package main

import (
    "fmt"
    "log"

    "github.com/rahulpoonia29/extractous-go"
)

func main() {
    // Create a new extractor
    extractor := extractous.New()
    if extractor == nil {
        log.Fatal("Failed to create extractor")
    }
    defer extractor.Close()

    // Extract text and metadata from file
    content, metadata, err := extractor.ExtractFileToString("document.pdf")
    if err != nil {
        log.Fatalf("Extraction failed: %v", err)
    }

    // Results
    fmt.Println("Content:", content)
    fmt.Println("Metadata:", metadata)
}

package main

import (
    "fmt"
    "io"
    "log"

    "github.com/rahulpoonia29/extractous-go"
)

func main() {
    extractor := extractous.New()
    if extractor == nil {
        log.Fatal("Failed to create extractor")
    }
    defer extractor.Close()

    // Get a streaming reader for the document
    reader, metadata, err := extractor.ExtractFile("large_document.pdf")
    if err != nil {
        log.Fatal(err)
    }
    defer reader.Close()

    // Process the document in chunks
    buffer := make([]byte, 8192)
    for {
        n, err := reader.Read(buffer)
        if err == io.EOF {
            break
        }
        if err != nil {
            log.Fatal(err)
        }

        // Process buffer[:n]
        fmt.Printf("Read %d bytes\n", n)
    }
}

package main

import (
    "log"

    "github.com/rahulpoonia29/extractous-go"
)

func main() {
    // Configure PDF extraction with OCR
    pdfConfig := extractous.NewPdfConfig()
    pdfConfig.SetOcrStrategy(extractous.PdfOcrAuto)
    pdfConfig.SetExtractInlineImages(true)
    pdfConfig.SetExtractAnnotationText(true)

    // Configure OCR settings
    ocrConfig := extractous.NewTesseractOcrConfig()
    ocrConfig.SetLanguage("eng")
    ocrConfig.SetDensity(300)

    // Apply configurations to extractor
    extractor := extractous.New()
    extractor.SetPdfConfig(pdfConfig)
    extractor.SetTesseractOcrConfig(ocrConfig)
    extractor.SetXmlOutput(true) // Enable structured output

    defer extractor.Close()

    content, _, err := extractor.ExtractFileToString("scanned_document.pdf")
    if err != nil {
        log.Fatal(err)
    }

    log.Println(content)
}

content, metadata, err := extractor.ExtractFileToString("document.pdf")
if err != nil {
    // Check error type
    if errors.Is(err, extractous.ErrIO) {
        log.Println("File I/O error")
    } else if errors.Is(err, extractous.ErrExtraction) {
        log.Println("Document extraction failed")
    }

    log.Fatal(err)
}

content, metadata, err := extractor.ExtractFileToString("document.pdf")
if err != nil {
    // Get structured error information
    var extractErr *extractous.ExtractError
    if errors.As(err, &extractErr) {
        fmt.Printf("Error code: %d\n", extractErr.Code)
        fmt.Printf("Message: %s\n", extractErr.Message)

        // Optionally get detailed debug information
        // (includes full error chain and backtrace if available)
        if debug := extractErr.Debug(); debug != "" {
            fmt.Printf("Debug info:\n%s\n", debug)
        }
    }
}