Recommended Free Tools
Docling’s table, page-reading-order, and heading-hierarchy problems usually come from different stages of its PDF pipeline. First identify what failed: whether the page text is available, layout detection found a table, table structure mapped its cells correctly, prose was read in the right order, or headings received hierarchy levels. Then change the setting for that stage—not a table option for every kind of column problem.
Diagnose the failure before changing settings
Docling processes PDFs through distinct stages, including layout detection, OCR where needed, table-structure recognition, reading-order handling, and document assembly. A table-structure setting cannot reconstruct a table region that layout detection did not identify. Likewise, a page with ordinary newspaper-style text columns is a reading-order problem, not necessarily a table problem.
As an Amazon Associate I earn from qualifying purchases.
- Compare the extracted text with the visible page. Determine whether the PDF has a usable text layer, is scanned, has image-only regions, or mixes these types. If text is missing or garbled, check whether OCR is needed and whether the selected engine and language are available. Don’t add OCR automatically to a digital PDF with a sound text layer; check the relevant page first. OCR can misread small type, symbols, and dense numeric tables. Docling’s model catalog describes separate layout, OCR, and table-recognition stages and lists engines and modes; availability depends on the installed release and environment.
- Check whether layout detection marked the region as a table. If it did not, the failure occurs before table-cell reconstruction. Docling’s layout stage labels page elements such as text, tables, pictures, and section headers; table structure recognition is a separate stage.
- Classify the symptom. A detected table with bad cells calls for a table-structure check. Merged prose columns call for a reading-order check. Headings all marked level one call for hierarchy inference. These fixes are not interchangeable.
Fix a detected table with incorrect structure
Try accurate table mode for difficult cell structure
The current advanced-options documentation describes TableFormer accurate mode as the default and says it is intended to improve quality on difficult table structures; fast mode is quicker but less accurate. If using an older or customized pipeline, confirm the installed version’s default. Accurate mode is not a cure for a table region that layout detection missed, and it does not guarantee correct output. See the advanced options documentation.
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions, TableFormerMode
from docling.document_converter import DocumentConverter, PdfFormatOption
pipeline_options = PdfPipelineOptions(do_table_structure=True)
pipeline_options.table_structure_options.mode = TableFormerMode.ACCURATE
converter = DocumentConverter(
format_options={InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)}
)Test cell matching when table columns merge
Docling normally maps recognized table structure back to cells from the PDF. If multiple columns inside an extracted table merge, compare the output with cell matching disabled:
#1 Best Overall
- PORTABLE SCANNER FOR USE ON-THE-GO — The fastest and lightest mobile single-sheet-fed compact document scanner in its class¹
- QUICK DOCUMENT SCANNING ― This Epson ultra-fast scanner scans a single page as quickly as 5.5 seconds²; Windows and Mac compatible
- VERSATILE PAPER HANDLING ― Portable scanner scans documents up to 8.5 x 72 in; Also easily digitizes receipts and ID cards to make accounting, bookkeeping, and organizing simpler
- INTUITIVE, HIGH-SPEED SOFTWARE — Epson ScanSmart Software³ is a smart tool allowing you to easily scan, review, and save; Stay organized easily with the help of this Epson scanner
- EASY SETUP — USB-powered connect to your computer for quick and simple scanning; No batteries or external power supply required to operate portable document scanner; Standard Connectivity: USB 2.0
pipeline_options.table_structure_options.do_cell_matching = FalseThis makes Docling use the text cells predicted by the table-structure model instead of matching them back to PDF cells. Compare both outputs against the source page. This option targets table cells; it is not a general fix for prose columns flowing together.
Check intentionally blank columns separately
A fully empty table column can be removed during post-processing. In a Docling project discussion, a maintainer explained that fully empty rows and columns are removed because they may be prediction anomalies; a June 2025 reply reported the behavior still occurring. Do not assume accurate mode preserves intentional blanks. Inspect the exported table against the page and verify behavior in the installed release. See Docling discussion #201.
Rank #2
- FAST SPEEDS - Scans color and black and white documents a blazing speed up to 16ppm (1). Color scanning won’t slow you down as the color scan speed is the same as the black and white scan speed.
- ULTRA COMPACT – At less than 1 foot in length and only about 1. 5lbs in weight you can fit this device virtually anywhere (a bag, a purse, even a pocket).
- READY WHENEVER YOU ARE – The DS-640 mobile scanner is powered via an included micro USB 3. 0 cable allowing you to use it even where there is no outlet available. Plug it into you PC or laptop and you are ready to scan.
- WORKS YOUR WAY – Use the Brother free iPrint&Scan desktop app for scanning to multiple “Scan-to” destinations like PC, Network, cloud services, Email and OCR. (2) Supports Windows, Mac and Linux and TWAIN/WIA for PC/ICA for Mac/SANE drivers. (3)
- OPTIMIZE IMAGES AND TEXT – Automatic color detection/adjustment, image rotation (PC only), bleed through prevention/background removal, text enhancement, color drop to enhance scans. Software suite includes document management and OCR software. (4)
Fix prose columns read in the wrong order
For a multi-column article, report, or financial page, investigate reading order rather than table reconstruction. Docling’s rule-based reading-order stage can use visible PDF rules as signals and is enabled by default. If rules separating columns or horizontal bands appear to disrupt the sequence, test with separators disabled:
Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallpipeline_options = PdfPipelineOptions(use_reading_order_separators=False)The equivalent CLI option is --no-reading-order-separators. The documented option affects ordering only. Test it on the affected pages and compare the resulting sequence to the visual layout.
