Abimael MartellandClaude Opus 4.6
350bbc0086
- Add --pages flag to insert <!-- Page N --> markers between pages - Add --select-pages flag to process only specific pages (e.g. 1,3,5-10) - Wire MarkdownOptions and page filter through process_pdf_with_config - Fix fuzzy CMap matching that caused Cyrillic substitution on Latin text - Fix whitespace Tj items not advancing text matrix (broke gap detection) - Tighten single-char fragment join threshold from 0.25 to 0.20 - Gitignore debug/diagnostic binaries and remove tracked ones Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
65 lines
1.0 KiB
TOML
65 lines
1.0 KiB
TOML
[package]
|
|
name = "pdf-inspector"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
autobins = false
|
|
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"
|
|
|
|
[[bin]]
|
|
name = "debug_pages"
|
|
path = "src/bin/debug_pages.rs"
|
|
|
|
[[bin]]
|
|
name = "debug_fonts"
|
|
path = "src/bin/debug_fonts.rs"
|
|
|
|
[[bin]]
|
|
name = "dump_ops"
|
|
path = "src/bin/dump_ops.rs"
|
|
|
|
[[bin]]
|
|
name = "debug_spaces"
|
|
path = "src/bin/debug_spaces.rs"
|