t4018/bash-nested-functions
@@ -0,0 +1,6 @@
+outer() {
+ RIGHT() {
+ :
+ echo 'ChangeMe'
+ }
+}
t/t4018/bash-other-characters
+4
new file mode 100644
index 0000000000..a3f390d525
--- /dev/null
+++ b/t/t4018/bash-other-characters
@@ -0,0 +1,4 @@
+_RIGHT_0n() {
+
+ ChangeMe
+}
t/t4018/bash-posix-style-compact
+4
new file mode 100644
index 0000000000..045bd2029b
--- /dev/null
+++ b/t/t4018/bash-posix-style-compact
@@ -0,0 +1,4 @@
+RIGHT(){
+
+ ChangeMe
+}
t/t4018/bash-posix-style-function
+4
new file mode 100644
index 0000000000..a4d144856e
--- /dev/null
+++ b/t/t4018/bash-posix-style-function
@@ -0,0 +1,4 @@
+RIGHT() {
+
+ ChangeMe
+}
t/t4018/bash-posix-style-whitespace
+4
new file mode 100644
index 0000000000..4d984f0aa4
--- /dev/null
+++ b/t/t4018/bash-posix-style-whitespace
@@ -0,0 +1,4 @@
+ RIGHT ( ) {
+
+ ChangeMe
+ }
t/t4018/bash-subshell-function
+4
new file mode 100644
index 0000000000..80baa09484
--- /dev/null
+++ b/t/t4018/bash-subshell-function
@@ -0,0 +1,4 @@
+RIGHT() (
+
+ ChangeMe=2
+)
t/t4018/bash-trailing-comment
+4
new file mode 100644
index 0000000000..f1edbeda31
--- /dev/null
+++ b/t/t4018/bash-trailing-comment
@@ -0,0 +1,4 @@
+RIGHT() { # Comment
+
+ ChangeMe
+}
userdiff.c
+21
index fde02f225b..eb698eaca7 100644
--- a/userdiff.c
+++ b/userdiff.c
@@ -23,6 +23,27 @@ IPATTERN("ada",
"[a-zA-Z][a-zA-Z0-9_]*"
"|[-+]?[0-9][0-9#_.aAbBcCdDeEfF]*([eE][+-]?[0-9_]+)?"
"|=>|\\.\\.|\\*\\*|:=|/=|>=|<=|<<|>>|<>"),
+PATTERNS("bash",
+ /* Optional leading indentation */
+ "^[ \t]*"
+ /* Start of captured text */
+ "("
+ "("
+ /* POSIX identifier with mandatory parentheses */
+ "[a-zA-Z_][a-zA-Z0-9_]*[ \t]*\\([ \t]*\\))"
+ "|"
+ /* Bashism identifier with optional parentheses */
+ "(function[ \t]+[a-zA-Z_][a-zA-Z0-9_]*(([ \t]*\\([ \t]*\\))|([ \t]+))"
+ ")"
+ /* Optional whitespace */
+ "[ \t]*"
+ /* Compound command starting with `{`, `(`, `((` or `[[` */
+ "(\\{|\\(\\(?|\\[\\[)"
+ /* End of captured text */
+ ")",
+ /* -- */
+ /* Characters not in the default $IFS value */
+ "[^ \t]+"),
PATTERNS("dts",
"!;\n"
"!=\n"