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
2.2 KiB
YAML
68 lines
2.2 KiB
YAML
description: Bank statement with account info, period, balances, transactions
|
|
priority: 42
|
|
match:
|
|
any:
|
|
- text_patterns:
|
|
- "(?i)statement\\s+of\\s+account"
|
|
- "(?i)bank\\s+statement"
|
|
- "(?i)account\\s+statement"
|
|
- "(?i)transaction\\s+history"
|
|
- text_patterns:
|
|
- "(?i)opening\\s+balance"
|
|
- "(?i)closing\\s+balance"
|
|
- "(?i)statement\\s+period"
|
|
- "(?i)account\\s*#?\\s*:?\\s*\\*{4,}"
|
|
- structural:
|
|
- has_monetary_columnar_layout: true
|
|
- has_date_column: true
|
|
page_count_hint: 1-10
|
|
profile_fields:
|
|
account_number:
|
|
type: string
|
|
extraction:
|
|
patterns:
|
|
- "(?i)account\\s*(?:number|#|no)?\\s*:?,?\\s*(\\*?\\d[\\d\\*]{3,})"
|
|
- "(?i)acct\\s*(?:#|:)?\\s*(\\*?\\d[\\d\\*]{3,})"
|
|
fallback: null
|
|
statement_period:
|
|
type: string
|
|
extraction:
|
|
patterns:
|
|
- "(?i)statement\\s+period\\s*:?.*?([A-Za-z]+\\s+[0-9]{1,2}.*?through.*?[A-Za-z]+\\s+[0-9]{1,2},?\\s+[0-9]{4})"
|
|
- "(?i)period\\s*:?.*?([0-9]{1,2}[/-][0-9]{1,2}[/-][0-9]{2,4})\\s+(?:to|through|-)\\s+([0-9]{1,2}[/-][0-9]{1,2}[/-][0-9]{2,4})"
|
|
fallback: null
|
|
opening_balance:
|
|
type: decimal
|
|
extraction:
|
|
patterns:
|
|
- "(?i)opening\\s+balance\\s*:?.*?[\\$€£¥]?\\s*([0-9,]+\\.?[0-9]*)"
|
|
- "(?i)beginning\\s+balance\\s*:?.*?[\\$€£¥]?\\s*([0-9,]+\\.?[0-9]*)"
|
|
fallback: null
|
|
closing_balance:
|
|
type: decimal
|
|
extraction:
|
|
patterns:
|
|
- "(?i)closing\\s+balance\\s*:?.*?[\\$€£¥]?\\s*([0-9,]+\\.?[0-9]*)"
|
|
- "(?i)ending\\s+balance\\s*:?.*?[\\$€£¥]?\\s*([0-9,]+\\.?[0-9]*)"
|
|
- "(?i)current\\s+balance\\s*:?.*?[\\$€£¥]?\\s*([0-9,]+\\.?[0-9]*)"
|
|
fallback: null
|
|
transactions:
|
|
type: array
|
|
extraction:
|
|
table_region: "largest_table_or_central_body"
|
|
schema:
|
|
- name: date
|
|
type: date
|
|
required: true
|
|
- name: description
|
|
type: string
|
|
required: true
|
|
- name: amount
|
|
type: decimal
|
|
required: false
|
|
- name: balance
|
|
type: decimal
|
|
required: false
|
|
fallback: []
|
|
reading_order: line_dominant
|
|
zone_filtering: exclude_headers_footers
|