The .docx file.
- Really a
- ZIP archive of XML parts
- Tables
- Stored as real structures, including merged cells
- Prose
- Discarded. Only the tables are read.
- Embedded objects
- Not read. An embedded workbook has to be sent as its own file.
- Read here as
- Extracted. The tables are lifted out and the rest of the document is dropped.
- Status
- Ready
- Fidelity
- Data extracted
- Largest file
- 25 MB free, 250 MB once a project is bought
What it actually is
Tables are lifted out of the document; the prose around them is kept as context.
A .docx is a ZIP of XML, and its tables are stored as genuine table structures with rows, cells and merges. This is the key difference from a PDF. Nothing has to be inferred from the geometry, because the grid is written down.
Only the tables come out. Everything else in the document, the prose, the headings, the footnotes, is discarded on the way in, so a sentence reading "figures exclude the Northern region pending migration" does not arrive beside the numbers it qualifies.
The awkward case is a document whose numbers are in the sentences rather than in a table, which is common in board reports. Nothing outside a table is read, so those figures do not arrive at all, and a document written that way is the wrong file to be analysing.
Upload one
The analysis runs before there is anything to pay for.
You see what it found, and the evidence behind it, first.
No account needed to start. You only pay when you like what you see.
What goes wrong, and what is done about it
2 named failures, each with the repair.
Merged cells that were doing two jobs
A merged cell spanning three columns is often a group heading rather than a value, and flattening it repeats the heading into three data cells that then look like observations.
What is done: Merged spans are not read as spans. A merged cell is one cell, so the row holding it comes out narrower than the header above it, and a table built with group headings is better sent as the spreadsheet it came from.
Numbers that only exist in a sentence
Board and management reports frequently state the important figure in prose and put only supporting detail in the tables. Extracting tables alone gets everything except the thing the document was written to say.
What is done: Nothing outside a table is read, so that figure does not arrive at all. Where the headline number lives in prose, put it into a table, or send the spreadsheet it was calculated in, before uploading.
If you have the choice, send something else
If the tables in the document were pasted from a spreadsheet, send the spreadsheet as well. The document has the numbers; the workbook has the formulas that produced them.
Questions people ask
About this format, not about the product.
Is this better than uploading the PDF version?
Yes, meaningfully. The Word file stores table structure explicitly, while the PDF stores glyph positions from which the structure has to be inferred. Send the .docx where you have the choice.
What happens to images and charts in the document?
Neither is read. Only the document's tables come out; a chart is dropped along with everything else that is not one, whether it is native or pasted in as a picture.
Can it handle a document with twenty tables?
Yes. Each one becomes its own table, keyed by where it sits in the document. The analysis then runs on the largest of them: the rest are read and available, but no figure is computed across two tables.
Keep reading
The jobs people do with this file, and the formats beside it.