Docling

from("file:///data/documents?include=.*\\.pdf")
    .to("docling:CONVERT_TO_MARKDOWN")
    .to("file:///data/output");

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"
      - to:
          uri: "file:///data/output"

from("file:///data/documents?include=.*\\.pdf")
    .to("docling:CONVERT_TO_HTML?contentInBody=true")
    .process(exchange -> {
        String htmlContent = exchange.getIn().getBody(String.class);
        // Process the HTML content
    });

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:CONVERT_TO_HTML"
          parameters:
            contentInBody: true
      - process:
          ref: "htmlProcessor"

from("file:///data/documents?include=.*\\.pdf")
    .to("docling:EXTRACT_STRUCTURED_DATA?useDoclingServe=true&contentInBody=true")
    .process(exchange -> {
        DoclingDocument doc = exchange.getIn().getBody(DoclingDocument.class);

        // Access tables extracted from the document
        List<DoclingDocument.TableItem> tables = doc.getTables();
        for (DoclingDocument.TableItem table : tables) {
            DoclingDocument.TableData data = table.getData();
            log.info("Table: {}x{}", data.getNumRows(), data.getNumCols());
        }
    });

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:EXTRACT_STRUCTURED_DATA"
          parameters:
            useDoclingServe: true
            contentInBody: true
      - process:
          ref: "structuredDataProcessor"

// CLI mode
from("file:///data/documents?include=.*\\.pdf")
    .to("docling:CONVERT_TO_MARKDOWN?enableOCR=false")
    .to("file:///data/output");

// API mode
from("file:///data/documents?include=.*\\.pdf")
    .to("docling:CONVERT_TO_MARKDOWN?useDoclingServe=true&doOcr=false&contentInBody=true")
    .to("file:///data/output");

# CLI mode
- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"
          parameters:
            enableOCR: false
      - to:
          uri: "file:///data/output"

# API mode
- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"
          parameters:
            useDoclingServe: true
            doOcr: false
            contentInBody: true
      - to:
          uri: "file:///data/output"

from("file:///data/documents?include=.*\\.pdf")
    .setHeader("CamelDoclingOperation", constant(DoclingOperations.CONVERT_TO_HTML))
    .setHeader("CamelDoclingEnableOCR", constant(true))
    .setHeader("CamelDoclingOCRLanguage", constant("es"))
    .to("docling:CONVERT_TO_MARKDOWN")  // Operation will be overridden by header
    .to("file:///data/output");

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - setHeader:
          name: "CamelDoclingOperation"
          constant: "CONVERT_TO_HTML"
      - setHeader:
          name: "CamelDoclingEnableOCR"
          constant: true
      - setHeader:
          name: "CamelDoclingOCRLanguage"
          constant: "es"
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"  # Operation will be overridden by header
      - to:
          uri: "file:///data/output"

from("file:///data/documents?include=.*\\.pdf")
    .process(exchange -> {
        List<String> customArgs = Arrays.asList("--verbose", "--preserve-tables");
        exchange.getIn().setHeader("CamelDoclingCustomArguments", customArgs);
    })
    .to("docling:CONVERT_TO_MARKDOWN")
    .to("file:///data/output");

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - setHeader:
          name: "CamelDoclingCustomArguments"
          expression:
            method:
              ref: "customArgsBean"
              method: "createCustomArgs"
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"
      - to:
          uri: "file:///data/output"

from("file:///data/documents?include=.*\\.pdf")
    .to("docling:EXTRACT_METADATA")
    .process(exchange -> {
        DocumentMetadata metadata = exchange.getIn().getBody(DocumentMetadata.class);

        // Access metadata fields
        String title = metadata.getTitle();
        String author = metadata.getAuthor();
        Integer pageCount = metadata.getPageCount();
        Instant creationDate = metadata.getCreationDate();

        log.info("Document: {} by {}, Pages: {}, Created: {}",
            title, author, pageCount, creationDate);

        // Metadata is also available in headers
        String titleFromHeader = exchange.getIn().getHeader("CamelDoclingMetadataTitle", String.class);
    });

