8b5dd4febb
This commit creates user-facing documentation for each built-in profile: - Profile YAML files defining match criteria, priority, and extracted fields - Per-profile READMEs with match criteria summary, extracted fields table, known limitations, sample input pointers, and configuration tips - xtask skeleton generator for automated README generation Profiles documented: - invoice: Commercial invoices with line items, vendor/customer, totals - receipt: POS receipts with items, payment method - contract: Legal contracts with parties, effective date, term, signatures - scientific_paper: Academic papers with title, authors, abstract, DOI, references - slide_deck: Presentation slides with title, presenter, date, slide titles - form: Fillable forms (degenerate case: uses Phase 7.4 form_fields) - bank_statement: Bank statements with account info, period, balances, transactions - legal_filing: Court filings with case number, court, parties, filing date, docket - book_chapter: Book chapters with title, chapter number, author, section headings Closes: pdftract-4iier Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
47 lines
1.2 KiB
YAML
47 lines
1.2 KiB
YAML
description: Presentation slides with title, presenter, date, slide titles
|
|
priority: 35
|
|
match:
|
|
any:
|
|
- structural:
|
|
- page_aspect_ratio: "landscape"
|
|
- page_count_gte: 3
|
|
- has_large_centred_text: true
|
|
- text_patterns:
|
|
- "(?i)presentation"
|
|
- "(?i)slide\\s+[0-9]+"
|
|
- "(?i)table\\s+of\\s+contents"
|
|
page_count_hint: 3-200
|
|
profile_fields:
|
|
title:
|
|
type: string
|
|
extraction:
|
|
region_hint: "first_page_centre"
|
|
patterns:
|
|
- "^(.+)$"
|
|
fallback: null
|
|
presenter:
|
|
type: string
|
|
extraction:
|
|
region_hint: "first_page_below_title"
|
|
patterns:
|
|
- "([A-Z][a-z]+\\s+[A-Z][a-z]+)"
|
|
- "([A-Z]\\.[A-Z]\\.[A-Za-z]+)"
|
|
fallback: null
|
|
date:
|
|
type: date
|
|
extraction:
|
|
region_hint: "first_page_bottom"
|
|
patterns:
|
|
- "([A-Za-z]+\\s+[0-9]{1,2},?\\s+[0-9]{4})"
|
|
- "([0-9]{1,2}[/-][0-9]{1,2}[/-][0-9]{2,4})"
|
|
fallback: null
|
|
slide_titles:
|
|
type: array
|
|
extraction:
|
|
per_page: true
|
|
region_hint: "top_left_or_centre"
|
|
patterns:
|
|
- "^[A-Z][A-Za-z0-9\\s\\-:]+$"
|
|
fallback: []
|
|
reading_order: line_dominant
|
|
zone_filtering: none
|