filehugger.comInvoice & Receipt to JSON/CSV
Extract vendor, invoice number, date, subtotal, tax, total and currency from document text, then review every field against its source line.
Analyse your own file
Choose a PDF, plain text and receipt/invoice images file
Drop it here or browse this device
Your original file is analysed in this browser and is not uploaded. An optional AI second-opinion button appears only after the local report; if you choose it, extracted text—not the original file—is sent to our server.
What happens to the file
- Default processing
- Browser-only JavaScript, PDF.js, pdf-lib and Tesseract where the task needs them
- Accepted input
- PDF, plain text and receipt/invoice images
- Report contract
- File Intelligence JSON schema 1.0 plus a flattened CSV view
- Optional AI
- Explicit second opinion; extracted text only; original file is not uploaded
Synthetic invoice fields: FH-2026-0042, 2026-07-18, EUR 120.00 subtotal, EUR 24.00 VAT and EUR 144.00 total.
How the result is calculated
PDF text or local OCR is normalised, then multilingual labels and bounded value patterns extract fields. Each value retains a source line and evidence preview. Optional AI can refine ambiguous labels but cannot bypass review.
Confidence = detected supported fields ÷ seven expected fields × 88. It measures coverage, not accounting correctness. Totals are never silently recalculated or invented.
Supported and unsupported cases
| Input or situation | What version 1.0.0 checks | What it does not claim |
|---|---|---|
| Labelled invoice/receipt | Vendor candidate, invoice number, date, subtotal, tax, total and currency | Every country-specific tax schema |
| Selectable PDF/text | Deterministic label extraction with source evidence | Complex tables and merged line items |
| Printed image | Local English or Turkish OCR before extraction | Handwriting, thermal damage or unsupported languages |
| JSON/CSV export | One reviewed record and evidence metadata | Direct bookkeeping-system posting |
What the confidence score means
Confidence describes how much of the file the published parser could inspect and how specific the evidence was. It is deliberately separate from the result score. A 95/100 confidence value does not mean “95% likely to be true,” and a high health/readiness score does not certify safety, compliance or factual correctness.
Comparison with other approaches
| Approach | Useful strength | Important limitation |
|---|---|---|
| Local evidence extractor | Local first, source-line evidence, JSON/CSV | Small published field schema |
| Manual spreadsheet entry | Flexible human judgment | Slow and vulnerable to transposition |
| Template OCR | Strong on one fixed layout | Breaks when the supplier layout changes |
| Accounting platform OCR | Integrates with posting workflow | Upload, subscription and vendor lock-in may apply |
7/7 fixtures passed (100%)
Dataset: FH-INT-SYNTH-2026-07. Scope: Vendor, number, date, subtotal, tax, total and currency labelled-field fixtures. Fixtures contain generated data only; no visitor file or personal record is collected.
When this result can be wrong
A document may contain several dates, currencies or totals. OCR decimal errors are costly. “Total” can mean a line item, subtotal or amount due. Confirm vendor, date, tax and final amount before importing.
Keep the original file, test the output in the receiving application and escalate high-stakes legal, financial, medical, accessibility or security decisions to a qualified reviewer.
Version and accuracy change log
| Release | Date | Calculation/coverage change | Re-test requirement |
|---|---|---|---|
| 1.0.0 | 2026-07-29 | Initial public engine, report schema, thresholds, synthetic fixtures and sample files. | All published fixtures and one browser sample per tool. |
Downloadable evidence, not a black-box verdict
After analysis, use Download JSON report for structured evidence or Download CSV report for review in a spreadsheet. Both include engine version, timestamp, score, confidence, metrics, findings, recommendations and limitations. Sensitive-data reports mask candidate values and no report includes the complete extracted document text.
Related tools and independent checks
Method or accuracy correction? Read the testing methodology and contact info@brothers.net.tr. Material scoring changes are published in the change log.