mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-31 14:34:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Actor: Enhance error handling and data logging

Browse Source 
- Add `apify pushData` calls to log errors when the document URL is missing or inaccessible.
- Introduce dataset record creation with processing results, including a success status and output file URL.
- Modify completion message to indicate successful processing and provide a link to the results.

Signed-off-by: Václav Vančura <commit@vancura.dev>
This commit is contained in:
Václav Vančura 2025-02-07 13:09:20 +01:00 committed by Adam Kliment
parent 1ca8251844
commit 7c486ce0cc
1 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
.actor/actor.sh
View File

@ -48,6 +48,7 @@ readonly ERR_STORAGE_FAILED=14
# Update error handling with codes. # Update error handling with codes.
if [ -z "$DOCUMENT_URL" ]; then if [ -z "$DOCUMENT_URL" ]; then
echo "Error: Missing document URL. Please provide 'documentUrl' in the input" echo "Error: Missing document URL. Please provide 'documentUrl' in the input"
apify pushData "{\"url\": \"${DOCUMENT_URL}\", \"status\": \"error\", \"error\": \"Missing document URL\"}" || true
exit $ERR_INVALID_INPUT exit $ERR_INVALID_INPUT
fi fi
@ -70,6 +71,7 @@ echo "Validating document URL..."
if ! curl --output /dev/null --silent --head --fail "${DOCUMENT_URL}"; then if ! curl --output /dev/null --silent --head --fail "${DOCUMENT_URL}"; then
echo "Error: Unable to access document at URL: ${DOCUMENT_URL}" echo "Error: Unable to access document at URL: ${DOCUMENT_URL}"
echo "Please ensure the URL is valid and publicly accessible." echo "Please ensure the URL is valid and publicly accessible."
apify pushData "{\"url\": \"${DOCUMENT_URL}\", \"status\": \"error\", \"error\": \"URL inaccessible\"}" || true
exit $ERR_URL_INACCESSIBLE exit $ERR_URL_INACCESSIBLE
fi fi
@ -145,6 +147,13 @@ apify actor:set-value "OUTPUT_RESULT" --contentType "application/$OUTPUT_FORMAT"
exit $ERR_STORAGE_FAILED exit $ERR_STORAGE_FAILED
} }
# Create dataset record with processing results.
RESULT_URL="https://api.apify.com/v2/key-value-stores/${APIFY_DEFAULT_KEY_VALUE_STORE_ID}/records/OUTPUT_RESULT"
echo "Adding record to dataset..."
apify pushData "{\"url\": \"${DOCUMENT_URL}\", \"output_file\": \"${RESULT_URL}\", \"status\": \"success\"}" || {
echo "Warning: Failed to push data to dataset"
}
if [ -f "$LOG_FILE" ]; then if [ -f "$LOG_FILE" ]; then
if [ -s "$LOG_FILE" ]; then if [ -s "$LOG_FILE" ]; then
echo "Log file is not empty, pushing to Key-Value Store (record key: DOCLING_LOG)..." echo "Log file is not empty, pushing to Key-Value Store (record key: DOCLING_LOG)..."
@ -168,4 +177,5 @@ cleanup() {
trap cleanup EXIT trap cleanup EXIT
echo "Done!" echo "Processing completed successfully!"
echo "You can find your results at: '$RESULT_URL'"