From: Moumita <dhar61595@gmail.com>
Date: Fri, 16 May 2025 14:45:11 GMT
Subject: [PATCH v7 0/1] Updated the word diff regex for Bash scripts
Message-ID: <20250516144515.49514-1-dhar61595@gmail.com>
In-Reply-To: <20250511141101.18450-1-dhar61595@gmail.com>

I cleaned up the parameter expansion regexes to avoid matching single-character operators like `:` or `#` that are already tokenized. 
I also removed the `:[0-9]+(:[0-9]+)?` pattern, which didn’t have a clear use case.
Variable matching now supports `$1`, `$2`, etc., not just `$foo`, by relaxing 
the first character requirement after the `$`. Also I removed the '?' after the second 
character of double character operators.
There are two test files in t/4018 which test the capturing of the complete line in the hunk header in the cases of both
posix style functions and bash style functions.



Moumita Dhar (1):
  userdiff: extend Bash pattern to cover more shell function forms

 .../bash-bashism-style-complete-line-capture  |  4 +++
 .../bash-posix-style-complete-line-capture    |  4 +++
 .../bash-posix-style-single-command-function  |  3 ++
 t/t4034-diff-words.sh                         |  1 +
 t/t4034/bash/expect                           | 36 +++++++++++++++++++
 t/t4034/bash/post                             | 31 ++++++++++++++++
 t/t4034/bash/pre                              | 31 ++++++++++++++++
 userdiff.c                                    | 26 +++++++++-----
 8 files changed, 128 insertions(+), 8 deletions(-)
 create mode 100644 t/t4018/bash-bashism-style-complete-line-capture
 create mode 100644 t/t4018/bash-posix-style-complete-line-capture
 create mode 100644 t/t4018/bash-posix-style-single-command-function
 create mode 100644 t/t4034/bash/expect
 create mode 100644 t/t4034/bash/post
 create mode 100644 t/t4034/bash/pre

Range-diff against v6:
1:  464cb8a1eb ! 1:  314ac45fa2 userdiff: extend Bash pattern to cover more shell function forms
    @@ Commit message
     
         Signed-off-by: Moumita Dhar <dhar61595@gmail.com>
     
    - ## t/t4018/bash-bashism-style-multiline-function (new) ##
    + ## t/t4018/bash-bashism-style-complete-line-capture (new) ##
     @@
    -+function RIGHT \
    -+{    
    ++function myfunc # RIGHT
    ++{
     +    echo 'ChangeMe'
     +}
     
    - ## t/t4018/bash-hunk-header-complete-line-capture (new) ##
    + ## t/t4018/bash-posix-style-complete-line-capture (new) ##
     @@
     +func() { # RIGHT
     +
     +    ChangeMe
    -+}
    -
    - ## t/t4018/bash-posix-style-multiline-function (new) ##
    -@@
    -+RIGHT() \
    -+{
    -+    ChangeMe
     +}
     
      ## t/t4018/bash-posix-style-single-command-function (new) ##
    @@ t/t4034/bash/expect (new)
     +<BOLD>index 09ac008..60ba6a2 100644<RESET>
     +<BOLD>--- a/pre<RESET>
     +<BOLD>+++ b/post<RESET>
    -+<CYAN>@@ -1,33 +1,33 @@<RESET>
    ++<CYAN>@@ -1,31 +1,31 @@<RESET>
     +<RED>my_var<RESET><GREEN>new_var<RESET>=10
     +x=<RED>123<RESET><GREEN>456<RESET>
    -+y=<RED>3.14<RESET><GREEN>2.71<RESET>
    -+z=<RED>.5<RESET><GREEN>.75<RESET>
    ++echo <RED>$1<RESET><GREEN>$2<RESET>
     +echo <RED>$USER<RESET><GREEN>$USERNAME<RESET>
     +${<RED>HOME<RESET><GREEN>HOMEDIR<RESET>}
     +((a<RED>+<RESET><GREEN>+=<RESET>b))
    @@ t/t4034/bash/expect (new)
     +${a<RED>,<RESET><GREEN>,,<RESET>}
     +${<GREEN>!<RESET>a}
     +${a[<RED>*<RESET><GREEN>@<RESET>]}
    -+${a<RED>:2:3<RESET><GREEN>:4:6<RESET>}
     +ls <RED>-a<RESET><GREEN>-x<RESET>
    -+ls <RED>--a<RESET><GREEN>--x<RESET>
    ++ls <RED>--all<RESET><GREEN>--color<RESET>
     
      ## t/t4034/bash/post (new) ##
     @@
     +new_var=10
     +x=456
    -+y=2.71
    -+z=.75
    ++echo $2
     +echo $USERNAME
     +${HOMEDIR}
     +((a+=b))
    @@ t/t4034/bash/post (new)
     +${a,,}
     +${!a}
     +${a[@]}
    -+${a:4:6}
     +ls -x
    -+ls --x
    ++ls --color
     
      ## t/t4034/bash/pre (new) ##
     @@
     +my_var=10
     +x=123
    -+y=3.14
    -+z=.5
    ++echo $1
     +echo $USER
     +${HOME}
     +((a+b))
    @@ t/t4034/bash/pre (new)
     +${a,}
     +${a}
     +${a[*]}
    -+${a:2:3}
     +ls -a
    -+ls --a
    ++ls --all
     
      ## userdiff.c ##
     @@ userdiff.c: PATTERNS("bash",
    @@ userdiff.c: PATTERNS("bash",
     -	 "[^ \t]+"),
     +	 /* Identifiers: variable and function names */
     +	  "[a-zA-Z_][a-zA-Z0-9_]*"
    -+	 /* Numeric constants: integers and decimals */
    -+	  "|[0-9]+(\\.[0-9]*)?|[-+]?\\.[0-9]+"
     +	 /* Shell variables: $VAR, ${VAR} */
    -+	  "|\\$[a-zA-Z_][a-zA-Z0-9_]*|\\$\\{"
    -+	  /* Logical and comparison operators */
    -+	 "|\\|\\||&&|<<|>>|==|!=|<=|>="
    -+	 /* Assignment and arithmetic operators */
    -+	 "|[-+*/%&|^!=<>]=?"
    ++	  "|\\$[a-zA-Z0-9_]+|\\$\\{"
    ++	  /*Command list separators and redirection operators  */
    ++	 "|\\|\\||&&|<<|>>"
    ++	 /* Operators ending in '=' (comparison + compound assignment) */
    ++	 "|==|!=|<=|>=|[-+*/%&|^]="
     +	 /* Additional parameter expansion operators */
    -+	 "|:?=|:-|:\\+|:\\?|:|#|##|%|%%|\\^\\^?|,|,,?|!|@|:[0-9]+(:[0-9]+)?"
    ++	 "|:=|:-|:\\+|:\\?|##|%%|\\^\\^|,,"
     +	 /* Command-line options (to avoid splitting -option) */
    -+	 "|--?[a-zA-Z0-9_-]+"
    ++	 "|[-a-zA-Z0-9_]+"
     +	 /* Brackets and grouping symbols */
     +	 "|\\(|\\)|\\{|\\}|\\[|\\]"),
      PATTERNS("bibtex",
-- 
2.48.0