Upload a technical-drawing PDF to Imnoo's drawing analysis and return the sensitive data it finds — company names, logos, person names, addresses, phone numbers, emails, websites, article numbers, drawing numbers, dates and other identifying text — each with a detection id, category, value, PDF page, box (analysis image pixels), confidence, whether it sits in the title block and whether it is masked by default, plus the page sizes. Up to 4 pages are treated as one drawing. Analysis takes roughly 10–120 s; the call waits up to timeout_seconds and otherwise returns status "processing" with the drawing_id to resume with. An identical PDF analysed earlier in this session is returned from memory (no upload). analyze_drawing uploads the PDF to Imnoo's drawing analysis (the service behind the web app): 1 free analysis per day per IP address (signed-in users get more in the web app); uploaded files are deleted automatically within 24 hours and nothing else is stored. Masking itself runs locally and is unlimited.

Open a drawing analysis JSON saved earlier (analyze_drawing with save_analysis_to, or the Imnoo FileStore analysis document) and register it as a drawing for review_masking and mask_drawing. Fully offline — no upload, no daily credit. Pass pdf_path as well: masking needs the original PDF, and custom terms search its text.

Compose the masks for an analysed drawing exactly as mask_drawing will, without writing anything: which detections are masked (with their replacement in mode "replace") and which stay visible, custom-term matches, rectangles, the article-number stamp, the pages written, the anonymity score (0–100) with its warnings, the output file name, and visible_text_after_masking — the text a reader will still see on each page (from the PDF text layer). Use it to find leftovers (a customer name in the notes, a person the analysis missed) and add them as terms or rectangles. Deterministic and offline — iterate freely.

Mask the drawing and write the anonymized PDF: blank (or replacement-text / own-logo) boxes over every masked detection, custom term and rectangle; by default every page is then rasterized at 288 dpi so the covered content is destroyed rather than painted over (tamper-proof single-layer PDF) and the document metadata (author, title, producer, XMP) is removed. Optional coverage report page and page selection. share_link additionally uploads the MASKED copy (never the original) and returns an expiring public link (1m, 15m, 1h or 24h). Accepts drawing_id (from analyze_drawing/load_analysis) or pdf_path for a one-shot run (analyses first). When masking is omitted for a drawing masked before in this session — including an identical PDF under another path — the previous masking is reused. Default location: next to the drawing PDF as _masked.pdf (else _masked.pdf); the source PDF is never modified.