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:EXTRACT_METADATA"
      - log: "Document: ${header.CamelDoclingMetadataTitle} by ${header.CamelDoclingMetadataAuthor}"
      - log: "Pages: ${header.CamelDoclingMetadataPageCount}"
      - process:
          ref: "metadataProcessor"

from("file:///data/documents?include=.*\\.pdf")
    .to("docling:EXTRACT_METADATA?includeRawMetadata=true")
    .process(exchange -> {
        DocumentMetadata metadata = exchange.getIn().getBody(DocumentMetadata.class);

        log.info("Page Count: {}", metadata.getPageCount());

        // Raw metadata from parser
        Map<String, Object> rawMetadata = metadata.getRawMetadata();
        log.info("Raw metadata: {}", rawMetadata);
    });

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:EXTRACT_METADATA"
          parameters:
            includeRawMetadata: true
      - process:
          ref: "fullMetadataProcessor"

from("file:///data/documents?include=.*\\.pdf")
    .to("docling:EXTRACT_METADATA")
    .choice()
        .when(simple("${header.CamelDoclingMetadataPageCount} > 100"))
            .log("Large document with ${header.CamelDoclingMetadataPageCount} pages")
            .to("file:///data/large-docs")
        .when(simple("${header.CamelDoclingMetadataLanguage} == 'fr'"))
            .log("French document")
            .to("file:///data/french-docs")
        .when(simple("${header.CamelDoclingMetadataAuthor} contains 'Smith'"))
            .log("Document by Smith")
            .to("file:///data/smith-docs")
        .otherwise()
            .to("file:///data/other-docs")
    .end();

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:EXTRACT_METADATA"
      - choice:
          when:
            - simple: "${header.CamelDoclingMetadataPageCount} > 100"
              steps:
                - log: "Large document with ${header.CamelDoclingMetadataPageCount} pages"
                - to: "file:///data/large-docs"
            - simple: "${header.CamelDoclingMetadataLanguage} == 'fr'"
              steps:
                - log: "French document"
                - to: "file:///data/french-docs"
            - simple: "${header.CamelDoclingMetadataAuthor} contains 'Smith'"
              steps:
                - log: "Document by Smith"
                - to: "file:///data/smith-docs"
          otherwise:
            steps:
              - to: "file:///data/other-docs"

from("file:///data/documents?include=.*\\.pdf")
    .to("docling:EXTRACT_METADATA?includeMetadataInHeaders=false")
    .process(exchange -> {
        DocumentMetadata metadata = exchange.getIn().getBody(DocumentMetadata.class);

        // All metadata is in the body object only
        // Headers are not populated with metadata fields
        log.info("Metadata: {}", metadata);
    });

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:EXTRACT_METADATA"
          parameters:
            includeMetadataInHeaders: false
      - process:
          ref: "metadataBodyProcessor"

// Get content directly in body (file is automatically deleted)
from("file:///data/documents?include=.*\\.pdf")
    .to("docling:CONVERT_TO_MARKDOWN?contentInBody=true")
    .process(exchange -> {
        String markdownContent = exchange.getIn().getBody(String.class);
        log.info("Converted content: {}", markdownContent);
    });

// Get file path (file is preserved)
from("file:///data/documents?include=.*\\.pdf")
    .to("docling:CONVERT_TO_MARKDOWN?contentInBody=false")
    .process(exchange -> {
        String outputFilePath = exchange.getIn().getBody(String.class);
        log.info("Output file saved at: {}", outputFilePath);
    });

# Get content directly in body (file is automatically deleted)
- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"
          parameters:
            contentInBody: true
      - process:
          ref: "contentProcessor"

# Get file path (file is preserved)
- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"
          parameters:
            contentInBody: false
      - process:
          ref: "filePathProcessor"

from("direct:documents")
    .process(exchange -> {
        List<String> documents = Arrays.asList(
            "/data/doc1.pdf",
            "/data/doc2.pdf",
            "/data/doc3.docx"
        );
        exchange.getIn().setBody(documents);
    })
    .to("docling:convert?" +
        "operation=BATCH_CONVERT_TO_MARKDOWN&" +
        "useDoclingServe=true&" +
        "batchParallelism=4&" +
        "batchFailOnFirstError=true")
    .process(exchange -> {
        BatchProcessingResults results = exchange.getIn().getBody(BatchProcessingResults.class);
        log.info("Processed {} documents, {} succeeded, {} failed",
            results.getTotalDocuments(),
            results.getSuccessCount(),
            results.getFailureCount());

