Supported formats

docparser dispatches by file extension and normalizes everything into the same Markdown + JSON block schema (see Output & schema). Here's what each parser captures.

.docx#

• Walks the document body in document order (paragraphs + tables + drawings).
• Preserves heading hierarchy (section_path) on every block.
• Extracts every embedded image to data/assets/<slug>/ with a stable img-<seq>-<sha10>.<ext> name.
• Detects figure/table captions (style Caption, or text matching Figure 1: … / Fig. 1. / Table 1.) and associates the caption with the preceding image.
• Captures context_before and context_after for every image so the VLM has document-grounded context.

.xlsx#

• Iterates every sheet, every row, every column.
• For each cell stores: address, row/col indices, value, openpyxl data_type, number_format, hyperlink, comment, and the formula (from a second pass with data_only=False).
• Stores merged_ranges, frozen_panes, and any embedded images.
• Markdown rendering uses the first non-empty row as a header heuristic and preserves multi-line cells with <br>.

.pdf#

• Page-by-page text extraction in reading order via PyMuPDF's blocks API.
• Best-effort heading detection from font size (≥120% of the body-text median promotes a line to a heading; the bold flag is tracked).
• Embedded raster images extracted via doc.extract_image(xref).
• Pluggable backends, OCR, and table extraction — covered in detail in PDF backends & OCR.

.html#

• Article-grade body extraction via trafilatura.
• Plus a structural BeautifulSoup walk that emits typed blocks (heading / paragraph / list / table / image) so downstream RAG layers can rely on the JSON.
• source may be a local path or an http(s):// URL.

.pptx#

• Walks slides in presentation order; each slide becomes a section.
• Emits per-slide headings (slide title), bulleted text frames (with list level), tables, pictures, and speaker notes.
• Embedded pictures are extracted and optionally captioned.

.epub#

• Walks the spine in reading order; per-chapter BeautifulSoup structural walk.
• Captures metadata (title/author/language), headings, paragraphs, lists, tables, and embedded images (resolved from the EPUB image manifest).

.txt / .md and .csv / .tsv (core, no extras)#

• Plain text is split into paragraph blocks; Markdown is passed through and also decomposed into heading / list / code / paragraph blocks.
• CSV/TSV: delimiter sniffing, header detection, a Markdown table, and one JSON record per row.