Done ticket GEPAFINBE-236

src/main/java/net/gepafin/tendermanagement/util/S3DocxProcessor.java

@@ -0,0 +1,140 @@
+package net.gepafin.tendermanagement.util;
+
+import com.amazonaws.services.s3.AmazonS3;
+import com.amazonaws.services.s3.AmazonS3URI;
+import com.amazonaws.services.s3.model.S3Object;
+import net.gepafin.tendermanagement.model.request.AttachmentRequest;
+import org.apache.poi.xwpf.usermodel.*;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.*;
+import java.net.URI;
+import java.nio.file.Files;
+import java.nio.file.Path;
+import java.nio.file.Paths;
+import java.util.*;
+import java.util.Base64;
+
+public class S3DocxProcessor {
+
+    private final AmazonS3 s3Client;
+
+    public static final Logger log = LoggerFactory.getLogger(S3DocxProcessor.class);
+
+
+    public S3DocxProcessor(AmazonS3 s3Client) {
+        this.s3Client = s3Client;
+    }
+
+    /**
+     * Fetches DOCX files from S3, replaces placeholders, and returns updated files
+     * as AttachmentRequest objects (ready for PEC API).
+     *
+     * @param s3Urls List of S3 file URLs
+     * @param replacements Map of placeholder -> value
+     * @return Map of original file name -> AttachmentRequest
+     * @throws IOException
+     */
+    public Map<String, AttachmentRequest> processFiles(List<String> s3Urls,
+                                                       Map<String, String> replacements) throws IOException {
+        Map<String, AttachmentRequest> processedFiles = new HashMap<>();
+
+        for (String s3Url : s3Urls) {
+            // Extract bucket & key from URL
+            AmazonS3URI s3Uri = new AmazonS3URI(s3Url);
+            String bucket = s3Uri.getBucket();
+            String key = s3Uri.getKey();
+            try (S3Object s3Object = s3Client.getObject(bucket, key);
+                 InputStream originalStream = new BufferedInputStream(s3Object.getObjectContent())) {
+                byte[] updatedBytes=null;
+                if (isDocxFile(originalStream)) {
+                    log.warn("Skipping non-DOCX file from S3: bucket={}, key={}", bucket, key);
+                    updatedBytes = replacePlaceholders(originalStream, replacements);
+                }else {
+                    // non-DOCX → just copy raw stream
+                    updatedBytes = originalStream.readAllBytes();
+                    log.info("Skipped placeholder replacement, copied file as-is: {}", key);
+                }
+
+                // convert to base64
+                String base64 = Base64.getEncoder().encodeToString(updatedBytes);
+                String fileString = "data:application/octet-stream;base64," + base64;
+
+                // create attachment request
+                AttachmentRequest attachment = new AttachmentRequest();
+                attachment.setName(extractFileName(key));
+                attachment.setFile(fileString);
+
+                processedFiles.put(key, attachment);
+            }
+        }
+
+        return processedFiles;
+    }
+
+
+    private byte[] replacePlaceholders(InputStream docInputStream,
+                                       Map<String, String> replacements) throws IOException {
+        try (XWPFDocument document = new XWPFDocument(docInputStream);
+             ByteArrayOutputStream out = new ByteArrayOutputStream()) {
+
+            // replace in body paragraphs
+            replaceInParagraphs(document.getParagraphs(), replacements);
+
+            // replace inside tables
+            for (XWPFTable table : document.getTables()) {
+                for (XWPFTableRow row : table.getRows()) {
+                    for (XWPFTableCell cell : row.getTableCells()) {
+                        replaceInParagraphs(cell.getParagraphs(), replacements);
+                    }
+                }
+            }
+
+            document.write(out);
+            return out.toByteArray();
+        }
+    }
+
+    private void replaceInParagraphs(List<XWPFParagraph> paragraphs, Map<String, String> replacements) {
+        for (XWPFParagraph paragraph : paragraphs) {
+            String paragraphText = paragraph.getText();
+
+            if (paragraphText != null && !paragraphText.isEmpty()) {
+                // Apply all replacements
+                for (Map.Entry<String, String> entry : replacements.entrySet()) {
+                    paragraphText = paragraphText.replace(entry.getKey(), entry.getValue());
+                }
+
+                // Remove old runs
+                int runCount = paragraph.getRuns().size();
+                for (int i = runCount - 1; i >= 0; i--) {
+                    paragraph.removeRun(i);
+                }
+
+                // Add one new run with replaced text
+                XWPFRun newRun = paragraph.createRun();
+                newRun.setText(paragraphText);
+            }
+        }
+    }
+
+
+    private String extractFileName(String key) {
+        int lastSlash = key.lastIndexOf('/');
+        if (lastSlash >= 0 && lastSlash < key.length() - 1) {
+            return key.substring(lastSlash + 1);
+        }
+        return key;
+    }
+
+    private boolean isDocxFile(InputStream inputStream) throws IOException {
+        inputStream.mark(4);
+        byte[] header = new byte[2];
+        int read = inputStream.read(header, 0, 2);
+        inputStream.reset();
+
+        // DOCX = ZIP = should start with PK (0x50 0x4B)
+        return read == 2 && header[0] == 0x50 && header[1] == 0x4B;
+    }
+}