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>
68 lines
1.8 KiB
YAML
68 lines
1.8 KiB
YAML
description: Point-of-sale or purchase receipt with items, payment method
|
|
priority: 45
|
|
match:
|
|
any:
|
|
- text_patterns:
|
|
- "(?i)receipt"
|
|
- "(?i)store receipt"
|
|
- "(?i)register receipt"
|
|
- "(?i)transaction receipt"
|
|
- text_patterns:
|
|
- "(?i)total.*sold"
|
|
- "(?i)change.*due"
|
|
- "(?i)cash.*credit"
|
|
- "(?i)card.*payment"
|
|
- structural:
|
|
- has_monetary_columnar_layout: true
|
|
- page_aspect_ratio: "narrow_or_square"
|
|
page_count_hint: 1
|
|
profile_fields:
|
|
merchant:
|
|
type: string
|
|
extraction:
|
|
patterns:
|
|
- "(?i)^([A-Z][A-Za-z0-9\\s&']+)$"
|
|
- "(?i)(?:store|merchant|retailer)\\s*:?\\s*([A-Z][A-Za-z0-9\\s&']+)"
|
|
fallback: null
|
|
date:
|
|
type: date
|
|
extraction:
|
|
patterns:
|
|
- "(?i)date\\s*:?\\s*([0-9]{1,2}[/-][0-9]{1,2}[/-][0-9]{2,4})"
|
|
- "([0-9]{1,2}[/-][0-9]{1,2}[/-][0-9]{2,4})\\s+([0-9]{1,2}:[0-9]{2})"
|
|
fallback: null
|
|
total:
|
|
type: decimal
|
|
extraction:
|
|
patterns:
|
|
- "(?i)total\\s*[:=]?\\s*[\\$€£¥]?\\s*([0-9,]+\\.?[0-9]*)"
|
|
fallback: null
|
|
tax:
|
|
type: decimal
|
|
extraction:
|
|
patterns:
|
|
- "(?i)tax\\s*[:=]?\\s*[\\$€£¥]?\\s*([0-9,]+\\.?[0-9]*)"
|
|
fallback: null
|
|
items:
|
|
type: array
|
|
extraction:
|
|
columnar_regions: "monetary_columns"
|
|
schema:
|
|
- name: name
|
|
type: string
|
|
required: true
|
|
- name: quantity
|
|
type: decimal
|
|
required: false
|
|
- name: price
|
|
type: decimal
|
|
required: false
|
|
fallback: []
|
|
payment_method:
|
|
type: string
|
|
extraction:
|
|
patterns:
|
|
- "(?i)(cash|credit|debit|visa|mastercard|amex|discover|check|cheque)"
|
|
fallback: null
|
|
reading_order: line_dominant
|
|
zone_filtering: exclude_headers_footers
|