Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update lambdas to not index files with metadata security classification #100

Merged
merged 2 commits into from
Oct 24, 2023
Merged

Update lambdas to not index files with metadata security classification #100

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f28c08f
Update lambdas to not index files with metadata security classificati…
CEBergin-Vivid Oct 24, 2023
87d5c2a
add pptx parsing to TikaParseDocument
CEBergin-Vivid Oct 24, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 31 additions & 14 deletions ...x-service/src/main/java/ca/bc/gov/nrs/wfdm/wfdm_file_index_service/ProcessSQSMessage.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -175,24 +175,41 @@ public String handleRequest(Map<String, Object> event, Context context) {
String fileName = filePath.substring(filePath.lastIndexOf("/") + 1);

OpenSearchRESTClient restClient = new OpenSearchRESTClient();
restClient.addIndex(content, fileName, fileDetailsJson, scanStatus);
// Push ID onto SQS for clamAV
logger.log("\nInfo: File parsing complete. Schedule ClamAV scan.");

// update metadata
boolean metaAdded = GetFileFromWFDMAPI.setIndexedMetadata(wfdmToken, fileId, versionNumber, fileDetailsJson);
if (!metaAdded) {
// We failed to apply the metadata regarding the virus scan status...
// Should we continue to process the data from this point, or just choke?
logger.log("\nERROR: Failed to add metadata to file resource");

// We are disabling indexing of files with a security classification of Protected B or Protected C
JSONArray metaArray = fileDetailsJson.getJSONArray("metadata");
boolean skipIndexing = false;
for (int i = 0; i < metaArray.length(); i++) {
String metadataName = metaArray.getJSONObject(i).getString("metadataName");
String metadataValue = metaArray.getJSONObject(i).getString("metadataValue");

if (metadataName.equals("SecurityClassification")
&& (metadataValue.equals("Protected B") || metadataValue.equals("Protected C"))) {
skipIndexing = true;
}
}

// after updating metadata, get file info again and update index
fileInfo = GetFileFromWFDMAPI.getFileInformation(wfdmToken, fileId);
fileDetailsJson = new JSONObject(fileInfo);
if (!skipIndexing) {

restClient.addIndex(content, fileName, fileDetailsJson, scanStatus);
restClient.addIndex(content, fileName, fileDetailsJson, scanStatus);
// Push ID onto SQS for clamAV
logger.log("\nInfo: File parsing complete. Schedule ClamAV scan.");

// update metadata
boolean metaAdded = GetFileFromWFDMAPI.setIndexedMetadata(wfdmToken, fileId, versionNumber, fileDetailsJson);
if (!metaAdded) {
// We failed to apply the metadata regarding the virus scan status...
// Should we continue to process the data from this point, or just choke?
logger.log("\nERROR: Failed to add metadata to file resource");
}

// after updating metadata, get file info again and update index
fileInfo = GetFileFromWFDMAPI.getFileInformation(wfdmToken, fileId);
fileDetailsJson = new JSONObject(fileInfo);

restClient.addIndex(content, fileName, fileDetailsJson, scanStatus);

}
}
} catch (UnirestException | TransformerConfigurationException | SAXException e) {
logger.log("\nError: Failure to recieve file from WFDM" + e.getLocalizedMessage());
Expand Down
1 change: 1 addition & 0 deletions ...x-service/src/main/java/ca/bc/gov/nrs/wfdm/wfdm_file_index_service/TikaParseDocument.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,6 +77,7 @@ public static String parseStream(InputStream stream, String mimeType)
case "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
case "application/vnd.ms-excel.sheet.macroEnabled.12":
case "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet":
case "application/vnd.openxmlformats-officedocument.presentationml.presentation":
parser = new OOXMLParser();
break;
case "application/pdf":
Expand Down
Loading