        // Access individual results
        for (BatchConversionResult result : results.getResults()) {
            if (result.isSuccess()) {
                log.info("Document {}: {}", result.getOriginalPath(), result.getResult());
            } else {
                log.error("Document {} failed: {}", result.getOriginalPath(), result.getErrorMessage());
            }
        }
    });

- route:
    id: batch-convert
    from:
      uri: "direct:documents"
    steps:
      - to:
          uri: "docling:convert"
          parameters:
            operation: "BATCH_CONVERT_TO_MARKDOWN"
            useDoclingServe: true
            batchParallelism: 4
            batchFailOnFirstError: true
      - log: "Processed ${header.CamelDoclingBatchSuccessCount}/${header.CamelDoclingBatchTotalDocuments} documents successfully"
      - split:
          simple: "${body.results}"
          steps:
            - choice:
                when:
                  - simple: "${body.success}"
                    steps:
                      - to: "file:///data/output?fileName=${body.documentId}.md"
                otherwise:
                  steps:
                    - log: "Failed: ${body.originalPath} - ${body.errorMessage}"

// Fail entire batch on first error
from("direct:batch-strict")
    .to("docling:convert?" +
        "operation=BATCH_CONVERT_TO_MARKDOWN&" +
        "useDoclingServe=true&" +
        "batchFailOnFirstError=true")
    .log("All documents converted successfully");

// Continue processing on errors
from("direct:batch-lenient")
    .to("docling:convert?" +
        "operation=BATCH_CONVERT_TO_MARKDOWN&" +
        "useDoclingServe=true&" +
        "batchFailOnFirstError=false")
    .process(exchange -> {
        BatchProcessingResults results = exchange.getIn().getBody(BatchProcessingResults.class);

        if (results.hasAnyFailures()) {
            log.warn("Batch completed with {} failures", results.getFailureCount());

            // Handle failed documents
            for (BatchConversionResult failure : results.getFailed()) {
                log.error("Failed: {} - {}",
                    failure.getOriginalPath(),
                    failure.getErrorMessage());
            }
        }
    });

# Fail on first error
- route:
    id: batch-strict
    from:
      uri: "direct:batch-strict"
    steps:
      - to:
          uri: "docling:convert"
          parameters:
            operation: "BATCH_CONVERT_TO_MARKDOWN"
            useDoclingServe: true
            batchFailOnFirstError: true
      - log: "All documents converted successfully"

# Continue on errors and process failures
- route:
    id: batch-lenient
    from:
      uri: "direct:batch-lenient"
    steps:
      - to:
          uri: "docling:convert"
          parameters:
            operation: "BATCH_CONVERT_TO_MARKDOWN"
            useDoclingServe: true
            batchFailOnFirstError: false
      - log: "Batch completed: ${header.CamelDoclingBatchSuccessCount} succeeded, ${header.CamelDoclingBatchFailureCount} failed"
      - choice:
          when:
            - simple: "${header.CamelDoclingBatchFailureCount} > 0"
              steps:
                - split:
                    simple: "${body.failed}"
                    steps:
                      - log: "Failed document: ${body.originalPath} - ${body.errorMessage}"
                      - to: "file:///data/failed?fileName=${body.documentId}.error"
          otherwise:
            steps:
              - log: "All documents processed successfully"

// Example 1: Split and process each document individually
from("direct:batch-documents")
    .to("docling:convert?" +
        "operation=BATCH_CONVERT_TO_MARKDOWN&" +
        "useDoclingServe=true&" +
        "splitBatchResults=true&" +
        "contentInBody=true")
    .split(body())
        .process(exchange -> {
            BatchConversionResult result = exchange.getIn().getBody(BatchConversionResult.class);
            log.info("Processing document: {}", result.getDocumentId());

            if (result.isSuccess()) {
                // Process successful conversion
                String content = result.getResult();
                // ... do something with content
            } else {
                // Handle failed conversion
                log.error("Failed to convert {}: {}",
                    result.getOriginalPath(), result.getErrorMessage());
            }
        })
    .end();

