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: Documentation update

Browse Source 
Signed-off-by: Václav Vančura <commit@vancura.dev>
Signed-off-by: Adam Kliment <adam@netmilk.net>
This commit is contained in:
Václav Vančura 2025-01-22 11:56:55 +01:00 committed by Adam Kliment
parent 66287e45a5
commit 67e1129365
1 changed files with 13 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
.actor/actor.sh
View File

@ -2,17 +2,18 @@
# --- Setup Error Handling ---
# Exit the script if any command fails.
trap 'echo "Error on line $LINENO"; exit 1' ERR
set -e
# --- Validate Docling Installation ---
# --- Validate Docling installation ---
if ! command -v docling &> /dev/null; then
echo "Error: Docling CLI is not installed or not in PATH"
exit 1
fi
# --- Input Parsing ---
# --- Input parsing ---
echo "Parsing actor input..."
INPUT=$(apify actor:get-input || { echo "Failed to get input"; exit 1; })
@ -21,11 +22,13 @@ DOCUMENT_URL=$(echo "$INPUT" | jq -r '.documentUrl')
OUTPUT_FORMAT=$(echo "$INPUT" | jq -r '.outputFormat')
OUTPUT_NAME="output_file.$OUTPUT_FORMAT"
# If no document URL is provided, exit with an error.
if [ -z "$DOCUMENT_URL" ]; then
echo "Error: Missing document URL. Please provide 'documentUrl' in the input"
exit 1
fi
# If no output format is specified, default to 'md'.
if [ -z "$OUTPUT_FORMAT" ]; then
OUTPUT_FORMAT="md"
echo "No output format specified. Defaulting to 'md'"
@ -40,7 +43,7 @@ case "$OUTPUT_FORMAT" in
;;
esac
# --- Build Docling Command ---
# --- Build Docling command ---
DOC_CONVERT_CMD="docling --verbose $DOCUMENT_URL --to $OUTPUT_FORMAT"
@ -48,11 +51,12 @@ if [ "$(echo "$INPUT" | jq -r '.ocr')" = "true" ]; then
DOC_CONVERT_CMD="$DOC_CONVERT_CMD --ocr"
fi
# --- Process Document with Docling ---
# --- Process document with Docling ---
echo "Processing document with Docling CLI..."
echo "Running: $DOC_CONVERT_CMD"
# Create a timestamp file to ensure the document is processed only once.
touch docling.timestamp
$DOC_CONVERT_CMD > docling.log 2>&1 || {
@ -70,13 +74,15 @@ fi
mv "$GENERATED_FILE" "$OUTPUT_NAME"
# --- Validate Output ---
# --- Validate output ---
# If the output file is not found, exit with an error.
if [ ! -f "$OUTPUT_NAME" ]; then
echo "Error: Expected output file '$OUTPUT_NAME' was not generated"
exit 1
fi
# If the output file is empty, exit with an error.
if [ ! -s "$OUTPUT_NAME" ]; then
echo "Error: Generated output file '$OUTPUT_NAME' is empty"
exit 1
@ -84,7 +90,7 @@ fi
echo "Document successfully processed and exported as '$OUTPUT_FORMAT' to file: $OUTPUT_NAME"
# --- Store Output in Key-Value Store ---
# --- Store output and log in Key-Value Store ---
echo "Pushing processed document to Key-Value Store (record key: OUTPUT_RESULT)..."
apify actor:set-value "OUTPUT_RESULT" --contentType "application/$OUTPUT_FORMAT" < "$OUTPUT_NAME" || {
@ -92,7 +98,7 @@ apify actor:set-value "OUTPUT_RESULT" --contentType "application/$OUTPUT_FORMAT"
exit 1
}
# --- Cleanup Temporary Files ---
# --- Cleanup temporary files ---
rm -f docling.timestamp docling.log || true