21fcd902d1
Implements the slide_deck document profile for PowerPoint/Keynote/Google Slides exports as PDF. Includes 5 fixtures, expected outputs, and regression tests. Components: - profiles/builtin/slide_deck/profile.yaml - Profile configuration - tests/fixtures/profiles/slide_deck/ - 5 PDF fixtures with expected outputs - crates/pdftract-cli/tests/test_slide_deck.rs - Regression tests (12 PASS) Fixtures cover: 1. pitch_deck - Sales pitch (10 slides) 2. academic_lecture - Academic lecture (40 slides) 3. corporate_kickoff - Corporate kickoff (15 slides) 4. bilingual_deck - Bilingual EN/ES (12 slides) 5. googleslides_handout - Google Slides handout mode (4 pages, 3 slides/page) Extracted fields: title, presenter, date, slide_titles Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
66 lines
1.6 KiB
YAML
66 lines
1.6 KiB
YAML
# Scientific Paper Profile
|
|
#
|
|
# Academic papers from arXiv, journals, conference proceedings.
|
|
# Extracts title, authors, abstract, DOI, journal, publication_date, references.
|
|
|
|
name: scientific_paper
|
|
description: Academic papers from arXiv, journals, conference proceedings
|
|
priority: 30
|
|
|
|
# Matching predicates for scientific paper classification
|
|
match:
|
|
all:
|
|
# Must have at least one scientific paper marker
|
|
- any:
|
|
- text_contains: ["Abstract", "References", "doi:", "arXiv:", "Bibliography"]
|
|
- heading_matches: '^(Abstract|Introduction|References|Bibliography)'
|
|
# And either has math OR structured headings OR appropriate page count
|
|
- any:
|
|
- structural:
|
|
has_math: true
|
|
- structural:
|
|
heading_depth: {min: 2}
|
|
- structural:
|
|
page_count: {min: 4, max: 50}
|
|
|
|
# Extraction tuning for scientific papers
|
|
extraction:
|
|
# Use xy_cut reading order for 2-column layout handling
|
|
reading_order: xy_cut
|
|
# Default table detection
|
|
table_detection: default
|
|
# Standard readability threshold
|
|
readability_threshold: 0.5
|
|
# Don't include invisible text
|
|
include_invisible: false
|
|
|
|
# Field extraction specifications
|
|
fields:
|
|
title:
|
|
region: top_quarter
|
|
pick: largest_font
|
|
|
|
authors:
|
|
region: top_quarter
|
|
pick: nearest_below
|
|
after: title
|
|
|
|
abstract:
|
|
near: ["Abstract"]
|
|
region: top_half
|
|
|
|
doi:
|
|
regex: 'doi[:\.]\s*(10\.\d{4,9}/[\w\-\._;()/:]+)'
|
|
parse: string
|
|
|
|
journal:
|
|
region: top_eighth
|
|
pick: first
|
|
|
|
publication_date:
|
|
near: ["Published", "Received", "Accepted"]
|
|
parse: date
|
|
|
|
references:
|
|
region: bottom_half
|
|
after_heading: References
|