From b27c24f806f9ea8646dc0630e2033b6eec8a41a9 Mon Sep 17 00:00:00 2001
From: Jakob <jakob@rowanbrook.net>
Date: Mon, 23 Mar 2026 14:38:56 +0100
Subject: [PATCH] Add shell script to rename PDFs by extracting customer
 numbers

- rename_pdfs.sh: Main script that renames PDFs based on content
- extract_customer.py: Helper script to extract customer number from PDF
---
 extract_customer.py | 25 +++++++++++++++++++++++++
 rename_pdfs.sh      | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)
 create mode 100755 extract_customer.py
 create mode 100755 rename_pdfs.sh

diff --git a/extract_customer.py b/extract_customer.py
new file mode 100755
index 0000000..0209f18
--- /dev/null
+++ b/extract_customer.py
@@ -0,0 +1,25 @@
+#!/usr/bin/env python3
+import sys
+import re
+from pypdf import PdfReader
+
+def extract_customer(pdf_path):
+    try:
+        reader = PdfReader(pdf_path)
+        for page in reader.pages:
+            text = page.extract_text()
+            if text:
+                if 'Fakturaöversikt' in text:
+                    return 'index'
+                match = re.search(r'Kund\s+(\d+)', text)
+                if match:
+                    return f'customer_{match.group(1)}'
+    except Exception as e:
+        pass
+    return None
+
+if __name__ == '__main__':
+    if len(sys.argv) > 1:
+        result = extract_customer(sys.argv[1])
+        if result:
+            print(result)
diff --git a/rename_pdfs.sh b/rename_pdfs.sh
new file mode 100755
index 0000000..64eed11
--- /dev/null
+++ b/rename_pdfs.sh
@@ -0,0 +1,34 @@
+#!/bin/bash
+
+# Script to rename PDF files based on customer number extracted from their content
+# Usage: ./rename_pdfs.sh [directory]
+# Default directory: output
+
+OUTPUT_DIR="${1:-output}"
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+FULL_DIR="$SCRIPT_DIR/$OUTPUT_DIR"
+
+if [ ! -d "$FULL_DIR" ]; then
+    echo "Error: Directory '$FULL_DIR' not found"
+    exit 1
+fi
+
+for pdf in "$FULL_DIR"/*.pdf; do
+    if [ -f "$pdf" ]; then
+        filename=$(basename "$pdf")
+        
+        # Extract text from PDF using Python and pypdf
+        result=$(python3 "$SCRIPT_DIR/extract_customer.py" "$pdf" 2>/dev/null)
+
+        if [ -n "$result" ]; then
+            new_name="${result}.pdf"
+            if [ "$filename" != "$new_name" ]; then
+                mv "$pdf" "$FULL_DIR/$new_name"
+                echo "Renamed: $filename -> $new_name"
+            fi
+        else
+            echo "Could not extract customer number from: $filename"
+        fi
+    fi
+done