Back (Current repo: scraps)

commit 185a19eaa91f679683a4caaf454ef0149a7e9604
parent e31a49cb21fa221a24f2a014426e80001aa4676b
Author: root <root>
Date:   Thu, 24 Apr 2025 10:29:53 +0200

new awk script

Diffstat:
A
awk/group_by_column_regex.awk
 | 
39
+++++++++++++++++++++++++++++++++++++++

1 file changed, 39 insertions(+), 0 deletions(-)
diff --git a/awk/group_by_column_regex.awk b/awk/group_by_column_regex.awk
@@ -0,0 +1,39 @@
+#!/bin/awk
+
+function push(arr, value) {
+    arr[length(arr)+1] = value;
+}
+
+# Helper to print the array in semicolon-delimited format
+function parray(arr) {
+    for (i = 0; i < length(arr); i++) {
+        printf arr[i] ";";
+    }
+    printf "\n";
+}
+BEGIN{
+    FS=",";
+    OFS=",";
+    regex="";
+    if (prefix == ""){prefix = 2}
+    split("",a);
+}
+{
+    #e.g. we want to group together rows that begin with the same two numbers, like 50,501,5010, etc
+    #because the file contains rows as a hierarchy
+    if(length($1)==prefix) {
+        if(length(a) > 0) {
+            parray(a);
+        }
+        split("",a);
+        regex="^"$1
+        push(a,$1"@"$2);
+    } else {
+        if($1 ~ regex) {
+            push(a,$1"@"$2);
+        }
+    }
+}
+END{
+    parray(a);
+}