// Example 2: Route based on success/failure
from("direct:batch-with-routing")
    .to("docling:convert?" +
        "operation=BATCH_CONVERT_TO_MARKDOWN&" +
        "useDoclingServe=true&" +
        "splitBatchResults=true&" +
        "batchFailOnFirstError=false&" +
        "contentInBody=true")
    .split(body())
        .choice()
            .when(simple("${body.success} == true"))
                .log("Success: ${body.documentId}")
                .to("file:///data/success?fileName=${body.documentId}.md")
            .otherwise()
                .log("Failed: ${body.documentId} - ${body.errorMessage}")
                .to("file:///data/failed?fileName=${body.documentId}.error")
        .end()
    .end();

// Example 3: Parallel processing with threads
from("direct:batch-parallel-individual")
    .to("docling:convert?" +
        "operation=BATCH_CONVERT_TO_MARKDOWN&" +
        "useDoclingServe=true&" +
        "splitBatchResults=true&" +
        "contentInBody=true")
    .split(body())
        .parallelProcessing()
        .threads(5)
        .process(exchange -> {
            BatchConversionResult result = exchange.getIn().getBody(BatchConversionResult.class);
            // Process each document in parallel
            processDocument(result);
        })
    .end();

# Example 1: Split and route based on success
- route:
    from:
      uri: "direct:batch-with-split"
    steps:
      - to:
          uri: "docling:convert"
          parameters:
            operation: "BATCH_CONVERT_TO_MARKDOWN"
            useDoclingServe: true
            splitBatchResults: true
            contentInBody: true
      - split:
          simple: "${body}"
          steps:
            - choice:
                when:
                  - simple: "${body.success}"
                    steps:
                      - log: "Success: ${body.documentId}"
                      - to: "file:///data/success?fileName=${body.documentId}.md"
                otherwise:
                  steps:
                    - log: "Failed: ${body.documentId}"
                    - to: "file:///data/failed?fileName=${body.documentId}.error"

# Example 2: Split with parallel processing
- route:
    id: batch-split-parallel
    from:
      uri: "direct:batch-parallel"
    steps:
      - to:
          uri: "docling:convert"
          parameters:
            operation: "BATCH_CONVERT_TO_MARKDOWN"
            useDoclingServe: true
            splitBatchResults: true
            batchParallelism: 4
            contentInBody: true
      - split:
          simple: "${body}"
          parallelProcessing: true
          steps:
            - log: "Processing document ${body.documentId} (index ${body.batchIndex})"
            - choice:
                when:
                  - simple: "${body.success}"
                    steps:
                      - log: "Successfully converted ${body.documentId}"
                      - to: "file:///data/processed?fileName=${body.documentId}.md"
                otherwise:
                  steps:
                    - log: "Failed to convert ${body.documentId}: ${body.errorMessage}"
                    - to: "file:///data/errors?fileName=${body.documentId}.error"

from("file:///data/documents?include=.*\\.pdf")
    .to("docling:CONVERT_TO_MARKDOWN?" +
        "useDoclingServe=true&" +
        "useAsyncMode=true&" +
        "asyncPollInterval=2000&" +
        "asyncTimeout=300000&" +
        "contentInBody=true")
    .to("file:///data/output");

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"
          parameters:
            useDoclingServe: true
            useAsyncMode: true
            asyncPollInterval: 2000
            asyncTimeout: 300000
            contentInBody: true
      - to:
          uri: "file:///data/output"

from("file:///data/large-documents?include=.*\\.pdf")
    .to("docling:CONVERT_TO_MARKDOWN?" +
        "useDoclingServe=true&" +
        "useAsyncMode=true&" +
        "asyncPollInterval=5000&" +
        "asyncTimeout=600000&" +  // 10 minutes
        "contentInBody=true")
    .to("file:///data/output");

