[1/2] Subject: [GSOC][RFC PATCH 1/2] Add builtin patterns for JavaScript function detection in userdiff.

Commit Message

Sergius Nyah Feb. 27, 2024, 2:19 p.m. UTC

From: Sergius Justus Chesami Nyah <[e-mail]>

This patch adds the regular expression for detecting JavaScript functions and expressions in Git diffs. The pattern accurately identifies function declerations, expressions, and definitions inside blocks.
---
 userdiff.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

Patch

diff --git a/userdiff.c b/userdiff.c
index e399543823..12e31ff14d 100644
--- a/userdiff.c
+++ b/userdiff.c
@@ -1,7 +1,7 @@ 
 #include "git-compat-util.h"
 #include "config.h"
 #include "userdiff.h"
-#include "attr.h"
+#include "attr.h" 
 #include "strbuf.h"
 
 static struct userdiff_driver *drivers;
@@ -183,6 +183,19 @@  PATTERNS("java",
 	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
 	 "|[-+*/<>%&^|=!]="
 	 "|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"),
+PATTERNS("javascript",
+     /* 
+	  * Looks for lines that start with optional whitespace, followed 
+	  * by 'function'* and any characters (for function declarations), 
+      * or valid JavaScript identifiers, equals sign '=', 'function' keyword
+	  * and any characters (for function expressions).
+      * Also considers functions defined inside blocks with '{...}'.
+	  */ 
+	 "^[ \t]*(function[ \t]*.*|[a-zA-Z_$][0-9a-zA-Z_$]*[ \t]*=[ \t]*function[ \t]*.*|(\\{[ \t]*)?)\n",
+     /* This pattern matches JavaScript identifiers */
+     "[a-zA-Z_$][0-9a-zA-Z_$]*"
+     "|[-+0-9.eE]+|0[xX][0-9a-fA-F]+" 
+     "|[-+*/<>%&^|=!:]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\|"), 
 PATTERNS("kotlin",
 	 "^[ \t]*(([a-z]+[ \t]+)*(fun|class|interface)[ \t]+.*)$",
 	 /* -- */
@@ -192,7 +205,7 @@  PATTERNS("kotlin",
 	 /* integers and floats */
 	 "|[0-9][0-9_]*([.][0-9_]*)?([Ee][-+]?[0-9]+)?[fFlLuU]*"
 	 /* floating point numbers beginning with decimal point */
-	 "|[.][0-9][0-9_]*([Ee][-+]?[0-9]+)?[fFlLuU]?"
+	 "|[.][0-9][0-9_]*([Ee][-+]?[0-9]+ )?[fFlLuU]?"
 	 /* unary and binary operators */
 	 "|[-+*/<>%&^|=!]==?|--|\\+\\+|<<=|>>=|&&|\\|\\||->|\\.\\*|!!|[?:.][.:]"),
 PATTERNS("markdown",