Rank #3
- FAST DOCUMENT SCANNING — Document scanner with feeder allows you to speed through stacks with a 50-sheet Auto Document Feeder (ADF); Efficient office scanner to help you scan more productively
- INTUITIVE, HIGH-SPEED SOFTWARE — Quickly scan with this desktop document scanner; Epson ScanSmart Software lets you easily preview scans, email files, upload to the cloud, and more; Plus, automatic file naming saves even more time
- SEAMLESS INTEGRATION — Easily incorporate your data into most document management software with the included TWAIN driver; Office document scanner integrates seamlessly with business workflows
- EASY SHARING — Duplex scanner allows you to scan straight to email or popular cloud storage2 services like Dropbox, Evernote, Google Drive, and OneDrive for simple storage and sharing
- SIMPLE FILE MANAGEMENT — Scanner allows the creation of searchable PDFs with Optical Character Recognition (OCR) and convert scans to editable Word or Excel files effortlessly; Designed for home and office document scanning
A Docling issue reported text flowing across columns in a three-column financial document even with table-structure processing enabled and do_cell_matching=False. That report concerned Docling 2.43.0 and was filed on 2025-08-10; it illustrates that table options do not guarantee correct page reading order, not that every current release has the same behavior. See Docling issue #2067.
Give PDF headings hierarchy levels
Recognizing a block as a section header and determining its depth in the document are separate tasks. Docling’s advanced-options documentation says: “The layout model marks section headers but not how deep they sit, so by default every heading in a PDF comes out at level 1.” Enable the heading-hierarchy stage for PDF processing:
Rank #4
- Scanner type: Document
- Connectivity technology: USB
- With Auto Scan Mode, the scanner automatically detects what you're scanning
- Digitize documents and images
from docling.datamodel.pipeline_options import HeadingHierarchyOptions, PdfPipelineOptions
pipeline_options = PdfPipelineOptions()
pipeline_options.heading_hierarchy_options = HeadingHierarchyOptions(enabled=True)
pipeline_options.generate_parsed_pages = TrueHierarchy inference uses PDF bookmarks first, then heading numbering, then visual style. Parsed pages are needed for font-style inference. The stage rewrites section-header levels; it does not add or reorder document content. Documentation and defaults can vary by release, so check the advanced options and heading-level guidance for the version in use.
Scanned PDFs have less style information
OCR does not provide font metadata. For scanned pages, hierarchy inference therefore cannot use font weight or slant and ranks visual style by size alone. Bookmarks and numbering may still provide signals when present. Review the inferred levels rather than assuming a scan will preserve the source’s full typographic hierarchy.
Best Value
- OUR MOST ADVANCED SCANSNAP. Large touchscreen, fast 45ppm double-sided scanning, 100-sheet document feeder, Wi-Fi and USB connectivity, automatic optimizations, and support for cloud services. Upgraded replacement for the discontinued iX1600
- CUSTOMIZABLE. SHARABLE. Select personalized profiles from the touchscreen. Send to PC, Mac, mobile devices, and clouds. QUICK MENU lets you quickly scan-drag-drop to your favorite computer apps
- STABLE WIRELESS OR USB CONNECTION. Built-in Wi-Fi 6 for the fastest and most secure scanning. Connect to smart devices or cloud services without a computer. USB-C connection also available
- PHOTO AND DOCUMENT ORGANIZATION MADE EFFORTLESS. Easily manage, edit, and use scanned data from documents, receipts, photos, and business cards. Automatically optimize, name, and sort files
- AVOIDS PAPER JAMS AND DAMAGE. Features a brake roller system to feed paper smoothly, a multi-feed sensor that detects pages stuck together, and skew detection to prevent paper damage and data loss
Validate fixes against the page
Judge each output dimension independently: page text, table cells, reading sequence, and heading levels. A plausible Markdown table or outline can still differ from the source page. For high-value documents, manually check affected pages and keep a small set of representative pages as a regression sample when changing settings or upgrading Docling. The official options expose parsed-page and image controls that can help inspect the page representation.
If targeted configuration still leaves important pages unreliable, compare other OCR or document-parsing approaches on the same representative pages. Evaluate whether each handles the input type and needed OCR languages, distinguishes ordinary columns from tables, represents merged cells and blank columns as required, retains page or region traceability, and processes documents locally or remotely. Docling’s documentation says use of remote OCR or hosted models is explicitly opt-in; decide whether that data flow meets the document’s privacy and deployment constraints before enabling a remote service: remote-service options. No comparative performance claim follows from the configuration guidance alone.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
Quick wins for a faster PC:
Repair Windows errors before they cause bigger problemsFix Now →Scan for outdated or missing drivers - takes under a minuteDriver Scan →