- route:
    from:
      uri: "file:///data/large-documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"
          parameters:
            useDoclingServe: true
            useAsyncMode: true
            asyncPollInterval: 5000
            asyncTimeout: 600000
            contentInBody: true
      - to:
          uri: "file:///data/output"

from("file:///data/documents?include=.*\\.pdf")
    .process(exchange -> {
        File file = exchange.getIn().getBody(File.class);
        // Use async mode only for large files
        if (file.length() > 10 * 1024 * 1024) { // > 10MB
            exchange.getIn().setHeader("CamelDoclingUseAsyncMode", true);
            exchange.getIn().setHeader("CamelDoclingAsyncTimeout", 600000L);
        }
    })
    .to("docling:CONVERT_TO_MARKDOWN?useDoclingServe=true&contentInBody=true")
    .to("file:///data/output");

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - process:
          ref: "asyncDecisionProcessor"
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"
          parameters:
            useDoclingServe: true
            contentInBody: true
      - to:
          uri: "file:///data/output"

from("file:///data/documents?include=.*\\.pdf")
    .to("docling:CONVERT_TO_MARKDOWN?useDoclingServe=true&doclingServeUrl=http://localhost:5001&contentInBody=true")
    .process(exchange -> {
        String markdown = exchange.getIn().getBody(String.class);
        log.info("Converted content: {}", markdown);
    });

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"
          parameters:
            useDoclingServe: true
            doclingServeUrl: "http://localhost:5001"
            contentInBody: true
      - process:
          ref: "markdownProcessor"

from("timer:convert?repeatCount=1")
    .setBody(constant("https://arxiv.org/pdf/2501.17887"))
    .to("docling:CONVERT_TO_MARKDOWN?useDoclingServe=true&contentInBody=true")
    .to("file:///data/output");

- route:
    from:
      uri: "timer:convert"
      parameters:
        repeatCount: 1
    steps:
      - setBody:
          constant: "https://arxiv.org/pdf/2501.17887"
      - to:
          uri: "docling:CONVERT_TO_MARKDOWN"
          parameters:
            useDoclingServe: true
            contentInBody: true
      - to:
          uri: "file:///data/output"

from("file:///data/documents?include=.*\\.(pdf|docx)")
    .to("docling:CONVERT_TO_HTML?useDoclingServe=true&doclingServeUrl=http://localhost:5001&contentInBody=true")
    .to("file:///data/converted?fileName=${file:name.noext}.html");

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.(pdf|docx)"
    steps:
      - to:
          uri: "docling:CONVERT_TO_HTML"
          parameters:
            useDoclingServe: true
            doclingServeUrl: "http://localhost:5001"
            contentInBody: true
      - to:
          uri: "file:///data/converted"
          parameters:
            fileName: "${file:name.noext}.html"

from("file:///data/documents?include=.*\\.pdf")
    .to("docling:EXTRACT_STRUCTURED_DATA?" +
        "useDoclingServe=true&" +
        "doOcr=true&" +
        "ocrEngine=TESSERACT&" +
        "doTableStructure=true&" +
        "tableMode=ACCURATE&" +
        "doCodeEnrichment=true&" +
        "pdfBackend=DLPARSE_V4&" +
        "processTimeout=120000&" +     // 2 minutes for complex PDFs
        "contentInBody=true")
    .process(exchange -> {
        DoclingDocument doc = exchange.getIn().getBody(DoclingDocument.class);
        // Process the structured document
    });

- route:
    from:
      uri: "file:///data/documents"
      parameters:
        include: ".*\\.pdf"
    steps:
      - to:
          uri: "docling:EXTRACT_STRUCTURED_DATA"
          parameters:
            useDoclingServe: true
            doOcr: true
            ocrEngine: "TESSERACT"
            doTableStructure: true
            tableMode: "ACCURATE"
            doCodeEnrichment: true
            pdfBackend: "DLPARSE_V4"
            processTimeout: 120000
            contentInBody: true
      - process:
          ref: "structuredDataProcessor"