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: Academic paper with title, authors, abstract, DOI, references
|
|
priority: 55
|
|
match:
|
|
any:
|
|
- text_patterns:
|
|
- "(?i)abstract"
|
|
- "(?i)introduction"
|
|
- "(?i)keywords\\s*[:\\.]"
|
|
- "(?i)doi\\s*10\\."
|
|
- text_patterns:
|
|
- "(?i)references\\s*[1-9]"
|
|
- "(?i)bibliography"
|
|
- "(?i)acknowledgments?"
|
|
- structural:
|
|
- has_two_column_layout: true
|
|
- has_bibliography_section: true
|
|
page_count_hint: 4-30
|
|
profile_fields:
|
|
title:
|
|
type: string
|
|
extraction:
|
|
region_hint: "first_page_top"
|
|
patterns:
|
|
- "^(.+)$"
|
|
fallback: null
|
|
authors:
|
|
type: array
|
|
extraction:
|
|
region_hint: "first_page_top_below_title"
|
|
patterns:
|
|
- "([A-Z][a-z]+\\s+[A-Z][a-z]+,?\\s+(?:et\\s+al\\.?|and\\s+[A-Z][a-z]+)*)"
|
|
fallback: []
|
|
abstract:
|
|
type: string
|
|
extraction:
|
|
region_hint: "after_abstract_heading"
|
|
patterns:
|
|
- "(?i)abstract\\s*[:\\.]?\\s*(.+?)(?=\\n\\n|keywords|introduction|$)"
|
|
fallback: null
|
|
doi:
|
|
type: string
|
|
extraction:
|
|
patterns:
|
|
- "(?i)doi\\s*:?\\s*(10\\.[0-9]{4,9}/[-._;()/:A-Z0-9]+)"
|
|
- "(?i)https?://doi\\.org/(10\\.[0-9]{4,9}/[-._;()/:A-Z0-9]+)"
|
|
fallback: null
|
|
journal:
|
|
type: string
|
|
extraction:
|
|
patterns:
|
|
- "(?i)(?:published\\s+in|journal|proceedings)\\s*:.*?([A-Z][A-Za-z\\s]+?)(?=,|\\.|\\n)"
|
|
fallback: null
|
|
publication_date:
|
|
type: date
|
|
extraction:
|
|
patterns:
|
|
- "(?i)(?:received|accepted|published|revised)\\s*:.*?([A-Za-z]+\\s+[0-9]{4})"
|
|
- "©\\s*([0-9]{4})"
|
|
fallback: null
|
|
references:
|
|
type: array
|
|
extraction:
|
|
region_hint: "after_references_heading"
|
|
patterns:
|
|
- "\\[\\d+\\]\\s+.+"
|
|
fallback: []
|
|
reading_order: column_aware
|
|
zone_filtering: exclude_headers_footers_page_numbers
|