Abimael MartellandClaude Opus 4.6
56cfd895b5
Add pairwise cross-row column alignment check to find_table_regions_strict(). Real tables have fixed column X positions that repeat across rows (score ~1.0), while paragraph text has varying word positions (score ~0.3-0.4). Regions with average pairwise alignment score < 0.5 are now rejected. Also remove the num_cols >= 5 content-check bypass for BodyFont mode, requiring body-font tables to always have ≥30% data-like cell content. Fixes false table detection across 9+ PDFs including AI_Cultural_Collections (-730 false lines), 131212888 (-740), Data-Processing-Agreement (-108), CEP_DN_Interest_Rates (-93). No regressions on legitimate tables. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
48 lines
809 B
TOML
48 lines
809 B
TOML
[package]
|
|
name = "pdf-inspector"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
authors = ["Firecrawl Team"]
|
|
description = "Fast PDF inspection, classification, and text extraction with smart scanned vs text-based detection"
|
|
license = "MIT"
|
|
repository = "https://github.com/firecrawl/pdf-inspector"
|
|
|
|
[dependencies]
|
|
# PDF parsing
|
|
lopdf = { git = "https://github.com/J-F-Liu/lopdf", features = ["rayon"] }
|
|
|
|
# Compression
|
|
flate2 = "1.0"
|
|
|
|
# Error handling
|
|
thiserror = "2.0"
|
|
|
|
# Parallel processing
|
|
rayon = "1.10"
|
|
|
|
# Logging
|
|
log = "0.4"
|
|
|
|
# Text processing
|
|
regex = "1.10"
|
|
once_cell = "1.19"
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3.3"
|
|
|
|
[features]
|
|
default = []
|
|
|
|
[[bin]]
|
|
name = "pdf2md"
|
|
path = "src/bin/pdf2md.rs"
|
|
|
|
[[bin]]
|
|
name = "detect-pdf"
|
|
path = "src/bin/detect_pdf.rs"
|
|
|
|
|
|
[[bin]]
|
|
name = "debug_ygaps"
|
|
path = "src/bin/debug_ygaps.rs"
|