* Handle a PDF buffer directly in memory
( fileBuffer: Buffer, filename: string, fileType?: string, originalPath?: string, maxParsedOutputBytes?: number )
| 912 | * Handle a PDF buffer directly in memory |
| 913 | */ |
| 914 | async function handlePdfBuffer( |
| 915 | fileBuffer: Buffer, |
| 916 | filename: string, |
| 917 | fileType?: string, |
| 918 | originalPath?: string, |
| 919 | maxParsedOutputBytes?: number |
| 920 | ): Promise<ParseResult> { |
| 921 | try { |
| 922 | logger.info(`Parsing PDF in memory: ${filename}`) |
| 923 | |
| 924 | const result = await parseBufferAsPdf(fileBuffer) |
| 925 | |
| 926 | const content = |
| 927 | result.content || |
| 928 | createPdfFallbackMessage(result.metadata?.pageCount || 0, fileBuffer.length, originalPath) |
| 929 | const limitedContent = assertParsedContentWithinLimit(content, maxParsedOutputBytes) |
| 930 | |
| 931 | return { |
| 932 | success: true, |
| 933 | content: limitedContent, |
| 934 | filePath: originalPath || filename, |
| 935 | metadata: { |
| 936 | fileType: fileType || 'application/pdf', |
| 937 | size: fileBuffer.length, |
| 938 | hash: createHash('md5').update(fileBuffer).digest('hex'), |
| 939 | processingTime: 0, |
| 940 | }, |
| 941 | } |
| 942 | } catch (error) { |
| 943 | if (isPayloadSizeLimitError(error)) throw error |
| 944 | |
| 945 | logger.error('Failed to parse PDF in memory:', error) |
| 946 | |
| 947 | const content = createPdfFailureMessage( |
| 948 | 0, |
| 949 | fileBuffer.length, |
| 950 | originalPath || filename, |
| 951 | (error as Error).message |
| 952 | ) |
| 953 | |
| 954 | return { |
| 955 | success: true, |
| 956 | content, |
| 957 | filePath: originalPath || filename, |
| 958 | metadata: { |
| 959 | fileType: fileType || 'application/pdf', |
| 960 | size: fileBuffer.length, |
| 961 | hash: createHash('md5').update(fileBuffer).digest('hex'), |
| 962 | processingTime: 0, |
| 963 | }, |
| 964 | } |
| 965 | } |
| 966 | } |
| 967 | |
| 968 | /** |
| 969 | * Handle a CSV buffer directly in memory |
no test coverage detected